{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 18584, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.3809728798966854e-05, "grad_norm": 5.64335823059082, "learning_rate": 5e-05, "loss": 5.6356, "step": 1 }, { "epoch": 0.00010761945759793371, "grad_norm": 3.742523193359375, "learning_rate": 4.999999964278362e-05, "loss": 5.4829, "step": 2 }, { "epoch": 0.00016142918639690056, "grad_norm": 5.101111888885498, "learning_rate": 4.99999985711345e-05, "loss": 5.3994, "step": 3 }, { "epoch": 0.00021523891519586742, "grad_norm": 4.833135604858398, "learning_rate": 4.999999678505265e-05, "loss": 5.4985, "step": 4 }, { "epoch": 0.00026904864399483427, "grad_norm": 4.255808353424072, "learning_rate": 4.9999994284538146e-05, "loss": 5.5022, "step": 5 }, { "epoch": 0.0003228583727938011, "grad_norm": 3.92927622795105, "learning_rate": 4.999999106959104e-05, "loss": 5.4066, "step": 6 }, { "epoch": 0.000376668101592768, "grad_norm": 4.444430828094482, "learning_rate": 4.999998714021144e-05, "loss": 5.2996, "step": 7 }, { "epoch": 0.00043047783039173483, "grad_norm": 3.918823003768921, "learning_rate": 4.999998249639943e-05, "loss": 5.1419, "step": 8 }, { "epoch": 0.0004842875591907017, "grad_norm": 3.1020617485046387, "learning_rate": 4.999997713815518e-05, "loss": 5.3866, "step": 9 }, { "epoch": 0.0005380972879896685, "grad_norm": 4.5511016845703125, "learning_rate": 4.999997106547882e-05, "loss": 5.3619, "step": 10 }, { "epoch": 0.0005919070167886354, "grad_norm": 3.356327772140503, "learning_rate": 4.9999964278370524e-05, "loss": 5.3835, "step": 11 }, { "epoch": 0.0006457167455876022, "grad_norm": 2.9358866214752197, "learning_rate": 4.9999956776830506e-05, "loss": 5.4981, "step": 12 }, { "epoch": 0.0006995264743865691, "grad_norm": 3.2326600551605225, "learning_rate": 4.999994856085895e-05, "loss": 5.441, "step": 13 }, { "epoch": 0.000753336203185536, "grad_norm": 3.6485350131988525, "learning_rate": 4.999993963045612e-05, "loss": 5.406, "step": 14 }, { "epoch": 0.0008071459319845028, "grad_norm": 2.744725227355957, "learning_rate": 4.9999929985622243e-05, "loss": 5.3755, "step": 15 }, { "epoch": 0.0008609556607834697, "grad_norm": 2.779391288757324, "learning_rate": 4.9999919626357616e-05, "loss": 5.3699, "step": 16 }, { "epoch": 0.0009147653895824365, "grad_norm": 4.640102386474609, "learning_rate": 4.999990855266252e-05, "loss": 5.3089, "step": 17 }, { "epoch": 0.0009685751183814034, "grad_norm": 3.3020265102386475, "learning_rate": 4.999989676453729e-05, "loss": 5.3747, "step": 18 }, { "epoch": 0.0010223848471803702, "grad_norm": 3.4012017250061035, "learning_rate": 4.999988426198225e-05, "loss": 5.4763, "step": 19 }, { "epoch": 0.001076194575979337, "grad_norm": 3.739928960800171, "learning_rate": 4.999987104499776e-05, "loss": 5.2708, "step": 20 }, { "epoch": 0.001130004304778304, "grad_norm": 5.882872104644775, "learning_rate": 4.999985711358419e-05, "loss": 5.1768, "step": 21 }, { "epoch": 0.0011838140335772708, "grad_norm": 3.5965123176574707, "learning_rate": 4.999984246774195e-05, "loss": 5.0267, "step": 22 }, { "epoch": 0.0012376237623762376, "grad_norm": 3.646698236465454, "learning_rate": 4.999982710747146e-05, "loss": 5.0213, "step": 23 }, { "epoch": 0.0012914334911752045, "grad_norm": 2.8432631492614746, "learning_rate": 4.999981103277315e-05, "loss": 5.2408, "step": 24 }, { "epoch": 0.0013452432199741713, "grad_norm": 2.683228015899658, "learning_rate": 4.999979424364748e-05, "loss": 5.2457, "step": 25 }, { "epoch": 0.0013990529487731382, "grad_norm": 4.031646251678467, "learning_rate": 4.9999776740094925e-05, "loss": 5.2867, "step": 26 }, { "epoch": 0.001452862677572105, "grad_norm": 3.1683199405670166, "learning_rate": 4.9999758522116e-05, "loss": 5.3496, "step": 27 }, { "epoch": 0.001506672406371072, "grad_norm": 3.7495322227478027, "learning_rate": 4.999973958971122e-05, "loss": 5.3479, "step": 28 }, { "epoch": 0.0015604821351700388, "grad_norm": 4.098349094390869, "learning_rate": 4.9999719942881116e-05, "loss": 5.0332, "step": 29 }, { "epoch": 0.0016142918639690056, "grad_norm": 5.090005874633789, "learning_rate": 4.999969958162627e-05, "loss": 5.0546, "step": 30 }, { "epoch": 0.0016681015927679725, "grad_norm": 3.703042984008789, "learning_rate": 4.999967850594725e-05, "loss": 5.1334, "step": 31 }, { "epoch": 0.0017219113215669393, "grad_norm": 3.815033435821533, "learning_rate": 4.999965671584464e-05, "loss": 5.3152, "step": 32 }, { "epoch": 0.0017757210503659062, "grad_norm": 5.634090423583984, "learning_rate": 4.99996342113191e-05, "loss": 5.2855, "step": 33 }, { "epoch": 0.001829530779164873, "grad_norm": 2.209415912628174, "learning_rate": 4.999961099237125e-05, "loss": 5.4035, "step": 34 }, { "epoch": 0.0018833405079638399, "grad_norm": 5.039535999298096, "learning_rate": 4.999958705900176e-05, "loss": 5.133, "step": 35 }, { "epoch": 0.0019371502367628067, "grad_norm": 2.359755277633667, "learning_rate": 4.999956241121131e-05, "loss": 5.1053, "step": 36 }, { "epoch": 0.0019909599655617734, "grad_norm": 2.564701795578003, "learning_rate": 4.999953704900061e-05, "loss": 5.114, "step": 37 }, { "epoch": 0.0020447696943607404, "grad_norm": 2.7811591625213623, "learning_rate": 4.9999510972370386e-05, "loss": 5.2074, "step": 38 }, { "epoch": 0.002098579423159707, "grad_norm": 3.807939291000366, "learning_rate": 4.999948418132138e-05, "loss": 5.0587, "step": 39 }, { "epoch": 0.002152389151958674, "grad_norm": 5.158015251159668, "learning_rate": 4.9999456675854345e-05, "loss": 5.1615, "step": 40 }, { "epoch": 0.002206198880757641, "grad_norm": 3.9624712467193604, "learning_rate": 4.9999428455970085e-05, "loss": 5.3947, "step": 41 }, { "epoch": 0.002260008609556608, "grad_norm": 3.4167613983154297, "learning_rate": 4.9999399521669396e-05, "loss": 5.1499, "step": 42 }, { "epoch": 0.0023138183383555745, "grad_norm": 3.1730260848999023, "learning_rate": 4.9999369872953114e-05, "loss": 5.1906, "step": 43 }, { "epoch": 0.0023676280671545416, "grad_norm": 3.7193872928619385, "learning_rate": 4.9999339509822085e-05, "loss": 5.1897, "step": 44 }, { "epoch": 0.002421437795953508, "grad_norm": 2.936814308166504, "learning_rate": 4.999930843227717e-05, "loss": 4.9317, "step": 45 }, { "epoch": 0.0024752475247524753, "grad_norm": 2.5229079723358154, "learning_rate": 4.999927664031926e-05, "loss": 4.9837, "step": 46 }, { "epoch": 0.002529057253551442, "grad_norm": 2.830495834350586, "learning_rate": 4.999924413394926e-05, "loss": 5.1023, "step": 47 }, { "epoch": 0.002582866982350409, "grad_norm": 3.130537748336792, "learning_rate": 4.9999210913168116e-05, "loss": 5.1131, "step": 48 }, { "epoch": 0.0026366767111493756, "grad_norm": 3.353931188583374, "learning_rate": 4.9999176977976755e-05, "loss": 5.1256, "step": 49 }, { "epoch": 0.0026904864399483427, "grad_norm": 4.206411361694336, "learning_rate": 4.9999142328376156e-05, "loss": 5.1082, "step": 50 }, { "epoch": 0.0027442961687473093, "grad_norm": 3.502548933029175, "learning_rate": 4.99991069643673e-05, "loss": 5.1327, "step": 51 }, { "epoch": 0.0027981058975462764, "grad_norm": 3.304880142211914, "learning_rate": 4.999907088595122e-05, "loss": 5.2495, "step": 52 }, { "epoch": 0.002851915626345243, "grad_norm": 2.4259400367736816, "learning_rate": 4.999903409312893e-05, "loss": 5.0008, "step": 53 }, { "epoch": 0.00290572535514421, "grad_norm": 4.48856782913208, "learning_rate": 4.999899658590148e-05, "loss": 5.0992, "step": 54 }, { "epoch": 0.0029595350839431767, "grad_norm": 5.906484603881836, "learning_rate": 4.999895836426995e-05, "loss": 4.9581, "step": 55 }, { "epoch": 0.003013344812742144, "grad_norm": 1.9166233539581299, "learning_rate": 4.9998919428235435e-05, "loss": 5.2651, "step": 56 }, { "epoch": 0.0030671545415411105, "grad_norm": 2.5478789806365967, "learning_rate": 4.999887977779903e-05, "loss": 5.1442, "step": 57 }, { "epoch": 0.0031209642703400775, "grad_norm": 4.1772236824035645, "learning_rate": 4.9998839412961894e-05, "loss": 5.1997, "step": 58 }, { "epoch": 0.003174773999139044, "grad_norm": 3.3969218730926514, "learning_rate": 4.999879833372516e-05, "loss": 5.1539, "step": 59 }, { "epoch": 0.0032285837279380112, "grad_norm": 3.8647871017456055, "learning_rate": 4.9998756540090006e-05, "loss": 5.036, "step": 60 }, { "epoch": 0.003282393456736978, "grad_norm": 3.6207833290100098, "learning_rate": 4.9998714032057633e-05, "loss": 5.1601, "step": 61 }, { "epoch": 0.003336203185535945, "grad_norm": 4.729786396026611, "learning_rate": 4.9998670809629244e-05, "loss": 4.889, "step": 62 }, { "epoch": 0.0033900129143349116, "grad_norm": 5.234291076660156, "learning_rate": 4.999862687280609e-05, "loss": 4.999, "step": 63 }, { "epoch": 0.0034438226431338786, "grad_norm": 2.5851409435272217, "learning_rate": 4.999858222158942e-05, "loss": 5.0874, "step": 64 }, { "epoch": 0.0034976323719328453, "grad_norm": 2.13712739944458, "learning_rate": 4.9998536855980506e-05, "loss": 5.0109, "step": 65 }, { "epoch": 0.0035514421007318124, "grad_norm": 3.2233192920684814, "learning_rate": 4.9998490775980644e-05, "loss": 5.1883, "step": 66 }, { "epoch": 0.003605251829530779, "grad_norm": 2.212803602218628, "learning_rate": 4.999844398159115e-05, "loss": 5.222, "step": 67 }, { "epoch": 0.003659061558329746, "grad_norm": 3.116034746170044, "learning_rate": 4.999839647281337e-05, "loss": 4.8964, "step": 68 }, { "epoch": 0.0037128712871287127, "grad_norm": 1.7029228210449219, "learning_rate": 4.999834824964866e-05, "loss": 5.177, "step": 69 }, { "epoch": 0.0037666810159276798, "grad_norm": 3.0051534175872803, "learning_rate": 4.9998299312098386e-05, "loss": 5.1217, "step": 70 }, { "epoch": 0.0038204907447266464, "grad_norm": 2.9930927753448486, "learning_rate": 4.9998249660163966e-05, "loss": 5.1623, "step": 71 }, { "epoch": 0.0038743004735256135, "grad_norm": 2.214249849319458, "learning_rate": 4.99981992938468e-05, "loss": 5.1454, "step": 72 }, { "epoch": 0.00392811020232458, "grad_norm": 2.539630651473999, "learning_rate": 4.999814821314833e-05, "loss": 5.2282, "step": 73 }, { "epoch": 0.003981919931123547, "grad_norm": 2.8968701362609863, "learning_rate": 4.999809641807003e-05, "loss": 4.9187, "step": 74 }, { "epoch": 0.004035729659922514, "grad_norm": 3.5447020530700684, "learning_rate": 4.9998043908613377e-05, "loss": 5.095, "step": 75 }, { "epoch": 0.004089539388721481, "grad_norm": 2.7898802757263184, "learning_rate": 4.999799068477986e-05, "loss": 4.9068, "step": 76 }, { "epoch": 0.0041433491175204475, "grad_norm": 3.859102487564087, "learning_rate": 4.999793674657101e-05, "loss": 4.9181, "step": 77 }, { "epoch": 0.004197158846319414, "grad_norm": 3.123687267303467, "learning_rate": 4.999788209398835e-05, "loss": 4.9658, "step": 78 }, { "epoch": 0.004250968575118382, "grad_norm": 2.153679609298706, "learning_rate": 4.999782672703347e-05, "loss": 5.1669, "step": 79 }, { "epoch": 0.004304778303917348, "grad_norm": 2.4217066764831543, "learning_rate": 4.999777064570793e-05, "loss": 5.1386, "step": 80 }, { "epoch": 0.004358588032716315, "grad_norm": 3.0634875297546387, "learning_rate": 4.999771385001335e-05, "loss": 4.7411, "step": 81 }, { "epoch": 0.004412397761515282, "grad_norm": 3.7208333015441895, "learning_rate": 4.999765633995134e-05, "loss": 4.9876, "step": 82 }, { "epoch": 0.004466207490314249, "grad_norm": 2.6770219802856445, "learning_rate": 4.999759811552354e-05, "loss": 5.3223, "step": 83 }, { "epoch": 0.004520017219113216, "grad_norm": 2.423748254776001, "learning_rate": 4.999753917673163e-05, "loss": 5.1341, "step": 84 }, { "epoch": 0.004573826947912182, "grad_norm": 2.470607280731201, "learning_rate": 4.999747952357728e-05, "loss": 5.2703, "step": 85 }, { "epoch": 0.004627636676711149, "grad_norm": 1.9186522960662842, "learning_rate": 4.999741915606221e-05, "loss": 4.9323, "step": 86 }, { "epoch": 0.0046814464055101165, "grad_norm": 2.584165096282959, "learning_rate": 4.999735807418813e-05, "loss": 5.0617, "step": 87 }, { "epoch": 0.004735256134309083, "grad_norm": 2.1151788234710693, "learning_rate": 4.999729627795679e-05, "loss": 5.1733, "step": 88 }, { "epoch": 0.00478906586310805, "grad_norm": 2.1565001010894775, "learning_rate": 4.999723376736995e-05, "loss": 5.1247, "step": 89 }, { "epoch": 0.004842875591907016, "grad_norm": 2.8871710300445557, "learning_rate": 4.9997170542429424e-05, "loss": 5.0909, "step": 90 }, { "epoch": 0.004896685320705984, "grad_norm": 3.5935819149017334, "learning_rate": 4.9997106603136985e-05, "loss": 4.9283, "step": 91 }, { "epoch": 0.0049504950495049506, "grad_norm": 2.651815891265869, "learning_rate": 4.999704194949447e-05, "loss": 5.1491, "step": 92 }, { "epoch": 0.005004304778303917, "grad_norm": 3.3463408946990967, "learning_rate": 4.999697658150374e-05, "loss": 5.0421, "step": 93 }, { "epoch": 0.005058114507102884, "grad_norm": 3.159661293029785, "learning_rate": 4.999691049916665e-05, "loss": 5.2956, "step": 94 }, { "epoch": 0.005111924235901851, "grad_norm": 2.7523341178894043, "learning_rate": 4.999684370248509e-05, "loss": 4.6378, "step": 95 }, { "epoch": 0.005165733964700818, "grad_norm": 2.724668502807617, "learning_rate": 4.999677619146097e-05, "loss": 5.0932, "step": 96 }, { "epoch": 0.005219543693499785, "grad_norm": 3.8348076343536377, "learning_rate": 4.999670796609622e-05, "loss": 4.9208, "step": 97 }, { "epoch": 0.005273353422298751, "grad_norm": 2.1012277603149414, "learning_rate": 4.999663902639279e-05, "loss": 5.0952, "step": 98 }, { "epoch": 0.005327163151097719, "grad_norm": 2.5343191623687744, "learning_rate": 4.999656937235265e-05, "loss": 4.9152, "step": 99 }, { "epoch": 0.005380972879896685, "grad_norm": 2.1880552768707275, "learning_rate": 4.9996499003977794e-05, "loss": 5.1008, "step": 100 }, { "epoch": 0.005434782608695652, "grad_norm": 2.1349096298217773, "learning_rate": 4.999642792127022e-05, "loss": 5.231, "step": 101 }, { "epoch": 0.005488592337494619, "grad_norm": 2.3971354961395264, "learning_rate": 4.999635612423198e-05, "loss": 5.0721, "step": 102 }, { "epoch": 0.005542402066293586, "grad_norm": 3.2297685146331787, "learning_rate": 4.99962836128651e-05, "loss": 4.9543, "step": 103 }, { "epoch": 0.005596211795092553, "grad_norm": 2.6240601539611816, "learning_rate": 4.999621038717168e-05, "loss": 4.9893, "step": 104 }, { "epoch": 0.0056500215238915194, "grad_norm": 1.8825185298919678, "learning_rate": 4.9996136447153794e-05, "loss": 5.1854, "step": 105 }, { "epoch": 0.005703831252690486, "grad_norm": 3.547574996948242, "learning_rate": 4.999606179281356e-05, "loss": 5.073, "step": 106 }, { "epoch": 0.005757640981489454, "grad_norm": 3.2630674839019775, "learning_rate": 4.999598642415311e-05, "loss": 4.8941, "step": 107 }, { "epoch": 0.00581145071028842, "grad_norm": 2.1516518592834473, "learning_rate": 4.99959103411746e-05, "loss": 4.9278, "step": 108 }, { "epoch": 0.005865260439087387, "grad_norm": 2.164091110229492, "learning_rate": 4.999583354388021e-05, "loss": 5.0543, "step": 109 }, { "epoch": 0.0059190701678863535, "grad_norm": 1.6949377059936523, "learning_rate": 4.9995756032272124e-05, "loss": 5.0351, "step": 110 }, { "epoch": 0.005972879896685321, "grad_norm": 3.28015398979187, "learning_rate": 4.999567780635256e-05, "loss": 4.8062, "step": 111 }, { "epoch": 0.006026689625484288, "grad_norm": 2.3244471549987793, "learning_rate": 4.999559886612375e-05, "loss": 4.9615, "step": 112 }, { "epoch": 0.006080499354283254, "grad_norm": 1.8038171529769897, "learning_rate": 4.999551921158796e-05, "loss": 5.1649, "step": 113 }, { "epoch": 0.006134309083082221, "grad_norm": 2.5504255294799805, "learning_rate": 4.999543884274746e-05, "loss": 4.7859, "step": 114 }, { "epoch": 0.006188118811881188, "grad_norm": 3.065108299255371, "learning_rate": 4.9995357759604546e-05, "loss": 5.0486, "step": 115 }, { "epoch": 0.006241928540680155, "grad_norm": 2.307523012161255, "learning_rate": 4.9995275962161534e-05, "loss": 5.087, "step": 116 }, { "epoch": 0.006295738269479122, "grad_norm": 3.240642547607422, "learning_rate": 4.9995193450420774e-05, "loss": 5.1124, "step": 117 }, { "epoch": 0.006349547998278088, "grad_norm": 2.433084726333618, "learning_rate": 4.999511022438461e-05, "loss": 5.1899, "step": 118 }, { "epoch": 0.006403357727077056, "grad_norm": 3.976531744003296, "learning_rate": 4.999502628405542e-05, "loss": 4.7455, "step": 119 }, { "epoch": 0.0064571674558760225, "grad_norm": 2.4177582263946533, "learning_rate": 4.9994941629435614e-05, "loss": 5.0912, "step": 120 }, { "epoch": 0.006510977184674989, "grad_norm": 2.1738550662994385, "learning_rate": 4.99948562605276e-05, "loss": 4.9488, "step": 121 }, { "epoch": 0.006564786913473956, "grad_norm": 3.1380889415740967, "learning_rate": 4.9994770177333824e-05, "loss": 5.3207, "step": 122 }, { "epoch": 0.006618596642272923, "grad_norm": 4.370920181274414, "learning_rate": 4.999468337985675e-05, "loss": 4.9836, "step": 123 }, { "epoch": 0.00667240637107189, "grad_norm": 2.8729865550994873, "learning_rate": 4.999459586809885e-05, "loss": 4.9211, "step": 124 }, { "epoch": 0.0067262160998708565, "grad_norm": 2.0912070274353027, "learning_rate": 4.9994507642062625e-05, "loss": 5.0662, "step": 125 }, { "epoch": 0.006780025828669823, "grad_norm": 3.379793643951416, "learning_rate": 4.99944187017506e-05, "loss": 5.0702, "step": 126 }, { "epoch": 0.006833835557468791, "grad_norm": 1.9219821691513062, "learning_rate": 4.999432904716531e-05, "loss": 4.9533, "step": 127 }, { "epoch": 0.006887645286267757, "grad_norm": 1.8260682821273804, "learning_rate": 4.999423867830934e-05, "loss": 5.0492, "step": 128 }, { "epoch": 0.006941455015066724, "grad_norm": 2.4954888820648193, "learning_rate": 4.9994147595185236e-05, "loss": 5.1363, "step": 129 }, { "epoch": 0.006995264743865691, "grad_norm": 4.271029472351074, "learning_rate": 4.999405579779563e-05, "loss": 4.88, "step": 130 }, { "epoch": 0.007049074472664658, "grad_norm": 4.518398761749268, "learning_rate": 4.9993963286143134e-05, "loss": 5.2038, "step": 131 }, { "epoch": 0.007102884201463625, "grad_norm": 2.521881580352783, "learning_rate": 4.9993870060230386e-05, "loss": 5.1429, "step": 132 }, { "epoch": 0.007156693930262591, "grad_norm": 2.179044723510742, "learning_rate": 4.9993776120060066e-05, "loss": 5.1178, "step": 133 }, { "epoch": 0.007210503659061558, "grad_norm": 2.187331438064575, "learning_rate": 4.9993681465634845e-05, "loss": 5.0069, "step": 134 }, { "epoch": 0.0072643133878605255, "grad_norm": 2.4100992679595947, "learning_rate": 4.999358609695743e-05, "loss": 4.9399, "step": 135 }, { "epoch": 0.007318123116659492, "grad_norm": 2.406818151473999, "learning_rate": 4.999349001403055e-05, "loss": 5.0229, "step": 136 }, { "epoch": 0.007371932845458459, "grad_norm": 2.543715476989746, "learning_rate": 4.999339321685696e-05, "loss": 5.0299, "step": 137 }, { "epoch": 0.007425742574257425, "grad_norm": 1.4019137620925903, "learning_rate": 4.999329570543941e-05, "loss": 5.1176, "step": 138 }, { "epoch": 0.007479552303056393, "grad_norm": 3.659712553024292, "learning_rate": 4.99931974797807e-05, "loss": 5.0569, "step": 139 }, { "epoch": 0.0075333620318553595, "grad_norm": 2.44423508644104, "learning_rate": 4.999309853988362e-05, "loss": 4.9737, "step": 140 }, { "epoch": 0.007587171760654326, "grad_norm": 2.478360176086426, "learning_rate": 4.999299888575101e-05, "loss": 5.0469, "step": 141 }, { "epoch": 0.007640981489453293, "grad_norm": 1.9175217151641846, "learning_rate": 4.999289851738571e-05, "loss": 5.1373, "step": 142 }, { "epoch": 0.00769479121825226, "grad_norm": 3.3660318851470947, "learning_rate": 4.99927974347906e-05, "loss": 5.2912, "step": 143 }, { "epoch": 0.007748600947051227, "grad_norm": 1.7431479692459106, "learning_rate": 4.999269563796856e-05, "loss": 5.1844, "step": 144 }, { "epoch": 0.007802410675850194, "grad_norm": 2.624450922012329, "learning_rate": 4.999259312692251e-05, "loss": 4.9952, "step": 145 }, { "epoch": 0.00785622040464916, "grad_norm": 2.4797286987304688, "learning_rate": 4.9992489901655354e-05, "loss": 5.0937, "step": 146 }, { "epoch": 0.007910030133448128, "grad_norm": 3.049701690673828, "learning_rate": 4.9992385962170066e-05, "loss": 4.8581, "step": 147 }, { "epoch": 0.007963839862247094, "grad_norm": 2.8863346576690674, "learning_rate": 4.999228130846961e-05, "loss": 5.1226, "step": 148 }, { "epoch": 0.008017649591046061, "grad_norm": 3.9367833137512207, "learning_rate": 4.9992175940556976e-05, "loss": 5.0038, "step": 149 }, { "epoch": 0.008071459319845029, "grad_norm": 3.353114366531372, "learning_rate": 4.999206985843518e-05, "loss": 5.0478, "step": 150 }, { "epoch": 0.008125269048643994, "grad_norm": 1.9904406070709229, "learning_rate": 4.999196306210724e-05, "loss": 5.2403, "step": 151 }, { "epoch": 0.008179078777442962, "grad_norm": 2.588024139404297, "learning_rate": 4.9991855551576215e-05, "loss": 5.0226, "step": 152 }, { "epoch": 0.00823288850624193, "grad_norm": 3.086094379425049, "learning_rate": 4.999174732684518e-05, "loss": 5.001, "step": 153 }, { "epoch": 0.008286698235040895, "grad_norm": 2.6612515449523926, "learning_rate": 4.9991638387917225e-05, "loss": 4.9617, "step": 154 }, { "epoch": 0.008340507963839863, "grad_norm": 2.335188388824463, "learning_rate": 4.9991528734795465e-05, "loss": 5.2256, "step": 155 }, { "epoch": 0.008394317692638828, "grad_norm": 3.122772216796875, "learning_rate": 4.999141836748304e-05, "loss": 4.9939, "step": 156 }, { "epoch": 0.008448127421437796, "grad_norm": 1.6079471111297607, "learning_rate": 4.999130728598309e-05, "loss": 5.0729, "step": 157 }, { "epoch": 0.008501937150236763, "grad_norm": 2.6528284549713135, "learning_rate": 4.9991195490298804e-05, "loss": 4.978, "step": 158 }, { "epoch": 0.008555746879035729, "grad_norm": 2.172025203704834, "learning_rate": 4.999108298043336e-05, "loss": 5.1669, "step": 159 }, { "epoch": 0.008609556607834697, "grad_norm": 2.9179317951202393, "learning_rate": 4.999096975638999e-05, "loss": 4.954, "step": 160 }, { "epoch": 0.008663366336633664, "grad_norm": 1.415764331817627, "learning_rate": 4.9990855818171926e-05, "loss": 5.054, "step": 161 }, { "epoch": 0.00871717606543263, "grad_norm": 4.152856349945068, "learning_rate": 4.999074116578241e-05, "loss": 5.012, "step": 162 }, { "epoch": 0.008770985794231597, "grad_norm": 3.03912615776062, "learning_rate": 4.9990625799224724e-05, "loss": 5.2217, "step": 163 }, { "epoch": 0.008824795523030563, "grad_norm": 1.9614449739456177, "learning_rate": 4.999050971850218e-05, "loss": 5.1161, "step": 164 }, { "epoch": 0.00887860525182953, "grad_norm": 2.224677562713623, "learning_rate": 4.999039292361808e-05, "loss": 4.9183, "step": 165 }, { "epoch": 0.008932414980628498, "grad_norm": 2.106471061706543, "learning_rate": 4.999027541457577e-05, "loss": 4.9816, "step": 166 }, { "epoch": 0.008986224709427464, "grad_norm": 3.1917080879211426, "learning_rate": 4.999015719137861e-05, "loss": 4.6656, "step": 167 }, { "epoch": 0.009040034438226431, "grad_norm": 1.6840863227844238, "learning_rate": 4.999003825402996e-05, "loss": 5.1301, "step": 168 }, { "epoch": 0.009093844167025399, "grad_norm": 1.6608436107635498, "learning_rate": 4.9989918602533245e-05, "loss": 5.1497, "step": 169 }, { "epoch": 0.009147653895824365, "grad_norm": 1.8958888053894043, "learning_rate": 4.998979823689186e-05, "loss": 5.2089, "step": 170 }, { "epoch": 0.009201463624623332, "grad_norm": 4.464609622955322, "learning_rate": 4.998967715710926e-05, "loss": 5.2911, "step": 171 }, { "epoch": 0.009255273353422298, "grad_norm": 1.6974176168441772, "learning_rate": 4.998955536318891e-05, "loss": 5.0188, "step": 172 }, { "epoch": 0.009309083082221266, "grad_norm": 2.3995492458343506, "learning_rate": 4.998943285513427e-05, "loss": 5.0149, "step": 173 }, { "epoch": 0.009362892811020233, "grad_norm": 2.0610785484313965, "learning_rate": 4.998930963294886e-05, "loss": 4.9541, "step": 174 }, { "epoch": 0.009416702539819199, "grad_norm": 1.6460095643997192, "learning_rate": 4.998918569663619e-05, "loss": 5.0803, "step": 175 }, { "epoch": 0.009470512268618166, "grad_norm": 2.042315721511841, "learning_rate": 4.9989061046199805e-05, "loss": 5.1718, "step": 176 }, { "epoch": 0.009524321997417134, "grad_norm": 2.2403626441955566, "learning_rate": 4.998893568164327e-05, "loss": 5.0323, "step": 177 }, { "epoch": 0.0095781317262161, "grad_norm": 1.9473832845687866, "learning_rate": 4.998880960297016e-05, "loss": 4.9582, "step": 178 }, { "epoch": 0.009631941455015067, "grad_norm": 2.7693679332733154, "learning_rate": 4.998868281018409e-05, "loss": 5.0347, "step": 179 }, { "epoch": 0.009685751183814033, "grad_norm": 2.0784735679626465, "learning_rate": 4.998855530328867e-05, "loss": 4.9558, "step": 180 }, { "epoch": 0.009739560912613, "grad_norm": 3.0320613384246826, "learning_rate": 4.998842708228756e-05, "loss": 4.8909, "step": 181 }, { "epoch": 0.009793370641411968, "grad_norm": 3.2216928005218506, "learning_rate": 4.998829814718441e-05, "loss": 5.1526, "step": 182 }, { "epoch": 0.009847180370210934, "grad_norm": 2.0347301959991455, "learning_rate": 4.998816849798291e-05, "loss": 4.6468, "step": 183 }, { "epoch": 0.009900990099009901, "grad_norm": 3.0000381469726562, "learning_rate": 4.9988038134686764e-05, "loss": 5.0942, "step": 184 }, { "epoch": 0.009954799827808869, "grad_norm": 2.100602149963379, "learning_rate": 4.998790705729971e-05, "loss": 5.046, "step": 185 }, { "epoch": 0.010008609556607834, "grad_norm": 3.523860454559326, "learning_rate": 4.998777526582546e-05, "loss": 5.1715, "step": 186 }, { "epoch": 0.010062419285406802, "grad_norm": 2.002608060836792, "learning_rate": 4.9987642760267816e-05, "loss": 5.066, "step": 187 }, { "epoch": 0.010116229014205768, "grad_norm": 2.620454788208008, "learning_rate": 4.998750954063055e-05, "loss": 4.9035, "step": 188 }, { "epoch": 0.010170038743004735, "grad_norm": 2.1703338623046875, "learning_rate": 4.998737560691747e-05, "loss": 5.1911, "step": 189 }, { "epoch": 0.010223848471803703, "grad_norm": 1.8290431499481201, "learning_rate": 4.9987240959132395e-05, "loss": 5.0095, "step": 190 }, { "epoch": 0.010277658200602668, "grad_norm": 2.2632510662078857, "learning_rate": 4.998710559727919e-05, "loss": 5.2636, "step": 191 }, { "epoch": 0.010331467929401636, "grad_norm": 2.906179428100586, "learning_rate": 4.998696952136172e-05, "loss": 4.9335, "step": 192 }, { "epoch": 0.010385277658200603, "grad_norm": 1.9524898529052734, "learning_rate": 4.9986832731383854e-05, "loss": 4.928, "step": 193 }, { "epoch": 0.01043908738699957, "grad_norm": 2.3735005855560303, "learning_rate": 4.9986695227349525e-05, "loss": 5.1436, "step": 194 }, { "epoch": 0.010492897115798537, "grad_norm": 1.8652291297912598, "learning_rate": 4.998655700926265e-05, "loss": 4.8144, "step": 195 }, { "epoch": 0.010546706844597502, "grad_norm": 1.645181655883789, "learning_rate": 4.998641807712717e-05, "loss": 5.2299, "step": 196 }, { "epoch": 0.01060051657339647, "grad_norm": 2.925264835357666, "learning_rate": 4.9986278430947086e-05, "loss": 5.0331, "step": 197 }, { "epoch": 0.010654326302195437, "grad_norm": 2.190974235534668, "learning_rate": 4.998613807072636e-05, "loss": 4.8547, "step": 198 }, { "epoch": 0.010708136030994403, "grad_norm": 2.4733011722564697, "learning_rate": 4.9985996996469015e-05, "loss": 5.0115, "step": 199 }, { "epoch": 0.01076194575979337, "grad_norm": 2.2047417163848877, "learning_rate": 4.998585520817908e-05, "loss": 5.2641, "step": 200 }, { "epoch": 0.010815755488592338, "grad_norm": 1.7298741340637207, "learning_rate": 4.9985712705860606e-05, "loss": 5.0674, "step": 201 }, { "epoch": 0.010869565217391304, "grad_norm": 1.637937068939209, "learning_rate": 4.998556948951767e-05, "loss": 4.9687, "step": 202 }, { "epoch": 0.010923374946190272, "grad_norm": 2.622509717941284, "learning_rate": 4.998542555915435e-05, "loss": 4.8281, "step": 203 }, { "epoch": 0.010977184674989237, "grad_norm": 1.6426870822906494, "learning_rate": 4.9985280914774776e-05, "loss": 5.1723, "step": 204 }, { "epoch": 0.011030994403788205, "grad_norm": 2.4605391025543213, "learning_rate": 4.9985135556383084e-05, "loss": 5.2001, "step": 205 }, { "epoch": 0.011084804132587172, "grad_norm": 2.2210841178894043, "learning_rate": 4.998498948398341e-05, "loss": 4.8942, "step": 206 }, { "epoch": 0.011138613861386138, "grad_norm": 2.143831253051758, "learning_rate": 4.9984842697579945e-05, "loss": 4.866, "step": 207 }, { "epoch": 0.011192423590185106, "grad_norm": 1.481131672859192, "learning_rate": 4.998469519717688e-05, "loss": 5.0824, "step": 208 }, { "epoch": 0.011246233318984073, "grad_norm": 2.015052318572998, "learning_rate": 4.998454698277842e-05, "loss": 5.0492, "step": 209 }, { "epoch": 0.011300043047783039, "grad_norm": 2.477905035018921, "learning_rate": 4.998439805438881e-05, "loss": 5.0703, "step": 210 }, { "epoch": 0.011353852776582006, "grad_norm": 3.375375747680664, "learning_rate": 4.99842484120123e-05, "loss": 4.9237, "step": 211 }, { "epoch": 0.011407662505380972, "grad_norm": 4.036435127258301, "learning_rate": 4.998409805565318e-05, "loss": 4.8701, "step": 212 }, { "epoch": 0.01146147223417994, "grad_norm": 2.597723960876465, "learning_rate": 4.9983946985315725e-05, "loss": 4.7472, "step": 213 }, { "epoch": 0.011515281962978907, "grad_norm": 1.6080222129821777, "learning_rate": 4.9983795201004266e-05, "loss": 4.9942, "step": 214 }, { "epoch": 0.011569091691777873, "grad_norm": 2.056795120239258, "learning_rate": 4.9983642702723146e-05, "loss": 4.9903, "step": 215 }, { "epoch": 0.01162290142057684, "grad_norm": 1.9411859512329102, "learning_rate": 4.9983489490476715e-05, "loss": 4.899, "step": 216 }, { "epoch": 0.011676711149375808, "grad_norm": 2.283792734146118, "learning_rate": 4.998333556426935e-05, "loss": 4.905, "step": 217 }, { "epoch": 0.011730520878174774, "grad_norm": 1.9229516983032227, "learning_rate": 4.998318092410545e-05, "loss": 5.0056, "step": 218 }, { "epoch": 0.011784330606973741, "grad_norm": 1.9736512899398804, "learning_rate": 4.998302556998944e-05, "loss": 4.9854, "step": 219 }, { "epoch": 0.011838140335772707, "grad_norm": 2.2215769290924072, "learning_rate": 4.998286950192575e-05, "loss": 5.0352, "step": 220 }, { "epoch": 0.011891950064571674, "grad_norm": 1.8905951976776123, "learning_rate": 4.9982712719918846e-05, "loss": 5.1641, "step": 221 }, { "epoch": 0.011945759793370642, "grad_norm": 1.8755733966827393, "learning_rate": 4.998255522397321e-05, "loss": 5.1516, "step": 222 }, { "epoch": 0.011999569522169608, "grad_norm": 1.8738369941711426, "learning_rate": 4.9982397014093344e-05, "loss": 5.058, "step": 223 }, { "epoch": 0.012053379250968575, "grad_norm": 2.612027645111084, "learning_rate": 4.998223809028376e-05, "loss": 4.5219, "step": 224 }, { "epoch": 0.012107188979767543, "grad_norm": 2.900996446609497, "learning_rate": 4.9982078452549006e-05, "loss": 4.9234, "step": 225 }, { "epoch": 0.012160998708566509, "grad_norm": 2.101858377456665, "learning_rate": 4.998191810089365e-05, "loss": 5.1269, "step": 226 }, { "epoch": 0.012214808437365476, "grad_norm": 2.923790693283081, "learning_rate": 4.998175703532227e-05, "loss": 5.1509, "step": 227 }, { "epoch": 0.012268618166164442, "grad_norm": 2.7409005165100098, "learning_rate": 4.998159525583946e-05, "loss": 4.8464, "step": 228 }, { "epoch": 0.01232242789496341, "grad_norm": 3.5548453330993652, "learning_rate": 4.998143276244985e-05, "loss": 5.0633, "step": 229 }, { "epoch": 0.012376237623762377, "grad_norm": 1.7686898708343506, "learning_rate": 4.998126955515808e-05, "loss": 4.9456, "step": 230 }, { "epoch": 0.012430047352561343, "grad_norm": 1.8811856508255005, "learning_rate": 4.9981105633968825e-05, "loss": 5.0435, "step": 231 }, { "epoch": 0.01248385708136031, "grad_norm": 2.892669200897217, "learning_rate": 4.998094099888677e-05, "loss": 5.1259, "step": 232 }, { "epoch": 0.012537666810159278, "grad_norm": 2.3954012393951416, "learning_rate": 4.99807756499166e-05, "loss": 4.9082, "step": 233 }, { "epoch": 0.012591476538958243, "grad_norm": 1.6602094173431396, "learning_rate": 4.998060958706306e-05, "loss": 5.2077, "step": 234 }, { "epoch": 0.012645286267757211, "grad_norm": 2.654202461242676, "learning_rate": 4.998044281033088e-05, "loss": 5.1945, "step": 235 }, { "epoch": 0.012699095996556177, "grad_norm": 2.332181930541992, "learning_rate": 4.9980275319724836e-05, "loss": 5.1863, "step": 236 }, { "epoch": 0.012752905725355144, "grad_norm": 2.0642287731170654, "learning_rate": 4.9980107115249714e-05, "loss": 5.1512, "step": 237 }, { "epoch": 0.012806715454154112, "grad_norm": 1.7050873041152954, "learning_rate": 4.997993819691032e-05, "loss": 5.0986, "step": 238 }, { "epoch": 0.012860525182953077, "grad_norm": 2.161627769470215, "learning_rate": 4.9979768564711483e-05, "loss": 4.8626, "step": 239 }, { "epoch": 0.012914334911752045, "grad_norm": 2.425778388977051, "learning_rate": 4.997959821865804e-05, "loss": 4.7983, "step": 240 }, { "epoch": 0.012968144640551012, "grad_norm": 2.3272159099578857, "learning_rate": 4.997942715875487e-05, "loss": 4.7904, "step": 241 }, { "epoch": 0.013021954369349978, "grad_norm": 2.5738608837127686, "learning_rate": 4.997925538500686e-05, "loss": 5.2423, "step": 242 }, { "epoch": 0.013075764098148946, "grad_norm": 2.8331196308135986, "learning_rate": 4.9979082897418914e-05, "loss": 4.9875, "step": 243 }, { "epoch": 0.013129573826947911, "grad_norm": 1.523768424987793, "learning_rate": 4.9978909695995976e-05, "loss": 4.9039, "step": 244 }, { "epoch": 0.013183383555746879, "grad_norm": 1.6924493312835693, "learning_rate": 4.9978735780742975e-05, "loss": 5.0167, "step": 245 }, { "epoch": 0.013237193284545846, "grad_norm": 1.8595242500305176, "learning_rate": 4.997856115166489e-05, "loss": 4.8506, "step": 246 }, { "epoch": 0.013291003013344812, "grad_norm": 1.9790562391281128, "learning_rate": 4.997838580876672e-05, "loss": 4.6495, "step": 247 }, { "epoch": 0.01334481274214378, "grad_norm": 3.0742177963256836, "learning_rate": 4.9978209752053456e-05, "loss": 4.9876, "step": 248 }, { "epoch": 0.013398622470942747, "grad_norm": 2.615360975265503, "learning_rate": 4.997803298153014e-05, "loss": 5.0247, "step": 249 }, { "epoch": 0.013452432199741713, "grad_norm": 2.570051908493042, "learning_rate": 4.997785549720184e-05, "loss": 4.7936, "step": 250 }, { "epoch": 0.01350624192854068, "grad_norm": 2.693331003189087, "learning_rate": 4.99776772990736e-05, "loss": 5.0499, "step": 251 }, { "epoch": 0.013560051657339646, "grad_norm": 1.7130229473114014, "learning_rate": 4.9977498387150525e-05, "loss": 5.0552, "step": 252 }, { "epoch": 0.013613861386138614, "grad_norm": 2.111001968383789, "learning_rate": 4.997731876143773e-05, "loss": 4.856, "step": 253 }, { "epoch": 0.013667671114937581, "grad_norm": 1.7777823209762573, "learning_rate": 4.997713842194035e-05, "loss": 5.1555, "step": 254 }, { "epoch": 0.013721480843736547, "grad_norm": 2.4698240756988525, "learning_rate": 4.997695736866353e-05, "loss": 4.8039, "step": 255 }, { "epoch": 0.013775290572535515, "grad_norm": 2.6121573448181152, "learning_rate": 4.9976775601612446e-05, "loss": 4.9144, "step": 256 }, { "epoch": 0.013829100301334482, "grad_norm": 2.1548852920532227, "learning_rate": 4.9976593120792305e-05, "loss": 5.2325, "step": 257 }, { "epoch": 0.013882910030133448, "grad_norm": 1.6555628776550293, "learning_rate": 4.99764099262083e-05, "loss": 5.2133, "step": 258 }, { "epoch": 0.013936719758932415, "grad_norm": 1.681726336479187, "learning_rate": 4.997622601786568e-05, "loss": 4.7923, "step": 259 }, { "epoch": 0.013990529487731381, "grad_norm": 1.8998854160308838, "learning_rate": 4.99760413957697e-05, "loss": 5.0068, "step": 260 }, { "epoch": 0.014044339216530349, "grad_norm": 1.919053077697754, "learning_rate": 4.997585605992564e-05, "loss": 5.0617, "step": 261 }, { "epoch": 0.014098148945329316, "grad_norm": 1.533626914024353, "learning_rate": 4.997567001033879e-05, "loss": 4.9985, "step": 262 }, { "epoch": 0.014151958674128282, "grad_norm": 2.191755533218384, "learning_rate": 4.997548324701447e-05, "loss": 4.8664, "step": 263 }, { "epoch": 0.01420576840292725, "grad_norm": 1.6340069770812988, "learning_rate": 4.9975295769958e-05, "loss": 5.0057, "step": 264 }, { "epoch": 0.014259578131726217, "grad_norm": 2.3464927673339844, "learning_rate": 4.9975107579174764e-05, "loss": 5.0701, "step": 265 }, { "epoch": 0.014313387860525183, "grad_norm": 1.6887654066085815, "learning_rate": 4.997491867467012e-05, "loss": 4.8659, "step": 266 }, { "epoch": 0.01436719758932415, "grad_norm": 1.4037449359893799, "learning_rate": 4.997472905644949e-05, "loss": 5.1934, "step": 267 }, { "epoch": 0.014421007318123116, "grad_norm": 1.9283753633499146, "learning_rate": 4.997453872451827e-05, "loss": 4.9765, "step": 268 }, { "epoch": 0.014474817046922083, "grad_norm": 2.713510036468506, "learning_rate": 4.997434767888191e-05, "loss": 4.8924, "step": 269 }, { "epoch": 0.014528626775721051, "grad_norm": 1.7105371952056885, "learning_rate": 4.9974155919545856e-05, "loss": 4.7472, "step": 270 }, { "epoch": 0.014582436504520017, "grad_norm": 2.808337450027466, "learning_rate": 4.9973963446515605e-05, "loss": 4.7307, "step": 271 }, { "epoch": 0.014636246233318984, "grad_norm": 4.289490699768066, "learning_rate": 4.997377025979665e-05, "loss": 4.8731, "step": 272 }, { "epoch": 0.014690055962117952, "grad_norm": 2.312568187713623, "learning_rate": 4.9973576359394514e-05, "loss": 4.9014, "step": 273 }, { "epoch": 0.014743865690916918, "grad_norm": 1.7401853799819946, "learning_rate": 4.997338174531474e-05, "loss": 4.9275, "step": 274 }, { "epoch": 0.014797675419715885, "grad_norm": 1.9649227857589722, "learning_rate": 4.9973186417562875e-05, "loss": 4.9227, "step": 275 }, { "epoch": 0.01485148514851485, "grad_norm": 2.705113649368286, "learning_rate": 4.9972990376144526e-05, "loss": 4.7466, "step": 276 }, { "epoch": 0.014905294877313818, "grad_norm": 1.8841334581375122, "learning_rate": 4.997279362106527e-05, "loss": 5.2496, "step": 277 }, { "epoch": 0.014959104606112786, "grad_norm": 2.4739301204681396, "learning_rate": 4.997259615233075e-05, "loss": 4.7808, "step": 278 }, { "epoch": 0.015012914334911752, "grad_norm": 3.548809766769409, "learning_rate": 4.997239796994659e-05, "loss": 4.7196, "step": 279 }, { "epoch": 0.015066724063710719, "grad_norm": 3.0794332027435303, "learning_rate": 4.997219907391848e-05, "loss": 4.6638, "step": 280 }, { "epoch": 0.015120533792509687, "grad_norm": 3.0693507194519043, "learning_rate": 4.997199946425207e-05, "loss": 5.0063, "step": 281 }, { "epoch": 0.015174343521308652, "grad_norm": 1.5591626167297363, "learning_rate": 4.99717991409531e-05, "loss": 5.0879, "step": 282 }, { "epoch": 0.01522815325010762, "grad_norm": 2.838560104370117, "learning_rate": 4.997159810402726e-05, "loss": 4.7707, "step": 283 }, { "epoch": 0.015281962978906586, "grad_norm": 2.293095588684082, "learning_rate": 4.997139635348032e-05, "loss": 5.1856, "step": 284 }, { "epoch": 0.015335772707705553, "grad_norm": 2.2833797931671143, "learning_rate": 4.997119388931803e-05, "loss": 5.1557, "step": 285 }, { "epoch": 0.01538958243650452, "grad_norm": 1.8231704235076904, "learning_rate": 4.99709907115462e-05, "loss": 5.2346, "step": 286 }, { "epoch": 0.015443392165303486, "grad_norm": 2.6971747875213623, "learning_rate": 4.9970786820170606e-05, "loss": 4.9813, "step": 287 }, { "epoch": 0.015497201894102454, "grad_norm": 2.584199905395508, "learning_rate": 4.997058221519709e-05, "loss": 4.9971, "step": 288 }, { "epoch": 0.015551011622901421, "grad_norm": 4.626810550689697, "learning_rate": 4.9970376896631496e-05, "loss": 4.7824, "step": 289 }, { "epoch": 0.015604821351700387, "grad_norm": 3.120943307876587, "learning_rate": 4.99701708644797e-05, "loss": 5.0601, "step": 290 }, { "epoch": 0.015658631080499353, "grad_norm": 1.5016857385635376, "learning_rate": 4.996996411874758e-05, "loss": 4.9177, "step": 291 }, { "epoch": 0.01571244080929832, "grad_norm": 2.0197200775146484, "learning_rate": 4.9969756659441045e-05, "loss": 5.1367, "step": 292 }, { "epoch": 0.015766250538097288, "grad_norm": 1.8844410181045532, "learning_rate": 4.996954848656602e-05, "loss": 5.1594, "step": 293 }, { "epoch": 0.015820060266896255, "grad_norm": 3.331974983215332, "learning_rate": 4.996933960012847e-05, "loss": 4.8092, "step": 294 }, { "epoch": 0.015873869995695223, "grad_norm": 1.7494280338287354, "learning_rate": 4.9969130000134344e-05, "loss": 4.9027, "step": 295 }, { "epoch": 0.015927679724494187, "grad_norm": 1.8797378540039062, "learning_rate": 4.996891968658965e-05, "loss": 5.0723, "step": 296 }, { "epoch": 0.015981489453293155, "grad_norm": 2.173431396484375, "learning_rate": 4.9968708659500385e-05, "loss": 4.9596, "step": 297 }, { "epoch": 0.016035299182092122, "grad_norm": 2.959029197692871, "learning_rate": 4.9968496918872587e-05, "loss": 4.8798, "step": 298 }, { "epoch": 0.01608910891089109, "grad_norm": 1.5195345878601074, "learning_rate": 4.99682844647123e-05, "loss": 5.1864, "step": 299 }, { "epoch": 0.016142918639690057, "grad_norm": 1.5560485124588013, "learning_rate": 4.996807129702561e-05, "loss": 5.2739, "step": 300 }, { "epoch": 0.016196728368489025, "grad_norm": 2.591665029525757, "learning_rate": 4.9967857415818586e-05, "loss": 5.0332, "step": 301 }, { "epoch": 0.01625053809728799, "grad_norm": 1.804572582244873, "learning_rate": 4.996764282109736e-05, "loss": 4.7582, "step": 302 }, { "epoch": 0.016304347826086956, "grad_norm": 1.8226374387741089, "learning_rate": 4.9967427512868054e-05, "loss": 4.7263, "step": 303 }, { "epoch": 0.016358157554885924, "grad_norm": 2.589613914489746, "learning_rate": 4.996721149113682e-05, "loss": 4.9478, "step": 304 }, { "epoch": 0.01641196728368489, "grad_norm": 2.2618486881256104, "learning_rate": 4.996699475590985e-05, "loss": 5.1881, "step": 305 }, { "epoch": 0.01646577701248386, "grad_norm": 1.4648332595825195, "learning_rate": 4.996677730719331e-05, "loss": 5.1246, "step": 306 }, { "epoch": 0.016519586741282823, "grad_norm": 1.6377110481262207, "learning_rate": 4.996655914499343e-05, "loss": 5.2136, "step": 307 }, { "epoch": 0.01657339647008179, "grad_norm": 1.6663756370544434, "learning_rate": 4.996634026931645e-05, "loss": 5.2112, "step": 308 }, { "epoch": 0.016627206198880758, "grad_norm": 1.7969907522201538, "learning_rate": 4.9966120680168606e-05, "loss": 4.8971, "step": 309 }, { "epoch": 0.016681015927679725, "grad_norm": 1.9095394611358643, "learning_rate": 4.9965900377556183e-05, "loss": 4.9148, "step": 310 }, { "epoch": 0.016734825656478693, "grad_norm": 1.9057974815368652, "learning_rate": 4.9965679361485484e-05, "loss": 4.7813, "step": 311 }, { "epoch": 0.016788635385277657, "grad_norm": 1.9602680206298828, "learning_rate": 4.996545763196282e-05, "loss": 4.9406, "step": 312 }, { "epoch": 0.016842445114076624, "grad_norm": 1.9150270223617554, "learning_rate": 4.996523518899452e-05, "loss": 5.0027, "step": 313 }, { "epoch": 0.01689625484287559, "grad_norm": 1.9695158004760742, "learning_rate": 4.9965012032586956e-05, "loss": 4.9484, "step": 314 }, { "epoch": 0.01695006457167456, "grad_norm": 1.675797939300537, "learning_rate": 4.996478816274649e-05, "loss": 5.1437, "step": 315 }, { "epoch": 0.017003874300473527, "grad_norm": 1.5444350242614746, "learning_rate": 4.9964563579479523e-05, "loss": 4.9769, "step": 316 }, { "epoch": 0.017057684029272494, "grad_norm": 1.8270559310913086, "learning_rate": 4.9964338282792476e-05, "loss": 4.938, "step": 317 }, { "epoch": 0.017111493758071458, "grad_norm": 1.372694492340088, "learning_rate": 4.996411227269179e-05, "loss": 5.1185, "step": 318 }, { "epoch": 0.017165303486870426, "grad_norm": 1.3551692962646484, "learning_rate": 4.996388554918392e-05, "loss": 4.9981, "step": 319 }, { "epoch": 0.017219113215669393, "grad_norm": 2.7649435997009277, "learning_rate": 4.9963658112275345e-05, "loss": 4.6842, "step": 320 }, { "epoch": 0.01727292294446836, "grad_norm": 2.525501251220703, "learning_rate": 4.9963429961972577e-05, "loss": 5.0508, "step": 321 }, { "epoch": 0.017326732673267328, "grad_norm": 1.525337815284729, "learning_rate": 4.9963201098282106e-05, "loss": 5.1226, "step": 322 }, { "epoch": 0.017380542402066292, "grad_norm": 1.5830132961273193, "learning_rate": 4.99629715212105e-05, "loss": 5.0154, "step": 323 }, { "epoch": 0.01743435213086526, "grad_norm": 1.5534614324569702, "learning_rate": 4.996274123076431e-05, "loss": 5.1265, "step": 324 }, { "epoch": 0.017488161859664227, "grad_norm": 2.3831474781036377, "learning_rate": 4.996251022695012e-05, "loss": 5.0377, "step": 325 }, { "epoch": 0.017541971588463195, "grad_norm": 1.7639321088790894, "learning_rate": 4.996227850977452e-05, "loss": 4.9864, "step": 326 }, { "epoch": 0.017595781317262162, "grad_norm": 2.020876169204712, "learning_rate": 4.996204607924415e-05, "loss": 4.8619, "step": 327 }, { "epoch": 0.017649591046061126, "grad_norm": 2.0956554412841797, "learning_rate": 4.9961812935365635e-05, "loss": 5.1359, "step": 328 }, { "epoch": 0.017703400774860094, "grad_norm": 1.3236801624298096, "learning_rate": 4.996157907814566e-05, "loss": 4.8065, "step": 329 }, { "epoch": 0.01775721050365906, "grad_norm": 1.6282894611358643, "learning_rate": 4.9961344507590876e-05, "loss": 4.8713, "step": 330 }, { "epoch": 0.01781102023245803, "grad_norm": 1.886735200881958, "learning_rate": 4.996110922370801e-05, "loss": 4.8552, "step": 331 }, { "epoch": 0.017864829961256996, "grad_norm": 2.873311996459961, "learning_rate": 4.996087322650379e-05, "loss": 4.7869, "step": 332 }, { "epoch": 0.01791863969005596, "grad_norm": 2.2285897731781006, "learning_rate": 4.996063651598494e-05, "loss": 4.9862, "step": 333 }, { "epoch": 0.017972449418854928, "grad_norm": 1.7606706619262695, "learning_rate": 4.9960399092158236e-05, "loss": 5.225, "step": 334 }, { "epoch": 0.018026259147653895, "grad_norm": 1.5912343263626099, "learning_rate": 4.996016095503047e-05, "loss": 4.9327, "step": 335 }, { "epoch": 0.018080068876452863, "grad_norm": 1.694615125656128, "learning_rate": 4.995992210460842e-05, "loss": 5.0155, "step": 336 }, { "epoch": 0.01813387860525183, "grad_norm": 1.5307213068008423, "learning_rate": 4.995968254089895e-05, "loss": 5.3567, "step": 337 }, { "epoch": 0.018187688334050798, "grad_norm": 2.6340556144714355, "learning_rate": 4.995944226390887e-05, "loss": 4.6873, "step": 338 }, { "epoch": 0.018241498062849762, "grad_norm": 1.4215731620788574, "learning_rate": 4.9959201273645077e-05, "loss": 5.0154, "step": 339 }, { "epoch": 0.01829530779164873, "grad_norm": 1.6457834243774414, "learning_rate": 4.995895957011444e-05, "loss": 4.8723, "step": 340 }, { "epoch": 0.018349117520447697, "grad_norm": 1.8471928834915161, "learning_rate": 4.9958717153323866e-05, "loss": 4.8838, "step": 341 }, { "epoch": 0.018402927249246664, "grad_norm": 2.199475049972534, "learning_rate": 4.9958474023280296e-05, "loss": 5.127, "step": 342 }, { "epoch": 0.018456736978045632, "grad_norm": 2.557954788208008, "learning_rate": 4.995823017999066e-05, "loss": 5.0133, "step": 343 }, { "epoch": 0.018510546706844596, "grad_norm": 1.6861189603805542, "learning_rate": 4.995798562346193e-05, "loss": 4.6132, "step": 344 }, { "epoch": 0.018564356435643563, "grad_norm": 1.238260269165039, "learning_rate": 4.995774035370112e-05, "loss": 5.1233, "step": 345 }, { "epoch": 0.01861816616444253, "grad_norm": 1.594909429550171, "learning_rate": 4.9957494370715205e-05, "loss": 5.0794, "step": 346 }, { "epoch": 0.0186719758932415, "grad_norm": 1.8480699062347412, "learning_rate": 4.995724767451123e-05, "loss": 5.0895, "step": 347 }, { "epoch": 0.018725785622040466, "grad_norm": 1.4733881950378418, "learning_rate": 4.995700026509624e-05, "loss": 4.9435, "step": 348 }, { "epoch": 0.01877959535083943, "grad_norm": 1.530259370803833, "learning_rate": 4.9956752142477316e-05, "loss": 5.0122, "step": 349 }, { "epoch": 0.018833405079638398, "grad_norm": 1.4226311445236206, "learning_rate": 4.995650330666154e-05, "loss": 5.1195, "step": 350 }, { "epoch": 0.018887214808437365, "grad_norm": 2.613901376724243, "learning_rate": 4.9956253757656016e-05, "loss": 5.0233, "step": 351 }, { "epoch": 0.018941024537236333, "grad_norm": 2.8775458335876465, "learning_rate": 4.995600349546789e-05, "loss": 4.7982, "step": 352 }, { "epoch": 0.0189948342660353, "grad_norm": 2.3565514087677, "learning_rate": 4.9955752520104314e-05, "loss": 5.02, "step": 353 }, { "epoch": 0.019048643994834268, "grad_norm": 1.6975376605987549, "learning_rate": 4.995550083157245e-05, "loss": 5.0901, "step": 354 }, { "epoch": 0.01910245372363323, "grad_norm": 1.3873175382614136, "learning_rate": 4.995524842987949e-05, "loss": 4.8943, "step": 355 }, { "epoch": 0.0191562634524322, "grad_norm": 2.023721694946289, "learning_rate": 4.995499531503266e-05, "loss": 5.1223, "step": 356 }, { "epoch": 0.019210073181231167, "grad_norm": 2.211900472640991, "learning_rate": 4.995474148703918e-05, "loss": 5.0761, "step": 357 }, { "epoch": 0.019263882910030134, "grad_norm": 2.1197469234466553, "learning_rate": 4.995448694590631e-05, "loss": 4.6749, "step": 358 }, { "epoch": 0.0193176926388291, "grad_norm": 2.4358813762664795, "learning_rate": 4.995423169164132e-05, "loss": 5.0276, "step": 359 }, { "epoch": 0.019371502367628066, "grad_norm": 2.1178507804870605, "learning_rate": 4.995397572425151e-05, "loss": 4.7584, "step": 360 }, { "epoch": 0.019425312096427033, "grad_norm": 2.024989366531372, "learning_rate": 4.9953719043744184e-05, "loss": 4.9574, "step": 361 }, { "epoch": 0.019479121825226, "grad_norm": 3.819998025894165, "learning_rate": 4.99534616501267e-05, "loss": 4.7491, "step": 362 }, { "epoch": 0.019532931554024968, "grad_norm": 3.015794038772583, "learning_rate": 4.995320354340639e-05, "loss": 5.0478, "step": 363 }, { "epoch": 0.019586741282823936, "grad_norm": 2.0589122772216797, "learning_rate": 4.9952944723590636e-05, "loss": 4.9638, "step": 364 }, { "epoch": 0.0196405510116229, "grad_norm": 1.3198777437210083, "learning_rate": 4.995268519068684e-05, "loss": 5.3295, "step": 365 }, { "epoch": 0.019694360740421867, "grad_norm": 2.469971179962158, "learning_rate": 4.9952424944702424e-05, "loss": 4.9539, "step": 366 }, { "epoch": 0.019748170469220835, "grad_norm": 1.9928866624832153, "learning_rate": 4.9952163985644805e-05, "loss": 5.1924, "step": 367 }, { "epoch": 0.019801980198019802, "grad_norm": 1.9667541980743408, "learning_rate": 4.995190231352146e-05, "loss": 4.7213, "step": 368 }, { "epoch": 0.01985578992681877, "grad_norm": 2.650057315826416, "learning_rate": 4.995163992833986e-05, "loss": 4.6559, "step": 369 }, { "epoch": 0.019909599655617737, "grad_norm": 1.4587669372558594, "learning_rate": 4.99513768301075e-05, "loss": 4.7067, "step": 370 }, { "epoch": 0.0199634093844167, "grad_norm": 2.0006330013275146, "learning_rate": 4.9951113018831906e-05, "loss": 4.8039, "step": 371 }, { "epoch": 0.02001721911321567, "grad_norm": 2.7181310653686523, "learning_rate": 4.995084849452061e-05, "loss": 5.0541, "step": 372 }, { "epoch": 0.020071028842014636, "grad_norm": 1.851328730583191, "learning_rate": 4.9950583257181174e-05, "loss": 5.1438, "step": 373 }, { "epoch": 0.020124838570813604, "grad_norm": 2.1449646949768066, "learning_rate": 4.995031730682117e-05, "loss": 5.271, "step": 374 }, { "epoch": 0.02017864829961257, "grad_norm": 1.617647647857666, "learning_rate": 4.9950050643448224e-05, "loss": 5.2362, "step": 375 }, { "epoch": 0.020232458028411535, "grad_norm": 2.1394407749176025, "learning_rate": 4.9949783267069916e-05, "loss": 4.9699, "step": 376 }, { "epoch": 0.020286267757210503, "grad_norm": 2.1332454681396484, "learning_rate": 4.994951517769393e-05, "loss": 5.0494, "step": 377 }, { "epoch": 0.02034007748600947, "grad_norm": 1.9327445030212402, "learning_rate": 4.9949246375327894e-05, "loss": 4.7478, "step": 378 }, { "epoch": 0.020393887214808438, "grad_norm": 3.08687162399292, "learning_rate": 4.99489768599795e-05, "loss": 4.6269, "step": 379 }, { "epoch": 0.020447696943607405, "grad_norm": 2.0090982913970947, "learning_rate": 4.994870663165646e-05, "loss": 4.9801, "step": 380 }, { "epoch": 0.02050150667240637, "grad_norm": 1.942278504371643, "learning_rate": 4.9948435690366486e-05, "loss": 4.9719, "step": 381 }, { "epoch": 0.020555316401205337, "grad_norm": 2.0043716430664062, "learning_rate": 4.994816403611732e-05, "loss": 4.6357, "step": 382 }, { "epoch": 0.020609126130004304, "grad_norm": 2.6363072395324707, "learning_rate": 4.994789166891674e-05, "loss": 4.7999, "step": 383 }, { "epoch": 0.020662935858803272, "grad_norm": 1.8272123336791992, "learning_rate": 4.9947618588772505e-05, "loss": 4.825, "step": 384 }, { "epoch": 0.02071674558760224, "grad_norm": 2.520494222640991, "learning_rate": 4.994734479569243e-05, "loss": 5.0424, "step": 385 }, { "epoch": 0.020770555316401207, "grad_norm": 1.7900012731552124, "learning_rate": 4.994707028968435e-05, "loss": 5.2218, "step": 386 }, { "epoch": 0.02082436504520017, "grad_norm": 2.462122678756714, "learning_rate": 4.9946795070756105e-05, "loss": 5.0781, "step": 387 }, { "epoch": 0.02087817477399914, "grad_norm": 2.0666542053222656, "learning_rate": 4.994651913891555e-05, "loss": 5.1172, "step": 388 }, { "epoch": 0.020931984502798106, "grad_norm": 1.68450129032135, "learning_rate": 4.994624249417057e-05, "loss": 5.0555, "step": 389 }, { "epoch": 0.020985794231597073, "grad_norm": 1.6662739515304565, "learning_rate": 4.9945965136529084e-05, "loss": 4.7609, "step": 390 }, { "epoch": 0.02103960396039604, "grad_norm": 3.5933210849761963, "learning_rate": 4.9945687065999015e-05, "loss": 5.2339, "step": 391 }, { "epoch": 0.021093413689195005, "grad_norm": 4.963655471801758, "learning_rate": 4.9945408282588304e-05, "loss": 4.7984, "step": 392 }, { "epoch": 0.021147223417993972, "grad_norm": 1.574520468711853, "learning_rate": 4.9945128786304914e-05, "loss": 5.1809, "step": 393 }, { "epoch": 0.02120103314679294, "grad_norm": 2.20190691947937, "learning_rate": 4.994484857715684e-05, "loss": 4.8149, "step": 394 }, { "epoch": 0.021254842875591907, "grad_norm": 1.7403955459594727, "learning_rate": 4.9944567655152086e-05, "loss": 4.9904, "step": 395 }, { "epoch": 0.021308652604390875, "grad_norm": 1.175632357597351, "learning_rate": 4.994428602029868e-05, "loss": 5.0251, "step": 396 }, { "epoch": 0.02136246233318984, "grad_norm": 1.4350612163543701, "learning_rate": 4.9944003672604675e-05, "loss": 4.9484, "step": 397 }, { "epoch": 0.021416272061988807, "grad_norm": 1.8563876152038574, "learning_rate": 4.994372061207814e-05, "loss": 4.9603, "step": 398 }, { "epoch": 0.021470081790787774, "grad_norm": 1.3091107606887817, "learning_rate": 4.994343683872715e-05, "loss": 4.9723, "step": 399 }, { "epoch": 0.02152389151958674, "grad_norm": 2.5263803005218506, "learning_rate": 4.994315235255984e-05, "loss": 5.0078, "step": 400 }, { "epoch": 0.02157770124838571, "grad_norm": 2.199232339859009, "learning_rate": 4.9942867153584314e-05, "loss": 4.8249, "step": 401 }, { "epoch": 0.021631510977184677, "grad_norm": 1.6543455123901367, "learning_rate": 4.9942581241808736e-05, "loss": 5.0378, "step": 402 }, { "epoch": 0.02168532070598364, "grad_norm": 1.359391212463379, "learning_rate": 4.994229461724127e-05, "loss": 4.8305, "step": 403 }, { "epoch": 0.021739130434782608, "grad_norm": 1.706023931503296, "learning_rate": 4.994200727989012e-05, "loss": 5.0195, "step": 404 }, { "epoch": 0.021792940163581576, "grad_norm": 1.9632998704910278, "learning_rate": 4.994171922976348e-05, "loss": 5.0525, "step": 405 }, { "epoch": 0.021846749892380543, "grad_norm": 2.5210254192352295, "learning_rate": 4.9941430466869597e-05, "loss": 4.6664, "step": 406 }, { "epoch": 0.02190055962117951, "grad_norm": 2.0374157428741455, "learning_rate": 4.99411409912167e-05, "loss": 4.9633, "step": 407 }, { "epoch": 0.021954369349978475, "grad_norm": 2.1133391857147217, "learning_rate": 4.99408508028131e-05, "loss": 4.8169, "step": 408 }, { "epoch": 0.022008179078777442, "grad_norm": 2.7097115516662598, "learning_rate": 4.994055990166705e-05, "loss": 5.0507, "step": 409 }, { "epoch": 0.02206198880757641, "grad_norm": 1.939815640449524, "learning_rate": 4.994026828778689e-05, "loss": 4.9355, "step": 410 }, { "epoch": 0.022115798536375377, "grad_norm": 2.0119576454162598, "learning_rate": 4.993997596118094e-05, "loss": 5.0694, "step": 411 }, { "epoch": 0.022169608265174345, "grad_norm": 2.007230520248413, "learning_rate": 4.993968292185756e-05, "loss": 4.9909, "step": 412 }, { "epoch": 0.02222341799397331, "grad_norm": 1.7422651052474976, "learning_rate": 4.993938916982511e-05, "loss": 4.818, "step": 413 }, { "epoch": 0.022277227722772276, "grad_norm": 1.6008079051971436, "learning_rate": 4.993909470509201e-05, "loss": 5.0423, "step": 414 }, { "epoch": 0.022331037451571244, "grad_norm": 1.702561616897583, "learning_rate": 4.9938799527666656e-05, "loss": 4.8984, "step": 415 }, { "epoch": 0.02238484718037021, "grad_norm": 1.3098591566085815, "learning_rate": 4.9938503637557496e-05, "loss": 4.9404, "step": 416 }, { "epoch": 0.02243865690916918, "grad_norm": 1.6867859363555908, "learning_rate": 4.9938207034772974e-05, "loss": 5.0637, "step": 417 }, { "epoch": 0.022492466637968146, "grad_norm": 1.6199231147766113, "learning_rate": 4.993790971932157e-05, "loss": 4.7702, "step": 418 }, { "epoch": 0.02254627636676711, "grad_norm": 1.613876461982727, "learning_rate": 4.993761169121178e-05, "loss": 4.8859, "step": 419 }, { "epoch": 0.022600086095566078, "grad_norm": 1.460210919380188, "learning_rate": 4.993731295045212e-05, "loss": 5.2381, "step": 420 }, { "epoch": 0.022653895824365045, "grad_norm": 1.7708066701889038, "learning_rate": 4.993701349705113e-05, "loss": 5.06, "step": 421 }, { "epoch": 0.022707705553164013, "grad_norm": 1.569915771484375, "learning_rate": 4.9936713331017374e-05, "loss": 5.0349, "step": 422 }, { "epoch": 0.02276151528196298, "grad_norm": 1.7284913063049316, "learning_rate": 4.993641245235942e-05, "loss": 5.0913, "step": 423 }, { "epoch": 0.022815325010761944, "grad_norm": 1.2284531593322754, "learning_rate": 4.993611086108587e-05, "loss": 5.2038, "step": 424 }, { "epoch": 0.022869134739560912, "grad_norm": 1.2580235004425049, "learning_rate": 4.9935808557205336e-05, "loss": 5.1539, "step": 425 }, { "epoch": 0.02292294446835988, "grad_norm": 1.7181081771850586, "learning_rate": 4.993550554072647e-05, "loss": 4.7869, "step": 426 }, { "epoch": 0.022976754197158847, "grad_norm": 1.1851123571395874, "learning_rate": 4.993520181165792e-05, "loss": 4.8984, "step": 427 }, { "epoch": 0.023030563925957814, "grad_norm": 1.9792814254760742, "learning_rate": 4.993489737000837e-05, "loss": 5.0898, "step": 428 }, { "epoch": 0.02308437365475678, "grad_norm": 1.9587032794952393, "learning_rate": 4.993459221578652e-05, "loss": 5.3243, "step": 429 }, { "epoch": 0.023138183383555746, "grad_norm": 1.6285510063171387, "learning_rate": 4.993428634900109e-05, "loss": 5.0789, "step": 430 }, { "epoch": 0.023191993112354713, "grad_norm": 1.4983834028244019, "learning_rate": 4.9933979769660834e-05, "loss": 5.0579, "step": 431 }, { "epoch": 0.02324580284115368, "grad_norm": 1.35521399974823, "learning_rate": 4.9933672477774486e-05, "loss": 4.9221, "step": 432 }, { "epoch": 0.02329961256995265, "grad_norm": 1.6057947874069214, "learning_rate": 4.9933364473350844e-05, "loss": 5.1543, "step": 433 }, { "epoch": 0.023353422298751616, "grad_norm": 2.559723138809204, "learning_rate": 4.993305575639871e-05, "loss": 4.997, "step": 434 }, { "epoch": 0.02340723202755058, "grad_norm": 1.722687840461731, "learning_rate": 4.9932746326926904e-05, "loss": 4.906, "step": 435 }, { "epoch": 0.023461041756349547, "grad_norm": 2.4400269985198975, "learning_rate": 4.993243618494428e-05, "loss": 4.7427, "step": 436 }, { "epoch": 0.023514851485148515, "grad_norm": 1.863434076309204, "learning_rate": 4.9932125330459677e-05, "loss": 4.87, "step": 437 }, { "epoch": 0.023568661213947482, "grad_norm": 1.7481725215911865, "learning_rate": 4.9931813763481994e-05, "loss": 4.9683, "step": 438 }, { "epoch": 0.02362247094274645, "grad_norm": 2.3604896068573, "learning_rate": 4.993150148402013e-05, "loss": 4.8782, "step": 439 }, { "epoch": 0.023676280671545414, "grad_norm": 1.6942100524902344, "learning_rate": 4.993118849208301e-05, "loss": 4.5796, "step": 440 }, { "epoch": 0.02373009040034438, "grad_norm": 1.6722463369369507, "learning_rate": 4.9930874787679596e-05, "loss": 4.9857, "step": 441 }, { "epoch": 0.02378390012914335, "grad_norm": 1.807773470878601, "learning_rate": 4.9930560370818824e-05, "loss": 5.1761, "step": 442 }, { "epoch": 0.023837709857942316, "grad_norm": 1.824683666229248, "learning_rate": 4.993024524150969e-05, "loss": 5.1264, "step": 443 }, { "epoch": 0.023891519586741284, "grad_norm": 1.3744322061538696, "learning_rate": 4.992992939976121e-05, "loss": 4.7094, "step": 444 }, { "epoch": 0.023945329315540248, "grad_norm": 1.5272525548934937, "learning_rate": 4.992961284558239e-05, "loss": 5.3233, "step": 445 }, { "epoch": 0.023999139044339216, "grad_norm": 1.3254120349884033, "learning_rate": 4.992929557898229e-05, "loss": 5.1003, "step": 446 }, { "epoch": 0.024052948773138183, "grad_norm": 1.3118109703063965, "learning_rate": 4.9928977599969984e-05, "loss": 4.9859, "step": 447 }, { "epoch": 0.02410675850193715, "grad_norm": 2.0536317825317383, "learning_rate": 4.992865890855454e-05, "loss": 4.8723, "step": 448 }, { "epoch": 0.024160568230736118, "grad_norm": 1.3503865003585815, "learning_rate": 4.992833950474508e-05, "loss": 4.744, "step": 449 }, { "epoch": 0.024214377959535086, "grad_norm": 1.794946551322937, "learning_rate": 4.992801938855073e-05, "loss": 4.943, "step": 450 }, { "epoch": 0.02426818768833405, "grad_norm": 2.2737715244293213, "learning_rate": 4.992769855998063e-05, "loss": 4.7722, "step": 451 }, { "epoch": 0.024321997417133017, "grad_norm": 1.7006499767303467, "learning_rate": 4.9927377019043946e-05, "loss": 4.9292, "step": 452 }, { "epoch": 0.024375807145931985, "grad_norm": 1.3020042181015015, "learning_rate": 4.992705476574988e-05, "loss": 4.8497, "step": 453 }, { "epoch": 0.024429616874730952, "grad_norm": 2.3219711780548096, "learning_rate": 4.9926731800107636e-05, "loss": 4.9528, "step": 454 }, { "epoch": 0.02448342660352992, "grad_norm": 1.7638261318206787, "learning_rate": 4.992640812212644e-05, "loss": 5.1147, "step": 455 }, { "epoch": 0.024537236332328884, "grad_norm": 3.2688655853271484, "learning_rate": 4.9926083731815544e-05, "loss": 5.3635, "step": 456 }, { "epoch": 0.02459104606112785, "grad_norm": 2.0250144004821777, "learning_rate": 4.992575862918422e-05, "loss": 4.8168, "step": 457 }, { "epoch": 0.02464485578992682, "grad_norm": 3.143329381942749, "learning_rate": 4.992543281424175e-05, "loss": 4.8643, "step": 458 }, { "epoch": 0.024698665518725786, "grad_norm": 1.4661206007003784, "learning_rate": 4.992510628699746e-05, "loss": 4.9099, "step": 459 }, { "epoch": 0.024752475247524754, "grad_norm": 1.9085936546325684, "learning_rate": 4.992477904746067e-05, "loss": 4.917, "step": 460 }, { "epoch": 0.024806284976323718, "grad_norm": 1.2698757648468018, "learning_rate": 4.992445109564073e-05, "loss": 4.8747, "step": 461 }, { "epoch": 0.024860094705122685, "grad_norm": 2.178769826889038, "learning_rate": 4.992412243154703e-05, "loss": 4.7956, "step": 462 }, { "epoch": 0.024913904433921653, "grad_norm": 1.8041950464248657, "learning_rate": 4.992379305518894e-05, "loss": 5.0571, "step": 463 }, { "epoch": 0.02496771416272062, "grad_norm": 1.4435086250305176, "learning_rate": 4.992346296657587e-05, "loss": 4.8885, "step": 464 }, { "epoch": 0.025021523891519588, "grad_norm": 1.8616122007369995, "learning_rate": 4.9923132165717284e-05, "loss": 5.2937, "step": 465 }, { "epoch": 0.025075333620318555, "grad_norm": 1.7200583219528198, "learning_rate": 4.992280065262261e-05, "loss": 5.1732, "step": 466 }, { "epoch": 0.02512914334911752, "grad_norm": 2.2213730812072754, "learning_rate": 4.992246842730133e-05, "loss": 4.8941, "step": 467 }, { "epoch": 0.025182953077916487, "grad_norm": 2.231336832046509, "learning_rate": 4.9922135489762924e-05, "loss": 4.8657, "step": 468 }, { "epoch": 0.025236762806715454, "grad_norm": 2.180351734161377, "learning_rate": 4.992180184001693e-05, "loss": 4.8834, "step": 469 }, { "epoch": 0.025290572535514422, "grad_norm": 1.388695240020752, "learning_rate": 4.992146747807287e-05, "loss": 4.7511, "step": 470 }, { "epoch": 0.02534438226431339, "grad_norm": 2.0961060523986816, "learning_rate": 4.9921132403940295e-05, "loss": 5.117, "step": 471 }, { "epoch": 0.025398191993112353, "grad_norm": 1.401611089706421, "learning_rate": 4.9920796617628785e-05, "loss": 4.8777, "step": 472 }, { "epoch": 0.02545200172191132, "grad_norm": 2.2602031230926514, "learning_rate": 4.9920460119147945e-05, "loss": 4.8838, "step": 473 }, { "epoch": 0.02550581145071029, "grad_norm": 1.335670828819275, "learning_rate": 4.992012290850738e-05, "loss": 4.7882, "step": 474 }, { "epoch": 0.025559621179509256, "grad_norm": 1.2491772174835205, "learning_rate": 4.991978498571672e-05, "loss": 4.9714, "step": 475 }, { "epoch": 0.025613430908308223, "grad_norm": 1.9244365692138672, "learning_rate": 4.9919446350785645e-05, "loss": 4.9676, "step": 476 }, { "epoch": 0.025667240637107187, "grad_norm": 1.548062801361084, "learning_rate": 4.9919107003723815e-05, "loss": 4.8058, "step": 477 }, { "epoch": 0.025721050365906155, "grad_norm": 1.8720457553863525, "learning_rate": 4.991876694454093e-05, "loss": 4.9994, "step": 478 }, { "epoch": 0.025774860094705122, "grad_norm": 2.282144784927368, "learning_rate": 4.991842617324671e-05, "loss": 4.8491, "step": 479 }, { "epoch": 0.02582866982350409, "grad_norm": 1.298319697380066, "learning_rate": 4.991808468985089e-05, "loss": 5.3543, "step": 480 }, { "epoch": 0.025882479552303057, "grad_norm": 1.233862042427063, "learning_rate": 4.991774249436323e-05, "loss": 4.9145, "step": 481 }, { "epoch": 0.025936289281102025, "grad_norm": 3.587808609008789, "learning_rate": 4.9917399586793514e-05, "loss": 4.753, "step": 482 }, { "epoch": 0.02599009900990099, "grad_norm": 1.7856680154800415, "learning_rate": 4.991705596715154e-05, "loss": 4.9108, "step": 483 }, { "epoch": 0.026043908738699956, "grad_norm": 2.622459650039673, "learning_rate": 4.9916711635447125e-05, "loss": 4.8088, "step": 484 }, { "epoch": 0.026097718467498924, "grad_norm": 1.2220526933670044, "learning_rate": 4.99163665916901e-05, "loss": 5.0332, "step": 485 }, { "epoch": 0.02615152819629789, "grad_norm": 1.274689793586731, "learning_rate": 4.991602083589034e-05, "loss": 5.1186, "step": 486 }, { "epoch": 0.02620533792509686, "grad_norm": 1.5419472455978394, "learning_rate": 4.991567436805773e-05, "loss": 4.9043, "step": 487 }, { "epoch": 0.026259147653895823, "grad_norm": 1.8560395240783691, "learning_rate": 4.9915327188202156e-05, "loss": 4.8916, "step": 488 }, { "epoch": 0.02631295738269479, "grad_norm": 2.051548719406128, "learning_rate": 4.991497929633354e-05, "loss": 5.1457, "step": 489 }, { "epoch": 0.026366767111493758, "grad_norm": 2.536724090576172, "learning_rate": 4.9914630692461835e-05, "loss": 5.0643, "step": 490 }, { "epoch": 0.026420576840292725, "grad_norm": 1.8641422986984253, "learning_rate": 4.991428137659699e-05, "loss": 4.8534, "step": 491 }, { "epoch": 0.026474386569091693, "grad_norm": 1.857721209526062, "learning_rate": 4.9913931348749e-05, "loss": 5.166, "step": 492 }, { "epoch": 0.026528196297890657, "grad_norm": 1.5271189212799072, "learning_rate": 4.991358060892787e-05, "loss": 5.1189, "step": 493 }, { "epoch": 0.026582006026689625, "grad_norm": 1.2300738096237183, "learning_rate": 4.991322915714361e-05, "loss": 5.0429, "step": 494 }, { "epoch": 0.026635815755488592, "grad_norm": 1.5328480005264282, "learning_rate": 4.991287699340627e-05, "loss": 4.884, "step": 495 }, { "epoch": 0.02668962548428756, "grad_norm": 2.167695999145508, "learning_rate": 4.9912524117725903e-05, "loss": 5.2551, "step": 496 }, { "epoch": 0.026743435213086527, "grad_norm": 2.214116096496582, "learning_rate": 4.991217053011261e-05, "loss": 4.9636, "step": 497 }, { "epoch": 0.026797244941885495, "grad_norm": 1.4551024436950684, "learning_rate": 4.991181623057649e-05, "loss": 4.9923, "step": 498 }, { "epoch": 0.02685105467068446, "grad_norm": 2.070800304412842, "learning_rate": 4.991146121912767e-05, "loss": 4.8089, "step": 499 }, { "epoch": 0.026904864399483426, "grad_norm": 1.3766615390777588, "learning_rate": 4.991110549577629e-05, "loss": 5.0143, "step": 500 }, { "epoch": 0.026958674128282394, "grad_norm": 1.7408137321472168, "learning_rate": 4.991074906053252e-05, "loss": 4.8389, "step": 501 }, { "epoch": 0.02701248385708136, "grad_norm": 1.5352953672409058, "learning_rate": 4.991039191340654e-05, "loss": 4.8791, "step": 502 }, { "epoch": 0.02706629358588033, "grad_norm": 2.3217685222625732, "learning_rate": 4.9910034054408566e-05, "loss": 5.0783, "step": 503 }, { "epoch": 0.027120103314679293, "grad_norm": 1.9651097059249878, "learning_rate": 4.9909675483548815e-05, "loss": 5.1248, "step": 504 }, { "epoch": 0.02717391304347826, "grad_norm": 1.5643870830535889, "learning_rate": 4.990931620083754e-05, "loss": 5.0519, "step": 505 }, { "epoch": 0.027227722772277228, "grad_norm": 1.9668128490447998, "learning_rate": 4.9908956206285e-05, "loss": 4.775, "step": 506 }, { "epoch": 0.027281532501076195, "grad_norm": 1.5788459777832031, "learning_rate": 4.9908595499901496e-05, "loss": 4.778, "step": 507 }, { "epoch": 0.027335342229875163, "grad_norm": 1.8891029357910156, "learning_rate": 4.990823408169733e-05, "loss": 4.9651, "step": 508 }, { "epoch": 0.027389151958674127, "grad_norm": 1.7915164232254028, "learning_rate": 4.990787195168282e-05, "loss": 4.8476, "step": 509 }, { "epoch": 0.027442961687473094, "grad_norm": 1.8559099435806274, "learning_rate": 4.990750910986833e-05, "loss": 4.7748, "step": 510 }, { "epoch": 0.02749677141627206, "grad_norm": 2.1612725257873535, "learning_rate": 4.990714555626422e-05, "loss": 4.8288, "step": 511 }, { "epoch": 0.02755058114507103, "grad_norm": 2.3719329833984375, "learning_rate": 4.990678129088089e-05, "loss": 5.1116, "step": 512 }, { "epoch": 0.027604390873869997, "grad_norm": 2.0821969509124756, "learning_rate": 4.990641631372873e-05, "loss": 5.2724, "step": 513 }, { "epoch": 0.027658200602668964, "grad_norm": 2.150468111038208, "learning_rate": 4.9906050624818193e-05, "loss": 4.8202, "step": 514 }, { "epoch": 0.027712010331467928, "grad_norm": 1.7897106409072876, "learning_rate": 4.990568422415971e-05, "loss": 5.1338, "step": 515 }, { "epoch": 0.027765820060266896, "grad_norm": 1.5600963830947876, "learning_rate": 4.990531711176377e-05, "loss": 4.9387, "step": 516 }, { "epoch": 0.027819629789065863, "grad_norm": 1.0945736169815063, "learning_rate": 4.990494928764085e-05, "loss": 4.6695, "step": 517 }, { "epoch": 0.02787343951786483, "grad_norm": 2.099961757659912, "learning_rate": 4.990458075180146e-05, "loss": 4.9589, "step": 518 }, { "epoch": 0.027927249246663798, "grad_norm": 1.6658295392990112, "learning_rate": 4.990421150425614e-05, "loss": 4.803, "step": 519 }, { "epoch": 0.027981058975462762, "grad_norm": 1.3044687509536743, "learning_rate": 4.990384154501544e-05, "loss": 5.0419, "step": 520 }, { "epoch": 0.02803486870426173, "grad_norm": 1.59005868434906, "learning_rate": 4.990347087408994e-05, "loss": 4.7841, "step": 521 }, { "epoch": 0.028088678433060697, "grad_norm": 2.2275502681732178, "learning_rate": 4.990309949149022e-05, "loss": 4.9427, "step": 522 }, { "epoch": 0.028142488161859665, "grad_norm": 1.9138269424438477, "learning_rate": 4.9902727397226895e-05, "loss": 4.8733, "step": 523 }, { "epoch": 0.028196297890658632, "grad_norm": 1.124435544013977, "learning_rate": 4.990235459131061e-05, "loss": 5.0212, "step": 524 }, { "epoch": 0.028250107619457596, "grad_norm": 1.5588762760162354, "learning_rate": 4.9901981073752005e-05, "loss": 4.9863, "step": 525 }, { "epoch": 0.028303917348256564, "grad_norm": 1.858726143836975, "learning_rate": 4.990160684456175e-05, "loss": 4.7944, "step": 526 }, { "epoch": 0.02835772707705553, "grad_norm": 1.9965991973876953, "learning_rate": 4.990123190375056e-05, "loss": 5.0796, "step": 527 }, { "epoch": 0.0284115368058545, "grad_norm": 1.5886762142181396, "learning_rate": 4.990085625132913e-05, "loss": 4.8622, "step": 528 }, { "epoch": 0.028465346534653466, "grad_norm": 1.459110140800476, "learning_rate": 4.9900479887308216e-05, "loss": 5.0482, "step": 529 }, { "epoch": 0.028519156263452434, "grad_norm": 1.3990452289581299, "learning_rate": 4.9900102811698553e-05, "loss": 5.0479, "step": 530 }, { "epoch": 0.028572965992251398, "grad_norm": 1.7698335647583008, "learning_rate": 4.9899725024510925e-05, "loss": 5.2908, "step": 531 }, { "epoch": 0.028626775721050365, "grad_norm": 2.2176132202148438, "learning_rate": 4.989934652575613e-05, "loss": 4.9903, "step": 532 }, { "epoch": 0.028680585449849333, "grad_norm": 1.108761191368103, "learning_rate": 4.9898967315444984e-05, "loss": 4.9533, "step": 533 }, { "epoch": 0.0287343951786483, "grad_norm": 1.4106864929199219, "learning_rate": 4.989858739358832e-05, "loss": 4.5702, "step": 534 }, { "epoch": 0.028788204907447268, "grad_norm": 1.5957893133163452, "learning_rate": 4.9898206760197e-05, "loss": 4.7771, "step": 535 }, { "epoch": 0.028842014636246232, "grad_norm": 2.245500326156616, "learning_rate": 4.9897825415281894e-05, "loss": 5.0946, "step": 536 }, { "epoch": 0.0288958243650452, "grad_norm": 1.4376338720321655, "learning_rate": 4.989744335885391e-05, "loss": 4.8023, "step": 537 }, { "epoch": 0.028949634093844167, "grad_norm": 1.4406222105026245, "learning_rate": 4.989706059092396e-05, "loss": 4.9176, "step": 538 }, { "epoch": 0.029003443822643134, "grad_norm": 1.4994499683380127, "learning_rate": 4.989667711150299e-05, "loss": 4.9309, "step": 539 }, { "epoch": 0.029057253551442102, "grad_norm": 2.7703499794006348, "learning_rate": 4.9896292920601936e-05, "loss": 4.9316, "step": 540 }, { "epoch": 0.029111063280241066, "grad_norm": 1.8437964916229248, "learning_rate": 4.989590801823181e-05, "loss": 4.6548, "step": 541 }, { "epoch": 0.029164873009040033, "grad_norm": 1.1226166486740112, "learning_rate": 4.9895522404403586e-05, "loss": 4.7811, "step": 542 }, { "epoch": 0.029218682737839, "grad_norm": 2.646778106689453, "learning_rate": 4.989513607912829e-05, "loss": 5.2336, "step": 543 }, { "epoch": 0.02927249246663797, "grad_norm": 2.0310165882110596, "learning_rate": 4.989474904241697e-05, "loss": 4.9123, "step": 544 }, { "epoch": 0.029326302195436936, "grad_norm": 1.5847797393798828, "learning_rate": 4.989436129428068e-05, "loss": 5.067, "step": 545 }, { "epoch": 0.029380111924235904, "grad_norm": 1.6709142923355103, "learning_rate": 4.989397283473051e-05, "loss": 4.6862, "step": 546 }, { "epoch": 0.029433921653034868, "grad_norm": 1.717976689338684, "learning_rate": 4.9893583663777545e-05, "loss": 5.0554, "step": 547 }, { "epoch": 0.029487731381833835, "grad_norm": 2.4512763023376465, "learning_rate": 4.9893193781432915e-05, "loss": 4.9588, "step": 548 }, { "epoch": 0.029541541110632803, "grad_norm": 1.7499862909317017, "learning_rate": 4.989280318770776e-05, "loss": 5.0266, "step": 549 }, { "epoch": 0.02959535083943177, "grad_norm": 1.5213866233825684, "learning_rate": 4.989241188261325e-05, "loss": 4.9279, "step": 550 }, { "epoch": 0.029649160568230738, "grad_norm": 1.422325611114502, "learning_rate": 4.989201986616056e-05, "loss": 4.8216, "step": 551 }, { "epoch": 0.0297029702970297, "grad_norm": 1.3422727584838867, "learning_rate": 4.989162713836088e-05, "loss": 4.9751, "step": 552 }, { "epoch": 0.02975678002582867, "grad_norm": 1.2933186292648315, "learning_rate": 4.989123369922547e-05, "loss": 4.8661, "step": 553 }, { "epoch": 0.029810589754627637, "grad_norm": 1.9802558422088623, "learning_rate": 4.9890839548765535e-05, "loss": 4.9593, "step": 554 }, { "epoch": 0.029864399483426604, "grad_norm": 1.2574690580368042, "learning_rate": 4.989044468699236e-05, "loss": 4.6626, "step": 555 }, { "epoch": 0.02991820921222557, "grad_norm": 1.4155038595199585, "learning_rate": 4.989004911391722e-05, "loss": 4.9521, "step": 556 }, { "epoch": 0.029972018941024536, "grad_norm": 1.1757925748825073, "learning_rate": 4.988965282955143e-05, "loss": 4.9574, "step": 557 }, { "epoch": 0.030025828669823503, "grad_norm": 1.3102785348892212, "learning_rate": 4.9889255833906295e-05, "loss": 4.7961, "step": 558 }, { "epoch": 0.03007963839862247, "grad_norm": 1.4583009481430054, "learning_rate": 4.988885812699318e-05, "loss": 5.0817, "step": 559 }, { "epoch": 0.030133448127421438, "grad_norm": 1.2372561693191528, "learning_rate": 4.9888459708823445e-05, "loss": 4.9943, "step": 560 }, { "epoch": 0.030187257856220406, "grad_norm": 1.6021082401275635, "learning_rate": 4.988806057940847e-05, "loss": 4.7776, "step": 561 }, { "epoch": 0.030241067585019373, "grad_norm": 1.6386116743087769, "learning_rate": 4.988766073875967e-05, "loss": 5.0447, "step": 562 }, { "epoch": 0.030294877313818337, "grad_norm": 3.1655595302581787, "learning_rate": 4.988726018688845e-05, "loss": 4.5289, "step": 563 }, { "epoch": 0.030348687042617305, "grad_norm": 1.1883624792099, "learning_rate": 4.988685892380629e-05, "loss": 4.9986, "step": 564 }, { "epoch": 0.030402496771416272, "grad_norm": 1.1454815864562988, "learning_rate": 4.988645694952463e-05, "loss": 4.9879, "step": 565 }, { "epoch": 0.03045630650021524, "grad_norm": 1.1566060781478882, "learning_rate": 4.988605426405497e-05, "loss": 5.062, "step": 566 }, { "epoch": 0.030510116229014207, "grad_norm": 1.6746513843536377, "learning_rate": 4.988565086740882e-05, "loss": 4.8445, "step": 567 }, { "epoch": 0.03056392595781317, "grad_norm": 1.2471083402633667, "learning_rate": 4.98852467595977e-05, "loss": 5.1292, "step": 568 }, { "epoch": 0.03061773568661214, "grad_norm": 1.5321441888809204, "learning_rate": 4.988484194063316e-05, "loss": 4.8815, "step": 569 }, { "epoch": 0.030671545415411106, "grad_norm": 1.773785948753357, "learning_rate": 4.988443641052677e-05, "loss": 4.7913, "step": 570 }, { "epoch": 0.030725355144210074, "grad_norm": 2.0083022117614746, "learning_rate": 4.988403016929011e-05, "loss": 4.6389, "step": 571 }, { "epoch": 0.03077916487300904, "grad_norm": 1.610957384109497, "learning_rate": 4.988362321693481e-05, "loss": 5.0094, "step": 572 }, { "epoch": 0.030832974601808005, "grad_norm": 3.496443748474121, "learning_rate": 4.988321555347248e-05, "loss": 4.7412, "step": 573 }, { "epoch": 0.030886784330606973, "grad_norm": 2.117119312286377, "learning_rate": 4.988280717891478e-05, "loss": 5.0836, "step": 574 }, { "epoch": 0.03094059405940594, "grad_norm": 2.0546979904174805, "learning_rate": 4.988239809327339e-05, "loss": 4.5049, "step": 575 }, { "epoch": 0.030994403788204908, "grad_norm": 1.1309620141983032, "learning_rate": 4.9881988296559965e-05, "loss": 4.997, "step": 576 }, { "epoch": 0.031048213517003875, "grad_norm": 1.5459357500076294, "learning_rate": 4.9881577788786256e-05, "loss": 4.7973, "step": 577 }, { "epoch": 0.031102023245802843, "grad_norm": 2.8671460151672363, "learning_rate": 4.988116656996397e-05, "loss": 5.1102, "step": 578 }, { "epoch": 0.031155832974601807, "grad_norm": 1.9740633964538574, "learning_rate": 4.9880754640104864e-05, "loss": 4.9387, "step": 579 }, { "epoch": 0.031209642703400774, "grad_norm": 2.692186117172241, "learning_rate": 4.988034199922072e-05, "loss": 4.9618, "step": 580 }, { "epoch": 0.03126345243219974, "grad_norm": 1.61105477809906, "learning_rate": 4.9879928647323314e-05, "loss": 4.9521, "step": 581 }, { "epoch": 0.031317262160998706, "grad_norm": 1.6322813034057617, "learning_rate": 4.987951458442448e-05, "loss": 4.7111, "step": 582 }, { "epoch": 0.03137107188979767, "grad_norm": 1.1269398927688599, "learning_rate": 4.9879099810536024e-05, "loss": 4.8102, "step": 583 }, { "epoch": 0.03142488161859664, "grad_norm": 2.047775983810425, "learning_rate": 4.987868432566981e-05, "loss": 4.8312, "step": 584 }, { "epoch": 0.03147869134739561, "grad_norm": 2.3071417808532715, "learning_rate": 4.987826812983772e-05, "loss": 5.0467, "step": 585 }, { "epoch": 0.031532501076194576, "grad_norm": 1.8031588792800903, "learning_rate": 4.9877851223051644e-05, "loss": 4.9567, "step": 586 }, { "epoch": 0.03158631080499354, "grad_norm": 1.7416033744812012, "learning_rate": 4.987743360532349e-05, "loss": 5.1325, "step": 587 }, { "epoch": 0.03164012053379251, "grad_norm": 1.6576075553894043, "learning_rate": 4.98770152766652e-05, "loss": 4.6159, "step": 588 }, { "epoch": 0.03169393026259148, "grad_norm": 1.539086937904358, "learning_rate": 4.987659623708872e-05, "loss": 4.8989, "step": 589 }, { "epoch": 0.031747739991390446, "grad_norm": 1.648729920387268, "learning_rate": 4.987617648660603e-05, "loss": 4.7991, "step": 590 }, { "epoch": 0.03180154972018941, "grad_norm": 1.1078143119812012, "learning_rate": 4.987575602522913e-05, "loss": 5.178, "step": 591 }, { "epoch": 0.031855359448988374, "grad_norm": 1.6555817127227783, "learning_rate": 4.9875334852970024e-05, "loss": 5.0236, "step": 592 }, { "epoch": 0.03190916917778734, "grad_norm": 1.3830054998397827, "learning_rate": 4.9874912969840756e-05, "loss": 4.8369, "step": 593 }, { "epoch": 0.03196297890658631, "grad_norm": 2.206355333328247, "learning_rate": 4.987449037585339e-05, "loss": 4.7974, "step": 594 }, { "epoch": 0.032016788635385277, "grad_norm": 1.4602018594741821, "learning_rate": 4.987406707101998e-05, "loss": 4.9693, "step": 595 }, { "epoch": 0.032070598364184244, "grad_norm": 1.7724555730819702, "learning_rate": 4.987364305535265e-05, "loss": 4.9019, "step": 596 }, { "epoch": 0.03212440809298321, "grad_norm": 1.9647198915481567, "learning_rate": 4.9873218328863494e-05, "loss": 5.1097, "step": 597 }, { "epoch": 0.03217821782178218, "grad_norm": 2.044926881790161, "learning_rate": 4.987279289156466e-05, "loss": 4.9135, "step": 598 }, { "epoch": 0.03223202755058115, "grad_norm": 2.096632242202759, "learning_rate": 4.98723667434683e-05, "loss": 4.8554, "step": 599 }, { "epoch": 0.032285837279380114, "grad_norm": 2.07541823387146, "learning_rate": 4.987193988458661e-05, "loss": 4.7171, "step": 600 }, { "epoch": 0.03233964700817908, "grad_norm": 1.2530823945999146, "learning_rate": 4.987151231493177e-05, "loss": 5.083, "step": 601 }, { "epoch": 0.03239345673697805, "grad_norm": 1.7036157846450806, "learning_rate": 4.9871084034516004e-05, "loss": 4.736, "step": 602 }, { "epoch": 0.03244726646577701, "grad_norm": 1.5897117853164673, "learning_rate": 4.987065504335155e-05, "loss": 5.0082, "step": 603 }, { "epoch": 0.03250107619457598, "grad_norm": 2.3178322315216064, "learning_rate": 4.9870225341450674e-05, "loss": 5.1941, "step": 604 }, { "epoch": 0.032554885923374945, "grad_norm": 1.8213326930999756, "learning_rate": 4.9869794928825645e-05, "loss": 4.949, "step": 605 }, { "epoch": 0.03260869565217391, "grad_norm": 1.2858408689498901, "learning_rate": 4.986936380548877e-05, "loss": 4.9081, "step": 606 }, { "epoch": 0.03266250538097288, "grad_norm": 1.5569844245910645, "learning_rate": 4.986893197145237e-05, "loss": 5.0267, "step": 607 }, { "epoch": 0.03271631510977185, "grad_norm": 1.518213152885437, "learning_rate": 4.9868499426728784e-05, "loss": 4.6225, "step": 608 }, { "epoch": 0.032770124838570815, "grad_norm": 1.7526887655258179, "learning_rate": 4.9868066171330376e-05, "loss": 5.0322, "step": 609 }, { "epoch": 0.03282393456736978, "grad_norm": 2.1219167709350586, "learning_rate": 4.986763220526952e-05, "loss": 4.7223, "step": 610 }, { "epoch": 0.03287774429616875, "grad_norm": 1.9344520568847656, "learning_rate": 4.986719752855862e-05, "loss": 4.9679, "step": 611 }, { "epoch": 0.03293155402496772, "grad_norm": 1.2141313552856445, "learning_rate": 4.986676214121011e-05, "loss": 4.8951, "step": 612 }, { "epoch": 0.03298536375376668, "grad_norm": 1.37516450881958, "learning_rate": 4.986632604323641e-05, "loss": 4.6461, "step": 613 }, { "epoch": 0.033039173482565645, "grad_norm": 2.3857262134552, "learning_rate": 4.9865889234649996e-05, "loss": 4.816, "step": 614 }, { "epoch": 0.03309298321136461, "grad_norm": 1.2917585372924805, "learning_rate": 4.986545171546335e-05, "loss": 5.0888, "step": 615 }, { "epoch": 0.03314679294016358, "grad_norm": 1.7153418064117432, "learning_rate": 4.986501348568897e-05, "loss": 4.9695, "step": 616 }, { "epoch": 0.03320060266896255, "grad_norm": 1.35307776927948, "learning_rate": 4.9864574545339394e-05, "loss": 4.7198, "step": 617 }, { "epoch": 0.033254412397761515, "grad_norm": 1.6043421030044556, "learning_rate": 4.9864134894427153e-05, "loss": 4.662, "step": 618 }, { "epoch": 0.03330822212656048, "grad_norm": 2.032127618789673, "learning_rate": 4.986369453296481e-05, "loss": 4.8235, "step": 619 }, { "epoch": 0.03336203185535945, "grad_norm": 1.955708384513855, "learning_rate": 4.986325346096495e-05, "loss": 4.8513, "step": 620 }, { "epoch": 0.03341584158415842, "grad_norm": 1.2068763971328735, "learning_rate": 4.986281167844018e-05, "loss": 5.3015, "step": 621 }, { "epoch": 0.033469651312957385, "grad_norm": 1.4577913284301758, "learning_rate": 4.986236918540313e-05, "loss": 5.1463, "step": 622 }, { "epoch": 0.03352346104175635, "grad_norm": 1.9096988439559937, "learning_rate": 4.986192598186644e-05, "loss": 4.8847, "step": 623 }, { "epoch": 0.03357727077055531, "grad_norm": 1.3396024703979492, "learning_rate": 4.986148206784278e-05, "loss": 5.1393, "step": 624 }, { "epoch": 0.03363108049935428, "grad_norm": 2.008422374725342, "learning_rate": 4.986103744334483e-05, "loss": 4.6828, "step": 625 }, { "epoch": 0.03368489022815325, "grad_norm": 1.6469120979309082, "learning_rate": 4.986059210838529e-05, "loss": 4.975, "step": 626 }, { "epoch": 0.033738699956952216, "grad_norm": 1.9562073945999146, "learning_rate": 4.98601460629769e-05, "loss": 4.9731, "step": 627 }, { "epoch": 0.03379250968575118, "grad_norm": 1.9664610624313354, "learning_rate": 4.98596993071324e-05, "loss": 5.1795, "step": 628 }, { "epoch": 0.03384631941455015, "grad_norm": 1.9665735960006714, "learning_rate": 4.985925184086456e-05, "loss": 4.8073, "step": 629 }, { "epoch": 0.03390012914334912, "grad_norm": 2.1400039196014404, "learning_rate": 4.9858803664186174e-05, "loss": 4.8685, "step": 630 }, { "epoch": 0.033953938872148086, "grad_norm": 2.111081838607788, "learning_rate": 4.985835477711003e-05, "loss": 5.0527, "step": 631 }, { "epoch": 0.03400774860094705, "grad_norm": 1.6271332502365112, "learning_rate": 4.9857905179648976e-05, "loss": 4.8, "step": 632 }, { "epoch": 0.03406155832974602, "grad_norm": 1.644210934638977, "learning_rate": 4.9857454871815846e-05, "loss": 4.9735, "step": 633 }, { "epoch": 0.03411536805854499, "grad_norm": 1.1443909406661987, "learning_rate": 4.9857003853623516e-05, "loss": 4.9165, "step": 634 }, { "epoch": 0.03416917778734395, "grad_norm": 1.3157728910446167, "learning_rate": 4.9856552125084874e-05, "loss": 4.9117, "step": 635 }, { "epoch": 0.034222987516142916, "grad_norm": 1.5567370653152466, "learning_rate": 4.985609968621282e-05, "loss": 4.8803, "step": 636 }, { "epoch": 0.034276797244941884, "grad_norm": 2.1538994312286377, "learning_rate": 4.985564653702031e-05, "loss": 4.9017, "step": 637 }, { "epoch": 0.03433060697374085, "grad_norm": 2.0071663856506348, "learning_rate": 4.9855192677520257e-05, "loss": 4.6257, "step": 638 }, { "epoch": 0.03438441670253982, "grad_norm": 1.3472275733947754, "learning_rate": 4.985473810772566e-05, "loss": 4.9569, "step": 639 }, { "epoch": 0.034438226431338786, "grad_norm": 1.3979874849319458, "learning_rate": 4.98542828276495e-05, "loss": 4.8865, "step": 640 }, { "epoch": 0.034492036160137754, "grad_norm": 1.4165732860565186, "learning_rate": 4.9853826837304785e-05, "loss": 4.9339, "step": 641 }, { "epoch": 0.03454584588893672, "grad_norm": 1.4161430597305298, "learning_rate": 4.985337013670455e-05, "loss": 4.9573, "step": 642 }, { "epoch": 0.03459965561773569, "grad_norm": 1.379313588142395, "learning_rate": 4.985291272586184e-05, "loss": 5.0806, "step": 643 }, { "epoch": 0.034653465346534656, "grad_norm": 1.2279621362686157, "learning_rate": 4.9852454604789735e-05, "loss": 4.9306, "step": 644 }, { "epoch": 0.03470727507533362, "grad_norm": 1.473591923713684, "learning_rate": 4.9851995773501315e-05, "loss": 4.7347, "step": 645 }, { "epoch": 0.034761084804132585, "grad_norm": 2.001661777496338, "learning_rate": 4.985153623200971e-05, "loss": 4.8737, "step": 646 }, { "epoch": 0.03481489453293155, "grad_norm": 1.4111828804016113, "learning_rate": 4.9851075980328035e-05, "loss": 4.9944, "step": 647 }, { "epoch": 0.03486870426173052, "grad_norm": 2.421048641204834, "learning_rate": 4.9850615018469446e-05, "loss": 4.9153, "step": 648 }, { "epoch": 0.03492251399052949, "grad_norm": 1.8610777854919434, "learning_rate": 4.985015334644713e-05, "loss": 4.8108, "step": 649 }, { "epoch": 0.034976323719328455, "grad_norm": 1.6087068319320679, "learning_rate": 4.984969096427427e-05, "loss": 4.614, "step": 650 }, { "epoch": 0.03503013344812742, "grad_norm": 1.3435581922531128, "learning_rate": 4.984922787196408e-05, "loss": 4.6978, "step": 651 }, { "epoch": 0.03508394317692639, "grad_norm": 1.4756181240081787, "learning_rate": 4.984876406952979e-05, "loss": 4.7929, "step": 652 }, { "epoch": 0.03513775290572536, "grad_norm": 1.5407626628875732, "learning_rate": 4.9848299556984654e-05, "loss": 4.9432, "step": 653 }, { "epoch": 0.035191562634524325, "grad_norm": 2.011578321456909, "learning_rate": 4.984783433434196e-05, "loss": 4.9349, "step": 654 }, { "epoch": 0.03524537236332329, "grad_norm": 2.043532609939575, "learning_rate": 4.984736840161499e-05, "loss": 5.0228, "step": 655 }, { "epoch": 0.03529918209212225, "grad_norm": 2.6323440074920654, "learning_rate": 4.984690175881706e-05, "loss": 4.8354, "step": 656 }, { "epoch": 0.03535299182092122, "grad_norm": 1.8974984884262085, "learning_rate": 4.984643440596151e-05, "loss": 4.8906, "step": 657 }, { "epoch": 0.03540680154972019, "grad_norm": 1.6744537353515625, "learning_rate": 4.98459663430617e-05, "loss": 5.1658, "step": 658 }, { "epoch": 0.035460611278519155, "grad_norm": 2.0195353031158447, "learning_rate": 4.9845497570130986e-05, "loss": 4.8274, "step": 659 }, { "epoch": 0.03551442100731812, "grad_norm": 1.5042212009429932, "learning_rate": 4.984502808718279e-05, "loss": 4.9545, "step": 660 }, { "epoch": 0.03556823073611709, "grad_norm": 1.9712953567504883, "learning_rate": 4.984455789423051e-05, "loss": 4.9773, "step": 661 }, { "epoch": 0.03562204046491606, "grad_norm": 2.275625467300415, "learning_rate": 4.984408699128759e-05, "loss": 5.0742, "step": 662 }, { "epoch": 0.035675850193715025, "grad_norm": 1.6699906587600708, "learning_rate": 4.984361537836749e-05, "loss": 5.1309, "step": 663 }, { "epoch": 0.03572965992251399, "grad_norm": 2.6560239791870117, "learning_rate": 4.984314305548368e-05, "loss": 4.8041, "step": 664 }, { "epoch": 0.03578346965131296, "grad_norm": 1.3727974891662598, "learning_rate": 4.984267002264966e-05, "loss": 5.3568, "step": 665 }, { "epoch": 0.03583727938011192, "grad_norm": 1.5194772481918335, "learning_rate": 4.984219627987896e-05, "loss": 4.6657, "step": 666 }, { "epoch": 0.03589108910891089, "grad_norm": 1.2052098512649536, "learning_rate": 4.98417218271851e-05, "loss": 4.8943, "step": 667 }, { "epoch": 0.035944898837709856, "grad_norm": 1.708103895187378, "learning_rate": 4.984124666458165e-05, "loss": 4.8211, "step": 668 }, { "epoch": 0.03599870856650882, "grad_norm": 2.068854570388794, "learning_rate": 4.984077079208218e-05, "loss": 4.9678, "step": 669 }, { "epoch": 0.03605251829530779, "grad_norm": 1.668481469154358, "learning_rate": 4.98402942097003e-05, "loss": 4.6941, "step": 670 }, { "epoch": 0.03610632802410676, "grad_norm": 1.3410675525665283, "learning_rate": 4.983981691744962e-05, "loss": 5.0545, "step": 671 }, { "epoch": 0.036160137752905726, "grad_norm": 1.5485033988952637, "learning_rate": 4.983933891534379e-05, "loss": 4.819, "step": 672 }, { "epoch": 0.03621394748170469, "grad_norm": 2.035048007965088, "learning_rate": 4.9838860203396455e-05, "loss": 4.8286, "step": 673 }, { "epoch": 0.03626775721050366, "grad_norm": 1.469665288925171, "learning_rate": 4.983838078162131e-05, "loss": 4.7603, "step": 674 }, { "epoch": 0.03632156693930263, "grad_norm": 1.3890527486801147, "learning_rate": 4.983790065003205e-05, "loss": 4.8217, "step": 675 }, { "epoch": 0.036375376668101596, "grad_norm": 1.5631173849105835, "learning_rate": 4.9837419808642395e-05, "loss": 5.0819, "step": 676 }, { "epoch": 0.036429186396900556, "grad_norm": 1.23890221118927, "learning_rate": 4.983693825746608e-05, "loss": 4.7993, "step": 677 }, { "epoch": 0.036482996125699524, "grad_norm": 1.1619170904159546, "learning_rate": 4.983645599651688e-05, "loss": 4.9576, "step": 678 }, { "epoch": 0.03653680585449849, "grad_norm": 2.0414652824401855, "learning_rate": 4.983597302580857e-05, "loss": 4.9409, "step": 679 }, { "epoch": 0.03659061558329746, "grad_norm": 1.2092394828796387, "learning_rate": 4.9835489345354954e-05, "loss": 4.7034, "step": 680 }, { "epoch": 0.036644425312096426, "grad_norm": 1.2801594734191895, "learning_rate": 4.9835004955169846e-05, "loss": 4.726, "step": 681 }, { "epoch": 0.036698235040895394, "grad_norm": 1.2405105829238892, "learning_rate": 4.98345198552671e-05, "loss": 4.5124, "step": 682 }, { "epoch": 0.03675204476969436, "grad_norm": 1.3504353761672974, "learning_rate": 4.983403404566057e-05, "loss": 4.6193, "step": 683 }, { "epoch": 0.03680585449849333, "grad_norm": 2.0172557830810547, "learning_rate": 4.983354752636414e-05, "loss": 4.9556, "step": 684 }, { "epoch": 0.036859664227292296, "grad_norm": 1.5073282718658447, "learning_rate": 4.983306029739172e-05, "loss": 5.1448, "step": 685 }, { "epoch": 0.036913473956091264, "grad_norm": 2.0116822719573975, "learning_rate": 4.983257235875723e-05, "loss": 4.8983, "step": 686 }, { "epoch": 0.03696728368489023, "grad_norm": 1.8848994970321655, "learning_rate": 4.9832083710474614e-05, "loss": 4.8389, "step": 687 }, { "epoch": 0.03702109341368919, "grad_norm": 2.164461851119995, "learning_rate": 4.983159435255783e-05, "loss": 4.9543, "step": 688 }, { "epoch": 0.03707490314248816, "grad_norm": 2.4369258880615234, "learning_rate": 4.983110428502088e-05, "loss": 4.6346, "step": 689 }, { "epoch": 0.03712871287128713, "grad_norm": 1.5463708639144897, "learning_rate": 4.983061350787775e-05, "loss": 5.0566, "step": 690 }, { "epoch": 0.037182522600086094, "grad_norm": 1.459750771522522, "learning_rate": 4.9830122021142474e-05, "loss": 4.9061, "step": 691 }, { "epoch": 0.03723633232888506, "grad_norm": 1.617972731590271, "learning_rate": 4.982962982482909e-05, "loss": 4.6488, "step": 692 }, { "epoch": 0.03729014205768403, "grad_norm": 1.6584935188293457, "learning_rate": 4.982913691895168e-05, "loss": 4.7476, "step": 693 }, { "epoch": 0.037343951786483, "grad_norm": 1.4244084358215332, "learning_rate": 4.982864330352431e-05, "loss": 5.0262, "step": 694 }, { "epoch": 0.037397761515281965, "grad_norm": 1.6200565099716187, "learning_rate": 4.98281489785611e-05, "loss": 4.8709, "step": 695 }, { "epoch": 0.03745157124408093, "grad_norm": 2.7667551040649414, "learning_rate": 4.982765394407617e-05, "loss": 5.097, "step": 696 }, { "epoch": 0.0375053809728799, "grad_norm": 1.3470478057861328, "learning_rate": 4.982715820008367e-05, "loss": 4.9927, "step": 697 }, { "epoch": 0.03755919070167886, "grad_norm": 1.809707522392273, "learning_rate": 4.982666174659777e-05, "loss": 5.0355, "step": 698 }, { "epoch": 0.03761300043047783, "grad_norm": 1.6508344411849976, "learning_rate": 4.982616458363265e-05, "loss": 5.0707, "step": 699 }, { "epoch": 0.037666810159276795, "grad_norm": 2.6217827796936035, "learning_rate": 4.982566671120252e-05, "loss": 4.4701, "step": 700 }, { "epoch": 0.03772061988807576, "grad_norm": 1.161030650138855, "learning_rate": 4.982516812932161e-05, "loss": 4.7452, "step": 701 }, { "epoch": 0.03777442961687473, "grad_norm": 1.3505330085754395, "learning_rate": 4.982466883800416e-05, "loss": 4.8944, "step": 702 }, { "epoch": 0.0378282393456737, "grad_norm": 1.5873386859893799, "learning_rate": 4.982416883726446e-05, "loss": 4.8167, "step": 703 }, { "epoch": 0.037882049074472665, "grad_norm": 4.099942684173584, "learning_rate": 4.982366812711678e-05, "loss": 4.7638, "step": 704 }, { "epoch": 0.03793585880327163, "grad_norm": 2.327502489089966, "learning_rate": 4.982316670757542e-05, "loss": 4.6887, "step": 705 }, { "epoch": 0.0379896685320706, "grad_norm": 1.8196436166763306, "learning_rate": 4.982266457865473e-05, "loss": 4.5673, "step": 706 }, { "epoch": 0.03804347826086957, "grad_norm": 1.643606185913086, "learning_rate": 4.982216174036904e-05, "loss": 4.6572, "step": 707 }, { "epoch": 0.038097287989668535, "grad_norm": 1.4621319770812988, "learning_rate": 4.982165819273275e-05, "loss": 5.0611, "step": 708 }, { "epoch": 0.038151097718467496, "grad_norm": 2.0491812229156494, "learning_rate": 4.9821153935760226e-05, "loss": 4.7862, "step": 709 }, { "epoch": 0.03820490744726646, "grad_norm": 1.5324673652648926, "learning_rate": 4.9820648969465874e-05, "loss": 5.1466, "step": 710 }, { "epoch": 0.03825871717606543, "grad_norm": 1.5499240159988403, "learning_rate": 4.982014329386414e-05, "loss": 4.6621, "step": 711 }, { "epoch": 0.0383125269048644, "grad_norm": 1.684787392616272, "learning_rate": 4.981963690896947e-05, "loss": 4.9913, "step": 712 }, { "epoch": 0.038366336633663366, "grad_norm": 1.79736328125, "learning_rate": 4.981912981479634e-05, "loss": 5.2102, "step": 713 }, { "epoch": 0.03842014636246233, "grad_norm": 1.9588755369186401, "learning_rate": 4.981862201135923e-05, "loss": 4.9641, "step": 714 }, { "epoch": 0.0384739560912613, "grad_norm": 2.4244673252105713, "learning_rate": 4.9818113498672656e-05, "loss": 4.5964, "step": 715 }, { "epoch": 0.03852776582006027, "grad_norm": 1.4753373861312866, "learning_rate": 4.981760427675115e-05, "loss": 4.9358, "step": 716 }, { "epoch": 0.038581575548859236, "grad_norm": 1.8416132926940918, "learning_rate": 4.9817094345609275e-05, "loss": 4.8227, "step": 717 }, { "epoch": 0.0386353852776582, "grad_norm": 1.6463648080825806, "learning_rate": 4.9816583705261574e-05, "loss": 4.644, "step": 718 }, { "epoch": 0.03868919500645717, "grad_norm": 1.307604193687439, "learning_rate": 4.9816072355722676e-05, "loss": 4.79, "step": 719 }, { "epoch": 0.03874300473525613, "grad_norm": 3.2848517894744873, "learning_rate": 4.981556029700717e-05, "loss": 4.8733, "step": 720 }, { "epoch": 0.0387968144640551, "grad_norm": 1.6936008930206299, "learning_rate": 4.9815047529129703e-05, "loss": 4.8367, "step": 721 }, { "epoch": 0.038850624192854066, "grad_norm": 2.0140790939331055, "learning_rate": 4.981453405210492e-05, "loss": 5.0575, "step": 722 }, { "epoch": 0.038904433921653034, "grad_norm": 1.6896440982818604, "learning_rate": 4.981401986594749e-05, "loss": 4.6985, "step": 723 }, { "epoch": 0.038958243650452, "grad_norm": 1.5817283391952515, "learning_rate": 4.981350497067213e-05, "loss": 4.759, "step": 724 }, { "epoch": 0.03901205337925097, "grad_norm": 1.7081702947616577, "learning_rate": 4.9812989366293525e-05, "loss": 5.0183, "step": 725 }, { "epoch": 0.039065863108049936, "grad_norm": 1.2891783714294434, "learning_rate": 4.981247305282643e-05, "loss": 5.0767, "step": 726 }, { "epoch": 0.039119672836848904, "grad_norm": 1.5460010766983032, "learning_rate": 4.9811956030285585e-05, "loss": 4.9333, "step": 727 }, { "epoch": 0.03917348256564787, "grad_norm": 1.3575879335403442, "learning_rate": 4.981143829868578e-05, "loss": 5.1645, "step": 728 }, { "epoch": 0.03922729229444684, "grad_norm": 1.8726423978805542, "learning_rate": 4.9810919858041794e-05, "loss": 4.913, "step": 729 }, { "epoch": 0.0392811020232458, "grad_norm": 1.8550007343292236, "learning_rate": 4.981040070836846e-05, "loss": 5.015, "step": 730 }, { "epoch": 0.03933491175204477, "grad_norm": 1.7242751121520996, "learning_rate": 4.980988084968061e-05, "loss": 4.8664, "step": 731 }, { "epoch": 0.039388721480843734, "grad_norm": 1.466747760772705, "learning_rate": 4.980936028199309e-05, "loss": 4.9357, "step": 732 }, { "epoch": 0.0394425312096427, "grad_norm": 1.1884678602218628, "learning_rate": 4.9808839005320786e-05, "loss": 4.7965, "step": 733 }, { "epoch": 0.03949634093844167, "grad_norm": 1.2931418418884277, "learning_rate": 4.980831701967858e-05, "loss": 4.8358, "step": 734 }, { "epoch": 0.03955015066724064, "grad_norm": 1.667789340019226, "learning_rate": 4.980779432508141e-05, "loss": 4.8838, "step": 735 }, { "epoch": 0.039603960396039604, "grad_norm": 1.5939857959747314, "learning_rate": 4.9807270921544204e-05, "loss": 4.9752, "step": 736 }, { "epoch": 0.03965777012483857, "grad_norm": 1.912355661392212, "learning_rate": 4.980674680908192e-05, "loss": 4.8485, "step": 737 }, { "epoch": 0.03971157985363754, "grad_norm": 1.3926721811294556, "learning_rate": 4.980622198770952e-05, "loss": 5.0321, "step": 738 }, { "epoch": 0.03976538958243651, "grad_norm": 2.1192476749420166, "learning_rate": 4.980569645744203e-05, "loss": 5.0083, "step": 739 }, { "epoch": 0.039819199311235474, "grad_norm": 1.8096246719360352, "learning_rate": 4.980517021829446e-05, "loss": 5.128, "step": 740 }, { "epoch": 0.039873009040034435, "grad_norm": 1.3661762475967407, "learning_rate": 4.980464327028183e-05, "loss": 5.0778, "step": 741 }, { "epoch": 0.0399268187688334, "grad_norm": 1.7024428844451904, "learning_rate": 4.980411561341922e-05, "loss": 4.7925, "step": 742 }, { "epoch": 0.03998062849763237, "grad_norm": 1.3257160186767578, "learning_rate": 4.9803587247721694e-05, "loss": 4.9929, "step": 743 }, { "epoch": 0.04003443822643134, "grad_norm": 1.2613685131072998, "learning_rate": 4.980305817320436e-05, "loss": 4.8451, "step": 744 }, { "epoch": 0.040088247955230305, "grad_norm": 2.1951704025268555, "learning_rate": 4.980252838988234e-05, "loss": 4.97, "step": 745 }, { "epoch": 0.04014205768402927, "grad_norm": 1.5771291255950928, "learning_rate": 4.980199789777077e-05, "loss": 4.8453, "step": 746 }, { "epoch": 0.04019586741282824, "grad_norm": 1.108168363571167, "learning_rate": 4.980146669688481e-05, "loss": 4.8853, "step": 747 }, { "epoch": 0.04024967714162721, "grad_norm": 1.300629734992981, "learning_rate": 4.980093478723964e-05, "loss": 4.8114, "step": 748 }, { "epoch": 0.040303486870426175, "grad_norm": 1.9691987037658691, "learning_rate": 4.980040216885046e-05, "loss": 4.8994, "step": 749 }, { "epoch": 0.04035729659922514, "grad_norm": 1.965375304222107, "learning_rate": 4.979986884173249e-05, "loss": 5.0384, "step": 750 }, { "epoch": 0.04041110632802411, "grad_norm": 1.5656206607818604, "learning_rate": 4.979933480590097e-05, "loss": 4.9178, "step": 751 }, { "epoch": 0.04046491605682307, "grad_norm": 1.087268590927124, "learning_rate": 4.9798800061371164e-05, "loss": 4.6466, "step": 752 }, { "epoch": 0.04051872578562204, "grad_norm": 1.196604609489441, "learning_rate": 4.979826460815835e-05, "loss": 4.9199, "step": 753 }, { "epoch": 0.040572535514421006, "grad_norm": 1.4755371809005737, "learning_rate": 4.9797728446277844e-05, "loss": 4.7843, "step": 754 }, { "epoch": 0.04062634524321997, "grad_norm": 2.1486434936523438, "learning_rate": 4.979719157574495e-05, "loss": 4.8019, "step": 755 }, { "epoch": 0.04068015497201894, "grad_norm": 1.9178686141967773, "learning_rate": 4.979665399657502e-05, "loss": 4.6902, "step": 756 }, { "epoch": 0.04073396470081791, "grad_norm": 2.3280725479125977, "learning_rate": 4.979611570878341e-05, "loss": 4.9726, "step": 757 }, { "epoch": 0.040787774429616876, "grad_norm": 1.5596811771392822, "learning_rate": 4.97955767123855e-05, "loss": 4.9366, "step": 758 }, { "epoch": 0.04084158415841584, "grad_norm": 2.030935525894165, "learning_rate": 4.979503700739671e-05, "loss": 5.0328, "step": 759 }, { "epoch": 0.04089539388721481, "grad_norm": 2.026083469390869, "learning_rate": 4.979449659383245e-05, "loss": 4.9533, "step": 760 }, { "epoch": 0.04094920361601378, "grad_norm": 1.6690484285354614, "learning_rate": 4.979395547170818e-05, "loss": 4.7809, "step": 761 }, { "epoch": 0.04100301334481274, "grad_norm": 1.7131123542785645, "learning_rate": 4.979341364103933e-05, "loss": 4.7734, "step": 762 }, { "epoch": 0.041056823073611706, "grad_norm": 1.5212644338607788, "learning_rate": 4.979287110184142e-05, "loss": 5.0644, "step": 763 }, { "epoch": 0.041110632802410674, "grad_norm": 1.118080496788025, "learning_rate": 4.9792327854129926e-05, "loss": 4.8914, "step": 764 }, { "epoch": 0.04116444253120964, "grad_norm": 2.167874574661255, "learning_rate": 4.9791783897920396e-05, "loss": 4.7214, "step": 765 }, { "epoch": 0.04121825226000861, "grad_norm": 2.3025479316711426, "learning_rate": 4.979123923322836e-05, "loss": 4.8889, "step": 766 }, { "epoch": 0.041272061988807576, "grad_norm": 1.4171528816223145, "learning_rate": 4.979069386006938e-05, "loss": 5.2364, "step": 767 }, { "epoch": 0.041325871717606544, "grad_norm": 1.560145616531372, "learning_rate": 4.979014777845906e-05, "loss": 5.0198, "step": 768 }, { "epoch": 0.04137968144640551, "grad_norm": 1.2893590927124023, "learning_rate": 4.978960098841299e-05, "loss": 4.6095, "step": 769 }, { "epoch": 0.04143349117520448, "grad_norm": 1.520357370376587, "learning_rate": 4.97890534899468e-05, "loss": 4.9887, "step": 770 }, { "epoch": 0.041487300904003446, "grad_norm": 1.667345404624939, "learning_rate": 4.9788505283076134e-05, "loss": 4.6547, "step": 771 }, { "epoch": 0.041541110632802414, "grad_norm": 1.4598151445388794, "learning_rate": 4.978795636781667e-05, "loss": 4.3572, "step": 772 }, { "epoch": 0.041594920361601374, "grad_norm": 1.1903170347213745, "learning_rate": 4.978740674418407e-05, "loss": 5.0662, "step": 773 }, { "epoch": 0.04164873009040034, "grad_norm": 1.9402356147766113, "learning_rate": 4.9786856412194065e-05, "loss": 5.0811, "step": 774 }, { "epoch": 0.04170253981919931, "grad_norm": 2.2015109062194824, "learning_rate": 4.978630537186237e-05, "loss": 4.8838, "step": 775 }, { "epoch": 0.04175634954799828, "grad_norm": 1.8728359937667847, "learning_rate": 4.978575362320473e-05, "loss": 4.744, "step": 776 }, { "epoch": 0.041810159276797244, "grad_norm": 1.7112596035003662, "learning_rate": 4.9785201166236926e-05, "loss": 5.0757, "step": 777 }, { "epoch": 0.04186396900559621, "grad_norm": 2.117769479751587, "learning_rate": 4.9784648000974734e-05, "loss": 4.9195, "step": 778 }, { "epoch": 0.04191777873439518, "grad_norm": 2.0756173133850098, "learning_rate": 4.9784094127433966e-05, "loss": 4.518, "step": 779 }, { "epoch": 0.04197158846319415, "grad_norm": 1.3620108366012573, "learning_rate": 4.978353954563045e-05, "loss": 4.9521, "step": 780 }, { "epoch": 0.042025398191993114, "grad_norm": 1.361369013786316, "learning_rate": 4.9782984255580026e-05, "loss": 5.0183, "step": 781 }, { "epoch": 0.04207920792079208, "grad_norm": 1.8134820461273193, "learning_rate": 4.978242825729857e-05, "loss": 5.0405, "step": 782 }, { "epoch": 0.04213301764959105, "grad_norm": 2.0688636302948, "learning_rate": 4.9781871550801984e-05, "loss": 4.9376, "step": 783 }, { "epoch": 0.04218682737839001, "grad_norm": 1.321933627128601, "learning_rate": 4.978131413610616e-05, "loss": 5.0601, "step": 784 }, { "epoch": 0.04224063710718898, "grad_norm": 1.9919722080230713, "learning_rate": 4.9780756013227025e-05, "loss": 4.6101, "step": 785 }, { "epoch": 0.042294446835987945, "grad_norm": 2.165909767150879, "learning_rate": 4.9780197182180544e-05, "loss": 4.7275, "step": 786 }, { "epoch": 0.04234825656478691, "grad_norm": 2.316189765930176, "learning_rate": 4.977963764298267e-05, "loss": 4.726, "step": 787 }, { "epoch": 0.04240206629358588, "grad_norm": 2.0047104358673096, "learning_rate": 4.977907739564941e-05, "loss": 4.9013, "step": 788 }, { "epoch": 0.04245587602238485, "grad_norm": 1.9033191204071045, "learning_rate": 4.9778516440196756e-05, "loss": 4.8987, "step": 789 }, { "epoch": 0.042509685751183815, "grad_norm": 1.870139718055725, "learning_rate": 4.977795477664075e-05, "loss": 5.0828, "step": 790 }, { "epoch": 0.04256349547998278, "grad_norm": 1.8644030094146729, "learning_rate": 4.9777392404997454e-05, "loss": 4.7167, "step": 791 }, { "epoch": 0.04261730520878175, "grad_norm": 1.6715723276138306, "learning_rate": 4.977682932528291e-05, "loss": 4.7661, "step": 792 }, { "epoch": 0.04267111493758072, "grad_norm": 1.6323878765106201, "learning_rate": 4.977626553751324e-05, "loss": 4.4519, "step": 793 }, { "epoch": 0.04272492466637968, "grad_norm": 1.4247163534164429, "learning_rate": 4.9775701041704536e-05, "loss": 4.9611, "step": 794 }, { "epoch": 0.042778734395178646, "grad_norm": 1.7790476083755493, "learning_rate": 4.9775135837872936e-05, "loss": 4.7287, "step": 795 }, { "epoch": 0.04283254412397761, "grad_norm": 1.5644526481628418, "learning_rate": 4.977456992603458e-05, "loss": 4.8303, "step": 796 }, { "epoch": 0.04288635385277658, "grad_norm": 2.0215752124786377, "learning_rate": 4.9774003306205666e-05, "loss": 4.8687, "step": 797 }, { "epoch": 0.04294016358157555, "grad_norm": 1.3885631561279297, "learning_rate": 4.977343597840237e-05, "loss": 4.7474, "step": 798 }, { "epoch": 0.042993973310374516, "grad_norm": 2.7508318424224854, "learning_rate": 4.97728679426409e-05, "loss": 5.1027, "step": 799 }, { "epoch": 0.04304778303917348, "grad_norm": 1.680391550064087, "learning_rate": 4.97722991989375e-05, "loss": 4.8234, "step": 800 }, { "epoch": 0.04310159276797245, "grad_norm": 1.5549778938293457, "learning_rate": 4.9771729747308413e-05, "loss": 4.589, "step": 801 }, { "epoch": 0.04315540249677142, "grad_norm": 1.4433304071426392, "learning_rate": 4.977115958776992e-05, "loss": 4.9641, "step": 802 }, { "epoch": 0.043209212225570386, "grad_norm": 1.3612568378448486, "learning_rate": 4.977058872033832e-05, "loss": 4.7738, "step": 803 }, { "epoch": 0.04326302195436935, "grad_norm": 1.6703213453292847, "learning_rate": 4.9770017145029916e-05, "loss": 4.7634, "step": 804 }, { "epoch": 0.043316831683168314, "grad_norm": 1.2385430335998535, "learning_rate": 4.976944486186104e-05, "loss": 4.8172, "step": 805 }, { "epoch": 0.04337064141196728, "grad_norm": 2.3732781410217285, "learning_rate": 4.9768871870848056e-05, "loss": 4.5485, "step": 806 }, { "epoch": 0.04342445114076625, "grad_norm": 1.4055736064910889, "learning_rate": 4.976829817200733e-05, "loss": 4.9428, "step": 807 }, { "epoch": 0.043478260869565216, "grad_norm": 1.6978334188461304, "learning_rate": 4.9767723765355265e-05, "loss": 4.9847, "step": 808 }, { "epoch": 0.043532070598364184, "grad_norm": 1.7165700197219849, "learning_rate": 4.976714865090827e-05, "loss": 5.0038, "step": 809 }, { "epoch": 0.04358588032716315, "grad_norm": 1.6468204259872437, "learning_rate": 4.976657282868278e-05, "loss": 4.9994, "step": 810 }, { "epoch": 0.04363969005596212, "grad_norm": 1.09394109249115, "learning_rate": 4.976599629869526e-05, "loss": 4.9111, "step": 811 }, { "epoch": 0.043693499784761086, "grad_norm": 1.5237363576889038, "learning_rate": 4.9765419060962176e-05, "loss": 5.0021, "step": 812 }, { "epoch": 0.043747309513560054, "grad_norm": 1.6850543022155762, "learning_rate": 4.9764841115500024e-05, "loss": 4.8624, "step": 813 }, { "epoch": 0.04380111924235902, "grad_norm": 1.2362726926803589, "learning_rate": 4.976426246232533e-05, "loss": 4.7742, "step": 814 }, { "epoch": 0.04385492897115799, "grad_norm": 1.3611111640930176, "learning_rate": 4.976368310145462e-05, "loss": 5.1865, "step": 815 }, { "epoch": 0.04390873869995695, "grad_norm": 1.3782706260681152, "learning_rate": 4.9763103032904444e-05, "loss": 4.9326, "step": 816 }, { "epoch": 0.04396254842875592, "grad_norm": 1.2649259567260742, "learning_rate": 4.9762522256691393e-05, "loss": 4.906, "step": 817 }, { "epoch": 0.044016358157554884, "grad_norm": 1.4445815086364746, "learning_rate": 4.976194077283206e-05, "loss": 5.0738, "step": 818 }, { "epoch": 0.04407016788635385, "grad_norm": 0.998049259185791, "learning_rate": 4.9761358581343065e-05, "loss": 4.8277, "step": 819 }, { "epoch": 0.04412397761515282, "grad_norm": 1.5238089561462402, "learning_rate": 4.976077568224104e-05, "loss": 4.8798, "step": 820 }, { "epoch": 0.04417778734395179, "grad_norm": 2.0193283557891846, "learning_rate": 4.9760192075542643e-05, "loss": 4.8606, "step": 821 }, { "epoch": 0.044231597072750754, "grad_norm": 1.5305333137512207, "learning_rate": 4.9759607761264556e-05, "loss": 4.926, "step": 822 }, { "epoch": 0.04428540680154972, "grad_norm": 1.3391433954238892, "learning_rate": 4.975902273942347e-05, "loss": 4.8993, "step": 823 }, { "epoch": 0.04433921653034869, "grad_norm": 1.5792328119277954, "learning_rate": 4.9758437010036116e-05, "loss": 5.1673, "step": 824 }, { "epoch": 0.04439302625914766, "grad_norm": 1.5278162956237793, "learning_rate": 4.975785057311921e-05, "loss": 4.7152, "step": 825 }, { "epoch": 0.04444683598794662, "grad_norm": 1.782726526260376, "learning_rate": 4.9757263428689545e-05, "loss": 4.8166, "step": 826 }, { "epoch": 0.044500645716745585, "grad_norm": 1.271550178527832, "learning_rate": 4.9756675576763866e-05, "loss": 4.8943, "step": 827 }, { "epoch": 0.04455445544554455, "grad_norm": 1.6328858137130737, "learning_rate": 4.975608701735899e-05, "loss": 4.9654, "step": 828 }, { "epoch": 0.04460826517434352, "grad_norm": 1.4963363409042358, "learning_rate": 4.9755497750491744e-05, "loss": 4.9383, "step": 829 }, { "epoch": 0.04466207490314249, "grad_norm": 1.300356149673462, "learning_rate": 4.975490777617894e-05, "loss": 4.8786, "step": 830 }, { "epoch": 0.044715884631941455, "grad_norm": 1.5126612186431885, "learning_rate": 4.9754317094437464e-05, "loss": 4.9488, "step": 831 }, { "epoch": 0.04476969436074042, "grad_norm": 1.9717572927474976, "learning_rate": 4.9753725705284185e-05, "loss": 4.9196, "step": 832 }, { "epoch": 0.04482350408953939, "grad_norm": 2.1627118587493896, "learning_rate": 4.9753133608736e-05, "loss": 5.0256, "step": 833 }, { "epoch": 0.04487731381833836, "grad_norm": 1.5359638929367065, "learning_rate": 4.9752540804809843e-05, "loss": 4.6429, "step": 834 }, { "epoch": 0.044931123547137325, "grad_norm": 1.9803013801574707, "learning_rate": 4.975194729352264e-05, "loss": 4.4898, "step": 835 }, { "epoch": 0.04498493327593629, "grad_norm": 1.1608695983886719, "learning_rate": 4.9751353074891364e-05, "loss": 4.8894, "step": 836 }, { "epoch": 0.04503874300473525, "grad_norm": 1.8342170715332031, "learning_rate": 4.9750758148932986e-05, "loss": 4.597, "step": 837 }, { "epoch": 0.04509255273353422, "grad_norm": 1.1319825649261475, "learning_rate": 4.975016251566451e-05, "loss": 4.7819, "step": 838 }, { "epoch": 0.04514636246233319, "grad_norm": 1.0757496356964111, "learning_rate": 4.974956617510297e-05, "loss": 4.8296, "step": 839 }, { "epoch": 0.045200172191132156, "grad_norm": 2.2344579696655273, "learning_rate": 4.974896912726539e-05, "loss": 4.7881, "step": 840 }, { "epoch": 0.04525398191993112, "grad_norm": 1.653883457183838, "learning_rate": 4.9748371372168835e-05, "loss": 4.7727, "step": 841 }, { "epoch": 0.04530779164873009, "grad_norm": 1.7113744020462036, "learning_rate": 4.97477729098304e-05, "loss": 4.9265, "step": 842 }, { "epoch": 0.04536160137752906, "grad_norm": 2.0007994174957275, "learning_rate": 4.974717374026717e-05, "loss": 4.7955, "step": 843 }, { "epoch": 0.045415411106328026, "grad_norm": 2.006582498550415, "learning_rate": 4.974657386349628e-05, "loss": 5.1408, "step": 844 }, { "epoch": 0.04546922083512699, "grad_norm": 1.6149383783340454, "learning_rate": 4.974597327953487e-05, "loss": 4.5941, "step": 845 }, { "epoch": 0.04552303056392596, "grad_norm": 1.7145549058914185, "learning_rate": 4.9745371988400104e-05, "loss": 4.9829, "step": 846 }, { "epoch": 0.04557684029272493, "grad_norm": 1.2621641159057617, "learning_rate": 4.9744769990109166e-05, "loss": 5.0718, "step": 847 }, { "epoch": 0.04563065002152389, "grad_norm": 1.8193217515945435, "learning_rate": 4.9744167284679256e-05, "loss": 4.7038, "step": 848 }, { "epoch": 0.045684459750322856, "grad_norm": 1.872920274734497, "learning_rate": 4.9743563872127594e-05, "loss": 5.0881, "step": 849 }, { "epoch": 0.045738269479121824, "grad_norm": 2.109140634536743, "learning_rate": 4.974295975247143e-05, "loss": 4.8661, "step": 850 }, { "epoch": 0.04579207920792079, "grad_norm": 1.9085631370544434, "learning_rate": 4.974235492572803e-05, "loss": 4.5966, "step": 851 }, { "epoch": 0.04584588893671976, "grad_norm": 1.3562718629837036, "learning_rate": 4.9741749391914676e-05, "loss": 4.9784, "step": 852 }, { "epoch": 0.045899698665518726, "grad_norm": 1.4286797046661377, "learning_rate": 4.974114315104867e-05, "loss": 4.841, "step": 853 }, { "epoch": 0.045953508394317694, "grad_norm": 1.0688761472702026, "learning_rate": 4.9740536203147335e-05, "loss": 4.8311, "step": 854 }, { "epoch": 0.04600731812311666, "grad_norm": 1.5745291709899902, "learning_rate": 4.973992854822803e-05, "loss": 5.059, "step": 855 }, { "epoch": 0.04606112785191563, "grad_norm": 1.861985206604004, "learning_rate": 4.97393201863081e-05, "loss": 4.8831, "step": 856 }, { "epoch": 0.046114937580714596, "grad_norm": 2.377424478530884, "learning_rate": 4.973871111740495e-05, "loss": 4.5412, "step": 857 }, { "epoch": 0.04616874730951356, "grad_norm": 1.5939232110977173, "learning_rate": 4.9738101341535956e-05, "loss": 4.9711, "step": 858 }, { "epoch": 0.046222557038312524, "grad_norm": 1.584129810333252, "learning_rate": 4.973749085871858e-05, "loss": 5.0297, "step": 859 }, { "epoch": 0.04627636676711149, "grad_norm": 2.7065653800964355, "learning_rate": 4.973687966897025e-05, "loss": 4.8455, "step": 860 }, { "epoch": 0.04633017649591046, "grad_norm": 1.4833612442016602, "learning_rate": 4.973626777230843e-05, "loss": 5.0149, "step": 861 }, { "epoch": 0.04638398622470943, "grad_norm": 1.344456672668457, "learning_rate": 4.973565516875061e-05, "loss": 4.8219, "step": 862 }, { "epoch": 0.046437795953508394, "grad_norm": 1.3562572002410889, "learning_rate": 4.9735041858314304e-05, "loss": 5.0777, "step": 863 }, { "epoch": 0.04649160568230736, "grad_norm": 1.1706032752990723, "learning_rate": 4.973442784101702e-05, "loss": 5.336, "step": 864 }, { "epoch": 0.04654541541110633, "grad_norm": 1.6459124088287354, "learning_rate": 4.9733813116876314e-05, "loss": 4.7788, "step": 865 }, { "epoch": 0.0465992251399053, "grad_norm": 1.5851339101791382, "learning_rate": 4.973319768590976e-05, "loss": 4.8322, "step": 866 }, { "epoch": 0.046653034868704264, "grad_norm": 1.0897870063781738, "learning_rate": 4.973258154813495e-05, "loss": 4.7484, "step": 867 }, { "epoch": 0.04670684459750323, "grad_norm": 1.7666946649551392, "learning_rate": 4.973196470356947e-05, "loss": 4.7613, "step": 868 }, { "epoch": 0.04676065432630219, "grad_norm": 1.9141474962234497, "learning_rate": 4.973134715223097e-05, "loss": 4.9426, "step": 869 }, { "epoch": 0.04681446405510116, "grad_norm": 1.3403170108795166, "learning_rate": 4.973072889413708e-05, "loss": 4.8498, "step": 870 }, { "epoch": 0.04686827378390013, "grad_norm": 1.258246660232544, "learning_rate": 4.973010992930548e-05, "loss": 5.0273, "step": 871 }, { "epoch": 0.046922083512699095, "grad_norm": 1.9267394542694092, "learning_rate": 4.972949025775385e-05, "loss": 4.7066, "step": 872 }, { "epoch": 0.04697589324149806, "grad_norm": 1.6910207271575928, "learning_rate": 4.972886987949991e-05, "loss": 4.9428, "step": 873 }, { "epoch": 0.04702970297029703, "grad_norm": 1.8152607679367065, "learning_rate": 4.972824879456137e-05, "loss": 4.9241, "step": 874 }, { "epoch": 0.047083512699096, "grad_norm": 1.9537076950073242, "learning_rate": 4.9727627002956e-05, "loss": 4.9509, "step": 875 }, { "epoch": 0.047137322427894965, "grad_norm": 1.5453553199768066, "learning_rate": 4.972700450470156e-05, "loss": 4.886, "step": 876 }, { "epoch": 0.04719113215669393, "grad_norm": 1.3859211206436157, "learning_rate": 4.9726381299815836e-05, "loss": 4.9394, "step": 877 }, { "epoch": 0.0472449418854929, "grad_norm": 1.509495496749878, "learning_rate": 4.9725757388316644e-05, "loss": 4.9909, "step": 878 }, { "epoch": 0.04729875161429187, "grad_norm": 1.606084942817688, "learning_rate": 4.972513277022181e-05, "loss": 5.0976, "step": 879 }, { "epoch": 0.04735256134309083, "grad_norm": 1.5201133489608765, "learning_rate": 4.972450744554917e-05, "loss": 4.7637, "step": 880 }, { "epoch": 0.047406371071889795, "grad_norm": 1.915410041809082, "learning_rate": 4.972388141431663e-05, "loss": 4.6055, "step": 881 }, { "epoch": 0.04746018080068876, "grad_norm": 2.166684627532959, "learning_rate": 4.972325467654204e-05, "loss": 5.0266, "step": 882 }, { "epoch": 0.04751399052948773, "grad_norm": 1.4601341485977173, "learning_rate": 4.972262723224335e-05, "loss": 4.696, "step": 883 }, { "epoch": 0.0475678002582867, "grad_norm": 2.4095897674560547, "learning_rate": 4.972199908143845e-05, "loss": 4.8928, "step": 884 }, { "epoch": 0.047621609987085665, "grad_norm": 1.7098472118377686, "learning_rate": 4.972137022414532e-05, "loss": 4.59, "step": 885 }, { "epoch": 0.04767541971588463, "grad_norm": 1.5252553224563599, "learning_rate": 4.9720740660381915e-05, "loss": 5.1871, "step": 886 }, { "epoch": 0.0477292294446836, "grad_norm": 1.528599739074707, "learning_rate": 4.9720110390166245e-05, "loss": 4.6511, "step": 887 }, { "epoch": 0.04778303917348257, "grad_norm": 1.122645378112793, "learning_rate": 4.97194794135163e-05, "loss": 5.1317, "step": 888 }, { "epoch": 0.047836848902281535, "grad_norm": 2.2038276195526123, "learning_rate": 4.971884773045012e-05, "loss": 4.7559, "step": 889 }, { "epoch": 0.047890658631080496, "grad_norm": 1.811598300933838, "learning_rate": 4.9718215340985766e-05, "loss": 4.9503, "step": 890 }, { "epoch": 0.047944468359879464, "grad_norm": 1.6739892959594727, "learning_rate": 4.971758224514129e-05, "loss": 5.2054, "step": 891 }, { "epoch": 0.04799827808867843, "grad_norm": 1.7360442876815796, "learning_rate": 4.971694844293481e-05, "loss": 5.0734, "step": 892 }, { "epoch": 0.0480520878174774, "grad_norm": 1.7363660335540771, "learning_rate": 4.971631393438441e-05, "loss": 4.9489, "step": 893 }, { "epoch": 0.048105897546276366, "grad_norm": 1.743390440940857, "learning_rate": 4.971567871950824e-05, "loss": 5.1359, "step": 894 }, { "epoch": 0.048159707275075334, "grad_norm": 1.4915201663970947, "learning_rate": 4.971504279832446e-05, "loss": 4.7071, "step": 895 }, { "epoch": 0.0482135170038743, "grad_norm": 1.1771512031555176, "learning_rate": 4.9714406170851224e-05, "loss": 4.9806, "step": 896 }, { "epoch": 0.04826732673267327, "grad_norm": 1.100136637687683, "learning_rate": 4.9713768837106735e-05, "loss": 4.9149, "step": 897 }, { "epoch": 0.048321136461472236, "grad_norm": 1.5125465393066406, "learning_rate": 4.971313079710921e-05, "loss": 4.8168, "step": 898 }, { "epoch": 0.048374946190271204, "grad_norm": 1.564544677734375, "learning_rate": 4.971249205087687e-05, "loss": 4.669, "step": 899 }, { "epoch": 0.04842875591907017, "grad_norm": 1.8596314191818237, "learning_rate": 4.9711852598427974e-05, "loss": 4.8185, "step": 900 }, { "epoch": 0.04848256564786913, "grad_norm": 1.2142059803009033, "learning_rate": 4.9711212439780806e-05, "loss": 4.9754, "step": 901 }, { "epoch": 0.0485363753766681, "grad_norm": 1.1393247842788696, "learning_rate": 4.9710571574953644e-05, "loss": 4.7235, "step": 902 }, { "epoch": 0.04859018510546707, "grad_norm": 1.6514875888824463, "learning_rate": 4.9709930003964824e-05, "loss": 5.1421, "step": 903 }, { "epoch": 0.048643994834266034, "grad_norm": 1.2048866748809814, "learning_rate": 4.9709287726832656e-05, "loss": 4.8283, "step": 904 }, { "epoch": 0.048697804563065, "grad_norm": 1.5762429237365723, "learning_rate": 4.97086447435755e-05, "loss": 4.8344, "step": 905 }, { "epoch": 0.04875161429186397, "grad_norm": 1.2666937112808228, "learning_rate": 4.970800105421174e-05, "loss": 4.7272, "step": 906 }, { "epoch": 0.04880542402066294, "grad_norm": 1.2113319635391235, "learning_rate": 4.970735665875977e-05, "loss": 5.2238, "step": 907 }, { "epoch": 0.048859233749461904, "grad_norm": 1.2327512502670288, "learning_rate": 4.9706711557238e-05, "loss": 4.8233, "step": 908 }, { "epoch": 0.04891304347826087, "grad_norm": 1.4799370765686035, "learning_rate": 4.970606574966486e-05, "loss": 4.9069, "step": 909 }, { "epoch": 0.04896685320705984, "grad_norm": 2.0211238861083984, "learning_rate": 4.9705419236058825e-05, "loss": 4.7103, "step": 910 }, { "epoch": 0.04902066293585881, "grad_norm": 1.0852103233337402, "learning_rate": 4.970477201643835e-05, "loss": 4.9582, "step": 911 }, { "epoch": 0.04907447266465777, "grad_norm": 1.3374834060668945, "learning_rate": 4.970412409082194e-05, "loss": 4.9114, "step": 912 }, { "epoch": 0.049128282393456735, "grad_norm": 1.685703992843628, "learning_rate": 4.970347545922811e-05, "loss": 4.9603, "step": 913 }, { "epoch": 0.0491820921222557, "grad_norm": 1.4630954265594482, "learning_rate": 4.9702826121675394e-05, "loss": 4.906, "step": 914 }, { "epoch": 0.04923590185105467, "grad_norm": 1.6866472959518433, "learning_rate": 4.9702176078182355e-05, "loss": 4.9131, "step": 915 }, { "epoch": 0.04928971157985364, "grad_norm": 2.1497786045074463, "learning_rate": 4.9701525328767565e-05, "loss": 4.6141, "step": 916 }, { "epoch": 0.049343521308652605, "grad_norm": 1.8442730903625488, "learning_rate": 4.970087387344962e-05, "loss": 4.8117, "step": 917 }, { "epoch": 0.04939733103745157, "grad_norm": 1.4412180185317993, "learning_rate": 4.970022171224713e-05, "loss": 4.5465, "step": 918 }, { "epoch": 0.04945114076625054, "grad_norm": 2.373248338699341, "learning_rate": 4.9699568845178745e-05, "loss": 4.7436, "step": 919 }, { "epoch": 0.04950495049504951, "grad_norm": 1.1186795234680176, "learning_rate": 4.9698915272263115e-05, "loss": 5.057, "step": 920 }, { "epoch": 0.049558760223848475, "grad_norm": 1.7192792892456055, "learning_rate": 4.969826099351892e-05, "loss": 5.0168, "step": 921 }, { "epoch": 0.049612569952647435, "grad_norm": 1.8341070413589478, "learning_rate": 4.969760600896486e-05, "loss": 5.1259, "step": 922 }, { "epoch": 0.0496663796814464, "grad_norm": 1.4011660814285278, "learning_rate": 4.969695031861964e-05, "loss": 4.5515, "step": 923 }, { "epoch": 0.04972018941024537, "grad_norm": 1.547736406326294, "learning_rate": 4.969629392250201e-05, "loss": 4.857, "step": 924 }, { "epoch": 0.04977399913904434, "grad_norm": 1.2629419565200806, "learning_rate": 4.969563682063073e-05, "loss": 4.8906, "step": 925 }, { "epoch": 0.049827808867843305, "grad_norm": 1.8200627565383911, "learning_rate": 4.969497901302457e-05, "loss": 4.8366, "step": 926 }, { "epoch": 0.04988161859664227, "grad_norm": 2.1423022747039795, "learning_rate": 4.969432049970233e-05, "loss": 4.5352, "step": 927 }, { "epoch": 0.04993542832544124, "grad_norm": 2.126661777496338, "learning_rate": 4.9693661280682834e-05, "loss": 4.7406, "step": 928 }, { "epoch": 0.04998923805424021, "grad_norm": 1.3279283046722412, "learning_rate": 4.969300135598491e-05, "loss": 4.7297, "step": 929 }, { "epoch": 0.050043047783039175, "grad_norm": 1.4666976928710938, "learning_rate": 4.969234072562743e-05, "loss": 4.9002, "step": 930 }, { "epoch": 0.05009685751183814, "grad_norm": 2.3326447010040283, "learning_rate": 4.969167938962927e-05, "loss": 4.6476, "step": 931 }, { "epoch": 0.05015066724063711, "grad_norm": 1.4922353029251099, "learning_rate": 4.9691017348009316e-05, "loss": 5.0221, "step": 932 }, { "epoch": 0.05020447696943607, "grad_norm": 1.6657003164291382, "learning_rate": 4.96903546007865e-05, "loss": 5.0489, "step": 933 }, { "epoch": 0.05025828669823504, "grad_norm": 1.860287070274353, "learning_rate": 4.9689691147979754e-05, "loss": 4.9742, "step": 934 }, { "epoch": 0.050312096427034006, "grad_norm": 1.4964319467544556, "learning_rate": 4.9689026989608056e-05, "loss": 5.096, "step": 935 }, { "epoch": 0.050365906155832973, "grad_norm": 1.7472161054611206, "learning_rate": 4.9688362125690365e-05, "loss": 4.8606, "step": 936 }, { "epoch": 0.05041971588463194, "grad_norm": 1.7244573831558228, "learning_rate": 4.968769655624569e-05, "loss": 4.7873, "step": 937 }, { "epoch": 0.05047352561343091, "grad_norm": 1.5425204038619995, "learning_rate": 4.9687030281293044e-05, "loss": 5.0966, "step": 938 }, { "epoch": 0.050527335342229876, "grad_norm": 2.133435010910034, "learning_rate": 4.968636330085147e-05, "loss": 4.8585, "step": 939 }, { "epoch": 0.050581145071028843, "grad_norm": 2.3289616107940674, "learning_rate": 4.968569561494004e-05, "loss": 4.8006, "step": 940 }, { "epoch": 0.05063495479982781, "grad_norm": 2.5128896236419678, "learning_rate": 4.9685027223577826e-05, "loss": 4.5603, "step": 941 }, { "epoch": 0.05068876452862678, "grad_norm": 1.8513984680175781, "learning_rate": 4.9684358126783925e-05, "loss": 4.624, "step": 942 }, { "epoch": 0.050742574257425746, "grad_norm": 1.5204353332519531, "learning_rate": 4.968368832457747e-05, "loss": 5.0401, "step": 943 }, { "epoch": 0.05079638398622471, "grad_norm": 1.7166504859924316, "learning_rate": 4.968301781697758e-05, "loss": 4.7177, "step": 944 }, { "epoch": 0.050850193715023674, "grad_norm": 1.620910882949829, "learning_rate": 4.968234660400344e-05, "loss": 4.8925, "step": 945 }, { "epoch": 0.05090400344382264, "grad_norm": 1.0842963457107544, "learning_rate": 4.9681674685674226e-05, "loss": 4.7953, "step": 946 }, { "epoch": 0.05095781317262161, "grad_norm": 1.8361228704452515, "learning_rate": 4.968100206200913e-05, "loss": 4.9119, "step": 947 }, { "epoch": 0.05101162290142058, "grad_norm": 1.019968032836914, "learning_rate": 4.968032873302737e-05, "loss": 5.1016, "step": 948 }, { "epoch": 0.051065432630219544, "grad_norm": 1.1779258251190186, "learning_rate": 4.9679654698748214e-05, "loss": 5.1417, "step": 949 }, { "epoch": 0.05111924235901851, "grad_norm": 1.676164150238037, "learning_rate": 4.9678979959190896e-05, "loss": 5.3398, "step": 950 }, { "epoch": 0.05117305208781748, "grad_norm": 1.9394707679748535, "learning_rate": 4.967830451437471e-05, "loss": 4.768, "step": 951 }, { "epoch": 0.05122686181661645, "grad_norm": 1.391218900680542, "learning_rate": 4.9677628364318964e-05, "loss": 4.9647, "step": 952 }, { "epoch": 0.051280671545415414, "grad_norm": 1.7893587350845337, "learning_rate": 4.967695150904297e-05, "loss": 4.9178, "step": 953 }, { "epoch": 0.051334481274214375, "grad_norm": 1.6198859214782715, "learning_rate": 4.967627394856607e-05, "loss": 4.8699, "step": 954 }, { "epoch": 0.05138829100301334, "grad_norm": 1.112981915473938, "learning_rate": 4.967559568290764e-05, "loss": 5.0642, "step": 955 }, { "epoch": 0.05144210073181231, "grad_norm": 2.2996206283569336, "learning_rate": 4.967491671208705e-05, "loss": 4.3596, "step": 956 }, { "epoch": 0.05149591046061128, "grad_norm": 2.593120574951172, "learning_rate": 4.967423703612371e-05, "loss": 5.0576, "step": 957 }, { "epoch": 0.051549720189410245, "grad_norm": 2.396836042404175, "learning_rate": 4.9673556655037044e-05, "loss": 4.967, "step": 958 }, { "epoch": 0.05160352991820921, "grad_norm": 2.1214230060577393, "learning_rate": 4.9672875568846485e-05, "loss": 4.9488, "step": 959 }, { "epoch": 0.05165733964700818, "grad_norm": 1.729894757270813, "learning_rate": 4.967219377757152e-05, "loss": 4.7065, "step": 960 }, { "epoch": 0.05171114937580715, "grad_norm": 1.470828890800476, "learning_rate": 4.9671511281231605e-05, "loss": 4.7435, "step": 961 }, { "epoch": 0.051764959104606115, "grad_norm": 1.8497812747955322, "learning_rate": 4.9670828079846254e-05, "loss": 4.8993, "step": 962 }, { "epoch": 0.05181876883340508, "grad_norm": 1.1785638332366943, "learning_rate": 4.9670144173435e-05, "loss": 4.8382, "step": 963 }, { "epoch": 0.05187257856220405, "grad_norm": 2.4487972259521484, "learning_rate": 4.9669459562017376e-05, "loss": 4.6279, "step": 964 }, { "epoch": 0.05192638829100301, "grad_norm": 1.97324538230896, "learning_rate": 4.966877424561296e-05, "loss": 4.8581, "step": 965 }, { "epoch": 0.05198019801980198, "grad_norm": 2.3756558895111084, "learning_rate": 4.9668088224241314e-05, "loss": 5.1566, "step": 966 }, { "epoch": 0.052034007748600945, "grad_norm": 1.8861510753631592, "learning_rate": 4.9667401497922064e-05, "loss": 4.4112, "step": 967 }, { "epoch": 0.05208781747739991, "grad_norm": 1.4360586404800415, "learning_rate": 4.9666714066674824e-05, "loss": 4.6676, "step": 968 }, { "epoch": 0.05214162720619888, "grad_norm": 1.9599971771240234, "learning_rate": 4.966602593051924e-05, "loss": 5.0998, "step": 969 }, { "epoch": 0.05219543693499785, "grad_norm": 1.9721623659133911, "learning_rate": 4.9665337089474985e-05, "loss": 4.5234, "step": 970 }, { "epoch": 0.052249246663796815, "grad_norm": 1.3633387088775635, "learning_rate": 4.966464754356173e-05, "loss": 5.1375, "step": 971 }, { "epoch": 0.05230305639259578, "grad_norm": 1.2687429189682007, "learning_rate": 4.96639572927992e-05, "loss": 5.0335, "step": 972 }, { "epoch": 0.05235686612139475, "grad_norm": 1.2920266389846802, "learning_rate": 4.96632663372071e-05, "loss": 4.9512, "step": 973 }, { "epoch": 0.05241067585019372, "grad_norm": 1.7702308893203735, "learning_rate": 4.9662574676805187e-05, "loss": 4.8797, "step": 974 }, { "epoch": 0.052464485578992685, "grad_norm": 2.0714786052703857, "learning_rate": 4.966188231161322e-05, "loss": 4.9932, "step": 975 }, { "epoch": 0.052518295307791646, "grad_norm": 1.3765947818756104, "learning_rate": 4.966118924165099e-05, "loss": 4.6609, "step": 976 }, { "epoch": 0.05257210503659061, "grad_norm": 1.8855364322662354, "learning_rate": 4.9660495466938306e-05, "loss": 5.0428, "step": 977 }, { "epoch": 0.05262591476538958, "grad_norm": 1.1877306699752808, "learning_rate": 4.9659800987494986e-05, "loss": 4.909, "step": 978 }, { "epoch": 0.05267972449418855, "grad_norm": 2.8346328735351562, "learning_rate": 4.965910580334089e-05, "loss": 4.3377, "step": 979 }, { "epoch": 0.052733534222987516, "grad_norm": 1.2907280921936035, "learning_rate": 4.9658409914495866e-05, "loss": 4.8534, "step": 980 }, { "epoch": 0.05278734395178648, "grad_norm": 1.3595772981643677, "learning_rate": 4.9657713320979814e-05, "loss": 4.8716, "step": 981 }, { "epoch": 0.05284115368058545, "grad_norm": 1.95460844039917, "learning_rate": 4.9657016022812636e-05, "loss": 4.5335, "step": 982 }, { "epoch": 0.05289496340938442, "grad_norm": 1.3670434951782227, "learning_rate": 4.965631802001426e-05, "loss": 4.9263, "step": 983 }, { "epoch": 0.052948773138183386, "grad_norm": 2.1020588874816895, "learning_rate": 4.965561931260463e-05, "loss": 4.7628, "step": 984 }, { "epoch": 0.05300258286698235, "grad_norm": 1.9637948274612427, "learning_rate": 4.965491990060372e-05, "loss": 4.5593, "step": 985 }, { "epoch": 0.053056392595781314, "grad_norm": 1.5949708223342896, "learning_rate": 4.9654219784031506e-05, "loss": 5.1821, "step": 986 }, { "epoch": 0.05311020232458028, "grad_norm": 1.2044737339019775, "learning_rate": 4.965351896290801e-05, "loss": 4.86, "step": 987 }, { "epoch": 0.05316401205337925, "grad_norm": 1.2579950094223022, "learning_rate": 4.9652817437253254e-05, "loss": 5.0607, "step": 988 }, { "epoch": 0.053217821782178217, "grad_norm": 1.5311731100082397, "learning_rate": 4.9652115207087277e-05, "loss": 4.8828, "step": 989 }, { "epoch": 0.053271631510977184, "grad_norm": 1.9179375171661377, "learning_rate": 4.965141227243016e-05, "loss": 4.6017, "step": 990 }, { "epoch": 0.05332544123977615, "grad_norm": 1.5699071884155273, "learning_rate": 4.965070863330198e-05, "loss": 4.9129, "step": 991 }, { "epoch": 0.05337925096857512, "grad_norm": 1.2243192195892334, "learning_rate": 4.9650004289722854e-05, "loss": 4.6306, "step": 992 }, { "epoch": 0.05343306069737409, "grad_norm": 1.8911586999893188, "learning_rate": 4.9649299241712896e-05, "loss": 4.9349, "step": 993 }, { "epoch": 0.053486870426173054, "grad_norm": 1.739288568496704, "learning_rate": 4.964859348929228e-05, "loss": 5.0415, "step": 994 }, { "epoch": 0.05354068015497202, "grad_norm": 1.4640296697616577, "learning_rate": 4.9647887032481146e-05, "loss": 5.0446, "step": 995 }, { "epoch": 0.05359448988377099, "grad_norm": 1.5124188661575317, "learning_rate": 4.9647179871299706e-05, "loss": 5.0441, "step": 996 }, { "epoch": 0.05364829961256995, "grad_norm": 1.4288400411605835, "learning_rate": 4.9646472005768155e-05, "loss": 4.806, "step": 997 }, { "epoch": 0.05370210934136892, "grad_norm": 1.4656950235366821, "learning_rate": 4.964576343590672e-05, "loss": 4.7229, "step": 998 }, { "epoch": 0.053755919070167885, "grad_norm": 1.5252357721328735, "learning_rate": 4.964505416173566e-05, "loss": 4.8213, "step": 999 }, { "epoch": 0.05380972879896685, "grad_norm": 1.0574454069137573, "learning_rate": 4.964434418327524e-05, "loss": 4.8786, "step": 1000 }, { "epoch": 0.05386353852776582, "grad_norm": 1.5845154523849487, "learning_rate": 4.964363350054574e-05, "loss": 4.7972, "step": 1001 }, { "epoch": 0.05391734825656479, "grad_norm": 2.2165639400482178, "learning_rate": 4.964292211356749e-05, "loss": 5.0245, "step": 1002 }, { "epoch": 0.053971157985363755, "grad_norm": 1.1614166498184204, "learning_rate": 4.96422100223608e-05, "loss": 4.9817, "step": 1003 }, { "epoch": 0.05402496771416272, "grad_norm": 1.328840732574463, "learning_rate": 4.964149722694603e-05, "loss": 4.7362, "step": 1004 }, { "epoch": 0.05407877744296169, "grad_norm": 1.3992263078689575, "learning_rate": 4.964078372734355e-05, "loss": 4.9728, "step": 1005 }, { "epoch": 0.05413258717176066, "grad_norm": 1.6499184370040894, "learning_rate": 4.964006952357374e-05, "loss": 4.8223, "step": 1006 }, { "epoch": 0.05418639690055962, "grad_norm": 1.3189488649368286, "learning_rate": 4.9639354615657026e-05, "loss": 4.8834, "step": 1007 }, { "epoch": 0.054240206629358585, "grad_norm": 1.9297161102294922, "learning_rate": 4.9638639003613825e-05, "loss": 4.6669, "step": 1008 }, { "epoch": 0.05429401635815755, "grad_norm": 1.6997666358947754, "learning_rate": 4.9637922687464586e-05, "loss": 4.809, "step": 1009 }, { "epoch": 0.05434782608695652, "grad_norm": 1.5638378858566284, "learning_rate": 4.9637205667229794e-05, "loss": 4.6686, "step": 1010 }, { "epoch": 0.05440163581575549, "grad_norm": 1.2765657901763916, "learning_rate": 4.963648794292992e-05, "loss": 4.8496, "step": 1011 }, { "epoch": 0.054455445544554455, "grad_norm": 1.8709620237350464, "learning_rate": 4.96357695145855e-05, "loss": 4.8821, "step": 1012 }, { "epoch": 0.05450925527335342, "grad_norm": 2.0520358085632324, "learning_rate": 4.9635050382217036e-05, "loss": 4.8541, "step": 1013 }, { "epoch": 0.05456306500215239, "grad_norm": 1.5719847679138184, "learning_rate": 4.9634330545845096e-05, "loss": 4.9217, "step": 1014 }, { "epoch": 0.05461687473095136, "grad_norm": 1.9884194135665894, "learning_rate": 4.963361000549025e-05, "loss": 5.0051, "step": 1015 }, { "epoch": 0.054670684459750325, "grad_norm": 1.075584888458252, "learning_rate": 4.9632888761173084e-05, "loss": 4.8462, "step": 1016 }, { "epoch": 0.05472449418854929, "grad_norm": 2.167534351348877, "learning_rate": 4.963216681291422e-05, "loss": 4.6281, "step": 1017 }, { "epoch": 0.05477830391734825, "grad_norm": 2.0738253593444824, "learning_rate": 4.963144416073427e-05, "loss": 4.9805, "step": 1018 }, { "epoch": 0.05483211364614722, "grad_norm": 1.4299266338348389, "learning_rate": 4.9630720804653904e-05, "loss": 5.0411, "step": 1019 }, { "epoch": 0.05488592337494619, "grad_norm": 1.1498335599899292, "learning_rate": 4.962999674469378e-05, "loss": 4.9021, "step": 1020 }, { "epoch": 0.054939733103745156, "grad_norm": 1.8706825971603394, "learning_rate": 4.9629271980874605e-05, "loss": 4.981, "step": 1021 }, { "epoch": 0.05499354283254412, "grad_norm": 1.1545315980911255, "learning_rate": 4.962854651321707e-05, "loss": 4.6934, "step": 1022 }, { "epoch": 0.05504735256134309, "grad_norm": 1.170122742652893, "learning_rate": 4.962782034174193e-05, "loss": 4.9505, "step": 1023 }, { "epoch": 0.05510116229014206, "grad_norm": 1.3131943941116333, "learning_rate": 4.962709346646992e-05, "loss": 5.1652, "step": 1024 }, { "epoch": 0.055154972018941026, "grad_norm": 2.0358645915985107, "learning_rate": 4.962636588742182e-05, "loss": 5.2563, "step": 1025 }, { "epoch": 0.05520878174773999, "grad_norm": 2.3683831691741943, "learning_rate": 4.9625637604618416e-05, "loss": 4.9572, "step": 1026 }, { "epoch": 0.05526259147653896, "grad_norm": 1.3650976419448853, "learning_rate": 4.9624908618080526e-05, "loss": 4.8371, "step": 1027 }, { "epoch": 0.05531640120533793, "grad_norm": 1.1344596147537231, "learning_rate": 4.962417892782898e-05, "loss": 4.9688, "step": 1028 }, { "epoch": 0.05537021093413689, "grad_norm": 1.3836886882781982, "learning_rate": 4.962344853388463e-05, "loss": 4.7909, "step": 1029 }, { "epoch": 0.055424020662935856, "grad_norm": 1.1300078630447388, "learning_rate": 4.962271743626836e-05, "loss": 4.8222, "step": 1030 }, { "epoch": 0.055477830391734824, "grad_norm": 1.6790508031845093, "learning_rate": 4.9621985635001043e-05, "loss": 4.7802, "step": 1031 }, { "epoch": 0.05553164012053379, "grad_norm": 2.2851152420043945, "learning_rate": 4.962125313010361e-05, "loss": 4.634, "step": 1032 }, { "epoch": 0.05558544984933276, "grad_norm": 1.8924180269241333, "learning_rate": 4.9620519921596975e-05, "loss": 5.2073, "step": 1033 }, { "epoch": 0.055639259578131726, "grad_norm": 1.5870108604431152, "learning_rate": 4.9619786009502114e-05, "loss": 5.0835, "step": 1034 }, { "epoch": 0.055693069306930694, "grad_norm": 1.2004917860031128, "learning_rate": 4.9619051393839976e-05, "loss": 4.8827, "step": 1035 }, { "epoch": 0.05574687903572966, "grad_norm": 1.5784515142440796, "learning_rate": 4.9618316074631574e-05, "loss": 4.7697, "step": 1036 }, { "epoch": 0.05580068876452863, "grad_norm": 2.128819704055786, "learning_rate": 4.9617580051897915e-05, "loss": 4.6598, "step": 1037 }, { "epoch": 0.055854498493327596, "grad_norm": 1.1668552160263062, "learning_rate": 4.961684332566003e-05, "loss": 4.7176, "step": 1038 }, { "epoch": 0.05590830822212656, "grad_norm": 1.7283192873001099, "learning_rate": 4.961610589593898e-05, "loss": 4.7643, "step": 1039 }, { "epoch": 0.055962117950925525, "grad_norm": 1.712202548980713, "learning_rate": 4.961536776275583e-05, "loss": 4.7806, "step": 1040 }, { "epoch": 0.05601592767972449, "grad_norm": 1.1753473281860352, "learning_rate": 4.961462892613167e-05, "loss": 5.1947, "step": 1041 }, { "epoch": 0.05606973740852346, "grad_norm": 1.2037301063537598, "learning_rate": 4.9613889386087625e-05, "loss": 5.1357, "step": 1042 }, { "epoch": 0.05612354713732243, "grad_norm": 1.534541130065918, "learning_rate": 4.961314914264482e-05, "loss": 4.8935, "step": 1043 }, { "epoch": 0.056177356866121395, "grad_norm": 1.7007427215576172, "learning_rate": 4.9612408195824424e-05, "loss": 4.9993, "step": 1044 }, { "epoch": 0.05623116659492036, "grad_norm": 1.3029334545135498, "learning_rate": 4.96116665456476e-05, "loss": 4.667, "step": 1045 }, { "epoch": 0.05628497632371933, "grad_norm": 1.8854602575302124, "learning_rate": 4.961092419213554e-05, "loss": 4.83, "step": 1046 }, { "epoch": 0.0563387860525183, "grad_norm": 1.7798646688461304, "learning_rate": 4.9610181135309464e-05, "loss": 4.757, "step": 1047 }, { "epoch": 0.056392595781317265, "grad_norm": 1.1645468473434448, "learning_rate": 4.9609437375190595e-05, "loss": 4.7822, "step": 1048 }, { "epoch": 0.05644640551011623, "grad_norm": 1.4995461702346802, "learning_rate": 4.960869291180021e-05, "loss": 4.9336, "step": 1049 }, { "epoch": 0.05650021523891519, "grad_norm": 1.8503563404083252, "learning_rate": 4.960794774515957e-05, "loss": 4.7375, "step": 1050 }, { "epoch": 0.05655402496771416, "grad_norm": 2.0026590824127197, "learning_rate": 4.9607201875289964e-05, "loss": 4.8293, "step": 1051 }, { "epoch": 0.05660783469651313, "grad_norm": 1.6596769094467163, "learning_rate": 4.960645530221272e-05, "loss": 4.8341, "step": 1052 }, { "epoch": 0.056661644425312095, "grad_norm": 1.3123376369476318, "learning_rate": 4.9605708025949166e-05, "loss": 5.0686, "step": 1053 }, { "epoch": 0.05671545415411106, "grad_norm": 2.475996732711792, "learning_rate": 4.9604960046520656e-05, "loss": 4.5913, "step": 1054 }, { "epoch": 0.05676926388291003, "grad_norm": 2.1002914905548096, "learning_rate": 4.960421136394857e-05, "loss": 5.1375, "step": 1055 }, { "epoch": 0.056823073611709, "grad_norm": 1.1046148538589478, "learning_rate": 4.9603461978254296e-05, "loss": 4.9722, "step": 1056 }, { "epoch": 0.056876883340507965, "grad_norm": 2.178680419921875, "learning_rate": 4.9602711889459264e-05, "loss": 4.429, "step": 1057 }, { "epoch": 0.05693069306930693, "grad_norm": 1.2960625886917114, "learning_rate": 4.9601961097584894e-05, "loss": 5.0092, "step": 1058 }, { "epoch": 0.0569845027981059, "grad_norm": 1.149678111076355, "learning_rate": 4.9601209602652646e-05, "loss": 4.8663, "step": 1059 }, { "epoch": 0.05703831252690487, "grad_norm": 1.9938029050827026, "learning_rate": 4.9600457404684e-05, "loss": 4.5816, "step": 1060 }, { "epoch": 0.05709212225570383, "grad_norm": 1.073405385017395, "learning_rate": 4.959970450370044e-05, "loss": 5.1913, "step": 1061 }, { "epoch": 0.057145931984502796, "grad_norm": 3.1118550300598145, "learning_rate": 4.959895089972349e-05, "loss": 4.5072, "step": 1062 }, { "epoch": 0.05719974171330176, "grad_norm": 2.4380342960357666, "learning_rate": 4.95981965927747e-05, "loss": 4.9964, "step": 1063 }, { "epoch": 0.05725355144210073, "grad_norm": 1.1765249967575073, "learning_rate": 4.959744158287561e-05, "loss": 5.0096, "step": 1064 }, { "epoch": 0.0573073611708997, "grad_norm": 0.9270060658454895, "learning_rate": 4.959668587004779e-05, "loss": 4.9856, "step": 1065 }, { "epoch": 0.057361170899698666, "grad_norm": 1.0468151569366455, "learning_rate": 4.9595929454312853e-05, "loss": 4.7391, "step": 1066 }, { "epoch": 0.05741498062849763, "grad_norm": 1.4622927904129028, "learning_rate": 4.959517233569241e-05, "loss": 5.1473, "step": 1067 }, { "epoch": 0.0574687903572966, "grad_norm": 1.5760760307312012, "learning_rate": 4.959441451420809e-05, "loss": 4.9705, "step": 1068 }, { "epoch": 0.05752260008609557, "grad_norm": 1.1256122589111328, "learning_rate": 4.9593655989881547e-05, "loss": 5.2082, "step": 1069 }, { "epoch": 0.057576409814894536, "grad_norm": 2.0533711910247803, "learning_rate": 4.959289676273447e-05, "loss": 4.9883, "step": 1070 }, { "epoch": 0.057630219543693496, "grad_norm": 1.380025863647461, "learning_rate": 4.959213683278856e-05, "loss": 5.0372, "step": 1071 }, { "epoch": 0.057684029272492464, "grad_norm": 1.3586885929107666, "learning_rate": 4.959137620006552e-05, "loss": 4.7571, "step": 1072 }, { "epoch": 0.05773783900129143, "grad_norm": 1.1300431489944458, "learning_rate": 4.9590614864587086e-05, "loss": 4.8431, "step": 1073 }, { "epoch": 0.0577916487300904, "grad_norm": 1.5703153610229492, "learning_rate": 4.9589852826375026e-05, "loss": 4.7526, "step": 1074 }, { "epoch": 0.057845458458889366, "grad_norm": 1.6285523176193237, "learning_rate": 4.9589090085451105e-05, "loss": 4.931, "step": 1075 }, { "epoch": 0.057899268187688334, "grad_norm": 1.584303855895996, "learning_rate": 4.9588326641837134e-05, "loss": 4.7086, "step": 1076 }, { "epoch": 0.0579530779164873, "grad_norm": 1.8517285585403442, "learning_rate": 4.958756249555492e-05, "loss": 4.5713, "step": 1077 }, { "epoch": 0.05800688764528627, "grad_norm": 1.2125190496444702, "learning_rate": 4.958679764662629e-05, "loss": 4.7499, "step": 1078 }, { "epoch": 0.058060697374085236, "grad_norm": 1.3534609079360962, "learning_rate": 4.958603209507313e-05, "loss": 4.8597, "step": 1079 }, { "epoch": 0.058114507102884204, "grad_norm": 1.4548226594924927, "learning_rate": 4.9585265840917293e-05, "loss": 5.0365, "step": 1080 }, { "epoch": 0.05816831683168317, "grad_norm": 1.3296197652816772, "learning_rate": 4.958449888418069e-05, "loss": 4.592, "step": 1081 }, { "epoch": 0.05822212656048213, "grad_norm": 1.0073871612548828, "learning_rate": 4.958373122488523e-05, "loss": 4.8468, "step": 1082 }, { "epoch": 0.0582759362892811, "grad_norm": 2.086268663406372, "learning_rate": 4.958296286305285e-05, "loss": 4.7928, "step": 1083 }, { "epoch": 0.05832974601808007, "grad_norm": 1.7328174114227295, "learning_rate": 4.9582193798705525e-05, "loss": 4.7337, "step": 1084 }, { "epoch": 0.058383555746879034, "grad_norm": 1.9242665767669678, "learning_rate": 4.958142403186521e-05, "loss": 4.8768, "step": 1085 }, { "epoch": 0.058437365475678, "grad_norm": 1.5703134536743164, "learning_rate": 4.958065356255391e-05, "loss": 4.9649, "step": 1086 }, { "epoch": 0.05849117520447697, "grad_norm": 1.0351152420043945, "learning_rate": 4.957988239079365e-05, "loss": 4.5349, "step": 1087 }, { "epoch": 0.05854498493327594, "grad_norm": 1.7748171091079712, "learning_rate": 4.957911051660647e-05, "loss": 4.8443, "step": 1088 }, { "epoch": 0.058598794662074905, "grad_norm": 1.0913161039352417, "learning_rate": 4.957833794001441e-05, "loss": 4.7492, "step": 1089 }, { "epoch": 0.05865260439087387, "grad_norm": 1.619136095046997, "learning_rate": 4.957756466103957e-05, "loss": 4.8341, "step": 1090 }, { "epoch": 0.05870641411967284, "grad_norm": 1.9212311506271362, "learning_rate": 4.957679067970403e-05, "loss": 4.9889, "step": 1091 }, { "epoch": 0.05876022384847181, "grad_norm": 1.9746683835983276, "learning_rate": 4.9576015996029914e-05, "loss": 4.9173, "step": 1092 }, { "epoch": 0.05881403357727077, "grad_norm": 2.5224757194519043, "learning_rate": 4.9575240610039365e-05, "loss": 4.7006, "step": 1093 }, { "epoch": 0.058867843306069735, "grad_norm": 1.109189510345459, "learning_rate": 4.957446452175454e-05, "loss": 5.1189, "step": 1094 }, { "epoch": 0.0589216530348687, "grad_norm": 1.1499916315078735, "learning_rate": 4.9573687731197614e-05, "loss": 5.0274, "step": 1095 }, { "epoch": 0.05897546276366767, "grad_norm": 2.0189995765686035, "learning_rate": 4.95729102383908e-05, "loss": 4.7586, "step": 1096 }, { "epoch": 0.05902927249246664, "grad_norm": 1.7147681713104248, "learning_rate": 4.957213204335629e-05, "loss": 4.9081, "step": 1097 }, { "epoch": 0.059083082221265605, "grad_norm": 1.46285879611969, "learning_rate": 4.9571353146116344e-05, "loss": 4.7461, "step": 1098 }, { "epoch": 0.05913689195006457, "grad_norm": 1.6639350652694702, "learning_rate": 4.957057354669321e-05, "loss": 4.3214, "step": 1099 }, { "epoch": 0.05919070167886354, "grad_norm": 2.317291021347046, "learning_rate": 4.956979324510918e-05, "loss": 4.9344, "step": 1100 }, { "epoch": 0.05924451140766251, "grad_norm": 1.5123437643051147, "learning_rate": 4.956901224138653e-05, "loss": 4.827, "step": 1101 }, { "epoch": 0.059298321136461475, "grad_norm": 2.150862216949463, "learning_rate": 4.956823053554761e-05, "loss": 4.8458, "step": 1102 }, { "epoch": 0.059352130865260436, "grad_norm": 2.0106096267700195, "learning_rate": 4.9567448127614736e-05, "loss": 4.7135, "step": 1103 }, { "epoch": 0.0594059405940594, "grad_norm": 2.1833081245422363, "learning_rate": 4.956666501761027e-05, "loss": 4.7982, "step": 1104 }, { "epoch": 0.05945975032285837, "grad_norm": 1.5478403568267822, "learning_rate": 4.9565881205556594e-05, "loss": 4.8748, "step": 1105 }, { "epoch": 0.05951356005165734, "grad_norm": 2.8224740028381348, "learning_rate": 4.956509669147611e-05, "loss": 4.4103, "step": 1106 }, { "epoch": 0.059567369780456306, "grad_norm": 1.4605135917663574, "learning_rate": 4.956431147539124e-05, "loss": 5.0413, "step": 1107 }, { "epoch": 0.05962117950925527, "grad_norm": 1.7869343757629395, "learning_rate": 4.9563525557324405e-05, "loss": 4.7473, "step": 1108 }, { "epoch": 0.05967498923805424, "grad_norm": 1.246880054473877, "learning_rate": 4.956273893729809e-05, "loss": 4.9919, "step": 1109 }, { "epoch": 0.05972879896685321, "grad_norm": 1.4626760482788086, "learning_rate": 4.956195161533476e-05, "loss": 5.041, "step": 1110 }, { "epoch": 0.059782608695652176, "grad_norm": 1.7075831890106201, "learning_rate": 4.9561163591456904e-05, "loss": 4.8107, "step": 1111 }, { "epoch": 0.05983641842445114, "grad_norm": 1.254982590675354, "learning_rate": 4.956037486568706e-05, "loss": 4.9515, "step": 1112 }, { "epoch": 0.05989022815325011, "grad_norm": 1.1022958755493164, "learning_rate": 4.9559585438047776e-05, "loss": 4.8862, "step": 1113 }, { "epoch": 0.05994403788204907, "grad_norm": 1.4259302616119385, "learning_rate": 4.9558795308561584e-05, "loss": 5.0184, "step": 1114 }, { "epoch": 0.05999784761084804, "grad_norm": 1.446751594543457, "learning_rate": 4.9558004477251085e-05, "loss": 4.8134, "step": 1115 }, { "epoch": 0.060051657339647006, "grad_norm": 1.6337475776672363, "learning_rate": 4.9557212944138864e-05, "loss": 4.812, "step": 1116 }, { "epoch": 0.060105467068445974, "grad_norm": 1.628391146659851, "learning_rate": 4.9556420709247555e-05, "loss": 4.8849, "step": 1117 }, { "epoch": 0.06015927679724494, "grad_norm": 1.3555108308792114, "learning_rate": 4.955562777259979e-05, "loss": 4.8734, "step": 1118 }, { "epoch": 0.06021308652604391, "grad_norm": 1.200727939605713, "learning_rate": 4.955483413421822e-05, "loss": 4.8429, "step": 1119 }, { "epoch": 0.060266896254842876, "grad_norm": 1.2435435056686401, "learning_rate": 4.955403979412555e-05, "loss": 5.0742, "step": 1120 }, { "epoch": 0.060320705983641844, "grad_norm": 1.4087778329849243, "learning_rate": 4.9553244752344454e-05, "loss": 4.9426, "step": 1121 }, { "epoch": 0.06037451571244081, "grad_norm": 1.4634541273117065, "learning_rate": 4.955244900889767e-05, "loss": 4.8587, "step": 1122 }, { "epoch": 0.06042832544123978, "grad_norm": 1.711671233177185, "learning_rate": 4.955165256380793e-05, "loss": 4.9201, "step": 1123 }, { "epoch": 0.060482135170038746, "grad_norm": 1.3144311904907227, "learning_rate": 4.9550855417097994e-05, "loss": 4.8232, "step": 1124 }, { "epoch": 0.06053594489883771, "grad_norm": 1.9324320554733276, "learning_rate": 4.955005756879064e-05, "loss": 4.8927, "step": 1125 }, { "epoch": 0.060589754627636674, "grad_norm": 1.5532457828521729, "learning_rate": 4.954925901890868e-05, "loss": 4.5586, "step": 1126 }, { "epoch": 0.06064356435643564, "grad_norm": 1.4372395277023315, "learning_rate": 4.954845976747493e-05, "loss": 4.822, "step": 1127 }, { "epoch": 0.06069737408523461, "grad_norm": 1.3816289901733398, "learning_rate": 4.954765981451222e-05, "loss": 4.7138, "step": 1128 }, { "epoch": 0.06075118381403358, "grad_norm": 1.2816741466522217, "learning_rate": 4.9546859160043426e-05, "loss": 4.6294, "step": 1129 }, { "epoch": 0.060804993542832544, "grad_norm": 1.4975166320800781, "learning_rate": 4.954605780409141e-05, "loss": 5.0754, "step": 1130 }, { "epoch": 0.06085880327163151, "grad_norm": 1.7548744678497314, "learning_rate": 4.9545255746679084e-05, "loss": 4.7933, "step": 1131 }, { "epoch": 0.06091261300043048, "grad_norm": 1.3006105422973633, "learning_rate": 4.954445298782938e-05, "loss": 4.9607, "step": 1132 }, { "epoch": 0.06096642272922945, "grad_norm": 1.3549442291259766, "learning_rate": 4.954364952756522e-05, "loss": 4.8742, "step": 1133 }, { "epoch": 0.061020232458028414, "grad_norm": 1.9625524282455444, "learning_rate": 4.9542845365909566e-05, "loss": 4.6111, "step": 1134 }, { "epoch": 0.061074042186827375, "grad_norm": 2.110137462615967, "learning_rate": 4.954204050288541e-05, "loss": 4.9915, "step": 1135 }, { "epoch": 0.06112785191562634, "grad_norm": 1.6790297031402588, "learning_rate": 4.9541234938515744e-05, "loss": 4.9043, "step": 1136 }, { "epoch": 0.06118166164442531, "grad_norm": 1.1329078674316406, "learning_rate": 4.9540428672823594e-05, "loss": 4.8136, "step": 1137 }, { "epoch": 0.06123547137322428, "grad_norm": 2.114204168319702, "learning_rate": 4.953962170583199e-05, "loss": 4.8057, "step": 1138 }, { "epoch": 0.061289281102023245, "grad_norm": 1.3999688625335693, "learning_rate": 4.9538814037564006e-05, "loss": 4.9262, "step": 1139 }, { "epoch": 0.06134309083082221, "grad_norm": 2.2725701332092285, "learning_rate": 4.953800566804273e-05, "loss": 4.9114, "step": 1140 }, { "epoch": 0.06139690055962118, "grad_norm": 2.161494016647339, "learning_rate": 4.953719659729124e-05, "loss": 4.8618, "step": 1141 }, { "epoch": 0.06145071028842015, "grad_norm": 1.4664708375930786, "learning_rate": 4.953638682533267e-05, "loss": 4.7444, "step": 1142 }, { "epoch": 0.061504520017219115, "grad_norm": 1.3474441766738892, "learning_rate": 4.953557635219016e-05, "loss": 5.3471, "step": 1143 }, { "epoch": 0.06155832974601808, "grad_norm": 1.8853949308395386, "learning_rate": 4.953476517788686e-05, "loss": 5.1208, "step": 1144 }, { "epoch": 0.06161213947481705, "grad_norm": 1.7731138467788696, "learning_rate": 4.953395330244598e-05, "loss": 4.4481, "step": 1145 }, { "epoch": 0.06166594920361601, "grad_norm": 1.0635203123092651, "learning_rate": 4.95331407258907e-05, "loss": 4.9931, "step": 1146 }, { "epoch": 0.06171975893241498, "grad_norm": 1.493653655052185, "learning_rate": 4.953232744824424e-05, "loss": 4.6273, "step": 1147 }, { "epoch": 0.061773568661213946, "grad_norm": 1.2051165103912354, "learning_rate": 4.9531513469529845e-05, "loss": 4.6958, "step": 1148 }, { "epoch": 0.06182737839001291, "grad_norm": 1.170573115348816, "learning_rate": 4.953069878977078e-05, "loss": 5.1704, "step": 1149 }, { "epoch": 0.06188118811881188, "grad_norm": 1.1505602598190308, "learning_rate": 4.952988340899032e-05, "loss": 5.0026, "step": 1150 }, { "epoch": 0.06193499784761085, "grad_norm": 1.635652780532837, "learning_rate": 4.952906732721178e-05, "loss": 4.4618, "step": 1151 }, { "epoch": 0.061988807576409816, "grad_norm": 2.0403623580932617, "learning_rate": 4.9528250544458455e-05, "loss": 4.9233, "step": 1152 }, { "epoch": 0.06204261730520878, "grad_norm": 1.9811972379684448, "learning_rate": 4.9527433060753716e-05, "loss": 4.6202, "step": 1153 }, { "epoch": 0.06209642703400775, "grad_norm": 1.5659030675888062, "learning_rate": 4.9526614876120905e-05, "loss": 4.7669, "step": 1154 }, { "epoch": 0.06215023676280672, "grad_norm": 1.0909333229064941, "learning_rate": 4.952579599058341e-05, "loss": 4.9171, "step": 1155 }, { "epoch": 0.062204046491605686, "grad_norm": 2.040940046310425, "learning_rate": 4.952497640416463e-05, "loss": 5.0585, "step": 1156 }, { "epoch": 0.062257856220404646, "grad_norm": 1.4094741344451904, "learning_rate": 4.952415611688799e-05, "loss": 4.8272, "step": 1157 }, { "epoch": 0.062311665949203614, "grad_norm": 1.4269112348556519, "learning_rate": 4.952333512877693e-05, "loss": 4.7372, "step": 1158 }, { "epoch": 0.06236547567800258, "grad_norm": 1.9201545715332031, "learning_rate": 4.952251343985492e-05, "loss": 4.5188, "step": 1159 }, { "epoch": 0.06241928540680155, "grad_norm": 0.8652633428573608, "learning_rate": 4.952169105014543e-05, "loss": 4.6256, "step": 1160 }, { "epoch": 0.062473095135600516, "grad_norm": 2.2228589057922363, "learning_rate": 4.9520867959671956e-05, "loss": 4.764, "step": 1161 }, { "epoch": 0.06252690486439948, "grad_norm": 2.16933274269104, "learning_rate": 4.9520044168458035e-05, "loss": 4.7135, "step": 1162 }, { "epoch": 0.06258071459319844, "grad_norm": 1.5266761779785156, "learning_rate": 4.9519219676527204e-05, "loss": 4.8976, "step": 1163 }, { "epoch": 0.06263452432199741, "grad_norm": 2.90962290763855, "learning_rate": 4.951839448390303e-05, "loss": 4.7658, "step": 1164 }, { "epoch": 0.06268833405079638, "grad_norm": 1.3273993730545044, "learning_rate": 4.951756859060908e-05, "loss": 4.5012, "step": 1165 }, { "epoch": 0.06274214377959535, "grad_norm": 1.2986629009246826, "learning_rate": 4.9516741996668966e-05, "loss": 4.839, "step": 1166 }, { "epoch": 0.06279595350839431, "grad_norm": 1.312103509902954, "learning_rate": 4.9515914702106304e-05, "loss": 4.9323, "step": 1167 }, { "epoch": 0.06284976323719328, "grad_norm": 2.263458490371704, "learning_rate": 4.951508670694475e-05, "loss": 4.5646, "step": 1168 }, { "epoch": 0.06290357296599225, "grad_norm": 1.9364519119262695, "learning_rate": 4.9514258011207946e-05, "loss": 4.785, "step": 1169 }, { "epoch": 0.06295738269479122, "grad_norm": 1.6767085790634155, "learning_rate": 4.951342861491959e-05, "loss": 4.8844, "step": 1170 }, { "epoch": 0.06301119242359018, "grad_norm": 1.4190900325775146, "learning_rate": 4.951259851810337e-05, "loss": 4.8226, "step": 1171 }, { "epoch": 0.06306500215238915, "grad_norm": 1.1385997533798218, "learning_rate": 4.951176772078302e-05, "loss": 5.0072, "step": 1172 }, { "epoch": 0.06311881188118812, "grad_norm": 1.3196110725402832, "learning_rate": 4.951093622298228e-05, "loss": 5.1173, "step": 1173 }, { "epoch": 0.06317262160998709, "grad_norm": 1.8396432399749756, "learning_rate": 4.9510104024724915e-05, "loss": 4.9023, "step": 1174 }, { "epoch": 0.06322643133878605, "grad_norm": 2.0408542156219482, "learning_rate": 4.9509271126034685e-05, "loss": 4.6411, "step": 1175 }, { "epoch": 0.06328024106758502, "grad_norm": 1.9416282176971436, "learning_rate": 4.950843752693542e-05, "loss": 4.855, "step": 1176 }, { "epoch": 0.06333405079638399, "grad_norm": 1.422703742980957, "learning_rate": 4.9507603227450927e-05, "loss": 4.7385, "step": 1177 }, { "epoch": 0.06338786052518296, "grad_norm": 2.221743583679199, "learning_rate": 4.950676822760505e-05, "loss": 4.9197, "step": 1178 }, { "epoch": 0.06344167025398192, "grad_norm": 1.2011252641677856, "learning_rate": 4.950593252742166e-05, "loss": 4.916, "step": 1179 }, { "epoch": 0.06349547998278089, "grad_norm": 1.46802818775177, "learning_rate": 4.9505096126924625e-05, "loss": 5.0565, "step": 1180 }, { "epoch": 0.06354928971157986, "grad_norm": 1.5254887342453003, "learning_rate": 4.950425902613786e-05, "loss": 4.7753, "step": 1181 }, { "epoch": 0.06360309944037883, "grad_norm": 1.9161139726638794, "learning_rate": 4.9503421225085265e-05, "loss": 4.6816, "step": 1182 }, { "epoch": 0.06365690916917778, "grad_norm": 1.8020527362823486, "learning_rate": 4.950258272379081e-05, "loss": 4.9116, "step": 1183 }, { "epoch": 0.06371071889797675, "grad_norm": 1.9505723714828491, "learning_rate": 4.950174352227844e-05, "loss": 4.5977, "step": 1184 }, { "epoch": 0.06376452862677572, "grad_norm": 1.2454156875610352, "learning_rate": 4.950090362057215e-05, "loss": 4.7573, "step": 1185 }, { "epoch": 0.06381833835557468, "grad_norm": 1.9461718797683716, "learning_rate": 4.950006301869593e-05, "loss": 4.6479, "step": 1186 }, { "epoch": 0.06387214808437365, "grad_norm": 1.7844120264053345, "learning_rate": 4.9499221716673804e-05, "loss": 4.6092, "step": 1187 }, { "epoch": 0.06392595781317262, "grad_norm": 1.0184340476989746, "learning_rate": 4.949837971452982e-05, "loss": 4.5131, "step": 1188 }, { "epoch": 0.06397976754197159, "grad_norm": 1.8642345666885376, "learning_rate": 4.9497537012288035e-05, "loss": 4.6226, "step": 1189 }, { "epoch": 0.06403357727077055, "grad_norm": 1.4165360927581787, "learning_rate": 4.949669360997253e-05, "loss": 4.8858, "step": 1190 }, { "epoch": 0.06408738699956952, "grad_norm": 1.6737585067749023, "learning_rate": 4.949584950760742e-05, "loss": 4.6131, "step": 1191 }, { "epoch": 0.06414119672836849, "grad_norm": 1.0790691375732422, "learning_rate": 4.9495004705216807e-05, "loss": 4.9324, "step": 1192 }, { "epoch": 0.06419500645716746, "grad_norm": 1.1500335931777954, "learning_rate": 4.9494159202824844e-05, "loss": 4.8279, "step": 1193 }, { "epoch": 0.06424881618596642, "grad_norm": 1.5663939714431763, "learning_rate": 4.94933130004557e-05, "loss": 4.6771, "step": 1194 }, { "epoch": 0.06430262591476539, "grad_norm": 1.463375210762024, "learning_rate": 4.9492466098133545e-05, "loss": 4.8717, "step": 1195 }, { "epoch": 0.06435643564356436, "grad_norm": 1.3796985149383545, "learning_rate": 4.9491618495882586e-05, "loss": 4.6714, "step": 1196 }, { "epoch": 0.06441024537236333, "grad_norm": 0.9362966418266296, "learning_rate": 4.949077019372704e-05, "loss": 4.7126, "step": 1197 }, { "epoch": 0.0644640551011623, "grad_norm": 1.3733265399932861, "learning_rate": 4.9489921191691165e-05, "loss": 4.7906, "step": 1198 }, { "epoch": 0.06451786482996126, "grad_norm": 1.4318069219589233, "learning_rate": 4.94890714897992e-05, "loss": 4.74, "step": 1199 }, { "epoch": 0.06457167455876023, "grad_norm": 1.194024682044983, "learning_rate": 4.948822108807545e-05, "loss": 4.78, "step": 1200 }, { "epoch": 0.0646254842875592, "grad_norm": 1.875438928604126, "learning_rate": 4.9487369986544205e-05, "loss": 4.4608, "step": 1201 }, { "epoch": 0.06467929401635816, "grad_norm": 1.6638027429580688, "learning_rate": 4.9486518185229785e-05, "loss": 4.7756, "step": 1202 }, { "epoch": 0.06473310374515713, "grad_norm": 1.656051516532898, "learning_rate": 4.948566568415654e-05, "loss": 4.8188, "step": 1203 }, { "epoch": 0.0647869134739561, "grad_norm": 2.017047643661499, "learning_rate": 4.948481248334883e-05, "loss": 4.7528, "step": 1204 }, { "epoch": 0.06484072320275505, "grad_norm": 1.5145044326782227, "learning_rate": 4.948395858283103e-05, "loss": 4.8769, "step": 1205 }, { "epoch": 0.06489453293155402, "grad_norm": 1.673841953277588, "learning_rate": 4.9483103982627556e-05, "loss": 5.249, "step": 1206 }, { "epoch": 0.06494834266035299, "grad_norm": 1.8776791095733643, "learning_rate": 4.948224868276281e-05, "loss": 4.5583, "step": 1207 }, { "epoch": 0.06500215238915195, "grad_norm": 1.442358374595642, "learning_rate": 4.948139268326125e-05, "loss": 4.8536, "step": 1208 }, { "epoch": 0.06505596211795092, "grad_norm": 1.773741602897644, "learning_rate": 4.9480535984147345e-05, "loss": 4.8219, "step": 1209 }, { "epoch": 0.06510977184674989, "grad_norm": 2.3795831203460693, "learning_rate": 4.947967858544556e-05, "loss": 4.6677, "step": 1210 }, { "epoch": 0.06516358157554886, "grad_norm": 1.1187818050384521, "learning_rate": 4.94788204871804e-05, "loss": 4.7435, "step": 1211 }, { "epoch": 0.06521739130434782, "grad_norm": 1.6198859214782715, "learning_rate": 4.947796168937639e-05, "loss": 5.0418, "step": 1212 }, { "epoch": 0.06527120103314679, "grad_norm": 2.415297031402588, "learning_rate": 4.947710219205808e-05, "loss": 4.6597, "step": 1213 }, { "epoch": 0.06532501076194576, "grad_norm": 1.3795305490493774, "learning_rate": 4.9476241995250016e-05, "loss": 4.9341, "step": 1214 }, { "epoch": 0.06537882049074473, "grad_norm": 1.438530445098877, "learning_rate": 4.9475381098976795e-05, "loss": 4.999, "step": 1215 }, { "epoch": 0.0654326302195437, "grad_norm": 1.9618123769760132, "learning_rate": 4.947451950326301e-05, "loss": 4.4281, "step": 1216 }, { "epoch": 0.06548643994834266, "grad_norm": 1.191112756729126, "learning_rate": 4.947365720813329e-05, "loss": 4.8387, "step": 1217 }, { "epoch": 0.06554024967714163, "grad_norm": 1.919060230255127, "learning_rate": 4.947279421361227e-05, "loss": 5.106, "step": 1218 }, { "epoch": 0.0655940594059406, "grad_norm": 1.2330121994018555, "learning_rate": 4.9471930519724616e-05, "loss": 4.8028, "step": 1219 }, { "epoch": 0.06564786913473956, "grad_norm": 1.6479053497314453, "learning_rate": 4.9471066126495014e-05, "loss": 5.1614, "step": 1220 }, { "epoch": 0.06570167886353853, "grad_norm": 1.0922847986221313, "learning_rate": 4.947020103394816e-05, "loss": 5.0331, "step": 1221 }, { "epoch": 0.0657554885923375, "grad_norm": 1.8435709476470947, "learning_rate": 4.946933524210877e-05, "loss": 4.7959, "step": 1222 }, { "epoch": 0.06580929832113647, "grad_norm": 3.0102803707122803, "learning_rate": 4.94684687510016e-05, "loss": 4.4808, "step": 1223 }, { "epoch": 0.06586310804993543, "grad_norm": 1.3578016757965088, "learning_rate": 4.946760156065141e-05, "loss": 4.8776, "step": 1224 }, { "epoch": 0.0659169177787344, "grad_norm": 1.7367838621139526, "learning_rate": 4.946673367108297e-05, "loss": 4.7171, "step": 1225 }, { "epoch": 0.06597072750753336, "grad_norm": 2.0342328548431396, "learning_rate": 4.9465865082321094e-05, "loss": 4.5973, "step": 1226 }, { "epoch": 0.06602453723633232, "grad_norm": 1.1669565439224243, "learning_rate": 4.9464995794390596e-05, "loss": 4.773, "step": 1227 }, { "epoch": 0.06607834696513129, "grad_norm": 1.2530927658081055, "learning_rate": 4.946412580731632e-05, "loss": 4.8391, "step": 1228 }, { "epoch": 0.06613215669393026, "grad_norm": 1.7347861528396606, "learning_rate": 4.946325512112313e-05, "loss": 5.2069, "step": 1229 }, { "epoch": 0.06618596642272923, "grad_norm": 1.9258822202682495, "learning_rate": 4.9462383735835915e-05, "loss": 4.9057, "step": 1230 }, { "epoch": 0.06623977615152819, "grad_norm": 1.1968944072723389, "learning_rate": 4.9461511651479566e-05, "loss": 4.6003, "step": 1231 }, { "epoch": 0.06629358588032716, "grad_norm": 1.4440513849258423, "learning_rate": 4.9460638868079e-05, "loss": 4.4715, "step": 1232 }, { "epoch": 0.06634739560912613, "grad_norm": 1.576624870300293, "learning_rate": 4.945976538565917e-05, "loss": 4.4216, "step": 1233 }, { "epoch": 0.0664012053379251, "grad_norm": 2.1285362243652344, "learning_rate": 4.945889120424504e-05, "loss": 4.1918, "step": 1234 }, { "epoch": 0.06645501506672406, "grad_norm": 1.6643075942993164, "learning_rate": 4.945801632386158e-05, "loss": 4.8188, "step": 1235 }, { "epoch": 0.06650882479552303, "grad_norm": 1.426979660987854, "learning_rate": 4.9457140744533796e-05, "loss": 4.9493, "step": 1236 }, { "epoch": 0.066562634524322, "grad_norm": 2.514714479446411, "learning_rate": 4.9456264466286716e-05, "loss": 5.3551, "step": 1237 }, { "epoch": 0.06661644425312097, "grad_norm": 2.752951145172119, "learning_rate": 4.945538748914538e-05, "loss": 4.6856, "step": 1238 }, { "epoch": 0.06667025398191993, "grad_norm": 1.6879642009735107, "learning_rate": 4.945450981313484e-05, "loss": 4.8261, "step": 1239 }, { "epoch": 0.0667240637107189, "grad_norm": 1.9016327857971191, "learning_rate": 4.9453631438280185e-05, "loss": 4.9238, "step": 1240 }, { "epoch": 0.06677787343951787, "grad_norm": 0.9835557341575623, "learning_rate": 4.945275236460652e-05, "loss": 4.8646, "step": 1241 }, { "epoch": 0.06683168316831684, "grad_norm": 2.148629665374756, "learning_rate": 4.945187259213896e-05, "loss": 5.0337, "step": 1242 }, { "epoch": 0.0668854928971158, "grad_norm": 1.547098159790039, "learning_rate": 4.945099212090265e-05, "loss": 4.9751, "step": 1243 }, { "epoch": 0.06693930262591477, "grad_norm": 1.4254368543624878, "learning_rate": 4.945011095092275e-05, "loss": 5.006, "step": 1244 }, { "epoch": 0.06699311235471374, "grad_norm": 1.9382002353668213, "learning_rate": 4.944922908222445e-05, "loss": 4.815, "step": 1245 }, { "epoch": 0.0670469220835127, "grad_norm": 2.4896271228790283, "learning_rate": 4.944834651483293e-05, "loss": 5.0513, "step": 1246 }, { "epoch": 0.06710073181231166, "grad_norm": 1.4721473455429077, "learning_rate": 4.944746324877343e-05, "loss": 4.9954, "step": 1247 }, { "epoch": 0.06715454154111063, "grad_norm": 1.4973236322402954, "learning_rate": 4.944657928407119e-05, "loss": 4.9585, "step": 1248 }, { "epoch": 0.0672083512699096, "grad_norm": 1.4518479108810425, "learning_rate": 4.944569462075147e-05, "loss": 4.9771, "step": 1249 }, { "epoch": 0.06726216099870856, "grad_norm": 1.6074501276016235, "learning_rate": 4.944480925883954e-05, "loss": 5.0576, "step": 1250 }, { "epoch": 0.06731597072750753, "grad_norm": 1.1579952239990234, "learning_rate": 4.9443923198360716e-05, "loss": 4.812, "step": 1251 }, { "epoch": 0.0673697804563065, "grad_norm": 1.0871493816375732, "learning_rate": 4.944303643934031e-05, "loss": 4.7555, "step": 1252 }, { "epoch": 0.06742359018510546, "grad_norm": 2.268993377685547, "learning_rate": 4.944214898180367e-05, "loss": 4.8306, "step": 1253 }, { "epoch": 0.06747739991390443, "grad_norm": 2.150473117828369, "learning_rate": 4.944126082577615e-05, "loss": 4.8472, "step": 1254 }, { "epoch": 0.0675312096427034, "grad_norm": 2.22576642036438, "learning_rate": 4.944037197128314e-05, "loss": 4.7593, "step": 1255 }, { "epoch": 0.06758501937150237, "grad_norm": 2.040665864944458, "learning_rate": 4.943948241835003e-05, "loss": 4.7727, "step": 1256 }, { "epoch": 0.06763882910030133, "grad_norm": 1.8635324239730835, "learning_rate": 4.943859216700225e-05, "loss": 4.7626, "step": 1257 }, { "epoch": 0.0676926388291003, "grad_norm": 2.1848864555358887, "learning_rate": 4.943770121726524e-05, "loss": 4.9995, "step": 1258 }, { "epoch": 0.06774644855789927, "grad_norm": 1.788810133934021, "learning_rate": 4.943680956916446e-05, "loss": 5.0154, "step": 1259 }, { "epoch": 0.06780025828669824, "grad_norm": 1.2317883968353271, "learning_rate": 4.943591722272538e-05, "loss": 5.0143, "step": 1260 }, { "epoch": 0.0678540680154972, "grad_norm": 1.6448734998703003, "learning_rate": 4.9435024177973524e-05, "loss": 5.0646, "step": 1261 }, { "epoch": 0.06790787774429617, "grad_norm": 2.17720627784729, "learning_rate": 4.9434130434934387e-05, "loss": 4.6991, "step": 1262 }, { "epoch": 0.06796168747309514, "grad_norm": 1.4132157564163208, "learning_rate": 4.943323599363353e-05, "loss": 4.9835, "step": 1263 }, { "epoch": 0.0680154972018941, "grad_norm": 2.6635818481445312, "learning_rate": 4.9432340854096505e-05, "loss": 4.715, "step": 1264 }, { "epoch": 0.06806930693069307, "grad_norm": 1.7870781421661377, "learning_rate": 4.943144501634889e-05, "loss": 4.6554, "step": 1265 }, { "epoch": 0.06812311665949204, "grad_norm": 1.1918388605117798, "learning_rate": 4.9430548480416297e-05, "loss": 4.8997, "step": 1266 }, { "epoch": 0.06817692638829101, "grad_norm": 1.486085057258606, "learning_rate": 4.942965124632433e-05, "loss": 4.8433, "step": 1267 }, { "epoch": 0.06823073611708998, "grad_norm": 1.2348016500473022, "learning_rate": 4.942875331409864e-05, "loss": 4.8004, "step": 1268 }, { "epoch": 0.06828454584588893, "grad_norm": 1.416433572769165, "learning_rate": 4.942785468376488e-05, "loss": 4.7927, "step": 1269 }, { "epoch": 0.0683383555746879, "grad_norm": 1.0978931188583374, "learning_rate": 4.9426955355348756e-05, "loss": 4.9857, "step": 1270 }, { "epoch": 0.06839216530348687, "grad_norm": 1.471416711807251, "learning_rate": 4.942605532887593e-05, "loss": 4.9818, "step": 1271 }, { "epoch": 0.06844597503228583, "grad_norm": 1.27640962600708, "learning_rate": 4.942515460437215e-05, "loss": 4.9787, "step": 1272 }, { "epoch": 0.0684997847610848, "grad_norm": 1.7796106338500977, "learning_rate": 4.942425318186314e-05, "loss": 4.479, "step": 1273 }, { "epoch": 0.06855359448988377, "grad_norm": 1.993654489517212, "learning_rate": 4.942335106137468e-05, "loss": 4.7939, "step": 1274 }, { "epoch": 0.06860740421868274, "grad_norm": 1.1292598247528076, "learning_rate": 4.9422448242932526e-05, "loss": 5.016, "step": 1275 }, { "epoch": 0.0686612139474817, "grad_norm": 0.9633069634437561, "learning_rate": 4.94215447265625e-05, "loss": 4.8426, "step": 1276 }, { "epoch": 0.06871502367628067, "grad_norm": 1.9606354236602783, "learning_rate": 4.942064051229041e-05, "loss": 4.4613, "step": 1277 }, { "epoch": 0.06876883340507964, "grad_norm": 1.502192497253418, "learning_rate": 4.9419735600142094e-05, "loss": 4.6524, "step": 1278 }, { "epoch": 0.0688226431338786, "grad_norm": 1.0472832918167114, "learning_rate": 4.941882999014342e-05, "loss": 4.8924, "step": 1279 }, { "epoch": 0.06887645286267757, "grad_norm": 1.3074867725372314, "learning_rate": 4.941792368232026e-05, "loss": 4.7931, "step": 1280 }, { "epoch": 0.06893026259147654, "grad_norm": 1.2675721645355225, "learning_rate": 4.941701667669851e-05, "loss": 5.02, "step": 1281 }, { "epoch": 0.06898407232027551, "grad_norm": 1.0800299644470215, "learning_rate": 4.941610897330411e-05, "loss": 4.9302, "step": 1282 }, { "epoch": 0.06903788204907448, "grad_norm": 1.5071593523025513, "learning_rate": 4.9415200572162984e-05, "loss": 4.8789, "step": 1283 }, { "epoch": 0.06909169177787344, "grad_norm": 1.499343991279602, "learning_rate": 4.9414291473301094e-05, "loss": 4.8191, "step": 1284 }, { "epoch": 0.06914550150667241, "grad_norm": 1.7008750438690186, "learning_rate": 4.941338167674442e-05, "loss": 4.9208, "step": 1285 }, { "epoch": 0.06919931123547138, "grad_norm": 1.2861000299453735, "learning_rate": 4.941247118251896e-05, "loss": 4.8143, "step": 1286 }, { "epoch": 0.06925312096427035, "grad_norm": 0.9367782473564148, "learning_rate": 4.941155999065074e-05, "loss": 4.7441, "step": 1287 }, { "epoch": 0.06930693069306931, "grad_norm": 1.608291745185852, "learning_rate": 4.941064810116579e-05, "loss": 5.0548, "step": 1288 }, { "epoch": 0.06936074042186828, "grad_norm": 2.1217684745788574, "learning_rate": 4.940973551409018e-05, "loss": 4.9379, "step": 1289 }, { "epoch": 0.06941455015066723, "grad_norm": 1.7054225206375122, "learning_rate": 4.940882222944998e-05, "loss": 4.9133, "step": 1290 }, { "epoch": 0.0694683598794662, "grad_norm": 2.223459005355835, "learning_rate": 4.940790824727129e-05, "loss": 4.6361, "step": 1291 }, { "epoch": 0.06952216960826517, "grad_norm": 1.2038501501083374, "learning_rate": 4.940699356758024e-05, "loss": 4.9683, "step": 1292 }, { "epoch": 0.06957597933706414, "grad_norm": 1.1515072584152222, "learning_rate": 4.940607819040295e-05, "loss": 4.8762, "step": 1293 }, { "epoch": 0.0696297890658631, "grad_norm": 2.0077474117279053, "learning_rate": 4.9405162115765594e-05, "loss": 4.7854, "step": 1294 }, { "epoch": 0.06968359879466207, "grad_norm": 1.690496802330017, "learning_rate": 4.940424534369435e-05, "loss": 4.587, "step": 1295 }, { "epoch": 0.06973740852346104, "grad_norm": 1.4298391342163086, "learning_rate": 4.940332787421541e-05, "loss": 4.6179, "step": 1296 }, { "epoch": 0.06979121825226, "grad_norm": 1.7304779291152954, "learning_rate": 4.9402409707355e-05, "loss": 4.7261, "step": 1297 }, { "epoch": 0.06984502798105897, "grad_norm": 1.4168835878372192, "learning_rate": 4.940149084313935e-05, "loss": 4.8005, "step": 1298 }, { "epoch": 0.06989883770985794, "grad_norm": 1.375099539756775, "learning_rate": 4.940057128159473e-05, "loss": 4.832, "step": 1299 }, { "epoch": 0.06995264743865691, "grad_norm": 1.112173318862915, "learning_rate": 4.9399651022747415e-05, "loss": 4.8903, "step": 1300 }, { "epoch": 0.07000645716745588, "grad_norm": 1.7838680744171143, "learning_rate": 4.93987300666237e-05, "loss": 4.6711, "step": 1301 }, { "epoch": 0.07006026689625484, "grad_norm": 1.2453972101211548, "learning_rate": 4.9397808413249904e-05, "loss": 4.9076, "step": 1302 }, { "epoch": 0.07011407662505381, "grad_norm": 2.0582666397094727, "learning_rate": 4.939688606265236e-05, "loss": 4.9613, "step": 1303 }, { "epoch": 0.07016788635385278, "grad_norm": 1.6777207851409912, "learning_rate": 4.939596301485743e-05, "loss": 4.7029, "step": 1304 }, { "epoch": 0.07022169608265175, "grad_norm": 2.0209903717041016, "learning_rate": 4.939503926989151e-05, "loss": 4.3646, "step": 1305 }, { "epoch": 0.07027550581145071, "grad_norm": 1.3843425512313843, "learning_rate": 4.9394114827780966e-05, "loss": 5.0591, "step": 1306 }, { "epoch": 0.07032931554024968, "grad_norm": 1.0675560235977173, "learning_rate": 4.9393189688552246e-05, "loss": 4.9164, "step": 1307 }, { "epoch": 0.07038312526904865, "grad_norm": 1.9637655019760132, "learning_rate": 4.939226385223176e-05, "loss": 4.7023, "step": 1308 }, { "epoch": 0.07043693499784762, "grad_norm": 2.1579270362854004, "learning_rate": 4.939133731884599e-05, "loss": 4.6688, "step": 1309 }, { "epoch": 0.07049074472664658, "grad_norm": 1.7492201328277588, "learning_rate": 4.9390410088421405e-05, "loss": 4.8709, "step": 1310 }, { "epoch": 0.07054455445544554, "grad_norm": 1.6936110258102417, "learning_rate": 4.93894821609845e-05, "loss": 4.8119, "step": 1311 }, { "epoch": 0.0705983641842445, "grad_norm": 1.5197174549102783, "learning_rate": 4.938855353656179e-05, "loss": 4.8249, "step": 1312 }, { "epoch": 0.07065217391304347, "grad_norm": 1.3546769618988037, "learning_rate": 4.938762421517983e-05, "loss": 4.9403, "step": 1313 }, { "epoch": 0.07070598364184244, "grad_norm": 1.1088283061981201, "learning_rate": 4.938669419686516e-05, "loss": 4.8337, "step": 1314 }, { "epoch": 0.07075979337064141, "grad_norm": 1.564928650856018, "learning_rate": 4.9385763481644356e-05, "loss": 4.5208, "step": 1315 }, { "epoch": 0.07081360309944038, "grad_norm": 1.5665441751480103, "learning_rate": 4.9384832069544023e-05, "loss": 4.8458, "step": 1316 }, { "epoch": 0.07086741282823934, "grad_norm": 1.5582194328308105, "learning_rate": 4.938389996059078e-05, "loss": 4.8826, "step": 1317 }, { "epoch": 0.07092122255703831, "grad_norm": 1.886569857597351, "learning_rate": 4.938296715481126e-05, "loss": 4.4974, "step": 1318 }, { "epoch": 0.07097503228583728, "grad_norm": 1.380468487739563, "learning_rate": 4.9382033652232127e-05, "loss": 4.6741, "step": 1319 }, { "epoch": 0.07102884201463625, "grad_norm": 1.805958867073059, "learning_rate": 4.938109945288004e-05, "loss": 4.8369, "step": 1320 }, { "epoch": 0.07108265174343521, "grad_norm": 1.2273625135421753, "learning_rate": 4.938016455678172e-05, "loss": 4.9542, "step": 1321 }, { "epoch": 0.07113646147223418, "grad_norm": 1.416166067123413, "learning_rate": 4.937922896396387e-05, "loss": 4.7254, "step": 1322 }, { "epoch": 0.07119027120103315, "grad_norm": 1.956860899925232, "learning_rate": 4.937829267445322e-05, "loss": 4.9514, "step": 1323 }, { "epoch": 0.07124408092983212, "grad_norm": 2.153315544128418, "learning_rate": 4.937735568827654e-05, "loss": 4.9697, "step": 1324 }, { "epoch": 0.07129789065863108, "grad_norm": 1.2985138893127441, "learning_rate": 4.93764180054606e-05, "loss": 5.0349, "step": 1325 }, { "epoch": 0.07135170038743005, "grad_norm": 1.812728762626648, "learning_rate": 4.93754796260322e-05, "loss": 4.8985, "step": 1326 }, { "epoch": 0.07140551011622902, "grad_norm": 1.3208670616149902, "learning_rate": 4.937454055001816e-05, "loss": 4.5864, "step": 1327 }, { "epoch": 0.07145931984502799, "grad_norm": 1.8737298250198364, "learning_rate": 4.9373600777445306e-05, "loss": 4.7725, "step": 1328 }, { "epoch": 0.07151312957382695, "grad_norm": 1.8246315717697144, "learning_rate": 4.9372660308340504e-05, "loss": 4.9041, "step": 1329 }, { "epoch": 0.07156693930262592, "grad_norm": 1.5917781591415405, "learning_rate": 4.9371719142730614e-05, "loss": 5.176, "step": 1330 }, { "epoch": 0.07162074903142489, "grad_norm": 1.623902440071106, "learning_rate": 4.9370777280642556e-05, "loss": 4.708, "step": 1331 }, { "epoch": 0.07167455876022384, "grad_norm": 1.1224819421768188, "learning_rate": 4.936983472210323e-05, "loss": 4.719, "step": 1332 }, { "epoch": 0.07172836848902281, "grad_norm": 1.5767972469329834, "learning_rate": 4.936889146713957e-05, "loss": 5.0262, "step": 1333 }, { "epoch": 0.07178217821782178, "grad_norm": 1.757869839668274, "learning_rate": 4.9367947515778535e-05, "loss": 4.657, "step": 1334 }, { "epoch": 0.07183598794662074, "grad_norm": 1.2074012756347656, "learning_rate": 4.9367002868047105e-05, "loss": 4.8336, "step": 1335 }, { "epoch": 0.07188979767541971, "grad_norm": 1.2231701612472534, "learning_rate": 4.936605752397227e-05, "loss": 4.6853, "step": 1336 }, { "epoch": 0.07194360740421868, "grad_norm": 1.3110979795455933, "learning_rate": 4.936511148358105e-05, "loss": 4.7152, "step": 1337 }, { "epoch": 0.07199741713301765, "grad_norm": 2.286715030670166, "learning_rate": 4.936416474690048e-05, "loss": 4.7995, "step": 1338 }, { "epoch": 0.07205122686181661, "grad_norm": 1.7137317657470703, "learning_rate": 4.936321731395761e-05, "loss": 4.689, "step": 1339 }, { "epoch": 0.07210503659061558, "grad_norm": 1.5048902034759521, "learning_rate": 4.936226918477953e-05, "loss": 4.9376, "step": 1340 }, { "epoch": 0.07215884631941455, "grad_norm": 1.9638898372650146, "learning_rate": 4.936132035939331e-05, "loss": 4.6843, "step": 1341 }, { "epoch": 0.07221265604821352, "grad_norm": 1.3641432523727417, "learning_rate": 4.936037083782608e-05, "loss": 4.9434, "step": 1342 }, { "epoch": 0.07226646577701248, "grad_norm": 1.188010334968567, "learning_rate": 4.935942062010498e-05, "loss": 5.2268, "step": 1343 }, { "epoch": 0.07232027550581145, "grad_norm": 1.273032307624817, "learning_rate": 4.935846970625715e-05, "loss": 4.9898, "step": 1344 }, { "epoch": 0.07237408523461042, "grad_norm": 1.9692076444625854, "learning_rate": 4.935751809630977e-05, "loss": 5.0984, "step": 1345 }, { "epoch": 0.07242789496340939, "grad_norm": 2.0249855518341064, "learning_rate": 4.9356565790290046e-05, "loss": 5.1888, "step": 1346 }, { "epoch": 0.07248170469220835, "grad_norm": 1.4551723003387451, "learning_rate": 4.935561278822518e-05, "loss": 4.971, "step": 1347 }, { "epoch": 0.07253551442100732, "grad_norm": 1.6785612106323242, "learning_rate": 4.935465909014242e-05, "loss": 4.7322, "step": 1348 }, { "epoch": 0.07258932414980629, "grad_norm": 1.3101061582565308, "learning_rate": 4.9353704696068995e-05, "loss": 4.7992, "step": 1349 }, { "epoch": 0.07264313387860526, "grad_norm": 1.6254431009292603, "learning_rate": 4.93527496060322e-05, "loss": 4.5137, "step": 1350 }, { "epoch": 0.07269694360740422, "grad_norm": 1.9093434810638428, "learning_rate": 4.935179382005932e-05, "loss": 4.707, "step": 1351 }, { "epoch": 0.07275075333620319, "grad_norm": 2.5900561809539795, "learning_rate": 4.935083733817767e-05, "loss": 4.664, "step": 1352 }, { "epoch": 0.07280456306500216, "grad_norm": 1.126718521118164, "learning_rate": 4.934988016041459e-05, "loss": 5.1625, "step": 1353 }, { "epoch": 0.07285837279380111, "grad_norm": 1.478562831878662, "learning_rate": 4.934892228679742e-05, "loss": 5.1267, "step": 1354 }, { "epoch": 0.07291218252260008, "grad_norm": 1.7091786861419678, "learning_rate": 4.9347963717353546e-05, "loss": 4.889, "step": 1355 }, { "epoch": 0.07296599225139905, "grad_norm": 1.7066504955291748, "learning_rate": 4.934700445211036e-05, "loss": 4.7803, "step": 1356 }, { "epoch": 0.07301980198019802, "grad_norm": 1.2106395959854126, "learning_rate": 4.934604449109527e-05, "loss": 4.9865, "step": 1357 }, { "epoch": 0.07307361170899698, "grad_norm": 1.2856824398040771, "learning_rate": 4.9345083834335716e-05, "loss": 5.0109, "step": 1358 }, { "epoch": 0.07312742143779595, "grad_norm": 1.549784541130066, "learning_rate": 4.9344122481859135e-05, "loss": 4.8939, "step": 1359 }, { "epoch": 0.07318123116659492, "grad_norm": 1.5398026704788208, "learning_rate": 4.934316043369303e-05, "loss": 4.8258, "step": 1360 }, { "epoch": 0.07323504089539389, "grad_norm": 2.058438301086426, "learning_rate": 4.9342197689864854e-05, "loss": 4.6329, "step": 1361 }, { "epoch": 0.07328885062419285, "grad_norm": 1.3780736923217773, "learning_rate": 4.934123425040216e-05, "loss": 4.8255, "step": 1362 }, { "epoch": 0.07334266035299182, "grad_norm": 1.7381386756896973, "learning_rate": 4.9340270115332444e-05, "loss": 4.9031, "step": 1363 }, { "epoch": 0.07339647008179079, "grad_norm": 1.431643009185791, "learning_rate": 4.933930528468329e-05, "loss": 4.6126, "step": 1364 }, { "epoch": 0.07345027981058976, "grad_norm": 1.2539713382720947, "learning_rate": 4.933833975848224e-05, "loss": 4.8906, "step": 1365 }, { "epoch": 0.07350408953938872, "grad_norm": 1.7296631336212158, "learning_rate": 4.933737353675692e-05, "loss": 4.6458, "step": 1366 }, { "epoch": 0.07355789926818769, "grad_norm": 1.1778688430786133, "learning_rate": 4.9336406619534914e-05, "loss": 4.9315, "step": 1367 }, { "epoch": 0.07361170899698666, "grad_norm": 3.3600826263427734, "learning_rate": 4.933543900684387e-05, "loss": 4.7414, "step": 1368 }, { "epoch": 0.07366551872578563, "grad_norm": 2.2413859367370605, "learning_rate": 4.933447069871143e-05, "loss": 4.4286, "step": 1369 }, { "epoch": 0.07371932845458459, "grad_norm": 1.284281611442566, "learning_rate": 4.933350169516527e-05, "loss": 4.6768, "step": 1370 }, { "epoch": 0.07377313818338356, "grad_norm": 1.811223030090332, "learning_rate": 4.933253199623308e-05, "loss": 4.4663, "step": 1371 }, { "epoch": 0.07382694791218253, "grad_norm": 1.9360101222991943, "learning_rate": 4.9331561601942575e-05, "loss": 4.8326, "step": 1372 }, { "epoch": 0.0738807576409815, "grad_norm": 1.1767922639846802, "learning_rate": 4.9330590512321486e-05, "loss": 4.6587, "step": 1373 }, { "epoch": 0.07393456736978046, "grad_norm": 1.767230749130249, "learning_rate": 4.932961872739755e-05, "loss": 4.9797, "step": 1374 }, { "epoch": 0.07398837709857942, "grad_norm": 1.9543477296829224, "learning_rate": 4.932864624719856e-05, "loss": 4.893, "step": 1375 }, { "epoch": 0.07404218682737838, "grad_norm": 1.3319416046142578, "learning_rate": 4.93276730717523e-05, "loss": 4.6915, "step": 1376 }, { "epoch": 0.07409599655617735, "grad_norm": 1.1846715211868286, "learning_rate": 4.932669920108657e-05, "loss": 5.326, "step": 1377 }, { "epoch": 0.07414980628497632, "grad_norm": 1.9222217798233032, "learning_rate": 4.932572463522921e-05, "loss": 4.7346, "step": 1378 }, { "epoch": 0.07420361601377529, "grad_norm": 1.3910716772079468, "learning_rate": 4.932474937420807e-05, "loss": 4.9214, "step": 1379 }, { "epoch": 0.07425742574257425, "grad_norm": 1.636051058769226, "learning_rate": 4.9323773418051014e-05, "loss": 4.8348, "step": 1380 }, { "epoch": 0.07431123547137322, "grad_norm": 2.0404438972473145, "learning_rate": 4.932279676678594e-05, "loss": 4.6788, "step": 1381 }, { "epoch": 0.07436504520017219, "grad_norm": 1.709633469581604, "learning_rate": 4.932181942044075e-05, "loss": 4.6416, "step": 1382 }, { "epoch": 0.07441885492897116, "grad_norm": 1.811087727546692, "learning_rate": 4.9320841379043384e-05, "loss": 4.8471, "step": 1383 }, { "epoch": 0.07447266465777012, "grad_norm": 1.091881513595581, "learning_rate": 4.931986264262179e-05, "loss": 4.9794, "step": 1384 }, { "epoch": 0.07452647438656909, "grad_norm": 0.9905086159706116, "learning_rate": 4.931888321120393e-05, "loss": 4.7215, "step": 1385 }, { "epoch": 0.07458028411536806, "grad_norm": 0.8749421238899231, "learning_rate": 4.93179030848178e-05, "loss": 4.8718, "step": 1386 }, { "epoch": 0.07463409384416703, "grad_norm": 1.2048152685165405, "learning_rate": 4.9316922263491407e-05, "loss": 5.1069, "step": 1387 }, { "epoch": 0.074687903572966, "grad_norm": 1.1200400590896606, "learning_rate": 4.9315940747252774e-05, "loss": 4.6962, "step": 1388 }, { "epoch": 0.07474171330176496, "grad_norm": 1.1999298334121704, "learning_rate": 4.931495853612997e-05, "loss": 4.9215, "step": 1389 }, { "epoch": 0.07479552303056393, "grad_norm": 1.566713571548462, "learning_rate": 4.931397563015104e-05, "loss": 5.0588, "step": 1390 }, { "epoch": 0.0748493327593629, "grad_norm": 1.6605042219161987, "learning_rate": 4.9312992029344086e-05, "loss": 5.059, "step": 1391 }, { "epoch": 0.07490314248816186, "grad_norm": 1.3731310367584229, "learning_rate": 4.931200773373721e-05, "loss": 4.9676, "step": 1392 }, { "epoch": 0.07495695221696083, "grad_norm": 1.7565399408340454, "learning_rate": 4.931102274335856e-05, "loss": 4.7979, "step": 1393 }, { "epoch": 0.0750107619457598, "grad_norm": 1.3042254447937012, "learning_rate": 4.9310037058236254e-05, "loss": 4.7893, "step": 1394 }, { "epoch": 0.07506457167455877, "grad_norm": 2.6442039012908936, "learning_rate": 4.9309050678398474e-05, "loss": 4.3773, "step": 1395 }, { "epoch": 0.07511838140335772, "grad_norm": 1.4016945362091064, "learning_rate": 4.930806360387342e-05, "loss": 4.8189, "step": 1396 }, { "epoch": 0.07517219113215669, "grad_norm": 1.8547635078430176, "learning_rate": 4.9307075834689284e-05, "loss": 4.4571, "step": 1397 }, { "epoch": 0.07522600086095566, "grad_norm": 1.5763636827468872, "learning_rate": 4.93060873708743e-05, "loss": 4.9829, "step": 1398 }, { "epoch": 0.07527981058975462, "grad_norm": 1.4619545936584473, "learning_rate": 4.930509821245671e-05, "loss": 5.0229, "step": 1399 }, { "epoch": 0.07533362031855359, "grad_norm": 1.480145812034607, "learning_rate": 4.930410835946479e-05, "loss": 5.0274, "step": 1400 }, { "epoch": 0.07538743004735256, "grad_norm": 1.4821906089782715, "learning_rate": 4.9303117811926825e-05, "loss": 4.8311, "step": 1401 }, { "epoch": 0.07544123977615153, "grad_norm": 1.1016485691070557, "learning_rate": 4.930212656987112e-05, "loss": 4.9471, "step": 1402 }, { "epoch": 0.07549504950495049, "grad_norm": 1.2067203521728516, "learning_rate": 4.9301134633325994e-05, "loss": 4.7284, "step": 1403 }, { "epoch": 0.07554885923374946, "grad_norm": 1.7959344387054443, "learning_rate": 4.9300142002319814e-05, "loss": 4.8504, "step": 1404 }, { "epoch": 0.07560266896254843, "grad_norm": 1.780130386352539, "learning_rate": 4.929914867688093e-05, "loss": 4.9483, "step": 1405 }, { "epoch": 0.0756564786913474, "grad_norm": 1.6822631359100342, "learning_rate": 4.9298154657037734e-05, "loss": 4.5627, "step": 1406 }, { "epoch": 0.07571028842014636, "grad_norm": 1.9332103729248047, "learning_rate": 4.929715994281864e-05, "loss": 4.9792, "step": 1407 }, { "epoch": 0.07576409814894533, "grad_norm": 1.9729609489440918, "learning_rate": 4.929616453425205e-05, "loss": 4.6931, "step": 1408 }, { "epoch": 0.0758179078777443, "grad_norm": 3.336193323135376, "learning_rate": 4.929516843136644e-05, "loss": 5.0594, "step": 1409 }, { "epoch": 0.07587171760654327, "grad_norm": 1.922236442565918, "learning_rate": 4.929417163419026e-05, "loss": 4.5507, "step": 1410 }, { "epoch": 0.07592552733534223, "grad_norm": 1.8982428312301636, "learning_rate": 4.9293174142751994e-05, "loss": 4.5808, "step": 1411 }, { "epoch": 0.0759793370641412, "grad_norm": 1.7379910945892334, "learning_rate": 4.929217595708015e-05, "loss": 4.8509, "step": 1412 }, { "epoch": 0.07603314679294017, "grad_norm": 1.2019861936569214, "learning_rate": 4.929117707720326e-05, "loss": 4.9085, "step": 1413 }, { "epoch": 0.07608695652173914, "grad_norm": 1.0674327611923218, "learning_rate": 4.929017750314987e-05, "loss": 4.9871, "step": 1414 }, { "epoch": 0.0761407662505381, "grad_norm": 1.571671485900879, "learning_rate": 4.9289177234948535e-05, "loss": 4.9603, "step": 1415 }, { "epoch": 0.07619457597933707, "grad_norm": 1.9939314126968384, "learning_rate": 4.928817627262785e-05, "loss": 4.675, "step": 1416 }, { "epoch": 0.07624838570813604, "grad_norm": 1.6051691770553589, "learning_rate": 4.928717461621641e-05, "loss": 5.0349, "step": 1417 }, { "epoch": 0.07630219543693499, "grad_norm": 1.277499794960022, "learning_rate": 4.9286172265742844e-05, "loss": 4.8786, "step": 1418 }, { "epoch": 0.07635600516573396, "grad_norm": 2.0542781352996826, "learning_rate": 4.928516922123579e-05, "loss": 4.422, "step": 1419 }, { "epoch": 0.07640981489453293, "grad_norm": 1.708398461341858, "learning_rate": 4.928416548272393e-05, "loss": 4.9008, "step": 1420 }, { "epoch": 0.0764636246233319, "grad_norm": 2.276777505874634, "learning_rate": 4.9283161050235934e-05, "loss": 4.9979, "step": 1421 }, { "epoch": 0.07651743435213086, "grad_norm": 1.1209102869033813, "learning_rate": 4.928215592380051e-05, "loss": 4.8846, "step": 1422 }, { "epoch": 0.07657124408092983, "grad_norm": 2.1232433319091797, "learning_rate": 4.928115010344638e-05, "loss": 4.5643, "step": 1423 }, { "epoch": 0.0766250538097288, "grad_norm": 1.36068856716156, "learning_rate": 4.9280143589202285e-05, "loss": 4.9333, "step": 1424 }, { "epoch": 0.07667886353852776, "grad_norm": 1.2235043048858643, "learning_rate": 4.9279136381096995e-05, "loss": 4.9094, "step": 1425 }, { "epoch": 0.07673267326732673, "grad_norm": 1.7640185356140137, "learning_rate": 4.927812847915929e-05, "loss": 4.6388, "step": 1426 }, { "epoch": 0.0767864829961257, "grad_norm": 1.585620403289795, "learning_rate": 4.9277119883417974e-05, "loss": 4.7653, "step": 1427 }, { "epoch": 0.07684029272492467, "grad_norm": 1.324849247932434, "learning_rate": 4.927611059390187e-05, "loss": 4.92, "step": 1428 }, { "epoch": 0.07689410245372363, "grad_norm": 1.1797963380813599, "learning_rate": 4.9275100610639826e-05, "loss": 4.7707, "step": 1429 }, { "epoch": 0.0769479121825226, "grad_norm": 1.9036824703216553, "learning_rate": 4.927408993366069e-05, "loss": 4.8244, "step": 1430 }, { "epoch": 0.07700172191132157, "grad_norm": 1.708448052406311, "learning_rate": 4.927307856299336e-05, "loss": 4.9858, "step": 1431 }, { "epoch": 0.07705553164012054, "grad_norm": 1.456147313117981, "learning_rate": 4.9272066498666727e-05, "loss": 4.9598, "step": 1432 }, { "epoch": 0.0771093413689195, "grad_norm": 1.2473268508911133, "learning_rate": 4.9271053740709714e-05, "loss": 4.883, "step": 1433 }, { "epoch": 0.07716315109771847, "grad_norm": 1.3058712482452393, "learning_rate": 4.9270040289151275e-05, "loss": 4.8284, "step": 1434 }, { "epoch": 0.07721696082651744, "grad_norm": 2.2584383487701416, "learning_rate": 4.926902614402036e-05, "loss": 4.9824, "step": 1435 }, { "epoch": 0.0772707705553164, "grad_norm": 1.506519079208374, "learning_rate": 4.926801130534595e-05, "loss": 5.015, "step": 1436 }, { "epoch": 0.07732458028411537, "grad_norm": 1.338596224784851, "learning_rate": 4.926699577315705e-05, "loss": 4.9419, "step": 1437 }, { "epoch": 0.07737839001291434, "grad_norm": 1.4214911460876465, "learning_rate": 4.926597954748269e-05, "loss": 4.6185, "step": 1438 }, { "epoch": 0.0774321997417133, "grad_norm": 1.2535693645477295, "learning_rate": 4.9264962628351896e-05, "loss": 5.0416, "step": 1439 }, { "epoch": 0.07748600947051226, "grad_norm": 1.078538179397583, "learning_rate": 4.926394501579373e-05, "loss": 4.6877, "step": 1440 }, { "epoch": 0.07753981919931123, "grad_norm": 2.4672560691833496, "learning_rate": 4.926292670983729e-05, "loss": 4.1555, "step": 1441 }, { "epoch": 0.0775936289281102, "grad_norm": 1.4709728956222534, "learning_rate": 4.9261907710511656e-05, "loss": 4.9218, "step": 1442 }, { "epoch": 0.07764743865690917, "grad_norm": 1.4763180017471313, "learning_rate": 4.926088801784596e-05, "loss": 4.6673, "step": 1443 }, { "epoch": 0.07770124838570813, "grad_norm": 1.1859130859375, "learning_rate": 4.9259867631869335e-05, "loss": 4.7571, "step": 1444 }, { "epoch": 0.0777550581145071, "grad_norm": 1.1038861274719238, "learning_rate": 4.925884655261095e-05, "loss": 5.0208, "step": 1445 }, { "epoch": 0.07780886784330607, "grad_norm": 1.2695971727371216, "learning_rate": 4.925782478009998e-05, "loss": 5.0431, "step": 1446 }, { "epoch": 0.07786267757210504, "grad_norm": 1.380267858505249, "learning_rate": 4.925680231436561e-05, "loss": 5.1461, "step": 1447 }, { "epoch": 0.077916487300904, "grad_norm": 2.2312114238739014, "learning_rate": 4.9255779155437084e-05, "loss": 4.9492, "step": 1448 }, { "epoch": 0.07797029702970297, "grad_norm": 0.9808217883110046, "learning_rate": 4.925475530334363e-05, "loss": 4.9336, "step": 1449 }, { "epoch": 0.07802410675850194, "grad_norm": 1.936686635017395, "learning_rate": 4.9253730758114506e-05, "loss": 4.7101, "step": 1450 }, { "epoch": 0.0780779164873009, "grad_norm": 1.437538504600525, "learning_rate": 4.9252705519778994e-05, "loss": 4.4632, "step": 1451 }, { "epoch": 0.07813172621609987, "grad_norm": 1.477249026298523, "learning_rate": 4.925167958836638e-05, "loss": 4.8964, "step": 1452 }, { "epoch": 0.07818553594489884, "grad_norm": 1.3208889961242676, "learning_rate": 4.9250652963906006e-05, "loss": 4.7725, "step": 1453 }, { "epoch": 0.07823934567369781, "grad_norm": 1.1043416261672974, "learning_rate": 4.924962564642719e-05, "loss": 4.7956, "step": 1454 }, { "epoch": 0.07829315540249678, "grad_norm": 1.918474555015564, "learning_rate": 4.92485976359593e-05, "loss": 4.8631, "step": 1455 }, { "epoch": 0.07834696513129574, "grad_norm": 2.433725118637085, "learning_rate": 4.9247568932531706e-05, "loss": 5.0944, "step": 1456 }, { "epoch": 0.07840077486009471, "grad_norm": 1.1825312376022339, "learning_rate": 4.924653953617382e-05, "loss": 4.9488, "step": 1457 }, { "epoch": 0.07845458458889368, "grad_norm": 1.1596492528915405, "learning_rate": 4.924550944691504e-05, "loss": 4.6689, "step": 1458 }, { "epoch": 0.07850839431769265, "grad_norm": 1.2441191673278809, "learning_rate": 4.9244478664784816e-05, "loss": 4.6343, "step": 1459 }, { "epoch": 0.0785622040464916, "grad_norm": 1.241461157798767, "learning_rate": 4.9243447189812594e-05, "loss": 5.1297, "step": 1460 }, { "epoch": 0.07861601377529057, "grad_norm": 1.3498899936676025, "learning_rate": 4.9242415022027873e-05, "loss": 4.8622, "step": 1461 }, { "epoch": 0.07866982350408953, "grad_norm": 2.073716640472412, "learning_rate": 4.924138216146012e-05, "loss": 4.7142, "step": 1462 }, { "epoch": 0.0787236332328885, "grad_norm": 2.110020637512207, "learning_rate": 4.9240348608138887e-05, "loss": 4.8604, "step": 1463 }, { "epoch": 0.07877744296168747, "grad_norm": 1.9369570016860962, "learning_rate": 4.923931436209367e-05, "loss": 4.69, "step": 1464 }, { "epoch": 0.07883125269048644, "grad_norm": 2.0298521518707275, "learning_rate": 4.9238279423354055e-05, "loss": 4.6055, "step": 1465 }, { "epoch": 0.0788850624192854, "grad_norm": 1.8055734634399414, "learning_rate": 4.92372437919496e-05, "loss": 5.0905, "step": 1466 }, { "epoch": 0.07893887214808437, "grad_norm": 1.7533012628555298, "learning_rate": 4.923620746790991e-05, "loss": 4.797, "step": 1467 }, { "epoch": 0.07899268187688334, "grad_norm": 1.07462477684021, "learning_rate": 4.9235170451264606e-05, "loss": 4.836, "step": 1468 }, { "epoch": 0.0790464916056823, "grad_norm": 1.5544748306274414, "learning_rate": 4.923413274204331e-05, "loss": 5.0141, "step": 1469 }, { "epoch": 0.07910030133448127, "grad_norm": 1.6622333526611328, "learning_rate": 4.9233094340275685e-05, "loss": 5.0331, "step": 1470 }, { "epoch": 0.07915411106328024, "grad_norm": 1.6305458545684814, "learning_rate": 4.92320552459914e-05, "loss": 4.523, "step": 1471 }, { "epoch": 0.07920792079207921, "grad_norm": 1.5668355226516724, "learning_rate": 4.923101545922015e-05, "loss": 4.5893, "step": 1472 }, { "epoch": 0.07926173052087818, "grad_norm": 1.5160586833953857, "learning_rate": 4.922997497999166e-05, "loss": 4.8286, "step": 1473 }, { "epoch": 0.07931554024967714, "grad_norm": 1.3855277299880981, "learning_rate": 4.922893380833564e-05, "loss": 5.0841, "step": 1474 }, { "epoch": 0.07936934997847611, "grad_norm": 1.8068325519561768, "learning_rate": 4.9227891944281876e-05, "loss": 4.8393, "step": 1475 }, { "epoch": 0.07942315970727508, "grad_norm": 1.1991355419158936, "learning_rate": 4.922684938786012e-05, "loss": 4.9612, "step": 1476 }, { "epoch": 0.07947696943607405, "grad_norm": 2.0684876441955566, "learning_rate": 4.922580613910017e-05, "loss": 4.7423, "step": 1477 }, { "epoch": 0.07953077916487301, "grad_norm": 1.134463906288147, "learning_rate": 4.922476219803185e-05, "loss": 5.0423, "step": 1478 }, { "epoch": 0.07958458889367198, "grad_norm": 1.6072033643722534, "learning_rate": 4.922371756468497e-05, "loss": 4.7262, "step": 1479 }, { "epoch": 0.07963839862247095, "grad_norm": 1.3897857666015625, "learning_rate": 4.9222672239089404e-05, "loss": 5.0626, "step": 1480 }, { "epoch": 0.07969220835126992, "grad_norm": 1.656458854675293, "learning_rate": 4.9221626221275005e-05, "loss": 4.8599, "step": 1481 }, { "epoch": 0.07974601808006887, "grad_norm": 1.4375274181365967, "learning_rate": 4.922057951127169e-05, "loss": 4.6387, "step": 1482 }, { "epoch": 0.07979982780886784, "grad_norm": 2.201317548751831, "learning_rate": 4.9219532109109356e-05, "loss": 4.8827, "step": 1483 }, { "epoch": 0.0798536375376668, "grad_norm": 1.1945900917053223, "learning_rate": 4.921848401481794e-05, "loss": 4.7345, "step": 1484 }, { "epoch": 0.07990744726646577, "grad_norm": 1.8288623094558716, "learning_rate": 4.921743522842738e-05, "loss": 4.6897, "step": 1485 }, { "epoch": 0.07996125699526474, "grad_norm": 1.2435837984085083, "learning_rate": 4.921638574996767e-05, "loss": 4.8599, "step": 1486 }, { "epoch": 0.08001506672406371, "grad_norm": 1.425359845161438, "learning_rate": 4.9215335579468784e-05, "loss": 4.7471, "step": 1487 }, { "epoch": 0.08006887645286268, "grad_norm": 1.0277442932128906, "learning_rate": 4.921428471696074e-05, "loss": 4.7723, "step": 1488 }, { "epoch": 0.08012268618166164, "grad_norm": 2.008527994155884, "learning_rate": 4.921323316247357e-05, "loss": 4.9514, "step": 1489 }, { "epoch": 0.08017649591046061, "grad_norm": 1.1861042976379395, "learning_rate": 4.9212180916037315e-05, "loss": 4.9264, "step": 1490 }, { "epoch": 0.08023030563925958, "grad_norm": 1.4403843879699707, "learning_rate": 4.921112797768206e-05, "loss": 4.9255, "step": 1491 }, { "epoch": 0.08028411536805855, "grad_norm": 2.3102478981018066, "learning_rate": 4.9210074347437886e-05, "loss": 4.3803, "step": 1492 }, { "epoch": 0.08033792509685751, "grad_norm": 1.5606155395507812, "learning_rate": 4.92090200253349e-05, "loss": 4.8074, "step": 1493 }, { "epoch": 0.08039173482565648, "grad_norm": 2.345325231552124, "learning_rate": 4.920796501140324e-05, "loss": 5.0547, "step": 1494 }, { "epoch": 0.08044554455445545, "grad_norm": 2.195010185241699, "learning_rate": 4.920690930567305e-05, "loss": 4.928, "step": 1495 }, { "epoch": 0.08049935428325442, "grad_norm": 2.0751326084136963, "learning_rate": 4.92058529081745e-05, "loss": 4.8855, "step": 1496 }, { "epoch": 0.08055316401205338, "grad_norm": 1.9358575344085693, "learning_rate": 4.9204795818937786e-05, "loss": 4.5586, "step": 1497 }, { "epoch": 0.08060697374085235, "grad_norm": 1.2809875011444092, "learning_rate": 4.920373803799311e-05, "loss": 4.7277, "step": 1498 }, { "epoch": 0.08066078346965132, "grad_norm": 2.4452152252197266, "learning_rate": 4.920267956537069e-05, "loss": 4.6687, "step": 1499 }, { "epoch": 0.08071459319845029, "grad_norm": 1.101351022720337, "learning_rate": 4.92016204011008e-05, "loss": 5.1068, "step": 1500 }, { "epoch": 0.08076840292724925, "grad_norm": 1.4492071866989136, "learning_rate": 4.9200560545213683e-05, "loss": 4.8116, "step": 1501 }, { "epoch": 0.08082221265604822, "grad_norm": 1.2177993059158325, "learning_rate": 4.919949999773964e-05, "loss": 4.8645, "step": 1502 }, { "epoch": 0.08087602238484717, "grad_norm": 1.68211829662323, "learning_rate": 4.9198438758708983e-05, "loss": 4.7947, "step": 1503 }, { "epoch": 0.08092983211364614, "grad_norm": 1.319271445274353, "learning_rate": 4.9197376828152026e-05, "loss": 4.8445, "step": 1504 }, { "epoch": 0.08098364184244511, "grad_norm": 2.203622579574585, "learning_rate": 4.919631420609913e-05, "loss": 4.5982, "step": 1505 }, { "epoch": 0.08103745157124408, "grad_norm": 1.121899962425232, "learning_rate": 4.919525089258064e-05, "loss": 4.7204, "step": 1506 }, { "epoch": 0.08109126130004304, "grad_norm": 1.4238101243972778, "learning_rate": 4.9194186887626966e-05, "loss": 4.9537, "step": 1507 }, { "epoch": 0.08114507102884201, "grad_norm": 0.9793069362640381, "learning_rate": 4.9193122191268505e-05, "loss": 4.7347, "step": 1508 }, { "epoch": 0.08119888075764098, "grad_norm": 1.7973012924194336, "learning_rate": 4.9192056803535684e-05, "loss": 4.8752, "step": 1509 }, { "epoch": 0.08125269048643995, "grad_norm": 1.3469921350479126, "learning_rate": 4.9190990724458955e-05, "loss": 4.9472, "step": 1510 }, { "epoch": 0.08130650021523891, "grad_norm": 1.281006932258606, "learning_rate": 4.9189923954068765e-05, "loss": 4.9664, "step": 1511 }, { "epoch": 0.08136030994403788, "grad_norm": 1.6420824527740479, "learning_rate": 4.918885649239562e-05, "loss": 5.1226, "step": 1512 }, { "epoch": 0.08141411967283685, "grad_norm": 2.717633008956909, "learning_rate": 4.9187788339470006e-05, "loss": 4.5087, "step": 1513 }, { "epoch": 0.08146792940163582, "grad_norm": 1.0026161670684814, "learning_rate": 4.918671949532247e-05, "loss": 4.846, "step": 1514 }, { "epoch": 0.08152173913043478, "grad_norm": 1.5044386386871338, "learning_rate": 4.9185649959983543e-05, "loss": 4.7349, "step": 1515 }, { "epoch": 0.08157554885923375, "grad_norm": 1.8133574724197388, "learning_rate": 4.9184579733483796e-05, "loss": 4.5671, "step": 1516 }, { "epoch": 0.08162935858803272, "grad_norm": 1.6543492078781128, "learning_rate": 4.9183508815853796e-05, "loss": 4.7746, "step": 1517 }, { "epoch": 0.08168316831683169, "grad_norm": 1.5454697608947754, "learning_rate": 4.9182437207124174e-05, "loss": 4.6028, "step": 1518 }, { "epoch": 0.08173697804563065, "grad_norm": 1.3969001770019531, "learning_rate": 4.9181364907325536e-05, "loss": 4.892, "step": 1519 }, { "epoch": 0.08179078777442962, "grad_norm": 1.6781316995620728, "learning_rate": 4.918029191648852e-05, "loss": 4.5692, "step": 1520 }, { "epoch": 0.08184459750322859, "grad_norm": 1.8862535953521729, "learning_rate": 4.917921823464381e-05, "loss": 4.9942, "step": 1521 }, { "epoch": 0.08189840723202756, "grad_norm": 1.8604711294174194, "learning_rate": 4.917814386182207e-05, "loss": 5.133, "step": 1522 }, { "epoch": 0.08195221696082652, "grad_norm": 0.9341810941696167, "learning_rate": 4.917706879805401e-05, "loss": 4.7946, "step": 1523 }, { "epoch": 0.08200602668962548, "grad_norm": 1.3329404592514038, "learning_rate": 4.9175993043370356e-05, "loss": 4.9188, "step": 1524 }, { "epoch": 0.08205983641842444, "grad_norm": 1.5968689918518066, "learning_rate": 4.9174916597801844e-05, "loss": 4.4481, "step": 1525 }, { "epoch": 0.08211364614722341, "grad_norm": 1.4469095468521118, "learning_rate": 4.9173839461379246e-05, "loss": 5.0652, "step": 1526 }, { "epoch": 0.08216745587602238, "grad_norm": 1.3233988285064697, "learning_rate": 4.917276163413332e-05, "loss": 4.7866, "step": 1527 }, { "epoch": 0.08222126560482135, "grad_norm": 1.204572081565857, "learning_rate": 4.91716831160949e-05, "loss": 4.9585, "step": 1528 }, { "epoch": 0.08227507533362031, "grad_norm": 2.401655673980713, "learning_rate": 4.917060390729479e-05, "loss": 4.8069, "step": 1529 }, { "epoch": 0.08232888506241928, "grad_norm": 1.4819858074188232, "learning_rate": 4.9169524007763826e-05, "loss": 4.4923, "step": 1530 }, { "epoch": 0.08238269479121825, "grad_norm": 2.003018379211426, "learning_rate": 4.916844341753287e-05, "loss": 4.8206, "step": 1531 }, { "epoch": 0.08243650452001722, "grad_norm": 2.055743455886841, "learning_rate": 4.9167362136632814e-05, "loss": 5.0645, "step": 1532 }, { "epoch": 0.08249031424881619, "grad_norm": 2.2959108352661133, "learning_rate": 4.9166280165094544e-05, "loss": 4.4319, "step": 1533 }, { "epoch": 0.08254412397761515, "grad_norm": 2.298915147781372, "learning_rate": 4.916519750294899e-05, "loss": 4.542, "step": 1534 }, { "epoch": 0.08259793370641412, "grad_norm": 1.0786998271942139, "learning_rate": 4.916411415022709e-05, "loss": 5.2151, "step": 1535 }, { "epoch": 0.08265174343521309, "grad_norm": 1.506905436515808, "learning_rate": 4.91630301069598e-05, "loss": 4.8597, "step": 1536 }, { "epoch": 0.08270555316401206, "grad_norm": 1.4120701551437378, "learning_rate": 4.9161945373178096e-05, "loss": 4.9158, "step": 1537 }, { "epoch": 0.08275936289281102, "grad_norm": 1.647460699081421, "learning_rate": 4.916085994891299e-05, "loss": 4.7451, "step": 1538 }, { "epoch": 0.08281317262160999, "grad_norm": 1.5528982877731323, "learning_rate": 4.915977383419549e-05, "loss": 4.892, "step": 1539 }, { "epoch": 0.08286698235040896, "grad_norm": 1.385907769203186, "learning_rate": 4.915868702905663e-05, "loss": 4.7999, "step": 1540 }, { "epoch": 0.08292079207920793, "grad_norm": 1.2009801864624023, "learning_rate": 4.9157599533527475e-05, "loss": 4.6651, "step": 1541 }, { "epoch": 0.08297460180800689, "grad_norm": 1.855475902557373, "learning_rate": 4.9156511347639106e-05, "loss": 4.6779, "step": 1542 }, { "epoch": 0.08302841153680586, "grad_norm": 1.2607940435409546, "learning_rate": 4.915542247142262e-05, "loss": 4.4933, "step": 1543 }, { "epoch": 0.08308222126560483, "grad_norm": 1.6596260070800781, "learning_rate": 4.9154332904909115e-05, "loss": 4.6188, "step": 1544 }, { "epoch": 0.0831360309944038, "grad_norm": 1.9734692573547363, "learning_rate": 4.915324264812976e-05, "loss": 4.5939, "step": 1545 }, { "epoch": 0.08318984072320275, "grad_norm": 1.410636067390442, "learning_rate": 4.9152151701115685e-05, "loss": 4.7672, "step": 1546 }, { "epoch": 0.08324365045200172, "grad_norm": 1.644832730293274, "learning_rate": 4.915106006389808e-05, "loss": 4.9157, "step": 1547 }, { "epoch": 0.08329746018080068, "grad_norm": 1.6479792594909668, "learning_rate": 4.914996773650813e-05, "loss": 4.8461, "step": 1548 }, { "epoch": 0.08335126990959965, "grad_norm": 2.8330278396606445, "learning_rate": 4.9148874718977065e-05, "loss": 5.1151, "step": 1549 }, { "epoch": 0.08340507963839862, "grad_norm": 1.4548912048339844, "learning_rate": 4.914778101133611e-05, "loss": 5.262, "step": 1550 }, { "epoch": 0.08345888936719759, "grad_norm": 1.4883887767791748, "learning_rate": 4.914668661361653e-05, "loss": 4.441, "step": 1551 }, { "epoch": 0.08351269909599655, "grad_norm": 1.179362177848816, "learning_rate": 4.914559152584959e-05, "loss": 4.9248, "step": 1552 }, { "epoch": 0.08356650882479552, "grad_norm": 2.0903773307800293, "learning_rate": 4.914449574806658e-05, "loss": 4.705, "step": 1553 }, { "epoch": 0.08362031855359449, "grad_norm": 0.959035336971283, "learning_rate": 4.914339928029883e-05, "loss": 4.543, "step": 1554 }, { "epoch": 0.08367412828239346, "grad_norm": 1.208752155303955, "learning_rate": 4.9142302122577666e-05, "loss": 4.7704, "step": 1555 }, { "epoch": 0.08372793801119242, "grad_norm": 1.5530213117599487, "learning_rate": 4.914120427493444e-05, "loss": 4.8062, "step": 1556 }, { "epoch": 0.08378174773999139, "grad_norm": 1.5061089992523193, "learning_rate": 4.914010573740053e-05, "loss": 4.7266, "step": 1557 }, { "epoch": 0.08383555746879036, "grad_norm": 1.4152960777282715, "learning_rate": 4.9139006510007335e-05, "loss": 4.7354, "step": 1558 }, { "epoch": 0.08388936719758933, "grad_norm": 1.5942686796188354, "learning_rate": 4.9137906592786256e-05, "loss": 4.7213, "step": 1559 }, { "epoch": 0.0839431769263883, "grad_norm": 1.5952931642532349, "learning_rate": 4.913680598576872e-05, "loss": 4.9222, "step": 1560 }, { "epoch": 0.08399698665518726, "grad_norm": 1.3073692321777344, "learning_rate": 4.91357046889862e-05, "loss": 4.7965, "step": 1561 }, { "epoch": 0.08405079638398623, "grad_norm": 0.9193435311317444, "learning_rate": 4.9134602702470154e-05, "loss": 4.665, "step": 1562 }, { "epoch": 0.0841046061127852, "grad_norm": 0.9589701890945435, "learning_rate": 4.913350002625208e-05, "loss": 4.7642, "step": 1563 }, { "epoch": 0.08415841584158416, "grad_norm": 1.638839840888977, "learning_rate": 4.913239666036348e-05, "loss": 4.8618, "step": 1564 }, { "epoch": 0.08421222557038313, "grad_norm": 1.1158604621887207, "learning_rate": 4.913129260483589e-05, "loss": 5.0451, "step": 1565 }, { "epoch": 0.0842660352991821, "grad_norm": 1.9643070697784424, "learning_rate": 4.913018785970087e-05, "loss": 5.0756, "step": 1566 }, { "epoch": 0.08431984502798105, "grad_norm": 1.3679699897766113, "learning_rate": 4.912908242498998e-05, "loss": 4.6293, "step": 1567 }, { "epoch": 0.08437365475678002, "grad_norm": 2.4669408798217773, "learning_rate": 4.912797630073482e-05, "loss": 4.4302, "step": 1568 }, { "epoch": 0.08442746448557899, "grad_norm": 1.0402629375457764, "learning_rate": 4.912686948696699e-05, "loss": 4.8317, "step": 1569 }, { "epoch": 0.08448127421437795, "grad_norm": 1.5368598699569702, "learning_rate": 4.912576198371812e-05, "loss": 5.1763, "step": 1570 }, { "epoch": 0.08453508394317692, "grad_norm": 1.8038561344146729, "learning_rate": 4.912465379101987e-05, "loss": 4.5786, "step": 1571 }, { "epoch": 0.08458889367197589, "grad_norm": 2.013927459716797, "learning_rate": 4.91235449089039e-05, "loss": 4.6196, "step": 1572 }, { "epoch": 0.08464270340077486, "grad_norm": 1.7731842994689941, "learning_rate": 4.91224353374019e-05, "loss": 4.8707, "step": 1573 }, { "epoch": 0.08469651312957382, "grad_norm": 1.1735080480575562, "learning_rate": 4.9121325076545576e-05, "loss": 4.8286, "step": 1574 }, { "epoch": 0.08475032285837279, "grad_norm": 1.452446460723877, "learning_rate": 4.912021412636667e-05, "loss": 4.9436, "step": 1575 }, { "epoch": 0.08480413258717176, "grad_norm": 1.6277893781661987, "learning_rate": 4.9119102486896914e-05, "loss": 4.6139, "step": 1576 }, { "epoch": 0.08485794231597073, "grad_norm": 1.4784913063049316, "learning_rate": 4.911799015816808e-05, "loss": 4.6704, "step": 1577 }, { "epoch": 0.0849117520447697, "grad_norm": 1.48597252368927, "learning_rate": 4.911687714021196e-05, "loss": 4.8751, "step": 1578 }, { "epoch": 0.08496556177356866, "grad_norm": 1.1860891580581665, "learning_rate": 4.911576343306036e-05, "loss": 4.7444, "step": 1579 }, { "epoch": 0.08501937150236763, "grad_norm": 1.7905704975128174, "learning_rate": 4.9114649036745095e-05, "loss": 5.076, "step": 1580 }, { "epoch": 0.0850731812311666, "grad_norm": 1.5059784650802612, "learning_rate": 4.911353395129803e-05, "loss": 4.5847, "step": 1581 }, { "epoch": 0.08512699095996556, "grad_norm": 1.6557637453079224, "learning_rate": 4.9112418176751026e-05, "loss": 4.686, "step": 1582 }, { "epoch": 0.08518080068876453, "grad_norm": 1.0705021619796753, "learning_rate": 4.911130171313596e-05, "loss": 4.8268, "step": 1583 }, { "epoch": 0.0852346104175635, "grad_norm": 1.920087218284607, "learning_rate": 4.911018456048474e-05, "loss": 4.8008, "step": 1584 }, { "epoch": 0.08528842014636247, "grad_norm": 1.893750786781311, "learning_rate": 4.91090667188293e-05, "loss": 4.7167, "step": 1585 }, { "epoch": 0.08534222987516143, "grad_norm": 1.0638383626937866, "learning_rate": 4.9107948188201575e-05, "loss": 4.9918, "step": 1586 }, { "epoch": 0.0853960396039604, "grad_norm": 1.4341846704483032, "learning_rate": 4.910682896863353e-05, "loss": 4.6802, "step": 1587 }, { "epoch": 0.08544984933275936, "grad_norm": 1.9117591381072998, "learning_rate": 4.910570906015716e-05, "loss": 4.6448, "step": 1588 }, { "epoch": 0.08550365906155832, "grad_norm": 1.8236445188522339, "learning_rate": 4.9104588462804455e-05, "loss": 4.9608, "step": 1589 }, { "epoch": 0.08555746879035729, "grad_norm": 1.2935184240341187, "learning_rate": 4.910346717660745e-05, "loss": 4.8052, "step": 1590 }, { "epoch": 0.08561127851915626, "grad_norm": 1.2346253395080566, "learning_rate": 4.910234520159819e-05, "loss": 4.9618, "step": 1591 }, { "epoch": 0.08566508824795523, "grad_norm": 2.755831241607666, "learning_rate": 4.910122253780872e-05, "loss": 4.8404, "step": 1592 }, { "epoch": 0.0857188979767542, "grad_norm": 2.601470947265625, "learning_rate": 4.910009918527114e-05, "loss": 4.7317, "step": 1593 }, { "epoch": 0.08577270770555316, "grad_norm": 1.9696364402770996, "learning_rate": 4.909897514401755e-05, "loss": 4.7744, "step": 1594 }, { "epoch": 0.08582651743435213, "grad_norm": 1.5230517387390137, "learning_rate": 4.9097850414080065e-05, "loss": 5.0983, "step": 1595 }, { "epoch": 0.0858803271631511, "grad_norm": 1.2238030433654785, "learning_rate": 4.9096724995490826e-05, "loss": 5.0105, "step": 1596 }, { "epoch": 0.08593413689195006, "grad_norm": 1.3286904096603394, "learning_rate": 4.9095598888282014e-05, "loss": 4.6804, "step": 1597 }, { "epoch": 0.08598794662074903, "grad_norm": 1.6423039436340332, "learning_rate": 4.9094472092485785e-05, "loss": 4.8943, "step": 1598 }, { "epoch": 0.086041756349548, "grad_norm": 1.3139057159423828, "learning_rate": 4.909334460813435e-05, "loss": 4.979, "step": 1599 }, { "epoch": 0.08609556607834697, "grad_norm": 1.4235093593597412, "learning_rate": 4.909221643525993e-05, "loss": 4.9051, "step": 1600 }, { "epoch": 0.08614937580714593, "grad_norm": 1.7490264177322388, "learning_rate": 4.9091087573894765e-05, "loss": 4.2548, "step": 1601 }, { "epoch": 0.0862031855359449, "grad_norm": 1.263035774230957, "learning_rate": 4.9089958024071115e-05, "loss": 4.7051, "step": 1602 }, { "epoch": 0.08625699526474387, "grad_norm": 1.2270996570587158, "learning_rate": 4.9088827785821255e-05, "loss": 4.7572, "step": 1603 }, { "epoch": 0.08631080499354284, "grad_norm": 1.4772870540618896, "learning_rate": 4.908769685917749e-05, "loss": 5.1452, "step": 1604 }, { "epoch": 0.0863646147223418, "grad_norm": 1.529206395149231, "learning_rate": 4.9086565244172144e-05, "loss": 5.05, "step": 1605 }, { "epoch": 0.08641842445114077, "grad_norm": 1.2331217527389526, "learning_rate": 4.908543294083755e-05, "loss": 4.734, "step": 1606 }, { "epoch": 0.08647223417993974, "grad_norm": 1.0161586999893188, "learning_rate": 4.908429994920605e-05, "loss": 4.6058, "step": 1607 }, { "epoch": 0.0865260439087387, "grad_norm": 1.3303874731063843, "learning_rate": 4.908316626931005e-05, "loss": 4.792, "step": 1608 }, { "epoch": 0.08657985363753767, "grad_norm": 2.0354976654052734, "learning_rate": 4.908203190118193e-05, "loss": 5.1975, "step": 1609 }, { "epoch": 0.08663366336633663, "grad_norm": 1.1694661378860474, "learning_rate": 4.908089684485411e-05, "loss": 4.7891, "step": 1610 }, { "epoch": 0.0866874730951356, "grad_norm": 1.5889075994491577, "learning_rate": 4.907976110035903e-05, "loss": 4.6663, "step": 1611 }, { "epoch": 0.08674128282393456, "grad_norm": 2.483680248260498, "learning_rate": 4.9078624667729144e-05, "loss": 5.0356, "step": 1612 }, { "epoch": 0.08679509255273353, "grad_norm": 1.9002866744995117, "learning_rate": 4.9077487546996927e-05, "loss": 5.0287, "step": 1613 }, { "epoch": 0.0868489022815325, "grad_norm": 1.4264073371887207, "learning_rate": 4.9076349738194876e-05, "loss": 4.8459, "step": 1614 }, { "epoch": 0.08690271201033146, "grad_norm": 1.749895691871643, "learning_rate": 4.907521124135551e-05, "loss": 4.561, "step": 1615 }, { "epoch": 0.08695652173913043, "grad_norm": 2.111785411834717, "learning_rate": 4.907407205651136e-05, "loss": 4.8266, "step": 1616 }, { "epoch": 0.0870103314679294, "grad_norm": 1.982405424118042, "learning_rate": 4.907293218369499e-05, "loss": 4.938, "step": 1617 }, { "epoch": 0.08706414119672837, "grad_norm": 0.9400355815887451, "learning_rate": 4.907179162293896e-05, "loss": 4.7516, "step": 1618 }, { "epoch": 0.08711795092552733, "grad_norm": 2.438404083251953, "learning_rate": 4.907065037427586e-05, "loss": 4.61, "step": 1619 }, { "epoch": 0.0871717606543263, "grad_norm": 1.4977328777313232, "learning_rate": 4.906950843773833e-05, "loss": 4.7822, "step": 1620 }, { "epoch": 0.08722557038312527, "grad_norm": 1.0068062543869019, "learning_rate": 4.906836581335899e-05, "loss": 4.444, "step": 1621 }, { "epoch": 0.08727938011192424, "grad_norm": 1.9108409881591797, "learning_rate": 4.906722250117048e-05, "loss": 5.1293, "step": 1622 }, { "epoch": 0.0873331898407232, "grad_norm": 1.7395808696746826, "learning_rate": 4.906607850120549e-05, "loss": 4.9121, "step": 1623 }, { "epoch": 0.08738699956952217, "grad_norm": 1.129618763923645, "learning_rate": 4.9064933813496706e-05, "loss": 4.8322, "step": 1624 }, { "epoch": 0.08744080929832114, "grad_norm": 1.6817244291305542, "learning_rate": 4.906378843807684e-05, "loss": 4.7183, "step": 1625 }, { "epoch": 0.08749461902712011, "grad_norm": 1.4366562366485596, "learning_rate": 4.906264237497863e-05, "loss": 4.841, "step": 1626 }, { "epoch": 0.08754842875591907, "grad_norm": 1.161676049232483, "learning_rate": 4.906149562423481e-05, "loss": 4.5349, "step": 1627 }, { "epoch": 0.08760223848471804, "grad_norm": 1.1005266904830933, "learning_rate": 4.906034818587817e-05, "loss": 4.7419, "step": 1628 }, { "epoch": 0.08765604821351701, "grad_norm": 1.1640119552612305, "learning_rate": 4.90592000599415e-05, "loss": 4.9092, "step": 1629 }, { "epoch": 0.08770985794231598, "grad_norm": 1.607825756072998, "learning_rate": 4.9058051246457595e-05, "loss": 4.6876, "step": 1630 }, { "epoch": 0.08776366767111493, "grad_norm": 1.5667585134506226, "learning_rate": 4.9056901745459295e-05, "loss": 4.7978, "step": 1631 }, { "epoch": 0.0878174773999139, "grad_norm": 1.8081016540527344, "learning_rate": 4.905575155697945e-05, "loss": 5.1747, "step": 1632 }, { "epoch": 0.08787128712871287, "grad_norm": 1.6359071731567383, "learning_rate": 4.905460068105093e-05, "loss": 4.8996, "step": 1633 }, { "epoch": 0.08792509685751183, "grad_norm": 1.3958110809326172, "learning_rate": 4.905344911770662e-05, "loss": 4.9472, "step": 1634 }, { "epoch": 0.0879789065863108, "grad_norm": 1.4638444185256958, "learning_rate": 4.905229686697942e-05, "loss": 4.6992, "step": 1635 }, { "epoch": 0.08803271631510977, "grad_norm": 1.3124725818634033, "learning_rate": 4.9051143928902286e-05, "loss": 4.7358, "step": 1636 }, { "epoch": 0.08808652604390874, "grad_norm": 2.0719826221466064, "learning_rate": 4.904999030350814e-05, "loss": 4.6294, "step": 1637 }, { "epoch": 0.0881403357727077, "grad_norm": 1.3419439792633057, "learning_rate": 4.9048835990829956e-05, "loss": 4.8059, "step": 1638 }, { "epoch": 0.08819414550150667, "grad_norm": 1.036613941192627, "learning_rate": 4.904768099090073e-05, "loss": 4.786, "step": 1639 }, { "epoch": 0.08824795523030564, "grad_norm": 1.1329365968704224, "learning_rate": 4.9046525303753456e-05, "loss": 4.7551, "step": 1640 }, { "epoch": 0.0883017649591046, "grad_norm": 1.1890733242034912, "learning_rate": 4.904536892942117e-05, "loss": 5.0316, "step": 1641 }, { "epoch": 0.08835557468790357, "grad_norm": 1.133653163909912, "learning_rate": 4.904421186793691e-05, "loss": 4.8334, "step": 1642 }, { "epoch": 0.08840938441670254, "grad_norm": 1.2103761434555054, "learning_rate": 4.9043054119333755e-05, "loss": 4.6701, "step": 1643 }, { "epoch": 0.08846319414550151, "grad_norm": 1.0262259244918823, "learning_rate": 4.9041895683644766e-05, "loss": 4.8031, "step": 1644 }, { "epoch": 0.08851700387430048, "grad_norm": 1.323559045791626, "learning_rate": 4.9040736560903074e-05, "loss": 4.8478, "step": 1645 }, { "epoch": 0.08857081360309944, "grad_norm": 1.1055278778076172, "learning_rate": 4.9039576751141796e-05, "loss": 5.1059, "step": 1646 }, { "epoch": 0.08862462333189841, "grad_norm": 2.1702280044555664, "learning_rate": 4.903841625439407e-05, "loss": 4.657, "step": 1647 }, { "epoch": 0.08867843306069738, "grad_norm": 2.3075857162475586, "learning_rate": 4.903725507069307e-05, "loss": 4.5915, "step": 1648 }, { "epoch": 0.08873224278949635, "grad_norm": 1.8511383533477783, "learning_rate": 4.903609320007196e-05, "loss": 4.8224, "step": 1649 }, { "epoch": 0.08878605251829531, "grad_norm": 1.389581322669983, "learning_rate": 4.903493064256396e-05, "loss": 4.7139, "step": 1650 }, { "epoch": 0.08883986224709428, "grad_norm": 2.164104461669922, "learning_rate": 4.903376739820229e-05, "loss": 4.7347, "step": 1651 }, { "epoch": 0.08889367197589323, "grad_norm": 1.3178309202194214, "learning_rate": 4.903260346702019e-05, "loss": 4.5259, "step": 1652 }, { "epoch": 0.0889474817046922, "grad_norm": 1.5467824935913086, "learning_rate": 4.903143884905093e-05, "loss": 4.7207, "step": 1653 }, { "epoch": 0.08900129143349117, "grad_norm": 1.5726042985916138, "learning_rate": 4.9030273544327777e-05, "loss": 4.7526, "step": 1654 }, { "epoch": 0.08905510116229014, "grad_norm": 1.1715118885040283, "learning_rate": 4.902910755288403e-05, "loss": 4.8326, "step": 1655 }, { "epoch": 0.0891089108910891, "grad_norm": 1.4043827056884766, "learning_rate": 4.902794087475304e-05, "loss": 5.0305, "step": 1656 }, { "epoch": 0.08916272061988807, "grad_norm": 1.81935453414917, "learning_rate": 4.9026773509968115e-05, "loss": 4.6892, "step": 1657 }, { "epoch": 0.08921653034868704, "grad_norm": 2.002201557159424, "learning_rate": 4.902560545856263e-05, "loss": 4.5612, "step": 1658 }, { "epoch": 0.08927034007748601, "grad_norm": 2.231562376022339, "learning_rate": 4.902443672056997e-05, "loss": 4.9004, "step": 1659 }, { "epoch": 0.08932414980628497, "grad_norm": 1.2419770956039429, "learning_rate": 4.902326729602351e-05, "loss": 4.7503, "step": 1660 }, { "epoch": 0.08937795953508394, "grad_norm": 1.3446900844573975, "learning_rate": 4.90220971849567e-05, "loss": 4.9377, "step": 1661 }, { "epoch": 0.08943176926388291, "grad_norm": 1.5298718214035034, "learning_rate": 4.902092638740297e-05, "loss": 5.0285, "step": 1662 }, { "epoch": 0.08948557899268188, "grad_norm": 1.2670809030532837, "learning_rate": 4.9019754903395755e-05, "loss": 4.9978, "step": 1663 }, { "epoch": 0.08953938872148084, "grad_norm": 1.337347149848938, "learning_rate": 4.901858273296855e-05, "loss": 5.0007, "step": 1664 }, { "epoch": 0.08959319845027981, "grad_norm": 1.0882748365402222, "learning_rate": 4.901740987615487e-05, "loss": 4.7685, "step": 1665 }, { "epoch": 0.08964700817907878, "grad_norm": 1.2596627473831177, "learning_rate": 4.9016236332988206e-05, "loss": 5.0356, "step": 1666 }, { "epoch": 0.08970081790787775, "grad_norm": 2.0475943088531494, "learning_rate": 4.90150621035021e-05, "loss": 4.8261, "step": 1667 }, { "epoch": 0.08975462763667671, "grad_norm": 1.4114352464675903, "learning_rate": 4.901388718773012e-05, "loss": 4.5836, "step": 1668 }, { "epoch": 0.08980843736547568, "grad_norm": 1.2657781839370728, "learning_rate": 4.901271158570583e-05, "loss": 4.6935, "step": 1669 }, { "epoch": 0.08986224709427465, "grad_norm": 1.6712117195129395, "learning_rate": 4.901153529746283e-05, "loss": 4.7654, "step": 1670 }, { "epoch": 0.08991605682307362, "grad_norm": 0.9471811652183533, "learning_rate": 4.901035832303473e-05, "loss": 4.8978, "step": 1671 }, { "epoch": 0.08996986655187258, "grad_norm": 2.0332608222961426, "learning_rate": 4.9009180662455175e-05, "loss": 4.9917, "step": 1672 }, { "epoch": 0.09002367628067154, "grad_norm": 1.694192886352539, "learning_rate": 4.9008002315757804e-05, "loss": 5.0366, "step": 1673 }, { "epoch": 0.0900774860094705, "grad_norm": 1.6511235237121582, "learning_rate": 4.900682328297631e-05, "loss": 5.1148, "step": 1674 }, { "epoch": 0.09013129573826947, "grad_norm": 1.6223640441894531, "learning_rate": 4.9005643564144375e-05, "loss": 4.8199, "step": 1675 }, { "epoch": 0.09018510546706844, "grad_norm": 2.3153529167175293, "learning_rate": 4.900446315929572e-05, "loss": 4.8681, "step": 1676 }, { "epoch": 0.09023891519586741, "grad_norm": 1.2246001958847046, "learning_rate": 4.900328206846407e-05, "loss": 4.6471, "step": 1677 }, { "epoch": 0.09029272492466638, "grad_norm": 1.3384532928466797, "learning_rate": 4.900210029168317e-05, "loss": 4.7978, "step": 1678 }, { "epoch": 0.09034653465346534, "grad_norm": 1.468916654586792, "learning_rate": 4.9000917828986816e-05, "loss": 4.812, "step": 1679 }, { "epoch": 0.09040034438226431, "grad_norm": 1.3978744745254517, "learning_rate": 4.8999734680408784e-05, "loss": 5.0124, "step": 1680 }, { "epoch": 0.09045415411106328, "grad_norm": 1.2071051597595215, "learning_rate": 4.8998550845982876e-05, "loss": 4.8699, "step": 1681 }, { "epoch": 0.09050796383986225, "grad_norm": 1.4628146886825562, "learning_rate": 4.899736632574294e-05, "loss": 4.5674, "step": 1682 }, { "epoch": 0.09056177356866121, "grad_norm": 1.6006755828857422, "learning_rate": 4.899618111972282e-05, "loss": 4.4433, "step": 1683 }, { "epoch": 0.09061558329746018, "grad_norm": 1.3443243503570557, "learning_rate": 4.899499522795638e-05, "loss": 4.7464, "step": 1684 }, { "epoch": 0.09066939302625915, "grad_norm": 1.3562589883804321, "learning_rate": 4.8993808650477516e-05, "loss": 4.4664, "step": 1685 }, { "epoch": 0.09072320275505812, "grad_norm": 1.8114852905273438, "learning_rate": 4.899262138732014e-05, "loss": 4.5738, "step": 1686 }, { "epoch": 0.09077701248385708, "grad_norm": 1.5908318758010864, "learning_rate": 4.899143343851818e-05, "loss": 4.9246, "step": 1687 }, { "epoch": 0.09083082221265605, "grad_norm": 2.2291083335876465, "learning_rate": 4.899024480410558e-05, "loss": 4.3797, "step": 1688 }, { "epoch": 0.09088463194145502, "grad_norm": 1.0574405193328857, "learning_rate": 4.8989055484116306e-05, "loss": 4.7895, "step": 1689 }, { "epoch": 0.09093844167025399, "grad_norm": 1.2002437114715576, "learning_rate": 4.898786547858435e-05, "loss": 4.8447, "step": 1690 }, { "epoch": 0.09099225139905295, "grad_norm": 1.2231279611587524, "learning_rate": 4.898667478754372e-05, "loss": 5.0165, "step": 1691 }, { "epoch": 0.09104606112785192, "grad_norm": 1.3228081464767456, "learning_rate": 4.8985483411028444e-05, "loss": 4.8521, "step": 1692 }, { "epoch": 0.09109987085665089, "grad_norm": 1.4987473487854004, "learning_rate": 4.8984291349072564e-05, "loss": 4.3386, "step": 1693 }, { "epoch": 0.09115368058544986, "grad_norm": 1.1817134618759155, "learning_rate": 4.8983098601710145e-05, "loss": 5.0594, "step": 1694 }, { "epoch": 0.09120749031424881, "grad_norm": 1.5851998329162598, "learning_rate": 4.898190516897528e-05, "loss": 4.8109, "step": 1695 }, { "epoch": 0.09126130004304778, "grad_norm": 1.6441237926483154, "learning_rate": 4.898071105090206e-05, "loss": 4.3235, "step": 1696 }, { "epoch": 0.09131510977184674, "grad_norm": 1.1102207899093628, "learning_rate": 4.897951624752463e-05, "loss": 4.9675, "step": 1697 }, { "epoch": 0.09136891950064571, "grad_norm": 1.2101590633392334, "learning_rate": 4.897832075887712e-05, "loss": 4.7869, "step": 1698 }, { "epoch": 0.09142272922944468, "grad_norm": 1.7056732177734375, "learning_rate": 4.897712458499369e-05, "loss": 4.8369, "step": 1699 }, { "epoch": 0.09147653895824365, "grad_norm": 2.0014445781707764, "learning_rate": 4.897592772590853e-05, "loss": 4.7856, "step": 1700 }, { "epoch": 0.09153034868704261, "grad_norm": 1.648635983467102, "learning_rate": 4.897473018165585e-05, "loss": 4.8097, "step": 1701 }, { "epoch": 0.09158415841584158, "grad_norm": 1.7219449281692505, "learning_rate": 4.8973531952269865e-05, "loss": 4.8236, "step": 1702 }, { "epoch": 0.09163796814464055, "grad_norm": 1.7730443477630615, "learning_rate": 4.8972333037784814e-05, "loss": 4.611, "step": 1703 }, { "epoch": 0.09169177787343952, "grad_norm": 0.926308810710907, "learning_rate": 4.8971133438234965e-05, "loss": 4.9545, "step": 1704 }, { "epoch": 0.09174558760223848, "grad_norm": 1.6322895288467407, "learning_rate": 4.896993315365459e-05, "loss": 4.8459, "step": 1705 }, { "epoch": 0.09179939733103745, "grad_norm": 1.7621289491653442, "learning_rate": 4.896873218407801e-05, "loss": 4.9461, "step": 1706 }, { "epoch": 0.09185320705983642, "grad_norm": 2.322435140609741, "learning_rate": 4.896753052953953e-05, "loss": 4.7589, "step": 1707 }, { "epoch": 0.09190701678863539, "grad_norm": 1.234574794769287, "learning_rate": 4.8966328190073484e-05, "loss": 4.9667, "step": 1708 }, { "epoch": 0.09196082651743435, "grad_norm": 1.6539465188980103, "learning_rate": 4.896512516571424e-05, "loss": 4.974, "step": 1709 }, { "epoch": 0.09201463624623332, "grad_norm": 1.299691915512085, "learning_rate": 4.896392145649619e-05, "loss": 4.7724, "step": 1710 }, { "epoch": 0.09206844597503229, "grad_norm": 1.86015784740448, "learning_rate": 4.896271706245371e-05, "loss": 4.6638, "step": 1711 }, { "epoch": 0.09212225570383126, "grad_norm": 1.3004695177078247, "learning_rate": 4.896151198362123e-05, "loss": 4.8866, "step": 1712 }, { "epoch": 0.09217606543263022, "grad_norm": 1.4934918880462646, "learning_rate": 4.896030622003319e-05, "loss": 4.8886, "step": 1713 }, { "epoch": 0.09222987516142919, "grad_norm": 1.3468178510665894, "learning_rate": 4.895909977172404e-05, "loss": 4.5303, "step": 1714 }, { "epoch": 0.09228368489022816, "grad_norm": 1.1781346797943115, "learning_rate": 4.8957892638728266e-05, "loss": 4.8871, "step": 1715 }, { "epoch": 0.09233749461902711, "grad_norm": 1.664321780204773, "learning_rate": 4.8956684821080354e-05, "loss": 5.0002, "step": 1716 }, { "epoch": 0.09239130434782608, "grad_norm": 1.9947632551193237, "learning_rate": 4.895547631881483e-05, "loss": 4.8826, "step": 1717 }, { "epoch": 0.09244511407662505, "grad_norm": 1.1560821533203125, "learning_rate": 4.8954267131966225e-05, "loss": 4.7243, "step": 1718 }, { "epoch": 0.09249892380542402, "grad_norm": 1.9040806293487549, "learning_rate": 4.895305726056909e-05, "loss": 4.1884, "step": 1719 }, { "epoch": 0.09255273353422298, "grad_norm": 1.1680078506469727, "learning_rate": 4.895184670465801e-05, "loss": 4.7762, "step": 1720 }, { "epoch": 0.09260654326302195, "grad_norm": 1.8898547887802124, "learning_rate": 4.895063546426757e-05, "loss": 4.6282, "step": 1721 }, { "epoch": 0.09266035299182092, "grad_norm": 1.4740971326828003, "learning_rate": 4.8949423539432396e-05, "loss": 4.632, "step": 1722 }, { "epoch": 0.09271416272061989, "grad_norm": 1.6635651588439941, "learning_rate": 4.89482109301871e-05, "loss": 4.549, "step": 1723 }, { "epoch": 0.09276797244941885, "grad_norm": 2.108173370361328, "learning_rate": 4.8946997636566364e-05, "loss": 4.6446, "step": 1724 }, { "epoch": 0.09282178217821782, "grad_norm": 1.320846676826477, "learning_rate": 4.8945783658604825e-05, "loss": 4.7697, "step": 1725 }, { "epoch": 0.09287559190701679, "grad_norm": 1.2813156843185425, "learning_rate": 4.8944568996337214e-05, "loss": 5.0105, "step": 1726 }, { "epoch": 0.09292940163581576, "grad_norm": 1.3439269065856934, "learning_rate": 4.8943353649798216e-05, "loss": 4.9868, "step": 1727 }, { "epoch": 0.09298321136461472, "grad_norm": 1.3144125938415527, "learning_rate": 4.8942137619022576e-05, "loss": 4.8527, "step": 1728 }, { "epoch": 0.09303702109341369, "grad_norm": 1.8848720788955688, "learning_rate": 4.894092090404504e-05, "loss": 4.5796, "step": 1729 }, { "epoch": 0.09309083082221266, "grad_norm": 1.5627778768539429, "learning_rate": 4.893970350490037e-05, "loss": 4.7562, "step": 1730 }, { "epoch": 0.09314464055101163, "grad_norm": 1.526063084602356, "learning_rate": 4.893848542162337e-05, "loss": 4.8887, "step": 1731 }, { "epoch": 0.0931984502798106, "grad_norm": 1.4606834650039673, "learning_rate": 4.893726665424885e-05, "loss": 4.6991, "step": 1732 }, { "epoch": 0.09325226000860956, "grad_norm": 1.4437154531478882, "learning_rate": 4.893604720281162e-05, "loss": 4.7753, "step": 1733 }, { "epoch": 0.09330606973740853, "grad_norm": 1.404153823852539, "learning_rate": 4.8934827067346544e-05, "loss": 4.6416, "step": 1734 }, { "epoch": 0.0933598794662075, "grad_norm": 3.08998703956604, "learning_rate": 4.893360624788849e-05, "loss": 4.7769, "step": 1735 }, { "epoch": 0.09341368919500646, "grad_norm": 1.2431392669677734, "learning_rate": 4.893238474447235e-05, "loss": 4.9635, "step": 1736 }, { "epoch": 0.09346749892380542, "grad_norm": 1.3223857879638672, "learning_rate": 4.8931162557133013e-05, "loss": 4.4903, "step": 1737 }, { "epoch": 0.09352130865260438, "grad_norm": 2.065150737762451, "learning_rate": 4.892993968590542e-05, "loss": 4.2992, "step": 1738 }, { "epoch": 0.09357511838140335, "grad_norm": 1.7851868867874146, "learning_rate": 4.8928716130824525e-05, "loss": 5.1325, "step": 1739 }, { "epoch": 0.09362892811020232, "grad_norm": 1.363927960395813, "learning_rate": 4.892749189192527e-05, "loss": 4.8139, "step": 1740 }, { "epoch": 0.09368273783900129, "grad_norm": 1.3788663148880005, "learning_rate": 4.8926266969242664e-05, "loss": 4.7687, "step": 1741 }, { "epoch": 0.09373654756780025, "grad_norm": 1.7923555374145508, "learning_rate": 4.89250413628117e-05, "loss": 4.9314, "step": 1742 }, { "epoch": 0.09379035729659922, "grad_norm": 1.9621881246566772, "learning_rate": 4.89238150726674e-05, "loss": 4.8969, "step": 1743 }, { "epoch": 0.09384416702539819, "grad_norm": 1.0860645771026611, "learning_rate": 4.892258809884481e-05, "loss": 4.8115, "step": 1744 }, { "epoch": 0.09389797675419716, "grad_norm": 1.845758080482483, "learning_rate": 4.8921360441379e-05, "loss": 4.7349, "step": 1745 }, { "epoch": 0.09395178648299612, "grad_norm": 1.4245109558105469, "learning_rate": 4.892013210030506e-05, "loss": 4.8438, "step": 1746 }, { "epoch": 0.09400559621179509, "grad_norm": 1.7748782634735107, "learning_rate": 4.891890307565807e-05, "loss": 4.5234, "step": 1747 }, { "epoch": 0.09405940594059406, "grad_norm": 2.0616395473480225, "learning_rate": 4.891767336747317e-05, "loss": 4.692, "step": 1748 }, { "epoch": 0.09411321566939303, "grad_norm": 2.003556251525879, "learning_rate": 4.891644297578549e-05, "loss": 4.6397, "step": 1749 }, { "epoch": 0.094167025398192, "grad_norm": 1.1651675701141357, "learning_rate": 4.891521190063021e-05, "loss": 4.9552, "step": 1750 }, { "epoch": 0.09422083512699096, "grad_norm": 1.3995689153671265, "learning_rate": 4.891398014204249e-05, "loss": 4.8232, "step": 1751 }, { "epoch": 0.09427464485578993, "grad_norm": 2.1237106323242188, "learning_rate": 4.891274770005754e-05, "loss": 4.484, "step": 1752 }, { "epoch": 0.0943284545845889, "grad_norm": 1.0243310928344727, "learning_rate": 4.891151457471057e-05, "loss": 4.6568, "step": 1753 }, { "epoch": 0.09438226431338786, "grad_norm": 1.3407529592514038, "learning_rate": 4.8910280766036835e-05, "loss": 4.7635, "step": 1754 }, { "epoch": 0.09443607404218683, "grad_norm": 1.2711009979248047, "learning_rate": 4.890904627407159e-05, "loss": 4.7645, "step": 1755 }, { "epoch": 0.0944898837709858, "grad_norm": 1.538223385810852, "learning_rate": 4.89078110988501e-05, "loss": 5.1798, "step": 1756 }, { "epoch": 0.09454369349978477, "grad_norm": 2.2444820404052734, "learning_rate": 4.8906575240407685e-05, "loss": 4.9725, "step": 1757 }, { "epoch": 0.09459750322858373, "grad_norm": 1.7459115982055664, "learning_rate": 4.890533869877965e-05, "loss": 4.8307, "step": 1758 }, { "epoch": 0.09465131295738269, "grad_norm": 1.835579752922058, "learning_rate": 4.8904101474001326e-05, "loss": 4.7004, "step": 1759 }, { "epoch": 0.09470512268618166, "grad_norm": 1.2512084245681763, "learning_rate": 4.890286356610808e-05, "loss": 4.6502, "step": 1760 }, { "epoch": 0.09475893241498062, "grad_norm": 2.1397149562835693, "learning_rate": 4.890162497513529e-05, "loss": 4.4974, "step": 1761 }, { "epoch": 0.09481274214377959, "grad_norm": 1.8418259620666504, "learning_rate": 4.890038570111833e-05, "loss": 4.4034, "step": 1762 }, { "epoch": 0.09486655187257856, "grad_norm": 1.2020058631896973, "learning_rate": 4.8899145744092644e-05, "loss": 5.0577, "step": 1763 }, { "epoch": 0.09492036160137753, "grad_norm": 1.8816159963607788, "learning_rate": 4.8897905104093646e-05, "loss": 4.7824, "step": 1764 }, { "epoch": 0.0949741713301765, "grad_norm": 1.3733417987823486, "learning_rate": 4.8896663781156804e-05, "loss": 4.6025, "step": 1765 }, { "epoch": 0.09502798105897546, "grad_norm": 1.652668833732605, "learning_rate": 4.8895421775317585e-05, "loss": 4.9816, "step": 1766 }, { "epoch": 0.09508179078777443, "grad_norm": 2.01625657081604, "learning_rate": 4.889417908661148e-05, "loss": 4.4325, "step": 1767 }, { "epoch": 0.0951356005165734, "grad_norm": 1.1965539455413818, "learning_rate": 4.8892935715074006e-05, "loss": 4.8046, "step": 1768 }, { "epoch": 0.09518941024537236, "grad_norm": 1.1696641445159912, "learning_rate": 4.8891691660740695e-05, "loss": 4.8524, "step": 1769 }, { "epoch": 0.09524321997417133, "grad_norm": 1.2151849269866943, "learning_rate": 4.889044692364709e-05, "loss": 4.8336, "step": 1770 }, { "epoch": 0.0952970297029703, "grad_norm": 1.5506949424743652, "learning_rate": 4.8889201503828786e-05, "loss": 5.1327, "step": 1771 }, { "epoch": 0.09535083943176927, "grad_norm": 1.6270161867141724, "learning_rate": 4.8887955401321344e-05, "loss": 4.7742, "step": 1772 }, { "epoch": 0.09540464916056823, "grad_norm": 1.672387719154358, "learning_rate": 4.888670861616039e-05, "loss": 4.8638, "step": 1773 }, { "epoch": 0.0954584588893672, "grad_norm": 1.6598930358886719, "learning_rate": 4.888546114838155e-05, "loss": 4.6276, "step": 1774 }, { "epoch": 0.09551226861816617, "grad_norm": 1.6383309364318848, "learning_rate": 4.888421299802048e-05, "loss": 5.051, "step": 1775 }, { "epoch": 0.09556607834696514, "grad_norm": 1.170621633529663, "learning_rate": 4.8882964165112845e-05, "loss": 4.5738, "step": 1776 }, { "epoch": 0.0956198880757641, "grad_norm": 1.2754732370376587, "learning_rate": 4.888171464969432e-05, "loss": 4.8333, "step": 1777 }, { "epoch": 0.09567369780456307, "grad_norm": 1.1105557680130005, "learning_rate": 4.8880464451800634e-05, "loss": 4.6941, "step": 1778 }, { "epoch": 0.09572750753336204, "grad_norm": 1.971024990081787, "learning_rate": 4.887921357146751e-05, "loss": 4.711, "step": 1779 }, { "epoch": 0.09578131726216099, "grad_norm": 1.669392466545105, "learning_rate": 4.8877962008730685e-05, "loss": 4.7902, "step": 1780 }, { "epoch": 0.09583512699095996, "grad_norm": 1.504904866218567, "learning_rate": 4.887670976362592e-05, "loss": 4.7916, "step": 1781 }, { "epoch": 0.09588893671975893, "grad_norm": 1.5236912965774536, "learning_rate": 4.887545683618902e-05, "loss": 4.6145, "step": 1782 }, { "epoch": 0.0959427464485579, "grad_norm": 1.6506215333938599, "learning_rate": 4.8874203226455785e-05, "loss": 4.9465, "step": 1783 }, { "epoch": 0.09599655617735686, "grad_norm": 1.3221783638000488, "learning_rate": 4.887294893446202e-05, "loss": 5.1271, "step": 1784 }, { "epoch": 0.09605036590615583, "grad_norm": 1.9680746793746948, "learning_rate": 4.8871693960243606e-05, "loss": 4.8398, "step": 1785 }, { "epoch": 0.0961041756349548, "grad_norm": 1.311873197555542, "learning_rate": 4.887043830383637e-05, "loss": 4.6501, "step": 1786 }, { "epoch": 0.09615798536375376, "grad_norm": 1.460279941558838, "learning_rate": 4.886918196527622e-05, "loss": 4.6093, "step": 1787 }, { "epoch": 0.09621179509255273, "grad_norm": 1.731728434562683, "learning_rate": 4.886792494459904e-05, "loss": 4.9668, "step": 1788 }, { "epoch": 0.0962656048213517, "grad_norm": 1.345057487487793, "learning_rate": 4.8866667241840775e-05, "loss": 4.8616, "step": 1789 }, { "epoch": 0.09631941455015067, "grad_norm": 1.6826485395431519, "learning_rate": 4.8865408857037345e-05, "loss": 4.626, "step": 1790 }, { "epoch": 0.09637322427894963, "grad_norm": 1.4706424474716187, "learning_rate": 4.8864149790224724e-05, "loss": 4.9726, "step": 1791 }, { "epoch": 0.0964270340077486, "grad_norm": 1.8169608116149902, "learning_rate": 4.8862890041438893e-05, "loss": 4.7677, "step": 1792 }, { "epoch": 0.09648084373654757, "grad_norm": 2.066715717315674, "learning_rate": 4.886162961071584e-05, "loss": 4.7146, "step": 1793 }, { "epoch": 0.09653465346534654, "grad_norm": 1.363027811050415, "learning_rate": 4.8860368498091595e-05, "loss": 4.6767, "step": 1794 }, { "epoch": 0.0965884631941455, "grad_norm": 1.1937310695648193, "learning_rate": 4.88591067036022e-05, "loss": 4.8891, "step": 1795 }, { "epoch": 0.09664227292294447, "grad_norm": 1.0821256637573242, "learning_rate": 4.88578442272837e-05, "loss": 4.9349, "step": 1796 }, { "epoch": 0.09669608265174344, "grad_norm": 0.9619722366333008, "learning_rate": 4.885658106917219e-05, "loss": 4.8377, "step": 1797 }, { "epoch": 0.09674989238054241, "grad_norm": 1.3803662061691284, "learning_rate": 4.885531722930375e-05, "loss": 4.5175, "step": 1798 }, { "epoch": 0.09680370210934137, "grad_norm": 1.4677836894989014, "learning_rate": 4.885405270771452e-05, "loss": 4.9022, "step": 1799 }, { "epoch": 0.09685751183814034, "grad_norm": 1.7176121473312378, "learning_rate": 4.8852787504440624e-05, "loss": 4.7031, "step": 1800 }, { "epoch": 0.0969113215669393, "grad_norm": 2.1145873069763184, "learning_rate": 4.8851521619518206e-05, "loss": 4.8227, "step": 1801 }, { "epoch": 0.09696513129573826, "grad_norm": 1.3041006326675415, "learning_rate": 4.885025505298346e-05, "loss": 4.7746, "step": 1802 }, { "epoch": 0.09701894102453723, "grad_norm": 1.147423267364502, "learning_rate": 4.884898780487257e-05, "loss": 4.8214, "step": 1803 }, { "epoch": 0.0970727507533362, "grad_norm": 1.9951632022857666, "learning_rate": 4.884771987522176e-05, "loss": 4.6809, "step": 1804 }, { "epoch": 0.09712656048213517, "grad_norm": 1.240348219871521, "learning_rate": 4.884645126406726e-05, "loss": 4.8733, "step": 1805 }, { "epoch": 0.09718037021093413, "grad_norm": 1.7922558784484863, "learning_rate": 4.8845181971445315e-05, "loss": 4.5975, "step": 1806 }, { "epoch": 0.0972341799397331, "grad_norm": 1.9094882011413574, "learning_rate": 4.884391199739221e-05, "loss": 4.488, "step": 1807 }, { "epoch": 0.09728798966853207, "grad_norm": 1.1581840515136719, "learning_rate": 4.884264134194423e-05, "loss": 4.766, "step": 1808 }, { "epoch": 0.09734179939733104, "grad_norm": 1.3368114233016968, "learning_rate": 4.884137000513769e-05, "loss": 4.7067, "step": 1809 }, { "epoch": 0.09739560912613, "grad_norm": 1.5731450319290161, "learning_rate": 4.884009798700893e-05, "loss": 4.5762, "step": 1810 }, { "epoch": 0.09744941885492897, "grad_norm": 1.7340805530548096, "learning_rate": 4.883882528759428e-05, "loss": 4.6414, "step": 1811 }, { "epoch": 0.09750322858372794, "grad_norm": 1.701902151107788, "learning_rate": 4.8837551906930124e-05, "loss": 4.7888, "step": 1812 }, { "epoch": 0.0975570383125269, "grad_norm": 1.2872555255889893, "learning_rate": 4.883627784505285e-05, "loss": 4.8617, "step": 1813 }, { "epoch": 0.09761084804132587, "grad_norm": 1.513602614402771, "learning_rate": 4.8835003101998865e-05, "loss": 4.35, "step": 1814 }, { "epoch": 0.09766465777012484, "grad_norm": 1.2840423583984375, "learning_rate": 4.883372767780461e-05, "loss": 4.7579, "step": 1815 }, { "epoch": 0.09771846749892381, "grad_norm": 1.1780319213867188, "learning_rate": 4.883245157250652e-05, "loss": 4.7185, "step": 1816 }, { "epoch": 0.09777227722772278, "grad_norm": 1.2197943925857544, "learning_rate": 4.883117478614106e-05, "loss": 4.84, "step": 1817 }, { "epoch": 0.09782608695652174, "grad_norm": 2.005730152130127, "learning_rate": 4.882989731874473e-05, "loss": 4.869, "step": 1818 }, { "epoch": 0.09787989668532071, "grad_norm": 0.9949093461036682, "learning_rate": 4.882861917035402e-05, "loss": 4.7014, "step": 1819 }, { "epoch": 0.09793370641411968, "grad_norm": 2.1143836975097656, "learning_rate": 4.882734034100547e-05, "loss": 4.7042, "step": 1820 }, { "epoch": 0.09798751614291865, "grad_norm": 1.0394790172576904, "learning_rate": 4.882606083073563e-05, "loss": 4.6039, "step": 1821 }, { "epoch": 0.09804132587171761, "grad_norm": 1.420357584953308, "learning_rate": 4.8824780639581045e-05, "loss": 4.9327, "step": 1822 }, { "epoch": 0.09809513560051657, "grad_norm": 1.5432546138763428, "learning_rate": 4.882349976757832e-05, "loss": 5.0976, "step": 1823 }, { "epoch": 0.09814894532931553, "grad_norm": 1.3056389093399048, "learning_rate": 4.8822218214764036e-05, "loss": 4.7584, "step": 1824 }, { "epoch": 0.0982027550581145, "grad_norm": 1.5221034288406372, "learning_rate": 4.882093598117484e-05, "loss": 4.8536, "step": 1825 }, { "epoch": 0.09825656478691347, "grad_norm": 1.6696851253509521, "learning_rate": 4.881965306684736e-05, "loss": 4.4663, "step": 1826 }, { "epoch": 0.09831037451571244, "grad_norm": 1.8050825595855713, "learning_rate": 4.8818369471818265e-05, "loss": 4.8155, "step": 1827 }, { "epoch": 0.0983641842445114, "grad_norm": 1.1324548721313477, "learning_rate": 4.8817085196124234e-05, "loss": 4.7117, "step": 1828 }, { "epoch": 0.09841799397331037, "grad_norm": 2.0068042278289795, "learning_rate": 4.881580023980197e-05, "loss": 4.401, "step": 1829 }, { "epoch": 0.09847180370210934, "grad_norm": 1.1573257446289062, "learning_rate": 4.8814514602888185e-05, "loss": 4.8442, "step": 1830 }, { "epoch": 0.09852561343090831, "grad_norm": 1.8951963186264038, "learning_rate": 4.881322828541963e-05, "loss": 5.1232, "step": 1831 }, { "epoch": 0.09857942315970727, "grad_norm": 2.1135709285736084, "learning_rate": 4.8811941287433066e-05, "loss": 5.0238, "step": 1832 }, { "epoch": 0.09863323288850624, "grad_norm": 1.3622183799743652, "learning_rate": 4.8810653608965266e-05, "loss": 4.8558, "step": 1833 }, { "epoch": 0.09868704261730521, "grad_norm": 1.0336878299713135, "learning_rate": 4.880936525005302e-05, "loss": 4.8713, "step": 1834 }, { "epoch": 0.09874085234610418, "grad_norm": 1.2870261669158936, "learning_rate": 4.880807621073316e-05, "loss": 4.8066, "step": 1835 }, { "epoch": 0.09879466207490314, "grad_norm": 1.1588579416275024, "learning_rate": 4.880678649104252e-05, "loss": 4.8919, "step": 1836 }, { "epoch": 0.09884847180370211, "grad_norm": 2.06329607963562, "learning_rate": 4.8805496091017954e-05, "loss": 4.2151, "step": 1837 }, { "epoch": 0.09890228153250108, "grad_norm": 1.4436684846878052, "learning_rate": 4.8804205010696335e-05, "loss": 4.4617, "step": 1838 }, { "epoch": 0.09895609126130005, "grad_norm": 1.7859026193618774, "learning_rate": 4.880291325011457e-05, "loss": 4.642, "step": 1839 }, { "epoch": 0.09900990099009901, "grad_norm": 1.1881601810455322, "learning_rate": 4.880162080930956e-05, "loss": 4.6863, "step": 1840 }, { "epoch": 0.09906371071889798, "grad_norm": 0.96369868516922, "learning_rate": 4.8800327688318246e-05, "loss": 4.9876, "step": 1841 }, { "epoch": 0.09911752044769695, "grad_norm": 1.297014594078064, "learning_rate": 4.8799033887177594e-05, "loss": 4.7059, "step": 1842 }, { "epoch": 0.09917133017649592, "grad_norm": 1.7694013118743896, "learning_rate": 4.879773940592455e-05, "loss": 4.9958, "step": 1843 }, { "epoch": 0.09922513990529487, "grad_norm": 0.9492163062095642, "learning_rate": 4.879644424459613e-05, "loss": 4.8606, "step": 1844 }, { "epoch": 0.09927894963409384, "grad_norm": 1.159171223640442, "learning_rate": 4.879514840322934e-05, "loss": 4.8771, "step": 1845 }, { "epoch": 0.0993327593628928, "grad_norm": 1.9394501447677612, "learning_rate": 4.87938518818612e-05, "loss": 5.0996, "step": 1846 }, { "epoch": 0.09938656909169177, "grad_norm": 1.7934741973876953, "learning_rate": 4.879255468052878e-05, "loss": 4.6295, "step": 1847 }, { "epoch": 0.09944037882049074, "grad_norm": 1.9842318296432495, "learning_rate": 4.879125679926913e-05, "loss": 4.8263, "step": 1848 }, { "epoch": 0.09949418854928971, "grad_norm": 1.654815912246704, "learning_rate": 4.878995823811937e-05, "loss": 4.9349, "step": 1849 }, { "epoch": 0.09954799827808868, "grad_norm": 2.2593271732330322, "learning_rate": 4.878865899711658e-05, "loss": 4.4057, "step": 1850 }, { "epoch": 0.09960180800688764, "grad_norm": 1.5015662908554077, "learning_rate": 4.87873590762979e-05, "loss": 4.6788, "step": 1851 }, { "epoch": 0.09965561773568661, "grad_norm": 1.5303869247436523, "learning_rate": 4.878605847570049e-05, "loss": 4.5029, "step": 1852 }, { "epoch": 0.09970942746448558, "grad_norm": 1.7072216272354126, "learning_rate": 4.878475719536149e-05, "loss": 4.6703, "step": 1853 }, { "epoch": 0.09976323719328455, "grad_norm": 1.6846524477005005, "learning_rate": 4.878345523531811e-05, "loss": 5.0429, "step": 1854 }, { "epoch": 0.09981704692208351, "grad_norm": 1.109466314315796, "learning_rate": 4.8782152595607545e-05, "loss": 4.8414, "step": 1855 }, { "epoch": 0.09987085665088248, "grad_norm": 1.7171549797058105, "learning_rate": 4.878084927626703e-05, "loss": 4.6967, "step": 1856 }, { "epoch": 0.09992466637968145, "grad_norm": 1.2066075801849365, "learning_rate": 4.8779545277333806e-05, "loss": 4.6319, "step": 1857 }, { "epoch": 0.09997847610848042, "grad_norm": 1.8321400880813599, "learning_rate": 4.877824059884514e-05, "loss": 4.7787, "step": 1858 }, { "epoch": 0.10003228583727938, "grad_norm": 2.1140902042388916, "learning_rate": 4.877693524083831e-05, "loss": 5.1933, "step": 1859 }, { "epoch": 0.10008609556607835, "grad_norm": 1.7973910570144653, "learning_rate": 4.8775629203350615e-05, "loss": 5.1081, "step": 1860 }, { "epoch": 0.10013990529487732, "grad_norm": 1.3291187286376953, "learning_rate": 4.8774322486419395e-05, "loss": 4.3121, "step": 1861 }, { "epoch": 0.10019371502367629, "grad_norm": 1.3313828706741333, "learning_rate": 4.8773015090081984e-05, "loss": 5.0073, "step": 1862 }, { "epoch": 0.10024752475247525, "grad_norm": 1.5966014862060547, "learning_rate": 4.877170701437574e-05, "loss": 4.7611, "step": 1863 }, { "epoch": 0.10030133448127422, "grad_norm": 1.7236722707748413, "learning_rate": 4.8770398259338054e-05, "loss": 4.7128, "step": 1864 }, { "epoch": 0.10035514421007317, "grad_norm": 1.9667452573776245, "learning_rate": 4.876908882500632e-05, "loss": 4.8918, "step": 1865 }, { "epoch": 0.10040895393887214, "grad_norm": 1.8211610317230225, "learning_rate": 4.876777871141794e-05, "loss": 4.6361, "step": 1866 }, { "epoch": 0.10046276366767111, "grad_norm": 1.6283416748046875, "learning_rate": 4.8766467918610394e-05, "loss": 4.6824, "step": 1867 }, { "epoch": 0.10051657339647008, "grad_norm": 0.9351378083229065, "learning_rate": 4.876515644662111e-05, "loss": 4.8012, "step": 1868 }, { "epoch": 0.10057038312526904, "grad_norm": 1.3619978427886963, "learning_rate": 4.876384429548758e-05, "loss": 4.6169, "step": 1869 }, { "epoch": 0.10062419285406801, "grad_norm": 1.2235841751098633, "learning_rate": 4.87625314652473e-05, "loss": 4.9077, "step": 1870 }, { "epoch": 0.10067800258286698, "grad_norm": 2.106931447982788, "learning_rate": 4.876121795593778e-05, "loss": 4.9419, "step": 1871 }, { "epoch": 0.10073181231166595, "grad_norm": 0.9849228858947754, "learning_rate": 4.875990376759656e-05, "loss": 4.9451, "step": 1872 }, { "epoch": 0.10078562204046491, "grad_norm": 1.1744346618652344, "learning_rate": 4.8758588900261194e-05, "loss": 4.7947, "step": 1873 }, { "epoch": 0.10083943176926388, "grad_norm": 1.4851495027542114, "learning_rate": 4.875727335396927e-05, "loss": 4.846, "step": 1874 }, { "epoch": 0.10089324149806285, "grad_norm": 1.5317877531051636, "learning_rate": 4.875595712875837e-05, "loss": 4.6799, "step": 1875 }, { "epoch": 0.10094705122686182, "grad_norm": 1.3617819547653198, "learning_rate": 4.87546402246661e-05, "loss": 4.7875, "step": 1876 }, { "epoch": 0.10100086095566078, "grad_norm": 1.8828178644180298, "learning_rate": 4.875332264173012e-05, "loss": 4.9169, "step": 1877 }, { "epoch": 0.10105467068445975, "grad_norm": 1.4221606254577637, "learning_rate": 4.875200437998806e-05, "loss": 5.0027, "step": 1878 }, { "epoch": 0.10110848041325872, "grad_norm": 2.4410576820373535, "learning_rate": 4.8750685439477596e-05, "loss": 4.7543, "step": 1879 }, { "epoch": 0.10116229014205769, "grad_norm": 1.0694950819015503, "learning_rate": 4.874936582023643e-05, "loss": 4.8819, "step": 1880 }, { "epoch": 0.10121609987085665, "grad_norm": 1.1601784229278564, "learning_rate": 4.8748045522302265e-05, "loss": 4.9593, "step": 1881 }, { "epoch": 0.10126990959965562, "grad_norm": 2.290566921234131, "learning_rate": 4.874672454571284e-05, "loss": 4.8449, "step": 1882 }, { "epoch": 0.10132371932845459, "grad_norm": 1.183154821395874, "learning_rate": 4.874540289050589e-05, "loss": 4.8647, "step": 1883 }, { "epoch": 0.10137752905725356, "grad_norm": 1.7554999589920044, "learning_rate": 4.874408055671919e-05, "loss": 4.9612, "step": 1884 }, { "epoch": 0.10143133878605252, "grad_norm": 1.9512451887130737, "learning_rate": 4.874275754439055e-05, "loss": 4.7459, "step": 1885 }, { "epoch": 0.10148514851485149, "grad_norm": 2.1535470485687256, "learning_rate": 4.874143385355775e-05, "loss": 4.7929, "step": 1886 }, { "epoch": 0.10153895824365045, "grad_norm": 1.5290018320083618, "learning_rate": 4.8740109484258625e-05, "loss": 5.0255, "step": 1887 }, { "epoch": 0.10159276797244941, "grad_norm": 1.217218041419983, "learning_rate": 4.8738784436531024e-05, "loss": 4.7894, "step": 1888 }, { "epoch": 0.10164657770124838, "grad_norm": 1.0194637775421143, "learning_rate": 4.873745871041281e-05, "loss": 4.8185, "step": 1889 }, { "epoch": 0.10170038743004735, "grad_norm": 1.9313515424728394, "learning_rate": 4.873613230594189e-05, "loss": 4.6087, "step": 1890 }, { "epoch": 0.10175419715884632, "grad_norm": 2.0886900424957275, "learning_rate": 4.8734805223156136e-05, "loss": 4.729, "step": 1891 }, { "epoch": 0.10180800688764528, "grad_norm": 1.2366013526916504, "learning_rate": 4.8733477462093485e-05, "loss": 4.7317, "step": 1892 }, { "epoch": 0.10186181661644425, "grad_norm": 1.6377754211425781, "learning_rate": 4.873214902279189e-05, "loss": 4.3746, "step": 1893 }, { "epoch": 0.10191562634524322, "grad_norm": 1.5711884498596191, "learning_rate": 4.87308199052893e-05, "loss": 4.7202, "step": 1894 }, { "epoch": 0.10196943607404219, "grad_norm": 1.1850602626800537, "learning_rate": 4.872949010962372e-05, "loss": 4.9687, "step": 1895 }, { "epoch": 0.10202324580284115, "grad_norm": 1.8329474925994873, "learning_rate": 4.872815963583313e-05, "loss": 4.6052, "step": 1896 }, { "epoch": 0.10207705553164012, "grad_norm": 1.0260086059570312, "learning_rate": 4.872682848395556e-05, "loss": 4.788, "step": 1897 }, { "epoch": 0.10213086526043909, "grad_norm": 1.8677210807800293, "learning_rate": 4.8725496654029045e-05, "loss": 4.6313, "step": 1898 }, { "epoch": 0.10218467498923806, "grad_norm": 1.6544477939605713, "learning_rate": 4.8724164146091654e-05, "loss": 4.655, "step": 1899 }, { "epoch": 0.10223848471803702, "grad_norm": 1.5759637355804443, "learning_rate": 4.872283096018147e-05, "loss": 4.4228, "step": 1900 }, { "epoch": 0.10229229444683599, "grad_norm": 1.0540326833724976, "learning_rate": 4.872149709633657e-05, "loss": 4.7717, "step": 1901 }, { "epoch": 0.10234610417563496, "grad_norm": 1.9326353073120117, "learning_rate": 4.87201625545951e-05, "loss": 4.588, "step": 1902 }, { "epoch": 0.10239991390443393, "grad_norm": 2.021794319152832, "learning_rate": 4.871882733499517e-05, "loss": 4.2271, "step": 1903 }, { "epoch": 0.1024537236332329, "grad_norm": 2.416884660720825, "learning_rate": 4.8717491437574955e-05, "loss": 4.9993, "step": 1904 }, { "epoch": 0.10250753336203186, "grad_norm": 1.4918323755264282, "learning_rate": 4.871615486237263e-05, "loss": 4.9138, "step": 1905 }, { "epoch": 0.10256134309083083, "grad_norm": 1.3354904651641846, "learning_rate": 4.871481760942639e-05, "loss": 4.842, "step": 1906 }, { "epoch": 0.1026151528196298, "grad_norm": 1.386366605758667, "learning_rate": 4.871347967877444e-05, "loss": 4.6787, "step": 1907 }, { "epoch": 0.10266896254842875, "grad_norm": 2.093756914138794, "learning_rate": 4.871214107045503e-05, "loss": 4.7934, "step": 1908 }, { "epoch": 0.10272277227722772, "grad_norm": 1.6527374982833862, "learning_rate": 4.87108017845064e-05, "loss": 5.0484, "step": 1909 }, { "epoch": 0.10277658200602668, "grad_norm": 0.9899904131889343, "learning_rate": 4.870946182096684e-05, "loss": 4.8156, "step": 1910 }, { "epoch": 0.10283039173482565, "grad_norm": 1.2808387279510498, "learning_rate": 4.870812117987462e-05, "loss": 4.7168, "step": 1911 }, { "epoch": 0.10288420146362462, "grad_norm": 1.0646032094955444, "learning_rate": 4.870677986126807e-05, "loss": 4.7705, "step": 1912 }, { "epoch": 0.10293801119242359, "grad_norm": 2.224790334701538, "learning_rate": 4.8705437865185525e-05, "loss": 4.7609, "step": 1913 }, { "epoch": 0.10299182092122255, "grad_norm": 1.6414378881454468, "learning_rate": 4.8704095191665314e-05, "loss": 4.9216, "step": 1914 }, { "epoch": 0.10304563065002152, "grad_norm": 1.4392549991607666, "learning_rate": 4.870275184074582e-05, "loss": 5.0093, "step": 1915 }, { "epoch": 0.10309944037882049, "grad_norm": 1.380635142326355, "learning_rate": 4.8701407812465424e-05, "loss": 5.125, "step": 1916 }, { "epoch": 0.10315325010761946, "grad_norm": 1.8401062488555908, "learning_rate": 4.870006310686256e-05, "loss": 4.8691, "step": 1917 }, { "epoch": 0.10320705983641842, "grad_norm": 1.9935638904571533, "learning_rate": 4.869871772397562e-05, "loss": 4.6588, "step": 1918 }, { "epoch": 0.10326086956521739, "grad_norm": 1.5484490394592285, "learning_rate": 4.8697371663843085e-05, "loss": 4.8506, "step": 1919 }, { "epoch": 0.10331467929401636, "grad_norm": 1.372771978378296, "learning_rate": 4.8696024926503396e-05, "loss": 4.8375, "step": 1920 }, { "epoch": 0.10336848902281533, "grad_norm": 2.0938966274261475, "learning_rate": 4.869467751199506e-05, "loss": 4.7361, "step": 1921 }, { "epoch": 0.1034222987516143, "grad_norm": 0.8959159851074219, "learning_rate": 4.869332942035656e-05, "loss": 4.6954, "step": 1922 }, { "epoch": 0.10347610848041326, "grad_norm": 1.523787021636963, "learning_rate": 4.869198065162644e-05, "loss": 4.9531, "step": 1923 }, { "epoch": 0.10352991820921223, "grad_norm": 2.233768939971924, "learning_rate": 4.869063120584323e-05, "loss": 4.869, "step": 1924 }, { "epoch": 0.1035837279380112, "grad_norm": 2.224788188934326, "learning_rate": 4.86892810830455e-05, "loss": 4.4609, "step": 1925 }, { "epoch": 0.10363753766681016, "grad_norm": 1.4063678979873657, "learning_rate": 4.868793028327184e-05, "loss": 5.0045, "step": 1926 }, { "epoch": 0.10369134739560913, "grad_norm": 1.4083876609802246, "learning_rate": 4.868657880656085e-05, "loss": 4.7523, "step": 1927 }, { "epoch": 0.1037451571244081, "grad_norm": 1.1786237955093384, "learning_rate": 4.868522665295114e-05, "loss": 4.8092, "step": 1928 }, { "epoch": 0.10379896685320705, "grad_norm": 1.7301839590072632, "learning_rate": 4.8683873822481354e-05, "loss": 5.0401, "step": 1929 }, { "epoch": 0.10385277658200602, "grad_norm": 1.1754133701324463, "learning_rate": 4.8682520315190163e-05, "loss": 5.1847, "step": 1930 }, { "epoch": 0.10390658631080499, "grad_norm": 1.2117060422897339, "learning_rate": 4.868116613111624e-05, "loss": 4.803, "step": 1931 }, { "epoch": 0.10396039603960396, "grad_norm": 1.042384386062622, "learning_rate": 4.867981127029828e-05, "loss": 4.6659, "step": 1932 }, { "epoch": 0.10401420576840292, "grad_norm": 1.2375102043151855, "learning_rate": 4.867845573277501e-05, "loss": 5.0572, "step": 1933 }, { "epoch": 0.10406801549720189, "grad_norm": 1.354000210762024, "learning_rate": 4.8677099518585154e-05, "loss": 4.4413, "step": 1934 }, { "epoch": 0.10412182522600086, "grad_norm": 3.0810227394104004, "learning_rate": 4.8675742627767485e-05, "loss": 4.5714, "step": 1935 }, { "epoch": 0.10417563495479983, "grad_norm": 2.309748411178589, "learning_rate": 4.867438506036077e-05, "loss": 4.4898, "step": 1936 }, { "epoch": 0.1042294446835988, "grad_norm": 1.1884944438934326, "learning_rate": 4.867302681640381e-05, "loss": 5.0035, "step": 1937 }, { "epoch": 0.10428325441239776, "grad_norm": 1.8657759428024292, "learning_rate": 4.867166789593541e-05, "loss": 4.618, "step": 1938 }, { "epoch": 0.10433706414119673, "grad_norm": 1.7394533157348633, "learning_rate": 4.867030829899441e-05, "loss": 4.9766, "step": 1939 }, { "epoch": 0.1043908738699957, "grad_norm": 1.4702404737472534, "learning_rate": 4.866894802561968e-05, "loss": 4.6276, "step": 1940 }, { "epoch": 0.10444468359879466, "grad_norm": 0.8837824463844299, "learning_rate": 4.8667587075850065e-05, "loss": 4.7931, "step": 1941 }, { "epoch": 0.10449849332759363, "grad_norm": 1.3884963989257812, "learning_rate": 4.8666225449724466e-05, "loss": 4.8705, "step": 1942 }, { "epoch": 0.1045523030563926, "grad_norm": 1.7533817291259766, "learning_rate": 4.8664863147281805e-05, "loss": 4.8728, "step": 1943 }, { "epoch": 0.10460611278519157, "grad_norm": 1.3479269742965698, "learning_rate": 4.8663500168561006e-05, "loss": 4.9672, "step": 1944 }, { "epoch": 0.10465992251399053, "grad_norm": 1.6224150657653809, "learning_rate": 4.866213651360102e-05, "loss": 4.7845, "step": 1945 }, { "epoch": 0.1047137322427895, "grad_norm": 1.183273196220398, "learning_rate": 4.8660772182440804e-05, "loss": 4.8291, "step": 1946 }, { "epoch": 0.10476754197158847, "grad_norm": 2.101999044418335, "learning_rate": 4.8659407175119376e-05, "loss": 4.4606, "step": 1947 }, { "epoch": 0.10482135170038744, "grad_norm": 1.2195125818252563, "learning_rate": 4.8658041491675724e-05, "loss": 4.8431, "step": 1948 }, { "epoch": 0.1048751614291864, "grad_norm": 0.9800867438316345, "learning_rate": 4.8656675132148866e-05, "loss": 4.5433, "step": 1949 }, { "epoch": 0.10492897115798537, "grad_norm": 1.6275843381881714, "learning_rate": 4.8655308096577873e-05, "loss": 4.3737, "step": 1950 }, { "epoch": 0.10498278088678432, "grad_norm": 1.3316413164138794, "learning_rate": 4.865394038500179e-05, "loss": 4.7315, "step": 1951 }, { "epoch": 0.10503659061558329, "grad_norm": 1.5641827583312988, "learning_rate": 4.865257199745973e-05, "loss": 4.9108, "step": 1952 }, { "epoch": 0.10509040034438226, "grad_norm": 1.3565208911895752, "learning_rate": 4.865120293399077e-05, "loss": 4.7717, "step": 1953 }, { "epoch": 0.10514421007318123, "grad_norm": 1.6396478414535522, "learning_rate": 4.864983319463404e-05, "loss": 4.6586, "step": 1954 }, { "epoch": 0.1051980198019802, "grad_norm": 1.115729570388794, "learning_rate": 4.8648462779428696e-05, "loss": 4.8514, "step": 1955 }, { "epoch": 0.10525182953077916, "grad_norm": 1.3936140537261963, "learning_rate": 4.864709168841389e-05, "loss": 4.6811, "step": 1956 }, { "epoch": 0.10530563925957813, "grad_norm": 1.984643816947937, "learning_rate": 4.864571992162881e-05, "loss": 4.5427, "step": 1957 }, { "epoch": 0.1053594489883771, "grad_norm": 1.5833879709243774, "learning_rate": 4.864434747911265e-05, "loss": 4.6929, "step": 1958 }, { "epoch": 0.10541325871717606, "grad_norm": 1.5383912324905396, "learning_rate": 4.8642974360904636e-05, "loss": 4.6123, "step": 1959 }, { "epoch": 0.10546706844597503, "grad_norm": 1.1464875936508179, "learning_rate": 4.8641600567043996e-05, "loss": 4.5677, "step": 1960 }, { "epoch": 0.105520878174774, "grad_norm": 1.3718153238296509, "learning_rate": 4.864022609757002e-05, "loss": 4.6104, "step": 1961 }, { "epoch": 0.10557468790357297, "grad_norm": 1.2501298189163208, "learning_rate": 4.863885095252195e-05, "loss": 4.8517, "step": 1962 }, { "epoch": 0.10562849763237193, "grad_norm": 1.1714427471160889, "learning_rate": 4.863747513193911e-05, "loss": 4.7362, "step": 1963 }, { "epoch": 0.1056823073611709, "grad_norm": 1.0315167903900146, "learning_rate": 4.8636098635860804e-05, "loss": 4.7181, "step": 1964 }, { "epoch": 0.10573611708996987, "grad_norm": 1.760271668434143, "learning_rate": 4.863472146432638e-05, "loss": 4.7348, "step": 1965 }, { "epoch": 0.10578992681876884, "grad_norm": 1.4885618686676025, "learning_rate": 4.863334361737518e-05, "loss": 4.879, "step": 1966 }, { "epoch": 0.1058437365475678, "grad_norm": 0.9052768349647522, "learning_rate": 4.8631965095046586e-05, "loss": 4.9143, "step": 1967 }, { "epoch": 0.10589754627636677, "grad_norm": 2.189993143081665, "learning_rate": 4.863058589738e-05, "loss": 4.7973, "step": 1968 }, { "epoch": 0.10595135600516574, "grad_norm": 1.488735318183899, "learning_rate": 4.862920602441481e-05, "loss": 4.4892, "step": 1969 }, { "epoch": 0.1060051657339647, "grad_norm": 0.9652047157287598, "learning_rate": 4.862782547619048e-05, "loss": 4.8339, "step": 1970 }, { "epoch": 0.10605897546276367, "grad_norm": 2.1188035011291504, "learning_rate": 4.862644425274645e-05, "loss": 4.9626, "step": 1971 }, { "epoch": 0.10611278519156263, "grad_norm": 1.7225253582000732, "learning_rate": 4.862506235412219e-05, "loss": 4.547, "step": 1972 }, { "epoch": 0.1061665949203616, "grad_norm": 1.4773224592208862, "learning_rate": 4.862367978035719e-05, "loss": 4.6743, "step": 1973 }, { "epoch": 0.10622040464916056, "grad_norm": 1.4791145324707031, "learning_rate": 4.862229653149096e-05, "loss": 4.9028, "step": 1974 }, { "epoch": 0.10627421437795953, "grad_norm": 1.4650940895080566, "learning_rate": 4.862091260756303e-05, "loss": 4.9189, "step": 1975 }, { "epoch": 0.1063280241067585, "grad_norm": 1.526556372642517, "learning_rate": 4.861952800861296e-05, "loss": 4.6292, "step": 1976 }, { "epoch": 0.10638183383555747, "grad_norm": 1.633817434310913, "learning_rate": 4.86181427346803e-05, "loss": 4.295, "step": 1977 }, { "epoch": 0.10643564356435643, "grad_norm": 1.6860991716384888, "learning_rate": 4.8616756785804654e-05, "loss": 4.9753, "step": 1978 }, { "epoch": 0.1064894532931554, "grad_norm": 1.340676188468933, "learning_rate": 4.8615370162025605e-05, "loss": 4.7332, "step": 1979 }, { "epoch": 0.10654326302195437, "grad_norm": 1.9502485990524292, "learning_rate": 4.8613982863382814e-05, "loss": 4.5136, "step": 1980 }, { "epoch": 0.10659707275075334, "grad_norm": 1.9292978048324585, "learning_rate": 4.8612594889915894e-05, "loss": 4.8282, "step": 1981 }, { "epoch": 0.1066508824795523, "grad_norm": 1.9810887575149536, "learning_rate": 4.861120624166453e-05, "loss": 4.7924, "step": 1982 }, { "epoch": 0.10670469220835127, "grad_norm": 1.1512082815170288, "learning_rate": 4.8609816918668394e-05, "loss": 4.5792, "step": 1983 }, { "epoch": 0.10675850193715024, "grad_norm": 1.4607629776000977, "learning_rate": 4.8608426920967185e-05, "loss": 4.9548, "step": 1984 }, { "epoch": 0.1068123116659492, "grad_norm": 1.4400622844696045, "learning_rate": 4.860703624860065e-05, "loss": 4.8503, "step": 1985 }, { "epoch": 0.10686612139474817, "grad_norm": 1.5835464000701904, "learning_rate": 4.860564490160851e-05, "loss": 5.0546, "step": 1986 }, { "epoch": 0.10691993112354714, "grad_norm": 1.8207836151123047, "learning_rate": 4.860425288003052e-05, "loss": 4.9625, "step": 1987 }, { "epoch": 0.10697374085234611, "grad_norm": 1.8014470338821411, "learning_rate": 4.8602860183906485e-05, "loss": 4.7019, "step": 1988 }, { "epoch": 0.10702755058114508, "grad_norm": 1.8971242904663086, "learning_rate": 4.860146681327618e-05, "loss": 4.476, "step": 1989 }, { "epoch": 0.10708136030994404, "grad_norm": 1.1193915605545044, "learning_rate": 4.860007276817944e-05, "loss": 5.1458, "step": 1990 }, { "epoch": 0.10713517003874301, "grad_norm": 1.4123053550720215, "learning_rate": 4.859867804865609e-05, "loss": 4.9775, "step": 1991 }, { "epoch": 0.10718897976754198, "grad_norm": 1.5339033603668213, "learning_rate": 4.8597282654746e-05, "loss": 4.8244, "step": 1992 }, { "epoch": 0.10724278949634093, "grad_norm": 1.2478002309799194, "learning_rate": 4.859588658648904e-05, "loss": 4.9097, "step": 1993 }, { "epoch": 0.1072965992251399, "grad_norm": 1.2570241689682007, "learning_rate": 4.859448984392511e-05, "loss": 4.7881, "step": 1994 }, { "epoch": 0.10735040895393887, "grad_norm": 1.40201997756958, "learning_rate": 4.8593092427094116e-05, "loss": 4.7348, "step": 1995 }, { "epoch": 0.10740421868273783, "grad_norm": 1.4803282022476196, "learning_rate": 4.8591694336036e-05, "loss": 4.852, "step": 1996 }, { "epoch": 0.1074580284115368, "grad_norm": 0.9006062150001526, "learning_rate": 4.8590295570790717e-05, "loss": 4.5578, "step": 1997 }, { "epoch": 0.10751183814033577, "grad_norm": 1.216911792755127, "learning_rate": 4.8588896131398236e-05, "loss": 4.9643, "step": 1998 }, { "epoch": 0.10756564786913474, "grad_norm": 1.4101812839508057, "learning_rate": 4.858749601789855e-05, "loss": 4.868, "step": 1999 }, { "epoch": 0.1076194575979337, "grad_norm": 1.844762921333313, "learning_rate": 4.858609523033167e-05, "loss": 4.9795, "step": 2000 }, { "epoch": 0.10767326732673267, "grad_norm": 1.54127037525177, "learning_rate": 4.858469376873763e-05, "loss": 5.039, "step": 2001 }, { "epoch": 0.10772707705553164, "grad_norm": 1.681921124458313, "learning_rate": 4.858329163315647e-05, "loss": 4.7, "step": 2002 }, { "epoch": 0.1077808867843306, "grad_norm": 1.711504578590393, "learning_rate": 4.858188882362827e-05, "loss": 5.038, "step": 2003 }, { "epoch": 0.10783469651312957, "grad_norm": 1.610231876373291, "learning_rate": 4.8580485340193123e-05, "loss": 4.8643, "step": 2004 }, { "epoch": 0.10788850624192854, "grad_norm": 1.6066241264343262, "learning_rate": 4.8579081182891115e-05, "loss": 4.9021, "step": 2005 }, { "epoch": 0.10794231597072751, "grad_norm": 1.0568735599517822, "learning_rate": 4.8577676351762404e-05, "loss": 5.0352, "step": 2006 }, { "epoch": 0.10799612569952648, "grad_norm": 1.0015170574188232, "learning_rate": 4.8576270846847104e-05, "loss": 4.7084, "step": 2007 }, { "epoch": 0.10804993542832544, "grad_norm": 0.9921973347663879, "learning_rate": 4.8574864668185406e-05, "loss": 4.9452, "step": 2008 }, { "epoch": 0.10810374515712441, "grad_norm": 1.3031046390533447, "learning_rate": 4.857345781581748e-05, "loss": 4.8924, "step": 2009 }, { "epoch": 0.10815755488592338, "grad_norm": 0.9302647113800049, "learning_rate": 4.8572050289783536e-05, "loss": 4.7679, "step": 2010 }, { "epoch": 0.10821136461472235, "grad_norm": 1.6832128763198853, "learning_rate": 4.85706420901238e-05, "loss": 4.5223, "step": 2011 }, { "epoch": 0.10826517434352131, "grad_norm": 1.929157018661499, "learning_rate": 4.856923321687851e-05, "loss": 4.5136, "step": 2012 }, { "epoch": 0.10831898407232028, "grad_norm": 1.816399335861206, "learning_rate": 4.856782367008792e-05, "loss": 4.6108, "step": 2013 }, { "epoch": 0.10837279380111924, "grad_norm": 1.5058432817459106, "learning_rate": 4.856641344979232e-05, "loss": 4.3522, "step": 2014 }, { "epoch": 0.1084266035299182, "grad_norm": 1.7018307447433472, "learning_rate": 4.856500255603202e-05, "loss": 4.7757, "step": 2015 }, { "epoch": 0.10848041325871717, "grad_norm": 1.204832911491394, "learning_rate": 4.8563590988847326e-05, "loss": 4.6319, "step": 2016 }, { "epoch": 0.10853422298751614, "grad_norm": 1.0661565065383911, "learning_rate": 4.8562178748278576e-05, "loss": 4.8968, "step": 2017 }, { "epoch": 0.1085880327163151, "grad_norm": 1.2747077941894531, "learning_rate": 4.8560765834366134e-05, "loss": 4.8721, "step": 2018 }, { "epoch": 0.10864184244511407, "grad_norm": 1.1071053743362427, "learning_rate": 4.8559352247150373e-05, "loss": 4.8082, "step": 2019 }, { "epoch": 0.10869565217391304, "grad_norm": 1.1669036149978638, "learning_rate": 4.8557937986671695e-05, "loss": 4.6659, "step": 2020 }, { "epoch": 0.10874946190271201, "grad_norm": 1.518971562385559, "learning_rate": 4.855652305297052e-05, "loss": 4.616, "step": 2021 }, { "epoch": 0.10880327163151098, "grad_norm": 1.1888974905014038, "learning_rate": 4.8555107446087264e-05, "loss": 4.6927, "step": 2022 }, { "epoch": 0.10885708136030994, "grad_norm": 1.5653047561645508, "learning_rate": 4.85536911660624e-05, "loss": 4.7205, "step": 2023 }, { "epoch": 0.10891089108910891, "grad_norm": 1.2617579698562622, "learning_rate": 4.855227421293639e-05, "loss": 4.9493, "step": 2024 }, { "epoch": 0.10896470081790788, "grad_norm": 0.9847437143325806, "learning_rate": 4.855085658674973e-05, "loss": 4.8451, "step": 2025 }, { "epoch": 0.10901851054670685, "grad_norm": 1.0501700639724731, "learning_rate": 4.8549438287542936e-05, "loss": 4.6014, "step": 2026 }, { "epoch": 0.10907232027550581, "grad_norm": 1.3698182106018066, "learning_rate": 4.8548019315356535e-05, "loss": 4.6477, "step": 2027 }, { "epoch": 0.10912613000430478, "grad_norm": 1.3392436504364014, "learning_rate": 4.854659967023109e-05, "loss": 4.5284, "step": 2028 }, { "epoch": 0.10917993973310375, "grad_norm": 1.0485185384750366, "learning_rate": 4.8545179352207135e-05, "loss": 4.8675, "step": 2029 }, { "epoch": 0.10923374946190272, "grad_norm": 0.9917144775390625, "learning_rate": 4.85437583613253e-05, "loss": 4.7837, "step": 2030 }, { "epoch": 0.10928755919070168, "grad_norm": 1.1318002939224243, "learning_rate": 4.854233669762618e-05, "loss": 4.7754, "step": 2031 }, { "epoch": 0.10934136891950065, "grad_norm": 0.9778985381126404, "learning_rate": 4.854091436115039e-05, "loss": 5.111, "step": 2032 }, { "epoch": 0.10939517864829962, "grad_norm": 1.705858588218689, "learning_rate": 4.8539491351938585e-05, "loss": 4.8475, "step": 2033 }, { "epoch": 0.10944898837709859, "grad_norm": 1.900793194770813, "learning_rate": 4.853806767003144e-05, "loss": 4.7251, "step": 2034 }, { "epoch": 0.10950279810589755, "grad_norm": 1.0318928956985474, "learning_rate": 4.853664331546962e-05, "loss": 4.8523, "step": 2035 }, { "epoch": 0.1095566078346965, "grad_norm": 1.367864966392517, "learning_rate": 4.853521828829385e-05, "loss": 4.8462, "step": 2036 }, { "epoch": 0.10961041756349547, "grad_norm": 1.1187348365783691, "learning_rate": 4.8533792588544835e-05, "loss": 5.1262, "step": 2037 }, { "epoch": 0.10966422729229444, "grad_norm": 2.188401222229004, "learning_rate": 4.8532366216263324e-05, "loss": 4.746, "step": 2038 }, { "epoch": 0.10971803702109341, "grad_norm": 1.096109390258789, "learning_rate": 4.8530939171490094e-05, "loss": 4.6973, "step": 2039 }, { "epoch": 0.10977184674989238, "grad_norm": 1.2562763690948486, "learning_rate": 4.8529511454265904e-05, "loss": 4.888, "step": 2040 }, { "epoch": 0.10982565647869134, "grad_norm": 1.171091914176941, "learning_rate": 4.852808306463156e-05, "loss": 4.9292, "step": 2041 }, { "epoch": 0.10987946620749031, "grad_norm": 1.5157439708709717, "learning_rate": 4.8526654002627894e-05, "loss": 4.8303, "step": 2042 }, { "epoch": 0.10993327593628928, "grad_norm": 1.203323483467102, "learning_rate": 4.8525224268295734e-05, "loss": 4.8323, "step": 2043 }, { "epoch": 0.10998708566508825, "grad_norm": 1.0442086458206177, "learning_rate": 4.8523793861675937e-05, "loss": 4.6722, "step": 2044 }, { "epoch": 0.11004089539388721, "grad_norm": 1.5704294443130493, "learning_rate": 4.852236278280938e-05, "loss": 4.8742, "step": 2045 }, { "epoch": 0.11009470512268618, "grad_norm": 1.5319880247116089, "learning_rate": 4.852093103173697e-05, "loss": 4.782, "step": 2046 }, { "epoch": 0.11014851485148515, "grad_norm": 1.3185802698135376, "learning_rate": 4.8519498608499616e-05, "loss": 4.9319, "step": 2047 }, { "epoch": 0.11020232458028412, "grad_norm": 1.195231556892395, "learning_rate": 4.851806551313824e-05, "loss": 4.737, "step": 2048 }, { "epoch": 0.11025613430908308, "grad_norm": 1.6501716375350952, "learning_rate": 4.851663174569382e-05, "loss": 4.5968, "step": 2049 }, { "epoch": 0.11030994403788205, "grad_norm": 1.6865521669387817, "learning_rate": 4.8515197306207314e-05, "loss": 5.0472, "step": 2050 }, { "epoch": 0.11036375376668102, "grad_norm": 1.2268519401550293, "learning_rate": 4.8513762194719714e-05, "loss": 4.9514, "step": 2051 }, { "epoch": 0.11041756349547999, "grad_norm": 1.329961895942688, "learning_rate": 4.8512326411272034e-05, "loss": 4.8138, "step": 2052 }, { "epoch": 0.11047137322427895, "grad_norm": 1.0426394939422607, "learning_rate": 4.851088995590532e-05, "loss": 4.8935, "step": 2053 }, { "epoch": 0.11052518295307792, "grad_norm": 1.2334966659545898, "learning_rate": 4.850945282866059e-05, "loss": 4.5651, "step": 2054 }, { "epoch": 0.11057899268187689, "grad_norm": 1.3323414325714111, "learning_rate": 4.850801502957894e-05, "loss": 4.8178, "step": 2055 }, { "epoch": 0.11063280241067586, "grad_norm": 1.0769468545913696, "learning_rate": 4.850657655870144e-05, "loss": 4.7942, "step": 2056 }, { "epoch": 0.11068661213947481, "grad_norm": 1.366410255432129, "learning_rate": 4.850513741606922e-05, "loss": 4.5861, "step": 2057 }, { "epoch": 0.11074042186827378, "grad_norm": 1.491286039352417, "learning_rate": 4.850369760172339e-05, "loss": 4.949, "step": 2058 }, { "epoch": 0.11079423159707275, "grad_norm": 2.0530014038085938, "learning_rate": 4.8502257115705094e-05, "loss": 4.7996, "step": 2059 }, { "epoch": 0.11084804132587171, "grad_norm": 1.6326982975006104, "learning_rate": 4.850081595805551e-05, "loss": 4.5763, "step": 2060 }, { "epoch": 0.11090185105467068, "grad_norm": 1.1221771240234375, "learning_rate": 4.8499374128815816e-05, "loss": 4.713, "step": 2061 }, { "epoch": 0.11095566078346965, "grad_norm": 1.1099348068237305, "learning_rate": 4.849793162802722e-05, "loss": 4.9591, "step": 2062 }, { "epoch": 0.11100947051226862, "grad_norm": 1.9937607049942017, "learning_rate": 4.8496488455730925e-05, "loss": 4.6965, "step": 2063 }, { "epoch": 0.11106328024106758, "grad_norm": 1.8495672941207886, "learning_rate": 4.84950446119682e-05, "loss": 4.6986, "step": 2064 }, { "epoch": 0.11111708996986655, "grad_norm": 1.3683866262435913, "learning_rate": 4.849360009678029e-05, "loss": 4.8006, "step": 2065 }, { "epoch": 0.11117089969866552, "grad_norm": 2.115027904510498, "learning_rate": 4.8492154910208477e-05, "loss": 4.7643, "step": 2066 }, { "epoch": 0.11122470942746449, "grad_norm": 0.8481748104095459, "learning_rate": 4.849070905229407e-05, "loss": 4.6905, "step": 2067 }, { "epoch": 0.11127851915626345, "grad_norm": 1.8125267028808594, "learning_rate": 4.848926252307837e-05, "loss": 4.7666, "step": 2068 }, { "epoch": 0.11133232888506242, "grad_norm": 1.3162193298339844, "learning_rate": 4.848781532260274e-05, "loss": 4.7533, "step": 2069 }, { "epoch": 0.11138613861386139, "grad_norm": 1.208017349243164, "learning_rate": 4.8486367450908516e-05, "loss": 4.7953, "step": 2070 }, { "epoch": 0.11143994834266036, "grad_norm": 1.1999672651290894, "learning_rate": 4.848491890803708e-05, "loss": 4.7396, "step": 2071 }, { "epoch": 0.11149375807145932, "grad_norm": 1.8792266845703125, "learning_rate": 4.848346969402983e-05, "loss": 4.9241, "step": 2072 }, { "epoch": 0.11154756780025829, "grad_norm": 1.653581976890564, "learning_rate": 4.848201980892818e-05, "loss": 4.7749, "step": 2073 }, { "epoch": 0.11160137752905726, "grad_norm": 1.36814546585083, "learning_rate": 4.848056925277356e-05, "loss": 4.9278, "step": 2074 }, { "epoch": 0.11165518725785623, "grad_norm": 2.5209028720855713, "learning_rate": 4.847911802560743e-05, "loss": 4.686, "step": 2075 }, { "epoch": 0.11170899698665519, "grad_norm": 1.7376917600631714, "learning_rate": 4.8477666127471254e-05, "loss": 4.9535, "step": 2076 }, { "epoch": 0.11176280671545416, "grad_norm": 0.9432201981544495, "learning_rate": 4.847621355840653e-05, "loss": 4.8893, "step": 2077 }, { "epoch": 0.11181661644425311, "grad_norm": 1.8975105285644531, "learning_rate": 4.8474760318454765e-05, "loss": 4.6507, "step": 2078 }, { "epoch": 0.11187042617305208, "grad_norm": 2.393684148788452, "learning_rate": 4.8473306407657495e-05, "loss": 4.5194, "step": 2079 }, { "epoch": 0.11192423590185105, "grad_norm": 1.281790852546692, "learning_rate": 4.8471851826056256e-05, "loss": 4.7664, "step": 2080 }, { "epoch": 0.11197804563065002, "grad_norm": 1.378978967666626, "learning_rate": 4.847039657369262e-05, "loss": 4.9299, "step": 2081 }, { "epoch": 0.11203185535944898, "grad_norm": 1.6949982643127441, "learning_rate": 4.846894065060819e-05, "loss": 4.7014, "step": 2082 }, { "epoch": 0.11208566508824795, "grad_norm": 1.6662211418151855, "learning_rate": 4.8467484056844557e-05, "loss": 5.0111, "step": 2083 }, { "epoch": 0.11213947481704692, "grad_norm": 2.2512001991271973, "learning_rate": 4.8466026792443345e-05, "loss": 4.605, "step": 2084 }, { "epoch": 0.11219328454584589, "grad_norm": 1.4887654781341553, "learning_rate": 4.846456885744621e-05, "loss": 4.6919, "step": 2085 }, { "epoch": 0.11224709427464485, "grad_norm": 2.557553768157959, "learning_rate": 4.8463110251894806e-05, "loss": 4.319, "step": 2086 }, { "epoch": 0.11230090400344382, "grad_norm": 1.6935136318206787, "learning_rate": 4.846165097583082e-05, "loss": 4.8254, "step": 2087 }, { "epoch": 0.11235471373224279, "grad_norm": 1.6675548553466797, "learning_rate": 4.846019102929595e-05, "loss": 4.7922, "step": 2088 }, { "epoch": 0.11240852346104176, "grad_norm": 2.0123369693756104, "learning_rate": 4.845873041233192e-05, "loss": 4.9476, "step": 2089 }, { "epoch": 0.11246233318984072, "grad_norm": 1.1808536052703857, "learning_rate": 4.845726912498047e-05, "loss": 5.2481, "step": 2090 }, { "epoch": 0.11251614291863969, "grad_norm": 2.154017686843872, "learning_rate": 4.845580716728337e-05, "loss": 4.8204, "step": 2091 }, { "epoch": 0.11256995264743866, "grad_norm": 0.9584236741065979, "learning_rate": 4.845434453928239e-05, "loss": 4.7978, "step": 2092 }, { "epoch": 0.11262376237623763, "grad_norm": 2.008392810821533, "learning_rate": 4.845288124101932e-05, "loss": 4.7771, "step": 2093 }, { "epoch": 0.1126775721050366, "grad_norm": 1.3228639364242554, "learning_rate": 4.845141727253599e-05, "loss": 4.6316, "step": 2094 }, { "epoch": 0.11273138183383556, "grad_norm": 1.6547940969467163, "learning_rate": 4.844995263387423e-05, "loss": 5.1185, "step": 2095 }, { "epoch": 0.11278519156263453, "grad_norm": 1.0428011417388916, "learning_rate": 4.84484873250759e-05, "loss": 4.6849, "step": 2096 }, { "epoch": 0.1128390012914335, "grad_norm": 1.5317928791046143, "learning_rate": 4.844702134618286e-05, "loss": 4.6524, "step": 2097 }, { "epoch": 0.11289281102023246, "grad_norm": 1.6379495859146118, "learning_rate": 4.844555469723703e-05, "loss": 4.8764, "step": 2098 }, { "epoch": 0.11294662074903143, "grad_norm": 1.636479139328003, "learning_rate": 4.84440873782803e-05, "loss": 4.5398, "step": 2099 }, { "epoch": 0.11300043047783039, "grad_norm": 1.0037845373153687, "learning_rate": 4.844261938935461e-05, "loss": 4.8543, "step": 2100 }, { "epoch": 0.11305424020662935, "grad_norm": 1.5788928270339966, "learning_rate": 4.844115073050192e-05, "loss": 4.5307, "step": 2101 }, { "epoch": 0.11310804993542832, "grad_norm": 1.534209966659546, "learning_rate": 4.843968140176418e-05, "loss": 4.9179, "step": 2102 }, { "epoch": 0.11316185966422729, "grad_norm": 1.1655651330947876, "learning_rate": 4.843821140318339e-05, "loss": 4.89, "step": 2103 }, { "epoch": 0.11321566939302626, "grad_norm": 1.6634207963943481, "learning_rate": 4.843674073480157e-05, "loss": 4.6697, "step": 2104 }, { "epoch": 0.11326947912182522, "grad_norm": 0.9455115795135498, "learning_rate": 4.843526939666072e-05, "loss": 4.9003, "step": 2105 }, { "epoch": 0.11332328885062419, "grad_norm": 1.6324479579925537, "learning_rate": 4.843379738880292e-05, "loss": 5.1189, "step": 2106 }, { "epoch": 0.11337709857942316, "grad_norm": 1.45358407497406, "learning_rate": 4.8432324711270215e-05, "loss": 4.7518, "step": 2107 }, { "epoch": 0.11343090830822213, "grad_norm": 1.833518624305725, "learning_rate": 4.843085136410469e-05, "loss": 4.7666, "step": 2108 }, { "epoch": 0.11348471803702109, "grad_norm": 0.958000898361206, "learning_rate": 4.8429377347348464e-05, "loss": 4.8002, "step": 2109 }, { "epoch": 0.11353852776582006, "grad_norm": 0.9701695442199707, "learning_rate": 4.8427902661043645e-05, "loss": 4.96, "step": 2110 }, { "epoch": 0.11359233749461903, "grad_norm": 1.3099390268325806, "learning_rate": 4.842642730523238e-05, "loss": 5.0396, "step": 2111 }, { "epoch": 0.113646147223418, "grad_norm": 1.3762123584747314, "learning_rate": 4.842495127995684e-05, "loss": 4.8504, "step": 2112 }, { "epoch": 0.11369995695221696, "grad_norm": 1.3824821710586548, "learning_rate": 4.84234745852592e-05, "loss": 4.6159, "step": 2113 }, { "epoch": 0.11375376668101593, "grad_norm": 1.9769800901412964, "learning_rate": 4.8421997221181644e-05, "loss": 4.8404, "step": 2114 }, { "epoch": 0.1138075764098149, "grad_norm": 2.4077141284942627, "learning_rate": 4.8420519187766415e-05, "loss": 4.4852, "step": 2115 }, { "epoch": 0.11386138613861387, "grad_norm": 2.166658878326416, "learning_rate": 4.841904048505574e-05, "loss": 4.4558, "step": 2116 }, { "epoch": 0.11391519586741283, "grad_norm": 1.524982213973999, "learning_rate": 4.8417561113091884e-05, "loss": 4.8286, "step": 2117 }, { "epoch": 0.1139690055962118, "grad_norm": 1.2811373472213745, "learning_rate": 4.841608107191711e-05, "loss": 4.9197, "step": 2118 }, { "epoch": 0.11402281532501077, "grad_norm": 1.1791199445724487, "learning_rate": 4.8414600361573715e-05, "loss": 4.8552, "step": 2119 }, { "epoch": 0.11407662505380974, "grad_norm": 1.6769267320632935, "learning_rate": 4.841311898210403e-05, "loss": 4.767, "step": 2120 }, { "epoch": 0.11413043478260869, "grad_norm": 1.2159810066223145, "learning_rate": 4.841163693355038e-05, "loss": 4.8298, "step": 2121 }, { "epoch": 0.11418424451140766, "grad_norm": 1.5500562191009521, "learning_rate": 4.841015421595511e-05, "loss": 4.5781, "step": 2122 }, { "epoch": 0.11423805424020662, "grad_norm": 1.0259517431259155, "learning_rate": 4.8408670829360595e-05, "loss": 4.92, "step": 2123 }, { "epoch": 0.11429186396900559, "grad_norm": 2.1712071895599365, "learning_rate": 4.8407186773809234e-05, "loss": 4.5064, "step": 2124 }, { "epoch": 0.11434567369780456, "grad_norm": 1.5531035661697388, "learning_rate": 4.8405702049343425e-05, "loss": 4.8654, "step": 2125 }, { "epoch": 0.11439948342660353, "grad_norm": 1.0790354013442993, "learning_rate": 4.840421665600562e-05, "loss": 4.8652, "step": 2126 }, { "epoch": 0.1144532931554025, "grad_norm": 1.9411929845809937, "learning_rate": 4.8402730593838244e-05, "loss": 4.4334, "step": 2127 }, { "epoch": 0.11450710288420146, "grad_norm": 1.3048137426376343, "learning_rate": 4.840124386288377e-05, "loss": 4.9619, "step": 2128 }, { "epoch": 0.11456091261300043, "grad_norm": 1.6091678142547607, "learning_rate": 4.83997564631847e-05, "loss": 4.841, "step": 2129 }, { "epoch": 0.1146147223417994, "grad_norm": 1.3642737865447998, "learning_rate": 4.8398268394783516e-05, "loss": 4.6507, "step": 2130 }, { "epoch": 0.11466853207059836, "grad_norm": 1.4391748905181885, "learning_rate": 4.839677965772277e-05, "loss": 4.9495, "step": 2131 }, { "epoch": 0.11472234179939733, "grad_norm": 1.1388654708862305, "learning_rate": 4.839529025204498e-05, "loss": 4.7284, "step": 2132 }, { "epoch": 0.1147761515281963, "grad_norm": 1.684967041015625, "learning_rate": 4.839380017779273e-05, "loss": 4.532, "step": 2133 }, { "epoch": 0.11482996125699527, "grad_norm": 2.0399930477142334, "learning_rate": 4.8392309435008575e-05, "loss": 4.4241, "step": 2134 }, { "epoch": 0.11488377098579423, "grad_norm": 1.9224265813827515, "learning_rate": 4.839081802373515e-05, "loss": 4.6066, "step": 2135 }, { "epoch": 0.1149375807145932, "grad_norm": 1.198029637336731, "learning_rate": 4.838932594401505e-05, "loss": 4.6103, "step": 2136 }, { "epoch": 0.11499139044339217, "grad_norm": 1.7444818019866943, "learning_rate": 4.838783319589093e-05, "loss": 4.8089, "step": 2137 }, { "epoch": 0.11504520017219114, "grad_norm": 1.8118069171905518, "learning_rate": 4.8386339779405445e-05, "loss": 4.9085, "step": 2138 }, { "epoch": 0.1150990099009901, "grad_norm": 1.363068699836731, "learning_rate": 4.838484569460127e-05, "loss": 4.8794, "step": 2139 }, { "epoch": 0.11515281962978907, "grad_norm": 1.7761094570159912, "learning_rate": 4.83833509415211e-05, "loss": 4.7042, "step": 2140 }, { "epoch": 0.11520662935858804, "grad_norm": 1.6038379669189453, "learning_rate": 4.838185552020766e-05, "loss": 4.3433, "step": 2141 }, { "epoch": 0.11526043908738699, "grad_norm": 1.729322075843811, "learning_rate": 4.838035943070367e-05, "loss": 4.7458, "step": 2142 }, { "epoch": 0.11531424881618596, "grad_norm": 1.7738547325134277, "learning_rate": 4.83788626730519e-05, "loss": 4.9102, "step": 2143 }, { "epoch": 0.11536805854498493, "grad_norm": 1.2482445240020752, "learning_rate": 4.837736524729512e-05, "loss": 5.0461, "step": 2144 }, { "epoch": 0.1154218682737839, "grad_norm": 1.217368721961975, "learning_rate": 4.8375867153476104e-05, "loss": 4.5275, "step": 2145 }, { "epoch": 0.11547567800258286, "grad_norm": 1.1161761283874512, "learning_rate": 4.837436839163769e-05, "loss": 4.6465, "step": 2146 }, { "epoch": 0.11552948773138183, "grad_norm": 1.0774935483932495, "learning_rate": 4.83728689618227e-05, "loss": 4.6712, "step": 2147 }, { "epoch": 0.1155832974601808, "grad_norm": 1.8016437292099, "learning_rate": 4.837136886407397e-05, "loss": 4.4499, "step": 2148 }, { "epoch": 0.11563710718897977, "grad_norm": 1.0531529188156128, "learning_rate": 4.836986809843439e-05, "loss": 4.8341, "step": 2149 }, { "epoch": 0.11569091691777873, "grad_norm": 1.9884549379348755, "learning_rate": 4.8368366664946826e-05, "loss": 4.6343, "step": 2150 }, { "epoch": 0.1157447266465777, "grad_norm": 1.940347671508789, "learning_rate": 4.8366864563654206e-05, "loss": 4.1619, "step": 2151 }, { "epoch": 0.11579853637537667, "grad_norm": 1.465052604675293, "learning_rate": 4.836536179459944e-05, "loss": 4.6464, "step": 2152 }, { "epoch": 0.11585234610417564, "grad_norm": 1.6191761493682861, "learning_rate": 4.836385835782549e-05, "loss": 4.7491, "step": 2153 }, { "epoch": 0.1159061558329746, "grad_norm": 1.0621957778930664, "learning_rate": 4.83623542533753e-05, "loss": 4.5676, "step": 2154 }, { "epoch": 0.11595996556177357, "grad_norm": 1.3537119626998901, "learning_rate": 4.836084948129186e-05, "loss": 4.592, "step": 2155 }, { "epoch": 0.11601377529057254, "grad_norm": 2.2115015983581543, "learning_rate": 4.835934404161818e-05, "loss": 4.4598, "step": 2156 }, { "epoch": 0.1160675850193715, "grad_norm": 1.2233506441116333, "learning_rate": 4.8357837934397275e-05, "loss": 4.9194, "step": 2157 }, { "epoch": 0.11612139474817047, "grad_norm": 1.1285874843597412, "learning_rate": 4.835633115967219e-05, "loss": 4.7584, "step": 2158 }, { "epoch": 0.11617520447696944, "grad_norm": 2.1259806156158447, "learning_rate": 4.835482371748598e-05, "loss": 4.6466, "step": 2159 }, { "epoch": 0.11622901420576841, "grad_norm": 1.891540288925171, "learning_rate": 4.8353315607881724e-05, "loss": 4.7463, "step": 2160 }, { "epoch": 0.11628282393456738, "grad_norm": 1.9501694440841675, "learning_rate": 4.835180683090252e-05, "loss": 4.8021, "step": 2161 }, { "epoch": 0.11633663366336634, "grad_norm": 1.9881234169006348, "learning_rate": 4.835029738659149e-05, "loss": 4.9414, "step": 2162 }, { "epoch": 0.11639044339216531, "grad_norm": 1.2386372089385986, "learning_rate": 4.8348787274991765e-05, "loss": 4.8509, "step": 2163 }, { "epoch": 0.11644425312096426, "grad_norm": 1.5126917362213135, "learning_rate": 4.83472764961465e-05, "loss": 4.7791, "step": 2164 }, { "epoch": 0.11649806284976323, "grad_norm": 1.7002671957015991, "learning_rate": 4.8345765050098866e-05, "loss": 4.7647, "step": 2165 }, { "epoch": 0.1165518725785622, "grad_norm": 1.7590998411178589, "learning_rate": 4.834425293689206e-05, "loss": 5.0298, "step": 2166 }, { "epoch": 0.11660568230736117, "grad_norm": 1.5585695505142212, "learning_rate": 4.83427401565693e-05, "loss": 4.8456, "step": 2167 }, { "epoch": 0.11665949203616013, "grad_norm": 1.6947880983352661, "learning_rate": 4.8341226709173804e-05, "loss": 4.8155, "step": 2168 }, { "epoch": 0.1167133017649591, "grad_norm": 1.3813707828521729, "learning_rate": 4.833971259474883e-05, "loss": 5.0111, "step": 2169 }, { "epoch": 0.11676711149375807, "grad_norm": 1.2865149974822998, "learning_rate": 4.833819781333765e-05, "loss": 4.7932, "step": 2170 }, { "epoch": 0.11682092122255704, "grad_norm": 2.1210389137268066, "learning_rate": 4.833668236498355e-05, "loss": 4.7491, "step": 2171 }, { "epoch": 0.116874730951356, "grad_norm": 1.8199892044067383, "learning_rate": 4.8335166249729834e-05, "loss": 4.8549, "step": 2172 }, { "epoch": 0.11692854068015497, "grad_norm": 1.1609649658203125, "learning_rate": 4.833364946761983e-05, "loss": 4.7352, "step": 2173 }, { "epoch": 0.11698235040895394, "grad_norm": 1.3500508069992065, "learning_rate": 4.833213201869688e-05, "loss": 4.9845, "step": 2174 }, { "epoch": 0.1170361601377529, "grad_norm": 1.1528065204620361, "learning_rate": 4.833061390300436e-05, "loss": 4.8308, "step": 2175 }, { "epoch": 0.11708996986655187, "grad_norm": 1.3512511253356934, "learning_rate": 4.832909512058564e-05, "loss": 4.7803, "step": 2176 }, { "epoch": 0.11714377959535084, "grad_norm": 1.0595614910125732, "learning_rate": 4.8327575671484135e-05, "loss": 4.5964, "step": 2177 }, { "epoch": 0.11719758932414981, "grad_norm": 1.8079566955566406, "learning_rate": 4.8326055555743265e-05, "loss": 4.4956, "step": 2178 }, { "epoch": 0.11725139905294878, "grad_norm": 1.6653707027435303, "learning_rate": 4.832453477340646e-05, "loss": 4.7878, "step": 2179 }, { "epoch": 0.11730520878174774, "grad_norm": 0.9946452975273132, "learning_rate": 4.8323013324517194e-05, "loss": 4.7276, "step": 2180 }, { "epoch": 0.11735901851054671, "grad_norm": 1.9489024877548218, "learning_rate": 4.832149120911893e-05, "loss": 4.9014, "step": 2181 }, { "epoch": 0.11741282823934568, "grad_norm": 1.710974097251892, "learning_rate": 4.831996842725518e-05, "loss": 4.7082, "step": 2182 }, { "epoch": 0.11746663796814465, "grad_norm": 2.2865841388702393, "learning_rate": 4.831844497896945e-05, "loss": 4.7549, "step": 2183 }, { "epoch": 0.11752044769694361, "grad_norm": 1.2900859117507935, "learning_rate": 4.831692086430529e-05, "loss": 5.1573, "step": 2184 }, { "epoch": 0.11757425742574257, "grad_norm": 1.0884841680526733, "learning_rate": 4.831539608330624e-05, "loss": 4.6146, "step": 2185 }, { "epoch": 0.11762806715454154, "grad_norm": 1.5135103464126587, "learning_rate": 4.831387063601588e-05, "loss": 4.837, "step": 2186 }, { "epoch": 0.1176818768833405, "grad_norm": 1.8560668230056763, "learning_rate": 4.831234452247781e-05, "loss": 4.9358, "step": 2187 }, { "epoch": 0.11773568661213947, "grad_norm": 0.8541394472122192, "learning_rate": 4.831081774273564e-05, "loss": 4.9164, "step": 2188 }, { "epoch": 0.11778949634093844, "grad_norm": 1.6394264698028564, "learning_rate": 4.830929029683299e-05, "loss": 4.961, "step": 2189 }, { "epoch": 0.1178433060697374, "grad_norm": 1.7345969676971436, "learning_rate": 4.830776218481352e-05, "loss": 4.7423, "step": 2190 }, { "epoch": 0.11789711579853637, "grad_norm": 1.5543841123580933, "learning_rate": 4.830623340672089e-05, "loss": 4.5526, "step": 2191 }, { "epoch": 0.11795092552733534, "grad_norm": 0.9931278228759766, "learning_rate": 4.830470396259881e-05, "loss": 4.9349, "step": 2192 }, { "epoch": 0.11800473525613431, "grad_norm": 1.4041354656219482, "learning_rate": 4.830317385249096e-05, "loss": 4.79, "step": 2193 }, { "epoch": 0.11805854498493328, "grad_norm": 1.3714807033538818, "learning_rate": 4.830164307644108e-05, "loss": 4.6457, "step": 2194 }, { "epoch": 0.11811235471373224, "grad_norm": 1.6771894693374634, "learning_rate": 4.8300111634492925e-05, "loss": 4.7791, "step": 2195 }, { "epoch": 0.11816616444253121, "grad_norm": 1.3078796863555908, "learning_rate": 4.8298579526690245e-05, "loss": 3.9408, "step": 2196 }, { "epoch": 0.11821997417133018, "grad_norm": 1.7361093759536743, "learning_rate": 4.829704675307682e-05, "loss": 4.8654, "step": 2197 }, { "epoch": 0.11827378390012915, "grad_norm": 1.3507946729660034, "learning_rate": 4.829551331369647e-05, "loss": 4.6569, "step": 2198 }, { "epoch": 0.11832759362892811, "grad_norm": 1.0736312866210938, "learning_rate": 4.829397920859301e-05, "loss": 4.7602, "step": 2199 }, { "epoch": 0.11838140335772708, "grad_norm": 1.6340051889419556, "learning_rate": 4.829244443781027e-05, "loss": 4.7321, "step": 2200 }, { "epoch": 0.11843521308652605, "grad_norm": 1.1586288213729858, "learning_rate": 4.829090900139212e-05, "loss": 4.8339, "step": 2201 }, { "epoch": 0.11848902281532502, "grad_norm": 1.2548130750656128, "learning_rate": 4.828937289938243e-05, "loss": 4.7308, "step": 2202 }, { "epoch": 0.11854283254412398, "grad_norm": 1.9481399059295654, "learning_rate": 4.8287836131825114e-05, "loss": 4.7816, "step": 2203 }, { "epoch": 0.11859664227292295, "grad_norm": 1.4979585409164429, "learning_rate": 4.828629869876408e-05, "loss": 4.916, "step": 2204 }, { "epoch": 0.11865045200172192, "grad_norm": 1.8014127016067505, "learning_rate": 4.828476060024325e-05, "loss": 4.8589, "step": 2205 }, { "epoch": 0.11870426173052087, "grad_norm": 1.1907224655151367, "learning_rate": 4.82832218363066e-05, "loss": 4.7036, "step": 2206 }, { "epoch": 0.11875807145931984, "grad_norm": 1.5348548889160156, "learning_rate": 4.8281682406998084e-05, "loss": 5.0559, "step": 2207 }, { "epoch": 0.1188118811881188, "grad_norm": 1.6000003814697266, "learning_rate": 4.8280142312361716e-05, "loss": 4.93, "step": 2208 }, { "epoch": 0.11886569091691777, "grad_norm": 1.5674340724945068, "learning_rate": 4.827860155244149e-05, "loss": 4.8045, "step": 2209 }, { "epoch": 0.11891950064571674, "grad_norm": 1.4629911184310913, "learning_rate": 4.827706012728145e-05, "loss": 4.7787, "step": 2210 }, { "epoch": 0.11897331037451571, "grad_norm": 0.9779052734375, "learning_rate": 4.8275518036925634e-05, "loss": 4.6347, "step": 2211 }, { "epoch": 0.11902712010331468, "grad_norm": 1.8848676681518555, "learning_rate": 4.8273975281418115e-05, "loss": 4.836, "step": 2212 }, { "epoch": 0.11908092983211364, "grad_norm": 1.8681516647338867, "learning_rate": 4.827243186080299e-05, "loss": 4.6617, "step": 2213 }, { "epoch": 0.11913473956091261, "grad_norm": 1.1043845415115356, "learning_rate": 4.827088777512435e-05, "loss": 4.7952, "step": 2214 }, { "epoch": 0.11918854928971158, "grad_norm": 1.0912271738052368, "learning_rate": 4.8269343024426336e-05, "loss": 4.7749, "step": 2215 }, { "epoch": 0.11924235901851055, "grad_norm": 1.0356011390686035, "learning_rate": 4.8267797608753076e-05, "loss": 4.8506, "step": 2216 }, { "epoch": 0.11929616874730951, "grad_norm": 1.3807610273361206, "learning_rate": 4.8266251528148754e-05, "loss": 4.6121, "step": 2217 }, { "epoch": 0.11934997847610848, "grad_norm": 1.235913634300232, "learning_rate": 4.826470478265753e-05, "loss": 4.9235, "step": 2218 }, { "epoch": 0.11940378820490745, "grad_norm": 1.7971312999725342, "learning_rate": 4.826315737232363e-05, "loss": 4.6989, "step": 2219 }, { "epoch": 0.11945759793370642, "grad_norm": 1.5515193939208984, "learning_rate": 4.826160929719126e-05, "loss": 4.6203, "step": 2220 }, { "epoch": 0.11951140766250538, "grad_norm": 2.311345100402832, "learning_rate": 4.8260060557304656e-05, "loss": 4.7755, "step": 2221 }, { "epoch": 0.11956521739130435, "grad_norm": 2.0351710319519043, "learning_rate": 4.825851115270808e-05, "loss": 4.4069, "step": 2222 }, { "epoch": 0.11961902712010332, "grad_norm": 1.3439390659332275, "learning_rate": 4.8256961083445826e-05, "loss": 4.842, "step": 2223 }, { "epoch": 0.11967283684890229, "grad_norm": 1.6644337177276611, "learning_rate": 4.825541034956218e-05, "loss": 4.9869, "step": 2224 }, { "epoch": 0.11972664657770125, "grad_norm": 0.9057691097259521, "learning_rate": 4.825385895110145e-05, "loss": 4.7842, "step": 2225 }, { "epoch": 0.11978045630650022, "grad_norm": 1.686539888381958, "learning_rate": 4.8252306888107976e-05, "loss": 4.7911, "step": 2226 }, { "epoch": 0.11983426603529919, "grad_norm": 1.0959573984146118, "learning_rate": 4.8250754160626114e-05, "loss": 4.8417, "step": 2227 }, { "epoch": 0.11988807576409814, "grad_norm": 1.5817338228225708, "learning_rate": 4.8249200768700234e-05, "loss": 4.7511, "step": 2228 }, { "epoch": 0.11994188549289711, "grad_norm": 1.8563944101333618, "learning_rate": 4.824764671237473e-05, "loss": 4.4563, "step": 2229 }, { "epoch": 0.11999569522169608, "grad_norm": 1.6177371740341187, "learning_rate": 4.824609199169401e-05, "loss": 4.7833, "step": 2230 }, { "epoch": 0.12004950495049505, "grad_norm": 1.1201967000961304, "learning_rate": 4.824453660670251e-05, "loss": 4.7017, "step": 2231 }, { "epoch": 0.12010331467929401, "grad_norm": 1.584941029548645, "learning_rate": 4.824298055744466e-05, "loss": 4.0387, "step": 2232 }, { "epoch": 0.12015712440809298, "grad_norm": 1.6359503269195557, "learning_rate": 4.824142384396496e-05, "loss": 4.6014, "step": 2233 }, { "epoch": 0.12021093413689195, "grad_norm": 2.0071165561676025, "learning_rate": 4.823986646630787e-05, "loss": 4.5272, "step": 2234 }, { "epoch": 0.12026474386569092, "grad_norm": 1.1606353521347046, "learning_rate": 4.82383084245179e-05, "loss": 4.7265, "step": 2235 }, { "epoch": 0.12031855359448988, "grad_norm": 1.8379936218261719, "learning_rate": 4.8236749718639584e-05, "loss": 5.0595, "step": 2236 }, { "epoch": 0.12037236332328885, "grad_norm": 1.5853205919265747, "learning_rate": 4.823519034871746e-05, "loss": 5.0756, "step": 2237 }, { "epoch": 0.12042617305208782, "grad_norm": 1.1733813285827637, "learning_rate": 4.8233630314796096e-05, "loss": 4.2726, "step": 2238 }, { "epoch": 0.12047998278088679, "grad_norm": 1.672919511795044, "learning_rate": 4.823206961692006e-05, "loss": 4.9566, "step": 2239 }, { "epoch": 0.12053379250968575, "grad_norm": 1.8240063190460205, "learning_rate": 4.823050825513397e-05, "loss": 4.4619, "step": 2240 }, { "epoch": 0.12058760223848472, "grad_norm": 1.1854459047317505, "learning_rate": 4.822894622948243e-05, "loss": 4.9916, "step": 2241 }, { "epoch": 0.12064141196728369, "grad_norm": 1.1532561779022217, "learning_rate": 4.822738354001009e-05, "loss": 4.6202, "step": 2242 }, { "epoch": 0.12069522169608266, "grad_norm": 0.996200680732727, "learning_rate": 4.82258201867616e-05, "loss": 4.6422, "step": 2243 }, { "epoch": 0.12074903142488162, "grad_norm": 1.1209943294525146, "learning_rate": 4.822425616978164e-05, "loss": 4.8831, "step": 2244 }, { "epoch": 0.12080284115368059, "grad_norm": 1.0708401203155518, "learning_rate": 4.82226914891149e-05, "loss": 4.7817, "step": 2245 }, { "epoch": 0.12085665088247956, "grad_norm": 1.1206849813461304, "learning_rate": 4.8221126144806106e-05, "loss": 4.8276, "step": 2246 }, { "epoch": 0.12091046061127853, "grad_norm": 1.2440162897109985, "learning_rate": 4.821956013689999e-05, "loss": 5.059, "step": 2247 }, { "epoch": 0.12096427034007749, "grad_norm": 1.8841718435287476, "learning_rate": 4.821799346544128e-05, "loss": 4.292, "step": 2248 }, { "epoch": 0.12101808006887645, "grad_norm": 2.4592080116271973, "learning_rate": 4.821642613047478e-05, "loss": 4.7423, "step": 2249 }, { "epoch": 0.12107188979767541, "grad_norm": 1.4395270347595215, "learning_rate": 4.8214858132045264e-05, "loss": 4.8522, "step": 2250 }, { "epoch": 0.12112569952647438, "grad_norm": 1.7055474519729614, "learning_rate": 4.821328947019754e-05, "loss": 4.6149, "step": 2251 }, { "epoch": 0.12117950925527335, "grad_norm": 2.1697092056274414, "learning_rate": 4.8211720144976444e-05, "loss": 4.8591, "step": 2252 }, { "epoch": 0.12123331898407232, "grad_norm": 1.4419891834259033, "learning_rate": 4.821015015642682e-05, "loss": 4.5026, "step": 2253 }, { "epoch": 0.12128712871287128, "grad_norm": 1.7797211408615112, "learning_rate": 4.820857950459352e-05, "loss": 4.8369, "step": 2254 }, { "epoch": 0.12134093844167025, "grad_norm": 2.2604079246520996, "learning_rate": 4.820700818952145e-05, "loss": 4.6976, "step": 2255 }, { "epoch": 0.12139474817046922, "grad_norm": 1.762474536895752, "learning_rate": 4.820543621125551e-05, "loss": 4.6829, "step": 2256 }, { "epoch": 0.12144855789926819, "grad_norm": 1.0044814348220825, "learning_rate": 4.820386356984061e-05, "loss": 4.8044, "step": 2257 }, { "epoch": 0.12150236762806715, "grad_norm": 1.3429951667785645, "learning_rate": 4.8202290265321704e-05, "loss": 4.9207, "step": 2258 }, { "epoch": 0.12155617735686612, "grad_norm": 1.9112038612365723, "learning_rate": 4.820071629774374e-05, "loss": 4.7723, "step": 2259 }, { "epoch": 0.12160998708566509, "grad_norm": 1.9145042896270752, "learning_rate": 4.819914166715172e-05, "loss": 4.5574, "step": 2260 }, { "epoch": 0.12166379681446406, "grad_norm": 1.2231837511062622, "learning_rate": 4.8197566373590625e-05, "loss": 5.0464, "step": 2261 }, { "epoch": 0.12171760654326302, "grad_norm": 1.3726412057876587, "learning_rate": 4.8195990417105474e-05, "loss": 4.8094, "step": 2262 }, { "epoch": 0.12177141627206199, "grad_norm": 1.8024345636367798, "learning_rate": 4.819441379774131e-05, "loss": 5.0823, "step": 2263 }, { "epoch": 0.12182522600086096, "grad_norm": 1.386160969734192, "learning_rate": 4.819283651554319e-05, "loss": 4.9061, "step": 2264 }, { "epoch": 0.12187903572965993, "grad_norm": 1.445059061050415, "learning_rate": 4.8191258570556175e-05, "loss": 4.9071, "step": 2265 }, { "epoch": 0.1219328454584589, "grad_norm": 1.3158526420593262, "learning_rate": 4.818967996282537e-05, "loss": 4.572, "step": 2266 }, { "epoch": 0.12198665518725786, "grad_norm": 1.678299903869629, "learning_rate": 4.818810069239589e-05, "loss": 4.7765, "step": 2267 }, { "epoch": 0.12204046491605683, "grad_norm": 1.625564694404602, "learning_rate": 4.818652075931285e-05, "loss": 4.7039, "step": 2268 }, { "epoch": 0.1220942746448558, "grad_norm": 1.4065965414047241, "learning_rate": 4.8184940163621425e-05, "loss": 4.6212, "step": 2269 }, { "epoch": 0.12214808437365475, "grad_norm": 1.1126983165740967, "learning_rate": 4.818335890536676e-05, "loss": 4.68, "step": 2270 }, { "epoch": 0.12220189410245372, "grad_norm": 1.6185208559036255, "learning_rate": 4.818177698459406e-05, "loss": 4.7386, "step": 2271 }, { "epoch": 0.12225570383125269, "grad_norm": 1.205345630645752, "learning_rate": 4.8180194401348524e-05, "loss": 5.0428, "step": 2272 }, { "epoch": 0.12230951356005165, "grad_norm": 1.2736263275146484, "learning_rate": 4.817861115567537e-05, "loss": 4.7715, "step": 2273 }, { "epoch": 0.12236332328885062, "grad_norm": 1.5114086866378784, "learning_rate": 4.817702724761986e-05, "loss": 4.7846, "step": 2274 }, { "epoch": 0.12241713301764959, "grad_norm": 1.4251494407653809, "learning_rate": 4.817544267722725e-05, "loss": 5.0611, "step": 2275 }, { "epoch": 0.12247094274644856, "grad_norm": 1.7232197523117065, "learning_rate": 4.8173857444542825e-05, "loss": 4.7452, "step": 2276 }, { "epoch": 0.12252475247524752, "grad_norm": 1.547532558441162, "learning_rate": 4.8172271549611883e-05, "loss": 4.705, "step": 2277 }, { "epoch": 0.12257856220404649, "grad_norm": 1.3732963800430298, "learning_rate": 4.8170684992479745e-05, "loss": 4.8628, "step": 2278 }, { "epoch": 0.12263237193284546, "grad_norm": 1.7938483953475952, "learning_rate": 4.816909777319175e-05, "loss": 4.5817, "step": 2279 }, { "epoch": 0.12268618166164443, "grad_norm": 1.8642877340316772, "learning_rate": 4.816750989179326e-05, "loss": 4.6727, "step": 2280 }, { "epoch": 0.12273999139044339, "grad_norm": 1.1536880731582642, "learning_rate": 4.8165921348329645e-05, "loss": 4.7981, "step": 2281 }, { "epoch": 0.12279380111924236, "grad_norm": 1.5374085903167725, "learning_rate": 4.8164332142846316e-05, "loss": 4.3705, "step": 2282 }, { "epoch": 0.12284761084804133, "grad_norm": 1.6824381351470947, "learning_rate": 4.8162742275388674e-05, "loss": 4.8109, "step": 2283 }, { "epoch": 0.1229014205768403, "grad_norm": 1.7995799779891968, "learning_rate": 4.8161151746002166e-05, "loss": 5.0559, "step": 2284 }, { "epoch": 0.12295523030563926, "grad_norm": 2.1313867568969727, "learning_rate": 4.815956055473223e-05, "loss": 4.3344, "step": 2285 }, { "epoch": 0.12300904003443823, "grad_norm": 1.4501286745071411, "learning_rate": 4.815796870162435e-05, "loss": 4.7449, "step": 2286 }, { "epoch": 0.1230628497632372, "grad_norm": 0.9124572277069092, "learning_rate": 4.815637618672401e-05, "loss": 4.6389, "step": 2287 }, { "epoch": 0.12311665949203617, "grad_norm": 1.6046574115753174, "learning_rate": 4.815478301007671e-05, "loss": 4.9349, "step": 2288 }, { "epoch": 0.12317046922083513, "grad_norm": 2.3552494049072266, "learning_rate": 4.8153189171728003e-05, "loss": 4.2155, "step": 2289 }, { "epoch": 0.1232242789496341, "grad_norm": 1.9228029251098633, "learning_rate": 4.8151594671723424e-05, "loss": 4.655, "step": 2290 }, { "epoch": 0.12327808867843307, "grad_norm": 1.7861241102218628, "learning_rate": 4.814999951010853e-05, "loss": 4.849, "step": 2291 }, { "epoch": 0.12333189840723202, "grad_norm": 1.6239519119262695, "learning_rate": 4.814840368692893e-05, "loss": 4.9178, "step": 2292 }, { "epoch": 0.12338570813603099, "grad_norm": 2.118180513381958, "learning_rate": 4.814680720223021e-05, "loss": 3.8629, "step": 2293 }, { "epoch": 0.12343951786482996, "grad_norm": 2.2412827014923096, "learning_rate": 4.8145210056058e-05, "loss": 4.678, "step": 2294 }, { "epoch": 0.12349332759362892, "grad_norm": 1.400559663772583, "learning_rate": 4.8143612248457935e-05, "loss": 4.6705, "step": 2295 }, { "epoch": 0.12354713732242789, "grad_norm": 2.6646296977996826, "learning_rate": 4.814201377947568e-05, "loss": 4.4568, "step": 2296 }, { "epoch": 0.12360094705122686, "grad_norm": 2.027010679244995, "learning_rate": 4.814041464915692e-05, "loss": 4.4909, "step": 2297 }, { "epoch": 0.12365475678002583, "grad_norm": 1.0991381406784058, "learning_rate": 4.813881485754734e-05, "loss": 5.0128, "step": 2298 }, { "epoch": 0.1237085665088248, "grad_norm": 1.3871287107467651, "learning_rate": 4.813721440469268e-05, "loss": 4.7201, "step": 2299 }, { "epoch": 0.12376237623762376, "grad_norm": 1.2688392400741577, "learning_rate": 4.813561329063866e-05, "loss": 4.7926, "step": 2300 }, { "epoch": 0.12381618596642273, "grad_norm": 1.1508370637893677, "learning_rate": 4.813401151543104e-05, "loss": 4.8368, "step": 2301 }, { "epoch": 0.1238699956952217, "grad_norm": 1.2923827171325684, "learning_rate": 4.813240907911559e-05, "loss": 4.4242, "step": 2302 }, { "epoch": 0.12392380542402066, "grad_norm": 1.831156849861145, "learning_rate": 4.813080598173811e-05, "loss": 4.6829, "step": 2303 }, { "epoch": 0.12397761515281963, "grad_norm": 2.006885051727295, "learning_rate": 4.812920222334441e-05, "loss": 4.8644, "step": 2304 }, { "epoch": 0.1240314248816186, "grad_norm": 1.867484211921692, "learning_rate": 4.812759780398033e-05, "loss": 4.891, "step": 2305 }, { "epoch": 0.12408523461041757, "grad_norm": 1.6993342638015747, "learning_rate": 4.81259927236917e-05, "loss": 4.6305, "step": 2306 }, { "epoch": 0.12413904433921653, "grad_norm": 1.3259309530258179, "learning_rate": 4.81243869825244e-05, "loss": 4.8154, "step": 2307 }, { "epoch": 0.1241928540680155, "grad_norm": 1.3539340496063232, "learning_rate": 4.8122780580524315e-05, "loss": 4.3623, "step": 2308 }, { "epoch": 0.12424666379681447, "grad_norm": 1.0944583415985107, "learning_rate": 4.812117351773736e-05, "loss": 4.6952, "step": 2309 }, { "epoch": 0.12430047352561344, "grad_norm": 1.727309226989746, "learning_rate": 4.8119565794209455e-05, "loss": 4.5719, "step": 2310 }, { "epoch": 0.1243542832544124, "grad_norm": 1.753814935684204, "learning_rate": 4.811795740998654e-05, "loss": 4.6713, "step": 2311 }, { "epoch": 0.12440809298321137, "grad_norm": 1.181848406791687, "learning_rate": 4.8116348365114585e-05, "loss": 4.7539, "step": 2312 }, { "epoch": 0.12446190271201032, "grad_norm": 1.7487215995788574, "learning_rate": 4.811473865963957e-05, "loss": 5.0164, "step": 2313 }, { "epoch": 0.12451571244080929, "grad_norm": 1.7670773267745972, "learning_rate": 4.811312829360749e-05, "loss": 4.8008, "step": 2314 }, { "epoch": 0.12456952216960826, "grad_norm": 1.2574714422225952, "learning_rate": 4.8111517267064374e-05, "loss": 4.8275, "step": 2315 }, { "epoch": 0.12462333189840723, "grad_norm": 1.2251698970794678, "learning_rate": 4.810990558005626e-05, "loss": 4.7594, "step": 2316 }, { "epoch": 0.1246771416272062, "grad_norm": 1.6466615200042725, "learning_rate": 4.81082932326292e-05, "loss": 5.0689, "step": 2317 }, { "epoch": 0.12473095135600516, "grad_norm": 1.3775575160980225, "learning_rate": 4.810668022482927e-05, "loss": 5.119, "step": 2318 }, { "epoch": 0.12478476108480413, "grad_norm": 1.3430120944976807, "learning_rate": 4.8105066556702574e-05, "loss": 4.7835, "step": 2319 }, { "epoch": 0.1248385708136031, "grad_norm": 1.8317276239395142, "learning_rate": 4.810345222829521e-05, "loss": 4.6873, "step": 2320 }, { "epoch": 0.12489238054240206, "grad_norm": 1.5409889221191406, "learning_rate": 4.810183723965334e-05, "loss": 4.7634, "step": 2321 }, { "epoch": 0.12494619027120103, "grad_norm": 1.8846259117126465, "learning_rate": 4.810022159082309e-05, "loss": 4.4695, "step": 2322 }, { "epoch": 0.125, "grad_norm": 1.840816855430603, "learning_rate": 4.8098605281850634e-05, "loss": 5.0794, "step": 2323 }, { "epoch": 0.12505380972879895, "grad_norm": 1.4165016412734985, "learning_rate": 4.8096988312782174e-05, "loss": 4.739, "step": 2324 }, { "epoch": 0.12510761945759794, "grad_norm": 0.9424957633018494, "learning_rate": 4.809537068366391e-05, "loss": 4.7708, "step": 2325 }, { "epoch": 0.1251614291863969, "grad_norm": 1.2511656284332275, "learning_rate": 4.809375239454207e-05, "loss": 4.7027, "step": 2326 }, { "epoch": 0.12521523891519587, "grad_norm": 1.5139822959899902, "learning_rate": 4.80921334454629e-05, "loss": 4.8461, "step": 2327 }, { "epoch": 0.12526904864399482, "grad_norm": 1.810868501663208, "learning_rate": 4.809051383647267e-05, "loss": 4.7373, "step": 2328 }, { "epoch": 0.1253228583727938, "grad_norm": 2.7635607719421387, "learning_rate": 4.8088893567617656e-05, "loss": 4.7759, "step": 2329 }, { "epoch": 0.12537666810159276, "grad_norm": 1.4061477184295654, "learning_rate": 4.808727263894417e-05, "loss": 5.1717, "step": 2330 }, { "epoch": 0.12543047783039174, "grad_norm": 1.0685961246490479, "learning_rate": 4.8085651050498524e-05, "loss": 4.8029, "step": 2331 }, { "epoch": 0.1254842875591907, "grad_norm": 1.8192800283432007, "learning_rate": 4.8084028802327076e-05, "loss": 4.4138, "step": 2332 }, { "epoch": 0.12553809728798968, "grad_norm": 1.9259769916534424, "learning_rate": 4.808240589447617e-05, "loss": 4.4509, "step": 2333 }, { "epoch": 0.12559190701678863, "grad_norm": 1.4760433435440063, "learning_rate": 4.8080782326992176e-05, "loss": 4.9591, "step": 2334 }, { "epoch": 0.1256457167455876, "grad_norm": 1.62619149684906, "learning_rate": 4.807915809992152e-05, "loss": 4.4684, "step": 2335 }, { "epoch": 0.12569952647438656, "grad_norm": 1.4257915019989014, "learning_rate": 4.807753321331059e-05, "loss": 4.748, "step": 2336 }, { "epoch": 0.12575333620318555, "grad_norm": 1.5058317184448242, "learning_rate": 4.807590766720583e-05, "loss": 4.7435, "step": 2337 }, { "epoch": 0.1258071459319845, "grad_norm": 1.29672372341156, "learning_rate": 4.80742814616537e-05, "loss": 5.0062, "step": 2338 }, { "epoch": 0.12586095566078348, "grad_norm": 1.1548668146133423, "learning_rate": 4.807265459670067e-05, "loss": 4.7549, "step": 2339 }, { "epoch": 0.12591476538958243, "grad_norm": 2.1286964416503906, "learning_rate": 4.8071027072393224e-05, "loss": 4.6464, "step": 2340 }, { "epoch": 0.12596857511838142, "grad_norm": 1.4037449359893799, "learning_rate": 4.806939888877788e-05, "loss": 4.7825, "step": 2341 }, { "epoch": 0.12602238484718037, "grad_norm": 1.2695238590240479, "learning_rate": 4.8067770045901175e-05, "loss": 4.6044, "step": 2342 }, { "epoch": 0.12607619457597935, "grad_norm": 2.046072483062744, "learning_rate": 4.806614054380963e-05, "loss": 4.4443, "step": 2343 }, { "epoch": 0.1261300043047783, "grad_norm": 1.2325359582901, "learning_rate": 4.806451038254984e-05, "loss": 4.4732, "step": 2344 }, { "epoch": 0.12618381403357726, "grad_norm": 1.7193994522094727, "learning_rate": 4.806287956216838e-05, "loss": 4.8579, "step": 2345 }, { "epoch": 0.12623762376237624, "grad_norm": 1.5543999671936035, "learning_rate": 4.806124808271186e-05, "loss": 4.797, "step": 2346 }, { "epoch": 0.1262914334911752, "grad_norm": 1.7823829650878906, "learning_rate": 4.8059615944226885e-05, "loss": 4.6119, "step": 2347 }, { "epoch": 0.12634524321997417, "grad_norm": 1.8060225248336792, "learning_rate": 4.805798314676011e-05, "loss": 4.9278, "step": 2348 }, { "epoch": 0.12639905294877313, "grad_norm": 1.4678438901901245, "learning_rate": 4.80563496903582e-05, "loss": 4.9106, "step": 2349 }, { "epoch": 0.1264528626775721, "grad_norm": 2.2274227142333984, "learning_rate": 4.805471557506783e-05, "loss": 4.4287, "step": 2350 }, { "epoch": 0.12650667240637106, "grad_norm": 1.3256149291992188, "learning_rate": 4.80530808009357e-05, "loss": 4.8786, "step": 2351 }, { "epoch": 0.12656048213517004, "grad_norm": 1.2919096946716309, "learning_rate": 4.805144536800852e-05, "loss": 4.6498, "step": 2352 }, { "epoch": 0.126614291863969, "grad_norm": 1.8196964263916016, "learning_rate": 4.804980927633304e-05, "loss": 4.4422, "step": 2353 }, { "epoch": 0.12666810159276798, "grad_norm": 1.558146357536316, "learning_rate": 4.8048172525956e-05, "loss": 4.7298, "step": 2354 }, { "epoch": 0.12672191132156693, "grad_norm": 1.9293254613876343, "learning_rate": 4.804653511692419e-05, "loss": 3.9818, "step": 2355 }, { "epoch": 0.1267757210503659, "grad_norm": 1.6608823537826538, "learning_rate": 4.8044897049284385e-05, "loss": 4.4966, "step": 2356 }, { "epoch": 0.12682953077916487, "grad_norm": 2.098313331604004, "learning_rate": 4.804325832308342e-05, "loss": 4.7795, "step": 2357 }, { "epoch": 0.12688334050796385, "grad_norm": 1.669766902923584, "learning_rate": 4.80416189383681e-05, "loss": 4.6208, "step": 2358 }, { "epoch": 0.1269371502367628, "grad_norm": 1.8916475772857666, "learning_rate": 4.803997889518529e-05, "loss": 4.6349, "step": 2359 }, { "epoch": 0.12699095996556178, "grad_norm": 1.8030060529708862, "learning_rate": 4.8038338193581846e-05, "loss": 4.4699, "step": 2360 }, { "epoch": 0.12704476969436074, "grad_norm": 2.0331623554229736, "learning_rate": 4.8036696833604666e-05, "loss": 4.2572, "step": 2361 }, { "epoch": 0.12709857942315972, "grad_norm": 1.639369249343872, "learning_rate": 4.803505481530066e-05, "loss": 4.5463, "step": 2362 }, { "epoch": 0.12715238915195867, "grad_norm": 1.4895976781845093, "learning_rate": 4.8033412138716735e-05, "loss": 5.0404, "step": 2363 }, { "epoch": 0.12720619888075765, "grad_norm": 2.8180460929870605, "learning_rate": 4.803176880389984e-05, "loss": 4.7565, "step": 2364 }, { "epoch": 0.1272600086095566, "grad_norm": 1.6165884733200073, "learning_rate": 4.803012481089695e-05, "loss": 4.7144, "step": 2365 }, { "epoch": 0.12731381833835556, "grad_norm": 0.8270487785339355, "learning_rate": 4.8028480159755037e-05, "loss": 4.7955, "step": 2366 }, { "epoch": 0.12736762806715454, "grad_norm": 1.4284745454788208, "learning_rate": 4.8026834850521095e-05, "loss": 4.5423, "step": 2367 }, { "epoch": 0.1274214377959535, "grad_norm": 1.2509527206420898, "learning_rate": 4.802518888324215e-05, "loss": 4.6785, "step": 2368 }, { "epoch": 0.12747524752475248, "grad_norm": 1.5134832859039307, "learning_rate": 4.802354225796524e-05, "loss": 4.5443, "step": 2369 }, { "epoch": 0.12752905725355143, "grad_norm": 0.9767996668815613, "learning_rate": 4.802189497473741e-05, "loss": 5.0288, "step": 2370 }, { "epoch": 0.1275828669823504, "grad_norm": 1.452685832977295, "learning_rate": 4.802024703360575e-05, "loss": 5.0937, "step": 2371 }, { "epoch": 0.12763667671114937, "grad_norm": 1.4620823860168457, "learning_rate": 4.8018598434617344e-05, "loss": 4.7437, "step": 2372 }, { "epoch": 0.12769048643994835, "grad_norm": 1.7578293085098267, "learning_rate": 4.801694917781931e-05, "loss": 4.7367, "step": 2373 }, { "epoch": 0.1277442961687473, "grad_norm": 1.4627174139022827, "learning_rate": 4.801529926325878e-05, "loss": 4.614, "step": 2374 }, { "epoch": 0.12779810589754628, "grad_norm": 0.8703826665878296, "learning_rate": 4.801364869098289e-05, "loss": 4.6748, "step": 2375 }, { "epoch": 0.12785191562634524, "grad_norm": 1.5560377836227417, "learning_rate": 4.8011997461038826e-05, "loss": 4.4486, "step": 2376 }, { "epoch": 0.12790572535514422, "grad_norm": 1.751011848449707, "learning_rate": 4.801034557347378e-05, "loss": 4.5599, "step": 2377 }, { "epoch": 0.12795953508394317, "grad_norm": 1.751336693763733, "learning_rate": 4.8008693028334933e-05, "loss": 3.7928, "step": 2378 }, { "epoch": 0.12801334481274215, "grad_norm": 1.5434281826019287, "learning_rate": 4.800703982566953e-05, "loss": 4.8246, "step": 2379 }, { "epoch": 0.1280671545415411, "grad_norm": 1.3251086473464966, "learning_rate": 4.800538596552481e-05, "loss": 4.7996, "step": 2380 }, { "epoch": 0.1281209642703401, "grad_norm": 1.4134093523025513, "learning_rate": 4.800373144794804e-05, "loss": 4.5883, "step": 2381 }, { "epoch": 0.12817477399913904, "grad_norm": 1.4306399822235107, "learning_rate": 4.8002076272986495e-05, "loss": 4.9049, "step": 2382 }, { "epoch": 0.12822858372793802, "grad_norm": 2.2894062995910645, "learning_rate": 4.8000420440687475e-05, "loss": 4.0619, "step": 2383 }, { "epoch": 0.12828239345673698, "grad_norm": 1.6923184394836426, "learning_rate": 4.7998763951098315e-05, "loss": 4.9532, "step": 2384 }, { "epoch": 0.12833620318553596, "grad_norm": 1.110944151878357, "learning_rate": 4.7997106804266326e-05, "loss": 4.7163, "step": 2385 }, { "epoch": 0.1283900129143349, "grad_norm": 1.579366683959961, "learning_rate": 4.799544900023889e-05, "loss": 4.7888, "step": 2386 }, { "epoch": 0.12844382264313386, "grad_norm": 1.9217252731323242, "learning_rate": 4.799379053906337e-05, "loss": 4.361, "step": 2387 }, { "epoch": 0.12849763237193285, "grad_norm": 1.0188177824020386, "learning_rate": 4.799213142078716e-05, "loss": 4.8753, "step": 2388 }, { "epoch": 0.1285514421007318, "grad_norm": 1.6164287328720093, "learning_rate": 4.799047164545767e-05, "loss": 4.6164, "step": 2389 }, { "epoch": 0.12860525182953078, "grad_norm": 1.506083607673645, "learning_rate": 4.798881121312234e-05, "loss": 4.5605, "step": 2390 }, { "epoch": 0.12865906155832973, "grad_norm": 1.0480751991271973, "learning_rate": 4.798715012382863e-05, "loss": 4.5641, "step": 2391 }, { "epoch": 0.12871287128712872, "grad_norm": 1.9347478151321411, "learning_rate": 4.798548837762399e-05, "loss": 5.022, "step": 2392 }, { "epoch": 0.12876668101592767, "grad_norm": 1.739999771118164, "learning_rate": 4.798382597455591e-05, "loss": 4.558, "step": 2393 }, { "epoch": 0.12882049074472665, "grad_norm": 1.0331172943115234, "learning_rate": 4.7982162914671915e-05, "loss": 4.865, "step": 2394 }, { "epoch": 0.1288743004735256, "grad_norm": 2.2504260540008545, "learning_rate": 4.79804991980195e-05, "loss": 4.7572, "step": 2395 }, { "epoch": 0.1289281102023246, "grad_norm": 1.130548357963562, "learning_rate": 4.797883482464625e-05, "loss": 4.6584, "step": 2396 }, { "epoch": 0.12898191993112354, "grad_norm": 1.3607203960418701, "learning_rate": 4.797716979459969e-05, "loss": 4.7156, "step": 2397 }, { "epoch": 0.12903572965992252, "grad_norm": 2.275286912918091, "learning_rate": 4.7975504107927426e-05, "loss": 4.6737, "step": 2398 }, { "epoch": 0.12908953938872147, "grad_norm": 1.3371697664260864, "learning_rate": 4.797383776467705e-05, "loss": 4.6301, "step": 2399 }, { "epoch": 0.12914334911752046, "grad_norm": 1.5122778415679932, "learning_rate": 4.797217076489618e-05, "loss": 4.8453, "step": 2400 }, { "epoch": 0.1291971588463194, "grad_norm": 1.2424769401550293, "learning_rate": 4.797050310863246e-05, "loss": 4.4266, "step": 2401 }, { "epoch": 0.1292509685751184, "grad_norm": 1.337956190109253, "learning_rate": 4.796883479593355e-05, "loss": 4.8256, "step": 2402 }, { "epoch": 0.12930477830391734, "grad_norm": 1.4004637002944946, "learning_rate": 4.796716582684712e-05, "loss": 4.8388, "step": 2403 }, { "epoch": 0.12935858803271633, "grad_norm": 2.1940314769744873, "learning_rate": 4.796549620142086e-05, "loss": 4.786, "step": 2404 }, { "epoch": 0.12941239776151528, "grad_norm": 1.5268422365188599, "learning_rate": 4.796382591970249e-05, "loss": 4.6987, "step": 2405 }, { "epoch": 0.12946620749031426, "grad_norm": 1.296830415725708, "learning_rate": 4.7962154981739735e-05, "loss": 4.8879, "step": 2406 }, { "epoch": 0.12952001721911321, "grad_norm": 1.3819304704666138, "learning_rate": 4.796048338758036e-05, "loss": 5.0282, "step": 2407 }, { "epoch": 0.1295738269479122, "grad_norm": 0.9391607046127319, "learning_rate": 4.795881113727212e-05, "loss": 4.9809, "step": 2408 }, { "epoch": 0.12962763667671115, "grad_norm": 1.1998445987701416, "learning_rate": 4.795713823086281e-05, "loss": 4.7125, "step": 2409 }, { "epoch": 0.1296814464055101, "grad_norm": 2.5138885974884033, "learning_rate": 4.795546466840024e-05, "loss": 4.5936, "step": 2410 }, { "epoch": 0.12973525613430908, "grad_norm": 1.5687302350997925, "learning_rate": 4.7953790449932234e-05, "loss": 4.6673, "step": 2411 }, { "epoch": 0.12978906586310804, "grad_norm": 1.3393011093139648, "learning_rate": 4.795211557550663e-05, "loss": 4.5959, "step": 2412 }, { "epoch": 0.12984287559190702, "grad_norm": 1.3985029458999634, "learning_rate": 4.795044004517131e-05, "loss": 4.95, "step": 2413 }, { "epoch": 0.12989668532070597, "grad_norm": 1.4828884601593018, "learning_rate": 4.794876385897413e-05, "loss": 4.7843, "step": 2414 }, { "epoch": 0.12995049504950495, "grad_norm": 0.9200325608253479, "learning_rate": 4.7947087016963005e-05, "loss": 4.9924, "step": 2415 }, { "epoch": 0.1300043047783039, "grad_norm": 1.2038449048995972, "learning_rate": 4.794540951918585e-05, "loss": 4.7973, "step": 2416 }, { "epoch": 0.1300581145071029, "grad_norm": 1.6900516748428345, "learning_rate": 4.7943731365690616e-05, "loss": 4.5699, "step": 2417 }, { "epoch": 0.13011192423590184, "grad_norm": 1.0989967584609985, "learning_rate": 4.794205255652525e-05, "loss": 4.7646, "step": 2418 }, { "epoch": 0.13016573396470082, "grad_norm": 1.338124394416809, "learning_rate": 4.794037309173772e-05, "loss": 4.6976, "step": 2419 }, { "epoch": 0.13021954369349978, "grad_norm": 1.5965379476547241, "learning_rate": 4.7938692971376036e-05, "loss": 4.6045, "step": 2420 }, { "epoch": 0.13027335342229876, "grad_norm": 1.3058947324752808, "learning_rate": 4.793701219548821e-05, "loss": 4.6253, "step": 2421 }, { "epoch": 0.1303271631510977, "grad_norm": 1.216261863708496, "learning_rate": 4.7935330764122256e-05, "loss": 4.4236, "step": 2422 }, { "epoch": 0.1303809728798967, "grad_norm": 1.4120879173278809, "learning_rate": 4.7933648677326247e-05, "loss": 4.8555, "step": 2423 }, { "epoch": 0.13043478260869565, "grad_norm": 1.6341010332107544, "learning_rate": 4.793196593514824e-05, "loss": 4.8363, "step": 2424 }, { "epoch": 0.13048859233749463, "grad_norm": 1.6356141567230225, "learning_rate": 4.793028253763633e-05, "loss": 4.6275, "step": 2425 }, { "epoch": 0.13054240206629358, "grad_norm": 1.423080563545227, "learning_rate": 4.792859848483862e-05, "loss": 4.6746, "step": 2426 }, { "epoch": 0.13059621179509256, "grad_norm": 1.531541109085083, "learning_rate": 4.792691377680323e-05, "loss": 4.7092, "step": 2427 }, { "epoch": 0.13065002152389152, "grad_norm": 1.8211711645126343, "learning_rate": 4.792522841357831e-05, "loss": 4.3211, "step": 2428 }, { "epoch": 0.1307038312526905, "grad_norm": 1.3316739797592163, "learning_rate": 4.792354239521203e-05, "loss": 4.9569, "step": 2429 }, { "epoch": 0.13075764098148945, "grad_norm": 1.788915991783142, "learning_rate": 4.792185572175256e-05, "loss": 4.9018, "step": 2430 }, { "epoch": 0.1308114507102884, "grad_norm": 1.6665139198303223, "learning_rate": 4.792016839324811e-05, "loss": 4.6557, "step": 2431 }, { "epoch": 0.1308652604390874, "grad_norm": 1.4490553140640259, "learning_rate": 4.791848040974689e-05, "loss": 4.5325, "step": 2432 }, { "epoch": 0.13091907016788634, "grad_norm": 1.6702876091003418, "learning_rate": 4.7916791771297154e-05, "loss": 4.8046, "step": 2433 }, { "epoch": 0.13097287989668532, "grad_norm": 1.21486496925354, "learning_rate": 4.791510247794714e-05, "loss": 4.3143, "step": 2434 }, { "epoch": 0.13102668962548428, "grad_norm": 1.020788311958313, "learning_rate": 4.7913412529745126e-05, "loss": 4.3339, "step": 2435 }, { "epoch": 0.13108049935428326, "grad_norm": 1.918824315071106, "learning_rate": 4.791172192673943e-05, "loss": 4.6057, "step": 2436 }, { "epoch": 0.1311343090830822, "grad_norm": 1.3172963857650757, "learning_rate": 4.791003066897833e-05, "loss": 5.0559, "step": 2437 }, { "epoch": 0.1311881188118812, "grad_norm": 1.8086745738983154, "learning_rate": 4.790833875651018e-05, "loss": 4.3621, "step": 2438 }, { "epoch": 0.13124192854068015, "grad_norm": 1.5650904178619385, "learning_rate": 4.790664618938332e-05, "loss": 4.818, "step": 2439 }, { "epoch": 0.13129573826947913, "grad_norm": 1.5877513885498047, "learning_rate": 4.7904952967646134e-05, "loss": 4.5013, "step": 2440 }, { "epoch": 0.13134954799827808, "grad_norm": 1.3311735391616821, "learning_rate": 4.790325909134699e-05, "loss": 4.7794, "step": 2441 }, { "epoch": 0.13140335772707706, "grad_norm": 1.1912425756454468, "learning_rate": 4.790156456053431e-05, "loss": 4.5516, "step": 2442 }, { "epoch": 0.13145716745587602, "grad_norm": 1.254288911819458, "learning_rate": 4.78998693752565e-05, "loss": 4.6159, "step": 2443 }, { "epoch": 0.131510977184675, "grad_norm": 1.134005069732666, "learning_rate": 4.789817353556203e-05, "loss": 4.4907, "step": 2444 }, { "epoch": 0.13156478691347395, "grad_norm": 1.5899715423583984, "learning_rate": 4.7896477041499344e-05, "loss": 4.5582, "step": 2445 }, { "epoch": 0.13161859664227293, "grad_norm": 1.2116048336029053, "learning_rate": 4.789477989311693e-05, "loss": 4.5099, "step": 2446 }, { "epoch": 0.1316724063710719, "grad_norm": 1.6289664506912231, "learning_rate": 4.789308209046329e-05, "loss": 4.9597, "step": 2447 }, { "epoch": 0.13172621609987087, "grad_norm": 1.489067554473877, "learning_rate": 4.789138363358693e-05, "loss": 4.5809, "step": 2448 }, { "epoch": 0.13178002582866982, "grad_norm": 1.0024563074111938, "learning_rate": 4.788968452253641e-05, "loss": 4.6302, "step": 2449 }, { "epoch": 0.1318338355574688, "grad_norm": 1.2015573978424072, "learning_rate": 4.788798475736026e-05, "loss": 4.7655, "step": 2450 }, { "epoch": 0.13188764528626776, "grad_norm": 2.7656280994415283, "learning_rate": 4.788628433810707e-05, "loss": 4.5532, "step": 2451 }, { "epoch": 0.1319414550150667, "grad_norm": 1.2393947839736938, "learning_rate": 4.788458326482543e-05, "loss": 5.1678, "step": 2452 }, { "epoch": 0.1319952647438657, "grad_norm": 1.2326701879501343, "learning_rate": 4.788288153756395e-05, "loss": 4.8754, "step": 2453 }, { "epoch": 0.13204907447266465, "grad_norm": 2.138580560684204, "learning_rate": 4.788117915637127e-05, "loss": 4.49, "step": 2454 }, { "epoch": 0.13210288420146363, "grad_norm": 1.4641976356506348, "learning_rate": 4.787947612129603e-05, "loss": 4.9754, "step": 2455 }, { "epoch": 0.13215669393026258, "grad_norm": 1.4598983526229858, "learning_rate": 4.78777724323869e-05, "loss": 4.6887, "step": 2456 }, { "epoch": 0.13221050365906156, "grad_norm": 0.8897148370742798, "learning_rate": 4.787606808969257e-05, "loss": 4.766, "step": 2457 }, { "epoch": 0.13226431338786052, "grad_norm": 1.4096951484680176, "learning_rate": 4.7874363093261745e-05, "loss": 4.8322, "step": 2458 }, { "epoch": 0.1323181231166595, "grad_norm": 1.7646185159683228, "learning_rate": 4.7872657443143144e-05, "loss": 4.5809, "step": 2459 }, { "epoch": 0.13237193284545845, "grad_norm": 1.4661496877670288, "learning_rate": 4.7870951139385515e-05, "loss": 4.9324, "step": 2460 }, { "epoch": 0.13242574257425743, "grad_norm": 1.3286957740783691, "learning_rate": 4.786924418203762e-05, "loss": 4.7363, "step": 2461 }, { "epoch": 0.13247955230305639, "grad_norm": 1.6935148239135742, "learning_rate": 4.786753657114823e-05, "loss": 4.5307, "step": 2462 }, { "epoch": 0.13253336203185537, "grad_norm": 1.8889009952545166, "learning_rate": 4.7865828306766157e-05, "loss": 4.0721, "step": 2463 }, { "epoch": 0.13258717176065432, "grad_norm": 1.3728049993515015, "learning_rate": 4.7864119388940216e-05, "loss": 4.7488, "step": 2464 }, { "epoch": 0.1326409814894533, "grad_norm": 1.2166599035263062, "learning_rate": 4.786240981771923e-05, "loss": 4.6906, "step": 2465 }, { "epoch": 0.13269479121825226, "grad_norm": 1.0575437545776367, "learning_rate": 4.786069959315208e-05, "loss": 4.7033, "step": 2466 }, { "epoch": 0.13274860094705124, "grad_norm": 2.1011300086975098, "learning_rate": 4.785898871528761e-05, "loss": 4.5165, "step": 2467 }, { "epoch": 0.1328024106758502, "grad_norm": 1.3338253498077393, "learning_rate": 4.7857277184174735e-05, "loss": 4.7056, "step": 2468 }, { "epoch": 0.13285622040464917, "grad_norm": 1.817445158958435, "learning_rate": 4.785556499986235e-05, "loss": 4.5404, "step": 2469 }, { "epoch": 0.13291003013344813, "grad_norm": 2.0685319900512695, "learning_rate": 4.7853852162399385e-05, "loss": 4.1256, "step": 2470 }, { "epoch": 0.1329638398622471, "grad_norm": 0.9836385846138, "learning_rate": 4.785213867183481e-05, "loss": 5.0175, "step": 2471 }, { "epoch": 0.13301764959104606, "grad_norm": 2.0241847038269043, "learning_rate": 4.785042452821756e-05, "loss": 4.8625, "step": 2472 }, { "epoch": 0.13307145931984501, "grad_norm": 2.2986183166503906, "learning_rate": 4.7848709731596654e-05, "loss": 4.8839, "step": 2473 }, { "epoch": 0.133125269048644, "grad_norm": 0.8503960371017456, "learning_rate": 4.784699428202107e-05, "loss": 4.6398, "step": 2474 }, { "epoch": 0.13317907877744295, "grad_norm": 1.772074818611145, "learning_rate": 4.784527817953984e-05, "loss": 4.761, "step": 2475 }, { "epoch": 0.13323288850624193, "grad_norm": 1.2942438125610352, "learning_rate": 4.784356142420202e-05, "loss": 4.662, "step": 2476 }, { "epoch": 0.13328669823504088, "grad_norm": 1.7803837060928345, "learning_rate": 4.784184401605664e-05, "loss": 4.4285, "step": 2477 }, { "epoch": 0.13334050796383987, "grad_norm": 1.45599365234375, "learning_rate": 4.7840125955152805e-05, "loss": 4.4273, "step": 2478 }, { "epoch": 0.13339431769263882, "grad_norm": 1.301159143447876, "learning_rate": 4.7838407241539595e-05, "loss": 4.8105, "step": 2479 }, { "epoch": 0.1334481274214378, "grad_norm": 1.8529523611068726, "learning_rate": 4.783668787526615e-05, "loss": 4.3975, "step": 2480 }, { "epoch": 0.13350193715023675, "grad_norm": 1.5463067293167114, "learning_rate": 4.783496785638158e-05, "loss": 4.7587, "step": 2481 }, { "epoch": 0.13355574687903574, "grad_norm": 1.6624661684036255, "learning_rate": 4.783324718493504e-05, "loss": 4.7481, "step": 2482 }, { "epoch": 0.1336095566078347, "grad_norm": 1.3330018520355225, "learning_rate": 4.783152586097571e-05, "loss": 4.7272, "step": 2483 }, { "epoch": 0.13366336633663367, "grad_norm": 1.1008062362670898, "learning_rate": 4.782980388455279e-05, "loss": 4.5592, "step": 2484 }, { "epoch": 0.13371717606543262, "grad_norm": 1.1632379293441772, "learning_rate": 4.782808125571547e-05, "loss": 4.9201, "step": 2485 }, { "epoch": 0.1337709857942316, "grad_norm": 1.5110808610916138, "learning_rate": 4.7826357974512994e-05, "loss": 4.8606, "step": 2486 }, { "epoch": 0.13382479552303056, "grad_norm": 1.5294158458709717, "learning_rate": 4.78246340409946e-05, "loss": 4.3025, "step": 2487 }, { "epoch": 0.13387860525182954, "grad_norm": 0.9155494570732117, "learning_rate": 4.7822909455209564e-05, "loss": 4.6661, "step": 2488 }, { "epoch": 0.1339324149806285, "grad_norm": 1.362605094909668, "learning_rate": 4.782118421720716e-05, "loss": 4.5706, "step": 2489 }, { "epoch": 0.13398622470942748, "grad_norm": 1.4117989540100098, "learning_rate": 4.781945832703668e-05, "loss": 4.6006, "step": 2490 }, { "epoch": 0.13404003443822643, "grad_norm": 2.1971797943115234, "learning_rate": 4.781773178474747e-05, "loss": 4.8885, "step": 2491 }, { "epoch": 0.1340938441670254, "grad_norm": 1.2026907205581665, "learning_rate": 4.781600459038886e-05, "loss": 4.875, "step": 2492 }, { "epoch": 0.13414765389582436, "grad_norm": 1.649084448814392, "learning_rate": 4.78142767440102e-05, "loss": 4.6529, "step": 2493 }, { "epoch": 0.13420146362462332, "grad_norm": 1.1119465827941895, "learning_rate": 4.7812548245660874e-05, "loss": 4.803, "step": 2494 }, { "epoch": 0.1342552733534223, "grad_norm": 1.183457612991333, "learning_rate": 4.781081909539028e-05, "loss": 4.9381, "step": 2495 }, { "epoch": 0.13430908308222125, "grad_norm": 1.394032597541809, "learning_rate": 4.7809089293247834e-05, "loss": 4.6641, "step": 2496 }, { "epoch": 0.13436289281102023, "grad_norm": 1.6918197870254517, "learning_rate": 4.780735883928296e-05, "loss": 4.8403, "step": 2497 }, { "epoch": 0.1344167025398192, "grad_norm": 1.134470820426941, "learning_rate": 4.780562773354512e-05, "loss": 4.7597, "step": 2498 }, { "epoch": 0.13447051226861817, "grad_norm": 1.2708948850631714, "learning_rate": 4.780389597608377e-05, "loss": 4.7982, "step": 2499 }, { "epoch": 0.13452432199741712, "grad_norm": 1.682474136352539, "learning_rate": 4.780216356694842e-05, "loss": 4.8357, "step": 2500 }, { "epoch": 0.1345781317262161, "grad_norm": 2.0432727336883545, "learning_rate": 4.7800430506188556e-05, "loss": 4.6838, "step": 2501 }, { "epoch": 0.13463194145501506, "grad_norm": 1.6467227935791016, "learning_rate": 4.7798696793853714e-05, "loss": 4.5347, "step": 2502 }, { "epoch": 0.13468575118381404, "grad_norm": 2.1237423419952393, "learning_rate": 4.779696242999345e-05, "loss": 4.6099, "step": 2503 }, { "epoch": 0.134739560912613, "grad_norm": 2.643050193786621, "learning_rate": 4.779522741465731e-05, "loss": 4.926, "step": 2504 }, { "epoch": 0.13479337064141197, "grad_norm": 1.4746464490890503, "learning_rate": 4.7793491747894874e-05, "loss": 5.0209, "step": 2505 }, { "epoch": 0.13484718037021093, "grad_norm": 2.2260611057281494, "learning_rate": 4.779175542975576e-05, "loss": 4.4832, "step": 2506 }, { "epoch": 0.1349009900990099, "grad_norm": 1.2958422899246216, "learning_rate": 4.779001846028957e-05, "loss": 4.5449, "step": 2507 }, { "epoch": 0.13495479982780886, "grad_norm": 1.8038233518600464, "learning_rate": 4.7788280839545965e-05, "loss": 4.3491, "step": 2508 }, { "epoch": 0.13500860955660784, "grad_norm": 2.296617031097412, "learning_rate": 4.7786542567574574e-05, "loss": 4.4833, "step": 2509 }, { "epoch": 0.1350624192854068, "grad_norm": 1.6909936666488647, "learning_rate": 4.77848036444251e-05, "loss": 4.7667, "step": 2510 }, { "epoch": 0.13511622901420578, "grad_norm": 1.5484894514083862, "learning_rate": 4.778306407014721e-05, "loss": 4.8559, "step": 2511 }, { "epoch": 0.13517003874300473, "grad_norm": 1.1481900215148926, "learning_rate": 4.7781323844790626e-05, "loss": 4.7817, "step": 2512 }, { "epoch": 0.13522384847180371, "grad_norm": 2.3800787925720215, "learning_rate": 4.777958296840509e-05, "loss": 4.7418, "step": 2513 }, { "epoch": 0.13527765820060267, "grad_norm": 1.5013508796691895, "learning_rate": 4.777784144104034e-05, "loss": 4.8338, "step": 2514 }, { "epoch": 0.13533146792940162, "grad_norm": 1.6646995544433594, "learning_rate": 4.7776099262746146e-05, "loss": 4.6957, "step": 2515 }, { "epoch": 0.1353852776582006, "grad_norm": 1.2384634017944336, "learning_rate": 4.777435643357229e-05, "loss": 4.9946, "step": 2516 }, { "epoch": 0.13543908738699956, "grad_norm": 1.7127777338027954, "learning_rate": 4.777261295356859e-05, "loss": 4.5042, "step": 2517 }, { "epoch": 0.13549289711579854, "grad_norm": 1.6444636583328247, "learning_rate": 4.777086882278485e-05, "loss": 5.296, "step": 2518 }, { "epoch": 0.1355467068445975, "grad_norm": 1.7927885055541992, "learning_rate": 4.7769124041270944e-05, "loss": 4.8018, "step": 2519 }, { "epoch": 0.13560051657339647, "grad_norm": 0.991309642791748, "learning_rate": 4.7767378609076706e-05, "loss": 4.835, "step": 2520 }, { "epoch": 0.13565432630219543, "grad_norm": 1.9776705503463745, "learning_rate": 4.7765632526252025e-05, "loss": 4.5791, "step": 2521 }, { "epoch": 0.1357081360309944, "grad_norm": 1.5937864780426025, "learning_rate": 4.77638857928468e-05, "loss": 4.7776, "step": 2522 }, { "epoch": 0.13576194575979336, "grad_norm": 0.8060270547866821, "learning_rate": 4.776213840891094e-05, "loss": 4.8134, "step": 2523 }, { "epoch": 0.13581575548859234, "grad_norm": 1.491960048675537, "learning_rate": 4.77603903744944e-05, "loss": 4.7688, "step": 2524 }, { "epoch": 0.1358695652173913, "grad_norm": 1.555223822593689, "learning_rate": 4.775864168964711e-05, "loss": 4.7765, "step": 2525 }, { "epoch": 0.13592337494619028, "grad_norm": 1.8091955184936523, "learning_rate": 4.775689235441906e-05, "loss": 4.7682, "step": 2526 }, { "epoch": 0.13597718467498923, "grad_norm": 1.4525161981582642, "learning_rate": 4.775514236886023e-05, "loss": 4.5997, "step": 2527 }, { "epoch": 0.1360309944037882, "grad_norm": 1.3059848546981812, "learning_rate": 4.775339173302064e-05, "loss": 4.713, "step": 2528 }, { "epoch": 0.13608480413258717, "grad_norm": 1.5738186836242676, "learning_rate": 4.7751640446950306e-05, "loss": 4.3063, "step": 2529 }, { "epoch": 0.13613861386138615, "grad_norm": 1.324399471282959, "learning_rate": 4.7749888510699293e-05, "loss": 4.7843, "step": 2530 }, { "epoch": 0.1361924235901851, "grad_norm": 1.4897373914718628, "learning_rate": 4.774813592431765e-05, "loss": 4.701, "step": 2531 }, { "epoch": 0.13624623331898408, "grad_norm": 1.5708398818969727, "learning_rate": 4.774638268785547e-05, "loss": 4.6214, "step": 2532 }, { "epoch": 0.13630004304778304, "grad_norm": 1.8021838665008545, "learning_rate": 4.7744628801362855e-05, "loss": 4.469, "step": 2533 }, { "epoch": 0.13635385277658202, "grad_norm": 1.314388394355774, "learning_rate": 4.7742874264889926e-05, "loss": 4.6745, "step": 2534 }, { "epoch": 0.13640766250538097, "grad_norm": 1.4707074165344238, "learning_rate": 4.774111907848682e-05, "loss": 4.7423, "step": 2535 }, { "epoch": 0.13646147223417995, "grad_norm": 1.4530538320541382, "learning_rate": 4.7739363242203695e-05, "loss": 5.0896, "step": 2536 }, { "epoch": 0.1365152819629789, "grad_norm": 1.2706533670425415, "learning_rate": 4.7737606756090725e-05, "loss": 4.8302, "step": 2537 }, { "epoch": 0.13656909169177786, "grad_norm": 1.4025484323501587, "learning_rate": 4.773584962019812e-05, "loss": 4.7738, "step": 2538 }, { "epoch": 0.13662290142057684, "grad_norm": 1.4179028272628784, "learning_rate": 4.7734091834576084e-05, "loss": 4.6471, "step": 2539 }, { "epoch": 0.1366767111493758, "grad_norm": 1.61436128616333, "learning_rate": 4.7732333399274845e-05, "loss": 4.7227, "step": 2540 }, { "epoch": 0.13673052087817478, "grad_norm": 1.0896885395050049, "learning_rate": 4.773057431434467e-05, "loss": 4.4607, "step": 2541 }, { "epoch": 0.13678433060697373, "grad_norm": 1.360518217086792, "learning_rate": 4.772881457983581e-05, "loss": 4.945, "step": 2542 }, { "epoch": 0.1368381403357727, "grad_norm": 1.1935646533966064, "learning_rate": 4.772705419579857e-05, "loss": 4.5678, "step": 2543 }, { "epoch": 0.13689195006457167, "grad_norm": 2.4390058517456055, "learning_rate": 4.772529316228324e-05, "loss": 4.5396, "step": 2544 }, { "epoch": 0.13694575979337065, "grad_norm": 1.1268610954284668, "learning_rate": 4.772353147934017e-05, "loss": 4.5703, "step": 2545 }, { "epoch": 0.1369995695221696, "grad_norm": 2.042168617248535, "learning_rate": 4.7721769147019674e-05, "loss": 4.5985, "step": 2546 }, { "epoch": 0.13705337925096858, "grad_norm": 1.325128436088562, "learning_rate": 4.772000616537213e-05, "loss": 4.5782, "step": 2547 }, { "epoch": 0.13710718897976754, "grad_norm": 1.0316673517227173, "learning_rate": 4.7718242534447935e-05, "loss": 4.9865, "step": 2548 }, { "epoch": 0.13716099870856652, "grad_norm": 2.3037474155426025, "learning_rate": 4.771647825429746e-05, "loss": 4.3558, "step": 2549 }, { "epoch": 0.13721480843736547, "grad_norm": 1.05557119846344, "learning_rate": 4.771471332497114e-05, "loss": 4.9033, "step": 2550 }, { "epoch": 0.13726861816616445, "grad_norm": 1.5074061155319214, "learning_rate": 4.771294774651941e-05, "loss": 4.4711, "step": 2551 }, { "epoch": 0.1373224278949634, "grad_norm": 1.0976890325546265, "learning_rate": 4.7711181518992726e-05, "loss": 4.5625, "step": 2552 }, { "epoch": 0.1373762376237624, "grad_norm": 1.524235486984253, "learning_rate": 4.770941464244156e-05, "loss": 4.4985, "step": 2553 }, { "epoch": 0.13743004735256134, "grad_norm": 1.572024941444397, "learning_rate": 4.77076471169164e-05, "loss": 4.3945, "step": 2554 }, { "epoch": 0.13748385708136032, "grad_norm": 1.641483187675476, "learning_rate": 4.770587894246776e-05, "loss": 4.8504, "step": 2555 }, { "epoch": 0.13753766681015928, "grad_norm": 1.9228572845458984, "learning_rate": 4.770411011914618e-05, "loss": 4.592, "step": 2556 }, { "epoch": 0.13759147653895826, "grad_norm": 1.5688366889953613, "learning_rate": 4.7702340647002195e-05, "loss": 5.0851, "step": 2557 }, { "epoch": 0.1376452862677572, "grad_norm": 1.9038852453231812, "learning_rate": 4.7700570526086377e-05, "loss": 4.5688, "step": 2558 }, { "epoch": 0.13769909599655616, "grad_norm": 1.2868177890777588, "learning_rate": 4.769879975644931e-05, "loss": 4.8222, "step": 2559 }, { "epoch": 0.13775290572535515, "grad_norm": 1.1757073402404785, "learning_rate": 4.7697028338141594e-05, "loss": 4.4881, "step": 2560 }, { "epoch": 0.1378067154541541, "grad_norm": 1.4720892906188965, "learning_rate": 4.769525627121386e-05, "loss": 4.6679, "step": 2561 }, { "epoch": 0.13786052518295308, "grad_norm": 1.1376234292984009, "learning_rate": 4.769348355571675e-05, "loss": 4.832, "step": 2562 }, { "epoch": 0.13791433491175203, "grad_norm": 1.0478229522705078, "learning_rate": 4.7691710191700914e-05, "loss": 4.9554, "step": 2563 }, { "epoch": 0.13796814464055102, "grad_norm": 1.8106491565704346, "learning_rate": 4.768993617921703e-05, "loss": 4.476, "step": 2564 }, { "epoch": 0.13802195436934997, "grad_norm": 1.490846872329712, "learning_rate": 4.7688161518315813e-05, "loss": 4.4528, "step": 2565 }, { "epoch": 0.13807576409814895, "grad_norm": 0.9283332824707031, "learning_rate": 4.768638620904795e-05, "loss": 4.8986, "step": 2566 }, { "epoch": 0.1381295738269479, "grad_norm": 0.8999826312065125, "learning_rate": 4.768461025146419e-05, "loss": 4.9151, "step": 2567 }, { "epoch": 0.13818338355574689, "grad_norm": 1.741570234298706, "learning_rate": 4.768283364561529e-05, "loss": 4.654, "step": 2568 }, { "epoch": 0.13823719328454584, "grad_norm": 1.6954715251922607, "learning_rate": 4.7681056391552004e-05, "loss": 4.8848, "step": 2569 }, { "epoch": 0.13829100301334482, "grad_norm": 1.8318060636520386, "learning_rate": 4.767927848932514e-05, "loss": 4.3829, "step": 2570 }, { "epoch": 0.13834481274214377, "grad_norm": 1.58379065990448, "learning_rate": 4.767749993898549e-05, "loss": 5.1983, "step": 2571 }, { "epoch": 0.13839862247094276, "grad_norm": 1.3008719682693481, "learning_rate": 4.7675720740583894e-05, "loss": 4.7489, "step": 2572 }, { "epoch": 0.1384524321997417, "grad_norm": 1.2651969194412231, "learning_rate": 4.7673940894171185e-05, "loss": 4.7797, "step": 2573 }, { "epoch": 0.1385062419285407, "grad_norm": 1.4228956699371338, "learning_rate": 4.767216039979824e-05, "loss": 4.8976, "step": 2574 }, { "epoch": 0.13856005165733964, "grad_norm": 1.147928237915039, "learning_rate": 4.767037925751592e-05, "loss": 4.7707, "step": 2575 }, { "epoch": 0.13861386138613863, "grad_norm": 2.234295129776001, "learning_rate": 4.766859746737514e-05, "loss": 4.4128, "step": 2576 }, { "epoch": 0.13866767111493758, "grad_norm": 1.6987725496292114, "learning_rate": 4.7666815029426816e-05, "loss": 4.9467, "step": 2577 }, { "epoch": 0.13872148084373656, "grad_norm": 1.3020001649856567, "learning_rate": 4.7665031943721884e-05, "loss": 4.6453, "step": 2578 }, { "epoch": 0.13877529057253551, "grad_norm": 1.2577264308929443, "learning_rate": 4.766324821031131e-05, "loss": 4.6974, "step": 2579 }, { "epoch": 0.13882910030133447, "grad_norm": 1.5564041137695312, "learning_rate": 4.7661463829246045e-05, "loss": 4.8268, "step": 2580 }, { "epoch": 0.13888291003013345, "grad_norm": 1.9025051593780518, "learning_rate": 4.765967880057711e-05, "loss": 4.7878, "step": 2581 }, { "epoch": 0.1389367197589324, "grad_norm": 1.4587403535842896, "learning_rate": 4.765789312435549e-05, "loss": 4.597, "step": 2582 }, { "epoch": 0.13899052948773138, "grad_norm": 1.2076297998428345, "learning_rate": 4.7656106800632234e-05, "loss": 4.8359, "step": 2583 }, { "epoch": 0.13904433921653034, "grad_norm": 1.7765823602676392, "learning_rate": 4.765431982945838e-05, "loss": 4.8558, "step": 2584 }, { "epoch": 0.13909814894532932, "grad_norm": 0.9990647435188293, "learning_rate": 4.7652532210885006e-05, "loss": 4.7786, "step": 2585 }, { "epoch": 0.13915195867412827, "grad_norm": 1.7945002317428589, "learning_rate": 4.7650743944963175e-05, "loss": 4.481, "step": 2586 }, { "epoch": 0.13920576840292725, "grad_norm": 1.4679183959960938, "learning_rate": 4.764895503174401e-05, "loss": 4.4777, "step": 2587 }, { "epoch": 0.1392595781317262, "grad_norm": 1.4214814901351929, "learning_rate": 4.764716547127864e-05, "loss": 4.6705, "step": 2588 }, { "epoch": 0.1393133878605252, "grad_norm": 1.8941351175308228, "learning_rate": 4.764537526361819e-05, "loss": 4.3358, "step": 2589 }, { "epoch": 0.13936719758932414, "grad_norm": 1.3879600763320923, "learning_rate": 4.764358440881382e-05, "loss": 4.8508, "step": 2590 }, { "epoch": 0.13942100731812312, "grad_norm": 1.5080329179763794, "learning_rate": 4.764179290691671e-05, "loss": 4.6433, "step": 2591 }, { "epoch": 0.13947481704692208, "grad_norm": 1.9254543781280518, "learning_rate": 4.764000075797806e-05, "loss": 4.3498, "step": 2592 }, { "epoch": 0.13952862677572106, "grad_norm": 1.5058389902114868, "learning_rate": 4.7638207962049084e-05, "loss": 4.6912, "step": 2593 }, { "epoch": 0.13958243650452, "grad_norm": 1.4938380718231201, "learning_rate": 4.7636414519181013e-05, "loss": 4.9412, "step": 2594 }, { "epoch": 0.139636246233319, "grad_norm": 1.348734736442566, "learning_rate": 4.7634620429425105e-05, "loss": 4.6373, "step": 2595 }, { "epoch": 0.13969005596211795, "grad_norm": 1.4956215620040894, "learning_rate": 4.7632825692832616e-05, "loss": 4.5532, "step": 2596 }, { "epoch": 0.13974386569091693, "grad_norm": 1.8838375806808472, "learning_rate": 4.763103030945485e-05, "loss": 4.8432, "step": 2597 }, { "epoch": 0.13979767541971588, "grad_norm": 2.0523862838745117, "learning_rate": 4.7629234279343105e-05, "loss": 4.889, "step": 2598 }, { "epoch": 0.13985148514851486, "grad_norm": 2.219208240509033, "learning_rate": 4.762743760254871e-05, "loss": 4.972, "step": 2599 }, { "epoch": 0.13990529487731382, "grad_norm": 1.2026262283325195, "learning_rate": 4.7625640279123014e-05, "loss": 4.8551, "step": 2600 }, { "epoch": 0.13995910460611277, "grad_norm": 2.4917685985565186, "learning_rate": 4.7623842309117374e-05, "loss": 4.5494, "step": 2601 }, { "epoch": 0.14001291433491175, "grad_norm": 1.1735877990722656, "learning_rate": 4.762204369258316e-05, "loss": 5.0087, "step": 2602 }, { "epoch": 0.1400667240637107, "grad_norm": 2.6380863189697266, "learning_rate": 4.762024442957179e-05, "loss": 4.5089, "step": 2603 }, { "epoch": 0.1401205337925097, "grad_norm": 2.434779644012451, "learning_rate": 4.761844452013469e-05, "loss": 4.1261, "step": 2604 }, { "epoch": 0.14017434352130864, "grad_norm": 2.453486680984497, "learning_rate": 4.761664396432326e-05, "loss": 4.7038, "step": 2605 }, { "epoch": 0.14022815325010762, "grad_norm": 1.6381837129592896, "learning_rate": 4.7614842762188996e-05, "loss": 4.9125, "step": 2606 }, { "epoch": 0.14028196297890658, "grad_norm": 1.4450719356536865, "learning_rate": 4.7613040913783334e-05, "loss": 5.0443, "step": 2607 }, { "epoch": 0.14033577270770556, "grad_norm": 1.625340223312378, "learning_rate": 4.76112384191578e-05, "loss": 4.7349, "step": 2608 }, { "epoch": 0.1403895824365045, "grad_norm": 1.1787699460983276, "learning_rate": 4.760943527836388e-05, "loss": 4.7726, "step": 2609 }, { "epoch": 0.1404433921653035, "grad_norm": 1.224400281906128, "learning_rate": 4.7607631491453117e-05, "loss": 4.854, "step": 2610 }, { "epoch": 0.14049720189410245, "grad_norm": 1.3582944869995117, "learning_rate": 4.7605827058477045e-05, "loss": 5.0227, "step": 2611 }, { "epoch": 0.14055101162290143, "grad_norm": 1.7479875087738037, "learning_rate": 4.760402197948725e-05, "loss": 4.9124, "step": 2612 }, { "epoch": 0.14060482135170038, "grad_norm": 1.46597158908844, "learning_rate": 4.76022162545353e-05, "loss": 4.3583, "step": 2613 }, { "epoch": 0.14065863108049936, "grad_norm": 1.532881259918213, "learning_rate": 4.7600409883672805e-05, "loss": 4.9181, "step": 2614 }, { "epoch": 0.14071244080929832, "grad_norm": 1.1608377695083618, "learning_rate": 4.7598602866951375e-05, "loss": 4.6447, "step": 2615 }, { "epoch": 0.1407662505380973, "grad_norm": 1.8352664709091187, "learning_rate": 4.7596795204422665e-05, "loss": 4.5328, "step": 2616 }, { "epoch": 0.14082006026689625, "grad_norm": 1.5524715185165405, "learning_rate": 4.759498689613832e-05, "loss": 4.8789, "step": 2617 }, { "epoch": 0.14087386999569523, "grad_norm": 1.5954465866088867, "learning_rate": 4.759317794215003e-05, "loss": 4.7837, "step": 2618 }, { "epoch": 0.1409276797244942, "grad_norm": 1.2962709665298462, "learning_rate": 4.759136834250948e-05, "loss": 4.783, "step": 2619 }, { "epoch": 0.14098148945329317, "grad_norm": 1.0135936737060547, "learning_rate": 4.7589558097268386e-05, "loss": 4.8987, "step": 2620 }, { "epoch": 0.14103529918209212, "grad_norm": 1.6557139158248901, "learning_rate": 4.7587747206478484e-05, "loss": 4.6618, "step": 2621 }, { "epoch": 0.14108910891089108, "grad_norm": 1.631569743156433, "learning_rate": 4.758593567019152e-05, "loss": 4.514, "step": 2622 }, { "epoch": 0.14114291863969006, "grad_norm": 1.5542728900909424, "learning_rate": 4.7584123488459256e-05, "loss": 5.0361, "step": 2623 }, { "epoch": 0.141196728368489, "grad_norm": 1.1254767179489136, "learning_rate": 4.75823106613335e-05, "loss": 4.7136, "step": 2624 }, { "epoch": 0.141250538097288, "grad_norm": 1.465639352798462, "learning_rate": 4.758049718886603e-05, "loss": 5.1977, "step": 2625 }, { "epoch": 0.14130434782608695, "grad_norm": 1.805277705192566, "learning_rate": 4.7578683071108686e-05, "loss": 4.7674, "step": 2626 }, { "epoch": 0.14135815755488593, "grad_norm": 1.0302845239639282, "learning_rate": 4.757686830811332e-05, "loss": 4.758, "step": 2627 }, { "epoch": 0.14141196728368488, "grad_norm": 2.3116495609283447, "learning_rate": 4.7575052899931774e-05, "loss": 4.8623, "step": 2628 }, { "epoch": 0.14146577701248386, "grad_norm": 1.886446475982666, "learning_rate": 4.757323684661594e-05, "loss": 4.4607, "step": 2629 }, { "epoch": 0.14151958674128282, "grad_norm": 1.1330114603042603, "learning_rate": 4.757142014821771e-05, "loss": 5.041, "step": 2630 }, { "epoch": 0.1415733964700818, "grad_norm": 1.0884767770767212, "learning_rate": 4.756960280478901e-05, "loss": 5.0388, "step": 2631 }, { "epoch": 0.14162720619888075, "grad_norm": 2.3583014011383057, "learning_rate": 4.756778481638176e-05, "loss": 4.4361, "step": 2632 }, { "epoch": 0.14168101592767973, "grad_norm": 1.3122270107269287, "learning_rate": 4.756596618304792e-05, "loss": 5.1345, "step": 2633 }, { "epoch": 0.14173482565647869, "grad_norm": 2.0811944007873535, "learning_rate": 4.7564146904839456e-05, "loss": 4.2736, "step": 2634 }, { "epoch": 0.14178863538527767, "grad_norm": 1.426693320274353, "learning_rate": 4.756232698180837e-05, "loss": 4.7582, "step": 2635 }, { "epoch": 0.14184244511407662, "grad_norm": 2.2457611560821533, "learning_rate": 4.756050641400667e-05, "loss": 4.7647, "step": 2636 }, { "epoch": 0.1418962548428756, "grad_norm": 2.0429797172546387, "learning_rate": 4.755868520148637e-05, "loss": 4.908, "step": 2637 }, { "epoch": 0.14195006457167456, "grad_norm": 1.222146987915039, "learning_rate": 4.755686334429952e-05, "loss": 4.9573, "step": 2638 }, { "epoch": 0.14200387430047354, "grad_norm": 1.8061447143554688, "learning_rate": 4.7555040842498194e-05, "loss": 4.3372, "step": 2639 }, { "epoch": 0.1420576840292725, "grad_norm": 1.865689992904663, "learning_rate": 4.755321769613446e-05, "loss": 4.6436, "step": 2640 }, { "epoch": 0.14211149375807147, "grad_norm": 1.550004243850708, "learning_rate": 4.755139390526043e-05, "loss": 4.8635, "step": 2641 }, { "epoch": 0.14216530348687043, "grad_norm": 0.9630684852600098, "learning_rate": 4.754956946992822e-05, "loss": 4.7235, "step": 2642 }, { "epoch": 0.14221911321566938, "grad_norm": 1.508097767829895, "learning_rate": 4.754774439018996e-05, "loss": 4.5303, "step": 2643 }, { "epoch": 0.14227292294446836, "grad_norm": 1.8387068510055542, "learning_rate": 4.754591866609782e-05, "loss": 4.5142, "step": 2644 }, { "epoch": 0.14232673267326731, "grad_norm": 2.0396926403045654, "learning_rate": 4.7544092297703955e-05, "loss": 4.6694, "step": 2645 }, { "epoch": 0.1423805424020663, "grad_norm": 1.628395438194275, "learning_rate": 4.7542265285060575e-05, "loss": 4.4971, "step": 2646 }, { "epoch": 0.14243435213086525, "grad_norm": 1.45489501953125, "learning_rate": 4.754043762821988e-05, "loss": 5.0197, "step": 2647 }, { "epoch": 0.14248816185966423, "grad_norm": 1.2630761861801147, "learning_rate": 4.7538609327234114e-05, "loss": 4.7713, "step": 2648 }, { "epoch": 0.14254197158846318, "grad_norm": 1.2282946109771729, "learning_rate": 4.75367803821555e-05, "loss": 4.7035, "step": 2649 }, { "epoch": 0.14259578131726217, "grad_norm": 1.2537845373153687, "learning_rate": 4.753495079303634e-05, "loss": 4.422, "step": 2650 }, { "epoch": 0.14264959104606112, "grad_norm": 1.2391133308410645, "learning_rate": 4.7533120559928875e-05, "loss": 4.7638, "step": 2651 }, { "epoch": 0.1427034007748601, "grad_norm": 1.1589059829711914, "learning_rate": 4.753128968288545e-05, "loss": 4.7308, "step": 2652 }, { "epoch": 0.14275721050365905, "grad_norm": 1.0430378913879395, "learning_rate": 4.752945816195836e-05, "loss": 4.909, "step": 2653 }, { "epoch": 0.14281102023245804, "grad_norm": 1.4420167207717896, "learning_rate": 4.752762599719995e-05, "loss": 4.8637, "step": 2654 }, { "epoch": 0.142864829961257, "grad_norm": 0.9489731192588806, "learning_rate": 4.7525793188662595e-05, "loss": 4.708, "step": 2655 }, { "epoch": 0.14291863969005597, "grad_norm": 1.3564984798431396, "learning_rate": 4.752395973639864e-05, "loss": 4.4702, "step": 2656 }, { "epoch": 0.14297244941885492, "grad_norm": 1.689976692199707, "learning_rate": 4.752212564046051e-05, "loss": 5.0276, "step": 2657 }, { "epoch": 0.1430262591476539, "grad_norm": 1.5990002155303955, "learning_rate": 4.7520290900900596e-05, "loss": 4.9022, "step": 2658 }, { "epoch": 0.14308006887645286, "grad_norm": 2.5367116928100586, "learning_rate": 4.751845551777135e-05, "loss": 4.4635, "step": 2659 }, { "epoch": 0.14313387860525184, "grad_norm": 2.0780842304229736, "learning_rate": 4.751661949112521e-05, "loss": 4.7253, "step": 2660 }, { "epoch": 0.1431876883340508, "grad_norm": 1.0043835639953613, "learning_rate": 4.751478282101465e-05, "loss": 4.8262, "step": 2661 }, { "epoch": 0.14324149806284978, "grad_norm": 1.2189922332763672, "learning_rate": 4.7512945507492154e-05, "loss": 4.3573, "step": 2662 }, { "epoch": 0.14329530779164873, "grad_norm": 1.3065212965011597, "learning_rate": 4.751110755061022e-05, "loss": 4.8279, "step": 2663 }, { "epoch": 0.14334911752044768, "grad_norm": 1.4503189325332642, "learning_rate": 4.750926895042139e-05, "loss": 4.8002, "step": 2664 }, { "epoch": 0.14340292724924666, "grad_norm": 1.6706420183181763, "learning_rate": 4.750742970697819e-05, "loss": 4.7395, "step": 2665 }, { "epoch": 0.14345673697804562, "grad_norm": 1.4103184938430786, "learning_rate": 4.75055898203332e-05, "loss": 4.8527, "step": 2666 }, { "epoch": 0.1435105467068446, "grad_norm": 2.025535821914673, "learning_rate": 4.750374929053897e-05, "loss": 4.6445, "step": 2667 }, { "epoch": 0.14356435643564355, "grad_norm": 1.1859409809112549, "learning_rate": 4.750190811764812e-05, "loss": 4.4666, "step": 2668 }, { "epoch": 0.14361816616444253, "grad_norm": 1.6138436794281006, "learning_rate": 4.7500066301713254e-05, "loss": 4.7734, "step": 2669 }, { "epoch": 0.1436719758932415, "grad_norm": 1.8148332834243774, "learning_rate": 4.749822384278702e-05, "loss": 4.4147, "step": 2670 }, { "epoch": 0.14372578562204047, "grad_norm": 2.1559629440307617, "learning_rate": 4.7496380740922054e-05, "loss": 4.8485, "step": 2671 }, { "epoch": 0.14377959535083942, "grad_norm": 1.2892249822616577, "learning_rate": 4.749453699617104e-05, "loss": 4.9003, "step": 2672 }, { "epoch": 0.1438334050796384, "grad_norm": 1.5951817035675049, "learning_rate": 4.749269260858665e-05, "loss": 4.724, "step": 2673 }, { "epoch": 0.14388721480843736, "grad_norm": 1.1551523208618164, "learning_rate": 4.749084757822161e-05, "loss": 4.58, "step": 2674 }, { "epoch": 0.14394102453723634, "grad_norm": 1.5332826375961304, "learning_rate": 4.748900190512865e-05, "loss": 5.0709, "step": 2675 }, { "epoch": 0.1439948342660353, "grad_norm": 2.036935567855835, "learning_rate": 4.748715558936049e-05, "loss": 4.6666, "step": 2676 }, { "epoch": 0.14404864399483427, "grad_norm": 1.6499162912368774, "learning_rate": 4.748530863096992e-05, "loss": 4.7618, "step": 2677 }, { "epoch": 0.14410245372363323, "grad_norm": 1.888453722000122, "learning_rate": 4.748346103000969e-05, "loss": 5.0135, "step": 2678 }, { "epoch": 0.1441562634524322, "grad_norm": 1.353999376296997, "learning_rate": 4.748161278653263e-05, "loss": 4.163, "step": 2679 }, { "epoch": 0.14421007318123116, "grad_norm": 1.146079659461975, "learning_rate": 4.747976390059154e-05, "loss": 4.6138, "step": 2680 }, { "epoch": 0.14426388291003014, "grad_norm": 1.6098649501800537, "learning_rate": 4.747791437223926e-05, "loss": 4.8999, "step": 2681 }, { "epoch": 0.1443176926388291, "grad_norm": 1.6034637689590454, "learning_rate": 4.747606420152866e-05, "loss": 4.758, "step": 2682 }, { "epoch": 0.14437150236762808, "grad_norm": 1.247009038925171, "learning_rate": 4.747421338851258e-05, "loss": 4.6286, "step": 2683 }, { "epoch": 0.14442531209642703, "grad_norm": 1.4658477306365967, "learning_rate": 4.747236193324394e-05, "loss": 4.6836, "step": 2684 }, { "epoch": 0.14447912182522601, "grad_norm": 1.9987623691558838, "learning_rate": 4.747050983577563e-05, "loss": 4.5944, "step": 2685 }, { "epoch": 0.14453293155402497, "grad_norm": 1.1522022485733032, "learning_rate": 4.74686570961606e-05, "loss": 4.8634, "step": 2686 }, { "epoch": 0.14458674128282392, "grad_norm": 1.4257731437683105, "learning_rate": 4.746680371445178e-05, "loss": 4.947, "step": 2687 }, { "epoch": 0.1446405510116229, "grad_norm": 1.394392490386963, "learning_rate": 4.7464949690702135e-05, "loss": 4.7804, "step": 2688 }, { "epoch": 0.14469436074042186, "grad_norm": 1.591322660446167, "learning_rate": 4.746309502496465e-05, "loss": 4.407, "step": 2689 }, { "epoch": 0.14474817046922084, "grad_norm": 1.607962965965271, "learning_rate": 4.746123971729234e-05, "loss": 4.7514, "step": 2690 }, { "epoch": 0.1448019801980198, "grad_norm": 1.8678319454193115, "learning_rate": 4.74593837677382e-05, "loss": 4.7394, "step": 2691 }, { "epoch": 0.14485578992681877, "grad_norm": 1.8463554382324219, "learning_rate": 4.745752717635529e-05, "loss": 5.0675, "step": 2692 }, { "epoch": 0.14490959965561773, "grad_norm": 1.3346149921417236, "learning_rate": 4.745566994319665e-05, "loss": 4.6726, "step": 2693 }, { "epoch": 0.1449634093844167, "grad_norm": 1.8102335929870605, "learning_rate": 4.7453812068315364e-05, "loss": 4.796, "step": 2694 }, { "epoch": 0.14501721911321566, "grad_norm": 1.9023631811141968, "learning_rate": 4.7451953551764516e-05, "loss": 4.5234, "step": 2695 }, { "epoch": 0.14507102884201464, "grad_norm": 2.135676145553589, "learning_rate": 4.7450094393597236e-05, "loss": 4.4847, "step": 2696 }, { "epoch": 0.1451248385708136, "grad_norm": 1.976017713546753, "learning_rate": 4.744823459386663e-05, "loss": 4.9601, "step": 2697 }, { "epoch": 0.14517864829961258, "grad_norm": 2.108983039855957, "learning_rate": 4.744637415262586e-05, "loss": 4.6153, "step": 2698 }, { "epoch": 0.14523245802841153, "grad_norm": 1.7643989324569702, "learning_rate": 4.74445130699281e-05, "loss": 4.7017, "step": 2699 }, { "epoch": 0.1452862677572105, "grad_norm": 1.7000285387039185, "learning_rate": 4.7442651345826515e-05, "loss": 4.4132, "step": 2700 }, { "epoch": 0.14534007748600947, "grad_norm": 1.2602651119232178, "learning_rate": 4.7440788980374326e-05, "loss": 5.1611, "step": 2701 }, { "epoch": 0.14539388721480845, "grad_norm": 1.3206530809402466, "learning_rate": 4.743892597362474e-05, "loss": 4.8365, "step": 2702 }, { "epoch": 0.1454476969436074, "grad_norm": 1.1897118091583252, "learning_rate": 4.7437062325631005e-05, "loss": 4.822, "step": 2703 }, { "epoch": 0.14550150667240638, "grad_norm": 1.1526191234588623, "learning_rate": 4.743519803644638e-05, "loss": 4.6792, "step": 2704 }, { "epoch": 0.14555531640120534, "grad_norm": 1.620611310005188, "learning_rate": 4.743333310612414e-05, "loss": 4.587, "step": 2705 }, { "epoch": 0.14560912613000432, "grad_norm": 1.8586151599884033, "learning_rate": 4.743146753471757e-05, "loss": 4.7279, "step": 2706 }, { "epoch": 0.14566293585880327, "grad_norm": 1.7940294742584229, "learning_rate": 4.742960132227999e-05, "loss": 4.6752, "step": 2707 }, { "epoch": 0.14571674558760223, "grad_norm": 1.5614813566207886, "learning_rate": 4.742773446886475e-05, "loss": 4.4446, "step": 2708 }, { "epoch": 0.1457705553164012, "grad_norm": 2.1707770824432373, "learning_rate": 4.742586697452517e-05, "loss": 4.6843, "step": 2709 }, { "epoch": 0.14582436504520016, "grad_norm": 1.5678311586380005, "learning_rate": 4.7423998839314634e-05, "loss": 4.8006, "step": 2710 }, { "epoch": 0.14587817477399914, "grad_norm": 1.6286665201187134, "learning_rate": 4.742213006328652e-05, "loss": 4.6391, "step": 2711 }, { "epoch": 0.1459319845027981, "grad_norm": 1.3035540580749512, "learning_rate": 4.742026064649424e-05, "loss": 4.8142, "step": 2712 }, { "epoch": 0.14598579423159708, "grad_norm": 1.9737998247146606, "learning_rate": 4.741839058899121e-05, "loss": 4.3274, "step": 2713 }, { "epoch": 0.14603960396039603, "grad_norm": 3.343991756439209, "learning_rate": 4.741651989083089e-05, "loss": 4.7697, "step": 2714 }, { "epoch": 0.146093413689195, "grad_norm": 1.6484167575836182, "learning_rate": 4.741464855206671e-05, "loss": 4.8312, "step": 2715 }, { "epoch": 0.14614722341799397, "grad_norm": 1.7838656902313232, "learning_rate": 4.741277657275217e-05, "loss": 4.6343, "step": 2716 }, { "epoch": 0.14620103314679295, "grad_norm": 1.271666169166565, "learning_rate": 4.7410903952940755e-05, "loss": 4.7781, "step": 2717 }, { "epoch": 0.1462548428755919, "grad_norm": 1.805808186531067, "learning_rate": 4.740903069268598e-05, "loss": 4.6932, "step": 2718 }, { "epoch": 0.14630865260439088, "grad_norm": 0.9596149325370789, "learning_rate": 4.740715679204139e-05, "loss": 4.7477, "step": 2719 }, { "epoch": 0.14636246233318984, "grad_norm": 1.4091678857803345, "learning_rate": 4.740528225106052e-05, "loss": 5.0757, "step": 2720 }, { "epoch": 0.14641627206198882, "grad_norm": 1.6499226093292236, "learning_rate": 4.740340706979695e-05, "loss": 4.5636, "step": 2721 }, { "epoch": 0.14647008179078777, "grad_norm": 2.0514345169067383, "learning_rate": 4.740153124830427e-05, "loss": 4.6456, "step": 2722 }, { "epoch": 0.14652389151958675, "grad_norm": 1.697109580039978, "learning_rate": 4.739965478663606e-05, "loss": 4.824, "step": 2723 }, { "epoch": 0.1465777012483857, "grad_norm": 1.868367314338684, "learning_rate": 4.739777768484598e-05, "loss": 4.5004, "step": 2724 }, { "epoch": 0.1466315109771847, "grad_norm": 1.3275628089904785, "learning_rate": 4.7395899942987654e-05, "loss": 4.7285, "step": 2725 }, { "epoch": 0.14668532070598364, "grad_norm": 1.068832278251648, "learning_rate": 4.739402156111475e-05, "loss": 4.8983, "step": 2726 }, { "epoch": 0.14673913043478262, "grad_norm": 1.6196001768112183, "learning_rate": 4.739214253928094e-05, "loss": 4.9548, "step": 2727 }, { "epoch": 0.14679294016358158, "grad_norm": 1.2992041110992432, "learning_rate": 4.739026287753991e-05, "loss": 5.0246, "step": 2728 }, { "epoch": 0.14684674989238053, "grad_norm": 1.2603979110717773, "learning_rate": 4.738838257594541e-05, "loss": 4.7961, "step": 2729 }, { "epoch": 0.1469005596211795, "grad_norm": 1.4470503330230713, "learning_rate": 4.738650163455114e-05, "loss": 5.0048, "step": 2730 }, { "epoch": 0.14695436934997846, "grad_norm": 1.3060909509658813, "learning_rate": 4.738462005341088e-05, "loss": 4.8042, "step": 2731 }, { "epoch": 0.14700817907877745, "grad_norm": 2.1419336795806885, "learning_rate": 4.7382737832578375e-05, "loss": 4.174, "step": 2732 }, { "epoch": 0.1470619888075764, "grad_norm": 1.9423677921295166, "learning_rate": 4.7380854972107424e-05, "loss": 4.7465, "step": 2733 }, { "epoch": 0.14711579853637538, "grad_norm": 1.2752305269241333, "learning_rate": 4.737897147205184e-05, "loss": 4.857, "step": 2734 }, { "epoch": 0.14716960826517433, "grad_norm": 1.4624720811843872, "learning_rate": 4.737708733246544e-05, "loss": 4.9125, "step": 2735 }, { "epoch": 0.14722341799397332, "grad_norm": 1.5291681289672852, "learning_rate": 4.7375202553402083e-05, "loss": 4.8313, "step": 2736 }, { "epoch": 0.14727722772277227, "grad_norm": 1.7273582220077515, "learning_rate": 4.737331713491561e-05, "loss": 4.9011, "step": 2737 }, { "epoch": 0.14733103745157125, "grad_norm": 1.1785869598388672, "learning_rate": 4.737143107705991e-05, "loss": 4.7676, "step": 2738 }, { "epoch": 0.1473848471803702, "grad_norm": 1.6138787269592285, "learning_rate": 4.736954437988888e-05, "loss": 4.2581, "step": 2739 }, { "epoch": 0.14743865690916919, "grad_norm": 0.9478234648704529, "learning_rate": 4.736765704345644e-05, "loss": 4.914, "step": 2740 }, { "epoch": 0.14749246663796814, "grad_norm": 1.5586352348327637, "learning_rate": 4.736576906781653e-05, "loss": 5.1985, "step": 2741 }, { "epoch": 0.14754627636676712, "grad_norm": 1.8354873657226562, "learning_rate": 4.736388045302309e-05, "loss": 4.8936, "step": 2742 }, { "epoch": 0.14760008609556607, "grad_norm": 1.6179360151290894, "learning_rate": 4.73619911991301e-05, "loss": 4.6255, "step": 2743 }, { "epoch": 0.14765389582436506, "grad_norm": 1.024337649345398, "learning_rate": 4.736010130619155e-05, "loss": 4.9657, "step": 2744 }, { "epoch": 0.147707705553164, "grad_norm": 1.1744797229766846, "learning_rate": 4.7358210774261444e-05, "loss": 4.8505, "step": 2745 }, { "epoch": 0.147761515281963, "grad_norm": 1.089333176612854, "learning_rate": 4.735631960339381e-05, "loss": 4.7314, "step": 2746 }, { "epoch": 0.14781532501076194, "grad_norm": 1.314778447151184, "learning_rate": 4.7354427793642694e-05, "loss": 4.5779, "step": 2747 }, { "epoch": 0.14786913473956093, "grad_norm": 1.275622010231018, "learning_rate": 4.735253534506216e-05, "loss": 4.7434, "step": 2748 }, { "epoch": 0.14792294446835988, "grad_norm": 1.6111226081848145, "learning_rate": 4.735064225770629e-05, "loss": 4.6862, "step": 2749 }, { "epoch": 0.14797675419715883, "grad_norm": 1.5738849639892578, "learning_rate": 4.734874853162917e-05, "loss": 4.4455, "step": 2750 }, { "epoch": 0.14803056392595781, "grad_norm": 1.2306914329528809, "learning_rate": 4.734685416688494e-05, "loss": 4.7267, "step": 2751 }, { "epoch": 0.14808437365475677, "grad_norm": 1.3741366863250732, "learning_rate": 4.7344959163527716e-05, "loss": 4.9845, "step": 2752 }, { "epoch": 0.14813818338355575, "grad_norm": 1.7962429523468018, "learning_rate": 4.734306352161166e-05, "loss": 4.7029, "step": 2753 }, { "epoch": 0.1481919931123547, "grad_norm": 1.3590081930160522, "learning_rate": 4.734116724119095e-05, "loss": 4.6649, "step": 2754 }, { "epoch": 0.14824580284115368, "grad_norm": 1.7424755096435547, "learning_rate": 4.733927032231977e-05, "loss": 5.0545, "step": 2755 }, { "epoch": 0.14829961256995264, "grad_norm": 1.502719759941101, "learning_rate": 4.733737276505232e-05, "loss": 5.1248, "step": 2756 }, { "epoch": 0.14835342229875162, "grad_norm": 2.6489226818084717, "learning_rate": 4.733547456944285e-05, "loss": 4.4629, "step": 2757 }, { "epoch": 0.14840723202755057, "grad_norm": 1.3810555934906006, "learning_rate": 4.7333575735545585e-05, "loss": 4.6626, "step": 2758 }, { "epoch": 0.14846104175634955, "grad_norm": 1.7630716562271118, "learning_rate": 4.733167626341479e-05, "loss": 4.6427, "step": 2759 }, { "epoch": 0.1485148514851485, "grad_norm": 1.7481356859207153, "learning_rate": 4.7329776153104766e-05, "loss": 4.6155, "step": 2760 }, { "epoch": 0.1485686612139475, "grad_norm": 1.2866097688674927, "learning_rate": 4.732787540466979e-05, "loss": 4.9834, "step": 2761 }, { "epoch": 0.14862247094274644, "grad_norm": 1.2275633811950684, "learning_rate": 4.73259740181642e-05, "loss": 4.7299, "step": 2762 }, { "epoch": 0.14867628067154542, "grad_norm": 1.312101125717163, "learning_rate": 4.732407199364231e-05, "loss": 4.5571, "step": 2763 }, { "epoch": 0.14873009040034438, "grad_norm": 2.1145405769348145, "learning_rate": 4.7322169331158496e-05, "loss": 4.476, "step": 2764 }, { "epoch": 0.14878390012914336, "grad_norm": 0.9053170680999756, "learning_rate": 4.732026603076711e-05, "loss": 4.6161, "step": 2765 }, { "epoch": 0.1488377098579423, "grad_norm": 1.7499380111694336, "learning_rate": 4.7318362092522575e-05, "loss": 4.7414, "step": 2766 }, { "epoch": 0.1488915195867413, "grad_norm": 2.0229814052581787, "learning_rate": 4.7316457516479264e-05, "loss": 4.4939, "step": 2767 }, { "epoch": 0.14894532931554025, "grad_norm": 2.1910202503204346, "learning_rate": 4.7314552302691626e-05, "loss": 4.8999, "step": 2768 }, { "epoch": 0.14899913904433923, "grad_norm": 1.267255425453186, "learning_rate": 4.73126464512141e-05, "loss": 5.0583, "step": 2769 }, { "epoch": 0.14905294877313818, "grad_norm": 1.4808528423309326, "learning_rate": 4.731073996210116e-05, "loss": 4.6003, "step": 2770 }, { "epoch": 0.14910675850193714, "grad_norm": 1.6346291303634644, "learning_rate": 4.730883283540728e-05, "loss": 4.6654, "step": 2771 }, { "epoch": 0.14916056823073612, "grad_norm": 1.5114315748214722, "learning_rate": 4.730692507118696e-05, "loss": 4.6764, "step": 2772 }, { "epoch": 0.14921437795953507, "grad_norm": 1.2714487314224243, "learning_rate": 4.730501666949471e-05, "loss": 4.7388, "step": 2773 }, { "epoch": 0.14926818768833405, "grad_norm": 1.0238358974456787, "learning_rate": 4.730310763038509e-05, "loss": 4.5249, "step": 2774 }, { "epoch": 0.149321997417133, "grad_norm": 2.2160627841949463, "learning_rate": 4.7301197953912634e-05, "loss": 4.2411, "step": 2775 }, { "epoch": 0.149375807145932, "grad_norm": 1.257063388824463, "learning_rate": 4.729928764013193e-05, "loss": 4.7438, "step": 2776 }, { "epoch": 0.14942961687473094, "grad_norm": 1.3981679677963257, "learning_rate": 4.7297376689097555e-05, "loss": 4.624, "step": 2777 }, { "epoch": 0.14948342660352992, "grad_norm": 1.0552127361297607, "learning_rate": 4.7295465100864133e-05, "loss": 4.4815, "step": 2778 }, { "epoch": 0.14953723633232888, "grad_norm": 1.0415598154067993, "learning_rate": 4.729355287548629e-05, "loss": 5.0499, "step": 2779 }, { "epoch": 0.14959104606112786, "grad_norm": 2.0810582637786865, "learning_rate": 4.7291640013018655e-05, "loss": 4.6082, "step": 2780 }, { "epoch": 0.1496448557899268, "grad_norm": 1.2622497081756592, "learning_rate": 4.728972651351592e-05, "loss": 4.9094, "step": 2781 }, { "epoch": 0.1496986655187258, "grad_norm": 1.8560675382614136, "learning_rate": 4.7287812377032746e-05, "loss": 4.7082, "step": 2782 }, { "epoch": 0.14975247524752475, "grad_norm": 1.7959803342819214, "learning_rate": 4.728589760362384e-05, "loss": 4.6025, "step": 2783 }, { "epoch": 0.14980628497632373, "grad_norm": 1.1583492755889893, "learning_rate": 4.728398219334393e-05, "loss": 4.3749, "step": 2784 }, { "epoch": 0.14986009470512268, "grad_norm": 1.123461365699768, "learning_rate": 4.728206614624774e-05, "loss": 4.8462, "step": 2785 }, { "epoch": 0.14991390443392166, "grad_norm": 1.0407016277313232, "learning_rate": 4.728014946239003e-05, "loss": 4.4941, "step": 2786 }, { "epoch": 0.14996771416272062, "grad_norm": 1.6342229843139648, "learning_rate": 4.727823214182558e-05, "loss": 4.7261, "step": 2787 }, { "epoch": 0.1500215238915196, "grad_norm": 1.9398432970046997, "learning_rate": 4.727631418460918e-05, "loss": 4.8148, "step": 2788 }, { "epoch": 0.15007533362031855, "grad_norm": 1.4391992092132568, "learning_rate": 4.727439559079563e-05, "loss": 4.4777, "step": 2789 }, { "epoch": 0.15012914334911753, "grad_norm": 1.2994260787963867, "learning_rate": 4.7272476360439766e-05, "loss": 4.6557, "step": 2790 }, { "epoch": 0.1501829530779165, "grad_norm": 1.150399088859558, "learning_rate": 4.7270556493596436e-05, "loss": 4.8526, "step": 2791 }, { "epoch": 0.15023676280671544, "grad_norm": 1.7409924268722534, "learning_rate": 4.7268635990320496e-05, "loss": 4.3334, "step": 2792 }, { "epoch": 0.15029057253551442, "grad_norm": 1.1310313940048218, "learning_rate": 4.726671485066685e-05, "loss": 4.7514, "step": 2793 }, { "epoch": 0.15034438226431338, "grad_norm": 1.3602906465530396, "learning_rate": 4.7264793074690365e-05, "loss": 4.2924, "step": 2794 }, { "epoch": 0.15039819199311236, "grad_norm": 1.8641756772994995, "learning_rate": 4.726287066244599e-05, "loss": 4.6362, "step": 2795 }, { "epoch": 0.1504520017219113, "grad_norm": 1.258466362953186, "learning_rate": 4.7260947613988646e-05, "loss": 5.0514, "step": 2796 }, { "epoch": 0.1505058114507103, "grad_norm": 1.4140727519989014, "learning_rate": 4.7259023929373304e-05, "loss": 4.8614, "step": 2797 }, { "epoch": 0.15055962117950925, "grad_norm": 2.244818925857544, "learning_rate": 4.725709960865492e-05, "loss": 4.6421, "step": 2798 }, { "epoch": 0.15061343090830823, "grad_norm": 1.374434232711792, "learning_rate": 4.725517465188849e-05, "loss": 4.8228, "step": 2799 }, { "epoch": 0.15066724063710718, "grad_norm": 1.9041584730148315, "learning_rate": 4.7253249059129037e-05, "loss": 4.6615, "step": 2800 }, { "epoch": 0.15072105036590616, "grad_norm": 1.045099139213562, "learning_rate": 4.7251322830431575e-05, "loss": 4.5864, "step": 2801 }, { "epoch": 0.15077486009470512, "grad_norm": 1.2159538269042969, "learning_rate": 4.724939596585116e-05, "loss": 4.3903, "step": 2802 }, { "epoch": 0.1508286698235041, "grad_norm": 0.954367458820343, "learning_rate": 4.7247468465442846e-05, "loss": 4.9548, "step": 2803 }, { "epoch": 0.15088247955230305, "grad_norm": 1.5335241556167603, "learning_rate": 4.724554032926172e-05, "loss": 4.7345, "step": 2804 }, { "epoch": 0.15093628928110203, "grad_norm": 1.8016430139541626, "learning_rate": 4.724361155736289e-05, "loss": 4.9844, "step": 2805 }, { "epoch": 0.15099009900990099, "grad_norm": 1.1299744844436646, "learning_rate": 4.724168214980147e-05, "loss": 4.6238, "step": 2806 }, { "epoch": 0.15104390873869997, "grad_norm": 1.4712862968444824, "learning_rate": 4.72397521066326e-05, "loss": 4.4859, "step": 2807 }, { "epoch": 0.15109771846749892, "grad_norm": 0.9241631031036377, "learning_rate": 4.723782142791143e-05, "loss": 4.7057, "step": 2808 }, { "epoch": 0.1511515281962979, "grad_norm": 1.9466115236282349, "learning_rate": 4.723589011369314e-05, "loss": 4.6736, "step": 2809 }, { "epoch": 0.15120533792509686, "grad_norm": 1.3125325441360474, "learning_rate": 4.723395816403291e-05, "loss": 4.6134, "step": 2810 }, { "epoch": 0.15125914765389584, "grad_norm": 2.0236940383911133, "learning_rate": 4.723202557898596e-05, "loss": 4.396, "step": 2811 }, { "epoch": 0.1513129573826948, "grad_norm": 1.2806729078292847, "learning_rate": 4.723009235860751e-05, "loss": 4.7795, "step": 2812 }, { "epoch": 0.15136676711149377, "grad_norm": 1.2257860898971558, "learning_rate": 4.7228158502952824e-05, "loss": 4.7409, "step": 2813 }, { "epoch": 0.15142057684029273, "grad_norm": 1.3234360218048096, "learning_rate": 4.7226224012077156e-05, "loss": 4.9567, "step": 2814 }, { "epoch": 0.15147438656909168, "grad_norm": 1.2810770273208618, "learning_rate": 4.722428888603578e-05, "loss": 4.5662, "step": 2815 }, { "epoch": 0.15152819629789066, "grad_norm": 1.786757469177246, "learning_rate": 4.722235312488401e-05, "loss": 4.5161, "step": 2816 }, { "epoch": 0.15158200602668961, "grad_norm": 1.3184807300567627, "learning_rate": 4.722041672867715e-05, "loss": 4.9021, "step": 2817 }, { "epoch": 0.1516358157554886, "grad_norm": 1.3302979469299316, "learning_rate": 4.7218479697470555e-05, "loss": 4.5643, "step": 2818 }, { "epoch": 0.15168962548428755, "grad_norm": 1.8296253681182861, "learning_rate": 4.7216542031319564e-05, "loss": 4.5839, "step": 2819 }, { "epoch": 0.15174343521308653, "grad_norm": 1.4805656671524048, "learning_rate": 4.721460373027956e-05, "loss": 4.9214, "step": 2820 }, { "epoch": 0.15179724494188548, "grad_norm": 1.8703042268753052, "learning_rate": 4.7212664794405934e-05, "loss": 4.382, "step": 2821 }, { "epoch": 0.15185105467068447, "grad_norm": 1.731192708015442, "learning_rate": 4.721072522375409e-05, "loss": 4.7981, "step": 2822 }, { "epoch": 0.15190486439948342, "grad_norm": 1.7404897212982178, "learning_rate": 4.7208785018379456e-05, "loss": 5.1825, "step": 2823 }, { "epoch": 0.1519586741282824, "grad_norm": 1.7036629915237427, "learning_rate": 4.7206844178337485e-05, "loss": 4.2445, "step": 2824 }, { "epoch": 0.15201248385708135, "grad_norm": 1.0815924406051636, "learning_rate": 4.720490270368364e-05, "loss": 4.8374, "step": 2825 }, { "epoch": 0.15206629358588034, "grad_norm": 2.1663687229156494, "learning_rate": 4.720296059447339e-05, "loss": 4.6409, "step": 2826 }, { "epoch": 0.1521201033146793, "grad_norm": 1.5443216562271118, "learning_rate": 4.7201017850762254e-05, "loss": 4.4963, "step": 2827 }, { "epoch": 0.15217391304347827, "grad_norm": 1.622479796409607, "learning_rate": 4.719907447260574e-05, "loss": 4.3197, "step": 2828 }, { "epoch": 0.15222772277227722, "grad_norm": 2.091301679611206, "learning_rate": 4.719713046005938e-05, "loss": 4.5063, "step": 2829 }, { "epoch": 0.1522815325010762, "grad_norm": 1.7567461729049683, "learning_rate": 4.7195185813178745e-05, "loss": 4.576, "step": 2830 }, { "epoch": 0.15233534222987516, "grad_norm": 1.8803300857543945, "learning_rate": 4.719324053201939e-05, "loss": 4.9078, "step": 2831 }, { "epoch": 0.15238915195867414, "grad_norm": 1.7327804565429688, "learning_rate": 4.7191294616636916e-05, "loss": 4.7864, "step": 2832 }, { "epoch": 0.1524429616874731, "grad_norm": 1.438459038734436, "learning_rate": 4.7189348067086924e-05, "loss": 4.5792, "step": 2833 }, { "epoch": 0.15249677141627208, "grad_norm": 1.5129210948944092, "learning_rate": 4.718740088342506e-05, "loss": 4.5671, "step": 2834 }, { "epoch": 0.15255058114507103, "grad_norm": 1.6299383640289307, "learning_rate": 4.718545306570694e-05, "loss": 3.9882, "step": 2835 }, { "epoch": 0.15260439087386998, "grad_norm": 1.1053327322006226, "learning_rate": 4.718350461398825e-05, "loss": 4.8459, "step": 2836 }, { "epoch": 0.15265820060266896, "grad_norm": 1.632910966873169, "learning_rate": 4.718155552832467e-05, "loss": 4.5019, "step": 2837 }, { "epoch": 0.15271201033146792, "grad_norm": 2.361739158630371, "learning_rate": 4.7179605808771885e-05, "loss": 4.172, "step": 2838 }, { "epoch": 0.1527658200602669, "grad_norm": 1.4552204608917236, "learning_rate": 4.7177655455385625e-05, "loss": 4.7943, "step": 2839 }, { "epoch": 0.15281962978906585, "grad_norm": 1.1535093784332275, "learning_rate": 4.7175704468221626e-05, "loss": 4.7646, "step": 2840 }, { "epoch": 0.15287343951786483, "grad_norm": 1.5953768491744995, "learning_rate": 4.717375284733564e-05, "loss": 4.9579, "step": 2841 }, { "epoch": 0.1529272492466638, "grad_norm": 2.1063809394836426, "learning_rate": 4.717180059278344e-05, "loss": 4.7179, "step": 2842 }, { "epoch": 0.15298105897546277, "grad_norm": 1.1281214952468872, "learning_rate": 4.716984770462081e-05, "loss": 4.9876, "step": 2843 }, { "epoch": 0.15303486870426172, "grad_norm": 1.9727963209152222, "learning_rate": 4.716789418290356e-05, "loss": 4.4317, "step": 2844 }, { "epoch": 0.1530886784330607, "grad_norm": 2.039260149002075, "learning_rate": 4.716594002768752e-05, "loss": 4.9891, "step": 2845 }, { "epoch": 0.15314248816185966, "grad_norm": 1.9825166463851929, "learning_rate": 4.7163985239028534e-05, "loss": 4.5715, "step": 2846 }, { "epoch": 0.15319629789065864, "grad_norm": 1.6788777112960815, "learning_rate": 4.716202981698247e-05, "loss": 4.9403, "step": 2847 }, { "epoch": 0.1532501076194576, "grad_norm": 1.7800008058547974, "learning_rate": 4.71600737616052e-05, "loss": 4.6797, "step": 2848 }, { "epoch": 0.15330391734825657, "grad_norm": 1.5913008451461792, "learning_rate": 4.7158117072952615e-05, "loss": 4.6985, "step": 2849 }, { "epoch": 0.15335772707705553, "grad_norm": 1.6751017570495605, "learning_rate": 4.715615975108065e-05, "loss": 4.8282, "step": 2850 }, { "epoch": 0.1534115368058545, "grad_norm": 1.1353965997695923, "learning_rate": 4.7154201796045236e-05, "loss": 4.6709, "step": 2851 }, { "epoch": 0.15346534653465346, "grad_norm": 1.633091926574707, "learning_rate": 4.7152243207902316e-05, "loss": 4.6968, "step": 2852 }, { "epoch": 0.15351915626345244, "grad_norm": 1.77277672290802, "learning_rate": 4.715028398670787e-05, "loss": 4.8587, "step": 2853 }, { "epoch": 0.1535729659922514, "grad_norm": 1.255760669708252, "learning_rate": 4.714832413251789e-05, "loss": 4.804, "step": 2854 }, { "epoch": 0.15362677572105038, "grad_norm": 1.4808834791183472, "learning_rate": 4.714636364538837e-05, "loss": 4.6378, "step": 2855 }, { "epoch": 0.15368058544984933, "grad_norm": 1.719038963317871, "learning_rate": 4.714440252537535e-05, "loss": 4.8408, "step": 2856 }, { "epoch": 0.1537343951786483, "grad_norm": 1.0115710496902466, "learning_rate": 4.714244077253487e-05, "loss": 4.6632, "step": 2857 }, { "epoch": 0.15378820490744727, "grad_norm": 1.6331151723861694, "learning_rate": 4.7140478386922984e-05, "loss": 4.615, "step": 2858 }, { "epoch": 0.15384201463624622, "grad_norm": 1.1642769575119019, "learning_rate": 4.713851536859577e-05, "loss": 4.862, "step": 2859 }, { "epoch": 0.1538958243650452, "grad_norm": 1.3404933214187622, "learning_rate": 4.713655171760934e-05, "loss": 4.6123, "step": 2860 }, { "epoch": 0.15394963409384416, "grad_norm": 1.0336366891860962, "learning_rate": 4.71345874340198e-05, "loss": 4.7814, "step": 2861 }, { "epoch": 0.15400344382264314, "grad_norm": 1.3268930912017822, "learning_rate": 4.7132622517883286e-05, "loss": 4.8459, "step": 2862 }, { "epoch": 0.1540572535514421, "grad_norm": 2.020115852355957, "learning_rate": 4.713065696925595e-05, "loss": 4.7385, "step": 2863 }, { "epoch": 0.15411106328024107, "grad_norm": 1.2914032936096191, "learning_rate": 4.712869078819397e-05, "loss": 4.5715, "step": 2864 }, { "epoch": 0.15416487300904003, "grad_norm": 1.4484955072402954, "learning_rate": 4.7126723974753515e-05, "loss": 5.0075, "step": 2865 }, { "epoch": 0.154218682737839, "grad_norm": 1.4071178436279297, "learning_rate": 4.712475652899081e-05, "loss": 4.7089, "step": 2866 }, { "epoch": 0.15427249246663796, "grad_norm": 1.5529040098190308, "learning_rate": 4.712278845096207e-05, "loss": 4.7283, "step": 2867 }, { "epoch": 0.15432630219543694, "grad_norm": 1.9792243242263794, "learning_rate": 4.7120819740723546e-05, "loss": 4.3954, "step": 2868 }, { "epoch": 0.1543801119242359, "grad_norm": 2.379870653152466, "learning_rate": 4.7118850398331484e-05, "loss": 4.6822, "step": 2869 }, { "epoch": 0.15443392165303488, "grad_norm": 1.6459856033325195, "learning_rate": 4.711688042384217e-05, "loss": 4.7491, "step": 2870 }, { "epoch": 0.15448773138183383, "grad_norm": 1.4592576026916504, "learning_rate": 4.7114909817311906e-05, "loss": 4.6243, "step": 2871 }, { "epoch": 0.1545415411106328, "grad_norm": 1.9518758058547974, "learning_rate": 4.7112938578797e-05, "loss": 4.3259, "step": 2872 }, { "epoch": 0.15459535083943177, "grad_norm": 1.0929532051086426, "learning_rate": 4.7110966708353776e-05, "loss": 4.5547, "step": 2873 }, { "epoch": 0.15464916056823075, "grad_norm": 1.4359737634658813, "learning_rate": 4.7108994206038606e-05, "loss": 4.8295, "step": 2874 }, { "epoch": 0.1547029702970297, "grad_norm": 1.8976640701293945, "learning_rate": 4.7107021071907844e-05, "loss": 4.317, "step": 2875 }, { "epoch": 0.15475678002582868, "grad_norm": 1.132369875907898, "learning_rate": 4.710504730601788e-05, "loss": 4.4747, "step": 2876 }, { "epoch": 0.15481058975462764, "grad_norm": 1.5391196012496948, "learning_rate": 4.710307290842512e-05, "loss": 4.925, "step": 2877 }, { "epoch": 0.1548643994834266, "grad_norm": 1.6209598779678345, "learning_rate": 4.7101097879185986e-05, "loss": 4.9734, "step": 2878 }, { "epoch": 0.15491820921222557, "grad_norm": 1.8283275365829468, "learning_rate": 4.709912221835692e-05, "loss": 4.7092, "step": 2879 }, { "epoch": 0.15497201894102453, "grad_norm": 1.0454550981521606, "learning_rate": 4.7097145925994385e-05, "loss": 4.753, "step": 2880 }, { "epoch": 0.1550258286698235, "grad_norm": 1.4930461645126343, "learning_rate": 4.709516900215485e-05, "loss": 4.4203, "step": 2881 }, { "epoch": 0.15507963839862246, "grad_norm": 1.155119776725769, "learning_rate": 4.7093191446894814e-05, "loss": 4.5846, "step": 2882 }, { "epoch": 0.15513344812742144, "grad_norm": 1.2915256023406982, "learning_rate": 4.709121326027079e-05, "loss": 4.3899, "step": 2883 }, { "epoch": 0.1551872578562204, "grad_norm": 2.1346309185028076, "learning_rate": 4.708923444233932e-05, "loss": 4.3309, "step": 2884 }, { "epoch": 0.15524106758501938, "grad_norm": 1.417412519454956, "learning_rate": 4.7087254993156925e-05, "loss": 4.7372, "step": 2885 }, { "epoch": 0.15529487731381833, "grad_norm": 1.0980846881866455, "learning_rate": 4.70852749127802e-05, "loss": 4.9311, "step": 2886 }, { "epoch": 0.1553486870426173, "grad_norm": 1.2706717252731323, "learning_rate": 4.7083294201265715e-05, "loss": 4.8275, "step": 2887 }, { "epoch": 0.15540249677141627, "grad_norm": 1.4039562940597534, "learning_rate": 4.708131285867009e-05, "loss": 4.6056, "step": 2888 }, { "epoch": 0.15545630650021525, "grad_norm": 1.7548627853393555, "learning_rate": 4.7079330885049924e-05, "loss": 4.9174, "step": 2889 }, { "epoch": 0.1555101162290142, "grad_norm": 1.9619101285934448, "learning_rate": 4.707734828046187e-05, "loss": 4.3862, "step": 2890 }, { "epoch": 0.15556392595781318, "grad_norm": 1.9477616548538208, "learning_rate": 4.707536504496258e-05, "loss": 4.4615, "step": 2891 }, { "epoch": 0.15561773568661214, "grad_norm": 1.7297409772872925, "learning_rate": 4.7073381178608746e-05, "loss": 4.4632, "step": 2892 }, { "epoch": 0.15567154541541112, "grad_norm": 2.153223752975464, "learning_rate": 4.7071396681457034e-05, "loss": 4.048, "step": 2893 }, { "epoch": 0.15572535514421007, "grad_norm": 2.0425140857696533, "learning_rate": 4.706941155356418e-05, "loss": 4.8777, "step": 2894 }, { "epoch": 0.15577916487300905, "grad_norm": 1.6253911256790161, "learning_rate": 4.70674257949869e-05, "loss": 4.4116, "step": 2895 }, { "epoch": 0.155832974601808, "grad_norm": 10.297679901123047, "learning_rate": 4.706543940578194e-05, "loss": 4.6443, "step": 2896 }, { "epoch": 0.155886784330607, "grad_norm": 2.1054458618164062, "learning_rate": 4.7063452386006077e-05, "loss": 4.5285, "step": 2897 }, { "epoch": 0.15594059405940594, "grad_norm": 1.2562555074691772, "learning_rate": 4.7061464735716086e-05, "loss": 4.9346, "step": 2898 }, { "epoch": 0.1559944037882049, "grad_norm": 1.3272675275802612, "learning_rate": 4.705947645496877e-05, "loss": 4.7205, "step": 2899 }, { "epoch": 0.15604821351700388, "grad_norm": 1.070313811302185, "learning_rate": 4.7057487543820955e-05, "loss": 4.6235, "step": 2900 }, { "epoch": 0.15610202324580283, "grad_norm": 1.2992900609970093, "learning_rate": 4.705549800232947e-05, "loss": 4.7687, "step": 2901 }, { "epoch": 0.1561558329746018, "grad_norm": 1.384365200996399, "learning_rate": 4.705350783055117e-05, "loss": 4.731, "step": 2902 }, { "epoch": 0.15620964270340076, "grad_norm": 1.479573130607605, "learning_rate": 4.705151702854294e-05, "loss": 4.6101, "step": 2903 }, { "epoch": 0.15626345243219975, "grad_norm": 1.782503604888916, "learning_rate": 4.7049525596361664e-05, "loss": 4.6725, "step": 2904 }, { "epoch": 0.1563172621609987, "grad_norm": 2.565446615219116, "learning_rate": 4.7047533534064245e-05, "loss": 4.2321, "step": 2905 }, { "epoch": 0.15637107188979768, "grad_norm": 1.6186195611953735, "learning_rate": 4.704554084170763e-05, "loss": 4.3318, "step": 2906 }, { "epoch": 0.15642488161859663, "grad_norm": 1.3102712631225586, "learning_rate": 4.704354751934875e-05, "loss": 4.6816, "step": 2907 }, { "epoch": 0.15647869134739562, "grad_norm": 1.8637202978134155, "learning_rate": 4.704155356704457e-05, "loss": 4.9561, "step": 2908 }, { "epoch": 0.15653250107619457, "grad_norm": 2.018284797668457, "learning_rate": 4.703955898485207e-05, "loss": 4.5973, "step": 2909 }, { "epoch": 0.15658631080499355, "grad_norm": 1.98957097530365, "learning_rate": 4.7037563772828264e-05, "loss": 4.4488, "step": 2910 }, { "epoch": 0.1566401205337925, "grad_norm": 1.4065743684768677, "learning_rate": 4.703556793103015e-05, "loss": 5.1402, "step": 2911 }, { "epoch": 0.15669393026259149, "grad_norm": 1.7464483976364136, "learning_rate": 4.703357145951478e-05, "loss": 4.6664, "step": 2912 }, { "epoch": 0.15674773999139044, "grad_norm": 1.0792545080184937, "learning_rate": 4.7031574358339193e-05, "loss": 4.5019, "step": 2913 }, { "epoch": 0.15680154972018942, "grad_norm": 1.8187850713729858, "learning_rate": 4.702957662756048e-05, "loss": 4.9983, "step": 2914 }, { "epoch": 0.15685535944898837, "grad_norm": 1.7606736421585083, "learning_rate": 4.7027578267235707e-05, "loss": 4.7335, "step": 2915 }, { "epoch": 0.15690916917778736, "grad_norm": 1.3679078817367554, "learning_rate": 4.702557927742201e-05, "loss": 4.5012, "step": 2916 }, { "epoch": 0.1569629789065863, "grad_norm": 1.7776005268096924, "learning_rate": 4.7023579658176486e-05, "loss": 4.5552, "step": 2917 }, { "epoch": 0.1570167886353853, "grad_norm": 1.5590741634368896, "learning_rate": 4.702157940955629e-05, "loss": 4.7235, "step": 2918 }, { "epoch": 0.15707059836418424, "grad_norm": 2.521332025527954, "learning_rate": 4.701957853161859e-05, "loss": 5.191, "step": 2919 }, { "epoch": 0.1571244080929832, "grad_norm": 1.2367639541625977, "learning_rate": 4.701757702442057e-05, "loss": 4.8046, "step": 2920 }, { "epoch": 0.15717821782178218, "grad_norm": 1.3712916374206543, "learning_rate": 4.701557488801941e-05, "loss": 4.6803, "step": 2921 }, { "epoch": 0.15723202755058113, "grad_norm": 1.5655677318572998, "learning_rate": 4.7013572122472335e-05, "loss": 4.3588, "step": 2922 }, { "epoch": 0.15728583727938011, "grad_norm": 1.1831587553024292, "learning_rate": 4.7011568727836575e-05, "loss": 4.8164, "step": 2923 }, { "epoch": 0.15733964700817907, "grad_norm": 1.8171534538269043, "learning_rate": 4.7009564704169395e-05, "loss": 4.9397, "step": 2924 }, { "epoch": 0.15739345673697805, "grad_norm": 2.2908852100372314, "learning_rate": 4.700756005152804e-05, "loss": 4.5454, "step": 2925 }, { "epoch": 0.157447266465777, "grad_norm": 1.0450366735458374, "learning_rate": 4.7005554769969826e-05, "loss": 4.5548, "step": 2926 }, { "epoch": 0.15750107619457598, "grad_norm": 2.1206159591674805, "learning_rate": 4.7003548859552036e-05, "loss": 4.4167, "step": 2927 }, { "epoch": 0.15755488592337494, "grad_norm": 1.2121416330337524, "learning_rate": 4.7001542320332006e-05, "loss": 4.6487, "step": 2928 }, { "epoch": 0.15760869565217392, "grad_norm": 1.3195594549179077, "learning_rate": 4.699953515236708e-05, "loss": 4.8559, "step": 2929 }, { "epoch": 0.15766250538097287, "grad_norm": 1.0416103601455688, "learning_rate": 4.69975273557146e-05, "loss": 4.9354, "step": 2930 }, { "epoch": 0.15771631510977185, "grad_norm": 1.4838035106658936, "learning_rate": 4.699551893043196e-05, "loss": 4.8261, "step": 2931 }, { "epoch": 0.1577701248385708, "grad_norm": 1.349153757095337, "learning_rate": 4.699350987657655e-05, "loss": 4.6563, "step": 2932 }, { "epoch": 0.1578239345673698, "grad_norm": 2.1828856468200684, "learning_rate": 4.699150019420578e-05, "loss": 4.8105, "step": 2933 }, { "epoch": 0.15787774429616874, "grad_norm": 1.1572699546813965, "learning_rate": 4.698948988337709e-05, "loss": 4.573, "step": 2934 }, { "epoch": 0.15793155402496772, "grad_norm": 1.626857042312622, "learning_rate": 4.698747894414792e-05, "loss": 4.8119, "step": 2935 }, { "epoch": 0.15798536375376668, "grad_norm": 1.7702614068984985, "learning_rate": 4.698546737657574e-05, "loss": 4.7622, "step": 2936 }, { "epoch": 0.15803917348256566, "grad_norm": 1.5537840127944946, "learning_rate": 4.698345518071804e-05, "loss": 4.1907, "step": 2937 }, { "epoch": 0.1580929832113646, "grad_norm": 1.0568993091583252, "learning_rate": 4.698144235663232e-05, "loss": 4.818, "step": 2938 }, { "epoch": 0.1581467929401636, "grad_norm": 1.4756442308425903, "learning_rate": 4.69794289043761e-05, "loss": 4.6912, "step": 2939 }, { "epoch": 0.15820060266896255, "grad_norm": 1.6612248420715332, "learning_rate": 4.697741482400691e-05, "loss": 4.7404, "step": 2940 }, { "epoch": 0.15825441239776153, "grad_norm": 1.7969599962234497, "learning_rate": 4.697540011558233e-05, "loss": 4.6145, "step": 2941 }, { "epoch": 0.15830822212656048, "grad_norm": 1.6537944078445435, "learning_rate": 4.6973384779159915e-05, "loss": 4.8276, "step": 2942 }, { "epoch": 0.15836203185535944, "grad_norm": 1.7478207349777222, "learning_rate": 4.697136881479727e-05, "loss": 4.7193, "step": 2943 }, { "epoch": 0.15841584158415842, "grad_norm": 1.016892671585083, "learning_rate": 4.696935222255199e-05, "loss": 4.8363, "step": 2944 }, { "epoch": 0.15846965131295737, "grad_norm": 0.9641923904418945, "learning_rate": 4.696733500248172e-05, "loss": 4.9438, "step": 2945 }, { "epoch": 0.15852346104175635, "grad_norm": 1.6835577487945557, "learning_rate": 4.696531715464411e-05, "loss": 4.6197, "step": 2946 }, { "epoch": 0.1585772707705553, "grad_norm": 1.78199303150177, "learning_rate": 4.69632986790968e-05, "loss": 4.5294, "step": 2947 }, { "epoch": 0.1586310804993543, "grad_norm": 1.0068156719207764, "learning_rate": 4.69612795758975e-05, "loss": 4.7546, "step": 2948 }, { "epoch": 0.15868489022815324, "grad_norm": 1.1052584648132324, "learning_rate": 4.6959259845103885e-05, "loss": 4.8632, "step": 2949 }, { "epoch": 0.15873869995695222, "grad_norm": 1.2763079404830933, "learning_rate": 4.69572394867737e-05, "loss": 4.8647, "step": 2950 }, { "epoch": 0.15879250968575118, "grad_norm": 1.0481951236724854, "learning_rate": 4.6955218500964657e-05, "loss": 4.7841, "step": 2951 }, { "epoch": 0.15884631941455016, "grad_norm": 1.5250362157821655, "learning_rate": 4.695319688773453e-05, "loss": 4.5483, "step": 2952 }, { "epoch": 0.1589001291433491, "grad_norm": 1.3454272747039795, "learning_rate": 4.695117464714108e-05, "loss": 4.8517, "step": 2953 }, { "epoch": 0.1589539388721481, "grad_norm": 1.9239914417266846, "learning_rate": 4.694915177924211e-05, "loss": 4.5302, "step": 2954 }, { "epoch": 0.15900774860094705, "grad_norm": 1.5731667280197144, "learning_rate": 4.694712828409541e-05, "loss": 4.7427, "step": 2955 }, { "epoch": 0.15906155832974603, "grad_norm": 1.5347439050674438, "learning_rate": 4.6945104161758813e-05, "loss": 4.9248, "step": 2956 }, { "epoch": 0.15911536805854498, "grad_norm": 2.2891528606414795, "learning_rate": 4.694307941229017e-05, "loss": 4.4483, "step": 2957 }, { "epoch": 0.15916917778734396, "grad_norm": 1.1745898723602295, "learning_rate": 4.6941054035747336e-05, "loss": 4.3678, "step": 2958 }, { "epoch": 0.15922298751614292, "grad_norm": 1.7940186262130737, "learning_rate": 4.693902803218818e-05, "loss": 4.6618, "step": 2959 }, { "epoch": 0.1592767972449419, "grad_norm": 1.7375885248184204, "learning_rate": 4.6937001401670624e-05, "loss": 4.8905, "step": 2960 }, { "epoch": 0.15933060697374085, "grad_norm": 1.6787550449371338, "learning_rate": 4.693497414425257e-05, "loss": 4.4416, "step": 2961 }, { "epoch": 0.15938441670253983, "grad_norm": 1.4558073282241821, "learning_rate": 4.693294625999195e-05, "loss": 4.8609, "step": 2962 }, { "epoch": 0.1594382264313388, "grad_norm": 2.0926413536071777, "learning_rate": 4.693091774894672e-05, "loss": 4.4996, "step": 2963 }, { "epoch": 0.15949203616013774, "grad_norm": 2.4056522846221924, "learning_rate": 4.692888861117485e-05, "loss": 4.7, "step": 2964 }, { "epoch": 0.15954584588893672, "grad_norm": 0.8636280298233032, "learning_rate": 4.692685884673433e-05, "loss": 4.6407, "step": 2965 }, { "epoch": 0.15959965561773568, "grad_norm": 1.3628575801849365, "learning_rate": 4.692482845568315e-05, "loss": 4.9226, "step": 2966 }, { "epoch": 0.15965346534653466, "grad_norm": 1.3270220756530762, "learning_rate": 4.692279743807935e-05, "loss": 4.3227, "step": 2967 }, { "epoch": 0.1597072750753336, "grad_norm": 1.4347116947174072, "learning_rate": 4.692076579398097e-05, "loss": 4.3188, "step": 2968 }, { "epoch": 0.1597610848041326, "grad_norm": 1.6879262924194336, "learning_rate": 4.691873352344605e-05, "loss": 4.4397, "step": 2969 }, { "epoch": 0.15981489453293155, "grad_norm": 1.871347427368164, "learning_rate": 4.6916700626532684e-05, "loss": 4.4532, "step": 2970 }, { "epoch": 0.15986870426173053, "grad_norm": 1.7080132961273193, "learning_rate": 4.691466710329897e-05, "loss": 4.6061, "step": 2971 }, { "epoch": 0.15992251399052948, "grad_norm": 0.9534225463867188, "learning_rate": 4.691263295380301e-05, "loss": 4.8591, "step": 2972 }, { "epoch": 0.15997632371932846, "grad_norm": 1.1163026094436646, "learning_rate": 4.691059817810294e-05, "loss": 4.3538, "step": 2973 }, { "epoch": 0.16003013344812742, "grad_norm": 1.1079957485198975, "learning_rate": 4.69085627762569e-05, "loss": 4.7499, "step": 2974 }, { "epoch": 0.1600839431769264, "grad_norm": 1.6962354183197021, "learning_rate": 4.690652674832307e-05, "loss": 4.6724, "step": 2975 }, { "epoch": 0.16013775290572535, "grad_norm": 1.12509024143219, "learning_rate": 4.690449009435962e-05, "loss": 4.9524, "step": 2976 }, { "epoch": 0.16019156263452433, "grad_norm": 1.0604057312011719, "learning_rate": 4.690245281442477e-05, "loss": 4.8493, "step": 2977 }, { "epoch": 0.16024537236332329, "grad_norm": 1.1883611679077148, "learning_rate": 4.6900414908576715e-05, "loss": 4.6734, "step": 2978 }, { "epoch": 0.16029918209212227, "grad_norm": 1.1314979791641235, "learning_rate": 4.689837637687372e-05, "loss": 4.8175, "step": 2979 }, { "epoch": 0.16035299182092122, "grad_norm": 1.56361722946167, "learning_rate": 4.689633721937403e-05, "loss": 4.7409, "step": 2980 }, { "epoch": 0.1604068015497202, "grad_norm": 1.557072639465332, "learning_rate": 4.6894297436135904e-05, "loss": 4.9711, "step": 2981 }, { "epoch": 0.16046061127851916, "grad_norm": 1.4117244482040405, "learning_rate": 4.6892257027217656e-05, "loss": 4.5251, "step": 2982 }, { "epoch": 0.16051442100731814, "grad_norm": 1.1968618631362915, "learning_rate": 4.689021599267758e-05, "loss": 4.7769, "step": 2983 }, { "epoch": 0.1605682307361171, "grad_norm": 1.5995759963989258, "learning_rate": 4.688817433257401e-05, "loss": 4.5698, "step": 2984 }, { "epoch": 0.16062204046491604, "grad_norm": 1.3862800598144531, "learning_rate": 4.688613204696529e-05, "loss": 4.5346, "step": 2985 }, { "epoch": 0.16067585019371503, "grad_norm": 1.8938311338424683, "learning_rate": 4.688408913590978e-05, "loss": 4.6774, "step": 2986 }, { "epoch": 0.16072965992251398, "grad_norm": 1.6553878784179688, "learning_rate": 4.688204559946587e-05, "loss": 4.3634, "step": 2987 }, { "epoch": 0.16078346965131296, "grad_norm": 1.4367531538009644, "learning_rate": 4.6880001437691944e-05, "loss": 4.6512, "step": 2988 }, { "epoch": 0.1608372793801119, "grad_norm": 1.5883783102035522, "learning_rate": 4.6877956650646434e-05, "loss": 4.7641, "step": 2989 }, { "epoch": 0.1608910891089109, "grad_norm": 1.154688835144043, "learning_rate": 4.687591123838777e-05, "loss": 4.7552, "step": 2990 }, { "epoch": 0.16094489883770985, "grad_norm": 1.2996002435684204, "learning_rate": 4.687386520097439e-05, "loss": 4.8004, "step": 2991 }, { "epoch": 0.16099870856650883, "grad_norm": 1.432349443435669, "learning_rate": 4.6871818538464784e-05, "loss": 4.6637, "step": 2992 }, { "epoch": 0.16105251829530778, "grad_norm": 1.5390886068344116, "learning_rate": 4.686977125091744e-05, "loss": 4.428, "step": 2993 }, { "epoch": 0.16110632802410677, "grad_norm": 2.1262054443359375, "learning_rate": 4.686772333839084e-05, "loss": 4.2781, "step": 2994 }, { "epoch": 0.16116013775290572, "grad_norm": 1.8238742351531982, "learning_rate": 4.6865674800943536e-05, "loss": 4.694, "step": 2995 }, { "epoch": 0.1612139474817047, "grad_norm": 1.855111002922058, "learning_rate": 4.6863625638634055e-05, "loss": 4.1486, "step": 2996 }, { "epoch": 0.16126775721050365, "grad_norm": 1.5044867992401123, "learning_rate": 4.6861575851520965e-05, "loss": 4.7305, "step": 2997 }, { "epoch": 0.16132156693930264, "grad_norm": 2.8767447471618652, "learning_rate": 4.6859525439662835e-05, "loss": 4.0551, "step": 2998 }, { "epoch": 0.1613753766681016, "grad_norm": 1.7158528566360474, "learning_rate": 4.685747440311826e-05, "loss": 4.1507, "step": 2999 }, { "epoch": 0.16142918639690057, "grad_norm": 1.7816052436828613, "learning_rate": 4.685542274194585e-05, "loss": 4.4561, "step": 3000 }, { "epoch": 0.16148299612569952, "grad_norm": 2.5709831714630127, "learning_rate": 4.685337045620425e-05, "loss": 4.8623, "step": 3001 }, { "epoch": 0.1615368058544985, "grad_norm": 2.3046340942382812, "learning_rate": 4.685131754595211e-05, "loss": 4.4462, "step": 3002 }, { "epoch": 0.16159061558329746, "grad_norm": 1.2960375547409058, "learning_rate": 4.6849264011248076e-05, "loss": 4.7091, "step": 3003 }, { "epoch": 0.16164442531209644, "grad_norm": 1.984968900680542, "learning_rate": 4.684720985215084e-05, "loss": 4.4366, "step": 3004 }, { "epoch": 0.1616982350408954, "grad_norm": 1.8706214427947998, "learning_rate": 4.684515506871911e-05, "loss": 4.5356, "step": 3005 }, { "epoch": 0.16175204476969435, "grad_norm": 1.957334041595459, "learning_rate": 4.684309966101161e-05, "loss": 4.8085, "step": 3006 }, { "epoch": 0.16180585449849333, "grad_norm": 1.5336560010910034, "learning_rate": 4.684104362908708e-05, "loss": 4.4564, "step": 3007 }, { "epoch": 0.16185966422729228, "grad_norm": 2.1019673347473145, "learning_rate": 4.683898697300426e-05, "loss": 4.3657, "step": 3008 }, { "epoch": 0.16191347395609126, "grad_norm": 2.5611729621887207, "learning_rate": 4.683692969282194e-05, "loss": 4.6695, "step": 3009 }, { "epoch": 0.16196728368489022, "grad_norm": 0.8904110193252563, "learning_rate": 4.683487178859889e-05, "loss": 4.754, "step": 3010 }, { "epoch": 0.1620210934136892, "grad_norm": 1.2473548650741577, "learning_rate": 4.683281326039394e-05, "loss": 5.0231, "step": 3011 }, { "epoch": 0.16207490314248815, "grad_norm": 1.6509419679641724, "learning_rate": 4.6830754108265915e-05, "loss": 4.7433, "step": 3012 }, { "epoch": 0.16212871287128713, "grad_norm": 1.5498194694519043, "learning_rate": 4.682869433227365e-05, "loss": 4.6925, "step": 3013 }, { "epoch": 0.1621825226000861, "grad_norm": 2.102527141571045, "learning_rate": 4.6826633932476014e-05, "loss": 4.3049, "step": 3014 }, { "epoch": 0.16223633232888507, "grad_norm": 1.7660958766937256, "learning_rate": 4.682457290893189e-05, "loss": 4.3196, "step": 3015 }, { "epoch": 0.16229014205768402, "grad_norm": 1.8753209114074707, "learning_rate": 4.6822511261700165e-05, "loss": 4.7733, "step": 3016 }, { "epoch": 0.162343951786483, "grad_norm": 1.4212883710861206, "learning_rate": 4.682044899083977e-05, "loss": 4.6156, "step": 3017 }, { "epoch": 0.16239776151528196, "grad_norm": 1.8467323780059814, "learning_rate": 4.6818386096409636e-05, "loss": 5.0236, "step": 3018 }, { "epoch": 0.16245157124408094, "grad_norm": 1.7855486869812012, "learning_rate": 4.6816322578468705e-05, "loss": 4.4261, "step": 3019 }, { "epoch": 0.1625053809728799, "grad_norm": 1.428719401359558, "learning_rate": 4.681425843707596e-05, "loss": 5.1296, "step": 3020 }, { "epoch": 0.16255919070167887, "grad_norm": 2.575284957885742, "learning_rate": 4.6812193672290375e-05, "loss": 4.6721, "step": 3021 }, { "epoch": 0.16261300043047783, "grad_norm": 1.7734861373901367, "learning_rate": 4.6810128284170966e-05, "loss": 4.5491, "step": 3022 }, { "epoch": 0.1626668101592768, "grad_norm": 1.6726399660110474, "learning_rate": 4.6808062272776755e-05, "loss": 4.7447, "step": 3023 }, { "epoch": 0.16272061988807576, "grad_norm": 1.7053760290145874, "learning_rate": 4.680599563816678e-05, "loss": 4.2415, "step": 3024 }, { "epoch": 0.16277442961687474, "grad_norm": 1.125268578529358, "learning_rate": 4.68039283804001e-05, "loss": 4.6474, "step": 3025 }, { "epoch": 0.1628282393456737, "grad_norm": 1.4351043701171875, "learning_rate": 4.68018604995358e-05, "loss": 4.7528, "step": 3026 }, { "epoch": 0.16288204907447265, "grad_norm": 2.1745870113372803, "learning_rate": 4.679979199563296e-05, "loss": 4.5643, "step": 3027 }, { "epoch": 0.16293585880327163, "grad_norm": 1.7332634925842285, "learning_rate": 4.67977228687507e-05, "loss": 4.4219, "step": 3028 }, { "epoch": 0.1629896685320706, "grad_norm": 1.9134000539779663, "learning_rate": 4.679565311894815e-05, "loss": 4.6681, "step": 3029 }, { "epoch": 0.16304347826086957, "grad_norm": 1.386321783065796, "learning_rate": 4.679358274628445e-05, "loss": 4.8152, "step": 3030 }, { "epoch": 0.16309728798966852, "grad_norm": 1.2128101587295532, "learning_rate": 4.6791511750818784e-05, "loss": 5.0147, "step": 3031 }, { "epoch": 0.1631510977184675, "grad_norm": 1.9905909299850464, "learning_rate": 4.678944013261032e-05, "loss": 4.4592, "step": 3032 }, { "epoch": 0.16320490744726646, "grad_norm": 1.621152400970459, "learning_rate": 4.678736789171826e-05, "loss": 4.7475, "step": 3033 }, { "epoch": 0.16325871717606544, "grad_norm": 1.1520789861679077, "learning_rate": 4.6785295028201834e-05, "loss": 4.6401, "step": 3034 }, { "epoch": 0.1633125269048644, "grad_norm": 2.0298895835876465, "learning_rate": 4.678322154212027e-05, "loss": 4.6524, "step": 3035 }, { "epoch": 0.16336633663366337, "grad_norm": 1.4132839441299438, "learning_rate": 4.678114743353282e-05, "loss": 4.8086, "step": 3036 }, { "epoch": 0.16342014636246233, "grad_norm": 1.7598737478256226, "learning_rate": 4.677907270249876e-05, "loss": 4.5182, "step": 3037 }, { "epoch": 0.1634739560912613, "grad_norm": 1.042033314704895, "learning_rate": 4.677699734907739e-05, "loss": 4.6313, "step": 3038 }, { "epoch": 0.16352776582006026, "grad_norm": 1.7399301528930664, "learning_rate": 4.6774921373328e-05, "loss": 5.0023, "step": 3039 }, { "epoch": 0.16358157554885924, "grad_norm": 1.515215277671814, "learning_rate": 4.677284477530993e-05, "loss": 4.6007, "step": 3040 }, { "epoch": 0.1636353852776582, "grad_norm": 1.1274046897888184, "learning_rate": 4.6770767555082516e-05, "loss": 4.5916, "step": 3041 }, { "epoch": 0.16368919500645718, "grad_norm": 1.373416781425476, "learning_rate": 4.6768689712705124e-05, "loss": 4.9294, "step": 3042 }, { "epoch": 0.16374300473525613, "grad_norm": 1.6546850204467773, "learning_rate": 4.6766611248237124e-05, "loss": 4.6347, "step": 3043 }, { "epoch": 0.1637968144640551, "grad_norm": 1.0401420593261719, "learning_rate": 4.676453216173793e-05, "loss": 4.7271, "step": 3044 }, { "epoch": 0.16385062419285407, "grad_norm": 1.643121600151062, "learning_rate": 4.6762452453266934e-05, "loss": 4.4015, "step": 3045 }, { "epoch": 0.16390443392165305, "grad_norm": 2.141517162322998, "learning_rate": 4.676037212288359e-05, "loss": 4.7891, "step": 3046 }, { "epoch": 0.163958243650452, "grad_norm": 2.3151233196258545, "learning_rate": 4.675829117064734e-05, "loss": 4.6627, "step": 3047 }, { "epoch": 0.16401205337925095, "grad_norm": 1.591930627822876, "learning_rate": 4.675620959661765e-05, "loss": 4.8038, "step": 3048 }, { "epoch": 0.16406586310804994, "grad_norm": 1.9639614820480347, "learning_rate": 4.6754127400854006e-05, "loss": 4.5043, "step": 3049 }, { "epoch": 0.1641196728368489, "grad_norm": 1.1940252780914307, "learning_rate": 4.6752044583415914e-05, "loss": 4.7608, "step": 3050 }, { "epoch": 0.16417348256564787, "grad_norm": 1.5700604915618896, "learning_rate": 4.67499611443629e-05, "loss": 4.6752, "step": 3051 }, { "epoch": 0.16422729229444682, "grad_norm": 1.4778891801834106, "learning_rate": 4.674787708375448e-05, "loss": 4.6862, "step": 3052 }, { "epoch": 0.1642811020232458, "grad_norm": 1.1847988367080688, "learning_rate": 4.674579240165024e-05, "loss": 4.6612, "step": 3053 }, { "epoch": 0.16433491175204476, "grad_norm": 1.9562331438064575, "learning_rate": 4.674370709810974e-05, "loss": 4.91, "step": 3054 }, { "epoch": 0.16438872148084374, "grad_norm": 2.044445276260376, "learning_rate": 4.674162117319257e-05, "loss": 4.9219, "step": 3055 }, { "epoch": 0.1644425312096427, "grad_norm": 1.918907880783081, "learning_rate": 4.673953462695836e-05, "loss": 4.7788, "step": 3056 }, { "epoch": 0.16449634093844168, "grad_norm": 1.8142026662826538, "learning_rate": 4.673744745946671e-05, "loss": 4.45, "step": 3057 }, { "epoch": 0.16455015066724063, "grad_norm": 1.9770452976226807, "learning_rate": 4.673535967077728e-05, "loss": 4.0458, "step": 3058 }, { "epoch": 0.1646039603960396, "grad_norm": 1.3116782903671265, "learning_rate": 4.673327126094973e-05, "loss": 4.6226, "step": 3059 }, { "epoch": 0.16465777012483857, "grad_norm": 1.924589991569519, "learning_rate": 4.673118223004375e-05, "loss": 5.0418, "step": 3060 }, { "epoch": 0.16471157985363755, "grad_norm": 1.7852914333343506, "learning_rate": 4.6729092578119025e-05, "loss": 4.16, "step": 3061 }, { "epoch": 0.1647653895824365, "grad_norm": 1.345263123512268, "learning_rate": 4.672700230523528e-05, "loss": 4.5757, "step": 3062 }, { "epoch": 0.16481919931123548, "grad_norm": 1.9467490911483765, "learning_rate": 4.672491141145225e-05, "loss": 4.825, "step": 3063 }, { "epoch": 0.16487300904003444, "grad_norm": 1.7272579669952393, "learning_rate": 4.672281989682969e-05, "loss": 4.8566, "step": 3064 }, { "epoch": 0.16492681876883342, "grad_norm": 1.798261046409607, "learning_rate": 4.6720727761427354e-05, "loss": 4.6635, "step": 3065 }, { "epoch": 0.16498062849763237, "grad_norm": 1.2881790399551392, "learning_rate": 4.671863500530505e-05, "loss": 4.9029, "step": 3066 }, { "epoch": 0.16503443822643135, "grad_norm": 1.693527102470398, "learning_rate": 4.671654162852257e-05, "loss": 4.8306, "step": 3067 }, { "epoch": 0.1650882479552303, "grad_norm": 1.183353066444397, "learning_rate": 4.6714447631139736e-05, "loss": 4.5077, "step": 3068 }, { "epoch": 0.16514205768402926, "grad_norm": 1.7202048301696777, "learning_rate": 4.67123530132164e-05, "loss": 4.7203, "step": 3069 }, { "epoch": 0.16519586741282824, "grad_norm": 1.4148883819580078, "learning_rate": 4.671025777481242e-05, "loss": 4.7313, "step": 3070 }, { "epoch": 0.1652496771416272, "grad_norm": 1.3796848058700562, "learning_rate": 4.6708161915987644e-05, "loss": 4.8201, "step": 3071 }, { "epoch": 0.16530348687042618, "grad_norm": 1.9472618103027344, "learning_rate": 4.670606543680201e-05, "loss": 4.5698, "step": 3072 }, { "epoch": 0.16535729659922513, "grad_norm": 1.3803036212921143, "learning_rate": 4.67039683373154e-05, "loss": 4.8511, "step": 3073 }, { "epoch": 0.1654111063280241, "grad_norm": 1.8057632446289062, "learning_rate": 4.670187061758775e-05, "loss": 5.1118, "step": 3074 }, { "epoch": 0.16546491605682306, "grad_norm": 1.2333414554595947, "learning_rate": 4.669977227767902e-05, "loss": 4.6639, "step": 3075 }, { "epoch": 0.16551872578562205, "grad_norm": 1.2877970933914185, "learning_rate": 4.669767331764916e-05, "loss": 4.6459, "step": 3076 }, { "epoch": 0.165572535514421, "grad_norm": 1.2045025825500488, "learning_rate": 4.669557373755815e-05, "loss": 4.7531, "step": 3077 }, { "epoch": 0.16562634524321998, "grad_norm": 1.1266127824783325, "learning_rate": 4.6693473537465995e-05, "loss": 4.5329, "step": 3078 }, { "epoch": 0.16568015497201893, "grad_norm": 1.3347394466400146, "learning_rate": 4.669137271743273e-05, "loss": 4.4795, "step": 3079 }, { "epoch": 0.16573396470081792, "grad_norm": 1.6321712732315063, "learning_rate": 4.668927127751835e-05, "loss": 4.6581, "step": 3080 }, { "epoch": 0.16578777442961687, "grad_norm": 1.3997788429260254, "learning_rate": 4.6687169217782956e-05, "loss": 4.8428, "step": 3081 }, { "epoch": 0.16584158415841585, "grad_norm": 1.4884536266326904, "learning_rate": 4.668506653828659e-05, "loss": 4.653, "step": 3082 }, { "epoch": 0.1658953938872148, "grad_norm": 1.0434980392456055, "learning_rate": 4.668296323908935e-05, "loss": 4.8366, "step": 3083 }, { "epoch": 0.16594920361601379, "grad_norm": 2.485868453979492, "learning_rate": 4.6680859320251336e-05, "loss": 4.5787, "step": 3084 }, { "epoch": 0.16600301334481274, "grad_norm": 1.2060151100158691, "learning_rate": 4.667875478183268e-05, "loss": 5.07, "step": 3085 }, { "epoch": 0.16605682307361172, "grad_norm": 2.0328235626220703, "learning_rate": 4.667664962389353e-05, "loss": 4.8744, "step": 3086 }, { "epoch": 0.16611063280241067, "grad_norm": 1.8033840656280518, "learning_rate": 4.6674543846494024e-05, "loss": 4.5998, "step": 3087 }, { "epoch": 0.16616444253120966, "grad_norm": 1.672668695449829, "learning_rate": 4.6672437449694364e-05, "loss": 4.922, "step": 3088 }, { "epoch": 0.1662182522600086, "grad_norm": 1.8443360328674316, "learning_rate": 4.6670330433554724e-05, "loss": 4.3756, "step": 3089 }, { "epoch": 0.1662720619888076, "grad_norm": 1.3474010229110718, "learning_rate": 4.666822279813533e-05, "loss": 5.0517, "step": 3090 }, { "epoch": 0.16632587171760654, "grad_norm": 0.993014395236969, "learning_rate": 4.666611454349641e-05, "loss": 4.618, "step": 3091 }, { "epoch": 0.1663796814464055, "grad_norm": 1.3630727529525757, "learning_rate": 4.666400566969821e-05, "loss": 5.0222, "step": 3092 }, { "epoch": 0.16643349117520448, "grad_norm": 1.3932143449783325, "learning_rate": 4.6661896176801e-05, "loss": 5.0498, "step": 3093 }, { "epoch": 0.16648730090400343, "grad_norm": 0.9046881198883057, "learning_rate": 4.6659786064865056e-05, "loss": 5.1002, "step": 3094 }, { "epoch": 0.1665411106328024, "grad_norm": 0.9993139505386353, "learning_rate": 4.665767533395069e-05, "loss": 4.6886, "step": 3095 }, { "epoch": 0.16659492036160137, "grad_norm": 0.9827600717544556, "learning_rate": 4.665556398411821e-05, "loss": 4.5563, "step": 3096 }, { "epoch": 0.16664873009040035, "grad_norm": 2.348259449005127, "learning_rate": 4.6653452015427965e-05, "loss": 4.594, "step": 3097 }, { "epoch": 0.1667025398191993, "grad_norm": 2.2149405479431152, "learning_rate": 4.6651339427940295e-05, "loss": 4.2787, "step": 3098 }, { "epoch": 0.16675634954799828, "grad_norm": 1.3414690494537354, "learning_rate": 4.664922622171558e-05, "loss": 4.8085, "step": 3099 }, { "epoch": 0.16681015927679724, "grad_norm": 1.5698933601379395, "learning_rate": 4.6647112396814216e-05, "loss": 4.9124, "step": 3100 }, { "epoch": 0.16686396900559622, "grad_norm": 2.3894906044006348, "learning_rate": 4.66449979532966e-05, "loss": 4.3437, "step": 3101 }, { "epoch": 0.16691777873439517, "grad_norm": 1.5031975507736206, "learning_rate": 4.6642882891223155e-05, "loss": 4.4365, "step": 3102 }, { "epoch": 0.16697158846319415, "grad_norm": 1.3495010137557983, "learning_rate": 4.6640767210654335e-05, "loss": 4.5335, "step": 3103 }, { "epoch": 0.1670253981919931, "grad_norm": 1.7208244800567627, "learning_rate": 4.663865091165059e-05, "loss": 4.8265, "step": 3104 }, { "epoch": 0.1670792079207921, "grad_norm": 1.5733133554458618, "learning_rate": 4.663653399427241e-05, "loss": 4.6211, "step": 3105 }, { "epoch": 0.16713301764959104, "grad_norm": 1.4891972541809082, "learning_rate": 4.663441645858028e-05, "loss": 4.9644, "step": 3106 }, { "epoch": 0.16718682737839002, "grad_norm": 1.6142255067825317, "learning_rate": 4.663229830463473e-05, "loss": 4.9471, "step": 3107 }, { "epoch": 0.16724063710718898, "grad_norm": 1.1823334693908691, "learning_rate": 4.6630179532496257e-05, "loss": 4.7602, "step": 3108 }, { "epoch": 0.16729444683598796, "grad_norm": 1.2165054082870483, "learning_rate": 4.6628060142225437e-05, "loss": 4.535, "step": 3109 }, { "epoch": 0.1673482565647869, "grad_norm": 1.513619303703308, "learning_rate": 4.662594013388284e-05, "loss": 4.6915, "step": 3110 }, { "epoch": 0.1674020662935859, "grad_norm": 0.8442388772964478, "learning_rate": 4.6623819507529034e-05, "loss": 4.4384, "step": 3111 }, { "epoch": 0.16745587602238485, "grad_norm": 1.6529861688613892, "learning_rate": 4.662169826322463e-05, "loss": 4.826, "step": 3112 }, { "epoch": 0.1675096857511838, "grad_norm": 1.4539238214492798, "learning_rate": 4.661957640103025e-05, "loss": 4.8349, "step": 3113 }, { "epoch": 0.16756349547998278, "grad_norm": 1.5496479272842407, "learning_rate": 4.661745392100651e-05, "loss": 4.6891, "step": 3114 }, { "epoch": 0.16761730520878174, "grad_norm": 1.1079294681549072, "learning_rate": 4.66153308232141e-05, "loss": 4.6518, "step": 3115 }, { "epoch": 0.16767111493758072, "grad_norm": 1.4818809032440186, "learning_rate": 4.6613207107713665e-05, "loss": 4.9052, "step": 3116 }, { "epoch": 0.16772492466637967, "grad_norm": 2.2036869525909424, "learning_rate": 4.6611082774565907e-05, "loss": 4.6728, "step": 3117 }, { "epoch": 0.16777873439517865, "grad_norm": 1.4818637371063232, "learning_rate": 4.6608957823831525e-05, "loss": 4.8575, "step": 3118 }, { "epoch": 0.1678325441239776, "grad_norm": 1.8324735164642334, "learning_rate": 4.6606832255571256e-05, "loss": 4.8874, "step": 3119 }, { "epoch": 0.1678863538527766, "grad_norm": 1.5938262939453125, "learning_rate": 4.660470606984583e-05, "loss": 4.3931, "step": 3120 }, { "epoch": 0.16794016358157554, "grad_norm": 2.1192243099212646, "learning_rate": 4.660257926671602e-05, "loss": 4.501, "step": 3121 }, { "epoch": 0.16799397331037452, "grad_norm": 1.1224507093429565, "learning_rate": 4.660045184624259e-05, "loss": 4.4603, "step": 3122 }, { "epoch": 0.16804778303917348, "grad_norm": 0.9294309616088867, "learning_rate": 4.6598323808486355e-05, "loss": 4.8738, "step": 3123 }, { "epoch": 0.16810159276797246, "grad_norm": 1.130436658859253, "learning_rate": 4.659619515350811e-05, "loss": 4.4595, "step": 3124 }, { "epoch": 0.1681554024967714, "grad_norm": 2.087029218673706, "learning_rate": 4.65940658813687e-05, "loss": 4.4839, "step": 3125 }, { "epoch": 0.1682092122255704, "grad_norm": 1.9587984085083008, "learning_rate": 4.6591935992128965e-05, "loss": 4.7723, "step": 3126 }, { "epoch": 0.16826302195436935, "grad_norm": 1.9733492136001587, "learning_rate": 4.6589805485849783e-05, "loss": 4.5824, "step": 3127 }, { "epoch": 0.16831683168316833, "grad_norm": 1.4677397012710571, "learning_rate": 4.658767436259202e-05, "loss": 4.6443, "step": 3128 }, { "epoch": 0.16837064141196728, "grad_norm": 2.0895073413848877, "learning_rate": 4.658554262241659e-05, "loss": 4.6664, "step": 3129 }, { "epoch": 0.16842445114076626, "grad_norm": 1.3496729135513306, "learning_rate": 4.658341026538441e-05, "loss": 4.7961, "step": 3130 }, { "epoch": 0.16847826086956522, "grad_norm": 1.5841747522354126, "learning_rate": 4.6581277291556416e-05, "loss": 5.0273, "step": 3131 }, { "epoch": 0.1685320705983642, "grad_norm": 0.9375933408737183, "learning_rate": 4.657914370099357e-05, "loss": 4.7933, "step": 3132 }, { "epoch": 0.16858588032716315, "grad_norm": 1.9655364751815796, "learning_rate": 4.657700949375683e-05, "loss": 4.8284, "step": 3133 }, { "epoch": 0.1686396900559621, "grad_norm": 1.8737257719039917, "learning_rate": 4.657487466990721e-05, "loss": 4.582, "step": 3134 }, { "epoch": 0.1686934997847611, "grad_norm": 1.0291532278060913, "learning_rate": 4.657273922950568e-05, "loss": 4.6903, "step": 3135 }, { "epoch": 0.16874730951356004, "grad_norm": 1.4676969051361084, "learning_rate": 4.6570603172613306e-05, "loss": 4.7448, "step": 3136 }, { "epoch": 0.16880111924235902, "grad_norm": 1.9646011590957642, "learning_rate": 4.65684664992911e-05, "loss": 4.2295, "step": 3137 }, { "epoch": 0.16885492897115797, "grad_norm": 1.2478913068771362, "learning_rate": 4.6566329209600133e-05, "loss": 4.6885, "step": 3138 }, { "epoch": 0.16890873869995696, "grad_norm": 1.9817442893981934, "learning_rate": 4.656419130360148e-05, "loss": 4.7967, "step": 3139 }, { "epoch": 0.1689625484287559, "grad_norm": 1.658109188079834, "learning_rate": 4.656205278135625e-05, "loss": 4.6713, "step": 3140 }, { "epoch": 0.1690163581575549, "grad_norm": 1.3782031536102295, "learning_rate": 4.655991364292554e-05, "loss": 4.7347, "step": 3141 }, { "epoch": 0.16907016788635384, "grad_norm": 1.6531225442886353, "learning_rate": 4.6557773888370496e-05, "loss": 4.6563, "step": 3142 }, { "epoch": 0.16912397761515283, "grad_norm": 1.7921284437179565, "learning_rate": 4.655563351775225e-05, "loss": 4.6646, "step": 3143 }, { "epoch": 0.16917778734395178, "grad_norm": 1.2553784847259521, "learning_rate": 4.655349253113198e-05, "loss": 4.7183, "step": 3144 }, { "epoch": 0.16923159707275076, "grad_norm": 1.288159966468811, "learning_rate": 4.655135092857087e-05, "loss": 5.0415, "step": 3145 }, { "epoch": 0.16928540680154971, "grad_norm": 1.5734378099441528, "learning_rate": 4.654920871013011e-05, "loss": 4.794, "step": 3146 }, { "epoch": 0.1693392165303487, "grad_norm": 1.946841835975647, "learning_rate": 4.654706587587093e-05, "loss": 4.6116, "step": 3147 }, { "epoch": 0.16939302625914765, "grad_norm": 1.736824631690979, "learning_rate": 4.654492242585455e-05, "loss": 4.849, "step": 3148 }, { "epoch": 0.16944683598794663, "grad_norm": 1.5636944770812988, "learning_rate": 4.6542778360142245e-05, "loss": 4.7231, "step": 3149 }, { "epoch": 0.16950064571674558, "grad_norm": 1.146799087524414, "learning_rate": 4.654063367879528e-05, "loss": 4.4553, "step": 3150 }, { "epoch": 0.16955445544554457, "grad_norm": 1.6110029220581055, "learning_rate": 4.653848838187495e-05, "loss": 4.9299, "step": 3151 }, { "epoch": 0.16960826517434352, "grad_norm": 1.3100578784942627, "learning_rate": 4.653634246944254e-05, "loss": 4.6374, "step": 3152 }, { "epoch": 0.1696620749031425, "grad_norm": 2.4580330848693848, "learning_rate": 4.653419594155939e-05, "loss": 4.4678, "step": 3153 }, { "epoch": 0.16971588463194145, "grad_norm": 1.3766412734985352, "learning_rate": 4.6532048798286844e-05, "loss": 4.6368, "step": 3154 }, { "epoch": 0.1697696943607404, "grad_norm": 2.0055010318756104, "learning_rate": 4.652990103968625e-05, "loss": 4.8773, "step": 3155 }, { "epoch": 0.1698235040895394, "grad_norm": 1.3356921672821045, "learning_rate": 4.6527752665819004e-05, "loss": 4.833, "step": 3156 }, { "epoch": 0.16987731381833834, "grad_norm": 1.8036741018295288, "learning_rate": 4.6525603676746476e-05, "loss": 4.2605, "step": 3157 }, { "epoch": 0.16993112354713732, "grad_norm": 2.0129880905151367, "learning_rate": 4.652345407253011e-05, "loss": 4.8935, "step": 3158 }, { "epoch": 0.16998493327593628, "grad_norm": 1.3779977560043335, "learning_rate": 4.6521303853231303e-05, "loss": 4.663, "step": 3159 }, { "epoch": 0.17003874300473526, "grad_norm": 2.0159149169921875, "learning_rate": 4.651915301891152e-05, "loss": 4.5021, "step": 3160 }, { "epoch": 0.1700925527335342, "grad_norm": 1.9791651964187622, "learning_rate": 4.651700156963222e-05, "loss": 4.9074, "step": 3161 }, { "epoch": 0.1701463624623332, "grad_norm": 1.8608449697494507, "learning_rate": 4.65148495054549e-05, "loss": 4.6044, "step": 3162 }, { "epoch": 0.17020017219113215, "grad_norm": 1.712713599205017, "learning_rate": 4.651269682644105e-05, "loss": 4.3955, "step": 3163 }, { "epoch": 0.17025398191993113, "grad_norm": 1.3504968881607056, "learning_rate": 4.651054353265218e-05, "loss": 4.8604, "step": 3164 }, { "epoch": 0.17030779164873008, "grad_norm": 1.802767276763916, "learning_rate": 4.650838962414983e-05, "loss": 4.9408, "step": 3165 }, { "epoch": 0.17036160137752906, "grad_norm": 1.2514009475708008, "learning_rate": 4.650623510099556e-05, "loss": 4.7931, "step": 3166 }, { "epoch": 0.17041541110632802, "grad_norm": 1.0332204103469849, "learning_rate": 4.650407996325093e-05, "loss": 4.9988, "step": 3167 }, { "epoch": 0.170469220835127, "grad_norm": 1.3504730463027954, "learning_rate": 4.6501924210977545e-05, "loss": 4.5214, "step": 3168 }, { "epoch": 0.17052303056392595, "grad_norm": 1.0740182399749756, "learning_rate": 4.6499767844236994e-05, "loss": 4.8393, "step": 3169 }, { "epoch": 0.17057684029272493, "grad_norm": 1.2808996438980103, "learning_rate": 4.6497610863090904e-05, "loss": 4.6423, "step": 3170 }, { "epoch": 0.1706306500215239, "grad_norm": 1.21689772605896, "learning_rate": 4.649545326760092e-05, "loss": 4.4645, "step": 3171 }, { "epoch": 0.17068445975032287, "grad_norm": 1.9258708953857422, "learning_rate": 4.649329505782869e-05, "loss": 4.4579, "step": 3172 }, { "epoch": 0.17073826947912182, "grad_norm": 0.971233606338501, "learning_rate": 4.649113623383591e-05, "loss": 4.5942, "step": 3173 }, { "epoch": 0.1707920792079208, "grad_norm": 1.338233232498169, "learning_rate": 4.648897679568425e-05, "loss": 4.6818, "step": 3174 }, { "epoch": 0.17084588893671976, "grad_norm": 1.8487313985824585, "learning_rate": 4.648681674343544e-05, "loss": 4.7544, "step": 3175 }, { "epoch": 0.1708996986655187, "grad_norm": 2.27838134765625, "learning_rate": 4.648465607715119e-05, "loss": 4.3932, "step": 3176 }, { "epoch": 0.1709535083943177, "grad_norm": 1.7403706312179565, "learning_rate": 4.6482494796893263e-05, "loss": 4.1479, "step": 3177 }, { "epoch": 0.17100731812311665, "grad_norm": 0.9431449770927429, "learning_rate": 4.648033290272341e-05, "loss": 4.7403, "step": 3178 }, { "epoch": 0.17106112785191563, "grad_norm": 1.5277659893035889, "learning_rate": 4.6478170394703424e-05, "loss": 5.0928, "step": 3179 }, { "epoch": 0.17111493758071458, "grad_norm": 1.574716567993164, "learning_rate": 4.6476007272895096e-05, "loss": 4.8814, "step": 3180 }, { "epoch": 0.17116874730951356, "grad_norm": 0.9830374121665955, "learning_rate": 4.647384353736025e-05, "loss": 4.9711, "step": 3181 }, { "epoch": 0.17122255703831252, "grad_norm": 1.6527864933013916, "learning_rate": 4.6471679188160705e-05, "loss": 4.4557, "step": 3182 }, { "epoch": 0.1712763667671115, "grad_norm": 0.9584505558013916, "learning_rate": 4.6469514225358324e-05, "loss": 4.6775, "step": 3183 }, { "epoch": 0.17133017649591045, "grad_norm": 1.1544852256774902, "learning_rate": 4.6467348649014973e-05, "loss": 4.451, "step": 3184 }, { "epoch": 0.17138398622470943, "grad_norm": 1.5221980810165405, "learning_rate": 4.6465182459192533e-05, "loss": 5.0057, "step": 3185 }, { "epoch": 0.1714377959535084, "grad_norm": 1.282132625579834, "learning_rate": 4.6463015655952926e-05, "loss": 4.6716, "step": 3186 }, { "epoch": 0.17149160568230737, "grad_norm": 1.107941746711731, "learning_rate": 4.6460848239358045e-05, "loss": 4.9934, "step": 3187 }, { "epoch": 0.17154541541110632, "grad_norm": 2.110388994216919, "learning_rate": 4.6458680209469853e-05, "loss": 4.7132, "step": 3188 }, { "epoch": 0.1715992251399053, "grad_norm": 1.8808895349502563, "learning_rate": 4.645651156635029e-05, "loss": 4.5129, "step": 3189 }, { "epoch": 0.17165303486870426, "grad_norm": 1.8242541551589966, "learning_rate": 4.645434231006135e-05, "loss": 4.5581, "step": 3190 }, { "epoch": 0.17170684459750324, "grad_norm": 1.7956111431121826, "learning_rate": 4.645217244066501e-05, "loss": 4.5791, "step": 3191 }, { "epoch": 0.1717606543263022, "grad_norm": 1.4280086755752563, "learning_rate": 4.645000195822327e-05, "loss": 4.6449, "step": 3192 }, { "epoch": 0.17181446405510117, "grad_norm": 1.3924130201339722, "learning_rate": 4.644783086279817e-05, "loss": 4.4174, "step": 3193 }, { "epoch": 0.17186827378390013, "grad_norm": 1.4705514907836914, "learning_rate": 4.644565915445176e-05, "loss": 4.5792, "step": 3194 }, { "epoch": 0.1719220835126991, "grad_norm": 1.0699132680892944, "learning_rate": 4.644348683324609e-05, "loss": 4.7883, "step": 3195 }, { "epoch": 0.17197589324149806, "grad_norm": 1.7279704809188843, "learning_rate": 4.644131389924324e-05, "loss": 4.7272, "step": 3196 }, { "epoch": 0.17202970297029702, "grad_norm": 1.2861649990081787, "learning_rate": 4.6439140352505314e-05, "loss": 5.0562, "step": 3197 }, { "epoch": 0.172083512699096, "grad_norm": 2.312875986099243, "learning_rate": 4.643696619309442e-05, "loss": 4.531, "step": 3198 }, { "epoch": 0.17213732242789495, "grad_norm": 1.6576933860778809, "learning_rate": 4.643479142107269e-05, "loss": 4.5722, "step": 3199 }, { "epoch": 0.17219113215669393, "grad_norm": 1.1829952001571655, "learning_rate": 4.643261603650227e-05, "loss": 4.7363, "step": 3200 }, { "epoch": 0.17224494188549289, "grad_norm": 1.4425276517868042, "learning_rate": 4.643044003944533e-05, "loss": 4.6242, "step": 3201 }, { "epoch": 0.17229875161429187, "grad_norm": 1.4290448427200317, "learning_rate": 4.642826342996406e-05, "loss": 4.3667, "step": 3202 }, { "epoch": 0.17235256134309082, "grad_norm": 1.0953325033187866, "learning_rate": 4.642608620812066e-05, "loss": 4.7987, "step": 3203 }, { "epoch": 0.1724063710718898, "grad_norm": 1.301328420639038, "learning_rate": 4.6423908373977335e-05, "loss": 4.6842, "step": 3204 }, { "epoch": 0.17246018080068876, "grad_norm": 1.8158786296844482, "learning_rate": 4.6421729927596334e-05, "loss": 4.5898, "step": 3205 }, { "epoch": 0.17251399052948774, "grad_norm": 1.6150315999984741, "learning_rate": 4.6419550869039915e-05, "loss": 4.759, "step": 3206 }, { "epoch": 0.1725678002582867, "grad_norm": 0.9885669350624084, "learning_rate": 4.641737119837034e-05, "loss": 4.8652, "step": 3207 }, { "epoch": 0.17262160998708567, "grad_norm": 1.6190292835235596, "learning_rate": 4.641519091564991e-05, "loss": 4.7107, "step": 3208 }, { "epoch": 0.17267541971588463, "grad_norm": 1.1856406927108765, "learning_rate": 4.6413010020940916e-05, "loss": 4.5079, "step": 3209 }, { "epoch": 0.1727292294446836, "grad_norm": 1.58607816696167, "learning_rate": 4.6410828514305696e-05, "loss": 4.5968, "step": 3210 }, { "epoch": 0.17278303917348256, "grad_norm": 1.73410165309906, "learning_rate": 4.640864639580658e-05, "loss": 4.6091, "step": 3211 }, { "epoch": 0.17283684890228154, "grad_norm": 1.0383270978927612, "learning_rate": 4.640646366550593e-05, "loss": 4.6066, "step": 3212 }, { "epoch": 0.1728906586310805, "grad_norm": 1.4117090702056885, "learning_rate": 4.640428032346613e-05, "loss": 4.9001, "step": 3213 }, { "epoch": 0.17294446835987948, "grad_norm": 1.5754671096801758, "learning_rate": 4.640209636974957e-05, "loss": 4.6478, "step": 3214 }, { "epoch": 0.17299827808867843, "grad_norm": 2.1582977771759033, "learning_rate": 4.639991180441866e-05, "loss": 4.5496, "step": 3215 }, { "epoch": 0.1730520878174774, "grad_norm": 1.3817002773284912, "learning_rate": 4.639772662753583e-05, "loss": 4.7531, "step": 3216 }, { "epoch": 0.17310589754627637, "grad_norm": 1.5668425559997559, "learning_rate": 4.639554083916352e-05, "loss": 4.5974, "step": 3217 }, { "epoch": 0.17315970727507535, "grad_norm": 1.0586886405944824, "learning_rate": 4.63933544393642e-05, "loss": 4.6787, "step": 3218 }, { "epoch": 0.1732135170038743, "grad_norm": 1.7661415338516235, "learning_rate": 4.6391167428200356e-05, "loss": 4.6198, "step": 3219 }, { "epoch": 0.17326732673267325, "grad_norm": 1.1611295938491821, "learning_rate": 4.638897980573449e-05, "loss": 4.6977, "step": 3220 }, { "epoch": 0.17332113646147224, "grad_norm": 1.2642542123794556, "learning_rate": 4.63867915720291e-05, "loss": 4.7593, "step": 3221 }, { "epoch": 0.1733749461902712, "grad_norm": 1.23446786403656, "learning_rate": 4.638460272714673e-05, "loss": 4.8152, "step": 3222 }, { "epoch": 0.17342875591907017, "grad_norm": 1.505529522895813, "learning_rate": 4.638241327114994e-05, "loss": 4.6357, "step": 3223 }, { "epoch": 0.17348256564786912, "grad_norm": 1.3632137775421143, "learning_rate": 4.638022320410128e-05, "loss": 4.7938, "step": 3224 }, { "epoch": 0.1735363753766681, "grad_norm": 1.1669962406158447, "learning_rate": 4.6378032526063354e-05, "loss": 4.767, "step": 3225 }, { "epoch": 0.17359018510546706, "grad_norm": 1.5817440748214722, "learning_rate": 4.637584123709876e-05, "loss": 4.7275, "step": 3226 }, { "epoch": 0.17364399483426604, "grad_norm": 1.502084732055664, "learning_rate": 4.637364933727012e-05, "loss": 4.8029, "step": 3227 }, { "epoch": 0.173697804563065, "grad_norm": 1.2394620180130005, "learning_rate": 4.637145682664006e-05, "loss": 4.7651, "step": 3228 }, { "epoch": 0.17375161429186398, "grad_norm": 1.2799937725067139, "learning_rate": 4.636926370527125e-05, "loss": 4.6827, "step": 3229 }, { "epoch": 0.17380542402066293, "grad_norm": 1.422295331954956, "learning_rate": 4.636706997322636e-05, "loss": 4.7888, "step": 3230 }, { "epoch": 0.1738592337494619, "grad_norm": 1.116562008857727, "learning_rate": 4.6364875630568086e-05, "loss": 4.7277, "step": 3231 }, { "epoch": 0.17391304347826086, "grad_norm": 1.3975363969802856, "learning_rate": 4.636268067735913e-05, "loss": 4.9384, "step": 3232 }, { "epoch": 0.17396685320705985, "grad_norm": 1.086309790611267, "learning_rate": 4.6360485113662216e-05, "loss": 4.8143, "step": 3233 }, { "epoch": 0.1740206629358588, "grad_norm": 1.176013469696045, "learning_rate": 4.635828893954009e-05, "loss": 4.6361, "step": 3234 }, { "epoch": 0.17407447266465778, "grad_norm": 1.4281312227249146, "learning_rate": 4.635609215505552e-05, "loss": 4.6688, "step": 3235 }, { "epoch": 0.17412828239345673, "grad_norm": 2.040745973587036, "learning_rate": 4.635389476027127e-05, "loss": 4.2216, "step": 3236 }, { "epoch": 0.17418209212225572, "grad_norm": 1.2430273294448853, "learning_rate": 4.635169675525014e-05, "loss": 4.8822, "step": 3237 }, { "epoch": 0.17423590185105467, "grad_norm": 0.9996951222419739, "learning_rate": 4.6349498140054955e-05, "loss": 4.8366, "step": 3238 }, { "epoch": 0.17428971157985365, "grad_norm": 1.7243770360946655, "learning_rate": 4.6347298914748526e-05, "loss": 5.1743, "step": 3239 }, { "epoch": 0.1743435213086526, "grad_norm": 1.1793845891952515, "learning_rate": 4.634509907939372e-05, "loss": 4.5295, "step": 3240 }, { "epoch": 0.17439733103745156, "grad_norm": 1.9621249437332153, "learning_rate": 4.634289863405339e-05, "loss": 4.482, "step": 3241 }, { "epoch": 0.17445114076625054, "grad_norm": 0.9127615094184875, "learning_rate": 4.634069757879043e-05, "loss": 4.8245, "step": 3242 }, { "epoch": 0.1745049504950495, "grad_norm": 1.8407210111618042, "learning_rate": 4.6338495913667725e-05, "loss": 4.6194, "step": 3243 }, { "epoch": 0.17455876022384847, "grad_norm": 1.0538259744644165, "learning_rate": 4.633629363874821e-05, "loss": 4.6946, "step": 3244 }, { "epoch": 0.17461256995264743, "grad_norm": 1.4969488382339478, "learning_rate": 4.63340907540948e-05, "loss": 4.6078, "step": 3245 }, { "epoch": 0.1746663796814464, "grad_norm": 1.1555249691009521, "learning_rate": 4.6331887259770464e-05, "loss": 4.8825, "step": 3246 }, { "epoch": 0.17472018941024536, "grad_norm": 1.5350104570388794, "learning_rate": 4.632968315583816e-05, "loss": 4.8705, "step": 3247 }, { "epoch": 0.17477399913904434, "grad_norm": 2.0614640712738037, "learning_rate": 4.632747844236088e-05, "loss": 4.8298, "step": 3248 }, { "epoch": 0.1748278088678433, "grad_norm": 1.483670711517334, "learning_rate": 4.632527311940165e-05, "loss": 4.9529, "step": 3249 }, { "epoch": 0.17488161859664228, "grad_norm": 1.218253254890442, "learning_rate": 4.632306718702345e-05, "loss": 4.8538, "step": 3250 }, { "epoch": 0.17493542832544123, "grad_norm": 1.8147822618484497, "learning_rate": 4.632086064528935e-05, "loss": 4.2772, "step": 3251 }, { "epoch": 0.17498923805424021, "grad_norm": 1.3959335088729858, "learning_rate": 4.63186534942624e-05, "loss": 4.8463, "step": 3252 }, { "epoch": 0.17504304778303917, "grad_norm": 1.7328970432281494, "learning_rate": 4.6316445734005676e-05, "loss": 4.545, "step": 3253 }, { "epoch": 0.17509685751183815, "grad_norm": 2.3177361488342285, "learning_rate": 4.6314237364582265e-05, "loss": 3.9695, "step": 3254 }, { "epoch": 0.1751506672406371, "grad_norm": 1.6595300436019897, "learning_rate": 4.631202838605527e-05, "loss": 4.5541, "step": 3255 }, { "epoch": 0.17520447696943608, "grad_norm": 1.359728217124939, "learning_rate": 4.630981879848784e-05, "loss": 4.6977, "step": 3256 }, { "epoch": 0.17525828669823504, "grad_norm": 1.5292755365371704, "learning_rate": 4.63076086019431e-05, "loss": 4.7325, "step": 3257 }, { "epoch": 0.17531209642703402, "grad_norm": 1.3763514757156372, "learning_rate": 4.630539779648422e-05, "loss": 4.9495, "step": 3258 }, { "epoch": 0.17536590615583297, "grad_norm": 1.188592791557312, "learning_rate": 4.630318638217437e-05, "loss": 4.6973, "step": 3259 }, { "epoch": 0.17541971588463195, "grad_norm": 1.1681886911392212, "learning_rate": 4.630097435907675e-05, "loss": 4.5686, "step": 3260 }, { "epoch": 0.1754735256134309, "grad_norm": 1.5921472311019897, "learning_rate": 4.6298761727254585e-05, "loss": 4.5915, "step": 3261 }, { "epoch": 0.17552733534222986, "grad_norm": 1.2831600904464722, "learning_rate": 4.6296548486771096e-05, "loss": 4.7874, "step": 3262 }, { "epoch": 0.17558114507102884, "grad_norm": 1.639295220375061, "learning_rate": 4.629433463768953e-05, "loss": 4.6239, "step": 3263 }, { "epoch": 0.1756349547998278, "grad_norm": 1.3208742141723633, "learning_rate": 4.629212018007315e-05, "loss": 4.9111, "step": 3264 }, { "epoch": 0.17568876452862678, "grad_norm": 1.2736356258392334, "learning_rate": 4.628990511398525e-05, "loss": 4.7775, "step": 3265 }, { "epoch": 0.17574257425742573, "grad_norm": 1.5042176246643066, "learning_rate": 4.628768943948913e-05, "loss": 4.7971, "step": 3266 }, { "epoch": 0.1757963839862247, "grad_norm": 2.0657570362091064, "learning_rate": 4.628547315664809e-05, "loss": 4.42, "step": 3267 }, { "epoch": 0.17585019371502367, "grad_norm": 1.3700178861618042, "learning_rate": 4.628325626552548e-05, "loss": 4.4839, "step": 3268 }, { "epoch": 0.17590400344382265, "grad_norm": 2.383899211883545, "learning_rate": 4.628103876618466e-05, "loss": 4.0425, "step": 3269 }, { "epoch": 0.1759578131726216, "grad_norm": 1.1918007135391235, "learning_rate": 4.627882065868898e-05, "loss": 4.9386, "step": 3270 }, { "epoch": 0.17601162290142058, "grad_norm": 1.5725204944610596, "learning_rate": 4.627660194310185e-05, "loss": 4.8365, "step": 3271 }, { "epoch": 0.17606543263021954, "grad_norm": 1.5867685079574585, "learning_rate": 4.6274382619486656e-05, "loss": 4.8107, "step": 3272 }, { "epoch": 0.17611924235901852, "grad_norm": 1.5517953634262085, "learning_rate": 4.627216268790684e-05, "loss": 4.8544, "step": 3273 }, { "epoch": 0.17617305208781747, "grad_norm": 1.8626587390899658, "learning_rate": 4.626994214842582e-05, "loss": 4.5015, "step": 3274 }, { "epoch": 0.17622686181661645, "grad_norm": 1.6483896970748901, "learning_rate": 4.6267721001107053e-05, "loss": 4.4246, "step": 3275 }, { "epoch": 0.1762806715454154, "grad_norm": 1.676328420639038, "learning_rate": 4.626549924601404e-05, "loss": 4.7152, "step": 3276 }, { "epoch": 0.1763344812742144, "grad_norm": 1.206005573272705, "learning_rate": 4.626327688321025e-05, "loss": 4.8703, "step": 3277 }, { "epoch": 0.17638829100301334, "grad_norm": 1.7291312217712402, "learning_rate": 4.62610539127592e-05, "loss": 4.6937, "step": 3278 }, { "epoch": 0.17644210073181232, "grad_norm": 1.5042825937271118, "learning_rate": 4.625883033472441e-05, "loss": 4.61, "step": 3279 }, { "epoch": 0.17649591046061128, "grad_norm": 2.5130746364593506, "learning_rate": 4.625660614916944e-05, "loss": 4.2195, "step": 3280 }, { "epoch": 0.17654972018941026, "grad_norm": 1.7629270553588867, "learning_rate": 4.625438135615783e-05, "loss": 4.4741, "step": 3281 }, { "epoch": 0.1766035299182092, "grad_norm": 1.4498064517974854, "learning_rate": 4.625215595575317e-05, "loss": 4.4903, "step": 3282 }, { "epoch": 0.17665733964700817, "grad_norm": 1.5181838274002075, "learning_rate": 4.624992994801905e-05, "loss": 4.4331, "step": 3283 }, { "epoch": 0.17671114937580715, "grad_norm": 1.037503719329834, "learning_rate": 4.62477033330191e-05, "loss": 4.8878, "step": 3284 }, { "epoch": 0.1767649591046061, "grad_norm": 1.622389793395996, "learning_rate": 4.6245476110816925e-05, "loss": 4.6479, "step": 3285 }, { "epoch": 0.17681876883340508, "grad_norm": 1.2250580787658691, "learning_rate": 4.624324828147619e-05, "loss": 4.7466, "step": 3286 }, { "epoch": 0.17687257856220404, "grad_norm": 1.7919470071792603, "learning_rate": 4.6241019845060565e-05, "loss": 4.7824, "step": 3287 }, { "epoch": 0.17692638829100302, "grad_norm": 1.1775176525115967, "learning_rate": 4.623879080163371e-05, "loss": 4.5001, "step": 3288 }, { "epoch": 0.17698019801980197, "grad_norm": 1.5864890813827515, "learning_rate": 4.623656115125935e-05, "loss": 4.5633, "step": 3289 }, { "epoch": 0.17703400774860095, "grad_norm": 1.4774916172027588, "learning_rate": 4.6234330894001196e-05, "loss": 4.7503, "step": 3290 }, { "epoch": 0.1770878174773999, "grad_norm": 1.1628553867340088, "learning_rate": 4.6232100029922964e-05, "loss": 4.8136, "step": 3291 }, { "epoch": 0.1771416272061989, "grad_norm": 1.033565878868103, "learning_rate": 4.622986855908843e-05, "loss": 4.8739, "step": 3292 }, { "epoch": 0.17719543693499784, "grad_norm": 2.442423105239868, "learning_rate": 4.6227636481561354e-05, "loss": 4.4807, "step": 3293 }, { "epoch": 0.17724924666379682, "grad_norm": 2.2740817070007324, "learning_rate": 4.6225403797405525e-05, "loss": 4.6382, "step": 3294 }, { "epoch": 0.17730305639259578, "grad_norm": 1.492679476737976, "learning_rate": 4.622317050668474e-05, "loss": 4.4952, "step": 3295 }, { "epoch": 0.17735686612139476, "grad_norm": 1.4301166534423828, "learning_rate": 4.6220936609462826e-05, "loss": 4.6448, "step": 3296 }, { "epoch": 0.1774106758501937, "grad_norm": 1.483916163444519, "learning_rate": 4.621870210580362e-05, "loss": 4.5399, "step": 3297 }, { "epoch": 0.1774644855789927, "grad_norm": 1.2789983749389648, "learning_rate": 4.621646699577099e-05, "loss": 4.7947, "step": 3298 }, { "epoch": 0.17751829530779165, "grad_norm": 1.8889353275299072, "learning_rate": 4.621423127942879e-05, "loss": 4.3648, "step": 3299 }, { "epoch": 0.17757210503659063, "grad_norm": 1.6329634189605713, "learning_rate": 4.621199495684092e-05, "loss": 4.6682, "step": 3300 }, { "epoch": 0.17762591476538958, "grad_norm": 1.1154038906097412, "learning_rate": 4.620975802807129e-05, "loss": 4.8493, "step": 3301 }, { "epoch": 0.17767972449418856, "grad_norm": 1.6878931522369385, "learning_rate": 4.620752049318382e-05, "loss": 4.8049, "step": 3302 }, { "epoch": 0.17773353422298752, "grad_norm": 1.1563712358474731, "learning_rate": 4.620528235224246e-05, "loss": 4.9362, "step": 3303 }, { "epoch": 0.17778734395178647, "grad_norm": 1.170566439628601, "learning_rate": 4.6203043605311166e-05, "loss": 4.7888, "step": 3304 }, { "epoch": 0.17784115368058545, "grad_norm": 1.7695503234863281, "learning_rate": 4.620080425245391e-05, "loss": 4.571, "step": 3305 }, { "epoch": 0.1778949634093844, "grad_norm": 1.9709020853042603, "learning_rate": 4.619856429373469e-05, "loss": 4.8191, "step": 3306 }, { "epoch": 0.17794877313818339, "grad_norm": 1.1326048374176025, "learning_rate": 4.619632372921753e-05, "loss": 4.75, "step": 3307 }, { "epoch": 0.17800258286698234, "grad_norm": 1.6769715547561646, "learning_rate": 4.6194082558966443e-05, "loss": 4.4789, "step": 3308 }, { "epoch": 0.17805639259578132, "grad_norm": 1.2354964017868042, "learning_rate": 4.619184078304548e-05, "loss": 4.8582, "step": 3309 }, { "epoch": 0.17811020232458027, "grad_norm": 1.7962945699691772, "learning_rate": 4.618959840151871e-05, "loss": 4.3551, "step": 3310 }, { "epoch": 0.17816401205337926, "grad_norm": 0.9739223122596741, "learning_rate": 4.618735541445022e-05, "loss": 4.7176, "step": 3311 }, { "epoch": 0.1782178217821782, "grad_norm": 1.3138076066970825, "learning_rate": 4.6185111821904085e-05, "loss": 4.5814, "step": 3312 }, { "epoch": 0.1782716315109772, "grad_norm": 1.0678335428237915, "learning_rate": 4.6182867623944436e-05, "loss": 4.5457, "step": 3313 }, { "epoch": 0.17832544123977614, "grad_norm": 1.7429698705673218, "learning_rate": 4.618062282063541e-05, "loss": 4.2667, "step": 3314 }, { "epoch": 0.17837925096857513, "grad_norm": 1.4227248430252075, "learning_rate": 4.617837741204116e-05, "loss": 4.7555, "step": 3315 }, { "epoch": 0.17843306069737408, "grad_norm": 1.6204572916030884, "learning_rate": 4.6176131398225836e-05, "loss": 4.7931, "step": 3316 }, { "epoch": 0.17848687042617306, "grad_norm": 0.9428834319114685, "learning_rate": 4.617388477925364e-05, "loss": 4.724, "step": 3317 }, { "epoch": 0.17854068015497201, "grad_norm": 0.9558742642402649, "learning_rate": 4.617163755518876e-05, "loss": 4.8143, "step": 3318 }, { "epoch": 0.178594489883771, "grad_norm": 1.1748031377792358, "learning_rate": 4.6169389726095435e-05, "loss": 4.7531, "step": 3319 }, { "epoch": 0.17864829961256995, "grad_norm": 1.4822593927383423, "learning_rate": 4.6167141292037884e-05, "loss": 4.1623, "step": 3320 }, { "epoch": 0.17870210934136893, "grad_norm": 1.3916044235229492, "learning_rate": 4.6164892253080374e-05, "loss": 4.5324, "step": 3321 }, { "epoch": 0.17875591907016788, "grad_norm": 1.1458392143249512, "learning_rate": 4.6162642609287156e-05, "loss": 4.7594, "step": 3322 }, { "epoch": 0.17880972879896687, "grad_norm": 0.9684093594551086, "learning_rate": 4.616039236072255e-05, "loss": 4.5661, "step": 3323 }, { "epoch": 0.17886353852776582, "grad_norm": 1.6773350238800049, "learning_rate": 4.615814150745084e-05, "loss": 4.565, "step": 3324 }, { "epoch": 0.17891734825656477, "grad_norm": 1.1101590394973755, "learning_rate": 4.6155890049536346e-05, "loss": 4.8114, "step": 3325 }, { "epoch": 0.17897115798536375, "grad_norm": 1.8887845277786255, "learning_rate": 4.615363798704342e-05, "loss": 4.5756, "step": 3326 }, { "epoch": 0.1790249677141627, "grad_norm": 2.1391518115997314, "learning_rate": 4.615138532003642e-05, "loss": 4.5194, "step": 3327 }, { "epoch": 0.1790787774429617, "grad_norm": 1.1741083860397339, "learning_rate": 4.614913204857972e-05, "loss": 4.5634, "step": 3328 }, { "epoch": 0.17913258717176064, "grad_norm": 1.3236209154129028, "learning_rate": 4.614687817273771e-05, "loss": 4.4661, "step": 3329 }, { "epoch": 0.17918639690055962, "grad_norm": 1.2031482458114624, "learning_rate": 4.61446236925748e-05, "loss": 5.0721, "step": 3330 }, { "epoch": 0.17924020662935858, "grad_norm": 1.2517398595809937, "learning_rate": 4.6142368608155405e-05, "loss": 4.8015, "step": 3331 }, { "epoch": 0.17929401635815756, "grad_norm": 1.431799292564392, "learning_rate": 4.6140112919544e-05, "loss": 4.7979, "step": 3332 }, { "epoch": 0.1793478260869565, "grad_norm": 1.4114460945129395, "learning_rate": 4.6137856626805015e-05, "loss": 4.9217, "step": 3333 }, { "epoch": 0.1794016358157555, "grad_norm": 1.668041706085205, "learning_rate": 4.613559973000295e-05, "loss": 4.9523, "step": 3334 }, { "epoch": 0.17945544554455445, "grad_norm": 1.4986401796340942, "learning_rate": 4.6133342229202287e-05, "loss": 4.3797, "step": 3335 }, { "epoch": 0.17950925527335343, "grad_norm": 1.3440130949020386, "learning_rate": 4.613108412446755e-05, "loss": 4.85, "step": 3336 }, { "epoch": 0.17956306500215238, "grad_norm": 0.943030059337616, "learning_rate": 4.6128825415863266e-05, "loss": 5.0982, "step": 3337 }, { "epoch": 0.17961687473095136, "grad_norm": 1.0846892595291138, "learning_rate": 4.6126566103453975e-05, "loss": 4.8716, "step": 3338 }, { "epoch": 0.17967068445975032, "grad_norm": 1.611315131187439, "learning_rate": 4.612430618730425e-05, "loss": 4.4329, "step": 3339 }, { "epoch": 0.1797244941885493, "grad_norm": 1.4728426933288574, "learning_rate": 4.612204566747867e-05, "loss": 4.8826, "step": 3340 }, { "epoch": 0.17977830391734825, "grad_norm": 1.7942761182785034, "learning_rate": 4.6119784544041843e-05, "loss": 4.2421, "step": 3341 }, { "epoch": 0.17983211364614723, "grad_norm": 1.4495875835418701, "learning_rate": 4.6117522817058376e-05, "loss": 5.0526, "step": 3342 }, { "epoch": 0.1798859233749462, "grad_norm": 1.5249933004379272, "learning_rate": 4.61152604865929e-05, "loss": 4.4889, "step": 3343 }, { "epoch": 0.17993973310374517, "grad_norm": 1.727034091949463, "learning_rate": 4.611299755271009e-05, "loss": 4.4447, "step": 3344 }, { "epoch": 0.17999354283254412, "grad_norm": 1.5973063707351685, "learning_rate": 4.611073401547458e-05, "loss": 4.546, "step": 3345 }, { "epoch": 0.18004735256134308, "grad_norm": 1.225244402885437, "learning_rate": 4.6108469874951075e-05, "loss": 4.5566, "step": 3346 }, { "epoch": 0.18010116229014206, "grad_norm": 0.9584915041923523, "learning_rate": 4.610620513120428e-05, "loss": 4.6362, "step": 3347 }, { "epoch": 0.180154972018941, "grad_norm": 1.496515154838562, "learning_rate": 4.610393978429892e-05, "loss": 4.4545, "step": 3348 }, { "epoch": 0.18020878174774, "grad_norm": 1.6105353832244873, "learning_rate": 4.610167383429972e-05, "loss": 4.4249, "step": 3349 }, { "epoch": 0.18026259147653895, "grad_norm": 1.290265440940857, "learning_rate": 4.6099407281271426e-05, "loss": 4.494, "step": 3350 }, { "epoch": 0.18031640120533793, "grad_norm": 1.1996957063674927, "learning_rate": 4.6097140125278835e-05, "loss": 4.7725, "step": 3351 }, { "epoch": 0.18037021093413688, "grad_norm": 1.9394100904464722, "learning_rate": 4.609487236638672e-05, "loss": 4.5047, "step": 3352 }, { "epoch": 0.18042402066293586, "grad_norm": 2.1739981174468994, "learning_rate": 4.609260400465989e-05, "loss": 4.9221, "step": 3353 }, { "epoch": 0.18047783039173482, "grad_norm": 1.5772852897644043, "learning_rate": 4.609033504016317e-05, "loss": 4.948, "step": 3354 }, { "epoch": 0.1805316401205338, "grad_norm": 1.5096807479858398, "learning_rate": 4.6088065472961406e-05, "loss": 4.5948, "step": 3355 }, { "epoch": 0.18058544984933275, "grad_norm": 1.0308858156204224, "learning_rate": 4.6085795303119446e-05, "loss": 4.6961, "step": 3356 }, { "epoch": 0.18063925957813173, "grad_norm": 1.1265077590942383, "learning_rate": 4.608352453070217e-05, "loss": 4.5472, "step": 3357 }, { "epoch": 0.1806930693069307, "grad_norm": 1.714309811592102, "learning_rate": 4.6081253155774475e-05, "loss": 4.4741, "step": 3358 }, { "epoch": 0.18074687903572967, "grad_norm": 1.7210288047790527, "learning_rate": 4.607898117840126e-05, "loss": 4.5987, "step": 3359 }, { "epoch": 0.18080068876452862, "grad_norm": 1.8259774446487427, "learning_rate": 4.607670859864747e-05, "loss": 4.743, "step": 3360 }, { "epoch": 0.1808544984933276, "grad_norm": 1.7765071392059326, "learning_rate": 4.607443541657802e-05, "loss": 4.3785, "step": 3361 }, { "epoch": 0.18090830822212656, "grad_norm": 1.48752760887146, "learning_rate": 4.607216163225791e-05, "loss": 4.613, "step": 3362 }, { "epoch": 0.18096211795092554, "grad_norm": 3.004080295562744, "learning_rate": 4.606988724575208e-05, "loss": 4.4347, "step": 3363 }, { "epoch": 0.1810159276797245, "grad_norm": 2.2287633419036865, "learning_rate": 4.606761225712555e-05, "loss": 4.5574, "step": 3364 }, { "epoch": 0.18106973740852347, "grad_norm": 2.2120320796966553, "learning_rate": 4.606533666644334e-05, "loss": 4.553, "step": 3365 }, { "epoch": 0.18112354713732243, "grad_norm": 1.295937180519104, "learning_rate": 4.606306047377045e-05, "loss": 4.521, "step": 3366 }, { "epoch": 0.1811773568661214, "grad_norm": 1.0355980396270752, "learning_rate": 4.606078367917195e-05, "loss": 5.0064, "step": 3367 }, { "epoch": 0.18123116659492036, "grad_norm": 0.9715438485145569, "learning_rate": 4.60585062827129e-05, "loss": 4.8902, "step": 3368 }, { "epoch": 0.18128497632371932, "grad_norm": 1.336042046546936, "learning_rate": 4.605622828445838e-05, "loss": 4.8394, "step": 3369 }, { "epoch": 0.1813387860525183, "grad_norm": 1.9702188968658447, "learning_rate": 4.60539496844735e-05, "loss": 4.8203, "step": 3370 }, { "epoch": 0.18139259578131725, "grad_norm": 1.5911225080490112, "learning_rate": 4.605167048282335e-05, "loss": 4.6711, "step": 3371 }, { "epoch": 0.18144640551011623, "grad_norm": 1.8133054971694946, "learning_rate": 4.604939067957309e-05, "loss": 4.8114, "step": 3372 }, { "epoch": 0.18150021523891519, "grad_norm": 1.9100196361541748, "learning_rate": 4.604711027478785e-05, "loss": 4.7076, "step": 3373 }, { "epoch": 0.18155402496771417, "grad_norm": 1.0563790798187256, "learning_rate": 4.6044829268532825e-05, "loss": 4.7104, "step": 3374 }, { "epoch": 0.18160783469651312, "grad_norm": 1.3139817714691162, "learning_rate": 4.604254766087317e-05, "loss": 4.7974, "step": 3375 }, { "epoch": 0.1816616444253121, "grad_norm": 2.497908592224121, "learning_rate": 4.604026545187411e-05, "loss": 4.5622, "step": 3376 }, { "epoch": 0.18171545415411106, "grad_norm": 2.1460623741149902, "learning_rate": 4.603798264160085e-05, "loss": 4.5756, "step": 3377 }, { "epoch": 0.18176926388291004, "grad_norm": 1.0596128702163696, "learning_rate": 4.603569923011863e-05, "loss": 4.6432, "step": 3378 }, { "epoch": 0.181823073611709, "grad_norm": 1.4579811096191406, "learning_rate": 4.603341521749272e-05, "loss": 5.0215, "step": 3379 }, { "epoch": 0.18187688334050797, "grad_norm": 1.9868861436843872, "learning_rate": 4.603113060378835e-05, "loss": 4.2042, "step": 3380 }, { "epoch": 0.18193069306930693, "grad_norm": 1.6825159788131714, "learning_rate": 4.6028845389070854e-05, "loss": 4.5468, "step": 3381 }, { "epoch": 0.1819845027981059, "grad_norm": 1.808550477027893, "learning_rate": 4.602655957340551e-05, "loss": 4.4863, "step": 3382 }, { "epoch": 0.18203831252690486, "grad_norm": 1.516169548034668, "learning_rate": 4.602427315685765e-05, "loss": 4.4846, "step": 3383 }, { "epoch": 0.18209212225570384, "grad_norm": 1.4626572132110596, "learning_rate": 4.6021986139492614e-05, "loss": 4.4309, "step": 3384 }, { "epoch": 0.1821459319845028, "grad_norm": 1.3912744522094727, "learning_rate": 4.601969852137575e-05, "loss": 4.476, "step": 3385 }, { "epoch": 0.18219974171330178, "grad_norm": 1.1578866243362427, "learning_rate": 4.601741030257245e-05, "loss": 4.6681, "step": 3386 }, { "epoch": 0.18225355144210073, "grad_norm": 1.4345611333847046, "learning_rate": 4.601512148314809e-05, "loss": 4.6617, "step": 3387 }, { "epoch": 0.1823073611708997, "grad_norm": 2.2418715953826904, "learning_rate": 4.6012832063168073e-05, "loss": 4.485, "step": 3388 }, { "epoch": 0.18236117089969867, "grad_norm": 1.5124586820602417, "learning_rate": 4.6010542042697844e-05, "loss": 4.66, "step": 3389 }, { "epoch": 0.18241498062849762, "grad_norm": 1.2236058712005615, "learning_rate": 4.600825142180283e-05, "loss": 4.7231, "step": 3390 }, { "epoch": 0.1824687903572966, "grad_norm": 1.9071435928344727, "learning_rate": 4.6005960200548505e-05, "loss": 4.9853, "step": 3391 }, { "epoch": 0.18252260008609555, "grad_norm": 1.4705966711044312, "learning_rate": 4.600366837900032e-05, "loss": 4.5628, "step": 3392 }, { "epoch": 0.18257640981489454, "grad_norm": 1.0849884748458862, "learning_rate": 4.6001375957223804e-05, "loss": 4.6368, "step": 3393 }, { "epoch": 0.1826302195436935, "grad_norm": 1.7830544710159302, "learning_rate": 4.599908293528443e-05, "loss": 4.6779, "step": 3394 }, { "epoch": 0.18268402927249247, "grad_norm": 1.7233855724334717, "learning_rate": 4.599678931324776e-05, "loss": 4.3127, "step": 3395 }, { "epoch": 0.18273783900129142, "grad_norm": 2.3636627197265625, "learning_rate": 4.599449509117933e-05, "loss": 4.3691, "step": 3396 }, { "epoch": 0.1827916487300904, "grad_norm": 1.6690865755081177, "learning_rate": 4.5992200269144695e-05, "loss": 4.6915, "step": 3397 }, { "epoch": 0.18284545845888936, "grad_norm": 1.5263433456420898, "learning_rate": 4.598990484720943e-05, "loss": 4.8978, "step": 3398 }, { "epoch": 0.18289926818768834, "grad_norm": 1.157516598701477, "learning_rate": 4.598760882543915e-05, "loss": 4.6696, "step": 3399 }, { "epoch": 0.1829530779164873, "grad_norm": 2.6232614517211914, "learning_rate": 4.598531220389945e-05, "loss": 3.9845, "step": 3400 }, { "epoch": 0.18300688764528628, "grad_norm": 1.7388795614242554, "learning_rate": 4.598301498265598e-05, "loss": 4.7658, "step": 3401 }, { "epoch": 0.18306069737408523, "grad_norm": 1.8353831768035889, "learning_rate": 4.598071716177438e-05, "loss": 4.3682, "step": 3402 }, { "epoch": 0.1831145071028842, "grad_norm": 1.527158260345459, "learning_rate": 4.597841874132032e-05, "loss": 5.1653, "step": 3403 }, { "epoch": 0.18316831683168316, "grad_norm": 1.5319963693618774, "learning_rate": 4.597611972135947e-05, "loss": 4.816, "step": 3404 }, { "epoch": 0.18322212656048215, "grad_norm": 1.6398594379425049, "learning_rate": 4.597382010195753e-05, "loss": 4.3453, "step": 3405 }, { "epoch": 0.1832759362892811, "grad_norm": 1.1516488790512085, "learning_rate": 4.597151988318024e-05, "loss": 5.1327, "step": 3406 }, { "epoch": 0.18332974601808008, "grad_norm": 2.088855266571045, "learning_rate": 4.596921906509331e-05, "loss": 4.4883, "step": 3407 }, { "epoch": 0.18338355574687903, "grad_norm": 1.5852599143981934, "learning_rate": 4.59669176477625e-05, "loss": 4.9626, "step": 3408 }, { "epoch": 0.18343736547567802, "grad_norm": 1.2311489582061768, "learning_rate": 4.596461563125357e-05, "loss": 4.7777, "step": 3409 }, { "epoch": 0.18349117520447697, "grad_norm": 2.710482597351074, "learning_rate": 4.5962313015632326e-05, "loss": 4.7686, "step": 3410 }, { "epoch": 0.18354498493327592, "grad_norm": 1.1167446374893188, "learning_rate": 4.596000980096455e-05, "loss": 4.9314, "step": 3411 }, { "epoch": 0.1835987946620749, "grad_norm": 1.805571436882019, "learning_rate": 4.595770598731608e-05, "loss": 4.6911, "step": 3412 }, { "epoch": 0.18365260439087386, "grad_norm": 1.2264186143875122, "learning_rate": 4.595540157475273e-05, "loss": 4.8026, "step": 3413 }, { "epoch": 0.18370641411967284, "grad_norm": 2.2416553497314453, "learning_rate": 4.595309656334038e-05, "loss": 4.0203, "step": 3414 }, { "epoch": 0.1837602238484718, "grad_norm": 1.1842970848083496, "learning_rate": 4.595079095314487e-05, "loss": 4.8544, "step": 3415 }, { "epoch": 0.18381403357727077, "grad_norm": 1.3184185028076172, "learning_rate": 4.594848474423212e-05, "loss": 4.575, "step": 3416 }, { "epoch": 0.18386784330606973, "grad_norm": 0.8770515322685242, "learning_rate": 4.5946177936668014e-05, "loss": 4.6236, "step": 3417 }, { "epoch": 0.1839216530348687, "grad_norm": 1.365926742553711, "learning_rate": 4.5943870530518484e-05, "loss": 5.0313, "step": 3418 }, { "epoch": 0.18397546276366766, "grad_norm": 0.903483510017395, "learning_rate": 4.594156252584947e-05, "loss": 4.5523, "step": 3419 }, { "epoch": 0.18402927249246664, "grad_norm": 1.3918216228485107, "learning_rate": 4.593925392272692e-05, "loss": 4.8745, "step": 3420 }, { "epoch": 0.1840830822212656, "grad_norm": 2.2054312229156494, "learning_rate": 4.593694472121681e-05, "loss": 4.6006, "step": 3421 }, { "epoch": 0.18413689195006458, "grad_norm": 1.4281362295150757, "learning_rate": 4.5934634921385146e-05, "loss": 4.3669, "step": 3422 }, { "epoch": 0.18419070167886353, "grad_norm": 3.3345046043395996, "learning_rate": 4.593232452329791e-05, "loss": 4.2473, "step": 3423 }, { "epoch": 0.18424451140766251, "grad_norm": 2.5660150051116943, "learning_rate": 4.5930013527021147e-05, "loss": 4.5183, "step": 3424 }, { "epoch": 0.18429832113646147, "grad_norm": 1.6581361293792725, "learning_rate": 4.592770193262089e-05, "loss": 4.6384, "step": 3425 }, { "epoch": 0.18435213086526045, "grad_norm": 1.287647008895874, "learning_rate": 4.59253897401632e-05, "loss": 4.7236, "step": 3426 }, { "epoch": 0.1844059405940594, "grad_norm": 2.066051721572876, "learning_rate": 4.592307694971416e-05, "loss": 4.5953, "step": 3427 }, { "epoch": 0.18445975032285838, "grad_norm": 1.3168941736221313, "learning_rate": 4.5920763561339855e-05, "loss": 4.69, "step": 3428 }, { "epoch": 0.18451356005165734, "grad_norm": 1.6899968385696411, "learning_rate": 4.5918449575106394e-05, "loss": 4.1017, "step": 3429 }, { "epoch": 0.18456736978045632, "grad_norm": 1.2809243202209473, "learning_rate": 4.5916134991079904e-05, "loss": 4.7294, "step": 3430 }, { "epoch": 0.18462117950925527, "grad_norm": 1.599859356880188, "learning_rate": 4.591381980932654e-05, "loss": 4.8351, "step": 3431 }, { "epoch": 0.18467498923805423, "grad_norm": 1.6659740209579468, "learning_rate": 4.591150402991246e-05, "loss": 4.8002, "step": 3432 }, { "epoch": 0.1847287989668532, "grad_norm": 1.79348886013031, "learning_rate": 4.590918765290384e-05, "loss": 4.659, "step": 3433 }, { "epoch": 0.18478260869565216, "grad_norm": 1.015991449356079, "learning_rate": 4.590687067836688e-05, "loss": 4.8057, "step": 3434 }, { "epoch": 0.18483641842445114, "grad_norm": 1.1139674186706543, "learning_rate": 4.5904553106367774e-05, "loss": 4.6724, "step": 3435 }, { "epoch": 0.1848902281532501, "grad_norm": 1.214199423789978, "learning_rate": 4.590223493697278e-05, "loss": 4.6406, "step": 3436 }, { "epoch": 0.18494403788204908, "grad_norm": 1.4231133460998535, "learning_rate": 4.589991617024813e-05, "loss": 4.4938, "step": 3437 }, { "epoch": 0.18499784761084803, "grad_norm": 1.572749137878418, "learning_rate": 4.5897596806260076e-05, "loss": 4.6384, "step": 3438 }, { "epoch": 0.185051657339647, "grad_norm": 1.7364416122436523, "learning_rate": 4.589527684507493e-05, "loss": 4.546, "step": 3439 }, { "epoch": 0.18510546706844597, "grad_norm": 2.3508620262145996, "learning_rate": 4.589295628675897e-05, "loss": 3.7164, "step": 3440 }, { "epoch": 0.18515927679724495, "grad_norm": 1.258973479270935, "learning_rate": 4.589063513137851e-05, "loss": 4.5658, "step": 3441 }, { "epoch": 0.1852130865260439, "grad_norm": 1.6377243995666504, "learning_rate": 4.5888313378999886e-05, "loss": 4.7118, "step": 3442 }, { "epoch": 0.18526689625484288, "grad_norm": 1.6943440437316895, "learning_rate": 4.5885991029689456e-05, "loss": 4.8624, "step": 3443 }, { "epoch": 0.18532070598364184, "grad_norm": 1.9066287279129028, "learning_rate": 4.588366808351357e-05, "loss": 4.5503, "step": 3444 }, { "epoch": 0.18537451571244082, "grad_norm": 1.9032119512557983, "learning_rate": 4.5881344540538627e-05, "loss": 4.6378, "step": 3445 }, { "epoch": 0.18542832544123977, "grad_norm": 1.7326626777648926, "learning_rate": 4.587902040083102e-05, "loss": 4.4507, "step": 3446 }, { "epoch": 0.18548213517003875, "grad_norm": 1.4712493419647217, "learning_rate": 4.587669566445717e-05, "loss": 4.8019, "step": 3447 }, { "epoch": 0.1855359448988377, "grad_norm": 1.3393689393997192, "learning_rate": 4.5874370331483505e-05, "loss": 4.4242, "step": 3448 }, { "epoch": 0.1855897546276367, "grad_norm": 2.1676666736602783, "learning_rate": 4.587204440197649e-05, "loss": 4.5461, "step": 3449 }, { "epoch": 0.18564356435643564, "grad_norm": 2.1576108932495117, "learning_rate": 4.586971787600257e-05, "loss": 4.748, "step": 3450 }, { "epoch": 0.18569737408523462, "grad_norm": 1.333265781402588, "learning_rate": 4.586739075362826e-05, "loss": 4.579, "step": 3451 }, { "epoch": 0.18575118381403358, "grad_norm": 1.4947803020477295, "learning_rate": 4.586506303492004e-05, "loss": 4.6011, "step": 3452 }, { "epoch": 0.18580499354283253, "grad_norm": 1.087462306022644, "learning_rate": 4.5862734719944446e-05, "loss": 4.5163, "step": 3453 }, { "epoch": 0.1858588032716315, "grad_norm": 1.582331657409668, "learning_rate": 4.5860405808768e-05, "loss": 4.7651, "step": 3454 }, { "epoch": 0.18591261300043047, "grad_norm": 1.362758994102478, "learning_rate": 4.585807630145727e-05, "loss": 4.6006, "step": 3455 }, { "epoch": 0.18596642272922945, "grad_norm": 1.399816632270813, "learning_rate": 4.5855746198078825e-05, "loss": 4.4759, "step": 3456 }, { "epoch": 0.1860202324580284, "grad_norm": 2.0238466262817383, "learning_rate": 4.5853415498699245e-05, "loss": 4.7391, "step": 3457 }, { "epoch": 0.18607404218682738, "grad_norm": 1.4017927646636963, "learning_rate": 4.5851084203385135e-05, "loss": 4.5693, "step": 3458 }, { "epoch": 0.18612785191562634, "grad_norm": 1.9298374652862549, "learning_rate": 4.5848752312203126e-05, "loss": 4.3458, "step": 3459 }, { "epoch": 0.18618166164442532, "grad_norm": 1.918239712715149, "learning_rate": 4.584641982521986e-05, "loss": 4.7702, "step": 3460 }, { "epoch": 0.18623547137322427, "grad_norm": 1.4661623239517212, "learning_rate": 4.5844086742501965e-05, "loss": 4.3343, "step": 3461 }, { "epoch": 0.18628928110202325, "grad_norm": 1.2911603450775146, "learning_rate": 4.584175306411615e-05, "loss": 4.6748, "step": 3462 }, { "epoch": 0.1863430908308222, "grad_norm": 1.8964412212371826, "learning_rate": 4.583941879012909e-05, "loss": 4.6853, "step": 3463 }, { "epoch": 0.1863969005596212, "grad_norm": 1.3130487203598022, "learning_rate": 4.5837083920607485e-05, "loss": 4.4111, "step": 3464 }, { "epoch": 0.18645071028842014, "grad_norm": 1.4890106916427612, "learning_rate": 4.583474845561807e-05, "loss": 4.4934, "step": 3465 }, { "epoch": 0.18650452001721912, "grad_norm": 1.4686616659164429, "learning_rate": 4.5832412395227584e-05, "loss": 4.5291, "step": 3466 }, { "epoch": 0.18655832974601808, "grad_norm": 1.4395948648452759, "learning_rate": 4.5830075739502784e-05, "loss": 4.7148, "step": 3467 }, { "epoch": 0.18661213947481706, "grad_norm": 1.3171851634979248, "learning_rate": 4.582773848851045e-05, "loss": 4.6992, "step": 3468 }, { "epoch": 0.186665949203616, "grad_norm": 1.727522611618042, "learning_rate": 4.582540064231736e-05, "loss": 5.0653, "step": 3469 }, { "epoch": 0.186719758932415, "grad_norm": 1.474251627922058, "learning_rate": 4.582306220099034e-05, "loss": 4.5599, "step": 3470 }, { "epoch": 0.18677356866121395, "grad_norm": 1.6509604454040527, "learning_rate": 4.582072316459621e-05, "loss": 4.7285, "step": 3471 }, { "epoch": 0.18682737839001293, "grad_norm": 1.4718447923660278, "learning_rate": 4.5818383533201814e-05, "loss": 4.6915, "step": 3472 }, { "epoch": 0.18688118811881188, "grad_norm": 1.184342622756958, "learning_rate": 4.581604330687401e-05, "loss": 4.6322, "step": 3473 }, { "epoch": 0.18693499784761083, "grad_norm": 1.382400393486023, "learning_rate": 4.5813702485679676e-05, "loss": 4.8122, "step": 3474 }, { "epoch": 0.18698880757640982, "grad_norm": 2.6265556812286377, "learning_rate": 4.581136106968571e-05, "loss": 4.4633, "step": 3475 }, { "epoch": 0.18704261730520877, "grad_norm": 1.7294526100158691, "learning_rate": 4.5809019058959016e-05, "loss": 4.1915, "step": 3476 }, { "epoch": 0.18709642703400775, "grad_norm": 1.617463231086731, "learning_rate": 4.580667645356653e-05, "loss": 4.8039, "step": 3477 }, { "epoch": 0.1871502367628067, "grad_norm": 1.0068687200546265, "learning_rate": 4.580433325357519e-05, "loss": 4.717, "step": 3478 }, { "epoch": 0.18720404649160569, "grad_norm": 0.8523563146591187, "learning_rate": 4.580198945905196e-05, "loss": 4.7905, "step": 3479 }, { "epoch": 0.18725785622040464, "grad_norm": 2.333731174468994, "learning_rate": 4.579964507006383e-05, "loss": 4.6174, "step": 3480 }, { "epoch": 0.18731166594920362, "grad_norm": 1.2812386751174927, "learning_rate": 4.579730008667779e-05, "loss": 4.6037, "step": 3481 }, { "epoch": 0.18736547567800257, "grad_norm": 1.8219871520996094, "learning_rate": 4.579495450896085e-05, "loss": 4.6913, "step": 3482 }, { "epoch": 0.18741928540680156, "grad_norm": 1.384088397026062, "learning_rate": 4.5792608336980045e-05, "loss": 4.7088, "step": 3483 }, { "epoch": 0.1874730951356005, "grad_norm": 1.1826958656311035, "learning_rate": 4.5790261570802406e-05, "loss": 4.7866, "step": 3484 }, { "epoch": 0.1875269048643995, "grad_norm": 1.473294734954834, "learning_rate": 4.578791421049502e-05, "loss": 4.9412, "step": 3485 }, { "epoch": 0.18758071459319844, "grad_norm": 1.5826395750045776, "learning_rate": 4.578556625612496e-05, "loss": 4.7291, "step": 3486 }, { "epoch": 0.18763452432199743, "grad_norm": 1.864142656326294, "learning_rate": 4.578321770775932e-05, "loss": 4.5793, "step": 3487 }, { "epoch": 0.18768833405079638, "grad_norm": 1.8812962770462036, "learning_rate": 4.5780868565465216e-05, "loss": 4.199, "step": 3488 }, { "epoch": 0.18774214377959536, "grad_norm": 1.528261423110962, "learning_rate": 4.577851882930979e-05, "loss": 4.7108, "step": 3489 }, { "epoch": 0.18779595350839431, "grad_norm": 2.3381662368774414, "learning_rate": 4.5776168499360186e-05, "loss": 4.4735, "step": 3490 }, { "epoch": 0.1878497632371933, "grad_norm": 1.3182222843170166, "learning_rate": 4.5773817575683556e-05, "loss": 4.571, "step": 3491 }, { "epoch": 0.18790357296599225, "grad_norm": 1.431089997291565, "learning_rate": 4.57714660583471e-05, "loss": 4.3171, "step": 3492 }, { "epoch": 0.18795738269479123, "grad_norm": 1.0739039182662964, "learning_rate": 4.5769113947418004e-05, "loss": 4.4907, "step": 3493 }, { "epoch": 0.18801119242359018, "grad_norm": 1.6031039953231812, "learning_rate": 4.576676124296351e-05, "loss": 4.728, "step": 3494 }, { "epoch": 0.18806500215238917, "grad_norm": 1.644141435623169, "learning_rate": 4.5764407945050825e-05, "loss": 4.518, "step": 3495 }, { "epoch": 0.18811881188118812, "grad_norm": 1.0039502382278442, "learning_rate": 4.5762054053747216e-05, "loss": 4.7395, "step": 3496 }, { "epoch": 0.18817262160998707, "grad_norm": 1.7235331535339355, "learning_rate": 4.575969956911994e-05, "loss": 4.6528, "step": 3497 }, { "epoch": 0.18822643133878605, "grad_norm": 1.6462883949279785, "learning_rate": 4.575734449123629e-05, "loss": 5.1176, "step": 3498 }, { "epoch": 0.188280241067585, "grad_norm": 1.791027545928955, "learning_rate": 4.575498882016357e-05, "loss": 4.5949, "step": 3499 }, { "epoch": 0.188334050796384, "grad_norm": 1.850181221961975, "learning_rate": 4.575263255596909e-05, "loss": 4.8251, "step": 3500 }, { "epoch": 0.18838786052518294, "grad_norm": 1.8055474758148193, "learning_rate": 4.575027569872018e-05, "loss": 4.7101, "step": 3501 }, { "epoch": 0.18844167025398192, "grad_norm": 1.044954776763916, "learning_rate": 4.574791824848421e-05, "loss": 4.4532, "step": 3502 }, { "epoch": 0.18849547998278088, "grad_norm": 1.131891131401062, "learning_rate": 4.574556020532855e-05, "loss": 5.0234, "step": 3503 }, { "epoch": 0.18854928971157986, "grad_norm": 2.357839584350586, "learning_rate": 4.5743201569320573e-05, "loss": 5.1184, "step": 3504 }, { "epoch": 0.1886030994403788, "grad_norm": 1.5817546844482422, "learning_rate": 4.574084234052768e-05, "loss": 4.5702, "step": 3505 }, { "epoch": 0.1886569091691778, "grad_norm": 1.832507848739624, "learning_rate": 4.5738482519017304e-05, "loss": 4.849, "step": 3506 }, { "epoch": 0.18871071889797675, "grad_norm": 1.0088127851486206, "learning_rate": 4.573612210485688e-05, "loss": 5.1372, "step": 3507 }, { "epoch": 0.18876452862677573, "grad_norm": 1.183308482170105, "learning_rate": 4.573376109811386e-05, "loss": 4.9807, "step": 3508 }, { "epoch": 0.18881833835557468, "grad_norm": 1.7681676149368286, "learning_rate": 4.573139949885571e-05, "loss": 4.4684, "step": 3509 }, { "epoch": 0.18887214808437366, "grad_norm": 1.9892204999923706, "learning_rate": 4.572903730714993e-05, "loss": 4.5926, "step": 3510 }, { "epoch": 0.18892595781317262, "grad_norm": 2.201666831970215, "learning_rate": 4.572667452306402e-05, "loss": 4.0866, "step": 3511 }, { "epoch": 0.1889797675419716, "grad_norm": 1.5763643980026245, "learning_rate": 4.572431114666549e-05, "loss": 4.768, "step": 3512 }, { "epoch": 0.18903357727077055, "grad_norm": 1.5816094875335693, "learning_rate": 4.572194717802189e-05, "loss": 4.3348, "step": 3513 }, { "epoch": 0.18908738699956953, "grad_norm": 1.7828227281570435, "learning_rate": 4.571958261720078e-05, "loss": 4.6623, "step": 3514 }, { "epoch": 0.1891411967283685, "grad_norm": 1.3500428199768066, "learning_rate": 4.571721746426973e-05, "loss": 4.5524, "step": 3515 }, { "epoch": 0.18919500645716747, "grad_norm": 1.159110426902771, "learning_rate": 4.5714851719296324e-05, "loss": 4.5425, "step": 3516 }, { "epoch": 0.18924881618596642, "grad_norm": 1.976499080657959, "learning_rate": 4.571248538234818e-05, "loss": 4.4874, "step": 3517 }, { "epoch": 0.18930262591476538, "grad_norm": 1.450547456741333, "learning_rate": 4.5710118453492906e-05, "loss": 4.4124, "step": 3518 }, { "epoch": 0.18935643564356436, "grad_norm": 2.4535577297210693, "learning_rate": 4.5707750932798157e-05, "loss": 4.588, "step": 3519 }, { "epoch": 0.1894102453723633, "grad_norm": 1.1649595499038696, "learning_rate": 4.570538282033157e-05, "loss": 4.8373, "step": 3520 }, { "epoch": 0.1894640551011623, "grad_norm": 1.5219848155975342, "learning_rate": 4.570301411616085e-05, "loss": 4.5298, "step": 3521 }, { "epoch": 0.18951786482996125, "grad_norm": 1.2326712608337402, "learning_rate": 4.5700644820353654e-05, "loss": 4.8455, "step": 3522 }, { "epoch": 0.18957167455876023, "grad_norm": 1.3969480991363525, "learning_rate": 4.569827493297772e-05, "loss": 4.5851, "step": 3523 }, { "epoch": 0.18962548428755918, "grad_norm": 2.2040648460388184, "learning_rate": 4.5695904454100755e-05, "loss": 4.6358, "step": 3524 }, { "epoch": 0.18967929401635816, "grad_norm": 2.253110885620117, "learning_rate": 4.569353338379051e-05, "loss": 4.6064, "step": 3525 }, { "epoch": 0.18973310374515712, "grad_norm": 1.1393065452575684, "learning_rate": 4.569116172211473e-05, "loss": 4.6596, "step": 3526 }, { "epoch": 0.1897869134739561, "grad_norm": 1.1671364307403564, "learning_rate": 4.568878946914121e-05, "loss": 4.8976, "step": 3527 }, { "epoch": 0.18984072320275505, "grad_norm": 1.8649324178695679, "learning_rate": 4.568641662493773e-05, "loss": 4.8825, "step": 3528 }, { "epoch": 0.18989453293155403, "grad_norm": 1.761763572692871, "learning_rate": 4.568404318957211e-05, "loss": 4.7093, "step": 3529 }, { "epoch": 0.189948342660353, "grad_norm": 1.1886467933654785, "learning_rate": 4.568166916311216e-05, "loss": 4.538, "step": 3530 }, { "epoch": 0.19000215238915197, "grad_norm": 2.0489792823791504, "learning_rate": 4.567929454562573e-05, "loss": 4.4073, "step": 3531 }, { "epoch": 0.19005596211795092, "grad_norm": 1.908449649810791, "learning_rate": 4.567691933718069e-05, "loss": 4.5652, "step": 3532 }, { "epoch": 0.1901097718467499, "grad_norm": 1.8098068237304688, "learning_rate": 4.567454353784491e-05, "loss": 4.8328, "step": 3533 }, { "epoch": 0.19016358157554886, "grad_norm": 1.6467087268829346, "learning_rate": 4.567216714768628e-05, "loss": 4.3508, "step": 3534 }, { "epoch": 0.19021739130434784, "grad_norm": 1.0774112939834595, "learning_rate": 4.566979016677272e-05, "loss": 4.5566, "step": 3535 }, { "epoch": 0.1902712010331468, "grad_norm": 1.1830483675003052, "learning_rate": 4.566741259517214e-05, "loss": 4.4739, "step": 3536 }, { "epoch": 0.19032501076194577, "grad_norm": 1.3917467594146729, "learning_rate": 4.566503443295251e-05, "loss": 4.4304, "step": 3537 }, { "epoch": 0.19037882049074473, "grad_norm": 1.5138391256332397, "learning_rate": 4.566265568018178e-05, "loss": 4.3988, "step": 3538 }, { "epoch": 0.19043263021954368, "grad_norm": 1.6709636449813843, "learning_rate": 4.5660276336927916e-05, "loss": 4.7794, "step": 3539 }, { "epoch": 0.19048643994834266, "grad_norm": 1.4481356143951416, "learning_rate": 4.5657896403258926e-05, "loss": 4.4805, "step": 3540 }, { "epoch": 0.19054024967714162, "grad_norm": 1.684065341949463, "learning_rate": 4.565551587924282e-05, "loss": 4.6036, "step": 3541 }, { "epoch": 0.1905940594059406, "grad_norm": 1.4126107692718506, "learning_rate": 4.565313476494763e-05, "loss": 4.8967, "step": 3542 }, { "epoch": 0.19064786913473955, "grad_norm": 1.617267370223999, "learning_rate": 4.5650753060441396e-05, "loss": 4.9738, "step": 3543 }, { "epoch": 0.19070167886353853, "grad_norm": 1.0684967041015625, "learning_rate": 4.5648370765792194e-05, "loss": 4.7393, "step": 3544 }, { "epoch": 0.19075548859233749, "grad_norm": 1.5343232154846191, "learning_rate": 4.564598788106808e-05, "loss": 4.3798, "step": 3545 }, { "epoch": 0.19080929832113647, "grad_norm": 1.9038190841674805, "learning_rate": 4.564360440633717e-05, "loss": 4.3867, "step": 3546 }, { "epoch": 0.19086310804993542, "grad_norm": 1.8265482187271118, "learning_rate": 4.5641220341667565e-05, "loss": 4.9641, "step": 3547 }, { "epoch": 0.1909169177787344, "grad_norm": 1.2085222005844116, "learning_rate": 4.563883568712741e-05, "loss": 4.6626, "step": 3548 }, { "epoch": 0.19097072750753336, "grad_norm": 2.257398843765259, "learning_rate": 4.563645044278483e-05, "loss": 4.2702, "step": 3549 }, { "epoch": 0.19102453723633234, "grad_norm": 1.4618312120437622, "learning_rate": 4.5634064608708016e-05, "loss": 4.7746, "step": 3550 }, { "epoch": 0.1910783469651313, "grad_norm": 1.5024991035461426, "learning_rate": 4.5631678184965126e-05, "loss": 4.7795, "step": 3551 }, { "epoch": 0.19113215669393027, "grad_norm": 2.293303966522217, "learning_rate": 4.562929117162437e-05, "loss": 4.3566, "step": 3552 }, { "epoch": 0.19118596642272923, "grad_norm": 1.7130954265594482, "learning_rate": 4.562690356875395e-05, "loss": 4.8936, "step": 3553 }, { "epoch": 0.1912397761515282, "grad_norm": 2.374870777130127, "learning_rate": 4.562451537642212e-05, "loss": 3.6723, "step": 3554 }, { "epoch": 0.19129358588032716, "grad_norm": 2.2809524536132812, "learning_rate": 4.5622126594697105e-05, "loss": 4.0127, "step": 3555 }, { "epoch": 0.19134739560912614, "grad_norm": 2.3582615852355957, "learning_rate": 4.5619737223647185e-05, "loss": 4.2372, "step": 3556 }, { "epoch": 0.1914012053379251, "grad_norm": 1.5298432111740112, "learning_rate": 4.561734726334063e-05, "loss": 4.2495, "step": 3557 }, { "epoch": 0.19145501506672408, "grad_norm": 1.2767503261566162, "learning_rate": 4.561495671384575e-05, "loss": 4.7217, "step": 3558 }, { "epoch": 0.19150882479552303, "grad_norm": 1.3792530298233032, "learning_rate": 4.561256557523085e-05, "loss": 4.3978, "step": 3559 }, { "epoch": 0.19156263452432198, "grad_norm": 1.8151514530181885, "learning_rate": 4.5610173847564266e-05, "loss": 4.6696, "step": 3560 }, { "epoch": 0.19161644425312097, "grad_norm": 1.1391730308532715, "learning_rate": 4.560778153091435e-05, "loss": 4.6014, "step": 3561 }, { "epoch": 0.19167025398191992, "grad_norm": 2.1158061027526855, "learning_rate": 4.5605388625349466e-05, "loss": 4.5668, "step": 3562 }, { "epoch": 0.1917240637107189, "grad_norm": 1.340730905532837, "learning_rate": 4.5602995130937995e-05, "loss": 4.68, "step": 3563 }, { "epoch": 0.19177787343951785, "grad_norm": 0.9753910899162292, "learning_rate": 4.560060104774834e-05, "loss": 4.7964, "step": 3564 }, { "epoch": 0.19183168316831684, "grad_norm": 1.5442087650299072, "learning_rate": 4.559820637584892e-05, "loss": 4.3298, "step": 3565 }, { "epoch": 0.1918854928971158, "grad_norm": 1.6078358888626099, "learning_rate": 4.5595811115308165e-05, "loss": 4.7944, "step": 3566 }, { "epoch": 0.19193930262591477, "grad_norm": 1.8812158107757568, "learning_rate": 4.5593415266194514e-05, "loss": 4.2674, "step": 3567 }, { "epoch": 0.19199311235471372, "grad_norm": 2.27557373046875, "learning_rate": 4.559101882857646e-05, "loss": 4.0578, "step": 3568 }, { "epoch": 0.1920469220835127, "grad_norm": 1.6898467540740967, "learning_rate": 4.558862180252246e-05, "loss": 4.6744, "step": 3569 }, { "epoch": 0.19210073181231166, "grad_norm": 1.9533522129058838, "learning_rate": 4.5586224188101026e-05, "loss": 4.7736, "step": 3570 }, { "epoch": 0.19215454154111064, "grad_norm": 1.5031709671020508, "learning_rate": 4.558382598538068e-05, "loss": 4.5839, "step": 3571 }, { "epoch": 0.1922083512699096, "grad_norm": 1.7474074363708496, "learning_rate": 4.5581427194429946e-05, "loss": 4.3529, "step": 3572 }, { "epoch": 0.19226216099870858, "grad_norm": 1.3872056007385254, "learning_rate": 4.557902781531739e-05, "loss": 4.6137, "step": 3573 }, { "epoch": 0.19231597072750753, "grad_norm": 1.9412341117858887, "learning_rate": 4.5576627848111566e-05, "loss": 4.7277, "step": 3574 }, { "epoch": 0.1923697804563065, "grad_norm": 0.9923033118247986, "learning_rate": 4.557422729288106e-05, "loss": 4.6259, "step": 3575 }, { "epoch": 0.19242359018510546, "grad_norm": 1.9863520860671997, "learning_rate": 4.557182614969447e-05, "loss": 4.3678, "step": 3576 }, { "epoch": 0.19247739991390445, "grad_norm": 1.3594411611557007, "learning_rate": 4.556942441862043e-05, "loss": 4.1918, "step": 3577 }, { "epoch": 0.1925312096427034, "grad_norm": 1.546194314956665, "learning_rate": 4.5567022099727565e-05, "loss": 4.4293, "step": 3578 }, { "epoch": 0.19258501937150238, "grad_norm": 1.6665964126586914, "learning_rate": 4.556461919308452e-05, "loss": 5.082, "step": 3579 }, { "epoch": 0.19263882910030133, "grad_norm": 1.505908489227295, "learning_rate": 4.556221569875998e-05, "loss": 4.2738, "step": 3580 }, { "epoch": 0.1926926388291003, "grad_norm": 2.4452078342437744, "learning_rate": 4.555981161682261e-05, "loss": 4.4792, "step": 3581 }, { "epoch": 0.19274644855789927, "grad_norm": 1.6563856601715088, "learning_rate": 4.555740694734113e-05, "loss": 4.6393, "step": 3582 }, { "epoch": 0.19280025828669822, "grad_norm": 1.5243998765945435, "learning_rate": 4.5555001690384256e-05, "loss": 4.509, "step": 3583 }, { "epoch": 0.1928540680154972, "grad_norm": 2.089663505554199, "learning_rate": 4.555259584602072e-05, "loss": 4.1666, "step": 3584 }, { "epoch": 0.19290787774429616, "grad_norm": 2.5600295066833496, "learning_rate": 4.555018941431927e-05, "loss": 4.5391, "step": 3585 }, { "epoch": 0.19296168747309514, "grad_norm": 0.9591318964958191, "learning_rate": 4.554778239534868e-05, "loss": 4.9614, "step": 3586 }, { "epoch": 0.1930154972018941, "grad_norm": 1.9144386053085327, "learning_rate": 4.554537478917774e-05, "loss": 4.8552, "step": 3587 }, { "epoch": 0.19306930693069307, "grad_norm": 1.7002103328704834, "learning_rate": 4.5542966595875245e-05, "loss": 4.4928, "step": 3588 }, { "epoch": 0.19312311665949203, "grad_norm": 1.6041675806045532, "learning_rate": 4.554055781551002e-05, "loss": 4.7372, "step": 3589 }, { "epoch": 0.193176926388291, "grad_norm": 2.490715503692627, "learning_rate": 4.55381484481509e-05, "loss": 4.5328, "step": 3590 }, { "epoch": 0.19323073611708996, "grad_norm": 0.9290887713432312, "learning_rate": 4.5535738493866736e-05, "loss": 4.7079, "step": 3591 }, { "epoch": 0.19328454584588894, "grad_norm": 1.0338002443313599, "learning_rate": 4.553332795272641e-05, "loss": 4.5339, "step": 3592 }, { "epoch": 0.1933383555746879, "grad_norm": 1.4183253049850464, "learning_rate": 4.5530916824798785e-05, "loss": 5.0211, "step": 3593 }, { "epoch": 0.19339216530348688, "grad_norm": 1.9542094469070435, "learning_rate": 4.552850511015279e-05, "loss": 4.6256, "step": 3594 }, { "epoch": 0.19344597503228583, "grad_norm": 1.4370158910751343, "learning_rate": 4.552609280885734e-05, "loss": 4.3019, "step": 3595 }, { "epoch": 0.19349978476108481, "grad_norm": 1.6065548658370972, "learning_rate": 4.552367992098135e-05, "loss": 4.5595, "step": 3596 }, { "epoch": 0.19355359448988377, "grad_norm": 1.203269362449646, "learning_rate": 4.552126644659379e-05, "loss": 4.9999, "step": 3597 }, { "epoch": 0.19360740421868275, "grad_norm": 1.7244950532913208, "learning_rate": 4.5518852385763643e-05, "loss": 4.4478, "step": 3598 }, { "epoch": 0.1936612139474817, "grad_norm": 1.7980380058288574, "learning_rate": 4.551643773855988e-05, "loss": 4.5925, "step": 3599 }, { "epoch": 0.19371502367628068, "grad_norm": 1.4785375595092773, "learning_rate": 4.5514022505051504e-05, "loss": 4.7864, "step": 3600 }, { "epoch": 0.19376883340507964, "grad_norm": 1.7280956506729126, "learning_rate": 4.5511606685307554e-05, "loss": 4.3132, "step": 3601 }, { "epoch": 0.1938226431338786, "grad_norm": 2.262080430984497, "learning_rate": 4.5509190279397044e-05, "loss": 4.39, "step": 3602 }, { "epoch": 0.19387645286267757, "grad_norm": 1.636059284210205, "learning_rate": 4.550677328738904e-05, "loss": 4.5613, "step": 3603 }, { "epoch": 0.19393026259147653, "grad_norm": 1.8715832233428955, "learning_rate": 4.550435570935261e-05, "loss": 4.2907, "step": 3604 }, { "epoch": 0.1939840723202755, "grad_norm": 1.7104547023773193, "learning_rate": 4.5501937545356844e-05, "loss": 4.5636, "step": 3605 }, { "epoch": 0.19403788204907446, "grad_norm": 1.3205105066299438, "learning_rate": 4.549951879547085e-05, "loss": 4.6906, "step": 3606 }, { "epoch": 0.19409169177787344, "grad_norm": 1.9593126773834229, "learning_rate": 4.549709945976375e-05, "loss": 4.19, "step": 3607 }, { "epoch": 0.1941455015066724, "grad_norm": 2.166144847869873, "learning_rate": 4.549467953830468e-05, "loss": 4.5958, "step": 3608 }, { "epoch": 0.19419931123547138, "grad_norm": 1.9486275911331177, "learning_rate": 4.5492259031162775e-05, "loss": 5.1376, "step": 3609 }, { "epoch": 0.19425312096427033, "grad_norm": 1.4094020128250122, "learning_rate": 4.5489837938407244e-05, "loss": 4.8311, "step": 3610 }, { "epoch": 0.1943069306930693, "grad_norm": 1.3046537637710571, "learning_rate": 4.548741626010724e-05, "loss": 4.5474, "step": 3611 }, { "epoch": 0.19436074042186827, "grad_norm": 2.294534683227539, "learning_rate": 4.5484993996332e-05, "loss": 4.3771, "step": 3612 }, { "epoch": 0.19441455015066725, "grad_norm": 1.5791306495666504, "learning_rate": 4.548257114715072e-05, "loss": 4.6316, "step": 3613 }, { "epoch": 0.1944683598794662, "grad_norm": 1.4074355363845825, "learning_rate": 4.548014771263265e-05, "loss": 4.6002, "step": 3614 }, { "epoch": 0.19452216960826518, "grad_norm": 1.858058214187622, "learning_rate": 4.547772369284704e-05, "loss": 4.3066, "step": 3615 }, { "epoch": 0.19457597933706414, "grad_norm": 2.193720579147339, "learning_rate": 4.5475299087863174e-05, "loss": 4.2342, "step": 3616 }, { "epoch": 0.19462978906586312, "grad_norm": 1.5752679109573364, "learning_rate": 4.547287389775032e-05, "loss": 4.6755, "step": 3617 }, { "epoch": 0.19468359879466207, "grad_norm": 1.4637479782104492, "learning_rate": 4.5470448122577806e-05, "loss": 4.6842, "step": 3618 }, { "epoch": 0.19473740852346105, "grad_norm": 1.9509861469268799, "learning_rate": 4.546802176241495e-05, "loss": 4.2682, "step": 3619 }, { "epoch": 0.19479121825226, "grad_norm": 1.452346920967102, "learning_rate": 4.546559481733107e-05, "loss": 4.7356, "step": 3620 }, { "epoch": 0.194845027981059, "grad_norm": 1.181291937828064, "learning_rate": 4.546316728739554e-05, "loss": 4.6751, "step": 3621 }, { "epoch": 0.19489883770985794, "grad_norm": 1.8179017305374146, "learning_rate": 4.546073917267773e-05, "loss": 4.4527, "step": 3622 }, { "epoch": 0.19495264743865692, "grad_norm": 1.290562629699707, "learning_rate": 4.545831047324703e-05, "loss": 4.9044, "step": 3623 }, { "epoch": 0.19500645716745588, "grad_norm": 1.245162010192871, "learning_rate": 4.5455881189172836e-05, "loss": 4.7341, "step": 3624 }, { "epoch": 0.19506026689625483, "grad_norm": 1.6162242889404297, "learning_rate": 4.5453451320524586e-05, "loss": 4.0634, "step": 3625 }, { "epoch": 0.1951140766250538, "grad_norm": 1.9866071939468384, "learning_rate": 4.545102086737171e-05, "loss": 4.3838, "step": 3626 }, { "epoch": 0.19516788635385277, "grad_norm": 2.004880905151367, "learning_rate": 4.544858982978366e-05, "loss": 4.7255, "step": 3627 }, { "epoch": 0.19522169608265175, "grad_norm": 1.1862339973449707, "learning_rate": 4.544615820782991e-05, "loss": 4.6662, "step": 3628 }, { "epoch": 0.1952755058114507, "grad_norm": 1.1209105253219604, "learning_rate": 4.544372600157996e-05, "loss": 4.7061, "step": 3629 }, { "epoch": 0.19532931554024968, "grad_norm": 2.5745604038238525, "learning_rate": 4.54412932111033e-05, "loss": 4.4307, "step": 3630 }, { "epoch": 0.19538312526904864, "grad_norm": 1.246907114982605, "learning_rate": 4.543885983646946e-05, "loss": 4.821, "step": 3631 }, { "epoch": 0.19543693499784762, "grad_norm": 1.3809698820114136, "learning_rate": 4.543642587774799e-05, "loss": 4.535, "step": 3632 }, { "epoch": 0.19549074472664657, "grad_norm": 1.1338461637496948, "learning_rate": 4.543399133500843e-05, "loss": 4.7334, "step": 3633 }, { "epoch": 0.19554455445544555, "grad_norm": 1.8951361179351807, "learning_rate": 4.543155620832036e-05, "loss": 4.2667, "step": 3634 }, { "epoch": 0.1955983641842445, "grad_norm": 1.6377828121185303, "learning_rate": 4.5429120497753365e-05, "loss": 4.4929, "step": 3635 }, { "epoch": 0.1956521739130435, "grad_norm": 1.3307985067367554, "learning_rate": 4.5426684203377055e-05, "loss": 4.9757, "step": 3636 }, { "epoch": 0.19570598364184244, "grad_norm": 1.4597996473312378, "learning_rate": 4.542424732526105e-05, "loss": 4.7106, "step": 3637 }, { "epoch": 0.19575979337064142, "grad_norm": 2.1200082302093506, "learning_rate": 4.542180986347499e-05, "loss": 4.9768, "step": 3638 }, { "epoch": 0.19581360309944038, "grad_norm": 1.0940150022506714, "learning_rate": 4.541937181808854e-05, "loss": 4.7365, "step": 3639 }, { "epoch": 0.19586741282823936, "grad_norm": 1.1661174297332764, "learning_rate": 4.5416933189171364e-05, "loss": 4.895, "step": 3640 }, { "epoch": 0.1959212225570383, "grad_norm": 1.6218724250793457, "learning_rate": 4.541449397679315e-05, "loss": 4.291, "step": 3641 }, { "epoch": 0.1959750322858373, "grad_norm": 1.9676792621612549, "learning_rate": 4.5412054181023605e-05, "loss": 4.5334, "step": 3642 }, { "epoch": 0.19602884201463625, "grad_norm": 2.0091609954833984, "learning_rate": 4.540961380193246e-05, "loss": 4.5486, "step": 3643 }, { "epoch": 0.19608265174343523, "grad_norm": 1.702095866203308, "learning_rate": 4.540717283958944e-05, "loss": 4.684, "step": 3644 }, { "epoch": 0.19613646147223418, "grad_norm": 1.5083401203155518, "learning_rate": 4.5404731294064314e-05, "loss": 4.6681, "step": 3645 }, { "epoch": 0.19619027120103313, "grad_norm": 2.2072298526763916, "learning_rate": 4.540228916542685e-05, "loss": 4.6177, "step": 3646 }, { "epoch": 0.19624408092983212, "grad_norm": 1.4000035524368286, "learning_rate": 4.539984645374683e-05, "loss": 4.5633, "step": 3647 }, { "epoch": 0.19629789065863107, "grad_norm": 1.1282302141189575, "learning_rate": 4.539740315909407e-05, "loss": 4.6204, "step": 3648 }, { "epoch": 0.19635170038743005, "grad_norm": 1.315675973892212, "learning_rate": 4.53949592815384e-05, "loss": 4.7332, "step": 3649 }, { "epoch": 0.196405510116229, "grad_norm": 1.8890628814697266, "learning_rate": 4.539251482114965e-05, "loss": 4.2478, "step": 3650 }, { "epoch": 0.19645931984502799, "grad_norm": 1.6767137050628662, "learning_rate": 4.5390069777997654e-05, "loss": 4.1925, "step": 3651 }, { "epoch": 0.19651312957382694, "grad_norm": 1.5371408462524414, "learning_rate": 4.538762415215233e-05, "loss": 4.4599, "step": 3652 }, { "epoch": 0.19656693930262592, "grad_norm": 2.013629674911499, "learning_rate": 4.538517794368353e-05, "loss": 4.8769, "step": 3653 }, { "epoch": 0.19662074903142487, "grad_norm": 1.566644310951233, "learning_rate": 4.538273115266118e-05, "loss": 4.7022, "step": 3654 }, { "epoch": 0.19667455876022386, "grad_norm": 2.4641523361206055, "learning_rate": 4.53802837791552e-05, "loss": 4.4016, "step": 3655 }, { "epoch": 0.1967283684890228, "grad_norm": 1.8990963697433472, "learning_rate": 4.537783582323552e-05, "loss": 4.8493, "step": 3656 }, { "epoch": 0.1967821782178218, "grad_norm": 1.9771947860717773, "learning_rate": 4.53753872849721e-05, "loss": 3.7477, "step": 3657 }, { "epoch": 0.19683598794662074, "grad_norm": 1.1647862195968628, "learning_rate": 4.5372938164434924e-05, "loss": 4.8335, "step": 3658 }, { "epoch": 0.19688979767541973, "grad_norm": 1.773905634880066, "learning_rate": 4.537048846169397e-05, "loss": 4.4842, "step": 3659 }, { "epoch": 0.19694360740421868, "grad_norm": 1.6117008924484253, "learning_rate": 4.536803817681924e-05, "loss": 4.7844, "step": 3660 }, { "epoch": 0.19699741713301766, "grad_norm": 1.9432824850082397, "learning_rate": 4.536558730988077e-05, "loss": 4.7139, "step": 3661 }, { "epoch": 0.19705122686181661, "grad_norm": 1.1271185874938965, "learning_rate": 4.536313586094858e-05, "loss": 4.6799, "step": 3662 }, { "epoch": 0.1971050365906156, "grad_norm": 1.88193678855896, "learning_rate": 4.536068383009275e-05, "loss": 4.2965, "step": 3663 }, { "epoch": 0.19715884631941455, "grad_norm": 1.5779749155044556, "learning_rate": 4.535823121738333e-05, "loss": 4.3844, "step": 3664 }, { "epoch": 0.19721265604821353, "grad_norm": 2.189443588256836, "learning_rate": 4.5355778022890425e-05, "loss": 4.4953, "step": 3665 }, { "epoch": 0.19726646577701248, "grad_norm": 1.0949891805648804, "learning_rate": 4.535332424668414e-05, "loss": 4.7713, "step": 3666 }, { "epoch": 0.19732027550581144, "grad_norm": 0.9775004386901855, "learning_rate": 4.535086988883458e-05, "loss": 4.621, "step": 3667 }, { "epoch": 0.19737408523461042, "grad_norm": 1.6219085454940796, "learning_rate": 4.534841494941191e-05, "loss": 4.2163, "step": 3668 }, { "epoch": 0.19742789496340937, "grad_norm": 2.3875539302825928, "learning_rate": 4.534595942848626e-05, "loss": 4.1925, "step": 3669 }, { "epoch": 0.19748170469220835, "grad_norm": 1.8338302373886108, "learning_rate": 4.534350332612781e-05, "loss": 4.6331, "step": 3670 }, { "epoch": 0.1975355144210073, "grad_norm": 2.6482651233673096, "learning_rate": 4.534104664240676e-05, "loss": 3.6956, "step": 3671 }, { "epoch": 0.1975893241498063, "grad_norm": 1.4796041250228882, "learning_rate": 4.533858937739332e-05, "loss": 4.9655, "step": 3672 }, { "epoch": 0.19764313387860524, "grad_norm": 1.681965708732605, "learning_rate": 4.533613153115768e-05, "loss": 4.5097, "step": 3673 }, { "epoch": 0.19769694360740422, "grad_norm": 2.522646188735962, "learning_rate": 4.5333673103770103e-05, "loss": 4.3281, "step": 3674 }, { "epoch": 0.19775075333620318, "grad_norm": 1.7418997287750244, "learning_rate": 4.5331214095300845e-05, "loss": 5.0007, "step": 3675 }, { "epoch": 0.19780456306500216, "grad_norm": 1.3335176706314087, "learning_rate": 4.532875450582017e-05, "loss": 4.9048, "step": 3676 }, { "epoch": 0.1978583727938011, "grad_norm": 2.0060572624206543, "learning_rate": 4.5326294335398366e-05, "loss": 4.5066, "step": 3677 }, { "epoch": 0.1979121825226001, "grad_norm": 2.3048698902130127, "learning_rate": 4.5323833584105746e-05, "loss": 4.5671, "step": 3678 }, { "epoch": 0.19796599225139905, "grad_norm": 2.228710889816284, "learning_rate": 4.532137225201263e-05, "loss": 4.4674, "step": 3679 }, { "epoch": 0.19801980198019803, "grad_norm": 1.287125825881958, "learning_rate": 4.531891033918935e-05, "loss": 4.6327, "step": 3680 }, { "epoch": 0.19807361170899698, "grad_norm": 2.0566465854644775, "learning_rate": 4.531644784570626e-05, "loss": 4.3733, "step": 3681 }, { "epoch": 0.19812742143779596, "grad_norm": 1.098467230796814, "learning_rate": 4.531398477163373e-05, "loss": 4.4476, "step": 3682 }, { "epoch": 0.19818123116659492, "grad_norm": 1.3639589548110962, "learning_rate": 4.5311521117042164e-05, "loss": 4.5551, "step": 3683 }, { "epoch": 0.1982350408953939, "grad_norm": 1.1765856742858887, "learning_rate": 4.530905688200196e-05, "loss": 4.8476, "step": 3684 }, { "epoch": 0.19828885062419285, "grad_norm": 2.019413471221924, "learning_rate": 4.530659206658353e-05, "loss": 4.1699, "step": 3685 }, { "epoch": 0.19834266035299183, "grad_norm": 1.9976234436035156, "learning_rate": 4.5304126670857314e-05, "loss": 4.6124, "step": 3686 }, { "epoch": 0.1983964700817908, "grad_norm": 1.940999984741211, "learning_rate": 4.530166069489377e-05, "loss": 4.5932, "step": 3687 }, { "epoch": 0.19845027981058974, "grad_norm": 1.2369391918182373, "learning_rate": 4.529919413876337e-05, "loss": 4.6813, "step": 3688 }, { "epoch": 0.19850408953938872, "grad_norm": 1.1923154592514038, "learning_rate": 4.5296727002536596e-05, "loss": 4.5881, "step": 3689 }, { "epoch": 0.19855789926818768, "grad_norm": 2.4398419857025146, "learning_rate": 4.529425928628396e-05, "loss": 4.4659, "step": 3690 }, { "epoch": 0.19861170899698666, "grad_norm": 1.8578494787216187, "learning_rate": 4.529179099007598e-05, "loss": 3.8949, "step": 3691 }, { "epoch": 0.1986655187257856, "grad_norm": 1.7927465438842773, "learning_rate": 4.528932211398319e-05, "loss": 4.8566, "step": 3692 }, { "epoch": 0.1987193284545846, "grad_norm": 2.1258597373962402, "learning_rate": 4.528685265807615e-05, "loss": 4.3569, "step": 3693 }, { "epoch": 0.19877313818338355, "grad_norm": 1.6142266988754272, "learning_rate": 4.5284382622425424e-05, "loss": 4.9769, "step": 3694 }, { "epoch": 0.19882694791218253, "grad_norm": 1.8518400192260742, "learning_rate": 4.52819120071016e-05, "loss": 4.1805, "step": 3695 }, { "epoch": 0.19888075764098148, "grad_norm": 0.8593434691429138, "learning_rate": 4.527944081217528e-05, "loss": 4.6965, "step": 3696 }, { "epoch": 0.19893456736978046, "grad_norm": 1.053521752357483, "learning_rate": 4.5276969037717085e-05, "loss": 4.7495, "step": 3697 }, { "epoch": 0.19898837709857942, "grad_norm": 1.464706540107727, "learning_rate": 4.527449668379766e-05, "loss": 4.5622, "step": 3698 }, { "epoch": 0.1990421868273784, "grad_norm": 1.8499501943588257, "learning_rate": 4.527202375048765e-05, "loss": 4.6437, "step": 3699 }, { "epoch": 0.19909599655617735, "grad_norm": 1.485766887664795, "learning_rate": 4.526955023785773e-05, "loss": 4.5651, "step": 3700 }, { "epoch": 0.19914980628497633, "grad_norm": 1.2219109535217285, "learning_rate": 4.526707614597858e-05, "loss": 4.5795, "step": 3701 }, { "epoch": 0.1992036160137753, "grad_norm": 1.6778700351715088, "learning_rate": 4.52646014749209e-05, "loss": 4.6942, "step": 3702 }, { "epoch": 0.19925742574257427, "grad_norm": 1.4831691980361938, "learning_rate": 4.526212622475542e-05, "loss": 4.7656, "step": 3703 }, { "epoch": 0.19931123547137322, "grad_norm": 1.5970916748046875, "learning_rate": 4.525965039555288e-05, "loss": 4.319, "step": 3704 }, { "epoch": 0.1993650452001722, "grad_norm": 2.1168596744537354, "learning_rate": 4.525717398738401e-05, "loss": 4.8992, "step": 3705 }, { "epoch": 0.19941885492897116, "grad_norm": 1.1427901983261108, "learning_rate": 4.52546970003196e-05, "loss": 4.7383, "step": 3706 }, { "epoch": 0.19947266465777014, "grad_norm": 1.6935961246490479, "learning_rate": 4.5252219434430424e-05, "loss": 4.8133, "step": 3707 }, { "epoch": 0.1995264743865691, "grad_norm": 1.2135926485061646, "learning_rate": 4.524974128978729e-05, "loss": 4.6416, "step": 3708 }, { "epoch": 0.19958028411536805, "grad_norm": 1.0388785600662231, "learning_rate": 4.524726256646102e-05, "loss": 4.7253, "step": 3709 }, { "epoch": 0.19963409384416703, "grad_norm": 1.1732861995697021, "learning_rate": 4.524478326452244e-05, "loss": 4.9482, "step": 3710 }, { "epoch": 0.19968790357296598, "grad_norm": 1.5327500104904175, "learning_rate": 4.524230338404241e-05, "loss": 4.6461, "step": 3711 }, { "epoch": 0.19974171330176496, "grad_norm": 1.5140438079833984, "learning_rate": 4.523982292509179e-05, "loss": 4.2734, "step": 3712 }, { "epoch": 0.19979552303056392, "grad_norm": 1.2474974393844604, "learning_rate": 4.5237341887741466e-05, "loss": 4.8848, "step": 3713 }, { "epoch": 0.1998493327593629, "grad_norm": 1.8337000608444214, "learning_rate": 4.5234860272062355e-05, "loss": 4.4545, "step": 3714 }, { "epoch": 0.19990314248816185, "grad_norm": 1.2998193502426147, "learning_rate": 4.5232378078125356e-05, "loss": 4.7575, "step": 3715 }, { "epoch": 0.19995695221696083, "grad_norm": 1.704888105392456, "learning_rate": 4.522989530600141e-05, "loss": 4.3257, "step": 3716 }, { "epoch": 0.20001076194575979, "grad_norm": 2.030160903930664, "learning_rate": 4.522741195576147e-05, "loss": 4.7841, "step": 3717 }, { "epoch": 0.20006457167455877, "grad_norm": 1.773424744606018, "learning_rate": 4.52249280274765e-05, "loss": 4.8589, "step": 3718 }, { "epoch": 0.20011838140335772, "grad_norm": 1.6929988861083984, "learning_rate": 4.522244352121748e-05, "loss": 4.411, "step": 3719 }, { "epoch": 0.2001721911321567, "grad_norm": 1.3820433616638184, "learning_rate": 4.521995843705543e-05, "loss": 4.7001, "step": 3720 }, { "epoch": 0.20022600086095566, "grad_norm": 1.1889058351516724, "learning_rate": 4.5217472775061346e-05, "loss": 4.6948, "step": 3721 }, { "epoch": 0.20027981058975464, "grad_norm": 1.8082585334777832, "learning_rate": 4.5214986535306264e-05, "loss": 5.0148, "step": 3722 }, { "epoch": 0.2003336203185536, "grad_norm": 1.8441294431686401, "learning_rate": 4.521249971786125e-05, "loss": 4.4907, "step": 3723 }, { "epoch": 0.20038743004735257, "grad_norm": 1.575441598892212, "learning_rate": 4.5210012322797346e-05, "loss": 5.0394, "step": 3724 }, { "epoch": 0.20044123977615153, "grad_norm": 1.848488688468933, "learning_rate": 4.5207524350185656e-05, "loss": 4.7257, "step": 3725 }, { "epoch": 0.2004950495049505, "grad_norm": 1.3168323040008545, "learning_rate": 4.5205035800097274e-05, "loss": 4.7407, "step": 3726 }, { "epoch": 0.20054885923374946, "grad_norm": 1.120757818222046, "learning_rate": 4.520254667260331e-05, "loss": 4.6511, "step": 3727 }, { "epoch": 0.20060266896254844, "grad_norm": 1.7078508138656616, "learning_rate": 4.520005696777489e-05, "loss": 4.7442, "step": 3728 }, { "epoch": 0.2006564786913474, "grad_norm": 2.2075085639953613, "learning_rate": 4.519756668568319e-05, "loss": 4.6677, "step": 3729 }, { "epoch": 0.20071028842014635, "grad_norm": 1.6059932708740234, "learning_rate": 4.5195075826399355e-05, "loss": 4.5484, "step": 3730 }, { "epoch": 0.20076409814894533, "grad_norm": 1.4892704486846924, "learning_rate": 4.519258438999458e-05, "loss": 4.8816, "step": 3731 }, { "epoch": 0.20081790787774428, "grad_norm": 1.2653758525848389, "learning_rate": 4.519009237654004e-05, "loss": 4.8248, "step": 3732 }, { "epoch": 0.20087171760654327, "grad_norm": 1.864336609840393, "learning_rate": 4.518759978610696e-05, "loss": 4.51, "step": 3733 }, { "epoch": 0.20092552733534222, "grad_norm": 1.7782710790634155, "learning_rate": 4.518510661876659e-05, "loss": 4.6625, "step": 3734 }, { "epoch": 0.2009793370641412, "grad_norm": 1.484006404876709, "learning_rate": 4.518261287459016e-05, "loss": 4.5796, "step": 3735 }, { "epoch": 0.20103314679294015, "grad_norm": 1.3934327363967896, "learning_rate": 4.5180118553648944e-05, "loss": 4.9064, "step": 3736 }, { "epoch": 0.20108695652173914, "grad_norm": 1.730388879776001, "learning_rate": 4.517762365601421e-05, "loss": 4.5622, "step": 3737 }, { "epoch": 0.2011407662505381, "grad_norm": 1.360932469367981, "learning_rate": 4.517512818175726e-05, "loss": 4.6217, "step": 3738 }, { "epoch": 0.20119457597933707, "grad_norm": 0.8662753105163574, "learning_rate": 4.517263213094942e-05, "loss": 4.6433, "step": 3739 }, { "epoch": 0.20124838570813602, "grad_norm": 1.034015417098999, "learning_rate": 4.517013550366201e-05, "loss": 4.5244, "step": 3740 }, { "epoch": 0.201302195436935, "grad_norm": 2.6440179347991943, "learning_rate": 4.5167638299966386e-05, "loss": 4.6681, "step": 3741 }, { "epoch": 0.20135600516573396, "grad_norm": 1.434453010559082, "learning_rate": 4.516514051993389e-05, "loss": 4.7367, "step": 3742 }, { "epoch": 0.20140981489453294, "grad_norm": 2.0324795246124268, "learning_rate": 4.5162642163635925e-05, "loss": 5.0317, "step": 3743 }, { "epoch": 0.2014636246233319, "grad_norm": 1.3006110191345215, "learning_rate": 4.516014323114387e-05, "loss": 4.5245, "step": 3744 }, { "epoch": 0.20151743435213088, "grad_norm": 1.8146779537200928, "learning_rate": 4.5157643722529154e-05, "loss": 4.5017, "step": 3745 }, { "epoch": 0.20157124408092983, "grad_norm": 1.7152739763259888, "learning_rate": 4.51551436378632e-05, "loss": 4.5816, "step": 3746 }, { "epoch": 0.2016250538097288, "grad_norm": 1.154386043548584, "learning_rate": 4.515264297721744e-05, "loss": 4.7377, "step": 3747 }, { "epoch": 0.20167886353852776, "grad_norm": 1.8330466747283936, "learning_rate": 4.5150141740663355e-05, "loss": 4.421, "step": 3748 }, { "epoch": 0.20173267326732675, "grad_norm": 1.4662634134292603, "learning_rate": 4.514763992827242e-05, "loss": 4.8951, "step": 3749 }, { "epoch": 0.2017864829961257, "grad_norm": 1.337834358215332, "learning_rate": 4.5145137540116126e-05, "loss": 4.567, "step": 3750 }, { "epoch": 0.20184029272492465, "grad_norm": 1.644469976425171, "learning_rate": 4.514263457626598e-05, "loss": 4.8006, "step": 3751 }, { "epoch": 0.20189410245372363, "grad_norm": 1.229084849357605, "learning_rate": 4.514013103679352e-05, "loss": 4.6949, "step": 3752 }, { "epoch": 0.2019479121825226, "grad_norm": 2.1658098697662354, "learning_rate": 4.513762692177028e-05, "loss": 4.2743, "step": 3753 }, { "epoch": 0.20200172191132157, "grad_norm": 1.7648924589157104, "learning_rate": 4.5135122231267826e-05, "loss": 4.701, "step": 3754 }, { "epoch": 0.20205553164012052, "grad_norm": 1.1370867490768433, "learning_rate": 4.5132616965357744e-05, "loss": 4.8355, "step": 3755 }, { "epoch": 0.2021093413689195, "grad_norm": 1.4502506256103516, "learning_rate": 4.513011112411161e-05, "loss": 4.9057, "step": 3756 }, { "epoch": 0.20216315109771846, "grad_norm": 1.7653851509094238, "learning_rate": 4.5127604707601054e-05, "loss": 4.3397, "step": 3757 }, { "epoch": 0.20221696082651744, "grad_norm": 1.1245393753051758, "learning_rate": 4.512509771589768e-05, "loss": 4.7983, "step": 3758 }, { "epoch": 0.2022707705553164, "grad_norm": 1.2724953889846802, "learning_rate": 4.512259014907315e-05, "loss": 4.6159, "step": 3759 }, { "epoch": 0.20232458028411537, "grad_norm": 1.624946117401123, "learning_rate": 4.512008200719912e-05, "loss": 4.4453, "step": 3760 }, { "epoch": 0.20237839001291433, "grad_norm": 1.9009603261947632, "learning_rate": 4.511757329034726e-05, "loss": 4.3194, "step": 3761 }, { "epoch": 0.2024321997417133, "grad_norm": 1.4574071168899536, "learning_rate": 4.511506399858927e-05, "loss": 4.5238, "step": 3762 }, { "epoch": 0.20248600947051226, "grad_norm": 1.8433858156204224, "learning_rate": 4.5112554131996844e-05, "loss": 4.376, "step": 3763 }, { "epoch": 0.20253981919931124, "grad_norm": 1.437110185623169, "learning_rate": 4.511004369064172e-05, "loss": 4.7802, "step": 3764 }, { "epoch": 0.2025936289281102, "grad_norm": 1.49800705909729, "learning_rate": 4.510753267459564e-05, "loss": 4.4035, "step": 3765 }, { "epoch": 0.20264743865690918, "grad_norm": 1.7637933492660522, "learning_rate": 4.510502108393037e-05, "loss": 4.3791, "step": 3766 }, { "epoch": 0.20270124838570813, "grad_norm": 1.8465583324432373, "learning_rate": 4.5102508918717656e-05, "loss": 4.8572, "step": 3767 }, { "epoch": 0.20275505811450711, "grad_norm": 1.3294811248779297, "learning_rate": 4.509999617902931e-05, "loss": 4.6559, "step": 3768 }, { "epoch": 0.20280886784330607, "grad_norm": 1.3615460395812988, "learning_rate": 4.509748286493714e-05, "loss": 4.6363, "step": 3769 }, { "epoch": 0.20286267757210505, "grad_norm": 1.1458548307418823, "learning_rate": 4.5094968976512965e-05, "loss": 4.7261, "step": 3770 }, { "epoch": 0.202916487300904, "grad_norm": 1.6350151300430298, "learning_rate": 4.509245451382862e-05, "loss": 4.9654, "step": 3771 }, { "epoch": 0.20297029702970298, "grad_norm": 1.0250648260116577, "learning_rate": 4.5089939476955975e-05, "loss": 4.5735, "step": 3772 }, { "epoch": 0.20302410675850194, "grad_norm": 1.3440096378326416, "learning_rate": 4.508742386596689e-05, "loss": 4.692, "step": 3773 }, { "epoch": 0.2030779164873009, "grad_norm": 1.0450875759124756, "learning_rate": 4.508490768093326e-05, "loss": 4.6377, "step": 3774 }, { "epoch": 0.20313172621609987, "grad_norm": 1.4286755323410034, "learning_rate": 4.5082390921927e-05, "loss": 4.8393, "step": 3775 }, { "epoch": 0.20318553594489883, "grad_norm": 1.4557392597198486, "learning_rate": 4.507987358902002e-05, "loss": 4.3328, "step": 3776 }, { "epoch": 0.2032393456736978, "grad_norm": 1.0869988203048706, "learning_rate": 4.507735568228425e-05, "loss": 4.9457, "step": 3777 }, { "epoch": 0.20329315540249676, "grad_norm": 1.781422734260559, "learning_rate": 4.5074837201791666e-05, "loss": 4.4469, "step": 3778 }, { "epoch": 0.20334696513129574, "grad_norm": 1.263002872467041, "learning_rate": 4.507231814761423e-05, "loss": 4.5751, "step": 3779 }, { "epoch": 0.2034007748600947, "grad_norm": 1.5109549760818481, "learning_rate": 4.5069798519823924e-05, "loss": 4.8597, "step": 3780 }, { "epoch": 0.20345458458889368, "grad_norm": 0.8413761258125305, "learning_rate": 4.506727831849276e-05, "loss": 4.9156, "step": 3781 }, { "epoch": 0.20350839431769263, "grad_norm": 1.0038959980010986, "learning_rate": 4.506475754369276e-05, "loss": 4.8711, "step": 3782 }, { "epoch": 0.2035622040464916, "grad_norm": 1.707809567451477, "learning_rate": 4.506223619549595e-05, "loss": 4.2676, "step": 3783 }, { "epoch": 0.20361601377529057, "grad_norm": 1.8165991306304932, "learning_rate": 4.5059714273974396e-05, "loss": 4.671, "step": 3784 }, { "epoch": 0.20366982350408955, "grad_norm": 0.9570227265357971, "learning_rate": 4.505719177920016e-05, "loss": 4.5986, "step": 3785 }, { "epoch": 0.2037236332328885, "grad_norm": 1.9366697072982788, "learning_rate": 4.5054668711245326e-05, "loss": 4.4252, "step": 3786 }, { "epoch": 0.20377744296168748, "grad_norm": 1.2948758602142334, "learning_rate": 4.505214507018201e-05, "loss": 4.8159, "step": 3787 }, { "epoch": 0.20383125269048644, "grad_norm": 1.696933388710022, "learning_rate": 4.504962085608232e-05, "loss": 5.0797, "step": 3788 }, { "epoch": 0.20388506241928542, "grad_norm": 2.245551347732544, "learning_rate": 4.504709606901839e-05, "loss": 4.5613, "step": 3789 }, { "epoch": 0.20393887214808437, "grad_norm": 1.4328030347824097, "learning_rate": 4.5044570709062377e-05, "loss": 4.7822, "step": 3790 }, { "epoch": 0.20399268187688335, "grad_norm": 1.5778518915176392, "learning_rate": 4.5042044776286445e-05, "loss": 4.5943, "step": 3791 }, { "epoch": 0.2040464916056823, "grad_norm": 2.1159305572509766, "learning_rate": 4.503951827076278e-05, "loss": 4.8701, "step": 3792 }, { "epoch": 0.2041003013344813, "grad_norm": 1.5692009925842285, "learning_rate": 4.503699119256358e-05, "loss": 4.9037, "step": 3793 }, { "epoch": 0.20415411106328024, "grad_norm": 1.1747517585754395, "learning_rate": 4.5034463541761076e-05, "loss": 4.7111, "step": 3794 }, { "epoch": 0.2042079207920792, "grad_norm": 1.208268165588379, "learning_rate": 4.5031935318427475e-05, "loss": 4.4345, "step": 3795 }, { "epoch": 0.20426173052087818, "grad_norm": 1.8696500062942505, "learning_rate": 4.502940652263505e-05, "loss": 4.3692, "step": 3796 }, { "epoch": 0.20431554024967713, "grad_norm": 1.0752791166305542, "learning_rate": 4.502687715445606e-05, "loss": 4.4603, "step": 3797 }, { "epoch": 0.2043693499784761, "grad_norm": 0.9977098703384399, "learning_rate": 4.502434721396279e-05, "loss": 4.6649, "step": 3798 }, { "epoch": 0.20442315970727507, "grad_norm": 1.7299225330352783, "learning_rate": 4.502181670122753e-05, "loss": 4.7978, "step": 3799 }, { "epoch": 0.20447696943607405, "grad_norm": 1.5279444456100464, "learning_rate": 4.50192856163226e-05, "loss": 4.8536, "step": 3800 }, { "epoch": 0.204530779164873, "grad_norm": 1.6362076997756958, "learning_rate": 4.501675395932034e-05, "loss": 4.7161, "step": 3801 }, { "epoch": 0.20458458889367198, "grad_norm": 0.9345262050628662, "learning_rate": 4.501422173029309e-05, "loss": 4.5358, "step": 3802 }, { "epoch": 0.20463839862247094, "grad_norm": 1.7518342733383179, "learning_rate": 4.501168892931321e-05, "loss": 4.8598, "step": 3803 }, { "epoch": 0.20469220835126992, "grad_norm": 2.0881335735321045, "learning_rate": 4.500915555645308e-05, "loss": 4.0827, "step": 3804 }, { "epoch": 0.20474601808006887, "grad_norm": 1.5086098909378052, "learning_rate": 4.500662161178512e-05, "loss": 4.5274, "step": 3805 }, { "epoch": 0.20479982780886785, "grad_norm": 2.0980498790740967, "learning_rate": 4.5004087095381706e-05, "loss": 3.9924, "step": 3806 }, { "epoch": 0.2048536375376668, "grad_norm": 1.8327417373657227, "learning_rate": 4.50015520073153e-05, "loss": 4.6321, "step": 3807 }, { "epoch": 0.2049074472664658, "grad_norm": 1.7750316858291626, "learning_rate": 4.499901634765833e-05, "loss": 4.3169, "step": 3808 }, { "epoch": 0.20496125699526474, "grad_norm": 1.6743671894073486, "learning_rate": 4.499648011648327e-05, "loss": 4.9712, "step": 3809 }, { "epoch": 0.20501506672406372, "grad_norm": 1.6179825067520142, "learning_rate": 4.4993943313862584e-05, "loss": 4.4619, "step": 3810 }, { "epoch": 0.20506887645286268, "grad_norm": 1.3372997045516968, "learning_rate": 4.499140593986878e-05, "loss": 4.5036, "step": 3811 }, { "epoch": 0.20512268618166166, "grad_norm": 2.0310018062591553, "learning_rate": 4.4988867994574366e-05, "loss": 4.5204, "step": 3812 }, { "epoch": 0.2051764959104606, "grad_norm": 2.685824155807495, "learning_rate": 4.498632947805187e-05, "loss": 4.3114, "step": 3813 }, { "epoch": 0.2052303056392596, "grad_norm": 1.951390027999878, "learning_rate": 4.498379039037382e-05, "loss": 4.4579, "step": 3814 }, { "epoch": 0.20528411536805855, "grad_norm": 1.6444859504699707, "learning_rate": 4.4981250731612815e-05, "loss": 4.5306, "step": 3815 }, { "epoch": 0.2053379250968575, "grad_norm": 1.9632619619369507, "learning_rate": 4.4978710501841384e-05, "loss": 4.5454, "step": 3816 }, { "epoch": 0.20539173482565648, "grad_norm": 2.118239641189575, "learning_rate": 4.497616970113216e-05, "loss": 4.4492, "step": 3817 }, { "epoch": 0.20544554455445543, "grad_norm": 1.5615946054458618, "learning_rate": 4.497362832955773e-05, "loss": 4.8097, "step": 3818 }, { "epoch": 0.20549935428325442, "grad_norm": 1.934550166130066, "learning_rate": 4.497108638719072e-05, "loss": 4.4906, "step": 3819 }, { "epoch": 0.20555316401205337, "grad_norm": 1.8931736946105957, "learning_rate": 4.496854387410379e-05, "loss": 4.6003, "step": 3820 }, { "epoch": 0.20560697374085235, "grad_norm": 1.4028571844100952, "learning_rate": 4.496600079036957e-05, "loss": 4.6108, "step": 3821 }, { "epoch": 0.2056607834696513, "grad_norm": 1.5839159488677979, "learning_rate": 4.496345713606076e-05, "loss": 4.7192, "step": 3822 }, { "epoch": 0.20571459319845029, "grad_norm": 1.4966390132904053, "learning_rate": 4.496091291125003e-05, "loss": 4.587, "step": 3823 }, { "epoch": 0.20576840292724924, "grad_norm": 1.4584048986434937, "learning_rate": 4.4958368116010106e-05, "loss": 4.6346, "step": 3824 }, { "epoch": 0.20582221265604822, "grad_norm": 0.9556276798248291, "learning_rate": 4.49558227504137e-05, "loss": 4.6034, "step": 3825 }, { "epoch": 0.20587602238484717, "grad_norm": 1.3726173639297485, "learning_rate": 4.4953276814533557e-05, "loss": 4.6872, "step": 3826 }, { "epoch": 0.20592983211364616, "grad_norm": 1.7391157150268555, "learning_rate": 4.495073030844243e-05, "loss": 4.2958, "step": 3827 }, { "epoch": 0.2059836418424451, "grad_norm": 1.5243819952011108, "learning_rate": 4.494818323221309e-05, "loss": 4.1916, "step": 3828 }, { "epoch": 0.2060374515712441, "grad_norm": 2.112445116043091, "learning_rate": 4.494563558591833e-05, "loss": 4.2438, "step": 3829 }, { "epoch": 0.20609126130004304, "grad_norm": 1.8843505382537842, "learning_rate": 4.494308736963095e-05, "loss": 4.4887, "step": 3830 }, { "epoch": 0.20614507102884203, "grad_norm": 1.1849291324615479, "learning_rate": 4.494053858342378e-05, "loss": 4.6698, "step": 3831 }, { "epoch": 0.20619888075764098, "grad_norm": 1.3705588579177856, "learning_rate": 4.493798922736964e-05, "loss": 4.7835, "step": 3832 }, { "epoch": 0.20625269048643996, "grad_norm": 1.0417580604553223, "learning_rate": 4.49354393015414e-05, "loss": 4.7949, "step": 3833 }, { "epoch": 0.2063065002152389, "grad_norm": 0.9837992191314697, "learning_rate": 4.493288880601193e-05, "loss": 4.7739, "step": 3834 }, { "epoch": 0.2063603099440379, "grad_norm": 1.6409305334091187, "learning_rate": 4.493033774085411e-05, "loss": 4.5278, "step": 3835 }, { "epoch": 0.20641411967283685, "grad_norm": 1.75767183303833, "learning_rate": 4.492778610614083e-05, "loss": 5.0379, "step": 3836 }, { "epoch": 0.2064679294016358, "grad_norm": 1.8271639347076416, "learning_rate": 4.492523390194504e-05, "loss": 4.5692, "step": 3837 }, { "epoch": 0.20652173913043478, "grad_norm": 1.3599921464920044, "learning_rate": 4.492268112833965e-05, "loss": 4.9443, "step": 3838 }, { "epoch": 0.20657554885923374, "grad_norm": 1.6613600254058838, "learning_rate": 4.492012778539762e-05, "loss": 4.0726, "step": 3839 }, { "epoch": 0.20662935858803272, "grad_norm": 2.1701624393463135, "learning_rate": 4.491757387319192e-05, "loss": 4.3924, "step": 3840 }, { "epoch": 0.20668316831683167, "grad_norm": 2.0690951347351074, "learning_rate": 4.491501939179552e-05, "loss": 4.8636, "step": 3841 }, { "epoch": 0.20673697804563065, "grad_norm": 2.1718733310699463, "learning_rate": 4.4912464341281435e-05, "loss": 4.5218, "step": 3842 }, { "epoch": 0.2067907877744296, "grad_norm": 1.5188779830932617, "learning_rate": 4.490990872172268e-05, "loss": 4.7586, "step": 3843 }, { "epoch": 0.2068445975032286, "grad_norm": 1.6828874349594116, "learning_rate": 4.490735253319229e-05, "loss": 4.8101, "step": 3844 }, { "epoch": 0.20689840723202754, "grad_norm": 1.3604850769042969, "learning_rate": 4.49047957757633e-05, "loss": 4.8904, "step": 3845 }, { "epoch": 0.20695221696082652, "grad_norm": 1.480628490447998, "learning_rate": 4.490223844950879e-05, "loss": 4.9248, "step": 3846 }, { "epoch": 0.20700602668962548, "grad_norm": 1.720157265663147, "learning_rate": 4.489968055450183e-05, "loss": 4.5054, "step": 3847 }, { "epoch": 0.20705983641842446, "grad_norm": 1.3022217750549316, "learning_rate": 4.489712209081553e-05, "loss": 4.6399, "step": 3848 }, { "epoch": 0.2071136461472234, "grad_norm": 2.055040121078491, "learning_rate": 4.4894563058523e-05, "loss": 4.1828, "step": 3849 }, { "epoch": 0.2071674558760224, "grad_norm": 1.2166820764541626, "learning_rate": 4.489200345769736e-05, "loss": 4.9065, "step": 3850 }, { "epoch": 0.20722126560482135, "grad_norm": 1.443855881690979, "learning_rate": 4.488944328841177e-05, "loss": 4.9307, "step": 3851 }, { "epoch": 0.20727507533362033, "grad_norm": 1.2335742712020874, "learning_rate": 4.488688255073938e-05, "loss": 4.6128, "step": 3852 }, { "epoch": 0.20732888506241928, "grad_norm": 1.9024293422698975, "learning_rate": 4.488432124475339e-05, "loss": 4.4195, "step": 3853 }, { "epoch": 0.20738269479121826, "grad_norm": 2.3293700218200684, "learning_rate": 4.488175937052697e-05, "loss": 4.4428, "step": 3854 }, { "epoch": 0.20743650452001722, "grad_norm": 1.7778109312057495, "learning_rate": 4.487919692813335e-05, "loss": 4.6994, "step": 3855 }, { "epoch": 0.2074903142488162, "grad_norm": 1.7195996046066284, "learning_rate": 4.487663391764574e-05, "loss": 4.7964, "step": 3856 }, { "epoch": 0.20754412397761515, "grad_norm": 1.9629369974136353, "learning_rate": 4.4874070339137405e-05, "loss": 4.5793, "step": 3857 }, { "epoch": 0.2075979337064141, "grad_norm": 1.5653340816497803, "learning_rate": 4.4871506192681586e-05, "loss": 4.7136, "step": 3858 }, { "epoch": 0.2076517434352131, "grad_norm": 1.8602514266967773, "learning_rate": 4.4868941478351576e-05, "loss": 5.0007, "step": 3859 }, { "epoch": 0.20770555316401204, "grad_norm": 0.960328996181488, "learning_rate": 4.486637619622065e-05, "loss": 4.7198, "step": 3860 }, { "epoch": 0.20775936289281102, "grad_norm": 1.7476598024368286, "learning_rate": 4.4863810346362136e-05, "loss": 4.6725, "step": 3861 }, { "epoch": 0.20781317262160998, "grad_norm": 1.676350712776184, "learning_rate": 4.486124392884935e-05, "loss": 4.5482, "step": 3862 }, { "epoch": 0.20786698235040896, "grad_norm": 2.697690486907959, "learning_rate": 4.485867694375563e-05, "loss": 4.5551, "step": 3863 }, { "epoch": 0.2079207920792079, "grad_norm": 1.0867005586624146, "learning_rate": 4.485610939115433e-05, "loss": 4.7874, "step": 3864 }, { "epoch": 0.2079746018080069, "grad_norm": 1.065238356590271, "learning_rate": 4.485354127111884e-05, "loss": 4.5758, "step": 3865 }, { "epoch": 0.20802841153680585, "grad_norm": 1.5977987051010132, "learning_rate": 4.485097258372254e-05, "loss": 4.489, "step": 3866 }, { "epoch": 0.20808222126560483, "grad_norm": 2.0167574882507324, "learning_rate": 4.484840332903883e-05, "loss": 4.4327, "step": 3867 }, { "epoch": 0.20813603099440378, "grad_norm": 2.0835840702056885, "learning_rate": 4.484583350714114e-05, "loss": 4.4017, "step": 3868 }, { "epoch": 0.20818984072320276, "grad_norm": 2.0968871116638184, "learning_rate": 4.4843263118102905e-05, "loss": 4.3012, "step": 3869 }, { "epoch": 0.20824365045200172, "grad_norm": 1.7275452613830566, "learning_rate": 4.484069216199759e-05, "loss": 4.6042, "step": 3870 }, { "epoch": 0.2082974601808007, "grad_norm": 3.1221437454223633, "learning_rate": 4.483812063889866e-05, "loss": 4.3264, "step": 3871 }, { "epoch": 0.20835126990959965, "grad_norm": 0.8837807178497314, "learning_rate": 4.483554854887959e-05, "loss": 4.7411, "step": 3872 }, { "epoch": 0.20840507963839863, "grad_norm": 0.9900106191635132, "learning_rate": 4.4832975892013894e-05, "loss": 4.5962, "step": 3873 }, { "epoch": 0.2084588893671976, "grad_norm": 1.602270483970642, "learning_rate": 4.48304026683751e-05, "loss": 4.9751, "step": 3874 }, { "epoch": 0.20851269909599657, "grad_norm": 1.7572643756866455, "learning_rate": 4.4827828878036726e-05, "loss": 4.1171, "step": 3875 }, { "epoch": 0.20856650882479552, "grad_norm": 1.6244065761566162, "learning_rate": 4.482525452107235e-05, "loss": 4.5343, "step": 3876 }, { "epoch": 0.2086203185535945, "grad_norm": 1.282395839691162, "learning_rate": 4.48226795975555e-05, "loss": 4.8369, "step": 3877 }, { "epoch": 0.20867412828239346, "grad_norm": 0.9403182864189148, "learning_rate": 4.48201041075598e-05, "loss": 4.4658, "step": 3878 }, { "epoch": 0.2087279380111924, "grad_norm": 1.1202685832977295, "learning_rate": 4.481752805115883e-05, "loss": 5.0154, "step": 3879 }, { "epoch": 0.2087817477399914, "grad_norm": 1.8294156789779663, "learning_rate": 4.481495142842621e-05, "loss": 4.4471, "step": 3880 }, { "epoch": 0.20883555746879034, "grad_norm": 0.8718909621238708, "learning_rate": 4.481237423943558e-05, "loss": 4.7494, "step": 3881 }, { "epoch": 0.20888936719758933, "grad_norm": 1.771908164024353, "learning_rate": 4.480979648426058e-05, "loss": 4.773, "step": 3882 }, { "epoch": 0.20894317692638828, "grad_norm": 2.3532330989837646, "learning_rate": 4.4807218162974875e-05, "loss": 4.8778, "step": 3883 }, { "epoch": 0.20899698665518726, "grad_norm": 1.3406792879104614, "learning_rate": 4.480463927565215e-05, "loss": 4.2942, "step": 3884 }, { "epoch": 0.20905079638398621, "grad_norm": 1.8137043714523315, "learning_rate": 4.4802059822366105e-05, "loss": 4.4502, "step": 3885 }, { "epoch": 0.2091046061127852, "grad_norm": 1.5614581108093262, "learning_rate": 4.479947980319046e-05, "loss": 4.7637, "step": 3886 }, { "epoch": 0.20915841584158415, "grad_norm": 0.8754671216011047, "learning_rate": 4.4796899218198915e-05, "loss": 4.7173, "step": 3887 }, { "epoch": 0.20921222557038313, "grad_norm": 2.081392526626587, "learning_rate": 4.4794318067465254e-05, "loss": 4.577, "step": 3888 }, { "epoch": 0.20926603529918208, "grad_norm": 2.0357632637023926, "learning_rate": 4.4791736351063225e-05, "loss": 4.5813, "step": 3889 }, { "epoch": 0.20931984502798107, "grad_norm": 1.917312502861023, "learning_rate": 4.4789154069066594e-05, "loss": 4.7497, "step": 3890 }, { "epoch": 0.20937365475678002, "grad_norm": 1.3846744298934937, "learning_rate": 4.4786571221549175e-05, "loss": 4.6082, "step": 3891 }, { "epoch": 0.209427464485579, "grad_norm": 0.9962999820709229, "learning_rate": 4.478398780858477e-05, "loss": 4.662, "step": 3892 }, { "epoch": 0.20948127421437795, "grad_norm": 1.4459266662597656, "learning_rate": 4.478140383024721e-05, "loss": 4.6197, "step": 3893 }, { "epoch": 0.20953508394317694, "grad_norm": 1.2046396732330322, "learning_rate": 4.477881928661032e-05, "loss": 4.6603, "step": 3894 }, { "epoch": 0.2095888936719759, "grad_norm": 2.1423568725585938, "learning_rate": 4.477623417774798e-05, "loss": 4.6197, "step": 3895 }, { "epoch": 0.20964270340077487, "grad_norm": 0.9908066987991333, "learning_rate": 4.4773648503734064e-05, "loss": 4.6374, "step": 3896 }, { "epoch": 0.20969651312957382, "grad_norm": 1.0002706050872803, "learning_rate": 4.477106226464245e-05, "loss": 4.7039, "step": 3897 }, { "epoch": 0.2097503228583728, "grad_norm": 1.3043931722640991, "learning_rate": 4.476847546054707e-05, "loss": 4.6752, "step": 3898 }, { "epoch": 0.20980413258717176, "grad_norm": 1.5150254964828491, "learning_rate": 4.476588809152181e-05, "loss": 4.5626, "step": 3899 }, { "epoch": 0.20985794231597074, "grad_norm": 2.311502695083618, "learning_rate": 4.476330015764064e-05, "loss": 4.2965, "step": 3900 }, { "epoch": 0.2099117520447697, "grad_norm": 1.6193363666534424, "learning_rate": 4.4760711658977515e-05, "loss": 4.5699, "step": 3901 }, { "epoch": 0.20996556177356865, "grad_norm": 1.8088843822479248, "learning_rate": 4.47581225956064e-05, "loss": 4.6149, "step": 3902 }, { "epoch": 0.21001937150236763, "grad_norm": 1.8373113870620728, "learning_rate": 4.475553296760129e-05, "loss": 4.4941, "step": 3903 }, { "epoch": 0.21007318123116658, "grad_norm": 1.586232304573059, "learning_rate": 4.475294277503617e-05, "loss": 4.6213, "step": 3904 }, { "epoch": 0.21012699095996556, "grad_norm": 1.7772740125656128, "learning_rate": 4.4750352017985084e-05, "loss": 5.0178, "step": 3905 }, { "epoch": 0.21018080068876452, "grad_norm": 1.7013152837753296, "learning_rate": 4.474776069652206e-05, "loss": 4.4388, "step": 3906 }, { "epoch": 0.2102346104175635, "grad_norm": 0.9159955382347107, "learning_rate": 4.474516881072114e-05, "loss": 4.3893, "step": 3907 }, { "epoch": 0.21028842014636245, "grad_norm": 1.1182103157043457, "learning_rate": 4.474257636065641e-05, "loss": 4.7642, "step": 3908 }, { "epoch": 0.21034222987516143, "grad_norm": 2.4405839443206787, "learning_rate": 4.4739983346401946e-05, "loss": 4.0725, "step": 3909 }, { "epoch": 0.2103960396039604, "grad_norm": 1.349387288093567, "learning_rate": 4.473738976803186e-05, "loss": 4.5778, "step": 3910 }, { "epoch": 0.21044984933275937, "grad_norm": 2.4659552574157715, "learning_rate": 4.473479562562026e-05, "loss": 4.1938, "step": 3911 }, { "epoch": 0.21050365906155832, "grad_norm": 1.9479882717132568, "learning_rate": 4.473220091924128e-05, "loss": 4.5164, "step": 3912 }, { "epoch": 0.2105574687903573, "grad_norm": 1.5944041013717651, "learning_rate": 4.472960564896907e-05, "loss": 4.8222, "step": 3913 }, { "epoch": 0.21061127851915626, "grad_norm": 1.4502670764923096, "learning_rate": 4.472700981487779e-05, "loss": 4.754, "step": 3914 }, { "epoch": 0.21066508824795524, "grad_norm": 1.0819813013076782, "learning_rate": 4.472441341704164e-05, "loss": 4.8579, "step": 3915 }, { "epoch": 0.2107188979767542, "grad_norm": 1.4549367427825928, "learning_rate": 4.472181645553481e-05, "loss": 4.6299, "step": 3916 }, { "epoch": 0.21077270770555318, "grad_norm": 2.0840489864349365, "learning_rate": 4.47192189304315e-05, "loss": 4.3799, "step": 3917 }, { "epoch": 0.21082651743435213, "grad_norm": 1.7885690927505493, "learning_rate": 4.4716620841805954e-05, "loss": 4.5026, "step": 3918 }, { "epoch": 0.2108803271631511, "grad_norm": 1.8406405448913574, "learning_rate": 4.471402218973242e-05, "loss": 4.5714, "step": 3919 }, { "epoch": 0.21093413689195006, "grad_norm": 1.2377413511276245, "learning_rate": 4.4711422974285154e-05, "loss": 4.2379, "step": 3920 }, { "epoch": 0.21098794662074905, "grad_norm": 1.4389305114746094, "learning_rate": 4.4708823195538434e-05, "loss": 4.4393, "step": 3921 }, { "epoch": 0.211041756349548, "grad_norm": 1.307868480682373, "learning_rate": 4.470622285356656e-05, "loss": 4.3405, "step": 3922 }, { "epoch": 0.21109556607834695, "grad_norm": 1.7447518110275269, "learning_rate": 4.470362194844384e-05, "loss": 4.5545, "step": 3923 }, { "epoch": 0.21114937580714593, "grad_norm": 0.933347225189209, "learning_rate": 4.470102048024461e-05, "loss": 4.9371, "step": 3924 }, { "epoch": 0.2112031855359449, "grad_norm": 1.8225339651107788, "learning_rate": 4.469841844904319e-05, "loss": 4.7997, "step": 3925 }, { "epoch": 0.21125699526474387, "grad_norm": 1.7400392293930054, "learning_rate": 4.469581585491396e-05, "loss": 4.5948, "step": 3926 }, { "epoch": 0.21131080499354282, "grad_norm": 1.536765456199646, "learning_rate": 4.469321269793128e-05, "loss": 4.8837, "step": 3927 }, { "epoch": 0.2113646147223418, "grad_norm": 1.7407633066177368, "learning_rate": 4.469060897816957e-05, "loss": 4.5282, "step": 3928 }, { "epoch": 0.21141842445114076, "grad_norm": 1.4254714250564575, "learning_rate": 4.46880046957032e-05, "loss": 4.806, "step": 3929 }, { "epoch": 0.21147223417993974, "grad_norm": 1.315954566001892, "learning_rate": 4.4685399850606615e-05, "loss": 4.7032, "step": 3930 }, { "epoch": 0.2115260439087387, "grad_norm": 1.332440733909607, "learning_rate": 4.468279444295425e-05, "loss": 4.5527, "step": 3931 }, { "epoch": 0.21157985363753767, "grad_norm": 2.191561460494995, "learning_rate": 4.468018847282056e-05, "loss": 4.5479, "step": 3932 }, { "epoch": 0.21163366336633663, "grad_norm": 1.7359145879745483, "learning_rate": 4.467758194028001e-05, "loss": 4.287, "step": 3933 }, { "epoch": 0.2116874730951356, "grad_norm": 1.5825375318527222, "learning_rate": 4.46749748454071e-05, "loss": 4.5847, "step": 3934 }, { "epoch": 0.21174128282393456, "grad_norm": 1.4724222421646118, "learning_rate": 4.4672367188276335e-05, "loss": 4.9969, "step": 3935 }, { "epoch": 0.21179509255273354, "grad_norm": 2.242964744567871, "learning_rate": 4.4669758968962224e-05, "loss": 4.7055, "step": 3936 }, { "epoch": 0.2118489022815325, "grad_norm": 1.3183534145355225, "learning_rate": 4.46671501875393e-05, "loss": 4.6211, "step": 3937 }, { "epoch": 0.21190271201033148, "grad_norm": 1.5334221124649048, "learning_rate": 4.466454084408214e-05, "loss": 4.6694, "step": 3938 }, { "epoch": 0.21195652173913043, "grad_norm": 1.6188191175460815, "learning_rate": 4.466193093866527e-05, "loss": 4.569, "step": 3939 }, { "epoch": 0.2120103314679294, "grad_norm": 1.1765778064727783, "learning_rate": 4.4659320471363314e-05, "loss": 4.784, "step": 3940 }, { "epoch": 0.21206414119672837, "grad_norm": 1.685043454170227, "learning_rate": 4.465670944225086e-05, "loss": 4.6694, "step": 3941 }, { "epoch": 0.21211795092552735, "grad_norm": 1.0355725288391113, "learning_rate": 4.465409785140251e-05, "loss": 4.6261, "step": 3942 }, { "epoch": 0.2121717606543263, "grad_norm": 1.805826187133789, "learning_rate": 4.4651485698892905e-05, "loss": 4.2943, "step": 3943 }, { "epoch": 0.21222557038312526, "grad_norm": 1.8327792882919312, "learning_rate": 4.46488729847967e-05, "loss": 4.4328, "step": 3944 }, { "epoch": 0.21227938011192424, "grad_norm": 2.264157772064209, "learning_rate": 4.4646259709188555e-05, "loss": 4.2008, "step": 3945 }, { "epoch": 0.2123331898407232, "grad_norm": 1.909286379814148, "learning_rate": 4.464364587214315e-05, "loss": 4.4321, "step": 3946 }, { "epoch": 0.21238699956952217, "grad_norm": 1.5194032192230225, "learning_rate": 4.464103147373518e-05, "loss": 4.4266, "step": 3947 }, { "epoch": 0.21244080929832113, "grad_norm": 1.3249921798706055, "learning_rate": 4.463841651403936e-05, "loss": 4.7668, "step": 3948 }, { "epoch": 0.2124946190271201, "grad_norm": 1.6464049816131592, "learning_rate": 4.4635800993130414e-05, "loss": 4.7505, "step": 3949 }, { "epoch": 0.21254842875591906, "grad_norm": 2.4243063926696777, "learning_rate": 4.463318491108309e-05, "loss": 4.8639, "step": 3950 }, { "epoch": 0.21260223848471804, "grad_norm": 1.2967216968536377, "learning_rate": 4.463056826797215e-05, "loss": 4.5633, "step": 3951 }, { "epoch": 0.212656048213517, "grad_norm": 1.631121277809143, "learning_rate": 4.462795106387237e-05, "loss": 4.7077, "step": 3952 }, { "epoch": 0.21270985794231598, "grad_norm": 1.1009390354156494, "learning_rate": 4.462533329885854e-05, "loss": 4.7932, "step": 3953 }, { "epoch": 0.21276366767111493, "grad_norm": 0.9518852233886719, "learning_rate": 4.462271497300547e-05, "loss": 4.7045, "step": 3954 }, { "epoch": 0.2128174773999139, "grad_norm": 1.3941237926483154, "learning_rate": 4.462009608638799e-05, "loss": 4.4276, "step": 3955 }, { "epoch": 0.21287128712871287, "grad_norm": 2.0200207233428955, "learning_rate": 4.461747663908092e-05, "loss": 4.7344, "step": 3956 }, { "epoch": 0.21292509685751185, "grad_norm": 1.1365736722946167, "learning_rate": 4.461485663115915e-05, "loss": 4.5006, "step": 3957 }, { "epoch": 0.2129789065863108, "grad_norm": 1.3037973642349243, "learning_rate": 4.461223606269753e-05, "loss": 4.411, "step": 3958 }, { "epoch": 0.21303271631510978, "grad_norm": 1.815402865409851, "learning_rate": 4.460961493377095e-05, "loss": 4.5847, "step": 3959 }, { "epoch": 0.21308652604390874, "grad_norm": 2.4605743885040283, "learning_rate": 4.460699324445433e-05, "loss": 4.3112, "step": 3960 }, { "epoch": 0.21314033577270772, "grad_norm": 2.3236851692199707, "learning_rate": 4.4604370994822565e-05, "loss": 4.4473, "step": 3961 }, { "epoch": 0.21319414550150667, "grad_norm": 1.6993346214294434, "learning_rate": 4.4601748184950615e-05, "loss": 4.7497, "step": 3962 }, { "epoch": 0.21324795523030565, "grad_norm": 2.656156063079834, "learning_rate": 4.459912481491342e-05, "loss": 3.9322, "step": 3963 }, { "epoch": 0.2133017649591046, "grad_norm": 1.3767973184585571, "learning_rate": 4.459650088478596e-05, "loss": 4.9526, "step": 3964 }, { "epoch": 0.21335557468790356, "grad_norm": 2.104823350906372, "learning_rate": 4.459387639464321e-05, "loss": 4.4728, "step": 3965 }, { "epoch": 0.21340938441670254, "grad_norm": 1.329262137413025, "learning_rate": 4.459125134456017e-05, "loss": 4.5812, "step": 3966 }, { "epoch": 0.2134631941455015, "grad_norm": 1.827573537826538, "learning_rate": 4.4588625734611865e-05, "loss": 4.0844, "step": 3967 }, { "epoch": 0.21351700387430048, "grad_norm": 2.115093231201172, "learning_rate": 4.458599956487332e-05, "loss": 4.3009, "step": 3968 }, { "epoch": 0.21357081360309943, "grad_norm": 1.5504001379013062, "learning_rate": 4.458337283541959e-05, "loss": 4.5985, "step": 3969 }, { "epoch": 0.2136246233318984, "grad_norm": 1.3045077323913574, "learning_rate": 4.458074554632574e-05, "loss": 5.1294, "step": 3970 }, { "epoch": 0.21367843306069736, "grad_norm": 1.6243653297424316, "learning_rate": 4.4578117697666845e-05, "loss": 4.4262, "step": 3971 }, { "epoch": 0.21373224278949635, "grad_norm": 1.9636061191558838, "learning_rate": 4.4575489289518e-05, "loss": 4.4175, "step": 3972 }, { "epoch": 0.2137860525182953, "grad_norm": 1.1806007623672485, "learning_rate": 4.4572860321954335e-05, "loss": 4.6362, "step": 3973 }, { "epoch": 0.21383986224709428, "grad_norm": 1.5592894554138184, "learning_rate": 4.457023079505096e-05, "loss": 4.7794, "step": 3974 }, { "epoch": 0.21389367197589323, "grad_norm": 1.2544554471969604, "learning_rate": 4.456760070888303e-05, "loss": 4.8948, "step": 3975 }, { "epoch": 0.21394748170469222, "grad_norm": 1.294911503791809, "learning_rate": 4.45649700635257e-05, "loss": 4.8238, "step": 3976 }, { "epoch": 0.21400129143349117, "grad_norm": 2.2901628017425537, "learning_rate": 4.456233885905414e-05, "loss": 4.2482, "step": 3977 }, { "epoch": 0.21405510116229015, "grad_norm": 1.6147505044937134, "learning_rate": 4.455970709554357e-05, "loss": 4.8063, "step": 3978 }, { "epoch": 0.2141089108910891, "grad_norm": 1.2478471994400024, "learning_rate": 4.4557074773069166e-05, "loss": 4.6261, "step": 3979 }, { "epoch": 0.2141627206198881, "grad_norm": 1.6309247016906738, "learning_rate": 4.455444189170618e-05, "loss": 4.9598, "step": 3980 }, { "epoch": 0.21421653034868704, "grad_norm": 0.8615685701370239, "learning_rate": 4.455180845152983e-05, "loss": 4.5841, "step": 3981 }, { "epoch": 0.21427034007748602, "grad_norm": 1.7808555364608765, "learning_rate": 4.454917445261538e-05, "loss": 4.7449, "step": 3982 }, { "epoch": 0.21432414980628497, "grad_norm": 1.3660354614257812, "learning_rate": 4.454653989503812e-05, "loss": 4.714, "step": 3983 }, { "epoch": 0.21437795953508396, "grad_norm": 1.7671581506729126, "learning_rate": 4.454390477887331e-05, "loss": 4.3818, "step": 3984 }, { "epoch": 0.2144317692638829, "grad_norm": 1.644509196281433, "learning_rate": 4.454126910419627e-05, "loss": 4.2527, "step": 3985 }, { "epoch": 0.21448557899268186, "grad_norm": 1.8511278629302979, "learning_rate": 4.453863287108232e-05, "loss": 4.6575, "step": 3986 }, { "epoch": 0.21453938872148084, "grad_norm": 1.1078945398330688, "learning_rate": 4.4535996079606803e-05, "loss": 4.7567, "step": 3987 }, { "epoch": 0.2145931984502798, "grad_norm": 1.9163731336593628, "learning_rate": 4.453335872984505e-05, "loss": 4.6142, "step": 3988 }, { "epoch": 0.21464700817907878, "grad_norm": 1.9687166213989258, "learning_rate": 4.4530720821872455e-05, "loss": 4.3221, "step": 3989 }, { "epoch": 0.21470081790787773, "grad_norm": 1.2579787969589233, "learning_rate": 4.452808235576439e-05, "loss": 4.7142, "step": 3990 }, { "epoch": 0.21475462763667671, "grad_norm": 2.778092861175537, "learning_rate": 4.452544333159625e-05, "loss": 4.4124, "step": 3991 }, { "epoch": 0.21480843736547567, "grad_norm": 1.3984345197677612, "learning_rate": 4.452280374944346e-05, "loss": 4.7913, "step": 3992 }, { "epoch": 0.21486224709427465, "grad_norm": 1.4598277807235718, "learning_rate": 4.452016360938145e-05, "loss": 4.4702, "step": 3993 }, { "epoch": 0.2149160568230736, "grad_norm": 1.0070825815200806, "learning_rate": 4.451752291148566e-05, "loss": 4.7458, "step": 3994 }, { "epoch": 0.21496986655187258, "grad_norm": 1.6029301881790161, "learning_rate": 4.451488165583156e-05, "loss": 4.3824, "step": 3995 }, { "epoch": 0.21502367628067154, "grad_norm": 1.8445956707000732, "learning_rate": 4.4512239842494643e-05, "loss": 4.7103, "step": 3996 }, { "epoch": 0.21507748600947052, "grad_norm": 2.034144639968872, "learning_rate": 4.450959747155039e-05, "loss": 4.6625, "step": 3997 }, { "epoch": 0.21513129573826947, "grad_norm": 1.759441614151001, "learning_rate": 4.450695454307431e-05, "loss": 4.5207, "step": 3998 }, { "epoch": 0.21518510546706845, "grad_norm": 2.019129991531372, "learning_rate": 4.450431105714194e-05, "loss": 4.66, "step": 3999 }, { "epoch": 0.2152389151958674, "grad_norm": 1.3157297372817993, "learning_rate": 4.450166701382882e-05, "loss": 4.958, "step": 4000 }, { "epoch": 0.2152927249246664, "grad_norm": 1.4039260149002075, "learning_rate": 4.449902241321051e-05, "loss": 4.834, "step": 4001 }, { "epoch": 0.21534653465346534, "grad_norm": 1.7457759380340576, "learning_rate": 4.4496377255362585e-05, "loss": 4.6179, "step": 4002 }, { "epoch": 0.21540034438226432, "grad_norm": 1.8355417251586914, "learning_rate": 4.449373154036064e-05, "loss": 4.3421, "step": 4003 }, { "epoch": 0.21545415411106328, "grad_norm": 1.7091994285583496, "learning_rate": 4.4491085268280275e-05, "loss": 4.8867, "step": 4004 }, { "epoch": 0.21550796383986226, "grad_norm": 1.6777814626693726, "learning_rate": 4.448843843919712e-05, "loss": 4.8698, "step": 4005 }, { "epoch": 0.2155617735686612, "grad_norm": 1.2941700220108032, "learning_rate": 4.4485791053186814e-05, "loss": 4.5716, "step": 4006 }, { "epoch": 0.21561558329746017, "grad_norm": 2.056157112121582, "learning_rate": 4.448314311032501e-05, "loss": 4.0832, "step": 4007 }, { "epoch": 0.21566939302625915, "grad_norm": 2.5034542083740234, "learning_rate": 4.4480494610687376e-05, "loss": 4.4771, "step": 4008 }, { "epoch": 0.2157232027550581, "grad_norm": 1.4651426076889038, "learning_rate": 4.447784555434961e-05, "loss": 4.5822, "step": 4009 }, { "epoch": 0.21577701248385708, "grad_norm": 1.5989218950271606, "learning_rate": 4.447519594138741e-05, "loss": 4.737, "step": 4010 }, { "epoch": 0.21583082221265604, "grad_norm": 1.463239312171936, "learning_rate": 4.4472545771876474e-05, "loss": 4.6365, "step": 4011 }, { "epoch": 0.21588463194145502, "grad_norm": 2.3100123405456543, "learning_rate": 4.446989504589256e-05, "loss": 4.6292, "step": 4012 }, { "epoch": 0.21593844167025397, "grad_norm": 2.2168002128601074, "learning_rate": 4.4467243763511424e-05, "loss": 4.6149, "step": 4013 }, { "epoch": 0.21599225139905295, "grad_norm": 1.101436734199524, "learning_rate": 4.446459192480882e-05, "loss": 4.7601, "step": 4014 }, { "epoch": 0.2160460611278519, "grad_norm": 1.8812719583511353, "learning_rate": 4.446193952986053e-05, "loss": 4.6586, "step": 4015 }, { "epoch": 0.2160998708566509, "grad_norm": 1.64924156665802, "learning_rate": 4.445928657874235e-05, "loss": 4.7266, "step": 4016 }, { "epoch": 0.21615368058544984, "grad_norm": 2.2698450088500977, "learning_rate": 4.44566330715301e-05, "loss": 4.5872, "step": 4017 }, { "epoch": 0.21620749031424882, "grad_norm": 1.4725053310394287, "learning_rate": 4.445397900829961e-05, "loss": 4.2242, "step": 4018 }, { "epoch": 0.21626130004304778, "grad_norm": 2.229947805404663, "learning_rate": 4.4451324389126724e-05, "loss": 4.4218, "step": 4019 }, { "epoch": 0.21631510977184676, "grad_norm": 1.9206098318099976, "learning_rate": 4.4448669214087315e-05, "loss": 4.4472, "step": 4020 }, { "epoch": 0.2163689195006457, "grad_norm": 1.211403489112854, "learning_rate": 4.444601348325724e-05, "loss": 4.7944, "step": 4021 }, { "epoch": 0.2164227292294447, "grad_norm": 1.1447864770889282, "learning_rate": 4.444335719671241e-05, "loss": 4.5896, "step": 4022 }, { "epoch": 0.21647653895824365, "grad_norm": 2.0463552474975586, "learning_rate": 4.444070035452872e-05, "loss": 4.4833, "step": 4023 }, { "epoch": 0.21653034868704263, "grad_norm": 1.4037654399871826, "learning_rate": 4.443804295678211e-05, "loss": 4.2786, "step": 4024 }, { "epoch": 0.21658415841584158, "grad_norm": 2.399376153945923, "learning_rate": 4.4435385003548516e-05, "loss": 4.3096, "step": 4025 }, { "epoch": 0.21663796814464056, "grad_norm": 1.7579269409179688, "learning_rate": 4.4432726494903885e-05, "loss": 4.6716, "step": 4026 }, { "epoch": 0.21669177787343952, "grad_norm": 1.1779030561447144, "learning_rate": 4.443006743092421e-05, "loss": 4.9137, "step": 4027 }, { "epoch": 0.21674558760223847, "grad_norm": 2.0770251750946045, "learning_rate": 4.442740781168545e-05, "loss": 4.2183, "step": 4028 }, { "epoch": 0.21679939733103745, "grad_norm": 1.0085833072662354, "learning_rate": 4.442474763726364e-05, "loss": 4.4702, "step": 4029 }, { "epoch": 0.2168532070598364, "grad_norm": 1.053895115852356, "learning_rate": 4.4422086907734795e-05, "loss": 4.6675, "step": 4030 }, { "epoch": 0.2169070167886354, "grad_norm": 1.6753356456756592, "learning_rate": 4.441942562317494e-05, "loss": 4.3924, "step": 4031 }, { "epoch": 0.21696082651743434, "grad_norm": 1.7803019285202026, "learning_rate": 4.4416763783660134e-05, "loss": 3.7225, "step": 4032 }, { "epoch": 0.21701463624623332, "grad_norm": 1.6395915746688843, "learning_rate": 4.441410138926644e-05, "loss": 4.5868, "step": 4033 }, { "epoch": 0.21706844597503228, "grad_norm": 1.1502074003219604, "learning_rate": 4.441143844006994e-05, "loss": 4.7545, "step": 4034 }, { "epoch": 0.21712225570383126, "grad_norm": 2.0815443992614746, "learning_rate": 4.440877493614676e-05, "loss": 4.5298, "step": 4035 }, { "epoch": 0.2171760654326302, "grad_norm": 1.3326975107192993, "learning_rate": 4.440611087757298e-05, "loss": 4.6892, "step": 4036 }, { "epoch": 0.2172298751614292, "grad_norm": 2.4550163745880127, "learning_rate": 4.4403446264424755e-05, "loss": 4.046, "step": 4037 }, { "epoch": 0.21728368489022815, "grad_norm": 1.2282993793487549, "learning_rate": 4.4400781096778215e-05, "loss": 4.7579, "step": 4038 }, { "epoch": 0.21733749461902713, "grad_norm": 1.6134061813354492, "learning_rate": 4.439811537470954e-05, "loss": 4.6491, "step": 4039 }, { "epoch": 0.21739130434782608, "grad_norm": 1.5973265171051025, "learning_rate": 4.4395449098294907e-05, "loss": 4.3257, "step": 4040 }, { "epoch": 0.21744511407662506, "grad_norm": 1.5773863792419434, "learning_rate": 4.43927822676105e-05, "loss": 4.7428, "step": 4041 }, { "epoch": 0.21749892380542402, "grad_norm": 1.7819236516952515, "learning_rate": 4.439011488273254e-05, "loss": 4.686, "step": 4042 }, { "epoch": 0.217552733534223, "grad_norm": 1.269572138786316, "learning_rate": 4.438744694373724e-05, "loss": 4.6722, "step": 4043 }, { "epoch": 0.21760654326302195, "grad_norm": 2.1713695526123047, "learning_rate": 4.438477845070086e-05, "loss": 4.314, "step": 4044 }, { "epoch": 0.21766035299182093, "grad_norm": 1.8144365549087524, "learning_rate": 4.438210940369966e-05, "loss": 4.6186, "step": 4045 }, { "epoch": 0.21771416272061989, "grad_norm": 2.5500500202178955, "learning_rate": 4.437943980280989e-05, "loss": 4.2849, "step": 4046 }, { "epoch": 0.21776797244941887, "grad_norm": 1.3979707956314087, "learning_rate": 4.437676964810786e-05, "loss": 4.5667, "step": 4047 }, { "epoch": 0.21782178217821782, "grad_norm": 1.4599766731262207, "learning_rate": 4.437409893966987e-05, "loss": 4.4091, "step": 4048 }, { "epoch": 0.2178755919070168, "grad_norm": 1.7601768970489502, "learning_rate": 4.437142767757225e-05, "loss": 4.7102, "step": 4049 }, { "epoch": 0.21792940163581576, "grad_norm": 2.502793788909912, "learning_rate": 4.436875586189132e-05, "loss": 4.1521, "step": 4050 }, { "epoch": 0.2179832113646147, "grad_norm": 0.9350618720054626, "learning_rate": 4.436608349270345e-05, "loss": 4.6091, "step": 4051 }, { "epoch": 0.2180370210934137, "grad_norm": 1.4557499885559082, "learning_rate": 4.4363410570085e-05, "loss": 4.9431, "step": 4052 }, { "epoch": 0.21809083082221264, "grad_norm": 1.0993309020996094, "learning_rate": 4.436073709411236e-05, "loss": 4.6378, "step": 4053 }, { "epoch": 0.21814464055101163, "grad_norm": 1.5202007293701172, "learning_rate": 4.4358063064861924e-05, "loss": 4.5632, "step": 4054 }, { "epoch": 0.21819845027981058, "grad_norm": 1.387909173965454, "learning_rate": 4.435538848241011e-05, "loss": 4.8264, "step": 4055 }, { "epoch": 0.21825226000860956, "grad_norm": 1.6722122430801392, "learning_rate": 4.435271334683336e-05, "loss": 4.7487, "step": 4056 }, { "epoch": 0.21830606973740851, "grad_norm": 1.1410719156265259, "learning_rate": 4.435003765820811e-05, "loss": 4.605, "step": 4057 }, { "epoch": 0.2183598794662075, "grad_norm": 2.317436933517456, "learning_rate": 4.434736141661083e-05, "loss": 4.0007, "step": 4058 }, { "epoch": 0.21841368919500645, "grad_norm": 1.9797323942184448, "learning_rate": 4.4344684622118004e-05, "loss": 4.4439, "step": 4059 }, { "epoch": 0.21846749892380543, "grad_norm": 2.1965789794921875, "learning_rate": 4.434200727480612e-05, "loss": 4.7402, "step": 4060 }, { "epoch": 0.21852130865260438, "grad_norm": 1.1442878246307373, "learning_rate": 4.433932937475169e-05, "loss": 4.7322, "step": 4061 }, { "epoch": 0.21857511838140337, "grad_norm": 2.1947755813598633, "learning_rate": 4.4336650922031245e-05, "loss": 4.5911, "step": 4062 }, { "epoch": 0.21862892811020232, "grad_norm": 2.152919292449951, "learning_rate": 4.433397191672133e-05, "loss": 4.9255, "step": 4063 }, { "epoch": 0.2186827378390013, "grad_norm": 1.8301671743392944, "learning_rate": 4.433129235889849e-05, "loss": 4.7655, "step": 4064 }, { "epoch": 0.21873654756780025, "grad_norm": 2.380314588546753, "learning_rate": 4.432861224863932e-05, "loss": 4.5587, "step": 4065 }, { "epoch": 0.21879035729659924, "grad_norm": 2.0386390686035156, "learning_rate": 4.432593158602039e-05, "loss": 3.9475, "step": 4066 }, { "epoch": 0.2188441670253982, "grad_norm": 1.3679535388946533, "learning_rate": 4.432325037111832e-05, "loss": 4.2292, "step": 4067 }, { "epoch": 0.21889797675419717, "grad_norm": 1.9712828397750854, "learning_rate": 4.432056860400973e-05, "loss": 4.4002, "step": 4068 }, { "epoch": 0.21895178648299612, "grad_norm": 1.8481765985488892, "learning_rate": 4.431788628477126e-05, "loss": 4.6492, "step": 4069 }, { "epoch": 0.2190055962117951, "grad_norm": 2.0867841243743896, "learning_rate": 4.431520341347955e-05, "loss": 4.5887, "step": 4070 }, { "epoch": 0.21905940594059406, "grad_norm": 1.6066659688949585, "learning_rate": 4.4312519990211275e-05, "loss": 4.5655, "step": 4071 }, { "epoch": 0.219113215669393, "grad_norm": 0.961697518825531, "learning_rate": 4.4309836015043135e-05, "loss": 4.9021, "step": 4072 }, { "epoch": 0.219167025398192, "grad_norm": 1.2775732278823853, "learning_rate": 4.430715148805181e-05, "loss": 4.408, "step": 4073 }, { "epoch": 0.21922083512699095, "grad_norm": 1.6907382011413574, "learning_rate": 4.430446640931403e-05, "loss": 4.5858, "step": 4074 }, { "epoch": 0.21927464485578993, "grad_norm": 1.840911865234375, "learning_rate": 4.430178077890652e-05, "loss": 4.3214, "step": 4075 }, { "epoch": 0.21932845458458888, "grad_norm": 1.4691380262374878, "learning_rate": 4.429909459690603e-05, "loss": 4.5546, "step": 4076 }, { "epoch": 0.21938226431338786, "grad_norm": 1.5886324644088745, "learning_rate": 4.4296407863389334e-05, "loss": 4.6014, "step": 4077 }, { "epoch": 0.21943607404218682, "grad_norm": 1.1743247509002686, "learning_rate": 4.4293720578433196e-05, "loss": 4.7799, "step": 4078 }, { "epoch": 0.2194898837709858, "grad_norm": 1.177559733390808, "learning_rate": 4.429103274211442e-05, "loss": 4.6865, "step": 4079 }, { "epoch": 0.21954369349978475, "grad_norm": 1.3918968439102173, "learning_rate": 4.428834435450981e-05, "loss": 4.6684, "step": 4080 }, { "epoch": 0.21959750322858373, "grad_norm": 1.5823216438293457, "learning_rate": 4.4285655415696203e-05, "loss": 4.6756, "step": 4081 }, { "epoch": 0.2196513129573827, "grad_norm": 2.0880939960479736, "learning_rate": 4.428296592575044e-05, "loss": 4.4015, "step": 4082 }, { "epoch": 0.21970512268618167, "grad_norm": 1.6704319715499878, "learning_rate": 4.428027588474937e-05, "loss": 5.1686, "step": 4083 }, { "epoch": 0.21975893241498062, "grad_norm": 1.5910375118255615, "learning_rate": 4.427758529276987e-05, "loss": 4.607, "step": 4084 }, { "epoch": 0.2198127421437796, "grad_norm": 1.3475914001464844, "learning_rate": 4.427489414988883e-05, "loss": 4.6973, "step": 4085 }, { "epoch": 0.21986655187257856, "grad_norm": 1.681526780128479, "learning_rate": 4.427220245618318e-05, "loss": 4.4313, "step": 4086 }, { "epoch": 0.21992036160137754, "grad_norm": 2.2322821617126465, "learning_rate": 4.42695102117298e-05, "loss": 4.7342, "step": 4087 }, { "epoch": 0.2199741713301765, "grad_norm": 1.7996370792388916, "learning_rate": 4.426681741660565e-05, "loss": 4.2321, "step": 4088 }, { "epoch": 0.22002798105897547, "grad_norm": 1.5539052486419678, "learning_rate": 4.426412407088768e-05, "loss": 4.549, "step": 4089 }, { "epoch": 0.22008179078777443, "grad_norm": 1.4501487016677856, "learning_rate": 4.4261430174652866e-05, "loss": 4.7501, "step": 4090 }, { "epoch": 0.2201356005165734, "grad_norm": 1.5839978456497192, "learning_rate": 4.4258735727978176e-05, "loss": 4.6084, "step": 4091 }, { "epoch": 0.22018941024537236, "grad_norm": 1.1326277256011963, "learning_rate": 4.4256040730940625e-05, "loss": 4.8378, "step": 4092 }, { "epoch": 0.22024321997417132, "grad_norm": 1.9909162521362305, "learning_rate": 4.4253345183617216e-05, "loss": 4.1826, "step": 4093 }, { "epoch": 0.2202970297029703, "grad_norm": 1.3262284994125366, "learning_rate": 4.4250649086084995e-05, "loss": 5.1976, "step": 4094 }, { "epoch": 0.22035083943176925, "grad_norm": 1.7106618881225586, "learning_rate": 4.424795243842099e-05, "loss": 4.4801, "step": 4095 }, { "epoch": 0.22040464916056823, "grad_norm": 1.332563877105713, "learning_rate": 4.4245255240702286e-05, "loss": 4.4227, "step": 4096 }, { "epoch": 0.2204584588893672, "grad_norm": 1.612545371055603, "learning_rate": 4.424255749300595e-05, "loss": 4.9016, "step": 4097 }, { "epoch": 0.22051226861816617, "grad_norm": 2.073378562927246, "learning_rate": 4.4239859195409075e-05, "loss": 4.6584, "step": 4098 }, { "epoch": 0.22056607834696512, "grad_norm": 2.0598835945129395, "learning_rate": 4.423716034798877e-05, "loss": 4.3167, "step": 4099 }, { "epoch": 0.2206198880757641, "grad_norm": 1.2173101902008057, "learning_rate": 4.423446095082217e-05, "loss": 4.3421, "step": 4100 }, { "epoch": 0.22067369780456306, "grad_norm": 1.5329183340072632, "learning_rate": 4.423176100398641e-05, "loss": 5.0073, "step": 4101 }, { "epoch": 0.22072750753336204, "grad_norm": 1.8905271291732788, "learning_rate": 4.422906050755864e-05, "loss": 4.3909, "step": 4102 }, { "epoch": 0.220781317262161, "grad_norm": 2.252551317214966, "learning_rate": 4.422635946161605e-05, "loss": 4.8692, "step": 4103 }, { "epoch": 0.22083512699095997, "grad_norm": 2.379509449005127, "learning_rate": 4.422365786623581e-05, "loss": 4.8456, "step": 4104 }, { "epoch": 0.22088893671975893, "grad_norm": 0.9950577616691589, "learning_rate": 4.422095572149514e-05, "loss": 4.7468, "step": 4105 }, { "epoch": 0.2209427464485579, "grad_norm": 2.6296987533569336, "learning_rate": 4.421825302747126e-05, "loss": 4.408, "step": 4106 }, { "epoch": 0.22099655617735686, "grad_norm": 1.1935914754867554, "learning_rate": 4.421554978424139e-05, "loss": 4.6374, "step": 4107 }, { "epoch": 0.22105036590615584, "grad_norm": 1.8639339208602905, "learning_rate": 4.421284599188279e-05, "loss": 4.5361, "step": 4108 }, { "epoch": 0.2211041756349548, "grad_norm": 1.4972736835479736, "learning_rate": 4.4210141650472736e-05, "loss": 4.3781, "step": 4109 }, { "epoch": 0.22115798536375378, "grad_norm": 1.2391338348388672, "learning_rate": 4.4207436760088496e-05, "loss": 4.6465, "step": 4110 }, { "epoch": 0.22121179509255273, "grad_norm": 1.0311192274093628, "learning_rate": 4.420473132080738e-05, "loss": 4.7754, "step": 4111 }, { "epoch": 0.2212656048213517, "grad_norm": 1.0236355066299438, "learning_rate": 4.42020253327067e-05, "loss": 4.8827, "step": 4112 }, { "epoch": 0.22131941455015067, "grad_norm": 1.8807051181793213, "learning_rate": 4.419931879586377e-05, "loss": 4.5284, "step": 4113 }, { "epoch": 0.22137322427894962, "grad_norm": 1.1737070083618164, "learning_rate": 4.419661171035596e-05, "loss": 4.522, "step": 4114 }, { "epoch": 0.2214270340077486, "grad_norm": 2.024845600128174, "learning_rate": 4.4193904076260614e-05, "loss": 4.4666, "step": 4115 }, { "epoch": 0.22148084373654756, "grad_norm": 2.0457701683044434, "learning_rate": 4.419119589365512e-05, "loss": 4.3133, "step": 4116 }, { "epoch": 0.22153465346534654, "grad_norm": 1.1229971647262573, "learning_rate": 4.4188487162616865e-05, "loss": 4.7738, "step": 4117 }, { "epoch": 0.2215884631941455, "grad_norm": 1.5417238473892212, "learning_rate": 4.418577788322326e-05, "loss": 4.3897, "step": 4118 }, { "epoch": 0.22164227292294447, "grad_norm": 1.6372146606445312, "learning_rate": 4.418306805555173e-05, "loss": 4.4749, "step": 4119 }, { "epoch": 0.22169608265174343, "grad_norm": 1.661339521408081, "learning_rate": 4.41803576796797e-05, "loss": 4.2029, "step": 4120 }, { "epoch": 0.2217498923805424, "grad_norm": 1.6715680360794067, "learning_rate": 4.417764675568464e-05, "loss": 4.1681, "step": 4121 }, { "epoch": 0.22180370210934136, "grad_norm": 1.9254807233810425, "learning_rate": 4.4174935283644024e-05, "loss": 4.8099, "step": 4122 }, { "epoch": 0.22185751183814034, "grad_norm": 1.4000846147537231, "learning_rate": 4.4172223263635325e-05, "loss": 4.3397, "step": 4123 }, { "epoch": 0.2219113215669393, "grad_norm": 2.160374402999878, "learning_rate": 4.4169510695736056e-05, "loss": 4.6378, "step": 4124 }, { "epoch": 0.22196513129573828, "grad_norm": 2.0739433765411377, "learning_rate": 4.416679758002373e-05, "loss": 4.402, "step": 4125 }, { "epoch": 0.22201894102453723, "grad_norm": 1.7908633947372437, "learning_rate": 4.416408391657588e-05, "loss": 4.6091, "step": 4126 }, { "epoch": 0.2220727507533362, "grad_norm": 2.0568432807922363, "learning_rate": 4.416136970547006e-05, "loss": 4.3201, "step": 4127 }, { "epoch": 0.22212656048213517, "grad_norm": 1.4365366697311401, "learning_rate": 4.415865494678383e-05, "loss": 5.0759, "step": 4128 }, { "epoch": 0.22218037021093415, "grad_norm": 2.0169994831085205, "learning_rate": 4.415593964059478e-05, "loss": 4.3833, "step": 4129 }, { "epoch": 0.2222341799397331, "grad_norm": 1.2079557180404663, "learning_rate": 4.415322378698049e-05, "loss": 4.3657, "step": 4130 }, { "epoch": 0.22228798966853208, "grad_norm": 2.0856223106384277, "learning_rate": 4.415050738601858e-05, "loss": 4.4186, "step": 4131 }, { "epoch": 0.22234179939733104, "grad_norm": 1.4621995687484741, "learning_rate": 4.414779043778668e-05, "loss": 4.6481, "step": 4132 }, { "epoch": 0.22239560912613002, "grad_norm": 1.7375065088272095, "learning_rate": 4.414507294236243e-05, "loss": 4.8478, "step": 4133 }, { "epoch": 0.22244941885492897, "grad_norm": 0.8809975385665894, "learning_rate": 4.414235489982349e-05, "loss": 4.7118, "step": 4134 }, { "epoch": 0.22250322858372792, "grad_norm": 2.1261425018310547, "learning_rate": 4.413963631024753e-05, "loss": 4.3502, "step": 4135 }, { "epoch": 0.2225570383125269, "grad_norm": 1.2648141384124756, "learning_rate": 4.4136917173712255e-05, "loss": 4.5793, "step": 4136 }, { "epoch": 0.22261084804132586, "grad_norm": 2.153660774230957, "learning_rate": 4.4134197490295345e-05, "loss": 4.554, "step": 4137 }, { "epoch": 0.22266465777012484, "grad_norm": 3.131401538848877, "learning_rate": 4.413147726007455e-05, "loss": 3.8685, "step": 4138 }, { "epoch": 0.2227184674989238, "grad_norm": 1.760855793952942, "learning_rate": 4.4128756483127586e-05, "loss": 4.6023, "step": 4139 }, { "epoch": 0.22277227722772278, "grad_norm": 1.1363493204116821, "learning_rate": 4.412603515953221e-05, "loss": 4.3379, "step": 4140 }, { "epoch": 0.22282608695652173, "grad_norm": 1.3764480352401733, "learning_rate": 4.4123313289366194e-05, "loss": 4.7456, "step": 4141 }, { "epoch": 0.2228798966853207, "grad_norm": 1.1000678539276123, "learning_rate": 4.412059087270732e-05, "loss": 4.5813, "step": 4142 }, { "epoch": 0.22293370641411966, "grad_norm": 1.8212450742721558, "learning_rate": 4.411786790963338e-05, "loss": 4.7962, "step": 4143 }, { "epoch": 0.22298751614291865, "grad_norm": 1.618822455406189, "learning_rate": 4.411514440022221e-05, "loss": 4.2815, "step": 4144 }, { "epoch": 0.2230413258717176, "grad_norm": 2.7324328422546387, "learning_rate": 4.411242034455162e-05, "loss": 4.0125, "step": 4145 }, { "epoch": 0.22309513560051658, "grad_norm": 1.3584001064300537, "learning_rate": 4.410969574269946e-05, "loss": 4.7127, "step": 4146 }, { "epoch": 0.22314894532931553, "grad_norm": 1.7426906824111938, "learning_rate": 4.4106970594743595e-05, "loss": 4.1488, "step": 4147 }, { "epoch": 0.22320275505811452, "grad_norm": 1.3151556253433228, "learning_rate": 4.4104244900761905e-05, "loss": 4.6502, "step": 4148 }, { "epoch": 0.22325656478691347, "grad_norm": 2.2908027172088623, "learning_rate": 4.4101518660832283e-05, "loss": 4.9405, "step": 4149 }, { "epoch": 0.22331037451571245, "grad_norm": 1.56131911277771, "learning_rate": 4.409879187503263e-05, "loss": 4.6231, "step": 4150 }, { "epoch": 0.2233641842445114, "grad_norm": 1.1359162330627441, "learning_rate": 4.4096064543440877e-05, "loss": 4.8195, "step": 4151 }, { "epoch": 0.22341799397331039, "grad_norm": 1.6994390487670898, "learning_rate": 4.409333666613496e-05, "loss": 4.5683, "step": 4152 }, { "epoch": 0.22347180370210934, "grad_norm": 1.1251963376998901, "learning_rate": 4.409060824319284e-05, "loss": 4.5256, "step": 4153 }, { "epoch": 0.22352561343090832, "grad_norm": 1.6854784488677979, "learning_rate": 4.408787927469248e-05, "loss": 4.4656, "step": 4154 }, { "epoch": 0.22357942315970727, "grad_norm": 1.179949164390564, "learning_rate": 4.408514976071187e-05, "loss": 4.655, "step": 4155 }, { "epoch": 0.22363323288850623, "grad_norm": 1.4304487705230713, "learning_rate": 4.408241970132901e-05, "loss": 4.5478, "step": 4156 }, { "epoch": 0.2236870426173052, "grad_norm": 1.398240566253662, "learning_rate": 4.407968909662193e-05, "loss": 4.658, "step": 4157 }, { "epoch": 0.22374085234610416, "grad_norm": 1.3387902975082397, "learning_rate": 4.4076957946668654e-05, "loss": 4.6012, "step": 4158 }, { "epoch": 0.22379466207490314, "grad_norm": 1.8416751623153687, "learning_rate": 4.407422625154723e-05, "loss": 4.1902, "step": 4159 }, { "epoch": 0.2238484718037021, "grad_norm": 1.8125934600830078, "learning_rate": 4.407149401133571e-05, "loss": 4.5338, "step": 4160 }, { "epoch": 0.22390228153250108, "grad_norm": 2.3417325019836426, "learning_rate": 4.40687612261122e-05, "loss": 4.9411, "step": 4161 }, { "epoch": 0.22395609126130003, "grad_norm": 1.4033434391021729, "learning_rate": 4.4066027895954773e-05, "loss": 5.0353, "step": 4162 }, { "epoch": 0.22400990099009901, "grad_norm": 1.9451979398727417, "learning_rate": 4.406329402094157e-05, "loss": 4.499, "step": 4163 }, { "epoch": 0.22406371071889797, "grad_norm": 2.263777256011963, "learning_rate": 4.406055960115068e-05, "loss": 4.464, "step": 4164 }, { "epoch": 0.22411752044769695, "grad_norm": 1.0088168382644653, "learning_rate": 4.405782463666027e-05, "loss": 4.6235, "step": 4165 }, { "epoch": 0.2241713301764959, "grad_norm": 1.1964887380599976, "learning_rate": 4.4055089127548485e-05, "loss": 4.4091, "step": 4166 }, { "epoch": 0.22422513990529488, "grad_norm": 1.7641922235488892, "learning_rate": 4.405235307389352e-05, "loss": 4.6106, "step": 4167 }, { "epoch": 0.22427894963409384, "grad_norm": 1.339189052581787, "learning_rate": 4.404961647577353e-05, "loss": 4.4863, "step": 4168 }, { "epoch": 0.22433275936289282, "grad_norm": 1.978676438331604, "learning_rate": 4.404687933326675e-05, "loss": 4.4923, "step": 4169 }, { "epoch": 0.22438656909169177, "grad_norm": 2.206144332885742, "learning_rate": 4.4044141646451384e-05, "loss": 4.2202, "step": 4170 }, { "epoch": 0.22444037882049075, "grad_norm": 1.5239862203598022, "learning_rate": 4.404140341540568e-05, "loss": 4.5641, "step": 4171 }, { "epoch": 0.2244941885492897, "grad_norm": 1.4713906049728394, "learning_rate": 4.4038664640207875e-05, "loss": 4.441, "step": 4172 }, { "epoch": 0.2245479982780887, "grad_norm": 0.975866973400116, "learning_rate": 4.403592532093624e-05, "loss": 4.6479, "step": 4173 }, { "epoch": 0.22460180800688764, "grad_norm": 1.357465386390686, "learning_rate": 4.403318545766907e-05, "loss": 4.6104, "step": 4174 }, { "epoch": 0.22465561773568662, "grad_norm": 1.6522670984268188, "learning_rate": 4.403044505048465e-05, "loss": 4.7795, "step": 4175 }, { "epoch": 0.22470942746448558, "grad_norm": 1.1572275161743164, "learning_rate": 4.402770409946129e-05, "loss": 4.3941, "step": 4176 }, { "epoch": 0.22476323719328456, "grad_norm": 1.116111159324646, "learning_rate": 4.402496260467733e-05, "loss": 4.6586, "step": 4177 }, { "epoch": 0.2248170469220835, "grad_norm": 1.2115126848220825, "learning_rate": 4.40222205662111e-05, "loss": 4.4782, "step": 4178 }, { "epoch": 0.22487085665088247, "grad_norm": 1.2538490295410156, "learning_rate": 4.401947798414099e-05, "loss": 4.3898, "step": 4179 }, { "epoch": 0.22492466637968145, "grad_norm": 1.163560390472412, "learning_rate": 4.401673485854534e-05, "loss": 4.7485, "step": 4180 }, { "epoch": 0.2249784761084804, "grad_norm": 2.0585808753967285, "learning_rate": 4.401399118950256e-05, "loss": 4.7017, "step": 4181 }, { "epoch": 0.22503228583727938, "grad_norm": 1.6759779453277588, "learning_rate": 4.401124697709106e-05, "loss": 4.874, "step": 4182 }, { "epoch": 0.22508609556607834, "grad_norm": 1.2546895742416382, "learning_rate": 4.400850222138925e-05, "loss": 4.4305, "step": 4183 }, { "epoch": 0.22513990529487732, "grad_norm": 0.8391903042793274, "learning_rate": 4.4005756922475574e-05, "loss": 4.6003, "step": 4184 }, { "epoch": 0.22519371502367627, "grad_norm": 1.127744436264038, "learning_rate": 4.400301108042848e-05, "loss": 4.3438, "step": 4185 }, { "epoch": 0.22524752475247525, "grad_norm": 2.7687737941741943, "learning_rate": 4.400026469532644e-05, "loss": 4.3547, "step": 4186 }, { "epoch": 0.2253013344812742, "grad_norm": 1.7977604866027832, "learning_rate": 4.399751776724795e-05, "loss": 4.8646, "step": 4187 }, { "epoch": 0.2253551442100732, "grad_norm": 2.4033095836639404, "learning_rate": 4.399477029627149e-05, "loss": 4.4297, "step": 4188 }, { "epoch": 0.22540895393887214, "grad_norm": 1.5958877801895142, "learning_rate": 4.3992022282475596e-05, "loss": 4.601, "step": 4189 }, { "epoch": 0.22546276366767112, "grad_norm": 1.639768123626709, "learning_rate": 4.398927372593878e-05, "loss": 4.7041, "step": 4190 }, { "epoch": 0.22551657339647008, "grad_norm": 1.4739983081817627, "learning_rate": 4.39865246267396e-05, "loss": 4.5086, "step": 4191 }, { "epoch": 0.22557038312526906, "grad_norm": 1.4788777828216553, "learning_rate": 4.398377498495661e-05, "loss": 4.0839, "step": 4192 }, { "epoch": 0.225624192854068, "grad_norm": 1.608940839767456, "learning_rate": 4.3981024800668393e-05, "loss": 4.7076, "step": 4193 }, { "epoch": 0.225678002582867, "grad_norm": 1.3878170251846313, "learning_rate": 4.397827407395354e-05, "loss": 4.2769, "step": 4194 }, { "epoch": 0.22573181231166595, "grad_norm": 1.743076205253601, "learning_rate": 4.397552280489066e-05, "loss": 4.3265, "step": 4195 }, { "epoch": 0.22578562204046493, "grad_norm": 1.3501936197280884, "learning_rate": 4.3972770993558376e-05, "loss": 4.6369, "step": 4196 }, { "epoch": 0.22583943176926388, "grad_norm": 2.37949800491333, "learning_rate": 4.3970018640035324e-05, "loss": 4.7781, "step": 4197 }, { "epoch": 0.22589324149806286, "grad_norm": 1.125921607017517, "learning_rate": 4.3967265744400167e-05, "loss": 4.7507, "step": 4198 }, { "epoch": 0.22594705122686182, "grad_norm": 1.3729292154312134, "learning_rate": 4.396451230673157e-05, "loss": 4.7218, "step": 4199 }, { "epoch": 0.22600086095566077, "grad_norm": 1.6261616945266724, "learning_rate": 4.396175832710822e-05, "loss": 4.3241, "step": 4200 }, { "epoch": 0.22605467068445975, "grad_norm": 2.2674763202667236, "learning_rate": 4.395900380560882e-05, "loss": 4.4873, "step": 4201 }, { "epoch": 0.2261084804132587, "grad_norm": 1.4147553443908691, "learning_rate": 4.3956248742312084e-05, "loss": 4.4252, "step": 4202 }, { "epoch": 0.2261622901420577, "grad_norm": 1.4480576515197754, "learning_rate": 4.395349313729674e-05, "loss": 4.6211, "step": 4203 }, { "epoch": 0.22621609987085664, "grad_norm": 1.623921275138855, "learning_rate": 4.395073699064155e-05, "loss": 4.609, "step": 4204 }, { "epoch": 0.22626990959965562, "grad_norm": 1.7637524604797363, "learning_rate": 4.3947980302425266e-05, "loss": 4.3734, "step": 4205 }, { "epoch": 0.22632371932845458, "grad_norm": 1.3611810207366943, "learning_rate": 4.394522307272666e-05, "loss": 5.0918, "step": 4206 }, { "epoch": 0.22637752905725356, "grad_norm": 0.9434999227523804, "learning_rate": 4.394246530162455e-05, "loss": 4.9226, "step": 4207 }, { "epoch": 0.2264313387860525, "grad_norm": 1.6258783340454102, "learning_rate": 4.3939706989197716e-05, "loss": 4.6155, "step": 4208 }, { "epoch": 0.2264851485148515, "grad_norm": 1.1339045763015747, "learning_rate": 4.393694813552501e-05, "loss": 4.6048, "step": 4209 }, { "epoch": 0.22653895824365045, "grad_norm": 1.1840033531188965, "learning_rate": 4.3934188740685254e-05, "loss": 4.7362, "step": 4210 }, { "epoch": 0.22659276797244943, "grad_norm": 1.5695154666900635, "learning_rate": 4.393142880475731e-05, "loss": 4.4256, "step": 4211 }, { "epoch": 0.22664657770124838, "grad_norm": 0.9738216996192932, "learning_rate": 4.392866832782006e-05, "loss": 4.7342, "step": 4212 }, { "epoch": 0.22670038743004736, "grad_norm": 1.2148005962371826, "learning_rate": 4.3925907309952366e-05, "loss": 4.598, "step": 4213 }, { "epoch": 0.22675419715884632, "grad_norm": 1.2914495468139648, "learning_rate": 4.392314575123315e-05, "loss": 4.3979, "step": 4214 }, { "epoch": 0.2268080068876453, "grad_norm": 1.3405349254608154, "learning_rate": 4.3920383651741337e-05, "loss": 4.64, "step": 4215 }, { "epoch": 0.22686181661644425, "grad_norm": 2.2512474060058594, "learning_rate": 4.3917621011555845e-05, "loss": 4.5304, "step": 4216 }, { "epoch": 0.22691562634524323, "grad_norm": 1.5888084173202515, "learning_rate": 4.391485783075562e-05, "loss": 4.5581, "step": 4217 }, { "epoch": 0.22696943607404219, "grad_norm": 1.9646191596984863, "learning_rate": 4.3912094109419634e-05, "loss": 4.5764, "step": 4218 }, { "epoch": 0.22702324580284117, "grad_norm": 1.62075936794281, "learning_rate": 4.390932984762687e-05, "loss": 4.7685, "step": 4219 }, { "epoch": 0.22707705553164012, "grad_norm": 1.4556761980056763, "learning_rate": 4.3906565045456316e-05, "loss": 4.7341, "step": 4220 }, { "epoch": 0.22713086526043907, "grad_norm": 2.0778284072875977, "learning_rate": 4.3903799702986994e-05, "loss": 4.5653, "step": 4221 }, { "epoch": 0.22718467498923806, "grad_norm": 2.3980705738067627, "learning_rate": 4.390103382029791e-05, "loss": 4.2644, "step": 4222 }, { "epoch": 0.227238484718037, "grad_norm": 1.8184022903442383, "learning_rate": 4.3898267397468126e-05, "loss": 4.5264, "step": 4223 }, { "epoch": 0.227292294446836, "grad_norm": 1.1397498846054077, "learning_rate": 4.3895500434576684e-05, "loss": 4.8157, "step": 4224 }, { "epoch": 0.22734610417563494, "grad_norm": 2.1896443367004395, "learning_rate": 4.389273293170266e-05, "loss": 4.4334, "step": 4225 }, { "epoch": 0.22739991390443393, "grad_norm": 1.414610505104065, "learning_rate": 4.3889964888925154e-05, "loss": 4.3987, "step": 4226 }, { "epoch": 0.22745372363323288, "grad_norm": 1.8574669361114502, "learning_rate": 4.388719630632325e-05, "loss": 4.881, "step": 4227 }, { "epoch": 0.22750753336203186, "grad_norm": 1.7194175720214844, "learning_rate": 4.388442718397608e-05, "loss": 4.2727, "step": 4228 }, { "epoch": 0.22756134309083081, "grad_norm": 1.0699496269226074, "learning_rate": 4.388165752196278e-05, "loss": 4.7344, "step": 4229 }, { "epoch": 0.2276151528196298, "grad_norm": 0.8875730037689209, "learning_rate": 4.387888732036249e-05, "loss": 4.7466, "step": 4230 }, { "epoch": 0.22766896254842875, "grad_norm": 0.9938664436340332, "learning_rate": 4.387611657925438e-05, "loss": 4.8076, "step": 4231 }, { "epoch": 0.22772277227722773, "grad_norm": 1.8905625343322754, "learning_rate": 4.387334529871763e-05, "loss": 4.9463, "step": 4232 }, { "epoch": 0.22777658200602668, "grad_norm": 1.584109902381897, "learning_rate": 4.387057347883143e-05, "loss": 5.0122, "step": 4233 }, { "epoch": 0.22783039173482567, "grad_norm": 1.4256985187530518, "learning_rate": 4.3867801119675e-05, "loss": 4.7335, "step": 4234 }, { "epoch": 0.22788420146362462, "grad_norm": 1.7690542936325073, "learning_rate": 4.386502822132755e-05, "loss": 4.5732, "step": 4235 }, { "epoch": 0.2279380111924236, "grad_norm": 1.203472375869751, "learning_rate": 4.386225478386835e-05, "loss": 4.718, "step": 4236 }, { "epoch": 0.22799182092122255, "grad_norm": 2.0421559810638428, "learning_rate": 4.385948080737663e-05, "loss": 4.353, "step": 4237 }, { "epoch": 0.22804563065002154, "grad_norm": 1.461416244506836, "learning_rate": 4.385670629193168e-05, "loss": 4.6081, "step": 4238 }, { "epoch": 0.2280994403788205, "grad_norm": 1.2204680442810059, "learning_rate": 4.385393123761279e-05, "loss": 4.7011, "step": 4239 }, { "epoch": 0.22815325010761947, "grad_norm": 1.8803095817565918, "learning_rate": 4.3851155644499246e-05, "loss": 4.143, "step": 4240 }, { "epoch": 0.22820705983641842, "grad_norm": 1.5453112125396729, "learning_rate": 4.384837951267038e-05, "loss": 4.6133, "step": 4241 }, { "epoch": 0.22826086956521738, "grad_norm": 2.1984639167785645, "learning_rate": 4.384560284220552e-05, "loss": 4.7128, "step": 4242 }, { "epoch": 0.22831467929401636, "grad_norm": 1.795398235321045, "learning_rate": 4.384282563318403e-05, "loss": 4.8989, "step": 4243 }, { "epoch": 0.2283684890228153, "grad_norm": 1.6825909614562988, "learning_rate": 4.384004788568526e-05, "loss": 4.7129, "step": 4244 }, { "epoch": 0.2284222987516143, "grad_norm": 1.7048890590667725, "learning_rate": 4.3837269599788594e-05, "loss": 4.6137, "step": 4245 }, { "epoch": 0.22847610848041325, "grad_norm": 2.8062808513641357, "learning_rate": 4.383449077557343e-05, "loss": 4.294, "step": 4246 }, { "epoch": 0.22852991820921223, "grad_norm": 1.6025415658950806, "learning_rate": 4.3831711413119184e-05, "loss": 4.5867, "step": 4247 }, { "epoch": 0.22858372793801118, "grad_norm": 2.0793259143829346, "learning_rate": 4.382893151250526e-05, "loss": 4.391, "step": 4248 }, { "epoch": 0.22863753766681016, "grad_norm": 1.054988145828247, "learning_rate": 4.3826151073811125e-05, "loss": 4.9239, "step": 4249 }, { "epoch": 0.22869134739560912, "grad_norm": 1.7824223041534424, "learning_rate": 4.382337009711623e-05, "loss": 4.1394, "step": 4250 }, { "epoch": 0.2287451571244081, "grad_norm": 1.9259562492370605, "learning_rate": 4.382058858250006e-05, "loss": 4.9371, "step": 4251 }, { "epoch": 0.22879896685320705, "grad_norm": 1.3991172313690186, "learning_rate": 4.381780653004207e-05, "loss": 4.7723, "step": 4252 }, { "epoch": 0.22885277658200603, "grad_norm": 1.6026349067687988, "learning_rate": 4.38150239398218e-05, "loss": 4.5848, "step": 4253 }, { "epoch": 0.228906586310805, "grad_norm": 2.64286732673645, "learning_rate": 4.381224081191874e-05, "loss": 3.7583, "step": 4254 }, { "epoch": 0.22896039603960397, "grad_norm": 1.025208592414856, "learning_rate": 4.3809457146412434e-05, "loss": 4.6413, "step": 4255 }, { "epoch": 0.22901420576840292, "grad_norm": 1.919162392616272, "learning_rate": 4.380667294338244e-05, "loss": 4.7499, "step": 4256 }, { "epoch": 0.2290680154972019, "grad_norm": 1.6024004220962524, "learning_rate": 4.3803888202908324e-05, "loss": 4.6378, "step": 4257 }, { "epoch": 0.22912182522600086, "grad_norm": 1.825219988822937, "learning_rate": 4.380110292506965e-05, "loss": 4.2504, "step": 4258 }, { "epoch": 0.22917563495479984, "grad_norm": 1.2582975625991821, "learning_rate": 4.379831710994603e-05, "loss": 4.4903, "step": 4259 }, { "epoch": 0.2292294446835988, "grad_norm": 1.5260703563690186, "learning_rate": 4.3795530757617066e-05, "loss": 4.927, "step": 4260 }, { "epoch": 0.22928325441239777, "grad_norm": 1.2696725130081177, "learning_rate": 4.379274386816238e-05, "loss": 4.9448, "step": 4261 }, { "epoch": 0.22933706414119673, "grad_norm": 0.9455543756484985, "learning_rate": 4.3789956441661626e-05, "loss": 4.6355, "step": 4262 }, { "epoch": 0.22939087386999568, "grad_norm": 1.4911237955093384, "learning_rate": 4.378716847819446e-05, "loss": 4.9158, "step": 4263 }, { "epoch": 0.22944468359879466, "grad_norm": 1.3480325937271118, "learning_rate": 4.378437997784055e-05, "loss": 4.9253, "step": 4264 }, { "epoch": 0.22949849332759362, "grad_norm": 0.957705020904541, "learning_rate": 4.378159094067958e-05, "loss": 4.5422, "step": 4265 }, { "epoch": 0.2295523030563926, "grad_norm": 1.3875174522399902, "learning_rate": 4.3778801366791264e-05, "loss": 4.5246, "step": 4266 }, { "epoch": 0.22960611278519155, "grad_norm": 1.426578164100647, "learning_rate": 4.37760112562553e-05, "loss": 4.5724, "step": 4267 }, { "epoch": 0.22965992251399053, "grad_norm": 1.2227866649627686, "learning_rate": 4.3773220609151446e-05, "loss": 4.6237, "step": 4268 }, { "epoch": 0.2297137322427895, "grad_norm": 1.0029875040054321, "learning_rate": 4.3770429425559446e-05, "loss": 4.7381, "step": 4269 }, { "epoch": 0.22976754197158847, "grad_norm": 1.272402286529541, "learning_rate": 4.376763770555905e-05, "loss": 4.8595, "step": 4270 }, { "epoch": 0.22982135170038742, "grad_norm": 2.057995557785034, "learning_rate": 4.376484544923005e-05, "loss": 4.4971, "step": 4271 }, { "epoch": 0.2298751614291864, "grad_norm": 1.1116868257522583, "learning_rate": 4.3762052656652244e-05, "loss": 4.6768, "step": 4272 }, { "epoch": 0.22992897115798536, "grad_norm": 1.7061054706573486, "learning_rate": 4.375925932790543e-05, "loss": 4.1275, "step": 4273 }, { "epoch": 0.22998278088678434, "grad_norm": 1.4112733602523804, "learning_rate": 4.375646546306944e-05, "loss": 4.7044, "step": 4274 }, { "epoch": 0.2300365906155833, "grad_norm": 1.7982693910598755, "learning_rate": 4.375367106222412e-05, "loss": 4.4696, "step": 4275 }, { "epoch": 0.23009040034438227, "grad_norm": 1.3326207399368286, "learning_rate": 4.375087612544932e-05, "loss": 4.1402, "step": 4276 }, { "epoch": 0.23014421007318123, "grad_norm": 2.123547077178955, "learning_rate": 4.3748080652824915e-05, "loss": 4.4797, "step": 4277 }, { "epoch": 0.2301980198019802, "grad_norm": 1.6465529203414917, "learning_rate": 4.3745284644430804e-05, "loss": 4.6365, "step": 4278 }, { "epoch": 0.23025182953077916, "grad_norm": 2.3761377334594727, "learning_rate": 4.374248810034686e-05, "loss": 4.1366, "step": 4279 }, { "epoch": 0.23030563925957814, "grad_norm": 1.5646443367004395, "learning_rate": 4.373969102065302e-05, "loss": 4.6575, "step": 4280 }, { "epoch": 0.2303594489883771, "grad_norm": 1.3208491802215576, "learning_rate": 4.373689340542922e-05, "loss": 5.0958, "step": 4281 }, { "epoch": 0.23041325871717608, "grad_norm": 1.9442623853683472, "learning_rate": 4.37340952547554e-05, "loss": 4.6711, "step": 4282 }, { "epoch": 0.23046706844597503, "grad_norm": 1.2626534700393677, "learning_rate": 4.373129656871153e-05, "loss": 4.385, "step": 4283 }, { "epoch": 0.23052087817477399, "grad_norm": 1.4789997339248657, "learning_rate": 4.372849734737758e-05, "loss": 4.7087, "step": 4284 }, { "epoch": 0.23057468790357297, "grad_norm": 0.9819945693016052, "learning_rate": 4.372569759083355e-05, "loss": 4.8367, "step": 4285 }, { "epoch": 0.23062849763237192, "grad_norm": 1.2108843326568604, "learning_rate": 4.3722897299159446e-05, "loss": 4.6169, "step": 4286 }, { "epoch": 0.2306823073611709, "grad_norm": 1.889590859413147, "learning_rate": 4.37200964724353e-05, "loss": 4.5015, "step": 4287 }, { "epoch": 0.23073611708996986, "grad_norm": 1.5294913053512573, "learning_rate": 4.371729511074115e-05, "loss": 4.4076, "step": 4288 }, { "epoch": 0.23078992681876884, "grad_norm": 1.3681058883666992, "learning_rate": 4.371449321415705e-05, "loss": 4.5119, "step": 4289 }, { "epoch": 0.2308437365475678, "grad_norm": 1.1699061393737793, "learning_rate": 4.371169078276307e-05, "loss": 4.6306, "step": 4290 }, { "epoch": 0.23089754627636677, "grad_norm": 1.0945004224777222, "learning_rate": 4.3708887816639286e-05, "loss": 4.7026, "step": 4291 }, { "epoch": 0.23095135600516573, "grad_norm": 1.7822362184524536, "learning_rate": 4.3706084315865824e-05, "loss": 4.8265, "step": 4292 }, { "epoch": 0.2310051657339647, "grad_norm": 1.9544827938079834, "learning_rate": 4.370328028052278e-05, "loss": 4.5055, "step": 4293 }, { "epoch": 0.23105897546276366, "grad_norm": 2.2057790756225586, "learning_rate": 4.3700475710690287e-05, "loss": 4.6463, "step": 4294 }, { "epoch": 0.23111278519156264, "grad_norm": 1.8476544618606567, "learning_rate": 4.36976706064485e-05, "loss": 4.8183, "step": 4295 }, { "epoch": 0.2311665949203616, "grad_norm": 1.139387607574463, "learning_rate": 4.369486496787758e-05, "loss": 4.6581, "step": 4296 }, { "epoch": 0.23122040464916058, "grad_norm": 1.2746541500091553, "learning_rate": 4.36920587950577e-05, "loss": 4.683, "step": 4297 }, { "epoch": 0.23127421437795953, "grad_norm": 0.8380082845687866, "learning_rate": 4.3689252088069055e-05, "loss": 4.6623, "step": 4298 }, { "epoch": 0.2313280241067585, "grad_norm": 2.031965494155884, "learning_rate": 4.3686444846991845e-05, "loss": 4.3895, "step": 4299 }, { "epoch": 0.23138183383555747, "grad_norm": 1.8545790910720825, "learning_rate": 4.368363707190631e-05, "loss": 4.6352, "step": 4300 }, { "epoch": 0.23143564356435645, "grad_norm": 1.717929720878601, "learning_rate": 4.368082876289269e-05, "loss": 4.6368, "step": 4301 }, { "epoch": 0.2314894532931554, "grad_norm": 1.9342100620269775, "learning_rate": 4.367801992003122e-05, "loss": 4.9347, "step": 4302 }, { "epoch": 0.23154326302195438, "grad_norm": 1.879477858543396, "learning_rate": 4.367521054340218e-05, "loss": 4.5107, "step": 4303 }, { "epoch": 0.23159707275075334, "grad_norm": 1.677054524421692, "learning_rate": 4.3672400633085854e-05, "loss": 4.6631, "step": 4304 }, { "epoch": 0.23165088247955232, "grad_norm": 1.421602487564087, "learning_rate": 4.3669590189162534e-05, "loss": 4.7073, "step": 4305 }, { "epoch": 0.23170469220835127, "grad_norm": 2.0812995433807373, "learning_rate": 4.366677921171255e-05, "loss": 4.809, "step": 4306 }, { "epoch": 0.23175850193715022, "grad_norm": 1.8752436637878418, "learning_rate": 4.366396770081622e-05, "loss": 4.3516, "step": 4307 }, { "epoch": 0.2318123116659492, "grad_norm": 1.3363749980926514, "learning_rate": 4.36611556565539e-05, "loss": 4.8214, "step": 4308 }, { "epoch": 0.23186612139474816, "grad_norm": 2.2995903491973877, "learning_rate": 4.3658343079005934e-05, "loss": 4.4745, "step": 4309 }, { "epoch": 0.23191993112354714, "grad_norm": 2.694877862930298, "learning_rate": 4.3655529968252715e-05, "loss": 4.1352, "step": 4310 }, { "epoch": 0.2319737408523461, "grad_norm": 1.7661288976669312, "learning_rate": 4.365271632437462e-05, "loss": 4.4893, "step": 4311 }, { "epoch": 0.23202755058114508, "grad_norm": 1.5093992948532104, "learning_rate": 4.3649902147452074e-05, "loss": 4.7559, "step": 4312 }, { "epoch": 0.23208136030994403, "grad_norm": 1.754501461982727, "learning_rate": 4.364708743756547e-05, "loss": 4.7301, "step": 4313 }, { "epoch": 0.232135170038743, "grad_norm": 1.5402452945709229, "learning_rate": 4.364427219479528e-05, "loss": 4.4412, "step": 4314 }, { "epoch": 0.23218897976754196, "grad_norm": 1.6810111999511719, "learning_rate": 4.364145641922192e-05, "loss": 4.7774, "step": 4315 }, { "epoch": 0.23224278949634095, "grad_norm": 2.2559168338775635, "learning_rate": 4.3638640110925885e-05, "loss": 4.106, "step": 4316 }, { "epoch": 0.2322965992251399, "grad_norm": 2.3422763347625732, "learning_rate": 4.363582326998765e-05, "loss": 4.8733, "step": 4317 }, { "epoch": 0.23235040895393888, "grad_norm": 2.13710618019104, "learning_rate": 4.3633005896487705e-05, "loss": 4.4977, "step": 4318 }, { "epoch": 0.23240421868273783, "grad_norm": 2.6119871139526367, "learning_rate": 4.363018799050657e-05, "loss": 4.3665, "step": 4319 }, { "epoch": 0.23245802841153682, "grad_norm": 2.4061362743377686, "learning_rate": 4.3627369552124776e-05, "loss": 4.2295, "step": 4320 }, { "epoch": 0.23251183814033577, "grad_norm": 1.2711117267608643, "learning_rate": 4.3624550581422855e-05, "loss": 4.5825, "step": 4321 }, { "epoch": 0.23256564786913475, "grad_norm": 1.8012999296188354, "learning_rate": 4.362173107848138e-05, "loss": 4.9467, "step": 4322 }, { "epoch": 0.2326194575979337, "grad_norm": 2.3190667629241943, "learning_rate": 4.361891104338091e-05, "loss": 4.7665, "step": 4323 }, { "epoch": 0.23267326732673269, "grad_norm": 1.9854211807250977, "learning_rate": 4.361609047620204e-05, "loss": 4.6384, "step": 4324 }, { "epoch": 0.23272707705553164, "grad_norm": 1.1874220371246338, "learning_rate": 4.3613269377025376e-05, "loss": 4.7859, "step": 4325 }, { "epoch": 0.23278088678433062, "grad_norm": 1.4206535816192627, "learning_rate": 4.361044774593155e-05, "loss": 5.0413, "step": 4326 }, { "epoch": 0.23283469651312957, "grad_norm": 1.905735731124878, "learning_rate": 4.360762558300117e-05, "loss": 4.3506, "step": 4327 }, { "epoch": 0.23288850624192853, "grad_norm": 1.4519340991973877, "learning_rate": 4.360480288831491e-05, "loss": 4.6752, "step": 4328 }, { "epoch": 0.2329423159707275, "grad_norm": 1.7645442485809326, "learning_rate": 4.360197966195342e-05, "loss": 4.5438, "step": 4329 }, { "epoch": 0.23299612569952646, "grad_norm": 1.1470222473144531, "learning_rate": 4.359915590399738e-05, "loss": 5.02, "step": 4330 }, { "epoch": 0.23304993542832544, "grad_norm": 1.5959423780441284, "learning_rate": 4.359633161452749e-05, "loss": 4.7395, "step": 4331 }, { "epoch": 0.2331037451571244, "grad_norm": 2.330240249633789, "learning_rate": 4.359350679362447e-05, "loss": 4.455, "step": 4332 }, { "epoch": 0.23315755488592338, "grad_norm": 1.5276097059249878, "learning_rate": 4.359068144136903e-05, "loss": 4.4626, "step": 4333 }, { "epoch": 0.23321136461472233, "grad_norm": 1.7592836618423462, "learning_rate": 4.358785555784192e-05, "loss": 4.5431, "step": 4334 }, { "epoch": 0.23326517434352131, "grad_norm": 1.3347996473312378, "learning_rate": 4.358502914312389e-05, "loss": 4.6567, "step": 4335 }, { "epoch": 0.23331898407232027, "grad_norm": 1.9356006383895874, "learning_rate": 4.3582202197295715e-05, "loss": 4.8361, "step": 4336 }, { "epoch": 0.23337279380111925, "grad_norm": 1.4637748003005981, "learning_rate": 4.357937472043818e-05, "loss": 4.4397, "step": 4337 }, { "epoch": 0.2334266035299182, "grad_norm": 1.2981548309326172, "learning_rate": 4.357654671263209e-05, "loss": 4.4862, "step": 4338 }, { "epoch": 0.23348041325871718, "grad_norm": 2.241626262664795, "learning_rate": 4.357371817395827e-05, "loss": 4.602, "step": 4339 }, { "epoch": 0.23353422298751614, "grad_norm": 2.429478406906128, "learning_rate": 4.357088910449752e-05, "loss": 4.6117, "step": 4340 }, { "epoch": 0.23358803271631512, "grad_norm": 1.99552321434021, "learning_rate": 4.356805950433073e-05, "loss": 4.7971, "step": 4341 }, { "epoch": 0.23364184244511407, "grad_norm": 2.7304961681365967, "learning_rate": 4.356522937353873e-05, "loss": 4.5455, "step": 4342 }, { "epoch": 0.23369565217391305, "grad_norm": 1.9110950231552124, "learning_rate": 4.3562398712202415e-05, "loss": 4.401, "step": 4343 }, { "epoch": 0.233749461902712, "grad_norm": 1.318566083908081, "learning_rate": 4.355956752040267e-05, "loss": 4.5832, "step": 4344 }, { "epoch": 0.233803271631511, "grad_norm": 1.3415881395339966, "learning_rate": 4.35567357982204e-05, "loss": 4.1185, "step": 4345 }, { "epoch": 0.23385708136030994, "grad_norm": 1.6960641145706177, "learning_rate": 4.355390354573654e-05, "loss": 4.3236, "step": 4346 }, { "epoch": 0.23391089108910892, "grad_norm": 2.163435697555542, "learning_rate": 4.355107076303202e-05, "loss": 5.0536, "step": 4347 }, { "epoch": 0.23396470081790788, "grad_norm": 2.1028709411621094, "learning_rate": 4.354823745018779e-05, "loss": 5.0251, "step": 4348 }, { "epoch": 0.23401851054670683, "grad_norm": 1.0239756107330322, "learning_rate": 4.354540360728483e-05, "loss": 4.6856, "step": 4349 }, { "epoch": 0.2340723202755058, "grad_norm": 2.041306495666504, "learning_rate": 4.354256923440411e-05, "loss": 5.0065, "step": 4350 }, { "epoch": 0.23412613000430477, "grad_norm": 0.9538405537605286, "learning_rate": 4.353973433162664e-05, "loss": 4.8228, "step": 4351 }, { "epoch": 0.23417993973310375, "grad_norm": 1.528704285621643, "learning_rate": 4.353689889903342e-05, "loss": 4.5061, "step": 4352 }, { "epoch": 0.2342337494619027, "grad_norm": 2.0283000469207764, "learning_rate": 4.353406293670549e-05, "loss": 4.2458, "step": 4353 }, { "epoch": 0.23428755919070168, "grad_norm": 1.1910386085510254, "learning_rate": 4.3531226444723894e-05, "loss": 5.0004, "step": 4354 }, { "epoch": 0.23434136891950064, "grad_norm": 1.1284974813461304, "learning_rate": 4.352838942316969e-05, "loss": 4.8917, "step": 4355 }, { "epoch": 0.23439517864829962, "grad_norm": 1.8297326564788818, "learning_rate": 4.352555187212396e-05, "loss": 4.6708, "step": 4356 }, { "epoch": 0.23444898837709857, "grad_norm": 1.9457823038101196, "learning_rate": 4.352271379166777e-05, "loss": 4.7822, "step": 4357 }, { "epoch": 0.23450279810589755, "grad_norm": 1.5939873456954956, "learning_rate": 4.3519875181882255e-05, "loss": 4.6555, "step": 4358 }, { "epoch": 0.2345566078346965, "grad_norm": 1.6854742765426636, "learning_rate": 4.3517036042848505e-05, "loss": 4.6356, "step": 4359 }, { "epoch": 0.2346104175634955, "grad_norm": 1.4828219413757324, "learning_rate": 4.351419637464768e-05, "loss": 4.2305, "step": 4360 }, { "epoch": 0.23466422729229444, "grad_norm": 2.084693431854248, "learning_rate": 4.351135617736092e-05, "loss": 4.6953, "step": 4361 }, { "epoch": 0.23471803702109342, "grad_norm": 2.0747649669647217, "learning_rate": 4.3508515451069384e-05, "loss": 4.2414, "step": 4362 }, { "epoch": 0.23477184674989238, "grad_norm": 1.8430962562561035, "learning_rate": 4.350567419585426e-05, "loss": 4.7376, "step": 4363 }, { "epoch": 0.23482565647869136, "grad_norm": 1.2876485586166382, "learning_rate": 4.350283241179674e-05, "loss": 4.3711, "step": 4364 }, { "epoch": 0.2348794662074903, "grad_norm": 1.7072862386703491, "learning_rate": 4.349999009897804e-05, "loss": 4.6134, "step": 4365 }, { "epoch": 0.2349332759362893, "grad_norm": 1.9234774112701416, "learning_rate": 4.3497147257479384e-05, "loss": 4.3197, "step": 4366 }, { "epoch": 0.23498708566508825, "grad_norm": 1.8308017253875732, "learning_rate": 4.3494303887382015e-05, "loss": 4.9379, "step": 4367 }, { "epoch": 0.23504089539388723, "grad_norm": 1.7508198022842407, "learning_rate": 4.349145998876718e-05, "loss": 4.6591, "step": 4368 }, { "epoch": 0.23509470512268618, "grad_norm": 2.2513115406036377, "learning_rate": 4.348861556171615e-05, "loss": 4.3607, "step": 4369 }, { "epoch": 0.23514851485148514, "grad_norm": 1.8118408918380737, "learning_rate": 4.3485770606310216e-05, "loss": 4.4043, "step": 4370 }, { "epoch": 0.23520232458028412, "grad_norm": 1.9050990343093872, "learning_rate": 4.348292512263068e-05, "loss": 4.9082, "step": 4371 }, { "epoch": 0.23525613430908307, "grad_norm": 1.4691569805145264, "learning_rate": 4.348007911075886e-05, "loss": 4.6665, "step": 4372 }, { "epoch": 0.23530994403788205, "grad_norm": 2.0711669921875, "learning_rate": 4.347723257077609e-05, "loss": 4.4849, "step": 4373 }, { "epoch": 0.235363753766681, "grad_norm": 2.1426596641540527, "learning_rate": 4.34743855027637e-05, "loss": 4.4679, "step": 4374 }, { "epoch": 0.23541756349548, "grad_norm": 1.38064706325531, "learning_rate": 4.3471537906803075e-05, "loss": 4.2823, "step": 4375 }, { "epoch": 0.23547137322427894, "grad_norm": 1.3551422357559204, "learning_rate": 4.346868978297556e-05, "loss": 4.5363, "step": 4376 }, { "epoch": 0.23552518295307792, "grad_norm": 1.899259090423584, "learning_rate": 4.3465841131362584e-05, "loss": 4.4158, "step": 4377 }, { "epoch": 0.23557899268187688, "grad_norm": 1.1276353597640991, "learning_rate": 4.3462991952045526e-05, "loss": 4.6451, "step": 4378 }, { "epoch": 0.23563280241067586, "grad_norm": 1.6970657110214233, "learning_rate": 4.346014224510583e-05, "loss": 4.0037, "step": 4379 }, { "epoch": 0.2356866121394748, "grad_norm": 1.9522031545639038, "learning_rate": 4.34572920106249e-05, "loss": 4.7506, "step": 4380 }, { "epoch": 0.2357404218682738, "grad_norm": 1.6319082975387573, "learning_rate": 4.345444124868423e-05, "loss": 4.1329, "step": 4381 }, { "epoch": 0.23579423159707275, "grad_norm": 1.7868963479995728, "learning_rate": 4.345158995936525e-05, "loss": 4.7656, "step": 4382 }, { "epoch": 0.23584804132587173, "grad_norm": 1.4195942878723145, "learning_rate": 4.344873814274947e-05, "loss": 4.7296, "step": 4383 }, { "epoch": 0.23590185105467068, "grad_norm": 1.6506766080856323, "learning_rate": 4.344588579891836e-05, "loss": 4.8265, "step": 4384 }, { "epoch": 0.23595566078346966, "grad_norm": 1.2992160320281982, "learning_rate": 4.3443032927953466e-05, "loss": 4.7247, "step": 4385 }, { "epoch": 0.23600947051226862, "grad_norm": 2.730618715286255, "learning_rate": 4.3440179529936284e-05, "loss": 4.0719, "step": 4386 }, { "epoch": 0.2360632802410676, "grad_norm": 1.1072888374328613, "learning_rate": 4.3437325604948376e-05, "loss": 4.7853, "step": 4387 }, { "epoch": 0.23611708996986655, "grad_norm": 2.0585806369781494, "learning_rate": 4.343447115307129e-05, "loss": 4.6186, "step": 4388 }, { "epoch": 0.23617089969866553, "grad_norm": 1.1505159139633179, "learning_rate": 4.343161617438659e-05, "loss": 4.5537, "step": 4389 }, { "epoch": 0.23622470942746449, "grad_norm": 1.8321369886398315, "learning_rate": 4.3428760668975885e-05, "loss": 4.7814, "step": 4390 }, { "epoch": 0.23627851915626344, "grad_norm": 1.4531198740005493, "learning_rate": 4.342590463692078e-05, "loss": 4.6627, "step": 4391 }, { "epoch": 0.23633232888506242, "grad_norm": 1.223516583442688, "learning_rate": 4.342304807830286e-05, "loss": 4.349, "step": 4392 }, { "epoch": 0.23638613861386137, "grad_norm": 2.6312341690063477, "learning_rate": 4.342019099320379e-05, "loss": 3.7333, "step": 4393 }, { "epoch": 0.23643994834266036, "grad_norm": 1.9548102617263794, "learning_rate": 4.3417333381705205e-05, "loss": 4.501, "step": 4394 }, { "epoch": 0.2364937580714593, "grad_norm": 1.6074626445770264, "learning_rate": 4.3414475243888765e-05, "loss": 4.3775, "step": 4395 }, { "epoch": 0.2365475678002583, "grad_norm": 1.3958112001419067, "learning_rate": 4.341161657983615e-05, "loss": 4.8608, "step": 4396 }, { "epoch": 0.23660137752905724, "grad_norm": 1.7855806350708008, "learning_rate": 4.340875738962906e-05, "loss": 4.6856, "step": 4397 }, { "epoch": 0.23665518725785623, "grad_norm": 1.4728769063949585, "learning_rate": 4.3405897673349196e-05, "loss": 4.9791, "step": 4398 }, { "epoch": 0.23670899698665518, "grad_norm": 1.959725260734558, "learning_rate": 4.340303743107829e-05, "loss": 4.4013, "step": 4399 }, { "epoch": 0.23676280671545416, "grad_norm": 1.9940054416656494, "learning_rate": 4.340017666289805e-05, "loss": 4.6111, "step": 4400 }, { "epoch": 0.23681661644425311, "grad_norm": 1.3721529245376587, "learning_rate": 4.339731536889027e-05, "loss": 4.7661, "step": 4401 }, { "epoch": 0.2368704261730521, "grad_norm": 2.0633456707000732, "learning_rate": 4.33944535491367e-05, "loss": 4.8332, "step": 4402 }, { "epoch": 0.23692423590185105, "grad_norm": 1.4633315801620483, "learning_rate": 4.339159120371912e-05, "loss": 4.9255, "step": 4403 }, { "epoch": 0.23697804563065003, "grad_norm": 1.0985749959945679, "learning_rate": 4.338872833271933e-05, "loss": 4.6184, "step": 4404 }, { "epoch": 0.23703185535944898, "grad_norm": 1.848535418510437, "learning_rate": 4.338586493621914e-05, "loss": 4.6669, "step": 4405 }, { "epoch": 0.23708566508824797, "grad_norm": 1.7016607522964478, "learning_rate": 4.338300101430039e-05, "loss": 4.9138, "step": 4406 }, { "epoch": 0.23713947481704692, "grad_norm": 0.9443835616111755, "learning_rate": 4.3380136567044906e-05, "loss": 4.6911, "step": 4407 }, { "epoch": 0.2371932845458459, "grad_norm": 1.774299144744873, "learning_rate": 4.337727159453456e-05, "loss": 4.3457, "step": 4408 }, { "epoch": 0.23724709427464485, "grad_norm": 1.6399623155593872, "learning_rate": 4.337440609685123e-05, "loss": 5.0524, "step": 4409 }, { "epoch": 0.23730090400344384, "grad_norm": 1.2886663675308228, "learning_rate": 4.3371540074076784e-05, "loss": 4.5729, "step": 4410 }, { "epoch": 0.2373547137322428, "grad_norm": 1.3047716617584229, "learning_rate": 4.336867352629314e-05, "loss": 4.4811, "step": 4411 }, { "epoch": 0.23740852346104174, "grad_norm": 3.3272604942321777, "learning_rate": 4.336580645358221e-05, "loss": 3.734, "step": 4412 }, { "epoch": 0.23746233318984072, "grad_norm": 1.953664779663086, "learning_rate": 4.336293885602594e-05, "loss": 4.479, "step": 4413 }, { "epoch": 0.23751614291863968, "grad_norm": 1.740648627281189, "learning_rate": 4.336007073370625e-05, "loss": 4.728, "step": 4414 }, { "epoch": 0.23756995264743866, "grad_norm": 1.2840468883514404, "learning_rate": 4.335720208670513e-05, "loss": 4.4718, "step": 4415 }, { "epoch": 0.2376237623762376, "grad_norm": 1.2897435426712036, "learning_rate": 4.3354332915104554e-05, "loss": 4.6416, "step": 4416 }, { "epoch": 0.2376775721050366, "grad_norm": 0.9298606514930725, "learning_rate": 4.335146321898651e-05, "loss": 5.0401, "step": 4417 }, { "epoch": 0.23773138183383555, "grad_norm": 2.1769227981567383, "learning_rate": 4.3348592998433004e-05, "loss": 4.1103, "step": 4418 }, { "epoch": 0.23778519156263453, "grad_norm": 1.991008996963501, "learning_rate": 4.3345722253526056e-05, "loss": 4.8896, "step": 4419 }, { "epoch": 0.23783900129143348, "grad_norm": 1.7937934398651123, "learning_rate": 4.334285098434771e-05, "loss": 4.2662, "step": 4420 }, { "epoch": 0.23789281102023246, "grad_norm": 1.1645474433898926, "learning_rate": 4.333997919098003e-05, "loss": 5.0661, "step": 4421 }, { "epoch": 0.23794662074903142, "grad_norm": 1.3062503337860107, "learning_rate": 4.333710687350507e-05, "loss": 4.8996, "step": 4422 }, { "epoch": 0.2380004304778304, "grad_norm": 1.5261421203613281, "learning_rate": 4.333423403200492e-05, "loss": 4.7371, "step": 4423 }, { "epoch": 0.23805424020662935, "grad_norm": 1.8795794248580933, "learning_rate": 4.333136066656167e-05, "loss": 4.0694, "step": 4424 }, { "epoch": 0.23810804993542833, "grad_norm": 1.9183831214904785, "learning_rate": 4.3328486777257435e-05, "loss": 4.6307, "step": 4425 }, { "epoch": 0.2381618596642273, "grad_norm": 1.195044994354248, "learning_rate": 4.332561236417435e-05, "loss": 4.736, "step": 4426 }, { "epoch": 0.23821566939302627, "grad_norm": 1.8057667016983032, "learning_rate": 4.3322737427394555e-05, "loss": 4.5702, "step": 4427 }, { "epoch": 0.23826947912182522, "grad_norm": 1.1780543327331543, "learning_rate": 4.3319861967000194e-05, "loss": 5.0432, "step": 4428 }, { "epoch": 0.2383232888506242, "grad_norm": 2.067643404006958, "learning_rate": 4.331698598307346e-05, "loss": 4.3826, "step": 4429 }, { "epoch": 0.23837709857942316, "grad_norm": 2.3077473640441895, "learning_rate": 4.3314109475696546e-05, "loss": 4.3528, "step": 4430 }, { "epoch": 0.23843090830822214, "grad_norm": 1.6487714052200317, "learning_rate": 4.331123244495163e-05, "loss": 4.8808, "step": 4431 }, { "epoch": 0.2384847180370211, "grad_norm": 1.0521681308746338, "learning_rate": 4.3308354890920944e-05, "loss": 4.6867, "step": 4432 }, { "epoch": 0.23853852776582005, "grad_norm": 1.8294398784637451, "learning_rate": 4.330547681368672e-05, "loss": 4.1857, "step": 4433 }, { "epoch": 0.23859233749461903, "grad_norm": 1.4334183931350708, "learning_rate": 4.33025982133312e-05, "loss": 4.5321, "step": 4434 }, { "epoch": 0.23864614722341798, "grad_norm": 1.862523078918457, "learning_rate": 4.3299719089936664e-05, "loss": 4.6953, "step": 4435 }, { "epoch": 0.23869995695221696, "grad_norm": 1.333458662033081, "learning_rate": 4.329683944358537e-05, "loss": 4.5381, "step": 4436 }, { "epoch": 0.23875376668101592, "grad_norm": 0.8572811484336853, "learning_rate": 4.3293959274359606e-05, "loss": 4.8157, "step": 4437 }, { "epoch": 0.2388075764098149, "grad_norm": 1.913581132888794, "learning_rate": 4.329107858234171e-05, "loss": 4.3363, "step": 4438 }, { "epoch": 0.23886138613861385, "grad_norm": 1.3356496095657349, "learning_rate": 4.328819736761397e-05, "loss": 4.2394, "step": 4439 }, { "epoch": 0.23891519586741283, "grad_norm": 1.1400538682937622, "learning_rate": 4.328531563025875e-05, "loss": 4.8304, "step": 4440 }, { "epoch": 0.2389690055962118, "grad_norm": 1.011035442352295, "learning_rate": 4.328243337035838e-05, "loss": 5.0913, "step": 4441 }, { "epoch": 0.23902281532501077, "grad_norm": 1.3541796207427979, "learning_rate": 4.3279550587995244e-05, "loss": 4.7945, "step": 4442 }, { "epoch": 0.23907662505380972, "grad_norm": 1.3227185010910034, "learning_rate": 4.327666728325172e-05, "loss": 4.4257, "step": 4443 }, { "epoch": 0.2391304347826087, "grad_norm": 1.8320815563201904, "learning_rate": 4.32737834562102e-05, "loss": 4.4868, "step": 4444 }, { "epoch": 0.23918424451140766, "grad_norm": 1.9462941884994507, "learning_rate": 4.3270899106953105e-05, "loss": 4.5365, "step": 4445 }, { "epoch": 0.23923805424020664, "grad_norm": 1.5886664390563965, "learning_rate": 4.3268014235562856e-05, "loss": 4.6507, "step": 4446 }, { "epoch": 0.2392918639690056, "grad_norm": 2.179187297821045, "learning_rate": 4.326512884212189e-05, "loss": 4.6457, "step": 4447 }, { "epoch": 0.23934567369780457, "grad_norm": 1.4041846990585327, "learning_rate": 4.326224292671267e-05, "loss": 4.5511, "step": 4448 }, { "epoch": 0.23939948342660353, "grad_norm": 2.4957971572875977, "learning_rate": 4.325935648941767e-05, "loss": 4.3904, "step": 4449 }, { "epoch": 0.2394532931554025, "grad_norm": 1.0754215717315674, "learning_rate": 4.325646953031937e-05, "loss": 4.5421, "step": 4450 }, { "epoch": 0.23950710288420146, "grad_norm": 1.7941163778305054, "learning_rate": 4.325358204950027e-05, "loss": 4.4232, "step": 4451 }, { "epoch": 0.23956091261300044, "grad_norm": 1.887123703956604, "learning_rate": 4.325069404704291e-05, "loss": 4.5942, "step": 4452 }, { "epoch": 0.2396147223417994, "grad_norm": 1.7320880889892578, "learning_rate": 4.3247805523029784e-05, "loss": 4.8527, "step": 4453 }, { "epoch": 0.23966853207059838, "grad_norm": 1.0423027276992798, "learning_rate": 4.324491647754346e-05, "loss": 4.8272, "step": 4454 }, { "epoch": 0.23972234179939733, "grad_norm": 1.6791772842407227, "learning_rate": 4.32420269106665e-05, "loss": 4.5376, "step": 4455 }, { "epoch": 0.23977615152819629, "grad_norm": 1.2934826612472534, "learning_rate": 4.323913682248148e-05, "loss": 4.9039, "step": 4456 }, { "epoch": 0.23982996125699527, "grad_norm": 1.2531765699386597, "learning_rate": 4.3236246213070986e-05, "loss": 4.8999, "step": 4457 }, { "epoch": 0.23988377098579422, "grad_norm": 1.8434258699417114, "learning_rate": 4.3233355082517627e-05, "loss": 4.4244, "step": 4458 }, { "epoch": 0.2399375807145932, "grad_norm": 1.1061116456985474, "learning_rate": 4.323046343090401e-05, "loss": 4.7118, "step": 4459 }, { "epoch": 0.23999139044339216, "grad_norm": 2.1045353412628174, "learning_rate": 4.322757125831279e-05, "loss": 4.5172, "step": 4460 }, { "epoch": 0.24004520017219114, "grad_norm": 2.0206871032714844, "learning_rate": 4.322467856482661e-05, "loss": 4.1533, "step": 4461 }, { "epoch": 0.2400990099009901, "grad_norm": 1.8055927753448486, "learning_rate": 4.322178535052813e-05, "loss": 4.3357, "step": 4462 }, { "epoch": 0.24015281962978907, "grad_norm": 2.0460927486419678, "learning_rate": 4.3218891615500044e-05, "loss": 4.5557, "step": 4463 }, { "epoch": 0.24020662935858803, "grad_norm": 1.3391916751861572, "learning_rate": 4.321599735982504e-05, "loss": 4.8122, "step": 4464 }, { "epoch": 0.240260439087387, "grad_norm": 2.7735486030578613, "learning_rate": 4.321310258358582e-05, "loss": 4.2805, "step": 4465 }, { "epoch": 0.24031424881618596, "grad_norm": 1.2800350189208984, "learning_rate": 4.321020728686511e-05, "loss": 4.6161, "step": 4466 }, { "epoch": 0.24036805854498494, "grad_norm": 1.0841845273971558, "learning_rate": 4.320731146974567e-05, "loss": 4.7297, "step": 4467 }, { "epoch": 0.2404218682737839, "grad_norm": 2.140249252319336, "learning_rate": 4.320441513231023e-05, "loss": 4.8258, "step": 4468 }, { "epoch": 0.24047567800258288, "grad_norm": 1.1808421611785889, "learning_rate": 4.320151827464157e-05, "loss": 4.6109, "step": 4469 }, { "epoch": 0.24052948773138183, "grad_norm": 1.2901654243469238, "learning_rate": 4.319862089682247e-05, "loss": 4.6195, "step": 4470 }, { "epoch": 0.2405832974601808, "grad_norm": 1.8011221885681152, "learning_rate": 4.319572299893575e-05, "loss": 4.6502, "step": 4471 }, { "epoch": 0.24063710718897977, "grad_norm": 1.6005324125289917, "learning_rate": 4.319282458106419e-05, "loss": 4.7151, "step": 4472 }, { "epoch": 0.24069091691777875, "grad_norm": 1.4917147159576416, "learning_rate": 4.3189925643290644e-05, "loss": 4.6848, "step": 4473 }, { "epoch": 0.2407447266465777, "grad_norm": 1.646606683731079, "learning_rate": 4.318702618569794e-05, "loss": 4.4782, "step": 4474 }, { "epoch": 0.24079853637537668, "grad_norm": 2.090381622314453, "learning_rate": 4.3184126208368956e-05, "loss": 4.3549, "step": 4475 }, { "epoch": 0.24085234610417564, "grad_norm": 2.9875426292419434, "learning_rate": 4.318122571138655e-05, "loss": 3.8315, "step": 4476 }, { "epoch": 0.2409061558329746, "grad_norm": 2.5813822746276855, "learning_rate": 4.317832469483362e-05, "loss": 4.2175, "step": 4477 }, { "epoch": 0.24095996556177357, "grad_norm": 1.7670037746429443, "learning_rate": 4.317542315879306e-05, "loss": 4.9501, "step": 4478 }, { "epoch": 0.24101377529057252, "grad_norm": 2.799804449081421, "learning_rate": 4.3172521103347796e-05, "loss": 4.3061, "step": 4479 }, { "epoch": 0.2410675850193715, "grad_norm": 1.3223503828048706, "learning_rate": 4.316961852858075e-05, "loss": 4.8947, "step": 4480 }, { "epoch": 0.24112139474817046, "grad_norm": 1.7726244926452637, "learning_rate": 4.316671543457488e-05, "loss": 4.4924, "step": 4481 }, { "epoch": 0.24117520447696944, "grad_norm": 2.323721408843994, "learning_rate": 4.316381182141315e-05, "loss": 4.0902, "step": 4482 }, { "epoch": 0.2412290142057684, "grad_norm": 1.2149766683578491, "learning_rate": 4.3160907689178526e-05, "loss": 4.6362, "step": 4483 }, { "epoch": 0.24128282393456738, "grad_norm": 1.4429477453231812, "learning_rate": 4.315800303795401e-05, "loss": 4.2729, "step": 4484 }, { "epoch": 0.24133663366336633, "grad_norm": 2.3897581100463867, "learning_rate": 4.3155097867822607e-05, "loss": 3.7967, "step": 4485 }, { "epoch": 0.2413904433921653, "grad_norm": 1.6901097297668457, "learning_rate": 4.315219217886734e-05, "loss": 4.68, "step": 4486 }, { "epoch": 0.24144425312096426, "grad_norm": 1.740866780281067, "learning_rate": 4.314928597117124e-05, "loss": 4.7353, "step": 4487 }, { "epoch": 0.24149806284976325, "grad_norm": 1.779313325881958, "learning_rate": 4.314637924481737e-05, "loss": 4.3041, "step": 4488 }, { "epoch": 0.2415518725785622, "grad_norm": 1.2810494899749756, "learning_rate": 4.314347199988878e-05, "loss": 4.8961, "step": 4489 }, { "epoch": 0.24160568230736118, "grad_norm": 1.8517591953277588, "learning_rate": 4.314056423646857e-05, "loss": 4.292, "step": 4490 }, { "epoch": 0.24165949203616013, "grad_norm": 1.950285792350769, "learning_rate": 4.313765595463982e-05, "loss": 4.6738, "step": 4491 }, { "epoch": 0.24171330176495912, "grad_norm": 1.6144839525222778, "learning_rate": 4.313474715448565e-05, "loss": 4.2941, "step": 4492 }, { "epoch": 0.24176711149375807, "grad_norm": 2.0651023387908936, "learning_rate": 4.313183783608919e-05, "loss": 4.5827, "step": 4493 }, { "epoch": 0.24182092122255705, "grad_norm": 2.3531322479248047, "learning_rate": 4.312892799953356e-05, "loss": 4.0537, "step": 4494 }, { "epoch": 0.241874730951356, "grad_norm": 1.5295761823654175, "learning_rate": 4.312601764490193e-05, "loss": 4.4226, "step": 4495 }, { "epoch": 0.24192854068015499, "grad_norm": 1.8203258514404297, "learning_rate": 4.3123106772277475e-05, "loss": 4.3506, "step": 4496 }, { "epoch": 0.24198235040895394, "grad_norm": 1.5368409156799316, "learning_rate": 4.312019538174337e-05, "loss": 4.8022, "step": 4497 }, { "epoch": 0.2420361601377529, "grad_norm": 0.9656983017921448, "learning_rate": 4.311728347338282e-05, "loss": 4.7418, "step": 4498 }, { "epoch": 0.24208996986655187, "grad_norm": 1.289625644683838, "learning_rate": 4.3114371047279044e-05, "loss": 4.4657, "step": 4499 }, { "epoch": 0.24214377959535083, "grad_norm": 1.7904218435287476, "learning_rate": 4.311145810351525e-05, "loss": 4.743, "step": 4500 }, { "epoch": 0.2421975893241498, "grad_norm": 1.7768906354904175, "learning_rate": 4.310854464217472e-05, "loss": 4.5312, "step": 4501 }, { "epoch": 0.24225139905294876, "grad_norm": 1.7310752868652344, "learning_rate": 4.310563066334068e-05, "loss": 4.6776, "step": 4502 }, { "epoch": 0.24230520878174774, "grad_norm": 1.1715961694717407, "learning_rate": 4.3102716167096406e-05, "loss": 4.6491, "step": 4503 }, { "epoch": 0.2423590185105467, "grad_norm": 1.9481314420700073, "learning_rate": 4.3099801153525196e-05, "loss": 4.8681, "step": 4504 }, { "epoch": 0.24241282823934568, "grad_norm": 2.1978814601898193, "learning_rate": 4.309688562271036e-05, "loss": 4.7039, "step": 4505 }, { "epoch": 0.24246663796814463, "grad_norm": 1.9808889627456665, "learning_rate": 4.3093969574735205e-05, "loss": 4.6834, "step": 4506 }, { "epoch": 0.24252044769694361, "grad_norm": 1.212988257408142, "learning_rate": 4.309105300968307e-05, "loss": 4.775, "step": 4507 }, { "epoch": 0.24257425742574257, "grad_norm": 1.6133077144622803, "learning_rate": 4.3088135927637294e-05, "loss": 4.4285, "step": 4508 }, { "epoch": 0.24262806715454155, "grad_norm": 1.3272161483764648, "learning_rate": 4.308521832868124e-05, "loss": 4.3659, "step": 4509 }, { "epoch": 0.2426818768833405, "grad_norm": 1.6183265447616577, "learning_rate": 4.3082300212898295e-05, "loss": 4.8217, "step": 4510 }, { "epoch": 0.24273568661213948, "grad_norm": 2.1909339427948, "learning_rate": 4.307938158037185e-05, "loss": 4.7468, "step": 4511 }, { "epoch": 0.24278949634093844, "grad_norm": 2.3966474533081055, "learning_rate": 4.30764624311853e-05, "loss": 4.9617, "step": 4512 }, { "epoch": 0.24284330606973742, "grad_norm": 1.5491023063659668, "learning_rate": 4.3073542765422083e-05, "loss": 4.5895, "step": 4513 }, { "epoch": 0.24289711579853637, "grad_norm": 1.8382068872451782, "learning_rate": 4.3070622583165624e-05, "loss": 4.8001, "step": 4514 }, { "epoch": 0.24295092552733535, "grad_norm": 1.2804101705551147, "learning_rate": 4.3067701884499366e-05, "loss": 4.7778, "step": 4515 }, { "epoch": 0.2430047352561343, "grad_norm": 1.2975764274597168, "learning_rate": 4.3064780669506795e-05, "loss": 4.5478, "step": 4516 }, { "epoch": 0.2430585449849333, "grad_norm": 1.8432137966156006, "learning_rate": 4.306185893827137e-05, "loss": 4.6922, "step": 4517 }, { "epoch": 0.24311235471373224, "grad_norm": 1.7480857372283936, "learning_rate": 4.30589366908766e-05, "loss": 4.6333, "step": 4518 }, { "epoch": 0.2431661644425312, "grad_norm": 1.6231849193572998, "learning_rate": 4.3056013927406004e-05, "loss": 4.7671, "step": 4519 }, { "epoch": 0.24321997417133018, "grad_norm": 1.3880655765533447, "learning_rate": 4.3053090647943086e-05, "loss": 4.5101, "step": 4520 }, { "epoch": 0.24327378390012913, "grad_norm": 2.547297239303589, "learning_rate": 4.3050166852571394e-05, "loss": 4.6313, "step": 4521 }, { "epoch": 0.2433275936289281, "grad_norm": 1.4019925594329834, "learning_rate": 4.3047242541374486e-05, "loss": 4.6839, "step": 4522 }, { "epoch": 0.24338140335772707, "grad_norm": 1.254737138748169, "learning_rate": 4.304431771443592e-05, "loss": 4.7583, "step": 4523 }, { "epoch": 0.24343521308652605, "grad_norm": 1.512892484664917, "learning_rate": 4.3041392371839294e-05, "loss": 4.4487, "step": 4524 }, { "epoch": 0.243489022815325, "grad_norm": 1.312617540359497, "learning_rate": 4.30384665136682e-05, "loss": 4.7652, "step": 4525 }, { "epoch": 0.24354283254412398, "grad_norm": 1.100006341934204, "learning_rate": 4.3035540140006246e-05, "loss": 4.55, "step": 4526 }, { "epoch": 0.24359664227292294, "grad_norm": 1.2908542156219482, "learning_rate": 4.303261325093707e-05, "loss": 4.3719, "step": 4527 }, { "epoch": 0.24365045200172192, "grad_norm": 1.2975033521652222, "learning_rate": 4.302968584654431e-05, "loss": 4.6609, "step": 4528 }, { "epoch": 0.24370426173052087, "grad_norm": 1.741666316986084, "learning_rate": 4.302675792691162e-05, "loss": 4.7374, "step": 4529 }, { "epoch": 0.24375807145931985, "grad_norm": 1.4516147375106812, "learning_rate": 4.302382949212267e-05, "loss": 4.498, "step": 4530 }, { "epoch": 0.2438118811881188, "grad_norm": 1.0128726959228516, "learning_rate": 4.3020900542261155e-05, "loss": 4.6312, "step": 4531 }, { "epoch": 0.2438656909169178, "grad_norm": 2.2435495853424072, "learning_rate": 4.3017971077410776e-05, "loss": 3.7848, "step": 4532 }, { "epoch": 0.24391950064571674, "grad_norm": 1.8441698551177979, "learning_rate": 4.301504109765525e-05, "loss": 4.6678, "step": 4533 }, { "epoch": 0.24397331037451572, "grad_norm": 1.5312086343765259, "learning_rate": 4.301211060307829e-05, "loss": 4.317, "step": 4534 }, { "epoch": 0.24402712010331468, "grad_norm": 1.644333004951477, "learning_rate": 4.300917959376367e-05, "loss": 5.1956, "step": 4535 }, { "epoch": 0.24408092983211366, "grad_norm": 1.9897409677505493, "learning_rate": 4.300624806979513e-05, "loss": 4.2936, "step": 4536 }, { "epoch": 0.2441347395609126, "grad_norm": 1.8778505325317383, "learning_rate": 4.300331603125645e-05, "loss": 4.2685, "step": 4537 }, { "epoch": 0.2441885492897116, "grad_norm": 1.931777000427246, "learning_rate": 4.300038347823142e-05, "loss": 4.6041, "step": 4538 }, { "epoch": 0.24424235901851055, "grad_norm": 1.2418419122695923, "learning_rate": 4.299745041080385e-05, "loss": 4.5735, "step": 4539 }, { "epoch": 0.2442961687473095, "grad_norm": 1.600730538368225, "learning_rate": 4.299451682905756e-05, "loss": 4.8958, "step": 4540 }, { "epoch": 0.24434997847610848, "grad_norm": 1.7242276668548584, "learning_rate": 4.299158273307637e-05, "loss": 4.6129, "step": 4541 }, { "epoch": 0.24440378820490744, "grad_norm": 1.380850911140442, "learning_rate": 4.2988648122944144e-05, "loss": 4.7993, "step": 4542 }, { "epoch": 0.24445759793370642, "grad_norm": 1.3028568029403687, "learning_rate": 4.298571299874473e-05, "loss": 4.7798, "step": 4543 }, { "epoch": 0.24451140766250537, "grad_norm": 2.101649284362793, "learning_rate": 4.298277736056202e-05, "loss": 4.2322, "step": 4544 }, { "epoch": 0.24456521739130435, "grad_norm": 1.194989800453186, "learning_rate": 4.297984120847989e-05, "loss": 4.6279, "step": 4545 }, { "epoch": 0.2446190271201033, "grad_norm": 0.9183930158615112, "learning_rate": 4.297690454258227e-05, "loss": 4.8243, "step": 4546 }, { "epoch": 0.2446728368489023, "grad_norm": 1.839417815208435, "learning_rate": 4.297396736295307e-05, "loss": 4.3704, "step": 4547 }, { "epoch": 0.24472664657770124, "grad_norm": 1.6900670528411865, "learning_rate": 4.297102966967622e-05, "loss": 4.4827, "step": 4548 }, { "epoch": 0.24478045630650022, "grad_norm": 1.2428791522979736, "learning_rate": 4.2968091462835684e-05, "loss": 4.4615, "step": 4549 }, { "epoch": 0.24483426603529918, "grad_norm": 3.0728681087493896, "learning_rate": 4.2965152742515426e-05, "loss": 3.7751, "step": 4550 }, { "epoch": 0.24488807576409816, "grad_norm": 2.46867299079895, "learning_rate": 4.296221350879941e-05, "loss": 3.9247, "step": 4551 }, { "epoch": 0.2449418854928971, "grad_norm": 1.6129201650619507, "learning_rate": 4.2959273761771654e-05, "loss": 4.1112, "step": 4552 }, { "epoch": 0.2449956952216961, "grad_norm": 2.253523349761963, "learning_rate": 4.2956333501516164e-05, "loss": 4.9972, "step": 4553 }, { "epoch": 0.24504950495049505, "grad_norm": 2.3050713539123535, "learning_rate": 4.295339272811695e-05, "loss": 4.3182, "step": 4554 }, { "epoch": 0.24510331467929403, "grad_norm": 1.757957935333252, "learning_rate": 4.295045144165807e-05, "loss": 4.2728, "step": 4555 }, { "epoch": 0.24515712440809298, "grad_norm": 1.4005478620529175, "learning_rate": 4.294750964222356e-05, "loss": 5.1987, "step": 4556 }, { "epoch": 0.24521093413689196, "grad_norm": 1.1692618131637573, "learning_rate": 4.29445673298975e-05, "loss": 4.5765, "step": 4557 }, { "epoch": 0.24526474386569092, "grad_norm": 1.143012285232544, "learning_rate": 4.294162450476396e-05, "loss": 4.6252, "step": 4558 }, { "epoch": 0.2453185535944899, "grad_norm": 1.7815256118774414, "learning_rate": 4.293868116690707e-05, "loss": 4.4814, "step": 4559 }, { "epoch": 0.24537236332328885, "grad_norm": 1.674292802810669, "learning_rate": 4.293573731641091e-05, "loss": 4.3549, "step": 4560 }, { "epoch": 0.2454261730520878, "grad_norm": 1.5585579872131348, "learning_rate": 4.2932792953359626e-05, "loss": 4.6991, "step": 4561 }, { "epoch": 0.24547998278088679, "grad_norm": 1.775922417640686, "learning_rate": 4.292984807783735e-05, "loss": 4.5479, "step": 4562 }, { "epoch": 0.24553379250968574, "grad_norm": 1.959948182106018, "learning_rate": 4.2926902689928233e-05, "loss": 4.4878, "step": 4563 }, { "epoch": 0.24558760223848472, "grad_norm": 1.9398467540740967, "learning_rate": 4.292395678971646e-05, "loss": 4.7761, "step": 4564 }, { "epoch": 0.24564141196728367, "grad_norm": 1.2776530981063843, "learning_rate": 4.292101037728622e-05, "loss": 4.6351, "step": 4565 }, { "epoch": 0.24569522169608266, "grad_norm": 1.9331908226013184, "learning_rate": 4.29180634527217e-05, "loss": 4.7586, "step": 4566 }, { "epoch": 0.2457490314248816, "grad_norm": 1.118078351020813, "learning_rate": 4.291511601610711e-05, "loss": 4.5565, "step": 4567 }, { "epoch": 0.2458028411536806, "grad_norm": 1.3062647581100464, "learning_rate": 4.2912168067526705e-05, "loss": 4.6845, "step": 4568 }, { "epoch": 0.24585665088247954, "grad_norm": 1.6890071630477905, "learning_rate": 4.290921960706471e-05, "loss": 4.4135, "step": 4569 }, { "epoch": 0.24591046061127853, "grad_norm": 2.0324697494506836, "learning_rate": 4.2906270634805384e-05, "loss": 4.2323, "step": 4570 }, { "epoch": 0.24596427034007748, "grad_norm": 2.8287100791931152, "learning_rate": 4.290332115083301e-05, "loss": 4.6775, "step": 4571 }, { "epoch": 0.24601808006887646, "grad_norm": 1.9430513381958008, "learning_rate": 4.2900371155231867e-05, "loss": 4.245, "step": 4572 }, { "epoch": 0.2460718897976754, "grad_norm": 1.7245522737503052, "learning_rate": 4.2897420648086275e-05, "loss": 4.6362, "step": 4573 }, { "epoch": 0.2461256995264744, "grad_norm": 2.184657573699951, "learning_rate": 4.2894469629480527e-05, "loss": 4.1021, "step": 4574 }, { "epoch": 0.24617950925527335, "grad_norm": 1.1917999982833862, "learning_rate": 4.2891518099498965e-05, "loss": 4.7859, "step": 4575 }, { "epoch": 0.24623331898407233, "grad_norm": 0.9588358998298645, "learning_rate": 4.288856605822595e-05, "loss": 4.9361, "step": 4576 }, { "epoch": 0.24628712871287128, "grad_norm": 2.015979766845703, "learning_rate": 4.2885613505745826e-05, "loss": 4.8825, "step": 4577 }, { "epoch": 0.24634093844167027, "grad_norm": 1.4323168992996216, "learning_rate": 4.288266044214297e-05, "loss": 4.7327, "step": 4578 }, { "epoch": 0.24639474817046922, "grad_norm": 1.5783103704452515, "learning_rate": 4.287970686750178e-05, "loss": 4.2798, "step": 4579 }, { "epoch": 0.2464485578992682, "grad_norm": 1.1353009939193726, "learning_rate": 4.287675278190666e-05, "loss": 4.7679, "step": 4580 }, { "epoch": 0.24650236762806715, "grad_norm": 1.2140206098556519, "learning_rate": 4.287379818544203e-05, "loss": 4.489, "step": 4581 }, { "epoch": 0.24655617735686614, "grad_norm": 2.055898666381836, "learning_rate": 4.287084307819232e-05, "loss": 4.3721, "step": 4582 }, { "epoch": 0.2466099870856651, "grad_norm": 1.9668244123458862, "learning_rate": 4.286788746024199e-05, "loss": 4.2311, "step": 4583 }, { "epoch": 0.24666379681446404, "grad_norm": 1.8954154253005981, "learning_rate": 4.2864931331675485e-05, "loss": 4.1795, "step": 4584 }, { "epoch": 0.24671760654326302, "grad_norm": 1.9785220623016357, "learning_rate": 4.28619746925773e-05, "loss": 4.3359, "step": 4585 }, { "epoch": 0.24677141627206198, "grad_norm": 1.4547749757766724, "learning_rate": 4.285901754303192e-05, "loss": 4.552, "step": 4586 }, { "epoch": 0.24682522600086096, "grad_norm": 1.7429473400115967, "learning_rate": 4.2856059883123855e-05, "loss": 4.5535, "step": 4587 }, { "epoch": 0.2468790357296599, "grad_norm": 1.993589162826538, "learning_rate": 4.285310171293762e-05, "loss": 4.8476, "step": 4588 }, { "epoch": 0.2469328454584589, "grad_norm": 1.521569013595581, "learning_rate": 4.285014303255776e-05, "loss": 4.448, "step": 4589 }, { "epoch": 0.24698665518725785, "grad_norm": 2.5270299911499023, "learning_rate": 4.2847183842068825e-05, "loss": 4.2804, "step": 4590 }, { "epoch": 0.24704046491605683, "grad_norm": 1.7172813415527344, "learning_rate": 4.284422414155538e-05, "loss": 4.5088, "step": 4591 }, { "epoch": 0.24709427464485578, "grad_norm": 2.6909236907958984, "learning_rate": 4.2841263931102e-05, "loss": 4.512, "step": 4592 }, { "epoch": 0.24714808437365476, "grad_norm": 2.4652602672576904, "learning_rate": 4.2838303210793284e-05, "loss": 3.9801, "step": 4593 }, { "epoch": 0.24720189410245372, "grad_norm": 1.6434651613235474, "learning_rate": 4.283534198071385e-05, "loss": 4.7, "step": 4594 }, { "epoch": 0.2472557038312527, "grad_norm": 2.23337459564209, "learning_rate": 4.28323802409483e-05, "loss": 4.5221, "step": 4595 }, { "epoch": 0.24730951356005165, "grad_norm": 2.1262238025665283, "learning_rate": 4.28294179915813e-05, "loss": 4.4417, "step": 4596 }, { "epoch": 0.24736332328885063, "grad_norm": 1.5592643022537231, "learning_rate": 4.2826455232697485e-05, "loss": 4.4504, "step": 4597 }, { "epoch": 0.2474171330176496, "grad_norm": 2.1350152492523193, "learning_rate": 4.282349196438152e-05, "loss": 4.3989, "step": 4598 }, { "epoch": 0.24747094274644857, "grad_norm": 1.756447434425354, "learning_rate": 4.28205281867181e-05, "loss": 4.6311, "step": 4599 }, { "epoch": 0.24752475247524752, "grad_norm": 2.387083053588867, "learning_rate": 4.281756389979191e-05, "loss": 4.3301, "step": 4600 }, { "epoch": 0.2475785622040465, "grad_norm": 2.106531858444214, "learning_rate": 4.281459910368768e-05, "loss": 4.2544, "step": 4601 }, { "epoch": 0.24763237193284546, "grad_norm": 1.552809476852417, "learning_rate": 4.281163379849011e-05, "loss": 4.6544, "step": 4602 }, { "epoch": 0.24768618166164444, "grad_norm": 1.4664498567581177, "learning_rate": 4.280866798428396e-05, "loss": 4.5779, "step": 4603 }, { "epoch": 0.2477399913904434, "grad_norm": 1.1997246742248535, "learning_rate": 4.280570166115397e-05, "loss": 4.5248, "step": 4604 }, { "epoch": 0.24779380111924235, "grad_norm": 3.377753496170044, "learning_rate": 4.2802734829184935e-05, "loss": 4.6988, "step": 4605 }, { "epoch": 0.24784761084804133, "grad_norm": 1.6524913311004639, "learning_rate": 4.279976748846162e-05, "loss": 4.3238, "step": 4606 }, { "epoch": 0.24790142057684028, "grad_norm": 2.158350944519043, "learning_rate": 4.2796799639068816e-05, "loss": 4.5345, "step": 4607 }, { "epoch": 0.24795523030563926, "grad_norm": 1.8629354238510132, "learning_rate": 4.279383128109135e-05, "loss": 4.3452, "step": 4608 }, { "epoch": 0.24800904003443822, "grad_norm": 2.015552282333374, "learning_rate": 4.279086241461404e-05, "loss": 3.8219, "step": 4609 }, { "epoch": 0.2480628497632372, "grad_norm": 2.2863218784332275, "learning_rate": 4.2787893039721744e-05, "loss": 4.2633, "step": 4610 }, { "epoch": 0.24811665949203615, "grad_norm": 1.0914603471755981, "learning_rate": 4.27849231564993e-05, "loss": 4.7904, "step": 4611 }, { "epoch": 0.24817046922083513, "grad_norm": 1.7716153860092163, "learning_rate": 4.27819527650316e-05, "loss": 4.6942, "step": 4612 }, { "epoch": 0.2482242789496341, "grad_norm": 1.6273164749145508, "learning_rate": 4.2778981865403506e-05, "loss": 4.6056, "step": 4613 }, { "epoch": 0.24827808867843307, "grad_norm": 1.1641684770584106, "learning_rate": 4.277601045769993e-05, "loss": 4.8693, "step": 4614 }, { "epoch": 0.24833189840723202, "grad_norm": 1.851542353630066, "learning_rate": 4.2773038542005794e-05, "loss": 4.5519, "step": 4615 }, { "epoch": 0.248385708136031, "grad_norm": 1.9398272037506104, "learning_rate": 4.2770066118406024e-05, "loss": 4.0684, "step": 4616 }, { "epoch": 0.24843951786482996, "grad_norm": 2.248232841491699, "learning_rate": 4.276709318698555e-05, "loss": 4.5223, "step": 4617 }, { "epoch": 0.24849332759362894, "grad_norm": 1.2741029262542725, "learning_rate": 4.276411974782935e-05, "loss": 4.86, "step": 4618 }, { "epoch": 0.2485471373224279, "grad_norm": 0.905052125453949, "learning_rate": 4.276114580102237e-05, "loss": 4.8067, "step": 4619 }, { "epoch": 0.24860094705122687, "grad_norm": 1.5620927810668945, "learning_rate": 4.275817134664963e-05, "loss": 4.7206, "step": 4620 }, { "epoch": 0.24865475678002583, "grad_norm": 2.1414852142333984, "learning_rate": 4.275519638479611e-05, "loss": 4.3013, "step": 4621 }, { "epoch": 0.2487085665088248, "grad_norm": 2.1917073726654053, "learning_rate": 4.275222091554684e-05, "loss": 4.3384, "step": 4622 }, { "epoch": 0.24876237623762376, "grad_norm": 1.8871980905532837, "learning_rate": 4.2749244938986845e-05, "loss": 4.0755, "step": 4623 }, { "epoch": 0.24881618596642274, "grad_norm": 1.8739622831344604, "learning_rate": 4.2746268455201164e-05, "loss": 4.3754, "step": 4624 }, { "epoch": 0.2488699956952217, "grad_norm": 1.656114101409912, "learning_rate": 4.274329146427486e-05, "loss": 4.6949, "step": 4625 }, { "epoch": 0.24892380542402065, "grad_norm": 1.3551522493362427, "learning_rate": 4.2740313966293015e-05, "loss": 4.6475, "step": 4626 }, { "epoch": 0.24897761515281963, "grad_norm": 0.9872857332229614, "learning_rate": 4.273733596134071e-05, "loss": 4.8329, "step": 4627 }, { "epoch": 0.24903142488161858, "grad_norm": 1.7097523212432861, "learning_rate": 4.273435744950306e-05, "loss": 4.1974, "step": 4628 }, { "epoch": 0.24908523461041757, "grad_norm": 2.179149866104126, "learning_rate": 4.2731378430865164e-05, "loss": 4.5052, "step": 4629 }, { "epoch": 0.24913904433921652, "grad_norm": 1.4084389209747314, "learning_rate": 4.2728398905512167e-05, "loss": 4.6305, "step": 4630 }, { "epoch": 0.2491928540680155, "grad_norm": 2.143686056137085, "learning_rate": 4.2725418873529214e-05, "loss": 4.3369, "step": 4631 }, { "epoch": 0.24924666379681445, "grad_norm": 1.197160005569458, "learning_rate": 4.2722438335001456e-05, "loss": 4.3846, "step": 4632 }, { "epoch": 0.24930047352561344, "grad_norm": 1.6191349029541016, "learning_rate": 4.271945729001409e-05, "loss": 4.594, "step": 4633 }, { "epoch": 0.2493542832544124, "grad_norm": 1.655733585357666, "learning_rate": 4.271647573865229e-05, "loss": 4.6666, "step": 4634 }, { "epoch": 0.24940809298321137, "grad_norm": 3.2532761096954346, "learning_rate": 4.271349368100127e-05, "loss": 4.4965, "step": 4635 }, { "epoch": 0.24946190271201032, "grad_norm": 1.5092041492462158, "learning_rate": 4.2710511117146236e-05, "loss": 4.7951, "step": 4636 }, { "epoch": 0.2495157124408093, "grad_norm": 2.223177433013916, "learning_rate": 4.270752804717244e-05, "loss": 4.5666, "step": 4637 }, { "epoch": 0.24956952216960826, "grad_norm": 1.6936407089233398, "learning_rate": 4.270454447116511e-05, "loss": 4.8366, "step": 4638 }, { "epoch": 0.24962333189840724, "grad_norm": 1.3756424188613892, "learning_rate": 4.270156038920951e-05, "loss": 4.3842, "step": 4639 }, { "epoch": 0.2496771416272062, "grad_norm": 0.8924546241760254, "learning_rate": 4.269857580139095e-05, "loss": 4.825, "step": 4640 }, { "epoch": 0.24973095135600518, "grad_norm": 1.5566821098327637, "learning_rate": 4.269559070779469e-05, "loss": 4.6733, "step": 4641 }, { "epoch": 0.24978476108480413, "grad_norm": 1.3144360780715942, "learning_rate": 4.269260510850604e-05, "loss": 4.859, "step": 4642 }, { "epoch": 0.2498385708136031, "grad_norm": 1.7401671409606934, "learning_rate": 4.2689619003610316e-05, "loss": 4.8624, "step": 4643 }, { "epoch": 0.24989238054240206, "grad_norm": 1.5091418027877808, "learning_rate": 4.268663239319286e-05, "loss": 4.5973, "step": 4644 }, { "epoch": 0.24994619027120105, "grad_norm": 1.038044810295105, "learning_rate": 4.268364527733903e-05, "loss": 4.5302, "step": 4645 }, { "epoch": 0.25, "grad_norm": 1.5523033142089844, "learning_rate": 4.268065765613418e-05, "loss": 4.5588, "step": 4646 }, { "epoch": 0.250053809728799, "grad_norm": 1.483837604522705, "learning_rate": 4.267766952966369e-05, "loss": 4.8628, "step": 4647 }, { "epoch": 0.2501076194575979, "grad_norm": 1.391803503036499, "learning_rate": 4.267468089801295e-05, "loss": 4.2758, "step": 4648 }, { "epoch": 0.2501614291863969, "grad_norm": 0.907181978225708, "learning_rate": 4.2671691761267374e-05, "loss": 4.7476, "step": 4649 }, { "epoch": 0.25021523891519587, "grad_norm": 1.8538724184036255, "learning_rate": 4.266870211951237e-05, "loss": 4.6056, "step": 4650 }, { "epoch": 0.25026904864399485, "grad_norm": 2.089336395263672, "learning_rate": 4.266571197283339e-05, "loss": 4.9032, "step": 4651 }, { "epoch": 0.2503228583727938, "grad_norm": 1.4785823822021484, "learning_rate": 4.2662721321315875e-05, "loss": 4.8384, "step": 4652 }, { "epoch": 0.25037666810159276, "grad_norm": 1.1299431324005127, "learning_rate": 4.2659730165045294e-05, "loss": 4.574, "step": 4653 }, { "epoch": 0.25043047783039174, "grad_norm": 1.3970352411270142, "learning_rate": 4.265673850410712e-05, "loss": 4.6566, "step": 4654 }, { "epoch": 0.2504842875591907, "grad_norm": 1.6628594398498535, "learning_rate": 4.265374633858685e-05, "loss": 4.5627, "step": 4655 }, { "epoch": 0.25053809728798965, "grad_norm": 1.422876000404358, "learning_rate": 4.2650753668569996e-05, "loss": 4.3461, "step": 4656 }, { "epoch": 0.25059190701678863, "grad_norm": 1.3416708707809448, "learning_rate": 4.264776049414207e-05, "loss": 4.772, "step": 4657 }, { "epoch": 0.2506457167455876, "grad_norm": 2.093780279159546, "learning_rate": 4.2644766815388625e-05, "loss": 4.0535, "step": 4658 }, { "epoch": 0.2506995264743866, "grad_norm": 1.1342023611068726, "learning_rate": 4.2641772632395204e-05, "loss": 4.6684, "step": 4659 }, { "epoch": 0.2507533362031855, "grad_norm": 1.4550508260726929, "learning_rate": 4.2638777945247366e-05, "loss": 4.6987, "step": 4660 }, { "epoch": 0.2508071459319845, "grad_norm": 1.9219908714294434, "learning_rate": 4.263578275403071e-05, "loss": 4.3278, "step": 4661 }, { "epoch": 0.2508609556607835, "grad_norm": 1.314157485961914, "learning_rate": 4.2632787058830796e-05, "loss": 4.4966, "step": 4662 }, { "epoch": 0.25091476538958246, "grad_norm": 2.3431458473205566, "learning_rate": 4.262979085973327e-05, "loss": 4.3516, "step": 4663 }, { "epoch": 0.2509685751183814, "grad_norm": 1.4210690259933472, "learning_rate": 4.262679415682373e-05, "loss": 4.3904, "step": 4664 }, { "epoch": 0.25102238484718037, "grad_norm": 2.628681182861328, "learning_rate": 4.262379695018783e-05, "loss": 4.5405, "step": 4665 }, { "epoch": 0.25107619457597935, "grad_norm": 1.5756771564483643, "learning_rate": 4.2620799239911214e-05, "loss": 5.0275, "step": 4666 }, { "epoch": 0.25113000430477833, "grad_norm": 1.8312748670578003, "learning_rate": 4.261780102607955e-05, "loss": 4.5669, "step": 4667 }, { "epoch": 0.25118381403357726, "grad_norm": 1.587821364402771, "learning_rate": 4.2614802308778525e-05, "loss": 4.7957, "step": 4668 }, { "epoch": 0.25123762376237624, "grad_norm": 3.212109088897705, "learning_rate": 4.261180308809382e-05, "loss": 4.119, "step": 4669 }, { "epoch": 0.2512914334911752, "grad_norm": 1.5692771673202515, "learning_rate": 4.260880336411115e-05, "loss": 4.4666, "step": 4670 }, { "epoch": 0.25134524321997415, "grad_norm": 1.8099706172943115, "learning_rate": 4.260580313691625e-05, "loss": 4.5711, "step": 4671 }, { "epoch": 0.2513990529487731, "grad_norm": 1.259977102279663, "learning_rate": 4.2602802406594846e-05, "loss": 4.6923, "step": 4672 }, { "epoch": 0.2514528626775721, "grad_norm": 1.6119639873504639, "learning_rate": 4.25998011732327e-05, "loss": 4.7935, "step": 4673 }, { "epoch": 0.2515066724063711, "grad_norm": 1.3628700971603394, "learning_rate": 4.259679943691557e-05, "loss": 4.4218, "step": 4674 }, { "epoch": 0.25156048213517, "grad_norm": 1.431584119796753, "learning_rate": 4.259379719772925e-05, "loss": 4.3356, "step": 4675 }, { "epoch": 0.251614291863969, "grad_norm": 2.314577579498291, "learning_rate": 4.259079445575952e-05, "loss": 4.2857, "step": 4676 }, { "epoch": 0.251668101592768, "grad_norm": 1.8465596437454224, "learning_rate": 4.25877912110922e-05, "loss": 5.1758, "step": 4677 }, { "epoch": 0.25172191132156696, "grad_norm": 1.8152284622192383, "learning_rate": 4.25847874638131e-05, "loss": 4.369, "step": 4678 }, { "epoch": 0.2517757210503659, "grad_norm": 1.423977255821228, "learning_rate": 4.2581783214008085e-05, "loss": 4.3058, "step": 4679 }, { "epoch": 0.25182953077916487, "grad_norm": 1.4730830192565918, "learning_rate": 4.2578778461763006e-05, "loss": 4.2125, "step": 4680 }, { "epoch": 0.25188334050796385, "grad_norm": 2.2110342979431152, "learning_rate": 4.2575773207163706e-05, "loss": 4.5283, "step": 4681 }, { "epoch": 0.25193715023676283, "grad_norm": 1.2358375787734985, "learning_rate": 4.257276745029608e-05, "loss": 4.792, "step": 4682 }, { "epoch": 0.25199095996556176, "grad_norm": 2.321467399597168, "learning_rate": 4.2569761191246026e-05, "loss": 4.8238, "step": 4683 }, { "epoch": 0.25204476969436074, "grad_norm": 2.4203031063079834, "learning_rate": 4.256675443009946e-05, "loss": 4.2066, "step": 4684 }, { "epoch": 0.2520985794231597, "grad_norm": 1.922981858253479, "learning_rate": 4.256374716694229e-05, "loss": 4.3909, "step": 4685 }, { "epoch": 0.2521523891519587, "grad_norm": 2.2819011211395264, "learning_rate": 4.2560739401860485e-05, "loss": 4.6034, "step": 4686 }, { "epoch": 0.2522061988807576, "grad_norm": 1.796951413154602, "learning_rate": 4.2557731134939964e-05, "loss": 4.446, "step": 4687 }, { "epoch": 0.2522600086095566, "grad_norm": 1.7079250812530518, "learning_rate": 4.255472236626672e-05, "loss": 4.6679, "step": 4688 }, { "epoch": 0.2523138183383556, "grad_norm": 1.76539146900177, "learning_rate": 4.255171309592673e-05, "loss": 4.1597, "step": 4689 }, { "epoch": 0.2523676280671545, "grad_norm": 1.5415955781936646, "learning_rate": 4.2548703324005975e-05, "loss": 4.7766, "step": 4690 }, { "epoch": 0.2524214377959535, "grad_norm": 1.8623454570770264, "learning_rate": 4.2545693050590495e-05, "loss": 4.6381, "step": 4691 }, { "epoch": 0.2524752475247525, "grad_norm": 1.3362452983856201, "learning_rate": 4.25426822757663e-05, "loss": 4.5591, "step": 4692 }, { "epoch": 0.25252905725355146, "grad_norm": 1.3500090837478638, "learning_rate": 4.253967099961942e-05, "loss": 4.7538, "step": 4693 }, { "epoch": 0.2525828669823504, "grad_norm": 1.5280107259750366, "learning_rate": 4.253665922223592e-05, "loss": 4.6231, "step": 4694 }, { "epoch": 0.25263667671114937, "grad_norm": 1.5738446712493896, "learning_rate": 4.253364694370188e-05, "loss": 4.861, "step": 4695 }, { "epoch": 0.25269048643994835, "grad_norm": 1.766079306602478, "learning_rate": 4.253063416410336e-05, "loss": 4.5329, "step": 4696 }, { "epoch": 0.25274429616874733, "grad_norm": 1.9095171689987183, "learning_rate": 4.252762088352646e-05, "loss": 4.6669, "step": 4697 }, { "epoch": 0.25279810589754625, "grad_norm": 1.8130462169647217, "learning_rate": 4.252460710205731e-05, "loss": 4.4447, "step": 4698 }, { "epoch": 0.25285191562634524, "grad_norm": 1.470289707183838, "learning_rate": 4.252159281978202e-05, "loss": 4.9056, "step": 4699 }, { "epoch": 0.2529057253551442, "grad_norm": 1.0955134630203247, "learning_rate": 4.251857803678674e-05, "loss": 4.4966, "step": 4700 }, { "epoch": 0.2529595350839432, "grad_norm": 1.145880937576294, "learning_rate": 4.251556275315761e-05, "loss": 4.5702, "step": 4701 }, { "epoch": 0.2530133448127421, "grad_norm": 1.62344229221344, "learning_rate": 4.251254696898081e-05, "loss": 4.551, "step": 4702 }, { "epoch": 0.2530671545415411, "grad_norm": 1.8606059551239014, "learning_rate": 4.250953068434252e-05, "loss": 4.488, "step": 4703 }, { "epoch": 0.2531209642703401, "grad_norm": 1.243013858795166, "learning_rate": 4.250651389932895e-05, "loss": 4.8298, "step": 4704 }, { "epoch": 0.25317477399913907, "grad_norm": 1.3392293453216553, "learning_rate": 4.250349661402629e-05, "loss": 4.9154, "step": 4705 }, { "epoch": 0.253228583727938, "grad_norm": 1.887160062789917, "learning_rate": 4.2500478828520775e-05, "loss": 4.436, "step": 4706 }, { "epoch": 0.253282393456737, "grad_norm": 1.6705191135406494, "learning_rate": 4.2497460542898654e-05, "loss": 4.6697, "step": 4707 }, { "epoch": 0.25333620318553596, "grad_norm": 1.3694474697113037, "learning_rate": 4.249444175724617e-05, "loss": 4.7688, "step": 4708 }, { "epoch": 0.25339001291433494, "grad_norm": 0.9923940300941467, "learning_rate": 4.2491422471649586e-05, "loss": 4.8062, "step": 4709 }, { "epoch": 0.25344382264313386, "grad_norm": 2.4023804664611816, "learning_rate": 4.2488402686195204e-05, "loss": 3.789, "step": 4710 }, { "epoch": 0.25349763237193285, "grad_norm": 2.0136046409606934, "learning_rate": 4.2485382400969306e-05, "loss": 4.4488, "step": 4711 }, { "epoch": 0.2535514421007318, "grad_norm": 1.966379165649414, "learning_rate": 4.248236161605822e-05, "loss": 4.4365, "step": 4712 }, { "epoch": 0.25360525182953075, "grad_norm": 1.8477472066879272, "learning_rate": 4.2479340331548246e-05, "loss": 4.8379, "step": 4713 }, { "epoch": 0.25365906155832973, "grad_norm": 1.163184404373169, "learning_rate": 4.247631854752575e-05, "loss": 4.4299, "step": 4714 }, { "epoch": 0.2537128712871287, "grad_norm": 1.286624789237976, "learning_rate": 4.2473296264077064e-05, "loss": 4.4816, "step": 4715 }, { "epoch": 0.2537666810159277, "grad_norm": 1.7348887920379639, "learning_rate": 4.247027348128858e-05, "loss": 3.9265, "step": 4716 }, { "epoch": 0.2538204907447266, "grad_norm": 1.5601811408996582, "learning_rate": 4.246725019924667e-05, "loss": 4.5188, "step": 4717 }, { "epoch": 0.2538743004735256, "grad_norm": 1.1881248950958252, "learning_rate": 4.2464226418037726e-05, "loss": 4.437, "step": 4718 }, { "epoch": 0.2539281102023246, "grad_norm": 1.623326301574707, "learning_rate": 4.246120213774816e-05, "loss": 4.7683, "step": 4719 }, { "epoch": 0.25398191993112357, "grad_norm": 1.2536604404449463, "learning_rate": 4.245817735846441e-05, "loss": 4.6694, "step": 4720 }, { "epoch": 0.2540357296599225, "grad_norm": 2.4899749755859375, "learning_rate": 4.24551520802729e-05, "loss": 4.723, "step": 4721 }, { "epoch": 0.2540895393887215, "grad_norm": 1.321203351020813, "learning_rate": 4.245212630326011e-05, "loss": 4.7646, "step": 4722 }, { "epoch": 0.25414334911752046, "grad_norm": 2.1969780921936035, "learning_rate": 4.244910002751247e-05, "loss": 4.4679, "step": 4723 }, { "epoch": 0.25419715884631944, "grad_norm": 1.0810390710830688, "learning_rate": 4.244607325311649e-05, "loss": 4.7437, "step": 4724 }, { "epoch": 0.25425096857511836, "grad_norm": 0.9974365830421448, "learning_rate": 4.2443045980158666e-05, "loss": 4.7868, "step": 4725 }, { "epoch": 0.25430477830391734, "grad_norm": 1.4354753494262695, "learning_rate": 4.2440018208725496e-05, "loss": 4.5437, "step": 4726 }, { "epoch": 0.2543585880327163, "grad_norm": 1.935836672782898, "learning_rate": 4.243698993890352e-05, "loss": 4.6944, "step": 4727 }, { "epoch": 0.2544123977615153, "grad_norm": 1.2095084190368652, "learning_rate": 4.243396117077927e-05, "loss": 4.5688, "step": 4728 }, { "epoch": 0.25446620749031423, "grad_norm": 0.9134387373924255, "learning_rate": 4.2430931904439296e-05, "loss": 4.4587, "step": 4729 }, { "epoch": 0.2545200172191132, "grad_norm": 1.9453400373458862, "learning_rate": 4.242790213997018e-05, "loss": 4.5631, "step": 4730 }, { "epoch": 0.2545738269479122, "grad_norm": 1.9578548669815063, "learning_rate": 4.2424871877458494e-05, "loss": 4.0663, "step": 4731 }, { "epoch": 0.2546276366767111, "grad_norm": 2.277218818664551, "learning_rate": 4.2421841116990835e-05, "loss": 4.131, "step": 4732 }, { "epoch": 0.2546814464055101, "grad_norm": 1.7829481363296509, "learning_rate": 4.2418809858653825e-05, "loss": 4.2759, "step": 4733 }, { "epoch": 0.2547352561343091, "grad_norm": 2.2412054538726807, "learning_rate": 4.241577810253407e-05, "loss": 4.2192, "step": 4734 }, { "epoch": 0.25478906586310807, "grad_norm": 1.7597228288650513, "learning_rate": 4.241274584871823e-05, "loss": 4.3215, "step": 4735 }, { "epoch": 0.254842875591907, "grad_norm": 2.0776214599609375, "learning_rate": 4.240971309729294e-05, "loss": 4.4263, "step": 4736 }, { "epoch": 0.254896685320706, "grad_norm": 1.323233723640442, "learning_rate": 4.240667984834488e-05, "loss": 4.8254, "step": 4737 }, { "epoch": 0.25495049504950495, "grad_norm": 1.7699501514434814, "learning_rate": 4.240364610196072e-05, "loss": 4.6328, "step": 4738 }, { "epoch": 0.25500430477830394, "grad_norm": 2.032360315322876, "learning_rate": 4.240061185822717e-05, "loss": 4.6104, "step": 4739 }, { "epoch": 0.25505811450710286, "grad_norm": 1.177498459815979, "learning_rate": 4.239757711723094e-05, "loss": 4.6587, "step": 4740 }, { "epoch": 0.25511192423590184, "grad_norm": 1.866175651550293, "learning_rate": 4.239454187905875e-05, "loss": 3.9972, "step": 4741 }, { "epoch": 0.2551657339647008, "grad_norm": 1.6676435470581055, "learning_rate": 4.239150614379733e-05, "loss": 4.347, "step": 4742 }, { "epoch": 0.2552195436934998, "grad_norm": 1.3749480247497559, "learning_rate": 4.238846991153345e-05, "loss": 4.4897, "step": 4743 }, { "epoch": 0.25527335342229873, "grad_norm": 2.0612518787384033, "learning_rate": 4.238543318235386e-05, "loss": 4.3065, "step": 4744 }, { "epoch": 0.2553271631510977, "grad_norm": 1.5260440111160278, "learning_rate": 4.2382395956345364e-05, "loss": 4.8023, "step": 4745 }, { "epoch": 0.2553809728798967, "grad_norm": 1.5526913404464722, "learning_rate": 4.2379358233594734e-05, "loss": 4.233, "step": 4746 }, { "epoch": 0.2554347826086957, "grad_norm": 1.1956816911697388, "learning_rate": 4.2376320014188795e-05, "loss": 4.6039, "step": 4747 }, { "epoch": 0.2554885923374946, "grad_norm": 1.650520920753479, "learning_rate": 4.2373281298214366e-05, "loss": 4.306, "step": 4748 }, { "epoch": 0.2555424020662936, "grad_norm": 1.2829005718231201, "learning_rate": 4.2370242085758296e-05, "loss": 4.9745, "step": 4749 }, { "epoch": 0.25559621179509256, "grad_norm": 1.0919182300567627, "learning_rate": 4.236720237690741e-05, "loss": 4.563, "step": 4750 }, { "epoch": 0.25565002152389155, "grad_norm": 2.6903750896453857, "learning_rate": 4.23641621717486e-05, "loss": 4.1792, "step": 4751 }, { "epoch": 0.25570383125269047, "grad_norm": 2.144249200820923, "learning_rate": 4.236112147036874e-05, "loss": 4.1057, "step": 4752 }, { "epoch": 0.25575764098148945, "grad_norm": 1.2532881498336792, "learning_rate": 4.2358080272854726e-05, "loss": 4.6359, "step": 4753 }, { "epoch": 0.25581145071028843, "grad_norm": 2.144791603088379, "learning_rate": 4.2355038579293464e-05, "loss": 4.318, "step": 4754 }, { "epoch": 0.25586526043908736, "grad_norm": 1.704017996788025, "learning_rate": 4.235199638977188e-05, "loss": 4.5176, "step": 4755 }, { "epoch": 0.25591907016788634, "grad_norm": 2.4930806159973145, "learning_rate": 4.2348953704376914e-05, "loss": 4.3755, "step": 4756 }, { "epoch": 0.2559728798966853, "grad_norm": 2.406437635421753, "learning_rate": 4.234591052319551e-05, "loss": 4.6426, "step": 4757 }, { "epoch": 0.2560266896254843, "grad_norm": 1.051173448562622, "learning_rate": 4.2342866846314634e-05, "loss": 4.8664, "step": 4758 }, { "epoch": 0.25608049935428323, "grad_norm": 1.0048867464065552, "learning_rate": 4.233982267382127e-05, "loss": 4.4869, "step": 4759 }, { "epoch": 0.2561343090830822, "grad_norm": 2.2349348068237305, "learning_rate": 4.2336778005802424e-05, "loss": 4.1318, "step": 4760 }, { "epoch": 0.2561881188118812, "grad_norm": 1.5319033861160278, "learning_rate": 4.2333732842345086e-05, "loss": 4.9495, "step": 4761 }, { "epoch": 0.2562419285406802, "grad_norm": 1.6116448640823364, "learning_rate": 4.233068718353629e-05, "loss": 4.2192, "step": 4762 }, { "epoch": 0.2562957382694791, "grad_norm": 1.7117578983306885, "learning_rate": 4.232764102946306e-05, "loss": 4.4943, "step": 4763 }, { "epoch": 0.2563495479982781, "grad_norm": 1.3298475742340088, "learning_rate": 4.232459438021246e-05, "loss": 4.8305, "step": 4764 }, { "epoch": 0.25640335772707706, "grad_norm": 1.0276826620101929, "learning_rate": 4.232154723587155e-05, "loss": 4.6206, "step": 4765 }, { "epoch": 0.25645716745587605, "grad_norm": 1.4245710372924805, "learning_rate": 4.231849959652741e-05, "loss": 4.4943, "step": 4766 }, { "epoch": 0.25651097718467497, "grad_norm": 2.188265323638916, "learning_rate": 4.231545146226713e-05, "loss": 4.8975, "step": 4767 }, { "epoch": 0.25656478691347395, "grad_norm": 2.772858142852783, "learning_rate": 4.231240283317782e-05, "loss": 4.103, "step": 4768 }, { "epoch": 0.25661859664227293, "grad_norm": 1.220950961112976, "learning_rate": 4.230935370934661e-05, "loss": 4.7805, "step": 4769 }, { "epoch": 0.2566724063710719, "grad_norm": 3.1059226989746094, "learning_rate": 4.230630409086062e-05, "loss": 3.9868, "step": 4770 }, { "epoch": 0.25672621609987084, "grad_norm": 1.696139931678772, "learning_rate": 4.230325397780701e-05, "loss": 4.4486, "step": 4771 }, { "epoch": 0.2567800258286698, "grad_norm": 2.06439471244812, "learning_rate": 4.230020337027294e-05, "loss": 4.3968, "step": 4772 }, { "epoch": 0.2568338355574688, "grad_norm": 1.3552227020263672, "learning_rate": 4.229715226834559e-05, "loss": 4.4958, "step": 4773 }, { "epoch": 0.25688764528626773, "grad_norm": 0.9869140982627869, "learning_rate": 4.229410067211215e-05, "loss": 4.7282, "step": 4774 }, { "epoch": 0.2569414550150667, "grad_norm": 1.633123755455017, "learning_rate": 4.229104858165984e-05, "loss": 4.7814, "step": 4775 }, { "epoch": 0.2569952647438657, "grad_norm": 1.231727957725525, "learning_rate": 4.228799599707586e-05, "loss": 4.5529, "step": 4776 }, { "epoch": 0.2570490744726647, "grad_norm": 1.0804314613342285, "learning_rate": 4.2284942918447454e-05, "loss": 4.6601, "step": 4777 }, { "epoch": 0.2571028842014636, "grad_norm": 1.9838348627090454, "learning_rate": 4.228188934586187e-05, "loss": 4.6036, "step": 4778 }, { "epoch": 0.2571566939302626, "grad_norm": 1.845334529876709, "learning_rate": 4.227883527940637e-05, "loss": 4.414, "step": 4779 }, { "epoch": 0.25721050365906156, "grad_norm": 2.071739673614502, "learning_rate": 4.227578071916823e-05, "loss": 4.5742, "step": 4780 }, { "epoch": 0.25726431338786054, "grad_norm": 2.034346342086792, "learning_rate": 4.227272566523475e-05, "loss": 4.6069, "step": 4781 }, { "epoch": 0.25731812311665947, "grad_norm": 1.6140676736831665, "learning_rate": 4.2269670117693226e-05, "loss": 4.57, "step": 4782 }, { "epoch": 0.25737193284545845, "grad_norm": 0.9034675359725952, "learning_rate": 4.226661407663098e-05, "loss": 4.6542, "step": 4783 }, { "epoch": 0.25742574257425743, "grad_norm": 2.1419167518615723, "learning_rate": 4.226355754213535e-05, "loss": 4.279, "step": 4784 }, { "epoch": 0.2574795523030564, "grad_norm": 2.1837778091430664, "learning_rate": 4.226050051429367e-05, "loss": 4.3554, "step": 4785 }, { "epoch": 0.25753336203185534, "grad_norm": 1.8462591171264648, "learning_rate": 4.225744299319332e-05, "loss": 4.3139, "step": 4786 }, { "epoch": 0.2575871717606543, "grad_norm": 1.1542675495147705, "learning_rate": 4.225438497892166e-05, "loss": 4.9799, "step": 4787 }, { "epoch": 0.2576409814894533, "grad_norm": 1.6996994018554688, "learning_rate": 4.225132647156609e-05, "loss": 4.7368, "step": 4788 }, { "epoch": 0.2576947912182523, "grad_norm": 1.6250523328781128, "learning_rate": 4.2248267471214007e-05, "loss": 4.3724, "step": 4789 }, { "epoch": 0.2577486009470512, "grad_norm": 0.8440660834312439, "learning_rate": 4.2245207977952825e-05, "loss": 4.6227, "step": 4790 }, { "epoch": 0.2578024106758502, "grad_norm": 1.5098092555999756, "learning_rate": 4.224214799186999e-05, "loss": 4.3451, "step": 4791 }, { "epoch": 0.2578562204046492, "grad_norm": 1.9612207412719727, "learning_rate": 4.223908751305295e-05, "loss": 4.1915, "step": 4792 }, { "epoch": 0.25791003013344815, "grad_norm": 1.6115261316299438, "learning_rate": 4.2236026541589144e-05, "loss": 4.2514, "step": 4793 }, { "epoch": 0.2579638398622471, "grad_norm": 1.3753300905227661, "learning_rate": 4.2232965077566064e-05, "loss": 4.5648, "step": 4794 }, { "epoch": 0.25801764959104606, "grad_norm": 1.1517581939697266, "learning_rate": 4.22299031210712e-05, "loss": 4.4432, "step": 4795 }, { "epoch": 0.25807145931984504, "grad_norm": 0.9479624032974243, "learning_rate": 4.2226840672192035e-05, "loss": 4.4841, "step": 4796 }, { "epoch": 0.25812526904864397, "grad_norm": 1.961166262626648, "learning_rate": 4.222377773101611e-05, "loss": 4.3687, "step": 4797 }, { "epoch": 0.25817907877744295, "grad_norm": 2.1340043544769287, "learning_rate": 4.222071429763094e-05, "loss": 4.2746, "step": 4798 }, { "epoch": 0.25823288850624193, "grad_norm": 0.8904715180397034, "learning_rate": 4.221765037212407e-05, "loss": 4.3651, "step": 4799 }, { "epoch": 0.2582866982350409, "grad_norm": 2.043494462966919, "learning_rate": 4.2214585954583065e-05, "loss": 4.1982, "step": 4800 }, { "epoch": 0.25834050796383984, "grad_norm": 1.475010633468628, "learning_rate": 4.221152104509549e-05, "loss": 4.6985, "step": 4801 }, { "epoch": 0.2583943176926388, "grad_norm": 2.396608829498291, "learning_rate": 4.220845564374895e-05, "loss": 4.2999, "step": 4802 }, { "epoch": 0.2584481274214378, "grad_norm": 1.8901410102844238, "learning_rate": 4.220538975063102e-05, "loss": 4.4412, "step": 4803 }, { "epoch": 0.2585019371502368, "grad_norm": 0.9131385087966919, "learning_rate": 4.220232336582933e-05, "loss": 4.537, "step": 4804 }, { "epoch": 0.2585557468790357, "grad_norm": 1.2387893199920654, "learning_rate": 4.219925648943151e-05, "loss": 4.6924, "step": 4805 }, { "epoch": 0.2586095566078347, "grad_norm": 1.9183598756790161, "learning_rate": 4.21961891215252e-05, "loss": 4.3844, "step": 4806 }, { "epoch": 0.25866336633663367, "grad_norm": 1.6136208772659302, "learning_rate": 4.219312126219805e-05, "loss": 4.6821, "step": 4807 }, { "epoch": 0.25871717606543265, "grad_norm": 1.8316744565963745, "learning_rate": 4.219005291153775e-05, "loss": 4.068, "step": 4808 }, { "epoch": 0.2587709857942316, "grad_norm": 1.950368046760559, "learning_rate": 4.218698406963197e-05, "loss": 4.4025, "step": 4809 }, { "epoch": 0.25882479552303056, "grad_norm": 1.207247018814087, "learning_rate": 4.218391473656841e-05, "loss": 4.7158, "step": 4810 }, { "epoch": 0.25887860525182954, "grad_norm": 2.419110059738159, "learning_rate": 4.218084491243479e-05, "loss": 4.4089, "step": 4811 }, { "epoch": 0.2589324149806285, "grad_norm": 2.2280874252319336, "learning_rate": 4.217777459731883e-05, "loss": 4.2847, "step": 4812 }, { "epoch": 0.25898622470942745, "grad_norm": 1.5433261394500732, "learning_rate": 4.217470379130828e-05, "loss": 4.6858, "step": 4813 }, { "epoch": 0.25904003443822643, "grad_norm": 2.284623146057129, "learning_rate": 4.2171632494490884e-05, "loss": 4.5127, "step": 4814 }, { "epoch": 0.2590938441670254, "grad_norm": 1.13517427444458, "learning_rate": 4.216856070695442e-05, "loss": 4.4645, "step": 4815 }, { "epoch": 0.2591476538958244, "grad_norm": 1.706762671470642, "learning_rate": 4.216548842878667e-05, "loss": 4.5826, "step": 4816 }, { "epoch": 0.2592014636246233, "grad_norm": 1.1599035263061523, "learning_rate": 4.2162415660075424e-05, "loss": 4.5981, "step": 4817 }, { "epoch": 0.2592552733534223, "grad_norm": 1.7159043550491333, "learning_rate": 4.215934240090851e-05, "loss": 4.4586, "step": 4818 }, { "epoch": 0.2593090830822213, "grad_norm": 1.9211812019348145, "learning_rate": 4.215626865137374e-05, "loss": 4.8148, "step": 4819 }, { "epoch": 0.2593628928110202, "grad_norm": 1.6591176986694336, "learning_rate": 4.2153194411558955e-05, "loss": 4.5042, "step": 4820 }, { "epoch": 0.2594167025398192, "grad_norm": 1.7362474203109741, "learning_rate": 4.215011968155202e-05, "loss": 4.3517, "step": 4821 }, { "epoch": 0.25947051226861817, "grad_norm": 2.0602762699127197, "learning_rate": 4.2147044461440777e-05, "loss": 4.4896, "step": 4822 }, { "epoch": 0.25952432199741715, "grad_norm": 1.5829719305038452, "learning_rate": 4.214396875131312e-05, "loss": 4.2287, "step": 4823 }, { "epoch": 0.2595781317262161, "grad_norm": 1.243997573852539, "learning_rate": 4.214089255125696e-05, "loss": 4.3844, "step": 4824 }, { "epoch": 0.25963194145501506, "grad_norm": 1.9896767139434814, "learning_rate": 4.2137815861360194e-05, "loss": 4.4561, "step": 4825 }, { "epoch": 0.25968575118381404, "grad_norm": 1.2355543375015259, "learning_rate": 4.213473868171075e-05, "loss": 4.772, "step": 4826 }, { "epoch": 0.259739560912613, "grad_norm": 1.4593085050582886, "learning_rate": 4.213166101239656e-05, "loss": 4.5151, "step": 4827 }, { "epoch": 0.25979337064141195, "grad_norm": 2.627788543701172, "learning_rate": 4.212858285350557e-05, "loss": 3.8931, "step": 4828 }, { "epoch": 0.25984718037021093, "grad_norm": 3.0572214126586914, "learning_rate": 4.212550420512575e-05, "loss": 4.2686, "step": 4829 }, { "epoch": 0.2599009900990099, "grad_norm": 1.7964255809783936, "learning_rate": 4.212242506734509e-05, "loss": 4.332, "step": 4830 }, { "epoch": 0.2599547998278089, "grad_norm": 1.6849216222763062, "learning_rate": 4.211934544025158e-05, "loss": 4.5039, "step": 4831 }, { "epoch": 0.2600086095566078, "grad_norm": 1.8830465078353882, "learning_rate": 4.2116265323933215e-05, "loss": 4.3792, "step": 4832 }, { "epoch": 0.2600624192854068, "grad_norm": 1.1936371326446533, "learning_rate": 4.211318471847803e-05, "loss": 4.6248, "step": 4833 }, { "epoch": 0.2601162290142058, "grad_norm": 1.3846461772918701, "learning_rate": 4.211010362397404e-05, "loss": 4.4742, "step": 4834 }, { "epoch": 0.26017003874300476, "grad_norm": 1.9093904495239258, "learning_rate": 4.2107022040509326e-05, "loss": 4.388, "step": 4835 }, { "epoch": 0.2602238484718037, "grad_norm": 2.1230316162109375, "learning_rate": 4.210393996817192e-05, "loss": 4.4468, "step": 4836 }, { "epoch": 0.26027765820060267, "grad_norm": 1.7616231441497803, "learning_rate": 4.210085740704993e-05, "loss": 4.1867, "step": 4837 }, { "epoch": 0.26033146792940165, "grad_norm": 1.3993741273880005, "learning_rate": 4.209777435723142e-05, "loss": 4.6432, "step": 4838 }, { "epoch": 0.2603852776582006, "grad_norm": 1.1316287517547607, "learning_rate": 4.2094690818804505e-05, "loss": 4.794, "step": 4839 }, { "epoch": 0.26043908738699956, "grad_norm": 1.8576456308364868, "learning_rate": 4.209160679185732e-05, "loss": 4.8862, "step": 4840 }, { "epoch": 0.26049289711579854, "grad_norm": 2.099261522293091, "learning_rate": 4.208852227647797e-05, "loss": 4.4936, "step": 4841 }, { "epoch": 0.2605467068445975, "grad_norm": 1.6680924892425537, "learning_rate": 4.208543727275463e-05, "loss": 4.6855, "step": 4842 }, { "epoch": 0.26060051657339645, "grad_norm": 1.8906090259552002, "learning_rate": 4.208235178077543e-05, "loss": 4.5264, "step": 4843 }, { "epoch": 0.2606543263021954, "grad_norm": 1.8830620050430298, "learning_rate": 4.207926580062857e-05, "loss": 4.6501, "step": 4844 }, { "epoch": 0.2607081360309944, "grad_norm": 1.8610572814941406, "learning_rate": 4.2076179332402235e-05, "loss": 4.537, "step": 4845 }, { "epoch": 0.2607619457597934, "grad_norm": 1.9886083602905273, "learning_rate": 4.207309237618461e-05, "loss": 4.6251, "step": 4846 }, { "epoch": 0.2608157554885923, "grad_norm": 2.0942230224609375, "learning_rate": 4.207000493206394e-05, "loss": 4.4857, "step": 4847 }, { "epoch": 0.2608695652173913, "grad_norm": 1.7776862382888794, "learning_rate": 4.206691700012844e-05, "loss": 4.4783, "step": 4848 }, { "epoch": 0.2609233749461903, "grad_norm": 2.0235466957092285, "learning_rate": 4.206382858046636e-05, "loss": 4.3042, "step": 4849 }, { "epoch": 0.26097718467498926, "grad_norm": 1.8131487369537354, "learning_rate": 4.2060739673165945e-05, "loss": 4.6455, "step": 4850 }, { "epoch": 0.2610309944037882, "grad_norm": 2.3982596397399902, "learning_rate": 4.205765027831548e-05, "loss": 4.2256, "step": 4851 }, { "epoch": 0.26108480413258717, "grad_norm": 0.9287981986999512, "learning_rate": 4.2054560396003264e-05, "loss": 4.7982, "step": 4852 }, { "epoch": 0.26113861386138615, "grad_norm": 1.7594932317733765, "learning_rate": 4.2051470026317564e-05, "loss": 4.7185, "step": 4853 }, { "epoch": 0.26119242359018513, "grad_norm": 2.4729397296905518, "learning_rate": 4.2048379169346726e-05, "loss": 4.5093, "step": 4854 }, { "epoch": 0.26124623331898406, "grad_norm": 1.3440383672714233, "learning_rate": 4.204528782517906e-05, "loss": 4.5782, "step": 4855 }, { "epoch": 0.26130004304778304, "grad_norm": 1.547644019126892, "learning_rate": 4.204219599390292e-05, "loss": 4.419, "step": 4856 }, { "epoch": 0.261353852776582, "grad_norm": 2.0532796382904053, "learning_rate": 4.203910367560665e-05, "loss": 4.4267, "step": 4857 }, { "epoch": 0.261407662505381, "grad_norm": 1.9678164720535278, "learning_rate": 4.203601087037863e-05, "loss": 4.7272, "step": 4858 }, { "epoch": 0.2614614722341799, "grad_norm": 1.5599963665008545, "learning_rate": 4.203291757830724e-05, "loss": 4.7202, "step": 4859 }, { "epoch": 0.2615152819629789, "grad_norm": 2.286973714828491, "learning_rate": 4.202982379948088e-05, "loss": 4.6253, "step": 4860 }, { "epoch": 0.2615690916917779, "grad_norm": 1.6019147634506226, "learning_rate": 4.202672953398796e-05, "loss": 4.7944, "step": 4861 }, { "epoch": 0.2616229014205768, "grad_norm": 1.5794864892959595, "learning_rate": 4.202363478191691e-05, "loss": 4.4072, "step": 4862 }, { "epoch": 0.2616767111493758, "grad_norm": 1.3390285968780518, "learning_rate": 4.202053954335616e-05, "loss": 4.48, "step": 4863 }, { "epoch": 0.2617305208781748, "grad_norm": 1.5198075771331787, "learning_rate": 4.201744381839417e-05, "loss": 4.383, "step": 4864 }, { "epoch": 0.26178433060697376, "grad_norm": 1.6736938953399658, "learning_rate": 4.201434760711942e-05, "loss": 4.5486, "step": 4865 }, { "epoch": 0.2618381403357727, "grad_norm": 1.4164342880249023, "learning_rate": 4.2011250909620366e-05, "loss": 4.709, "step": 4866 }, { "epoch": 0.26189195006457167, "grad_norm": 1.4198161363601685, "learning_rate": 4.200815372598552e-05, "loss": 4.5024, "step": 4867 }, { "epoch": 0.26194575979337065, "grad_norm": 1.4372767210006714, "learning_rate": 4.200505605630338e-05, "loss": 4.5867, "step": 4868 }, { "epoch": 0.26199956952216963, "grad_norm": 0.8998299837112427, "learning_rate": 4.2001957900662484e-05, "loss": 4.7382, "step": 4869 }, { "epoch": 0.26205337925096855, "grad_norm": 1.6631760597229004, "learning_rate": 4.199885925915136e-05, "loss": 4.452, "step": 4870 }, { "epoch": 0.26210718897976754, "grad_norm": 2.058297872543335, "learning_rate": 4.199576013185857e-05, "loss": 4.579, "step": 4871 }, { "epoch": 0.2621609987085665, "grad_norm": 1.3951852321624756, "learning_rate": 4.199266051887265e-05, "loss": 4.6104, "step": 4872 }, { "epoch": 0.2622148084373655, "grad_norm": 1.4588353633880615, "learning_rate": 4.19895604202822e-05, "loss": 4.5649, "step": 4873 }, { "epoch": 0.2622686181661644, "grad_norm": 2.0716135501861572, "learning_rate": 4.198645983617582e-05, "loss": 4.4623, "step": 4874 }, { "epoch": 0.2623224278949634, "grad_norm": 1.3598167896270752, "learning_rate": 4.19833587666421e-05, "loss": 4.4744, "step": 4875 }, { "epoch": 0.2623762376237624, "grad_norm": 1.0582338571548462, "learning_rate": 4.1980257211769666e-05, "loss": 4.4256, "step": 4876 }, { "epoch": 0.26243004735256137, "grad_norm": 1.2553088665008545, "learning_rate": 4.197715517164715e-05, "loss": 4.3361, "step": 4877 }, { "epoch": 0.2624838570813603, "grad_norm": 2.064699411392212, "learning_rate": 4.19740526463632e-05, "loss": 4.8362, "step": 4878 }, { "epoch": 0.2625376668101593, "grad_norm": 2.5420196056365967, "learning_rate": 4.1970949636006495e-05, "loss": 4.7733, "step": 4879 }, { "epoch": 0.26259147653895826, "grad_norm": 1.693981409072876, "learning_rate": 4.196784614066569e-05, "loss": 4.8299, "step": 4880 }, { "epoch": 0.2626452862677572, "grad_norm": 1.124480962753296, "learning_rate": 4.196474216042947e-05, "loss": 4.5085, "step": 4881 }, { "epoch": 0.26269909599655616, "grad_norm": 2.0193819999694824, "learning_rate": 4.1961637695386554e-05, "loss": 4.2487, "step": 4882 }, { "epoch": 0.26275290572535515, "grad_norm": 1.5266162157058716, "learning_rate": 4.1958532745625664e-05, "loss": 4.898, "step": 4883 }, { "epoch": 0.2628067154541541, "grad_norm": 1.6608555316925049, "learning_rate": 4.195542731123551e-05, "loss": 4.3718, "step": 4884 }, { "epoch": 0.26286052518295305, "grad_norm": 1.5484730005264282, "learning_rate": 4.195232139230485e-05, "loss": 4.7083, "step": 4885 }, { "epoch": 0.26291433491175203, "grad_norm": 2.044621706008911, "learning_rate": 4.1949214988922445e-05, "loss": 4.4281, "step": 4886 }, { "epoch": 0.262968144640551, "grad_norm": 1.512579083442688, "learning_rate": 4.194610810117706e-05, "loss": 4.4415, "step": 4887 }, { "epoch": 0.26302195436935, "grad_norm": 1.6592354774475098, "learning_rate": 4.1943000729157486e-05, "loss": 4.8144, "step": 4888 }, { "epoch": 0.2630757640981489, "grad_norm": 2.294053077697754, "learning_rate": 4.193989287295252e-05, "loss": 4.6917, "step": 4889 }, { "epoch": 0.2631295738269479, "grad_norm": 1.5060206651687622, "learning_rate": 4.193678453265099e-05, "loss": 4.4928, "step": 4890 }, { "epoch": 0.2631833835557469, "grad_norm": 1.7047312259674072, "learning_rate": 4.19336757083417e-05, "loss": 4.3762, "step": 4891 }, { "epoch": 0.26323719328454587, "grad_norm": 1.829335331916809, "learning_rate": 4.193056640011351e-05, "loss": 4.7042, "step": 4892 }, { "epoch": 0.2632910030133448, "grad_norm": 1.3892781734466553, "learning_rate": 4.192745660805527e-05, "loss": 4.6197, "step": 4893 }, { "epoch": 0.2633448127421438, "grad_norm": 1.7567729949951172, "learning_rate": 4.192434633225585e-05, "loss": 4.7261, "step": 4894 }, { "epoch": 0.26339862247094276, "grad_norm": 1.920934796333313, "learning_rate": 4.192123557280413e-05, "loss": 4.6465, "step": 4895 }, { "epoch": 0.26345243219974174, "grad_norm": 1.6295024156570435, "learning_rate": 4.191812432978901e-05, "loss": 4.2336, "step": 4896 }, { "epoch": 0.26350624192854066, "grad_norm": 1.8487563133239746, "learning_rate": 4.19150126032994e-05, "loss": 4.601, "step": 4897 }, { "epoch": 0.26356005165733964, "grad_norm": 2.221284866333008, "learning_rate": 4.191190039342423e-05, "loss": 4.1212, "step": 4898 }, { "epoch": 0.2636138613861386, "grad_norm": 2.18227219581604, "learning_rate": 4.1908787700252436e-05, "loss": 4.552, "step": 4899 }, { "epoch": 0.2636676711149376, "grad_norm": 1.5272830724716187, "learning_rate": 4.190567452387296e-05, "loss": 4.5297, "step": 4900 }, { "epoch": 0.26372148084373653, "grad_norm": 1.340095043182373, "learning_rate": 4.1902560864374786e-05, "loss": 4.8974, "step": 4901 }, { "epoch": 0.2637752905725355, "grad_norm": 1.6412582397460938, "learning_rate": 4.189944672184688e-05, "loss": 3.9288, "step": 4902 }, { "epoch": 0.2638291003013345, "grad_norm": 2.1900057792663574, "learning_rate": 4.189633209637824e-05, "loss": 4.1966, "step": 4903 }, { "epoch": 0.2638829100301334, "grad_norm": 0.912434995174408, "learning_rate": 4.189321698805788e-05, "loss": 4.626, "step": 4904 }, { "epoch": 0.2639367197589324, "grad_norm": 1.557834267616272, "learning_rate": 4.1890101396974815e-05, "loss": 4.7578, "step": 4905 }, { "epoch": 0.2639905294877314, "grad_norm": 1.6795779466629028, "learning_rate": 4.188698532321808e-05, "loss": 4.6119, "step": 4906 }, { "epoch": 0.26404433921653037, "grad_norm": 1.636688470840454, "learning_rate": 4.188386876687672e-05, "loss": 4.7245, "step": 4907 }, { "epoch": 0.2640981489453293, "grad_norm": 2.2888200283050537, "learning_rate": 4.1880751728039814e-05, "loss": 4.1804, "step": 4908 }, { "epoch": 0.2641519586741283, "grad_norm": 1.9190346002578735, "learning_rate": 4.187763420679642e-05, "loss": 4.0789, "step": 4909 }, { "epoch": 0.26420576840292725, "grad_norm": 1.5919158458709717, "learning_rate": 4.187451620323564e-05, "loss": 4.4012, "step": 4910 }, { "epoch": 0.26425957813172624, "grad_norm": 1.612368106842041, "learning_rate": 4.187139771744656e-05, "loss": 4.4317, "step": 4911 }, { "epoch": 0.26431338786052516, "grad_norm": 1.1184066534042358, "learning_rate": 4.186827874951833e-05, "loss": 4.8115, "step": 4912 }, { "epoch": 0.26436719758932414, "grad_norm": 2.0674264430999756, "learning_rate": 4.186515929954006e-05, "loss": 4.3157, "step": 4913 }, { "epoch": 0.2644210073181231, "grad_norm": 1.495236873626709, "learning_rate": 4.1862039367600895e-05, "loss": 4.4347, "step": 4914 }, { "epoch": 0.2644748170469221, "grad_norm": 1.1572158336639404, "learning_rate": 4.1858918953789994e-05, "loss": 4.6613, "step": 4915 }, { "epoch": 0.26452862677572103, "grad_norm": 1.077061414718628, "learning_rate": 4.185579805819654e-05, "loss": 4.6292, "step": 4916 }, { "epoch": 0.26458243650452, "grad_norm": 1.611175298690796, "learning_rate": 4.1852676680909716e-05, "loss": 4.6414, "step": 4917 }, { "epoch": 0.264636246233319, "grad_norm": 1.0729624032974243, "learning_rate": 4.184955482201872e-05, "loss": 4.7907, "step": 4918 }, { "epoch": 0.264690055962118, "grad_norm": 1.5327696800231934, "learning_rate": 4.184643248161276e-05, "loss": 4.2318, "step": 4919 }, { "epoch": 0.2647438656909169, "grad_norm": 1.6870425939559937, "learning_rate": 4.184330965978108e-05, "loss": 4.1026, "step": 4920 }, { "epoch": 0.2647976754197159, "grad_norm": 2.3784258365631104, "learning_rate": 4.184018635661291e-05, "loss": 3.7851, "step": 4921 }, { "epoch": 0.26485148514851486, "grad_norm": 1.3021281957626343, "learning_rate": 4.1837062572197504e-05, "loss": 4.4055, "step": 4922 }, { "epoch": 0.26490529487731385, "grad_norm": 1.7667618989944458, "learning_rate": 4.183393830662414e-05, "loss": 4.1155, "step": 4923 }, { "epoch": 0.26495910460611277, "grad_norm": 1.3290704488754272, "learning_rate": 4.1830813559982096e-05, "loss": 4.6451, "step": 4924 }, { "epoch": 0.26501291433491175, "grad_norm": 2.2711803913116455, "learning_rate": 4.182768833236068e-05, "loss": 4.5853, "step": 4925 }, { "epoch": 0.26506672406371073, "grad_norm": 1.5021284818649292, "learning_rate": 4.182456262384919e-05, "loss": 4.6666, "step": 4926 }, { "epoch": 0.26512053379250966, "grad_norm": 0.9291321039199829, "learning_rate": 4.1821436434536946e-05, "loss": 4.564, "step": 4927 }, { "epoch": 0.26517434352130864, "grad_norm": 1.460453748703003, "learning_rate": 4.1818309764513294e-05, "loss": 4.7101, "step": 4928 }, { "epoch": 0.2652281532501076, "grad_norm": 1.9470521211624146, "learning_rate": 4.1815182613867575e-05, "loss": 4.7512, "step": 4929 }, { "epoch": 0.2652819629789066, "grad_norm": 1.5082638263702393, "learning_rate": 4.181205498268918e-05, "loss": 4.8129, "step": 4930 }, { "epoch": 0.26533577270770553, "grad_norm": 1.398073673248291, "learning_rate": 4.180892687106747e-05, "loss": 4.8994, "step": 4931 }, { "epoch": 0.2653895824365045, "grad_norm": 1.1468257904052734, "learning_rate": 4.1805798279091833e-05, "loss": 4.9688, "step": 4932 }, { "epoch": 0.2654433921653035, "grad_norm": 1.3311092853546143, "learning_rate": 4.1802669206851694e-05, "loss": 4.6854, "step": 4933 }, { "epoch": 0.2654972018941025, "grad_norm": 1.616712212562561, "learning_rate": 4.179953965443645e-05, "loss": 4.8668, "step": 4934 }, { "epoch": 0.2655510116229014, "grad_norm": 2.0097789764404297, "learning_rate": 4.1796409621935564e-05, "loss": 4.6777, "step": 4935 }, { "epoch": 0.2656048213517004, "grad_norm": 1.172197937965393, "learning_rate": 4.1793279109438454e-05, "loss": 4.7985, "step": 4936 }, { "epoch": 0.26565863108049936, "grad_norm": 1.4682719707489014, "learning_rate": 4.1790148117034606e-05, "loss": 4.8788, "step": 4937 }, { "epoch": 0.26571244080929834, "grad_norm": 1.349087119102478, "learning_rate": 4.178701664481348e-05, "loss": 4.4148, "step": 4938 }, { "epoch": 0.26576625053809727, "grad_norm": 1.8234604597091675, "learning_rate": 4.178388469286457e-05, "loss": 4.6566, "step": 4939 }, { "epoch": 0.26582006026689625, "grad_norm": 1.6723642349243164, "learning_rate": 4.1780752261277376e-05, "loss": 4.369, "step": 4940 }, { "epoch": 0.26587386999569523, "grad_norm": 1.5356500148773193, "learning_rate": 4.177761935014143e-05, "loss": 4.6741, "step": 4941 }, { "epoch": 0.2659276797244942, "grad_norm": 1.566149115562439, "learning_rate": 4.1774485959546235e-05, "loss": 4.7355, "step": 4942 }, { "epoch": 0.26598148945329314, "grad_norm": 1.052720069885254, "learning_rate": 4.177135208958135e-05, "loss": 4.856, "step": 4943 }, { "epoch": 0.2660352991820921, "grad_norm": 1.296579360961914, "learning_rate": 4.176821774033634e-05, "loss": 4.3998, "step": 4944 }, { "epoch": 0.2660891089108911, "grad_norm": 1.8781818151474, "learning_rate": 4.1765082911900765e-05, "loss": 4.7454, "step": 4945 }, { "epoch": 0.26614291863969003, "grad_norm": 1.5334582328796387, "learning_rate": 4.1761947604364214e-05, "loss": 4.4349, "step": 4946 }, { "epoch": 0.266196728368489, "grad_norm": 2.2046897411346436, "learning_rate": 4.175881181781628e-05, "loss": 4.3282, "step": 4947 }, { "epoch": 0.266250538097288, "grad_norm": 1.1161686182022095, "learning_rate": 4.175567555234658e-05, "loss": 4.774, "step": 4948 }, { "epoch": 0.266304347826087, "grad_norm": 1.7662955522537231, "learning_rate": 4.175253880804475e-05, "loss": 4.9813, "step": 4949 }, { "epoch": 0.2663581575548859, "grad_norm": 2.2692952156066895, "learning_rate": 4.174940158500041e-05, "loss": 3.6186, "step": 4950 }, { "epoch": 0.2664119672836849, "grad_norm": 1.9629160165786743, "learning_rate": 4.174626388330323e-05, "loss": 4.7509, "step": 4951 }, { "epoch": 0.26646577701248386, "grad_norm": 1.5181134939193726, "learning_rate": 4.1743125703042874e-05, "loss": 4.4694, "step": 4952 }, { "epoch": 0.26651958674128284, "grad_norm": 1.2943283319473267, "learning_rate": 4.1739987044309006e-05, "loss": 4.5442, "step": 4953 }, { "epoch": 0.26657339647008177, "grad_norm": 2.0350916385650635, "learning_rate": 4.1736847907191347e-05, "loss": 4.2786, "step": 4954 }, { "epoch": 0.26662720619888075, "grad_norm": 2.1860191822052, "learning_rate": 4.1733708291779586e-05, "loss": 4.606, "step": 4955 }, { "epoch": 0.26668101592767973, "grad_norm": 1.3637319803237915, "learning_rate": 4.173056819816344e-05, "loss": 4.5142, "step": 4956 }, { "epoch": 0.2667348256564787, "grad_norm": 2.244628667831421, "learning_rate": 4.1727427626432666e-05, "loss": 4.2739, "step": 4957 }, { "epoch": 0.26678863538527764, "grad_norm": 1.285359501838684, "learning_rate": 4.1724286576677e-05, "loss": 4.7726, "step": 4958 }, { "epoch": 0.2668424451140766, "grad_norm": 1.6188727617263794, "learning_rate": 4.172114504898621e-05, "loss": 4.3674, "step": 4959 }, { "epoch": 0.2668962548428756, "grad_norm": 1.4127681255340576, "learning_rate": 4.1718003043450064e-05, "loss": 4.4766, "step": 4960 }, { "epoch": 0.2669500645716746, "grad_norm": 2.6768100261688232, "learning_rate": 4.171486056015836e-05, "loss": 3.8686, "step": 4961 }, { "epoch": 0.2670038743004735, "grad_norm": 1.1391719579696655, "learning_rate": 4.1711717599200894e-05, "loss": 4.5616, "step": 4962 }, { "epoch": 0.2670576840292725, "grad_norm": 2.171255111694336, "learning_rate": 4.17085741606675e-05, "loss": 4.4324, "step": 4963 }, { "epoch": 0.26711149375807147, "grad_norm": 1.311306118965149, "learning_rate": 4.170543024464799e-05, "loss": 4.6576, "step": 4964 }, { "epoch": 0.26716530348687045, "grad_norm": 1.502670407295227, "learning_rate": 4.1702285851232206e-05, "loss": 4.8965, "step": 4965 }, { "epoch": 0.2672191132156694, "grad_norm": 2.3006503582000732, "learning_rate": 4.169914098051002e-05, "loss": 4.2141, "step": 4966 }, { "epoch": 0.26727292294446836, "grad_norm": 1.2183588743209839, "learning_rate": 4.1695995632571315e-05, "loss": 4.5865, "step": 4967 }, { "epoch": 0.26732673267326734, "grad_norm": 1.1967397928237915, "learning_rate": 4.1692849807505954e-05, "loss": 4.5889, "step": 4968 }, { "epoch": 0.26738054240206627, "grad_norm": 1.291110873222351, "learning_rate": 4.168970350540384e-05, "loss": 4.5415, "step": 4969 }, { "epoch": 0.26743435213086525, "grad_norm": 1.4023555517196655, "learning_rate": 4.16865567263549e-05, "loss": 4.6962, "step": 4970 }, { "epoch": 0.26748816185966423, "grad_norm": 1.5350788831710815, "learning_rate": 4.168340947044904e-05, "loss": 4.7445, "step": 4971 }, { "epoch": 0.2675419715884632, "grad_norm": 1.7012419700622559, "learning_rate": 4.168026173777621e-05, "loss": 4.5528, "step": 4972 }, { "epoch": 0.26759578131726214, "grad_norm": 2.1482362747192383, "learning_rate": 4.167711352842637e-05, "loss": 4.1949, "step": 4973 }, { "epoch": 0.2676495910460611, "grad_norm": 1.649898886680603, "learning_rate": 4.167396484248948e-05, "loss": 4.6295, "step": 4974 }, { "epoch": 0.2677034007748601, "grad_norm": 1.6067485809326172, "learning_rate": 4.167081568005552e-05, "loss": 4.6615, "step": 4975 }, { "epoch": 0.2677572105036591, "grad_norm": 1.318740725517273, "learning_rate": 4.166766604121449e-05, "loss": 4.7221, "step": 4976 }, { "epoch": 0.267811020232458, "grad_norm": 1.774343490600586, "learning_rate": 4.166451592605639e-05, "loss": 4.5158, "step": 4977 }, { "epoch": 0.267864829961257, "grad_norm": 1.2501041889190674, "learning_rate": 4.1661365334671254e-05, "loss": 4.9983, "step": 4978 }, { "epoch": 0.26791863969005597, "grad_norm": 2.1565377712249756, "learning_rate": 4.16582142671491e-05, "loss": 4.4143, "step": 4979 }, { "epoch": 0.26797244941885495, "grad_norm": 1.8401635885238647, "learning_rate": 4.165506272358e-05, "loss": 4.8275, "step": 4980 }, { "epoch": 0.2680262591476539, "grad_norm": 1.593061089515686, "learning_rate": 4.1651910704054e-05, "loss": 4.4457, "step": 4981 }, { "epoch": 0.26808006887645286, "grad_norm": 1.525553822517395, "learning_rate": 4.1648758208661185e-05, "loss": 4.5136, "step": 4982 }, { "epoch": 0.26813387860525184, "grad_norm": 1.4699920415878296, "learning_rate": 4.1645605237491626e-05, "loss": 4.6488, "step": 4983 }, { "epoch": 0.2681876883340508, "grad_norm": 1.6303709745407104, "learning_rate": 4.164245179063545e-05, "loss": 4.785, "step": 4984 }, { "epoch": 0.26824149806284975, "grad_norm": 2.163771152496338, "learning_rate": 4.163929786818277e-05, "loss": 4.3922, "step": 4985 }, { "epoch": 0.26829530779164873, "grad_norm": 1.5919787883758545, "learning_rate": 4.1636143470223704e-05, "loss": 4.6727, "step": 4986 }, { "epoch": 0.2683491175204477, "grad_norm": 1.9585363864898682, "learning_rate": 4.16329885968484e-05, "loss": 4.0168, "step": 4987 }, { "epoch": 0.26840292724924664, "grad_norm": 1.5181760787963867, "learning_rate": 4.162983324814703e-05, "loss": 4.8782, "step": 4988 }, { "epoch": 0.2684567369780456, "grad_norm": 2.250309705734253, "learning_rate": 4.162667742420975e-05, "loss": 4.4709, "step": 4989 }, { "epoch": 0.2685105467068446, "grad_norm": 2.3310372829437256, "learning_rate": 4.162352112512675e-05, "loss": 4.6889, "step": 4990 }, { "epoch": 0.2685643564356436, "grad_norm": 1.3065311908721924, "learning_rate": 4.162036435098823e-05, "loss": 4.4193, "step": 4991 }, { "epoch": 0.2686181661644425, "grad_norm": 1.985416054725647, "learning_rate": 4.1617207101884394e-05, "loss": 4.5474, "step": 4992 }, { "epoch": 0.2686719758932415, "grad_norm": 2.265747308731079, "learning_rate": 4.1614049377905476e-05, "loss": 4.1899, "step": 4993 }, { "epoch": 0.26872578562204047, "grad_norm": 1.5149259567260742, "learning_rate": 4.161089117914172e-05, "loss": 4.4416, "step": 4994 }, { "epoch": 0.26877959535083945, "grad_norm": 1.866929531097412, "learning_rate": 4.1607732505683364e-05, "loss": 4.6256, "step": 4995 }, { "epoch": 0.2688334050796384, "grad_norm": 1.0217626094818115, "learning_rate": 4.160457335762068e-05, "loss": 4.6965, "step": 4996 }, { "epoch": 0.26888721480843736, "grad_norm": 1.2613376379013062, "learning_rate": 4.1601413735043963e-05, "loss": 4.9113, "step": 4997 }, { "epoch": 0.26894102453723634, "grad_norm": 3.192302703857422, "learning_rate": 4.159825363804349e-05, "loss": 3.8618, "step": 4998 }, { "epoch": 0.2689948342660353, "grad_norm": 1.4856641292572021, "learning_rate": 4.159509306670957e-05, "loss": 4.4271, "step": 4999 }, { "epoch": 0.26904864399483425, "grad_norm": 1.0826807022094727, "learning_rate": 4.1591932021132515e-05, "loss": 4.5456, "step": 5000 }, { "epoch": 0.26910245372363323, "grad_norm": 1.0724329948425293, "learning_rate": 4.158877050140269e-05, "loss": 4.7658, "step": 5001 }, { "epoch": 0.2691562634524322, "grad_norm": 2.362014055252075, "learning_rate": 4.1585608507610405e-05, "loss": 4.5906, "step": 5002 }, { "epoch": 0.2692100731812312, "grad_norm": 1.7250878810882568, "learning_rate": 4.158244603984606e-05, "loss": 4.8027, "step": 5003 }, { "epoch": 0.2692638829100301, "grad_norm": 1.7070566415786743, "learning_rate": 4.157928309819998e-05, "loss": 4.7682, "step": 5004 }, { "epoch": 0.2693176926388291, "grad_norm": 2.363025665283203, "learning_rate": 4.1576119682762605e-05, "loss": 4.4629, "step": 5005 }, { "epoch": 0.2693715023676281, "grad_norm": 1.7076712846755981, "learning_rate": 4.157295579362431e-05, "loss": 4.3898, "step": 5006 }, { "epoch": 0.26942531209642706, "grad_norm": 2.4095356464385986, "learning_rate": 4.156979143087551e-05, "loss": 4.3727, "step": 5007 }, { "epoch": 0.269479121825226, "grad_norm": 1.565641164779663, "learning_rate": 4.156662659460664e-05, "loss": 4.526, "step": 5008 }, { "epoch": 0.26953293155402497, "grad_norm": 1.3118834495544434, "learning_rate": 4.156346128490814e-05, "loss": 4.6021, "step": 5009 }, { "epoch": 0.26958674128282395, "grad_norm": 2.4673705101013184, "learning_rate": 4.1560295501870466e-05, "loss": 4.2606, "step": 5010 }, { "epoch": 0.2696405510116229, "grad_norm": 1.4228368997573853, "learning_rate": 4.155712924558409e-05, "loss": 4.8469, "step": 5011 }, { "epoch": 0.26969436074042186, "grad_norm": 2.4380037784576416, "learning_rate": 4.155396251613949e-05, "loss": 3.6489, "step": 5012 }, { "epoch": 0.26974817046922084, "grad_norm": 1.8420521020889282, "learning_rate": 4.155079531362718e-05, "loss": 4.5074, "step": 5013 }, { "epoch": 0.2698019801980198, "grad_norm": 1.7922649383544922, "learning_rate": 4.1547627638137643e-05, "loss": 4.7076, "step": 5014 }, { "epoch": 0.26985578992681875, "grad_norm": 1.4054087400436401, "learning_rate": 4.154445948976141e-05, "loss": 4.3808, "step": 5015 }, { "epoch": 0.2699095996556177, "grad_norm": 1.6221365928649902, "learning_rate": 4.154129086858904e-05, "loss": 4.7373, "step": 5016 }, { "epoch": 0.2699634093844167, "grad_norm": 1.9842400550842285, "learning_rate": 4.153812177471106e-05, "loss": 4.2139, "step": 5017 }, { "epoch": 0.2700172191132157, "grad_norm": 1.759901523590088, "learning_rate": 4.153495220821804e-05, "loss": 4.5792, "step": 5018 }, { "epoch": 0.2700710288420146, "grad_norm": 1.0399144887924194, "learning_rate": 4.153178216920056e-05, "loss": 4.5615, "step": 5019 }, { "epoch": 0.2701248385708136, "grad_norm": 1.2692660093307495, "learning_rate": 4.1528611657749216e-05, "loss": 4.4117, "step": 5020 }, { "epoch": 0.2701786482996126, "grad_norm": 2.0972423553466797, "learning_rate": 4.152544067395461e-05, "loss": 3.9606, "step": 5021 }, { "epoch": 0.27023245802841156, "grad_norm": 1.4802900552749634, "learning_rate": 4.152226921790735e-05, "loss": 4.2903, "step": 5022 }, { "epoch": 0.2702862677572105, "grad_norm": 2.63946270942688, "learning_rate": 4.151909728969808e-05, "loss": 4.091, "step": 5023 }, { "epoch": 0.27034007748600947, "grad_norm": 1.7845866680145264, "learning_rate": 4.151592488941743e-05, "loss": 4.6376, "step": 5024 }, { "epoch": 0.27039388721480845, "grad_norm": 1.399909257888794, "learning_rate": 4.1512752017156085e-05, "loss": 4.4538, "step": 5025 }, { "epoch": 0.27044769694360743, "grad_norm": 2.248185396194458, "learning_rate": 4.1509578673004695e-05, "loss": 4.0726, "step": 5026 }, { "epoch": 0.27050150667240636, "grad_norm": 2.43495512008667, "learning_rate": 4.150640485705395e-05, "loss": 4.3587, "step": 5027 }, { "epoch": 0.27055531640120534, "grad_norm": 1.6201812028884888, "learning_rate": 4.1503230569394556e-05, "loss": 4.2042, "step": 5028 }, { "epoch": 0.2706091261300043, "grad_norm": 2.4309356212615967, "learning_rate": 4.1500055810117215e-05, "loss": 4.7214, "step": 5029 }, { "epoch": 0.27066293585880324, "grad_norm": 2.9612627029418945, "learning_rate": 4.1496880579312664e-05, "loss": 4.4363, "step": 5030 }, { "epoch": 0.2707167455876022, "grad_norm": 2.6944079399108887, "learning_rate": 4.149370487707164e-05, "loss": 4.3511, "step": 5031 }, { "epoch": 0.2707705553164012, "grad_norm": 2.309502601623535, "learning_rate": 4.1490528703484886e-05, "loss": 4.4806, "step": 5032 }, { "epoch": 0.2708243650452002, "grad_norm": 2.1357808113098145, "learning_rate": 4.1487352058643175e-05, "loss": 4.3752, "step": 5033 }, { "epoch": 0.2708781747739991, "grad_norm": 2.3325746059417725, "learning_rate": 4.1484174942637286e-05, "loss": 4.4475, "step": 5034 }, { "epoch": 0.2709319845027981, "grad_norm": 0.9636420011520386, "learning_rate": 4.148099735555803e-05, "loss": 4.3678, "step": 5035 }, { "epoch": 0.2709857942315971, "grad_norm": 2.1098577976226807, "learning_rate": 4.147781929749618e-05, "loss": 4.2248, "step": 5036 }, { "epoch": 0.27103960396039606, "grad_norm": 1.275378942489624, "learning_rate": 4.1474640768542585e-05, "loss": 4.4058, "step": 5037 }, { "epoch": 0.271093413689195, "grad_norm": 1.6457693576812744, "learning_rate": 4.1471461768788066e-05, "loss": 4.624, "step": 5038 }, { "epoch": 0.27114722341799397, "grad_norm": 1.907555341720581, "learning_rate": 4.1468282298323474e-05, "loss": 4.2358, "step": 5039 }, { "epoch": 0.27120103314679295, "grad_norm": 1.895339846611023, "learning_rate": 4.146510235723967e-05, "loss": 4.4591, "step": 5040 }, { "epoch": 0.27125484287559193, "grad_norm": 1.7705284357070923, "learning_rate": 4.1461921945627516e-05, "loss": 4.3579, "step": 5041 }, { "epoch": 0.27130865260439085, "grad_norm": 1.4566025733947754, "learning_rate": 4.145874106357792e-05, "loss": 4.5946, "step": 5042 }, { "epoch": 0.27136246233318984, "grad_norm": 1.4624764919281006, "learning_rate": 4.1455559711181776e-05, "loss": 4.7138, "step": 5043 }, { "epoch": 0.2714162720619888, "grad_norm": 1.8039873838424683, "learning_rate": 4.145237788852999e-05, "loss": 4.5776, "step": 5044 }, { "epoch": 0.2714700817907878, "grad_norm": 2.0083608627319336, "learning_rate": 4.14491955957135e-05, "loss": 4.6852, "step": 5045 }, { "epoch": 0.2715238915195867, "grad_norm": 2.061134099960327, "learning_rate": 4.144601283282323e-05, "loss": 4.5715, "step": 5046 }, { "epoch": 0.2715777012483857, "grad_norm": 2.4871327877044678, "learning_rate": 4.144282959995016e-05, "loss": 3.9758, "step": 5047 }, { "epoch": 0.2716315109771847, "grad_norm": 1.5204358100891113, "learning_rate": 4.1439645897185245e-05, "loss": 4.6546, "step": 5048 }, { "epoch": 0.27168532070598367, "grad_norm": 2.4350686073303223, "learning_rate": 4.143646172461947e-05, "loss": 4.2213, "step": 5049 }, { "epoch": 0.2717391304347826, "grad_norm": 2.0442092418670654, "learning_rate": 4.143327708234381e-05, "loss": 4.5942, "step": 5050 }, { "epoch": 0.2717929401635816, "grad_norm": 1.9452428817749023, "learning_rate": 4.143009197044932e-05, "loss": 4.6534, "step": 5051 }, { "epoch": 0.27184674989238056, "grad_norm": 1.7763111591339111, "learning_rate": 4.142690638902697e-05, "loss": 4.1026, "step": 5052 }, { "epoch": 0.2719005596211795, "grad_norm": 1.9900258779525757, "learning_rate": 4.1423720338167824e-05, "loss": 4.2096, "step": 5053 }, { "epoch": 0.27195436934997846, "grad_norm": 1.8461265563964844, "learning_rate": 4.142053381796294e-05, "loss": 3.8615, "step": 5054 }, { "epoch": 0.27200817907877745, "grad_norm": 1.1995874643325806, "learning_rate": 4.141734682850334e-05, "loss": 4.5197, "step": 5055 }, { "epoch": 0.2720619888075764, "grad_norm": 1.3656306266784668, "learning_rate": 4.141415936988015e-05, "loss": 4.6494, "step": 5056 }, { "epoch": 0.27211579853637535, "grad_norm": 0.9754788875579834, "learning_rate": 4.1410971442184424e-05, "loss": 4.6786, "step": 5057 }, { "epoch": 0.27216960826517433, "grad_norm": 1.821390986442566, "learning_rate": 4.140778304550727e-05, "loss": 4.3783, "step": 5058 }, { "epoch": 0.2722234179939733, "grad_norm": 1.5166571140289307, "learning_rate": 4.1404594179939814e-05, "loss": 4.184, "step": 5059 }, { "epoch": 0.2722772277227723, "grad_norm": 2.3654415607452393, "learning_rate": 4.1401404845573175e-05, "loss": 4.5712, "step": 5060 }, { "epoch": 0.2723310374515712, "grad_norm": 1.184073805809021, "learning_rate": 4.13982150424985e-05, "loss": 4.7589, "step": 5061 }, { "epoch": 0.2723848471803702, "grad_norm": 2.4229049682617188, "learning_rate": 4.139502477080695e-05, "loss": 3.6728, "step": 5062 }, { "epoch": 0.2724386569091692, "grad_norm": 2.1620237827301025, "learning_rate": 4.1391834030589686e-05, "loss": 4.1841, "step": 5063 }, { "epoch": 0.27249246663796817, "grad_norm": 1.698757529258728, "learning_rate": 4.1388642821937896e-05, "loss": 4.765, "step": 5064 }, { "epoch": 0.2725462763667671, "grad_norm": 1.714102029800415, "learning_rate": 4.138545114494277e-05, "loss": 4.645, "step": 5065 }, { "epoch": 0.2726000860955661, "grad_norm": 2.237746477127075, "learning_rate": 4.1382258999695535e-05, "loss": 4.8796, "step": 5066 }, { "epoch": 0.27265389582436506, "grad_norm": 2.495936870574951, "learning_rate": 4.137906638628739e-05, "loss": 4.2953, "step": 5067 }, { "epoch": 0.27270770555316404, "grad_norm": 1.900787115097046, "learning_rate": 4.1375873304809574e-05, "loss": 4.4419, "step": 5068 }, { "epoch": 0.27276151528196296, "grad_norm": 2.7472846508026123, "learning_rate": 4.137267975535336e-05, "loss": 4.2562, "step": 5069 }, { "epoch": 0.27281532501076194, "grad_norm": 1.8528960943222046, "learning_rate": 4.136948573800999e-05, "loss": 4.6598, "step": 5070 }, { "epoch": 0.2728691347395609, "grad_norm": 1.3301087617874146, "learning_rate": 4.136629125287075e-05, "loss": 4.6501, "step": 5071 }, { "epoch": 0.2729229444683599, "grad_norm": 1.882582664489746, "learning_rate": 4.136309630002692e-05, "loss": 4.2517, "step": 5072 }, { "epoch": 0.27297675419715883, "grad_norm": 2.758849620819092, "learning_rate": 4.135990087956981e-05, "loss": 4.7048, "step": 5073 }, { "epoch": 0.2730305639259578, "grad_norm": 2.1531035900115967, "learning_rate": 4.135670499159074e-05, "loss": 4.6301, "step": 5074 }, { "epoch": 0.2730843736547568, "grad_norm": 1.4879237413406372, "learning_rate": 4.135350863618104e-05, "loss": 4.7073, "step": 5075 }, { "epoch": 0.2731381833835557, "grad_norm": 1.9848926067352295, "learning_rate": 4.1350311813432044e-05, "loss": 4.3852, "step": 5076 }, { "epoch": 0.2731919931123547, "grad_norm": 1.6894394159317017, "learning_rate": 4.134711452343511e-05, "loss": 4.4105, "step": 5077 }, { "epoch": 0.2732458028411537, "grad_norm": 1.5073466300964355, "learning_rate": 4.134391676628161e-05, "loss": 4.3184, "step": 5078 }, { "epoch": 0.27329961256995267, "grad_norm": 2.4199159145355225, "learning_rate": 4.1340718542062934e-05, "loss": 3.9823, "step": 5079 }, { "epoch": 0.2733534222987516, "grad_norm": 1.6527259349822998, "learning_rate": 4.133751985087047e-05, "loss": 4.8232, "step": 5080 }, { "epoch": 0.2734072320275506, "grad_norm": 1.8892452716827393, "learning_rate": 4.133432069279564e-05, "loss": 4.4238, "step": 5081 }, { "epoch": 0.27346104175634955, "grad_norm": 2.024118423461914, "learning_rate": 4.1331121067929846e-05, "loss": 4.3361, "step": 5082 }, { "epoch": 0.27351485148514854, "grad_norm": 1.3983515501022339, "learning_rate": 4.132792097636454e-05, "loss": 5.0888, "step": 5083 }, { "epoch": 0.27356866121394746, "grad_norm": 1.5581822395324707, "learning_rate": 4.132472041819117e-05, "loss": 4.3911, "step": 5084 }, { "epoch": 0.27362247094274644, "grad_norm": 1.647045612335205, "learning_rate": 4.132151939350121e-05, "loss": 4.586, "step": 5085 }, { "epoch": 0.2736762806715454, "grad_norm": 2.064241647720337, "learning_rate": 4.131831790238612e-05, "loss": 4.5498, "step": 5086 }, { "epoch": 0.2737300904003444, "grad_norm": 1.688191294670105, "learning_rate": 4.131511594493739e-05, "loss": 4.8345, "step": 5087 }, { "epoch": 0.27378390012914333, "grad_norm": 1.6715660095214844, "learning_rate": 4.1311913521246534e-05, "loss": 4.5861, "step": 5088 }, { "epoch": 0.2738377098579423, "grad_norm": 1.7372335195541382, "learning_rate": 4.1308710631405065e-05, "loss": 4.528, "step": 5089 }, { "epoch": 0.2738915195867413, "grad_norm": 1.665115475654602, "learning_rate": 4.1305507275504505e-05, "loss": 4.7647, "step": 5090 }, { "epoch": 0.2739453293155403, "grad_norm": 1.3265067338943481, "learning_rate": 4.1302303453636404e-05, "loss": 4.703, "step": 5091 }, { "epoch": 0.2739991390443392, "grad_norm": 1.1442523002624512, "learning_rate": 4.129909916589232e-05, "loss": 4.7156, "step": 5092 }, { "epoch": 0.2740529487731382, "grad_norm": 2.1162822246551514, "learning_rate": 4.1295894412363824e-05, "loss": 4.4954, "step": 5093 }, { "epoch": 0.27410675850193716, "grad_norm": 1.2702707052230835, "learning_rate": 4.12926891931425e-05, "loss": 4.1349, "step": 5094 }, { "epoch": 0.2741605682307361, "grad_norm": 2.0173349380493164, "learning_rate": 4.128948350831993e-05, "loss": 4.4382, "step": 5095 }, { "epoch": 0.27421437795953507, "grad_norm": 1.265312671661377, "learning_rate": 4.1286277357987743e-05, "loss": 4.7283, "step": 5096 }, { "epoch": 0.27426818768833405, "grad_norm": 1.2736412286758423, "learning_rate": 4.128307074223755e-05, "loss": 3.9845, "step": 5097 }, { "epoch": 0.27432199741713303, "grad_norm": 1.7882356643676758, "learning_rate": 4.127986366116099e-05, "loss": 4.7091, "step": 5098 }, { "epoch": 0.27437580714593196, "grad_norm": 1.7946897745132446, "learning_rate": 4.127665611484972e-05, "loss": 4.3672, "step": 5099 }, { "epoch": 0.27442961687473094, "grad_norm": 2.572472333908081, "learning_rate": 4.1273448103395396e-05, "loss": 4.2451, "step": 5100 }, { "epoch": 0.2744834266035299, "grad_norm": 1.9820476770401, "learning_rate": 4.127023962688969e-05, "loss": 4.8075, "step": 5101 }, { "epoch": 0.2745372363323289, "grad_norm": 1.6357340812683105, "learning_rate": 4.1267030685424304e-05, "loss": 4.8375, "step": 5102 }, { "epoch": 0.27459104606112783, "grad_norm": 1.5679343938827515, "learning_rate": 4.126382127909093e-05, "loss": 4.3825, "step": 5103 }, { "epoch": 0.2746448557899268, "grad_norm": 3.02329421043396, "learning_rate": 4.126061140798129e-05, "loss": 4.6161, "step": 5104 }, { "epoch": 0.2746986655187258, "grad_norm": 1.2528654336929321, "learning_rate": 4.1257401072187114e-05, "loss": 4.8166, "step": 5105 }, { "epoch": 0.2747524752475248, "grad_norm": 1.1024805307388306, "learning_rate": 4.125419027180014e-05, "loss": 4.7242, "step": 5106 }, { "epoch": 0.2748062849763237, "grad_norm": 1.4402306079864502, "learning_rate": 4.1250979006912125e-05, "loss": 4.5922, "step": 5107 }, { "epoch": 0.2748600947051227, "grad_norm": 2.0609614849090576, "learning_rate": 4.124776727761484e-05, "loss": 4.3832, "step": 5108 }, { "epoch": 0.27491390443392166, "grad_norm": 1.9818837642669678, "learning_rate": 4.124455508400007e-05, "loss": 4.8742, "step": 5109 }, { "epoch": 0.27496771416272064, "grad_norm": 1.0946471691131592, "learning_rate": 4.124134242615961e-05, "loss": 4.4349, "step": 5110 }, { "epoch": 0.27502152389151957, "grad_norm": 1.4172395467758179, "learning_rate": 4.1238129304185266e-05, "loss": 4.4454, "step": 5111 }, { "epoch": 0.27507533362031855, "grad_norm": 2.0204923152923584, "learning_rate": 4.1234915718168866e-05, "loss": 4.7958, "step": 5112 }, { "epoch": 0.27512914334911753, "grad_norm": 1.491126537322998, "learning_rate": 4.123170166820223e-05, "loss": 4.6823, "step": 5113 }, { "epoch": 0.2751829530779165, "grad_norm": 1.6483911275863647, "learning_rate": 4.122848715437723e-05, "loss": 4.2213, "step": 5114 }, { "epoch": 0.27523676280671544, "grad_norm": 1.8230488300323486, "learning_rate": 4.122527217678571e-05, "loss": 4.2303, "step": 5115 }, { "epoch": 0.2752905725355144, "grad_norm": 1.549346685409546, "learning_rate": 4.1222056735519555e-05, "loss": 4.8398, "step": 5116 }, { "epoch": 0.2753443822643134, "grad_norm": 1.4732102155685425, "learning_rate": 4.121884083067065e-05, "loss": 4.5231, "step": 5117 }, { "epoch": 0.27539819199311233, "grad_norm": 1.8279259204864502, "learning_rate": 4.1215624462330896e-05, "loss": 4.5007, "step": 5118 }, { "epoch": 0.2754520017219113, "grad_norm": 1.5665464401245117, "learning_rate": 4.1212407630592215e-05, "loss": 4.4928, "step": 5119 }, { "epoch": 0.2755058114507103, "grad_norm": 2.0065364837646484, "learning_rate": 4.120919033554653e-05, "loss": 4.1397, "step": 5120 }, { "epoch": 0.2755596211795093, "grad_norm": 1.4627609252929688, "learning_rate": 4.120597257728578e-05, "loss": 4.5307, "step": 5121 }, { "epoch": 0.2756134309083082, "grad_norm": 1.7656958103179932, "learning_rate": 4.120275435590192e-05, "loss": 4.9844, "step": 5122 }, { "epoch": 0.2756672406371072, "grad_norm": 1.299544095993042, "learning_rate": 4.119953567148692e-05, "loss": 4.6672, "step": 5123 }, { "epoch": 0.27572105036590616, "grad_norm": 1.6844379901885986, "learning_rate": 4.119631652413277e-05, "loss": 4.369, "step": 5124 }, { "epoch": 0.27577486009470514, "grad_norm": 1.158407211303711, "learning_rate": 4.119309691393145e-05, "loss": 4.6963, "step": 5125 }, { "epoch": 0.27582866982350407, "grad_norm": 1.8925317525863647, "learning_rate": 4.118987684097497e-05, "loss": 4.4732, "step": 5126 }, { "epoch": 0.27588247955230305, "grad_norm": 1.23883855342865, "learning_rate": 4.118665630535537e-05, "loss": 4.6069, "step": 5127 }, { "epoch": 0.27593628928110203, "grad_norm": 1.8655158281326294, "learning_rate": 4.118343530716465e-05, "loss": 4.2654, "step": 5128 }, { "epoch": 0.275990099009901, "grad_norm": 1.0579960346221924, "learning_rate": 4.1180213846494896e-05, "loss": 4.7055, "step": 5129 }, { "epoch": 0.27604390873869994, "grad_norm": 2.2138068675994873, "learning_rate": 4.117699192343814e-05, "loss": 4.4226, "step": 5130 }, { "epoch": 0.2760977184674989, "grad_norm": 2.4101226329803467, "learning_rate": 4.117376953808647e-05, "loss": 4.098, "step": 5131 }, { "epoch": 0.2761515281962979, "grad_norm": 1.1362286806106567, "learning_rate": 4.117054669053196e-05, "loss": 4.6426, "step": 5132 }, { "epoch": 0.2762053379250969, "grad_norm": 1.1951067447662354, "learning_rate": 4.1167323380866736e-05, "loss": 4.5301, "step": 5133 }, { "epoch": 0.2762591476538958, "grad_norm": 1.5617998838424683, "learning_rate": 4.116409960918288e-05, "loss": 4.6079, "step": 5134 }, { "epoch": 0.2763129573826948, "grad_norm": 1.3170422315597534, "learning_rate": 4.1160875375572545e-05, "loss": 4.2912, "step": 5135 }, { "epoch": 0.27636676711149377, "grad_norm": 1.3530032634735107, "learning_rate": 4.115765068012785e-05, "loss": 4.5655, "step": 5136 }, { "epoch": 0.2764205768402927, "grad_norm": 1.569757103919983, "learning_rate": 4.1154425522940966e-05, "loss": 4.9318, "step": 5137 }, { "epoch": 0.2764743865690917, "grad_norm": 1.685656189918518, "learning_rate": 4.1151199904104046e-05, "loss": 4.6546, "step": 5138 }, { "epoch": 0.27652819629789066, "grad_norm": 1.4375600814819336, "learning_rate": 4.114797382370927e-05, "loss": 4.6778, "step": 5139 }, { "epoch": 0.27658200602668964, "grad_norm": 2.3789350986480713, "learning_rate": 4.114474728184884e-05, "loss": 4.8061, "step": 5140 }, { "epoch": 0.27663581575548857, "grad_norm": 3.6324572563171387, "learning_rate": 4.1141520278614954e-05, "loss": 4.825, "step": 5141 }, { "epoch": 0.27668962548428755, "grad_norm": 1.7103772163391113, "learning_rate": 4.113829281409984e-05, "loss": 4.3411, "step": 5142 }, { "epoch": 0.27674343521308653, "grad_norm": 1.9566497802734375, "learning_rate": 4.113506488839573e-05, "loss": 4.4664, "step": 5143 }, { "epoch": 0.2767972449418855, "grad_norm": 1.3554623126983643, "learning_rate": 4.113183650159484e-05, "loss": 4.2858, "step": 5144 }, { "epoch": 0.27685105467068444, "grad_norm": 1.5120444297790527, "learning_rate": 4.112860765378947e-05, "loss": 4.5381, "step": 5145 }, { "epoch": 0.2769048643994834, "grad_norm": 1.536808729171753, "learning_rate": 4.1125378345071876e-05, "loss": 4.8186, "step": 5146 }, { "epoch": 0.2769586741282824, "grad_norm": 2.234931230545044, "learning_rate": 4.112214857553434e-05, "loss": 4.7467, "step": 5147 }, { "epoch": 0.2770124838570814, "grad_norm": 1.169215202331543, "learning_rate": 4.111891834526915e-05, "loss": 4.9199, "step": 5148 }, { "epoch": 0.2770662935858803, "grad_norm": 1.5803841352462769, "learning_rate": 4.111568765436863e-05, "loss": 4.4853, "step": 5149 }, { "epoch": 0.2771201033146793, "grad_norm": 1.36176335811615, "learning_rate": 4.111245650292511e-05, "loss": 4.4717, "step": 5150 }, { "epoch": 0.27717391304347827, "grad_norm": 1.1449131965637207, "learning_rate": 4.1109224891030923e-05, "loss": 4.7076, "step": 5151 }, { "epoch": 0.27722772277227725, "grad_norm": 1.8093937635421753, "learning_rate": 4.110599281877841e-05, "loss": 4.4081, "step": 5152 }, { "epoch": 0.2772815325010762, "grad_norm": 1.0996572971343994, "learning_rate": 4.110276028625995e-05, "loss": 4.4536, "step": 5153 }, { "epoch": 0.27733534222987516, "grad_norm": 2.1828713417053223, "learning_rate": 4.109952729356791e-05, "loss": 4.4045, "step": 5154 }, { "epoch": 0.27738915195867414, "grad_norm": 1.3415203094482422, "learning_rate": 4.1096293840794674e-05, "loss": 4.8011, "step": 5155 }, { "epoch": 0.2774429616874731, "grad_norm": 1.3182964324951172, "learning_rate": 4.1093059928032664e-05, "loss": 4.6643, "step": 5156 }, { "epoch": 0.27749677141627205, "grad_norm": 2.032042980194092, "learning_rate": 4.108982555537428e-05, "loss": 4.5495, "step": 5157 }, { "epoch": 0.27755058114507103, "grad_norm": 1.362945556640625, "learning_rate": 4.1086590722911965e-05, "loss": 4.8183, "step": 5158 }, { "epoch": 0.27760439087387, "grad_norm": 1.7222373485565186, "learning_rate": 4.1083355430738145e-05, "loss": 4.6585, "step": 5159 }, { "epoch": 0.27765820060266894, "grad_norm": 1.093682885169983, "learning_rate": 4.1080119678945295e-05, "loss": 4.5572, "step": 5160 }, { "epoch": 0.2777120103314679, "grad_norm": 1.3711649179458618, "learning_rate": 4.107688346762588e-05, "loss": 4.7359, "step": 5161 }, { "epoch": 0.2777658200602669, "grad_norm": 1.8284566402435303, "learning_rate": 4.107364679687236e-05, "loss": 4.494, "step": 5162 }, { "epoch": 0.2778196297890659, "grad_norm": 1.159419059753418, "learning_rate": 4.107040966677725e-05, "loss": 4.5236, "step": 5163 }, { "epoch": 0.2778734395178648, "grad_norm": 2.2398056983947754, "learning_rate": 4.106717207743307e-05, "loss": 4.334, "step": 5164 }, { "epoch": 0.2779272492466638, "grad_norm": 1.5691570043563843, "learning_rate": 4.1063934028932326e-05, "loss": 4.9661, "step": 5165 }, { "epoch": 0.27798105897546277, "grad_norm": 2.716111421585083, "learning_rate": 4.106069552136754e-05, "loss": 3.945, "step": 5166 }, { "epoch": 0.27803486870426175, "grad_norm": 1.4404855966567993, "learning_rate": 4.1057456554831284e-05, "loss": 4.3401, "step": 5167 }, { "epoch": 0.2780886784330607, "grad_norm": 1.7608013153076172, "learning_rate": 4.1054217129416115e-05, "loss": 4.9122, "step": 5168 }, { "epoch": 0.27814248816185966, "grad_norm": 2.0186026096343994, "learning_rate": 4.1050977245214596e-05, "loss": 4.4164, "step": 5169 }, { "epoch": 0.27819629789065864, "grad_norm": 1.1007789373397827, "learning_rate": 4.104773690231931e-05, "loss": 4.7474, "step": 5170 }, { "epoch": 0.2782501076194576, "grad_norm": 1.6415718793869019, "learning_rate": 4.104449610082288e-05, "loss": 4.8123, "step": 5171 }, { "epoch": 0.27830391734825655, "grad_norm": 1.5112797021865845, "learning_rate": 4.10412548408179e-05, "loss": 4.7551, "step": 5172 }, { "epoch": 0.27835772707705553, "grad_norm": 1.5887953042984009, "learning_rate": 4.1038013122397004e-05, "loss": 4.5754, "step": 5173 }, { "epoch": 0.2784115368058545, "grad_norm": 1.4187901020050049, "learning_rate": 4.103477094565283e-05, "loss": 4.6803, "step": 5174 }, { "epoch": 0.2784653465346535, "grad_norm": 1.7893192768096924, "learning_rate": 4.103152831067802e-05, "loss": 4.1384, "step": 5175 }, { "epoch": 0.2785191562634524, "grad_norm": 2.420731782913208, "learning_rate": 4.1028285217565265e-05, "loss": 4.3261, "step": 5176 }, { "epoch": 0.2785729659922514, "grad_norm": 0.9905709624290466, "learning_rate": 4.102504166640723e-05, "loss": 4.9837, "step": 5177 }, { "epoch": 0.2786267757210504, "grad_norm": 2.0094234943389893, "learning_rate": 4.1021797657296604e-05, "loss": 4.1129, "step": 5178 }, { "epoch": 0.2786805854498493, "grad_norm": 2.871777296066284, "learning_rate": 4.101855319032609e-05, "loss": 4.144, "step": 5179 }, { "epoch": 0.2787343951786483, "grad_norm": 1.2493786811828613, "learning_rate": 4.1015308265588416e-05, "loss": 4.8607, "step": 5180 }, { "epoch": 0.27878820490744727, "grad_norm": 1.8586922883987427, "learning_rate": 4.1012062883176307e-05, "loss": 4.2994, "step": 5181 }, { "epoch": 0.27884201463624625, "grad_norm": 1.6487449407577515, "learning_rate": 4.1008817043182505e-05, "loss": 4.9403, "step": 5182 }, { "epoch": 0.2788958243650452, "grad_norm": 2.4961471557617188, "learning_rate": 4.100557074569977e-05, "loss": 4.3977, "step": 5183 }, { "epoch": 0.27894963409384416, "grad_norm": 1.7429701089859009, "learning_rate": 4.100232399082087e-05, "loss": 4.7504, "step": 5184 }, { "epoch": 0.27900344382264314, "grad_norm": 1.2939903736114502, "learning_rate": 4.09990767786386e-05, "loss": 4.5868, "step": 5185 }, { "epoch": 0.2790572535514421, "grad_norm": 1.5034037828445435, "learning_rate": 4.099582910924574e-05, "loss": 4.9659, "step": 5186 }, { "epoch": 0.27911106328024105, "grad_norm": 1.6142427921295166, "learning_rate": 4.0992580982735116e-05, "loss": 5.0072, "step": 5187 }, { "epoch": 0.27916487300904, "grad_norm": 1.5625606775283813, "learning_rate": 4.0989332399199545e-05, "loss": 4.5025, "step": 5188 }, { "epoch": 0.279218682737839, "grad_norm": 1.4621284008026123, "learning_rate": 4.098608335873185e-05, "loss": 4.6775, "step": 5189 }, { "epoch": 0.279272492466638, "grad_norm": 1.7383403778076172, "learning_rate": 4.098283386142489e-05, "loss": 4.7201, "step": 5190 }, { "epoch": 0.2793263021954369, "grad_norm": 2.402933120727539, "learning_rate": 4.097958390737153e-05, "loss": 4.3161, "step": 5191 }, { "epoch": 0.2793801119242359, "grad_norm": 2.063589096069336, "learning_rate": 4.0976333496664646e-05, "loss": 4.6267, "step": 5192 }, { "epoch": 0.2794339216530349, "grad_norm": 1.4309272766113281, "learning_rate": 4.097308262939712e-05, "loss": 4.5949, "step": 5193 }, { "epoch": 0.27948773138183386, "grad_norm": 1.767345666885376, "learning_rate": 4.0969831305661854e-05, "loss": 4.4889, "step": 5194 }, { "epoch": 0.2795415411106328, "grad_norm": 1.108444333076477, "learning_rate": 4.096657952555176e-05, "loss": 4.6379, "step": 5195 }, { "epoch": 0.27959535083943177, "grad_norm": 2.086514472961426, "learning_rate": 4.096332728915978e-05, "loss": 4.372, "step": 5196 }, { "epoch": 0.27964916056823075, "grad_norm": 2.430504322052002, "learning_rate": 4.096007459657883e-05, "loss": 4.2317, "step": 5197 }, { "epoch": 0.27970297029702973, "grad_norm": 1.1251509189605713, "learning_rate": 4.095682144790187e-05, "loss": 4.6823, "step": 5198 }, { "epoch": 0.27975678002582866, "grad_norm": 1.7290005683898926, "learning_rate": 4.0953567843221885e-05, "loss": 4.8805, "step": 5199 }, { "epoch": 0.27981058975462764, "grad_norm": 1.2674912214279175, "learning_rate": 4.0950313782631835e-05, "loss": 4.6403, "step": 5200 }, { "epoch": 0.2798643994834266, "grad_norm": 1.5457568168640137, "learning_rate": 4.0947059266224726e-05, "loss": 4.9445, "step": 5201 }, { "epoch": 0.27991820921222554, "grad_norm": 1.2692371606826782, "learning_rate": 4.094380429409355e-05, "loss": 4.5994, "step": 5202 }, { "epoch": 0.2799720189410245, "grad_norm": 1.3521356582641602, "learning_rate": 4.094054886633133e-05, "loss": 4.4063, "step": 5203 }, { "epoch": 0.2800258286698235, "grad_norm": 0.9777380228042603, "learning_rate": 4.09372929830311e-05, "loss": 4.7986, "step": 5204 }, { "epoch": 0.2800796383986225, "grad_norm": 1.4684510231018066, "learning_rate": 4.09340366442859e-05, "loss": 4.6758, "step": 5205 }, { "epoch": 0.2801334481274214, "grad_norm": 1.2929342985153198, "learning_rate": 4.0930779850188796e-05, "loss": 4.4109, "step": 5206 }, { "epoch": 0.2801872578562204, "grad_norm": 1.6597741842269897, "learning_rate": 4.092752260083285e-05, "loss": 4.6398, "step": 5207 }, { "epoch": 0.2802410675850194, "grad_norm": 1.6433379650115967, "learning_rate": 4.092426489631115e-05, "loss": 4.1941, "step": 5208 }, { "epoch": 0.28029487731381836, "grad_norm": 1.5367727279663086, "learning_rate": 4.0921006736716785e-05, "loss": 4.554, "step": 5209 }, { "epoch": 0.2803486870426173, "grad_norm": 2.304797410964966, "learning_rate": 4.091774812214288e-05, "loss": 4.2692, "step": 5210 }, { "epoch": 0.28040249677141627, "grad_norm": 1.0939300060272217, "learning_rate": 4.0914489052682535e-05, "loss": 4.7499, "step": 5211 }, { "epoch": 0.28045630650021525, "grad_norm": 1.7123535871505737, "learning_rate": 4.09112295284289e-05, "loss": 4.3413, "step": 5212 }, { "epoch": 0.28051011622901423, "grad_norm": 1.3697618246078491, "learning_rate": 4.090796954947512e-05, "loss": 4.703, "step": 5213 }, { "epoch": 0.28056392595781315, "grad_norm": 1.7812596559524536, "learning_rate": 4.0904709115914364e-05, "loss": 4.3142, "step": 5214 }, { "epoch": 0.28061773568661214, "grad_norm": 1.598099708557129, "learning_rate": 4.09014482278398e-05, "loss": 4.8038, "step": 5215 }, { "epoch": 0.2806715454154111, "grad_norm": 1.2094879150390625, "learning_rate": 4.0898186885344616e-05, "loss": 4.2815, "step": 5216 }, { "epoch": 0.2807253551442101, "grad_norm": 1.3678758144378662, "learning_rate": 4.0894925088522006e-05, "loss": 4.2407, "step": 5217 }, { "epoch": 0.280779164873009, "grad_norm": 1.5518934726715088, "learning_rate": 4.089166283746519e-05, "loss": 4.611, "step": 5218 }, { "epoch": 0.280832974601808, "grad_norm": 2.043466806411743, "learning_rate": 4.08884001322674e-05, "loss": 4.5329, "step": 5219 }, { "epoch": 0.280886784330607, "grad_norm": 1.7356164455413818, "learning_rate": 4.088513697302187e-05, "loss": 4.8774, "step": 5220 }, { "epoch": 0.28094059405940597, "grad_norm": 1.7898372411727905, "learning_rate": 4.0881873359821844e-05, "loss": 4.3061, "step": 5221 }, { "epoch": 0.2809944037882049, "grad_norm": 1.1589491367340088, "learning_rate": 4.08786092927606e-05, "loss": 4.6325, "step": 5222 }, { "epoch": 0.2810482135170039, "grad_norm": 1.8462904691696167, "learning_rate": 4.087534477193141e-05, "loss": 4.5773, "step": 5223 }, { "epoch": 0.28110202324580286, "grad_norm": 2.2065529823303223, "learning_rate": 4.087207979742757e-05, "loss": 3.9815, "step": 5224 }, { "epoch": 0.2811558329746018, "grad_norm": 1.4750456809997559, "learning_rate": 4.086881436934237e-05, "loss": 4.7131, "step": 5225 }, { "epoch": 0.28120964270340076, "grad_norm": 2.2794997692108154, "learning_rate": 4.086554848776914e-05, "loss": 3.9365, "step": 5226 }, { "epoch": 0.28126345243219975, "grad_norm": 2.1774394512176514, "learning_rate": 4.0862282152801214e-05, "loss": 3.9435, "step": 5227 }, { "epoch": 0.2813172621609987, "grad_norm": 1.576804280281067, "learning_rate": 4.085901536453192e-05, "loss": 4.547, "step": 5228 }, { "epoch": 0.28137107188979765, "grad_norm": 1.3559768199920654, "learning_rate": 4.085574812305463e-05, "loss": 4.6174, "step": 5229 }, { "epoch": 0.28142488161859663, "grad_norm": 1.3565441370010376, "learning_rate": 4.08524804284627e-05, "loss": 4.7734, "step": 5230 }, { "epoch": 0.2814786913473956, "grad_norm": 2.045398235321045, "learning_rate": 4.0849212280849516e-05, "loss": 4.6293, "step": 5231 }, { "epoch": 0.2815325010761946, "grad_norm": 1.770758867263794, "learning_rate": 4.084594368030848e-05, "loss": 4.2489, "step": 5232 }, { "epoch": 0.2815863108049935, "grad_norm": 1.3370412588119507, "learning_rate": 4.0842674626933e-05, "loss": 4.6381, "step": 5233 }, { "epoch": 0.2816401205337925, "grad_norm": 1.257830023765564, "learning_rate": 4.083940512081648e-05, "loss": 4.409, "step": 5234 }, { "epoch": 0.2816939302625915, "grad_norm": 1.0018680095672607, "learning_rate": 4.083613516205237e-05, "loss": 4.6946, "step": 5235 }, { "epoch": 0.28174773999139047, "grad_norm": 1.527158498764038, "learning_rate": 4.0832864750734105e-05, "loss": 4.5796, "step": 5236 }, { "epoch": 0.2818015497201894, "grad_norm": 1.9044189453125, "learning_rate": 4.0829593886955155e-05, "loss": 4.4405, "step": 5237 }, { "epoch": 0.2818553594489884, "grad_norm": 1.4026200771331787, "learning_rate": 4.0826322570809e-05, "loss": 4.4797, "step": 5238 }, { "epoch": 0.28190916917778736, "grad_norm": 3.2262797355651855, "learning_rate": 4.0823050802389095e-05, "loss": 3.9521, "step": 5239 }, { "epoch": 0.28196297890658634, "grad_norm": 1.4962714910507202, "learning_rate": 4.081977858178896e-05, "loss": 4.2292, "step": 5240 }, { "epoch": 0.28201678863538526, "grad_norm": 1.0300313234329224, "learning_rate": 4.081650590910211e-05, "loss": 4.6267, "step": 5241 }, { "epoch": 0.28207059836418424, "grad_norm": 1.264788031578064, "learning_rate": 4.081323278442206e-05, "loss": 4.5503, "step": 5242 }, { "epoch": 0.2821244080929832, "grad_norm": 1.9861303567886353, "learning_rate": 4.0809959207842354e-05, "loss": 4.5542, "step": 5243 }, { "epoch": 0.28217821782178215, "grad_norm": 1.8296622037887573, "learning_rate": 4.080668517945653e-05, "loss": 4.6024, "step": 5244 }, { "epoch": 0.28223202755058113, "grad_norm": 2.261720895767212, "learning_rate": 4.0803410699358164e-05, "loss": 4.5506, "step": 5245 }, { "epoch": 0.2822858372793801, "grad_norm": 1.6878575086593628, "learning_rate": 4.0800135767640825e-05, "loss": 4.5092, "step": 5246 }, { "epoch": 0.2823396470081791, "grad_norm": 2.105884075164795, "learning_rate": 4.07968603843981e-05, "loss": 4.5882, "step": 5247 }, { "epoch": 0.282393456736978, "grad_norm": 1.7180153131484985, "learning_rate": 4.0793584549723595e-05, "loss": 4.582, "step": 5248 }, { "epoch": 0.282447266465777, "grad_norm": 1.8086096048355103, "learning_rate": 4.079030826371093e-05, "loss": 4.4795, "step": 5249 }, { "epoch": 0.282501076194576, "grad_norm": 1.7211239337921143, "learning_rate": 4.0787031526453724e-05, "loss": 4.6863, "step": 5250 }, { "epoch": 0.28255488592337497, "grad_norm": 1.3220593929290771, "learning_rate": 4.078375433804561e-05, "loss": 4.3449, "step": 5251 }, { "epoch": 0.2826086956521739, "grad_norm": 1.9284090995788574, "learning_rate": 4.078047669858025e-05, "loss": 4.0439, "step": 5252 }, { "epoch": 0.2826625053809729, "grad_norm": 1.2851347923278809, "learning_rate": 4.077719860815132e-05, "loss": 4.2687, "step": 5253 }, { "epoch": 0.28271631510977185, "grad_norm": 1.9455304145812988, "learning_rate": 4.077392006685249e-05, "loss": 4.675, "step": 5254 }, { "epoch": 0.28277012483857084, "grad_norm": 1.6402535438537598, "learning_rate": 4.077064107477745e-05, "loss": 4.5076, "step": 5255 }, { "epoch": 0.28282393456736976, "grad_norm": 2.0790855884552, "learning_rate": 4.0767361632019894e-05, "loss": 4.2283, "step": 5256 }, { "epoch": 0.28287774429616874, "grad_norm": 1.502074122428894, "learning_rate": 4.076408173867357e-05, "loss": 4.529, "step": 5257 }, { "epoch": 0.2829315540249677, "grad_norm": 1.7764806747436523, "learning_rate": 4.076080139483218e-05, "loss": 4.5322, "step": 5258 }, { "epoch": 0.2829853637537667, "grad_norm": 3.2234833240509033, "learning_rate": 4.0757520600589476e-05, "loss": 4.405, "step": 5259 }, { "epoch": 0.28303917348256563, "grad_norm": 1.176156759262085, "learning_rate": 4.075423935603922e-05, "loss": 4.7036, "step": 5260 }, { "epoch": 0.2830929832113646, "grad_norm": 0.948064386844635, "learning_rate": 4.075095766127518e-05, "loss": 4.4308, "step": 5261 }, { "epoch": 0.2831467929401636, "grad_norm": 1.1294893026351929, "learning_rate": 4.0747675516391123e-05, "loss": 4.8216, "step": 5262 }, { "epoch": 0.2832006026689626, "grad_norm": 0.8774902820587158, "learning_rate": 4.074439292148087e-05, "loss": 4.4391, "step": 5263 }, { "epoch": 0.2832544123977615, "grad_norm": 2.5141215324401855, "learning_rate": 4.0741109876638206e-05, "loss": 4.2451, "step": 5264 }, { "epoch": 0.2833082221265605, "grad_norm": 1.2244690656661987, "learning_rate": 4.0737826381956964e-05, "loss": 4.0066, "step": 5265 }, { "epoch": 0.28336203185535946, "grad_norm": 2.225205183029175, "learning_rate": 4.0734542437530975e-05, "loss": 4.3875, "step": 5266 }, { "epoch": 0.2834158415841584, "grad_norm": 1.701527714729309, "learning_rate": 4.073125804345408e-05, "loss": 4.1363, "step": 5267 }, { "epoch": 0.28346965131295737, "grad_norm": 1.6234248876571655, "learning_rate": 4.072797319982015e-05, "loss": 4.3839, "step": 5268 }, { "epoch": 0.28352346104175635, "grad_norm": 1.4351856708526611, "learning_rate": 4.072468790672304e-05, "loss": 4.6916, "step": 5269 }, { "epoch": 0.28357727077055533, "grad_norm": 1.885085105895996, "learning_rate": 4.072140216425665e-05, "loss": 4.2773, "step": 5270 }, { "epoch": 0.28363108049935426, "grad_norm": 1.7160797119140625, "learning_rate": 4.071811597251487e-05, "loss": 4.4439, "step": 5271 }, { "epoch": 0.28368489022815324, "grad_norm": 1.2283210754394531, "learning_rate": 4.071482933159161e-05, "loss": 4.4476, "step": 5272 }, { "epoch": 0.2837386999569522, "grad_norm": 2.2985568046569824, "learning_rate": 4.07115422415808e-05, "loss": 4.3582, "step": 5273 }, { "epoch": 0.2837925096857512, "grad_norm": 1.41886568069458, "learning_rate": 4.070825470257636e-05, "loss": 4.7796, "step": 5274 }, { "epoch": 0.28384631941455013, "grad_norm": 1.1203902959823608, "learning_rate": 4.070496671467226e-05, "loss": 4.4357, "step": 5275 }, { "epoch": 0.2839001291433491, "grad_norm": 2.034658193588257, "learning_rate": 4.0701678277962464e-05, "loss": 4.3811, "step": 5276 }, { "epoch": 0.2839539388721481, "grad_norm": 1.742856740951538, "learning_rate": 4.0698389392540926e-05, "loss": 4.6906, "step": 5277 }, { "epoch": 0.2840077486009471, "grad_norm": 1.4016788005828857, "learning_rate": 4.0695100058501634e-05, "loss": 4.34, "step": 5278 }, { "epoch": 0.284061558329746, "grad_norm": 0.9798899292945862, "learning_rate": 4.0691810275938604e-05, "loss": 4.6473, "step": 5279 }, { "epoch": 0.284115368058545, "grad_norm": 2.011362314224243, "learning_rate": 4.068852004494584e-05, "loss": 4.3807, "step": 5280 }, { "epoch": 0.28416917778734396, "grad_norm": 2.6615095138549805, "learning_rate": 4.068522936561738e-05, "loss": 3.9564, "step": 5281 }, { "epoch": 0.28422298751614294, "grad_norm": 1.7852438688278198, "learning_rate": 4.0681938238047244e-05, "loss": 4.3684, "step": 5282 }, { "epoch": 0.28427679724494187, "grad_norm": 1.5987164974212646, "learning_rate": 4.06786466623295e-05, "loss": 4.6328, "step": 5283 }, { "epoch": 0.28433060697374085, "grad_norm": 1.875746250152588, "learning_rate": 4.067535463855819e-05, "loss": 4.3686, "step": 5284 }, { "epoch": 0.28438441670253983, "grad_norm": 1.538713812828064, "learning_rate": 4.0672062166827424e-05, "loss": 4.0848, "step": 5285 }, { "epoch": 0.28443822643133876, "grad_norm": 1.8137705326080322, "learning_rate": 4.0668769247231266e-05, "loss": 4.3706, "step": 5286 }, { "epoch": 0.28449203616013774, "grad_norm": 1.824278473854065, "learning_rate": 4.0665475879863826e-05, "loss": 4.2227, "step": 5287 }, { "epoch": 0.2845458458889367, "grad_norm": 2.4946177005767822, "learning_rate": 4.066218206481922e-05, "loss": 4.4015, "step": 5288 }, { "epoch": 0.2845996556177357, "grad_norm": 1.5285149812698364, "learning_rate": 4.065888780219158e-05, "loss": 4.7612, "step": 5289 }, { "epoch": 0.28465346534653463, "grad_norm": 0.9280834197998047, "learning_rate": 4.065559309207504e-05, "loss": 4.7218, "step": 5290 }, { "epoch": 0.2847072750753336, "grad_norm": 0.9016199111938477, "learning_rate": 4.065229793456377e-05, "loss": 4.8021, "step": 5291 }, { "epoch": 0.2847610848041326, "grad_norm": 1.7854732275009155, "learning_rate": 4.064900232975191e-05, "loss": 4.0765, "step": 5292 }, { "epoch": 0.2848148945329316, "grad_norm": 2.0929439067840576, "learning_rate": 4.064570627773365e-05, "loss": 4.3577, "step": 5293 }, { "epoch": 0.2848687042617305, "grad_norm": 1.674699068069458, "learning_rate": 4.06424097786032e-05, "loss": 4.2209, "step": 5294 }, { "epoch": 0.2849225139905295, "grad_norm": 1.6652493476867676, "learning_rate": 4.063911283245475e-05, "loss": 4.3056, "step": 5295 }, { "epoch": 0.28497632371932846, "grad_norm": 1.8251267671585083, "learning_rate": 4.063581543938252e-05, "loss": 4.2876, "step": 5296 }, { "epoch": 0.28503013344812744, "grad_norm": 1.3594996929168701, "learning_rate": 4.063251759948073e-05, "loss": 4.5265, "step": 5297 }, { "epoch": 0.28508394317692637, "grad_norm": 0.9612566828727722, "learning_rate": 4.062921931284365e-05, "loss": 4.4115, "step": 5298 }, { "epoch": 0.28513775290572535, "grad_norm": 1.6198233366012573, "learning_rate": 4.062592057956551e-05, "loss": 4.3799, "step": 5299 }, { "epoch": 0.28519156263452433, "grad_norm": 1.2502609491348267, "learning_rate": 4.062262139974059e-05, "loss": 4.6651, "step": 5300 }, { "epoch": 0.2852453723633233, "grad_norm": 1.7354265451431274, "learning_rate": 4.0619321773463165e-05, "loss": 4.2952, "step": 5301 }, { "epoch": 0.28529918209212224, "grad_norm": 1.1056352853775024, "learning_rate": 4.061602170082754e-05, "loss": 4.4308, "step": 5302 }, { "epoch": 0.2853529918209212, "grad_norm": 1.7758973836898804, "learning_rate": 4.0612721181928016e-05, "loss": 5.1238, "step": 5303 }, { "epoch": 0.2854068015497202, "grad_norm": 1.9201754331588745, "learning_rate": 4.060942021685892e-05, "loss": 4.4807, "step": 5304 }, { "epoch": 0.2854606112785192, "grad_norm": 2.1544625759124756, "learning_rate": 4.0606118805714565e-05, "loss": 4.5333, "step": 5305 }, { "epoch": 0.2855144210073181, "grad_norm": 1.7057193517684937, "learning_rate": 4.060281694858932e-05, "loss": 4.727, "step": 5306 }, { "epoch": 0.2855682307361171, "grad_norm": 1.9890280961990356, "learning_rate": 4.059951464557753e-05, "loss": 4.5619, "step": 5307 }, { "epoch": 0.28562204046491607, "grad_norm": 1.3508186340332031, "learning_rate": 4.0596211896773574e-05, "loss": 4.6473, "step": 5308 }, { "epoch": 0.285675850193715, "grad_norm": 1.5057547092437744, "learning_rate": 4.059290870227182e-05, "loss": 4.7998, "step": 5309 }, { "epoch": 0.285729659922514, "grad_norm": 2.8628854751586914, "learning_rate": 4.058960506216669e-05, "loss": 3.8063, "step": 5310 }, { "epoch": 0.28578346965131296, "grad_norm": 1.3699495792388916, "learning_rate": 4.0586300976552574e-05, "loss": 4.6223, "step": 5311 }, { "epoch": 0.28583727938011194, "grad_norm": 1.805445909500122, "learning_rate": 4.058299644552389e-05, "loss": 4.5623, "step": 5312 }, { "epoch": 0.28589108910891087, "grad_norm": 1.2662583589553833, "learning_rate": 4.057969146917508e-05, "loss": 4.4834, "step": 5313 }, { "epoch": 0.28594489883770985, "grad_norm": 2.1636438369750977, "learning_rate": 4.0576386047600604e-05, "loss": 4.2853, "step": 5314 }, { "epoch": 0.28599870856650883, "grad_norm": 1.0228906869888306, "learning_rate": 4.057308018089491e-05, "loss": 4.9335, "step": 5315 }, { "epoch": 0.2860525182953078, "grad_norm": 2.172557830810547, "learning_rate": 4.056977386915246e-05, "loss": 4.1691, "step": 5316 }, { "epoch": 0.28610632802410674, "grad_norm": 1.086806058883667, "learning_rate": 4.0566467112467756e-05, "loss": 4.2049, "step": 5317 }, { "epoch": 0.2861601377529057, "grad_norm": 1.9456833600997925, "learning_rate": 4.05631599109353e-05, "loss": 4.6741, "step": 5318 }, { "epoch": 0.2862139474817047, "grad_norm": 1.155276894569397, "learning_rate": 4.0559852264649576e-05, "loss": 4.7895, "step": 5319 }, { "epoch": 0.2862677572105037, "grad_norm": 1.4886358976364136, "learning_rate": 4.055654417370514e-05, "loss": 4.7759, "step": 5320 }, { "epoch": 0.2863215669393026, "grad_norm": 1.691097617149353, "learning_rate": 4.0553235638196506e-05, "loss": 4.7357, "step": 5321 }, { "epoch": 0.2863753766681016, "grad_norm": 1.3343002796173096, "learning_rate": 4.054992665821823e-05, "loss": 4.6081, "step": 5322 }, { "epoch": 0.28642918639690057, "grad_norm": 2.231884002685547, "learning_rate": 4.0546617233864884e-05, "loss": 4.2521, "step": 5323 }, { "epoch": 0.28648299612569955, "grad_norm": 2.2498764991760254, "learning_rate": 4.054330736523102e-05, "loss": 4.6443, "step": 5324 }, { "epoch": 0.2865368058544985, "grad_norm": 1.9592498540878296, "learning_rate": 4.053999705241125e-05, "loss": 4.8867, "step": 5325 }, { "epoch": 0.28659061558329746, "grad_norm": 1.8533464670181274, "learning_rate": 4.053668629550015e-05, "loss": 4.8761, "step": 5326 }, { "epoch": 0.28664442531209644, "grad_norm": 1.7185543775558472, "learning_rate": 4.053337509459235e-05, "loss": 4.433, "step": 5327 }, { "epoch": 0.28669823504089537, "grad_norm": 1.1269416809082031, "learning_rate": 4.0530063449782476e-05, "loss": 4.6224, "step": 5328 }, { "epoch": 0.28675204476969435, "grad_norm": 1.2093408107757568, "learning_rate": 4.052675136116515e-05, "loss": 4.4938, "step": 5329 }, { "epoch": 0.28680585449849333, "grad_norm": 1.5462937355041504, "learning_rate": 4.052343882883504e-05, "loss": 4.6086, "step": 5330 }, { "epoch": 0.2868596642272923, "grad_norm": 1.586302638053894, "learning_rate": 4.052012585288679e-05, "loss": 4.2562, "step": 5331 }, { "epoch": 0.28691347395609124, "grad_norm": 2.175891876220703, "learning_rate": 4.0516812433415095e-05, "loss": 4.2509, "step": 5332 }, { "epoch": 0.2869672836848902, "grad_norm": 1.4953596591949463, "learning_rate": 4.051349857051464e-05, "loss": 4.4856, "step": 5333 }, { "epoch": 0.2870210934136892, "grad_norm": 1.399535059928894, "learning_rate": 4.051018426428012e-05, "loss": 4.6528, "step": 5334 }, { "epoch": 0.2870749031424882, "grad_norm": 1.8708090782165527, "learning_rate": 4.050686951480625e-05, "loss": 4.8047, "step": 5335 }, { "epoch": 0.2871287128712871, "grad_norm": 1.5660744905471802, "learning_rate": 4.0503554322187756e-05, "loss": 4.7938, "step": 5336 }, { "epoch": 0.2871825226000861, "grad_norm": 1.7244279384613037, "learning_rate": 4.050023868651938e-05, "loss": 4.7502, "step": 5337 }, { "epoch": 0.28723633232888507, "grad_norm": 1.6950141191482544, "learning_rate": 4.049692260789587e-05, "loss": 4.639, "step": 5338 }, { "epoch": 0.28729014205768405, "grad_norm": 1.1509212255477905, "learning_rate": 4.049360608641201e-05, "loss": 4.5312, "step": 5339 }, { "epoch": 0.287343951786483, "grad_norm": 1.5518782138824463, "learning_rate": 4.049028912216254e-05, "loss": 4.5128, "step": 5340 }, { "epoch": 0.28739776151528196, "grad_norm": 1.8030729293823242, "learning_rate": 4.0486971715242286e-05, "loss": 4.6035, "step": 5341 }, { "epoch": 0.28745157124408094, "grad_norm": 2.7594077587127686, "learning_rate": 4.048365386574602e-05, "loss": 3.9123, "step": 5342 }, { "epoch": 0.2875053809728799, "grad_norm": 2.1799874305725098, "learning_rate": 4.048033557376858e-05, "loss": 4.1431, "step": 5343 }, { "epoch": 0.28755919070167885, "grad_norm": 1.2839393615722656, "learning_rate": 4.047701683940479e-05, "loss": 4.7561, "step": 5344 }, { "epoch": 0.2876130004304778, "grad_norm": 1.9613772630691528, "learning_rate": 4.047369766274949e-05, "loss": 4.7283, "step": 5345 }, { "epoch": 0.2876668101592768, "grad_norm": 1.2022044658660889, "learning_rate": 4.0470378043897514e-05, "loss": 4.8473, "step": 5346 }, { "epoch": 0.2877206198880758, "grad_norm": 2.057061195373535, "learning_rate": 4.0467057982943754e-05, "loss": 3.9942, "step": 5347 }, { "epoch": 0.2877744296168747, "grad_norm": 1.6462851762771606, "learning_rate": 4.046373747998308e-05, "loss": 4.342, "step": 5348 }, { "epoch": 0.2878282393456737, "grad_norm": 1.5118119716644287, "learning_rate": 4.046041653511039e-05, "loss": 4.6637, "step": 5349 }, { "epoch": 0.2878820490744727, "grad_norm": 2.078350782394409, "learning_rate": 4.0457095148420564e-05, "loss": 4.2553, "step": 5350 }, { "epoch": 0.2879358588032716, "grad_norm": 1.3978687524795532, "learning_rate": 4.0453773320008534e-05, "loss": 4.8045, "step": 5351 }, { "epoch": 0.2879896685320706, "grad_norm": 1.7639566659927368, "learning_rate": 4.045045104996924e-05, "loss": 4.4729, "step": 5352 }, { "epoch": 0.28804347826086957, "grad_norm": 1.4218509197235107, "learning_rate": 4.04471283383976e-05, "loss": 4.4343, "step": 5353 }, { "epoch": 0.28809728798966855, "grad_norm": 2.257511854171753, "learning_rate": 4.044380518538859e-05, "loss": 3.9859, "step": 5354 }, { "epoch": 0.2881510977184675, "grad_norm": 1.593963623046875, "learning_rate": 4.044048159103716e-05, "loss": 4.4895, "step": 5355 }, { "epoch": 0.28820490744726646, "grad_norm": 1.7298897504806519, "learning_rate": 4.04371575554383e-05, "loss": 4.534, "step": 5356 }, { "epoch": 0.28825871717606544, "grad_norm": 0.9782199859619141, "learning_rate": 4.0433833078687e-05, "loss": 4.744, "step": 5357 }, { "epoch": 0.2883125269048644, "grad_norm": 1.6336956024169922, "learning_rate": 4.0430508160878256e-05, "loss": 4.6723, "step": 5358 }, { "epoch": 0.28836633663366334, "grad_norm": 2.4659860134124756, "learning_rate": 4.042718280210709e-05, "loss": 4.1663, "step": 5359 }, { "epoch": 0.2884201463624623, "grad_norm": 1.12699556350708, "learning_rate": 4.0423857002468545e-05, "loss": 4.7806, "step": 5360 }, { "epoch": 0.2884739560912613, "grad_norm": 2.022355079650879, "learning_rate": 4.042053076205764e-05, "loss": 4.3537, "step": 5361 }, { "epoch": 0.2885277658200603, "grad_norm": 2.0108230113983154, "learning_rate": 4.041720408096945e-05, "loss": 4.5244, "step": 5362 }, { "epoch": 0.2885815755488592, "grad_norm": 2.0611348152160645, "learning_rate": 4.041387695929903e-05, "loss": 4.2519, "step": 5363 }, { "epoch": 0.2886353852776582, "grad_norm": 1.7776366472244263, "learning_rate": 4.041054939714147e-05, "loss": 4.4144, "step": 5364 }, { "epoch": 0.2886891950064572, "grad_norm": 1.4342082738876343, "learning_rate": 4.0407221394591856e-05, "loss": 4.6192, "step": 5365 }, { "epoch": 0.28874300473525616, "grad_norm": 2.1222033500671387, "learning_rate": 4.0403892951745294e-05, "loss": 4.4366, "step": 5366 }, { "epoch": 0.2887968144640551, "grad_norm": 1.2181293964385986, "learning_rate": 4.04005640686969e-05, "loss": 4.5536, "step": 5367 }, { "epoch": 0.28885062419285407, "grad_norm": 2.0219364166259766, "learning_rate": 4.039723474554181e-05, "loss": 4.3413, "step": 5368 }, { "epoch": 0.28890443392165305, "grad_norm": 2.5159835815429688, "learning_rate": 4.039390498237517e-05, "loss": 4.1861, "step": 5369 }, { "epoch": 0.28895824365045203, "grad_norm": 2.0648224353790283, "learning_rate": 4.0390574779292126e-05, "loss": 4.3418, "step": 5370 }, { "epoch": 0.28901205337925095, "grad_norm": 1.1048122644424438, "learning_rate": 4.038724413638785e-05, "loss": 4.5798, "step": 5371 }, { "epoch": 0.28906586310804994, "grad_norm": 1.779640555381775, "learning_rate": 4.038391305375753e-05, "loss": 4.7083, "step": 5372 }, { "epoch": 0.2891196728368489, "grad_norm": 2.0195062160491943, "learning_rate": 4.038058153149634e-05, "loss": 4.437, "step": 5373 }, { "epoch": 0.28917348256564784, "grad_norm": 1.6717724800109863, "learning_rate": 4.0377249569699504e-05, "loss": 4.2144, "step": 5374 }, { "epoch": 0.2892272922944468, "grad_norm": 1.4718283414840698, "learning_rate": 4.037391716846224e-05, "loss": 4.3111, "step": 5375 }, { "epoch": 0.2892811020232458, "grad_norm": 1.7991061210632324, "learning_rate": 4.0370584327879765e-05, "loss": 4.7842, "step": 5376 }, { "epoch": 0.2893349117520448, "grad_norm": 1.6085386276245117, "learning_rate": 4.036725104804734e-05, "loss": 4.4175, "step": 5377 }, { "epoch": 0.2893887214808437, "grad_norm": 2.192575216293335, "learning_rate": 4.036391732906021e-05, "loss": 4.395, "step": 5378 }, { "epoch": 0.2894425312096427, "grad_norm": 1.7165955305099487, "learning_rate": 4.0360583171013656e-05, "loss": 4.5917, "step": 5379 }, { "epoch": 0.2894963409384417, "grad_norm": 1.2978112697601318, "learning_rate": 4.0357248574002934e-05, "loss": 4.6936, "step": 5380 }, { "epoch": 0.28955015066724066, "grad_norm": 1.7021753787994385, "learning_rate": 4.035391353812337e-05, "loss": 4.9888, "step": 5381 }, { "epoch": 0.2896039603960396, "grad_norm": 1.9922207593917847, "learning_rate": 4.035057806347024e-05, "loss": 4.4367, "step": 5382 }, { "epoch": 0.28965777012483857, "grad_norm": 1.8335925340652466, "learning_rate": 4.034724215013889e-05, "loss": 4.5703, "step": 5383 }, { "epoch": 0.28971157985363755, "grad_norm": 1.704948902130127, "learning_rate": 4.034390579822463e-05, "loss": 4.6636, "step": 5384 }, { "epoch": 0.28976538958243653, "grad_norm": 1.2854268550872803, "learning_rate": 4.034056900782282e-05, "loss": 4.1255, "step": 5385 }, { "epoch": 0.28981919931123545, "grad_norm": 1.503829002380371, "learning_rate": 4.0337231779028794e-05, "loss": 4.6906, "step": 5386 }, { "epoch": 0.28987300904003444, "grad_norm": 2.33198618888855, "learning_rate": 4.0333894111937946e-05, "loss": 3.9827, "step": 5387 }, { "epoch": 0.2899268187688334, "grad_norm": 1.3263676166534424, "learning_rate": 4.033055600664565e-05, "loss": 4.7221, "step": 5388 }, { "epoch": 0.2899806284976324, "grad_norm": 2.3383731842041016, "learning_rate": 4.032721746324729e-05, "loss": 4.4511, "step": 5389 }, { "epoch": 0.2900344382264313, "grad_norm": 1.4433186054229736, "learning_rate": 4.0323878481838285e-05, "loss": 4.6695, "step": 5390 }, { "epoch": 0.2900882479552303, "grad_norm": 1.8066679239273071, "learning_rate": 4.032053906251405e-05, "loss": 4.2179, "step": 5391 }, { "epoch": 0.2901420576840293, "grad_norm": 2.7375850677490234, "learning_rate": 4.0317199205370014e-05, "loss": 3.7635, "step": 5392 }, { "epoch": 0.2901958674128282, "grad_norm": 1.0771912336349487, "learning_rate": 4.0313858910501626e-05, "loss": 4.423, "step": 5393 }, { "epoch": 0.2902496771416272, "grad_norm": 1.3192682266235352, "learning_rate": 4.031051817800434e-05, "loss": 4.1948, "step": 5394 }, { "epoch": 0.2903034868704262, "grad_norm": 2.56589412689209, "learning_rate": 4.0307177007973626e-05, "loss": 4.1253, "step": 5395 }, { "epoch": 0.29035729659922516, "grad_norm": 1.3785245418548584, "learning_rate": 4.030383540050496e-05, "loss": 4.4016, "step": 5396 }, { "epoch": 0.2904111063280241, "grad_norm": 2.1302289962768555, "learning_rate": 4.0300493355693847e-05, "loss": 4.7507, "step": 5397 }, { "epoch": 0.29046491605682306, "grad_norm": 1.8291505575180054, "learning_rate": 4.029715087363578e-05, "loss": 4.727, "step": 5398 }, { "epoch": 0.29051872578562205, "grad_norm": 2.454951763153076, "learning_rate": 4.0293807954426286e-05, "loss": 4.0239, "step": 5399 }, { "epoch": 0.290572535514421, "grad_norm": 1.180015206336975, "learning_rate": 4.02904645981609e-05, "loss": 4.4872, "step": 5400 }, { "epoch": 0.29062634524321995, "grad_norm": 1.491248369216919, "learning_rate": 4.028712080493516e-05, "loss": 4.654, "step": 5401 }, { "epoch": 0.29068015497201893, "grad_norm": 1.6501749753952026, "learning_rate": 4.028377657484463e-05, "loss": 4.7744, "step": 5402 }, { "epoch": 0.2907339647008179, "grad_norm": 1.3335644006729126, "learning_rate": 4.0280431907984875e-05, "loss": 4.9138, "step": 5403 }, { "epoch": 0.2907877744296169, "grad_norm": 1.1773173809051514, "learning_rate": 4.0277086804451465e-05, "loss": 4.5727, "step": 5404 }, { "epoch": 0.2908415841584158, "grad_norm": 2.446552276611328, "learning_rate": 4.027374126434001e-05, "loss": 3.8864, "step": 5405 }, { "epoch": 0.2908953938872148, "grad_norm": 2.262115955352783, "learning_rate": 4.027039528774611e-05, "loss": 4.2927, "step": 5406 }, { "epoch": 0.2909492036160138, "grad_norm": 1.376939058303833, "learning_rate": 4.026704887476539e-05, "loss": 4.4729, "step": 5407 }, { "epoch": 0.29100301334481277, "grad_norm": 2.3229711055755615, "learning_rate": 4.0263702025493473e-05, "loss": 3.8361, "step": 5408 }, { "epoch": 0.2910568230736117, "grad_norm": 1.8083653450012207, "learning_rate": 4.0260354740026e-05, "loss": 4.6688, "step": 5409 }, { "epoch": 0.2911106328024107, "grad_norm": 1.326298475265503, "learning_rate": 4.025700701845865e-05, "loss": 4.3727, "step": 5410 }, { "epoch": 0.29116444253120966, "grad_norm": 1.414492130279541, "learning_rate": 4.025365886088707e-05, "loss": 4.5751, "step": 5411 }, { "epoch": 0.29121825226000864, "grad_norm": 1.7015925645828247, "learning_rate": 4.0250310267406937e-05, "loss": 4.7304, "step": 5412 }, { "epoch": 0.29127206198880756, "grad_norm": 2.482001543045044, "learning_rate": 4.024696123811396e-05, "loss": 4.5923, "step": 5413 }, { "epoch": 0.29132587171760654, "grad_norm": 1.2625559568405151, "learning_rate": 4.024361177310384e-05, "loss": 4.6788, "step": 5414 }, { "epoch": 0.2913796814464055, "grad_norm": 2.0406899452209473, "learning_rate": 4.024026187247231e-05, "loss": 4.532, "step": 5415 }, { "epoch": 0.29143349117520445, "grad_norm": 1.1981630325317383, "learning_rate": 4.023691153631507e-05, "loss": 5.1127, "step": 5416 }, { "epoch": 0.29148730090400343, "grad_norm": 1.2973151206970215, "learning_rate": 4.023356076472789e-05, "loss": 4.8651, "step": 5417 }, { "epoch": 0.2915411106328024, "grad_norm": 2.2372498512268066, "learning_rate": 4.023020955780651e-05, "loss": 4.1694, "step": 5418 }, { "epoch": 0.2915949203616014, "grad_norm": 2.2358903884887695, "learning_rate": 4.022685791564671e-05, "loss": 4.3512, "step": 5419 }, { "epoch": 0.2916487300904003, "grad_norm": 2.3439362049102783, "learning_rate": 4.0223505838344265e-05, "loss": 4.0555, "step": 5420 }, { "epoch": 0.2917025398191993, "grad_norm": 1.7983967065811157, "learning_rate": 4.022015332599497e-05, "loss": 4.2159, "step": 5421 }, { "epoch": 0.2917563495479983, "grad_norm": 2.6859517097473145, "learning_rate": 4.021680037869463e-05, "loss": 3.7378, "step": 5422 }, { "epoch": 0.29181015927679727, "grad_norm": 1.3619953393936157, "learning_rate": 4.021344699653906e-05, "loss": 4.8253, "step": 5423 }, { "epoch": 0.2918639690055962, "grad_norm": 1.449432134628296, "learning_rate": 4.0210093179624094e-05, "loss": 4.5337, "step": 5424 }, { "epoch": 0.2919177787343952, "grad_norm": 1.5977282524108887, "learning_rate": 4.0206738928045584e-05, "loss": 4.5459, "step": 5425 }, { "epoch": 0.29197158846319415, "grad_norm": 2.2572340965270996, "learning_rate": 4.020338424189938e-05, "loss": 4.1105, "step": 5426 }, { "epoch": 0.29202539819199314, "grad_norm": 1.7713181972503662, "learning_rate": 4.020002912128133e-05, "loss": 4.4391, "step": 5427 }, { "epoch": 0.29207920792079206, "grad_norm": 1.9950437545776367, "learning_rate": 4.019667356628734e-05, "loss": 4.3722, "step": 5428 }, { "epoch": 0.29213301764959104, "grad_norm": 1.3407313823699951, "learning_rate": 4.01933175770133e-05, "loss": 4.6945, "step": 5429 }, { "epoch": 0.29218682737839, "grad_norm": 1.6194974184036255, "learning_rate": 4.01899611535551e-05, "loss": 4.583, "step": 5430 }, { "epoch": 0.292240637107189, "grad_norm": 3.3445980548858643, "learning_rate": 4.018660429600867e-05, "loss": 4.1802, "step": 5431 }, { "epoch": 0.29229444683598793, "grad_norm": 1.3735144138336182, "learning_rate": 4.018324700446993e-05, "loss": 4.669, "step": 5432 }, { "epoch": 0.2923482565647869, "grad_norm": 1.7708300352096558, "learning_rate": 4.017988927903483e-05, "loss": 4.7227, "step": 5433 }, { "epoch": 0.2924020662935859, "grad_norm": 1.5094473361968994, "learning_rate": 4.0176531119799335e-05, "loss": 4.6869, "step": 5434 }, { "epoch": 0.2924558760223848, "grad_norm": 2.3424794673919678, "learning_rate": 4.0173172526859386e-05, "loss": 3.6783, "step": 5435 }, { "epoch": 0.2925096857511838, "grad_norm": 1.7269880771636963, "learning_rate": 4.0169813500310986e-05, "loss": 4.4191, "step": 5436 }, { "epoch": 0.2925634954799828, "grad_norm": 1.4930418729782104, "learning_rate": 4.0166454040250114e-05, "loss": 4.8036, "step": 5437 }, { "epoch": 0.29261730520878176, "grad_norm": 1.2583895921707153, "learning_rate": 4.0163094146772784e-05, "loss": 4.669, "step": 5438 }, { "epoch": 0.2926711149375807, "grad_norm": 1.5167654752731323, "learning_rate": 4.0159733819975e-05, "loss": 4.5983, "step": 5439 }, { "epoch": 0.29272492466637967, "grad_norm": 2.271125316619873, "learning_rate": 4.015637305995281e-05, "loss": 4.181, "step": 5440 }, { "epoch": 0.29277873439517865, "grad_norm": 1.7003909349441528, "learning_rate": 4.015301186680223e-05, "loss": 4.6245, "step": 5441 }, { "epoch": 0.29283254412397763, "grad_norm": 0.8699198961257935, "learning_rate": 4.0149650240619335e-05, "loss": 4.471, "step": 5442 }, { "epoch": 0.29288635385277656, "grad_norm": 1.7061713933944702, "learning_rate": 4.014628818150018e-05, "loss": 4.658, "step": 5443 }, { "epoch": 0.29294016358157554, "grad_norm": 1.6496498584747314, "learning_rate": 4.014292568954086e-05, "loss": 4.8035, "step": 5444 }, { "epoch": 0.2929939733103745, "grad_norm": 2.033588409423828, "learning_rate": 4.013956276483743e-05, "loss": 4.3698, "step": 5445 }, { "epoch": 0.2930477830391735, "grad_norm": 1.3980371952056885, "learning_rate": 4.013619940748604e-05, "loss": 4.4975, "step": 5446 }, { "epoch": 0.29310159276797243, "grad_norm": 1.4113229513168335, "learning_rate": 4.0132835617582766e-05, "loss": 4.4793, "step": 5447 }, { "epoch": 0.2931554024967714, "grad_norm": 2.6090056896209717, "learning_rate": 4.012947139522376e-05, "loss": 3.8172, "step": 5448 }, { "epoch": 0.2932092122255704, "grad_norm": 1.7241367101669312, "learning_rate": 4.0126106740505156e-05, "loss": 4.4197, "step": 5449 }, { "epoch": 0.2932630219543694, "grad_norm": 2.272998571395874, "learning_rate": 4.012274165352311e-05, "loss": 4.3781, "step": 5450 }, { "epoch": 0.2933168316831683, "grad_norm": 1.6882919073104858, "learning_rate": 4.011937613437377e-05, "loss": 4.6578, "step": 5451 }, { "epoch": 0.2933706414119673, "grad_norm": 1.845701813697815, "learning_rate": 4.011601018315334e-05, "loss": 5.0343, "step": 5452 }, { "epoch": 0.29342445114076626, "grad_norm": 1.7154508829116821, "learning_rate": 4.0112643799957984e-05, "loss": 4.5561, "step": 5453 }, { "epoch": 0.29347826086956524, "grad_norm": 1.8212686777114868, "learning_rate": 4.010927698488393e-05, "loss": 4.2929, "step": 5454 }, { "epoch": 0.29353207059836417, "grad_norm": 2.2831053733825684, "learning_rate": 4.0105909738027365e-05, "loss": 4.6904, "step": 5455 }, { "epoch": 0.29358588032716315, "grad_norm": 2.0051615238189697, "learning_rate": 4.010254205948454e-05, "loss": 4.7287, "step": 5456 }, { "epoch": 0.29363969005596213, "grad_norm": 1.2693246603012085, "learning_rate": 4.009917394935168e-05, "loss": 4.8369, "step": 5457 }, { "epoch": 0.29369349978476106, "grad_norm": 1.3456530570983887, "learning_rate": 4.009580540772504e-05, "loss": 4.5574, "step": 5458 }, { "epoch": 0.29374730951356004, "grad_norm": 1.3394765853881836, "learning_rate": 4.009243643470089e-05, "loss": 4.4162, "step": 5459 }, { "epoch": 0.293801119242359, "grad_norm": 1.839892029762268, "learning_rate": 4.0089067030375494e-05, "loss": 4.411, "step": 5460 }, { "epoch": 0.293854928971158, "grad_norm": 2.8187763690948486, "learning_rate": 4.008569719484514e-05, "loss": 4.2835, "step": 5461 }, { "epoch": 0.29390873869995693, "grad_norm": 1.9932950735092163, "learning_rate": 4.0082326928206146e-05, "loss": 4.5336, "step": 5462 }, { "epoch": 0.2939625484287559, "grad_norm": 1.3461809158325195, "learning_rate": 4.007895623055482e-05, "loss": 4.356, "step": 5463 }, { "epoch": 0.2940163581575549, "grad_norm": 0.9138823747634888, "learning_rate": 4.007558510198747e-05, "loss": 4.6024, "step": 5464 }, { "epoch": 0.2940701678863539, "grad_norm": 1.7321484088897705, "learning_rate": 4.007221354260046e-05, "loss": 4.5253, "step": 5465 }, { "epoch": 0.2941239776151528, "grad_norm": 0.977817177772522, "learning_rate": 4.006884155249011e-05, "loss": 4.5852, "step": 5466 }, { "epoch": 0.2941777873439518, "grad_norm": 0.9302509427070618, "learning_rate": 4.006546913175281e-05, "loss": 4.5156, "step": 5467 }, { "epoch": 0.29423159707275076, "grad_norm": 1.3396565914154053, "learning_rate": 4.0062096280484924e-05, "loss": 3.9827, "step": 5468 }, { "epoch": 0.29428540680154974, "grad_norm": 1.4636696577072144, "learning_rate": 4.005872299878284e-05, "loss": 4.5022, "step": 5469 }, { "epoch": 0.29433921653034867, "grad_norm": 1.2294893264770508, "learning_rate": 4.005534928674295e-05, "loss": 4.7342, "step": 5470 }, { "epoch": 0.29439302625914765, "grad_norm": 1.8638352155685425, "learning_rate": 4.005197514446167e-05, "loss": 4.7138, "step": 5471 }, { "epoch": 0.29444683598794663, "grad_norm": 1.7393018007278442, "learning_rate": 4.0048600572035435e-05, "loss": 4.6504, "step": 5472 }, { "epoch": 0.2945006457167456, "grad_norm": 1.2050973176956177, "learning_rate": 4.0045225569560664e-05, "loss": 4.7451, "step": 5473 }, { "epoch": 0.29455445544554454, "grad_norm": 2.4682724475860596, "learning_rate": 4.0041850137133804e-05, "loss": 4.1265, "step": 5474 }, { "epoch": 0.2946082651743435, "grad_norm": 2.6951260566711426, "learning_rate": 4.0038474274851344e-05, "loss": 4.64, "step": 5475 }, { "epoch": 0.2946620749031425, "grad_norm": 1.1786426305770874, "learning_rate": 4.0035097982809724e-05, "loss": 4.6775, "step": 5476 }, { "epoch": 0.2947158846319415, "grad_norm": 1.8099122047424316, "learning_rate": 4.003172126110545e-05, "loss": 4.429, "step": 5477 }, { "epoch": 0.2947696943607404, "grad_norm": 1.9659098386764526, "learning_rate": 4.002834410983501e-05, "loss": 4.3328, "step": 5478 }, { "epoch": 0.2948235040895394, "grad_norm": 1.553015947341919, "learning_rate": 4.002496652909493e-05, "loss": 4.7887, "step": 5479 }, { "epoch": 0.29487731381833837, "grad_norm": 1.7374986410140991, "learning_rate": 4.00215885189817e-05, "loss": 4.5177, "step": 5480 }, { "epoch": 0.2949311235471373, "grad_norm": 1.4041748046875, "learning_rate": 4.001821007959188e-05, "loss": 4.7681, "step": 5481 }, { "epoch": 0.2949849332759363, "grad_norm": 2.0228841304779053, "learning_rate": 4.0014831211022016e-05, "loss": 4.4563, "step": 5482 }, { "epoch": 0.29503874300473526, "grad_norm": 2.2038888931274414, "learning_rate": 4.001145191336866e-05, "loss": 4.3114, "step": 5483 }, { "epoch": 0.29509255273353424, "grad_norm": 1.4900985956192017, "learning_rate": 4.000807218672838e-05, "loss": 4.678, "step": 5484 }, { "epoch": 0.29514636246233317, "grad_norm": 1.9240206480026245, "learning_rate": 4.000469203119775e-05, "loss": 4.5212, "step": 5485 }, { "epoch": 0.29520017219113215, "grad_norm": 1.986048698425293, "learning_rate": 4.00013114468734e-05, "loss": 4.2122, "step": 5486 }, { "epoch": 0.29525398191993113, "grad_norm": 1.4155054092407227, "learning_rate": 3.9997930433851916e-05, "loss": 4.6507, "step": 5487 }, { "epoch": 0.2953077916487301, "grad_norm": 2.2917680740356445, "learning_rate": 3.999454899222992e-05, "loss": 4.5868, "step": 5488 }, { "epoch": 0.29536160137752904, "grad_norm": 1.6014090776443481, "learning_rate": 3.9991167122104035e-05, "loss": 4.2958, "step": 5489 }, { "epoch": 0.295415411106328, "grad_norm": 2.2862653732299805, "learning_rate": 3.998778482357092e-05, "loss": 4.5748, "step": 5490 }, { "epoch": 0.295469220835127, "grad_norm": 2.0467400550842285, "learning_rate": 3.998440209672723e-05, "loss": 4.1622, "step": 5491 }, { "epoch": 0.295523030563926, "grad_norm": 1.5890508890151978, "learning_rate": 3.9981018941669626e-05, "loss": 4.5267, "step": 5492 }, { "epoch": 0.2955768402927249, "grad_norm": 1.2606744766235352, "learning_rate": 3.99776353584948e-05, "loss": 4.5025, "step": 5493 }, { "epoch": 0.2956306500215239, "grad_norm": 2.250544309616089, "learning_rate": 3.997425134729944e-05, "loss": 4.3805, "step": 5494 }, { "epoch": 0.29568445975032287, "grad_norm": 2.2998483180999756, "learning_rate": 3.997086690818025e-05, "loss": 3.9921, "step": 5495 }, { "epoch": 0.29573826947912185, "grad_norm": 1.0421717166900635, "learning_rate": 3.996748204123395e-05, "loss": 4.4157, "step": 5496 }, { "epoch": 0.2957920792079208, "grad_norm": 2.831751585006714, "learning_rate": 3.996409674655727e-05, "loss": 4.329, "step": 5497 }, { "epoch": 0.29584588893671976, "grad_norm": 1.5181667804718018, "learning_rate": 3.9960711024246964e-05, "loss": 4.82, "step": 5498 }, { "epoch": 0.29589969866551874, "grad_norm": 1.1081544160842896, "learning_rate": 3.995732487439976e-05, "loss": 4.3389, "step": 5499 }, { "epoch": 0.29595350839431767, "grad_norm": 1.3551262617111206, "learning_rate": 3.995393829711246e-05, "loss": 4.7135, "step": 5500 }, { "epoch": 0.29600731812311665, "grad_norm": 0.9861265420913696, "learning_rate": 3.9950551292481814e-05, "loss": 4.5427, "step": 5501 }, { "epoch": 0.29606112785191563, "grad_norm": 2.4788360595703125, "learning_rate": 3.994716386060462e-05, "loss": 4.1296, "step": 5502 }, { "epoch": 0.2961149375807146, "grad_norm": 1.6988646984100342, "learning_rate": 3.9943776001577693e-05, "loss": 4.2599, "step": 5503 }, { "epoch": 0.29616874730951354, "grad_norm": 1.3618718385696411, "learning_rate": 3.994038771549784e-05, "loss": 4.8342, "step": 5504 }, { "epoch": 0.2962225570383125, "grad_norm": 2.4517853260040283, "learning_rate": 3.9936999002461896e-05, "loss": 4.2399, "step": 5505 }, { "epoch": 0.2962763667671115, "grad_norm": 1.6991076469421387, "learning_rate": 3.993360986256669e-05, "loss": 4.3391, "step": 5506 }, { "epoch": 0.2963301764959105, "grad_norm": 2.2222635746002197, "learning_rate": 3.9930220295909084e-05, "loss": 4.4795, "step": 5507 }, { "epoch": 0.2963839862247094, "grad_norm": 1.3367267847061157, "learning_rate": 3.992683030258594e-05, "loss": 4.9031, "step": 5508 }, { "epoch": 0.2964377959535084, "grad_norm": 1.4021517038345337, "learning_rate": 3.992343988269412e-05, "loss": 4.3156, "step": 5509 }, { "epoch": 0.29649160568230737, "grad_norm": 1.8287900686264038, "learning_rate": 3.992004903633055e-05, "loss": 4.2965, "step": 5510 }, { "epoch": 0.29654541541110635, "grad_norm": 1.3239762783050537, "learning_rate": 3.991665776359209e-05, "loss": 4.2733, "step": 5511 }, { "epoch": 0.2965992251399053, "grad_norm": 2.212369918823242, "learning_rate": 3.991326606457568e-05, "loss": 4.2524, "step": 5512 }, { "epoch": 0.29665303486870426, "grad_norm": 1.834359049797058, "learning_rate": 3.990987393937824e-05, "loss": 4.4401, "step": 5513 }, { "epoch": 0.29670684459750324, "grad_norm": 1.8175921440124512, "learning_rate": 3.990648138809671e-05, "loss": 4.4533, "step": 5514 }, { "epoch": 0.2967606543263022, "grad_norm": 1.8403563499450684, "learning_rate": 3.990308841082803e-05, "loss": 4.0524, "step": 5515 }, { "epoch": 0.29681446405510115, "grad_norm": 0.9273127913475037, "learning_rate": 3.989969500766917e-05, "loss": 4.5346, "step": 5516 }, { "epoch": 0.2968682737839001, "grad_norm": 1.9903512001037598, "learning_rate": 3.9896301178717097e-05, "loss": 4.5885, "step": 5517 }, { "epoch": 0.2969220835126991, "grad_norm": 1.8121343851089478, "learning_rate": 3.989290692406881e-05, "loss": 4.9692, "step": 5518 }, { "epoch": 0.2969758932414981, "grad_norm": 2.242936611175537, "learning_rate": 3.988951224382129e-05, "loss": 4.1293, "step": 5519 }, { "epoch": 0.297029702970297, "grad_norm": 1.825955867767334, "learning_rate": 3.9886117138071565e-05, "loss": 4.758, "step": 5520 }, { "epoch": 0.297083512699096, "grad_norm": 1.9362021684646606, "learning_rate": 3.988272160691665e-05, "loss": 4.9415, "step": 5521 }, { "epoch": 0.297137322427895, "grad_norm": 2.0037853717803955, "learning_rate": 3.987932565045358e-05, "loss": 4.7957, "step": 5522 }, { "epoch": 0.2971911321566939, "grad_norm": 1.642937421798706, "learning_rate": 3.987592926877941e-05, "loss": 4.5676, "step": 5523 }, { "epoch": 0.2972449418854929, "grad_norm": 2.6780688762664795, "learning_rate": 3.987253246199119e-05, "loss": 3.9947, "step": 5524 }, { "epoch": 0.29729875161429187, "grad_norm": 1.11287522315979, "learning_rate": 3.9869135230186e-05, "loss": 4.6041, "step": 5525 }, { "epoch": 0.29735256134309085, "grad_norm": 2.0351450443267822, "learning_rate": 3.9865737573460904e-05, "loss": 4.6599, "step": 5526 }, { "epoch": 0.2974063710718898, "grad_norm": 1.758073091506958, "learning_rate": 3.9862339491913015e-05, "loss": 4.3261, "step": 5527 }, { "epoch": 0.29746018080068876, "grad_norm": 2.0109810829162598, "learning_rate": 3.985894098563945e-05, "loss": 4.5185, "step": 5528 }, { "epoch": 0.29751399052948774, "grad_norm": 0.9703384637832642, "learning_rate": 3.98555420547373e-05, "loss": 4.6584, "step": 5529 }, { "epoch": 0.2975678002582867, "grad_norm": 1.1765023469924927, "learning_rate": 3.985214269930373e-05, "loss": 4.6187, "step": 5530 }, { "epoch": 0.29762160998708564, "grad_norm": 1.8452720642089844, "learning_rate": 3.9848742919435865e-05, "loss": 4.1579, "step": 5531 }, { "epoch": 0.2976754197158846, "grad_norm": 1.0490843057632446, "learning_rate": 3.984534271523087e-05, "loss": 4.8013, "step": 5532 }, { "epoch": 0.2977292294446836, "grad_norm": 1.3234386444091797, "learning_rate": 3.98419420867859e-05, "loss": 4.3655, "step": 5533 }, { "epoch": 0.2977830391734826, "grad_norm": 1.7314504384994507, "learning_rate": 3.983854103419815e-05, "loss": 4.2046, "step": 5534 }, { "epoch": 0.2978368489022815, "grad_norm": 1.3193646669387817, "learning_rate": 3.983513955756481e-05, "loss": 5.0198, "step": 5535 }, { "epoch": 0.2978906586310805, "grad_norm": 2.9243640899658203, "learning_rate": 3.983173765698308e-05, "loss": 4.3798, "step": 5536 }, { "epoch": 0.2979444683598795, "grad_norm": 2.2469494342803955, "learning_rate": 3.982833533255018e-05, "loss": 4.6747, "step": 5537 }, { "epoch": 0.29799827808867846, "grad_norm": 1.8813698291778564, "learning_rate": 3.982493258436335e-05, "loss": 4.2506, "step": 5538 }, { "epoch": 0.2980520878174774, "grad_norm": 1.7210530042648315, "learning_rate": 3.982152941251981e-05, "loss": 4.572, "step": 5539 }, { "epoch": 0.29810589754627637, "grad_norm": 1.3564223051071167, "learning_rate": 3.981812581711683e-05, "loss": 4.4057, "step": 5540 }, { "epoch": 0.29815970727507535, "grad_norm": 2.0689947605133057, "learning_rate": 3.9814721798251663e-05, "loss": 4.3495, "step": 5541 }, { "epoch": 0.2982135170038743, "grad_norm": 1.8626927137374878, "learning_rate": 3.98113173560216e-05, "loss": 4.3024, "step": 5542 }, { "epoch": 0.29826732673267325, "grad_norm": 1.913271188735962, "learning_rate": 3.9807912490523924e-05, "loss": 4.1124, "step": 5543 }, { "epoch": 0.29832113646147224, "grad_norm": 2.302194356918335, "learning_rate": 3.9804507201855934e-05, "loss": 4.3768, "step": 5544 }, { "epoch": 0.2983749461902712, "grad_norm": 1.4924722909927368, "learning_rate": 3.980110149011496e-05, "loss": 4.7381, "step": 5545 }, { "epoch": 0.29842875591907014, "grad_norm": 1.9508841037750244, "learning_rate": 3.97976953553983e-05, "loss": 4.3201, "step": 5546 }, { "epoch": 0.2984825656478691, "grad_norm": 1.5531764030456543, "learning_rate": 3.979428879780331e-05, "loss": 4.7132, "step": 5547 }, { "epoch": 0.2985363753766681, "grad_norm": 2.0507688522338867, "learning_rate": 3.9790881817427343e-05, "loss": 4.2539, "step": 5548 }, { "epoch": 0.2985901851054671, "grad_norm": 1.364033579826355, "learning_rate": 3.978747441436776e-05, "loss": 4.4408, "step": 5549 }, { "epoch": 0.298643994834266, "grad_norm": 1.8358829021453857, "learning_rate": 3.9784066588721926e-05, "loss": 4.5691, "step": 5550 }, { "epoch": 0.298697804563065, "grad_norm": 2.1002209186553955, "learning_rate": 3.978065834058724e-05, "loss": 3.9806, "step": 5551 }, { "epoch": 0.298751614291864, "grad_norm": 2.3941564559936523, "learning_rate": 3.977724967006108e-05, "loss": 3.9389, "step": 5552 }, { "epoch": 0.29880542402066296, "grad_norm": 1.6123219728469849, "learning_rate": 3.977384057724088e-05, "loss": 4.7275, "step": 5553 }, { "epoch": 0.2988592337494619, "grad_norm": 2.0767085552215576, "learning_rate": 3.9770431062224056e-05, "loss": 3.8895, "step": 5554 }, { "epoch": 0.29891304347826086, "grad_norm": 1.9063621759414673, "learning_rate": 3.976702112510804e-05, "loss": 4.2016, "step": 5555 }, { "epoch": 0.29896685320705985, "grad_norm": 1.4619115591049194, "learning_rate": 3.976361076599027e-05, "loss": 4.5033, "step": 5556 }, { "epoch": 0.2990206629358588, "grad_norm": 2.312964677810669, "learning_rate": 3.976019998496822e-05, "loss": 4.0796, "step": 5557 }, { "epoch": 0.29907447266465775, "grad_norm": 1.9395654201507568, "learning_rate": 3.9756788782139353e-05, "loss": 4.6486, "step": 5558 }, { "epoch": 0.29912828239345673, "grad_norm": 2.1309280395507812, "learning_rate": 3.9753377157601154e-05, "loss": 4.4143, "step": 5559 }, { "epoch": 0.2991820921222557, "grad_norm": 2.5562095642089844, "learning_rate": 3.9749965111451126e-05, "loss": 4.3496, "step": 5560 }, { "epoch": 0.2992359018510547, "grad_norm": 1.4623006582260132, "learning_rate": 3.974655264378675e-05, "loss": 4.8194, "step": 5561 }, { "epoch": 0.2992897115798536, "grad_norm": 1.2666724920272827, "learning_rate": 3.9743139754705586e-05, "loss": 4.8099, "step": 5562 }, { "epoch": 0.2993435213086526, "grad_norm": 1.2551733255386353, "learning_rate": 3.973972644430513e-05, "loss": 4.5448, "step": 5563 }, { "epoch": 0.2993973310374516, "grad_norm": 2.034511089324951, "learning_rate": 3.973631271268293e-05, "loss": 4.14, "step": 5564 }, { "epoch": 0.2994511407662505, "grad_norm": 1.6483796834945679, "learning_rate": 3.973289855993656e-05, "loss": 4.2393, "step": 5565 }, { "epoch": 0.2995049504950495, "grad_norm": 2.1238112449645996, "learning_rate": 3.972948398616357e-05, "loss": 4.4682, "step": 5566 }, { "epoch": 0.2995587602238485, "grad_norm": 1.2831947803497314, "learning_rate": 3.972606899146154e-05, "loss": 4.8708, "step": 5567 }, { "epoch": 0.29961256995264746, "grad_norm": 2.486128807067871, "learning_rate": 3.972265357592808e-05, "loss": 4.2255, "step": 5568 }, { "epoch": 0.2996663796814464, "grad_norm": 1.2730580568313599, "learning_rate": 3.971923773966077e-05, "loss": 4.8805, "step": 5569 }, { "epoch": 0.29972018941024536, "grad_norm": 1.3497565984725952, "learning_rate": 3.971582148275724e-05, "loss": 4.5823, "step": 5570 }, { "epoch": 0.29977399913904434, "grad_norm": 1.3051724433898926, "learning_rate": 3.971240480531512e-05, "loss": 4.7418, "step": 5571 }, { "epoch": 0.2998278088678433, "grad_norm": 1.5674675703048706, "learning_rate": 3.970898770743203e-05, "loss": 4.2557, "step": 5572 }, { "epoch": 0.29988161859664225, "grad_norm": 1.469018816947937, "learning_rate": 3.970557018920564e-05, "loss": 4.5841, "step": 5573 }, { "epoch": 0.29993542832544123, "grad_norm": 2.180325746536255, "learning_rate": 3.970215225073361e-05, "loss": 4.8319, "step": 5574 }, { "epoch": 0.2999892380542402, "grad_norm": 1.5668818950653076, "learning_rate": 3.96987338921136e-05, "loss": 4.335, "step": 5575 }, { "epoch": 0.3000430477830392, "grad_norm": 2.2402303218841553, "learning_rate": 3.969531511344332e-05, "loss": 4.3165, "step": 5576 }, { "epoch": 0.3000968575118381, "grad_norm": 1.6036232709884644, "learning_rate": 3.969189591482046e-05, "loss": 4.9266, "step": 5577 }, { "epoch": 0.3001506672406371, "grad_norm": 1.3674404621124268, "learning_rate": 3.9688476296342736e-05, "loss": 4.6211, "step": 5578 }, { "epoch": 0.3002044769694361, "grad_norm": 1.2609496116638184, "learning_rate": 3.9685056258107856e-05, "loss": 4.4472, "step": 5579 }, { "epoch": 0.30025828669823507, "grad_norm": 1.8575843572616577, "learning_rate": 3.968163580021357e-05, "loss": 4.089, "step": 5580 }, { "epoch": 0.300312096427034, "grad_norm": 1.4814667701721191, "learning_rate": 3.9678214922757626e-05, "loss": 4.4069, "step": 5581 }, { "epoch": 0.300365906155833, "grad_norm": 2.8503472805023193, "learning_rate": 3.9674793625837783e-05, "loss": 3.3544, "step": 5582 }, { "epoch": 0.30041971588463195, "grad_norm": 1.1325106620788574, "learning_rate": 3.9671371909551794e-05, "loss": 4.6245, "step": 5583 }, { "epoch": 0.3004735256134309, "grad_norm": 1.8326671123504639, "learning_rate": 3.9667949773997464e-05, "loss": 4.5671, "step": 5584 }, { "epoch": 0.30052733534222986, "grad_norm": 1.2299423217773438, "learning_rate": 3.9664527219272585e-05, "loss": 4.7727, "step": 5585 }, { "epoch": 0.30058114507102884, "grad_norm": 1.6855131387710571, "learning_rate": 3.966110424547496e-05, "loss": 4.0092, "step": 5586 }, { "epoch": 0.3006349547998278, "grad_norm": 2.6073801517486572, "learning_rate": 3.9657680852702407e-05, "loss": 4.4137, "step": 5587 }, { "epoch": 0.30068876452862675, "grad_norm": 1.237788200378418, "learning_rate": 3.965425704105275e-05, "loss": 4.6755, "step": 5588 }, { "epoch": 0.30074257425742573, "grad_norm": 2.2829055786132812, "learning_rate": 3.9650832810623864e-05, "loss": 4.4655, "step": 5589 }, { "epoch": 0.3007963839862247, "grad_norm": 2.7661588191986084, "learning_rate": 3.9647408161513575e-05, "loss": 3.6467, "step": 5590 }, { "epoch": 0.3008501937150237, "grad_norm": 1.1971580982208252, "learning_rate": 3.964398309381975e-05, "loss": 4.9018, "step": 5591 }, { "epoch": 0.3009040034438226, "grad_norm": 1.7163844108581543, "learning_rate": 3.9640557607640285e-05, "loss": 4.104, "step": 5592 }, { "epoch": 0.3009578131726216, "grad_norm": 2.325282573699951, "learning_rate": 3.9637131703073056e-05, "loss": 4.4396, "step": 5593 }, { "epoch": 0.3010116229014206, "grad_norm": 1.1144887208938599, "learning_rate": 3.9633705380215966e-05, "loss": 4.7827, "step": 5594 }, { "epoch": 0.30106543263021956, "grad_norm": 3.3963499069213867, "learning_rate": 3.9630278639166954e-05, "loss": 4.4317, "step": 5595 }, { "epoch": 0.3011192423590185, "grad_norm": 2.513171911239624, "learning_rate": 3.962685148002391e-05, "loss": 4.0448, "step": 5596 }, { "epoch": 0.30117305208781747, "grad_norm": 1.4935985803604126, "learning_rate": 3.96234239028848e-05, "loss": 4.7992, "step": 5597 }, { "epoch": 0.30122686181661645, "grad_norm": 1.9502558708190918, "learning_rate": 3.961999590784757e-05, "loss": 4.0196, "step": 5598 }, { "epoch": 0.30128067154541543, "grad_norm": 2.19319224357605, "learning_rate": 3.961656749501018e-05, "loss": 4.2071, "step": 5599 }, { "epoch": 0.30133448127421436, "grad_norm": 1.3537617921829224, "learning_rate": 3.961313866447061e-05, "loss": 4.3519, "step": 5600 }, { "epoch": 0.30138829100301334, "grad_norm": 1.8761056661605835, "learning_rate": 3.960970941632684e-05, "loss": 3.9662, "step": 5601 }, { "epoch": 0.3014421007318123, "grad_norm": 1.2556920051574707, "learning_rate": 3.9606279750676854e-05, "loss": 4.5871, "step": 5602 }, { "epoch": 0.3014959104606113, "grad_norm": 1.300977349281311, "learning_rate": 3.960284966761869e-05, "loss": 4.6778, "step": 5603 }, { "epoch": 0.30154972018941023, "grad_norm": 4.183806419372559, "learning_rate": 3.959941916725036e-05, "loss": 4.0783, "step": 5604 }, { "epoch": 0.3016035299182092, "grad_norm": 2.2229301929473877, "learning_rate": 3.95959882496699e-05, "loss": 4.3911, "step": 5605 }, { "epoch": 0.3016573396470082, "grad_norm": 2.454655885696411, "learning_rate": 3.9592556914975355e-05, "loss": 3.9735, "step": 5606 }, { "epoch": 0.3017111493758071, "grad_norm": 1.9389774799346924, "learning_rate": 3.958912516326478e-05, "loss": 4.5434, "step": 5607 }, { "epoch": 0.3017649591046061, "grad_norm": 1.6699405908584595, "learning_rate": 3.9585692994636246e-05, "loss": 4.5623, "step": 5608 }, { "epoch": 0.3018187688334051, "grad_norm": 1.970869541168213, "learning_rate": 3.958226040918785e-05, "loss": 4.2298, "step": 5609 }, { "epoch": 0.30187257856220406, "grad_norm": 2.0008978843688965, "learning_rate": 3.957882740701765e-05, "loss": 4.6207, "step": 5610 }, { "epoch": 0.301926388291003, "grad_norm": 1.246211051940918, "learning_rate": 3.957539398822379e-05, "loss": 4.8345, "step": 5611 }, { "epoch": 0.30198019801980197, "grad_norm": 1.2720043659210205, "learning_rate": 3.957196015290437e-05, "loss": 4.7215, "step": 5612 }, { "epoch": 0.30203400774860095, "grad_norm": 1.9062221050262451, "learning_rate": 3.956852590115753e-05, "loss": 3.9944, "step": 5613 }, { "epoch": 0.30208781747739993, "grad_norm": 1.5752863883972168, "learning_rate": 3.956509123308139e-05, "loss": 4.6453, "step": 5614 }, { "epoch": 0.30214162720619886, "grad_norm": 1.8370541334152222, "learning_rate": 3.956165614877413e-05, "loss": 4.1576, "step": 5615 }, { "epoch": 0.30219543693499784, "grad_norm": 1.5404527187347412, "learning_rate": 3.95582206483339e-05, "loss": 4.7187, "step": 5616 }, { "epoch": 0.3022492466637968, "grad_norm": 1.8376164436340332, "learning_rate": 3.955478473185889e-05, "loss": 4.2198, "step": 5617 }, { "epoch": 0.3023030563925958, "grad_norm": 1.3985235691070557, "learning_rate": 3.9551348399447267e-05, "loss": 4.5107, "step": 5618 }, { "epoch": 0.30235686612139473, "grad_norm": 1.4509105682373047, "learning_rate": 3.954791165119724e-05, "loss": 4.9083, "step": 5619 }, { "epoch": 0.3024106758501937, "grad_norm": 2.1431121826171875, "learning_rate": 3.954447448720704e-05, "loss": 4.4264, "step": 5620 }, { "epoch": 0.3024644855789927, "grad_norm": 2.517603635787964, "learning_rate": 3.9541036907574876e-05, "loss": 4.659, "step": 5621 }, { "epoch": 0.3025182953077917, "grad_norm": 1.861621379852295, "learning_rate": 3.953759891239899e-05, "loss": 4.1363, "step": 5622 }, { "epoch": 0.3025721050365906, "grad_norm": 2.192983388900757, "learning_rate": 3.953416050177762e-05, "loss": 4.2259, "step": 5623 }, { "epoch": 0.3026259147653896, "grad_norm": 1.723972201347351, "learning_rate": 3.953072167580905e-05, "loss": 4.4712, "step": 5624 }, { "epoch": 0.30267972449418856, "grad_norm": 1.0607045888900757, "learning_rate": 3.952728243459152e-05, "loss": 4.6459, "step": 5625 }, { "epoch": 0.30273353422298754, "grad_norm": 1.188342571258545, "learning_rate": 3.952384277822334e-05, "loss": 4.4824, "step": 5626 }, { "epoch": 0.30278734395178647, "grad_norm": 1.6349058151245117, "learning_rate": 3.9520402706802795e-05, "loss": 4.3236, "step": 5627 }, { "epoch": 0.30284115368058545, "grad_norm": 1.617799162864685, "learning_rate": 3.9516962220428206e-05, "loss": 4.3472, "step": 5628 }, { "epoch": 0.30289496340938443, "grad_norm": 1.500259280204773, "learning_rate": 3.951352131919788e-05, "loss": 4.813, "step": 5629 }, { "epoch": 0.30294877313818336, "grad_norm": 1.9581743478775024, "learning_rate": 3.9510080003210145e-05, "loss": 4.4839, "step": 5630 }, { "epoch": 0.30300258286698234, "grad_norm": 1.4139461517333984, "learning_rate": 3.9506638272563354e-05, "loss": 4.2526, "step": 5631 }, { "epoch": 0.3030563925957813, "grad_norm": 2.019890308380127, "learning_rate": 3.9503196127355856e-05, "loss": 4.4755, "step": 5632 }, { "epoch": 0.3031102023245803, "grad_norm": 1.2185629606246948, "learning_rate": 3.9499753567686024e-05, "loss": 4.7222, "step": 5633 }, { "epoch": 0.30316401205337923, "grad_norm": 2.9307613372802734, "learning_rate": 3.9496310593652234e-05, "loss": 4.3179, "step": 5634 }, { "epoch": 0.3032178217821782, "grad_norm": 1.5523090362548828, "learning_rate": 3.9492867205352885e-05, "loss": 4.6127, "step": 5635 }, { "epoch": 0.3032716315109772, "grad_norm": 1.3214706182479858, "learning_rate": 3.948942340288637e-05, "loss": 4.478, "step": 5636 }, { "epoch": 0.3033254412397762, "grad_norm": 1.7113544940948486, "learning_rate": 3.9485979186351094e-05, "loss": 4.3122, "step": 5637 }, { "epoch": 0.3033792509685751, "grad_norm": 1.7015470266342163, "learning_rate": 3.948253455584551e-05, "loss": 4.4671, "step": 5638 }, { "epoch": 0.3034330606973741, "grad_norm": 2.53102970123291, "learning_rate": 3.9479089511468034e-05, "loss": 4.7982, "step": 5639 }, { "epoch": 0.30348687042617306, "grad_norm": 2.1713004112243652, "learning_rate": 3.947564405331713e-05, "loss": 4.1313, "step": 5640 }, { "epoch": 0.30354068015497204, "grad_norm": 0.9886669516563416, "learning_rate": 3.947219818149125e-05, "loss": 4.8519, "step": 5641 }, { "epoch": 0.30359448988377097, "grad_norm": 1.686082363128662, "learning_rate": 3.9468751896088864e-05, "loss": 4.2279, "step": 5642 }, { "epoch": 0.30364829961256995, "grad_norm": 1.3513420820236206, "learning_rate": 3.946530519720848e-05, "loss": 4.4143, "step": 5643 }, { "epoch": 0.30370210934136893, "grad_norm": 1.435682773590088, "learning_rate": 3.946185808494857e-05, "loss": 4.4906, "step": 5644 }, { "epoch": 0.3037559190701679, "grad_norm": 2.3889713287353516, "learning_rate": 3.945841055940765e-05, "loss": 3.9076, "step": 5645 }, { "epoch": 0.30380972879896684, "grad_norm": 2.087284803390503, "learning_rate": 3.945496262068425e-05, "loss": 3.9509, "step": 5646 }, { "epoch": 0.3038635385277658, "grad_norm": 2.630699396133423, "learning_rate": 3.945151426887691e-05, "loss": 4.3265, "step": 5647 }, { "epoch": 0.3039173482565648, "grad_norm": 2.484572649002075, "learning_rate": 3.944806550408415e-05, "loss": 4.8199, "step": 5648 }, { "epoch": 0.3039711579853637, "grad_norm": 1.5309185981750488, "learning_rate": 3.944461632640454e-05, "loss": 4.4826, "step": 5649 }, { "epoch": 0.3040249677141627, "grad_norm": 2.138324499130249, "learning_rate": 3.944116673593665e-05, "loss": 4.6571, "step": 5650 }, { "epoch": 0.3040787774429617, "grad_norm": 2.3138182163238525, "learning_rate": 3.943771673277906e-05, "loss": 4.6721, "step": 5651 }, { "epoch": 0.30413258717176067, "grad_norm": 1.6245121955871582, "learning_rate": 3.943426631703035e-05, "loss": 4.5181, "step": 5652 }, { "epoch": 0.3041863969005596, "grad_norm": 1.2380447387695312, "learning_rate": 3.943081548878913e-05, "loss": 4.6757, "step": 5653 }, { "epoch": 0.3042402066293586, "grad_norm": 2.27299427986145, "learning_rate": 3.942736424815403e-05, "loss": 4.1514, "step": 5654 }, { "epoch": 0.30429401635815756, "grad_norm": 1.9955967664718628, "learning_rate": 3.942391259522366e-05, "loss": 4.7475, "step": 5655 }, { "epoch": 0.30434782608695654, "grad_norm": 1.2773200273513794, "learning_rate": 3.9420460530096654e-05, "loss": 4.4345, "step": 5656 }, { "epoch": 0.30440163581575547, "grad_norm": 1.1783863306045532, "learning_rate": 3.941700805287168e-05, "loss": 4.5365, "step": 5657 }, { "epoch": 0.30445544554455445, "grad_norm": 1.6497471332550049, "learning_rate": 3.94135551636474e-05, "loss": 4.5057, "step": 5658 }, { "epoch": 0.30450925527335343, "grad_norm": 1.8925870656967163, "learning_rate": 3.941010186252247e-05, "loss": 4.2136, "step": 5659 }, { "epoch": 0.3045630650021524, "grad_norm": 1.8346278667449951, "learning_rate": 3.9406648149595594e-05, "loss": 4.2858, "step": 5660 }, { "epoch": 0.30461687473095134, "grad_norm": 1.6776461601257324, "learning_rate": 3.9403194024965455e-05, "loss": 4.394, "step": 5661 }, { "epoch": 0.3046706844597503, "grad_norm": 1.0471229553222656, "learning_rate": 3.939973948873078e-05, "loss": 4.7639, "step": 5662 }, { "epoch": 0.3047244941885493, "grad_norm": 1.7396399974822998, "learning_rate": 3.939628454099028e-05, "loss": 4.4795, "step": 5663 }, { "epoch": 0.3047783039173483, "grad_norm": 2.1287593841552734, "learning_rate": 3.9392829181842686e-05, "loss": 4.5749, "step": 5664 }, { "epoch": 0.3048321136461472, "grad_norm": 2.150799036026001, "learning_rate": 3.9389373411386744e-05, "loss": 4.0501, "step": 5665 }, { "epoch": 0.3048859233749462, "grad_norm": 1.634709358215332, "learning_rate": 3.938591722972122e-05, "loss": 4.4669, "step": 5666 }, { "epoch": 0.30493973310374517, "grad_norm": 1.1802691221237183, "learning_rate": 3.938246063694487e-05, "loss": 4.4624, "step": 5667 }, { "epoch": 0.30499354283254415, "grad_norm": 1.908767819404602, "learning_rate": 3.9379003633156476e-05, "loss": 5.1141, "step": 5668 }, { "epoch": 0.3050473525613431, "grad_norm": 1.9726221561431885, "learning_rate": 3.937554621845484e-05, "loss": 4.1148, "step": 5669 }, { "epoch": 0.30510116229014206, "grad_norm": 1.9966962337493896, "learning_rate": 3.9372088392938756e-05, "loss": 4.1602, "step": 5670 }, { "epoch": 0.30515497201894104, "grad_norm": 1.8561509847640991, "learning_rate": 3.936863015670704e-05, "loss": 4.3784, "step": 5671 }, { "epoch": 0.30520878174773997, "grad_norm": 1.1828795671463013, "learning_rate": 3.936517150985853e-05, "loss": 4.3829, "step": 5672 }, { "epoch": 0.30526259147653895, "grad_norm": 2.502685546875, "learning_rate": 3.936171245249205e-05, "loss": 4.8035, "step": 5673 }, { "epoch": 0.30531640120533793, "grad_norm": 2.294661521911621, "learning_rate": 3.935825298470646e-05, "loss": 4.507, "step": 5674 }, { "epoch": 0.3053702109341369, "grad_norm": 2.4984681606292725, "learning_rate": 3.9354793106600606e-05, "loss": 4.7148, "step": 5675 }, { "epoch": 0.30542402066293584, "grad_norm": 1.3768644332885742, "learning_rate": 3.935133281827339e-05, "loss": 4.5167, "step": 5676 }, { "epoch": 0.3054778303917348, "grad_norm": 2.307588577270508, "learning_rate": 3.934787211982367e-05, "loss": 4.1221, "step": 5677 }, { "epoch": 0.3055316401205338, "grad_norm": 1.8135029077529907, "learning_rate": 3.934441101135037e-05, "loss": 4.4679, "step": 5678 }, { "epoch": 0.3055854498493328, "grad_norm": 1.2024271488189697, "learning_rate": 3.9340949492952374e-05, "loss": 4.6821, "step": 5679 }, { "epoch": 0.3056392595781317, "grad_norm": 1.8395932912826538, "learning_rate": 3.933748756472862e-05, "loss": 4.1287, "step": 5680 }, { "epoch": 0.3056930693069307, "grad_norm": 1.139076828956604, "learning_rate": 3.933402522677804e-05, "loss": 4.8452, "step": 5681 }, { "epoch": 0.30574687903572967, "grad_norm": 1.4186108112335205, "learning_rate": 3.933056247919956e-05, "loss": 4.6614, "step": 5682 }, { "epoch": 0.30580068876452865, "grad_norm": 2.6464812755584717, "learning_rate": 3.9327099322092154e-05, "loss": 3.9552, "step": 5683 }, { "epoch": 0.3058544984933276, "grad_norm": 1.605369210243225, "learning_rate": 3.9323635755554785e-05, "loss": 4.4141, "step": 5684 }, { "epoch": 0.30590830822212656, "grad_norm": 2.374892234802246, "learning_rate": 3.932017177968643e-05, "loss": 4.7736, "step": 5685 }, { "epoch": 0.30596211795092554, "grad_norm": 1.360275149345398, "learning_rate": 3.9316707394586085e-05, "loss": 4.2966, "step": 5686 }, { "epoch": 0.3060159276797245, "grad_norm": 2.6250226497650146, "learning_rate": 3.931324260035275e-05, "loss": 4.71, "step": 5687 }, { "epoch": 0.30606973740852345, "grad_norm": 2.5286824703216553, "learning_rate": 3.9309777397085445e-05, "loss": 4.5879, "step": 5688 }, { "epoch": 0.3061235471373224, "grad_norm": 1.9389293193817139, "learning_rate": 3.930631178488319e-05, "loss": 4.4005, "step": 5689 }, { "epoch": 0.3061773568661214, "grad_norm": 2.238210439682007, "learning_rate": 3.930284576384502e-05, "loss": 4.3715, "step": 5690 }, { "epoch": 0.30623116659492033, "grad_norm": 1.7488726377487183, "learning_rate": 3.929937933406997e-05, "loss": 4.2928, "step": 5691 }, { "epoch": 0.3062849763237193, "grad_norm": 2.4914650917053223, "learning_rate": 3.929591249565715e-05, "loss": 4.2781, "step": 5692 }, { "epoch": 0.3063387860525183, "grad_norm": 1.6817365884780884, "learning_rate": 3.929244524870559e-05, "loss": 4.7004, "step": 5693 }, { "epoch": 0.3063925957813173, "grad_norm": 0.8947528600692749, "learning_rate": 3.928897759331438e-05, "loss": 4.6955, "step": 5694 }, { "epoch": 0.3064464055101162, "grad_norm": 1.3514628410339355, "learning_rate": 3.928550952958263e-05, "loss": 4.4623, "step": 5695 }, { "epoch": 0.3065002152389152, "grad_norm": 2.632147789001465, "learning_rate": 3.928204105760944e-05, "loss": 3.8208, "step": 5696 }, { "epoch": 0.30655402496771417, "grad_norm": 1.897322654724121, "learning_rate": 3.9278572177493935e-05, "loss": 4.7936, "step": 5697 }, { "epoch": 0.30660783469651315, "grad_norm": 1.1878547668457031, "learning_rate": 3.9275102889335235e-05, "loss": 4.5971, "step": 5698 }, { "epoch": 0.3066616444253121, "grad_norm": 1.1978201866149902, "learning_rate": 3.927163319323249e-05, "loss": 4.803, "step": 5699 }, { "epoch": 0.30671545415411106, "grad_norm": 2.0607998371124268, "learning_rate": 3.9268163089284865e-05, "loss": 4.1703, "step": 5700 }, { "epoch": 0.30676926388291004, "grad_norm": 0.954766571521759, "learning_rate": 3.9264692577591504e-05, "loss": 4.8575, "step": 5701 }, { "epoch": 0.306823073611709, "grad_norm": 1.1907333135604858, "learning_rate": 3.9261221658251604e-05, "loss": 4.5423, "step": 5702 }, { "epoch": 0.30687688334050794, "grad_norm": 1.1530861854553223, "learning_rate": 3.925775033136434e-05, "loss": 4.7472, "step": 5703 }, { "epoch": 0.3069306930693069, "grad_norm": 1.7370613813400269, "learning_rate": 3.9254278597028924e-05, "loss": 4.2867, "step": 5704 }, { "epoch": 0.3069845027981059, "grad_norm": 1.5041749477386475, "learning_rate": 3.925080645534457e-05, "loss": 4.5326, "step": 5705 }, { "epoch": 0.3070383125269049, "grad_norm": 1.1165632009506226, "learning_rate": 3.9247333906410495e-05, "loss": 4.6241, "step": 5706 }, { "epoch": 0.3070921222557038, "grad_norm": 1.5874934196472168, "learning_rate": 3.9243860950325935e-05, "loss": 4.3297, "step": 5707 }, { "epoch": 0.3071459319845028, "grad_norm": 1.4463871717453003, "learning_rate": 3.924038758719014e-05, "loss": 4.6837, "step": 5708 }, { "epoch": 0.3071997417133018, "grad_norm": 1.5364474058151245, "learning_rate": 3.923691381710237e-05, "loss": 4.5627, "step": 5709 }, { "epoch": 0.30725355144210076, "grad_norm": 1.3335647583007812, "learning_rate": 3.9233439640161904e-05, "loss": 4.6231, "step": 5710 }, { "epoch": 0.3073073611708997, "grad_norm": 1.6597734689712524, "learning_rate": 3.922996505646801e-05, "loss": 4.4413, "step": 5711 }, { "epoch": 0.30736117089969867, "grad_norm": 2.516975164413452, "learning_rate": 3.922649006611999e-05, "loss": 4.6399, "step": 5712 }, { "epoch": 0.30741498062849765, "grad_norm": 2.055915594100952, "learning_rate": 3.922301466921714e-05, "loss": 4.2624, "step": 5713 }, { "epoch": 0.3074687903572966, "grad_norm": 1.7340168952941895, "learning_rate": 3.921953886585879e-05, "loss": 4.3197, "step": 5714 }, { "epoch": 0.30752260008609555, "grad_norm": 1.8680789470672607, "learning_rate": 3.921606265614428e-05, "loss": 4.3635, "step": 5715 }, { "epoch": 0.30757640981489454, "grad_norm": 2.6840357780456543, "learning_rate": 3.921258604017293e-05, "loss": 4.0988, "step": 5716 }, { "epoch": 0.3076302195436935, "grad_norm": 1.958875298500061, "learning_rate": 3.920910901804409e-05, "loss": 4.1034, "step": 5717 }, { "epoch": 0.30768402927249244, "grad_norm": 1.9975237846374512, "learning_rate": 3.920563158985713e-05, "loss": 4.4462, "step": 5718 }, { "epoch": 0.3077378390012914, "grad_norm": 1.898159146308899, "learning_rate": 3.920215375571143e-05, "loss": 4.7211, "step": 5719 }, { "epoch": 0.3077916487300904, "grad_norm": 2.3764917850494385, "learning_rate": 3.919867551570639e-05, "loss": 4.6591, "step": 5720 }, { "epoch": 0.3078454584588894, "grad_norm": 1.7008850574493408, "learning_rate": 3.9195196869941376e-05, "loss": 4.5733, "step": 5721 }, { "epoch": 0.3078992681876883, "grad_norm": 1.5974514484405518, "learning_rate": 3.919171781851582e-05, "loss": 4.6228, "step": 5722 }, { "epoch": 0.3079530779164873, "grad_norm": 1.9118032455444336, "learning_rate": 3.918823836152914e-05, "loss": 4.3736, "step": 5723 }, { "epoch": 0.3080068876452863, "grad_norm": 1.825282335281372, "learning_rate": 3.9184758499080774e-05, "loss": 4.2395, "step": 5724 }, { "epoch": 0.30806069737408526, "grad_norm": 2.061225175857544, "learning_rate": 3.9181278231270166e-05, "loss": 4.2397, "step": 5725 }, { "epoch": 0.3081145071028842, "grad_norm": 1.0664246082305908, "learning_rate": 3.917779755819676e-05, "loss": 4.8669, "step": 5726 }, { "epoch": 0.30816831683168316, "grad_norm": 1.3671268224716187, "learning_rate": 3.917431647996004e-05, "loss": 4.5575, "step": 5727 }, { "epoch": 0.30822212656048215, "grad_norm": 1.687626600265503, "learning_rate": 3.9170834996659475e-05, "loss": 4.519, "step": 5728 }, { "epoch": 0.3082759362892811, "grad_norm": 1.8492649793624878, "learning_rate": 3.916735310839457e-05, "loss": 4.6288, "step": 5729 }, { "epoch": 0.30832974601808005, "grad_norm": 2.9853994846343994, "learning_rate": 3.9163870815264805e-05, "loss": 3.6853, "step": 5730 }, { "epoch": 0.30838355574687903, "grad_norm": 2.7583656311035156, "learning_rate": 3.9160388117369716e-05, "loss": 4.1914, "step": 5731 }, { "epoch": 0.308437365475678, "grad_norm": 1.674519419670105, "learning_rate": 3.915690501480882e-05, "loss": 4.2011, "step": 5732 }, { "epoch": 0.30849117520447694, "grad_norm": 1.2021313905715942, "learning_rate": 3.915342150768165e-05, "loss": 4.4155, "step": 5733 }, { "epoch": 0.3085449849332759, "grad_norm": 1.534496545791626, "learning_rate": 3.914993759608778e-05, "loss": 4.8042, "step": 5734 }, { "epoch": 0.3085987946620749, "grad_norm": 1.6056325435638428, "learning_rate": 3.914645328012674e-05, "loss": 4.6809, "step": 5735 }, { "epoch": 0.3086526043908739, "grad_norm": 1.6170942783355713, "learning_rate": 3.914296855989811e-05, "loss": 4.2232, "step": 5736 }, { "epoch": 0.3087064141196728, "grad_norm": 1.7808951139450073, "learning_rate": 3.913948343550148e-05, "loss": 4.5203, "step": 5737 }, { "epoch": 0.3087602238484718, "grad_norm": 2.051588773727417, "learning_rate": 3.913599790703646e-05, "loss": 4.3728, "step": 5738 }, { "epoch": 0.3088140335772708, "grad_norm": 1.2773770093917847, "learning_rate": 3.913251197460262e-05, "loss": 4.6624, "step": 5739 }, { "epoch": 0.30886784330606976, "grad_norm": 1.2963149547576904, "learning_rate": 3.9129025638299613e-05, "loss": 4.6242, "step": 5740 }, { "epoch": 0.3089216530348687, "grad_norm": 1.3832634687423706, "learning_rate": 3.912553889822706e-05, "loss": 4.791, "step": 5741 }, { "epoch": 0.30897546276366766, "grad_norm": 2.2349185943603516, "learning_rate": 3.912205175448458e-05, "loss": 4.3706, "step": 5742 }, { "epoch": 0.30902927249246664, "grad_norm": 1.8893349170684814, "learning_rate": 3.911856420717186e-05, "loss": 4.6865, "step": 5743 }, { "epoch": 0.3090830822212656, "grad_norm": 2.0416150093078613, "learning_rate": 3.911507625638854e-05, "loss": 4.425, "step": 5744 }, { "epoch": 0.30913689195006455, "grad_norm": 1.5256215333938599, "learning_rate": 3.9111587902234306e-05, "loss": 4.4713, "step": 5745 }, { "epoch": 0.30919070167886353, "grad_norm": 1.7642041444778442, "learning_rate": 3.910809914480886e-05, "loss": 4.6716, "step": 5746 }, { "epoch": 0.3092445114076625, "grad_norm": 1.2613914012908936, "learning_rate": 3.9104609984211874e-05, "loss": 4.8815, "step": 5747 }, { "epoch": 0.3092983211364615, "grad_norm": 2.0547451972961426, "learning_rate": 3.910112042054307e-05, "loss": 4.0017, "step": 5748 }, { "epoch": 0.3093521308652604, "grad_norm": 2.0069262981414795, "learning_rate": 3.909763045390218e-05, "loss": 4.3507, "step": 5749 }, { "epoch": 0.3094059405940594, "grad_norm": 1.4224679470062256, "learning_rate": 3.909414008438892e-05, "loss": 4.3507, "step": 5750 }, { "epoch": 0.3094597503228584, "grad_norm": 2.1347806453704834, "learning_rate": 3.9090649312103054e-05, "loss": 4.0481, "step": 5751 }, { "epoch": 0.30951356005165737, "grad_norm": 2.6241884231567383, "learning_rate": 3.908715813714433e-05, "loss": 4.7168, "step": 5752 }, { "epoch": 0.3095673697804563, "grad_norm": 2.1909728050231934, "learning_rate": 3.908366655961251e-05, "loss": 4.4728, "step": 5753 }, { "epoch": 0.3096211795092553, "grad_norm": 1.5312830209732056, "learning_rate": 3.908017457960739e-05, "loss": 4.5734, "step": 5754 }, { "epoch": 0.30967498923805425, "grad_norm": 2.8824362754821777, "learning_rate": 3.9076682197228744e-05, "loss": 4.3627, "step": 5755 }, { "epoch": 0.3097287989668532, "grad_norm": 2.599428415298462, "learning_rate": 3.9073189412576386e-05, "loss": 3.6459, "step": 5756 }, { "epoch": 0.30978260869565216, "grad_norm": 4.019623756408691, "learning_rate": 3.906969622575012e-05, "loss": 4.4669, "step": 5757 }, { "epoch": 0.30983641842445114, "grad_norm": 1.8739144802093506, "learning_rate": 3.906620263684979e-05, "loss": 4.4302, "step": 5758 }, { "epoch": 0.3098902281532501, "grad_norm": 2.2776191234588623, "learning_rate": 3.906270864597521e-05, "loss": 3.9779, "step": 5759 }, { "epoch": 0.30994403788204905, "grad_norm": 1.1412910223007202, "learning_rate": 3.905921425322625e-05, "loss": 4.4186, "step": 5760 }, { "epoch": 0.30999784761084803, "grad_norm": 1.8472825288772583, "learning_rate": 3.905571945870277e-05, "loss": 4.4914, "step": 5761 }, { "epoch": 0.310051657339647, "grad_norm": 2.421259641647339, "learning_rate": 3.905222426250461e-05, "loss": 4.2081, "step": 5762 }, { "epoch": 0.310105467068446, "grad_norm": 2.325180768966675, "learning_rate": 3.904872866473169e-05, "loss": 4.4308, "step": 5763 }, { "epoch": 0.3101592767972449, "grad_norm": 1.4487062692642212, "learning_rate": 3.9045232665483894e-05, "loss": 4.6125, "step": 5764 }, { "epoch": 0.3102130865260439, "grad_norm": 1.1931010484695435, "learning_rate": 3.9041736264861125e-05, "loss": 4.742, "step": 5765 }, { "epoch": 0.3102668962548429, "grad_norm": 2.001239538192749, "learning_rate": 3.90382394629633e-05, "loss": 4.6226, "step": 5766 }, { "epoch": 0.31032070598364186, "grad_norm": 2.259918689727783, "learning_rate": 3.9034742259890344e-05, "loss": 4.0362, "step": 5767 }, { "epoch": 0.3103745157124408, "grad_norm": 2.2641143798828125, "learning_rate": 3.9031244655742205e-05, "loss": 4.6749, "step": 5768 }, { "epoch": 0.31042832544123977, "grad_norm": 0.9980936050415039, "learning_rate": 3.902774665061884e-05, "loss": 4.6304, "step": 5769 }, { "epoch": 0.31048213517003875, "grad_norm": 1.266480803489685, "learning_rate": 3.90242482446202e-05, "loss": 5.0252, "step": 5770 }, { "epoch": 0.31053594489883773, "grad_norm": 1.6479521989822388, "learning_rate": 3.902074943784626e-05, "loss": 4.5738, "step": 5771 }, { "epoch": 0.31058975462763666, "grad_norm": 2.8997650146484375, "learning_rate": 3.901725023039703e-05, "loss": 4.1842, "step": 5772 }, { "epoch": 0.31064356435643564, "grad_norm": 1.0325138568878174, "learning_rate": 3.901375062237248e-05, "loss": 4.47, "step": 5773 }, { "epoch": 0.3106973740852346, "grad_norm": 1.432181715965271, "learning_rate": 3.9010250613872625e-05, "loss": 4.7062, "step": 5774 }, { "epoch": 0.3107511838140336, "grad_norm": 2.327488899230957, "learning_rate": 3.90067502049975e-05, "loss": 4.2266, "step": 5775 }, { "epoch": 0.31080499354283253, "grad_norm": 1.070285677909851, "learning_rate": 3.900324939584712e-05, "loss": 4.588, "step": 5776 }, { "epoch": 0.3108588032716315, "grad_norm": 1.1270512342453003, "learning_rate": 3.8999748186521544e-05, "loss": 4.3409, "step": 5777 }, { "epoch": 0.3109126130004305, "grad_norm": 1.7034634351730347, "learning_rate": 3.899624657712081e-05, "loss": 4.7847, "step": 5778 }, { "epoch": 0.3109664227292294, "grad_norm": 2.4352283477783203, "learning_rate": 3.8992744567745006e-05, "loss": 4.2602, "step": 5779 }, { "epoch": 0.3110202324580284, "grad_norm": 2.078646183013916, "learning_rate": 3.8989242158494194e-05, "loss": 4.093, "step": 5780 }, { "epoch": 0.3110740421868274, "grad_norm": 2.054292678833008, "learning_rate": 3.898573934946846e-05, "loss": 4.7511, "step": 5781 }, { "epoch": 0.31112785191562636, "grad_norm": 1.1864659786224365, "learning_rate": 3.8982236140767924e-05, "loss": 4.5057, "step": 5782 }, { "epoch": 0.3111816616444253, "grad_norm": 1.979215145111084, "learning_rate": 3.897873253249268e-05, "loss": 4.2145, "step": 5783 }, { "epoch": 0.31123547137322427, "grad_norm": 1.7701520919799805, "learning_rate": 3.897522852474287e-05, "loss": 4.4698, "step": 5784 }, { "epoch": 0.31128928110202325, "grad_norm": 4.053342342376709, "learning_rate": 3.89717241176186e-05, "loss": 4.2616, "step": 5785 }, { "epoch": 0.31134309083082223, "grad_norm": 1.6234124898910522, "learning_rate": 3.8968219311220047e-05, "loss": 4.7339, "step": 5786 }, { "epoch": 0.31139690055962116, "grad_norm": 1.4887934923171997, "learning_rate": 3.896471410564735e-05, "loss": 4.189, "step": 5787 }, { "epoch": 0.31145071028842014, "grad_norm": 1.9323275089263916, "learning_rate": 3.896120850100069e-05, "loss": 4.58, "step": 5788 }, { "epoch": 0.3115045200172191, "grad_norm": 1.0892441272735596, "learning_rate": 3.8957702497380234e-05, "loss": 4.5443, "step": 5789 }, { "epoch": 0.3115583297460181, "grad_norm": 1.4812493324279785, "learning_rate": 3.8954196094886185e-05, "loss": 4.7179, "step": 5790 }, { "epoch": 0.31161213947481703, "grad_norm": 2.223763942718506, "learning_rate": 3.895068929361875e-05, "loss": 3.9324, "step": 5791 }, { "epoch": 0.311665949203616, "grad_norm": 2.1275906562805176, "learning_rate": 3.8947182093678133e-05, "loss": 4.6772, "step": 5792 }, { "epoch": 0.311719758932415, "grad_norm": 2.1074442863464355, "learning_rate": 3.8943674495164565e-05, "loss": 4.4135, "step": 5793 }, { "epoch": 0.311773568661214, "grad_norm": 1.035366415977478, "learning_rate": 3.8940166498178285e-05, "loss": 4.5449, "step": 5794 }, { "epoch": 0.3118273783900129, "grad_norm": 1.1615482568740845, "learning_rate": 3.893665810281954e-05, "loss": 4.6013, "step": 5795 }, { "epoch": 0.3118811881188119, "grad_norm": 1.0844433307647705, "learning_rate": 3.89331493091886e-05, "loss": 4.31, "step": 5796 }, { "epoch": 0.31193499784761086, "grad_norm": 1.183652400970459, "learning_rate": 3.892964011738571e-05, "loss": 4.7772, "step": 5797 }, { "epoch": 0.3119888075764098, "grad_norm": 1.792762041091919, "learning_rate": 3.892613052751118e-05, "loss": 4.4659, "step": 5798 }, { "epoch": 0.31204261730520877, "grad_norm": 1.86208176612854, "learning_rate": 3.892262053966531e-05, "loss": 4.7316, "step": 5799 }, { "epoch": 0.31209642703400775, "grad_norm": 1.2420212030410767, "learning_rate": 3.891911015394838e-05, "loss": 5.0041, "step": 5800 }, { "epoch": 0.31215023676280673, "grad_norm": 2.0389463901519775, "learning_rate": 3.891559937046072e-05, "loss": 4.7041, "step": 5801 }, { "epoch": 0.31220404649160566, "grad_norm": 1.7841850519180298, "learning_rate": 3.8912088189302665e-05, "loss": 4.4002, "step": 5802 }, { "epoch": 0.31225785622040464, "grad_norm": 1.1205140352249146, "learning_rate": 3.890857661057454e-05, "loss": 4.6687, "step": 5803 }, { "epoch": 0.3123116659492036, "grad_norm": 1.5111310482025146, "learning_rate": 3.890506463437671e-05, "loss": 4.5638, "step": 5804 }, { "epoch": 0.3123654756780026, "grad_norm": 2.4352831840515137, "learning_rate": 3.890155226080954e-05, "loss": 3.9058, "step": 5805 }, { "epoch": 0.31241928540680153, "grad_norm": 1.7956093549728394, "learning_rate": 3.8898039489973384e-05, "loss": 3.9271, "step": 5806 }, { "epoch": 0.3124730951356005, "grad_norm": 1.1830109357833862, "learning_rate": 3.889452632196865e-05, "loss": 4.5124, "step": 5807 }, { "epoch": 0.3125269048643995, "grad_norm": 1.7986317873001099, "learning_rate": 3.8891012756895716e-05, "loss": 4.2496, "step": 5808 }, { "epoch": 0.31258071459319847, "grad_norm": 1.5125095844268799, "learning_rate": 3.8887498794855004e-05, "loss": 4.7581, "step": 5809 }, { "epoch": 0.3126345243219974, "grad_norm": 2.2970550060272217, "learning_rate": 3.888398443594693e-05, "loss": 4.6303, "step": 5810 }, { "epoch": 0.3126883340507964, "grad_norm": 2.0826663970947266, "learning_rate": 3.888046968027193e-05, "loss": 4.1197, "step": 5811 }, { "epoch": 0.31274214377959536, "grad_norm": 1.819014549255371, "learning_rate": 3.887695452793043e-05, "loss": 4.7163, "step": 5812 }, { "epoch": 0.31279595350839434, "grad_norm": 2.045020580291748, "learning_rate": 3.88734389790229e-05, "loss": 4.3877, "step": 5813 }, { "epoch": 0.31284976323719327, "grad_norm": 2.2416138648986816, "learning_rate": 3.88699230336498e-05, "loss": 3.5311, "step": 5814 }, { "epoch": 0.31290357296599225, "grad_norm": 2.6277530193328857, "learning_rate": 3.886640669191161e-05, "loss": 3.9414, "step": 5815 }, { "epoch": 0.31295738269479123, "grad_norm": 1.24774169921875, "learning_rate": 3.886288995390881e-05, "loss": 4.6818, "step": 5816 }, { "epoch": 0.3130111924235902, "grad_norm": 1.9279913902282715, "learning_rate": 3.885937281974189e-05, "loss": 4.3016, "step": 5817 }, { "epoch": 0.31306500215238914, "grad_norm": 2.100343942642212, "learning_rate": 3.885585528951139e-05, "loss": 4.1778, "step": 5818 }, { "epoch": 0.3131188118811881, "grad_norm": 2.626088857650757, "learning_rate": 3.88523373633178e-05, "loss": 4.2388, "step": 5819 }, { "epoch": 0.3131726216099871, "grad_norm": 2.0320427417755127, "learning_rate": 3.884881904126168e-05, "loss": 4.2714, "step": 5820 }, { "epoch": 0.313226431338786, "grad_norm": 1.3957210779190063, "learning_rate": 3.884530032344355e-05, "loss": 4.6174, "step": 5821 }, { "epoch": 0.313280241067585, "grad_norm": 1.9916170835494995, "learning_rate": 3.8841781209963976e-05, "loss": 4.3397, "step": 5822 }, { "epoch": 0.313334050796384, "grad_norm": 2.653911590576172, "learning_rate": 3.883826170092353e-05, "loss": 4.5209, "step": 5823 }, { "epoch": 0.31338786052518297, "grad_norm": 1.2281728982925415, "learning_rate": 3.883474179642278e-05, "loss": 4.442, "step": 5824 }, { "epoch": 0.3134416702539819, "grad_norm": 2.6500282287597656, "learning_rate": 3.8831221496562324e-05, "loss": 4.4355, "step": 5825 }, { "epoch": 0.3134954799827809, "grad_norm": 1.2796828746795654, "learning_rate": 3.882770080144276e-05, "loss": 4.2837, "step": 5826 }, { "epoch": 0.31354928971157986, "grad_norm": 1.991344690322876, "learning_rate": 3.88241797111647e-05, "loss": 4.8108, "step": 5827 }, { "epoch": 0.31360309944037884, "grad_norm": 2.106308698654175, "learning_rate": 3.8820658225828766e-05, "loss": 4.3417, "step": 5828 }, { "epoch": 0.31365690916917777, "grad_norm": 1.832930088043213, "learning_rate": 3.881713634553559e-05, "loss": 4.0675, "step": 5829 }, { "epoch": 0.31371071889797675, "grad_norm": 2.915748357772827, "learning_rate": 3.881361407038583e-05, "loss": 3.7481, "step": 5830 }, { "epoch": 0.31376452862677573, "grad_norm": 2.326779842376709, "learning_rate": 3.881009140048012e-05, "loss": 4.2539, "step": 5831 }, { "epoch": 0.3138183383555747, "grad_norm": 1.6200673580169678, "learning_rate": 3.8806568335919146e-05, "loss": 4.3825, "step": 5832 }, { "epoch": 0.31387214808437364, "grad_norm": 1.9945791959762573, "learning_rate": 3.880304487680359e-05, "loss": 4.244, "step": 5833 }, { "epoch": 0.3139259578131726, "grad_norm": 1.25491201877594, "learning_rate": 3.8799521023234145e-05, "loss": 4.6493, "step": 5834 }, { "epoch": 0.3139797675419716, "grad_norm": 2.9966788291931152, "learning_rate": 3.8795996775311484e-05, "loss": 3.8281, "step": 5835 }, { "epoch": 0.3140335772707706, "grad_norm": 1.5306729078292847, "learning_rate": 3.879247213313636e-05, "loss": 4.5021, "step": 5836 }, { "epoch": 0.3140873869995695, "grad_norm": 2.2478554248809814, "learning_rate": 3.878894709680947e-05, "loss": 4.7704, "step": 5837 }, { "epoch": 0.3141411967283685, "grad_norm": 2.3722732067108154, "learning_rate": 3.8785421666431564e-05, "loss": 4.3452, "step": 5838 }, { "epoch": 0.31419500645716747, "grad_norm": 1.7939133644104004, "learning_rate": 3.878189584210338e-05, "loss": 4.4984, "step": 5839 }, { "epoch": 0.3142488161859664, "grad_norm": 2.659106731414795, "learning_rate": 3.877836962392569e-05, "loss": 4.127, "step": 5840 }, { "epoch": 0.3143026259147654, "grad_norm": 2.586709976196289, "learning_rate": 3.8774843011999256e-05, "loss": 4.5634, "step": 5841 }, { "epoch": 0.31435643564356436, "grad_norm": 1.752918004989624, "learning_rate": 3.877131600642485e-05, "loss": 4.0444, "step": 5842 }, { "epoch": 0.31441024537236334, "grad_norm": 1.3021442890167236, "learning_rate": 3.8767788607303276e-05, "loss": 4.7295, "step": 5843 }, { "epoch": 0.31446405510116227, "grad_norm": 1.8467546701431274, "learning_rate": 3.8764260814735345e-05, "loss": 4.8122, "step": 5844 }, { "epoch": 0.31451786482996125, "grad_norm": 1.1675523519515991, "learning_rate": 3.876073262882185e-05, "loss": 4.7137, "step": 5845 }, { "epoch": 0.31457167455876023, "grad_norm": 2.6509032249450684, "learning_rate": 3.875720404966363e-05, "loss": 4.2937, "step": 5846 }, { "epoch": 0.3146254842875592, "grad_norm": 1.384564757347107, "learning_rate": 3.875367507736152e-05, "loss": 4.4312, "step": 5847 }, { "epoch": 0.31467929401635814, "grad_norm": 1.6410396099090576, "learning_rate": 3.875014571201637e-05, "loss": 4.4335, "step": 5848 }, { "epoch": 0.3147331037451571, "grad_norm": 1.9210249185562134, "learning_rate": 3.8746615953729046e-05, "loss": 4.4369, "step": 5849 }, { "epoch": 0.3147869134739561, "grad_norm": 1.6044502258300781, "learning_rate": 3.87430858026004e-05, "loss": 4.4674, "step": 5850 }, { "epoch": 0.3148407232027551, "grad_norm": 1.445713996887207, "learning_rate": 3.873955525873134e-05, "loss": 4.5703, "step": 5851 }, { "epoch": 0.314894532931554, "grad_norm": 1.1299071311950684, "learning_rate": 3.873602432222273e-05, "loss": 4.827, "step": 5852 }, { "epoch": 0.314948342660353, "grad_norm": 1.849672794342041, "learning_rate": 3.8732492993175506e-05, "loss": 4.3746, "step": 5853 }, { "epoch": 0.31500215238915197, "grad_norm": 1.7278263568878174, "learning_rate": 3.8728961271690556e-05, "loss": 4.217, "step": 5854 }, { "epoch": 0.31505596211795095, "grad_norm": 1.1349037885665894, "learning_rate": 3.872542915786883e-05, "loss": 4.7129, "step": 5855 }, { "epoch": 0.3151097718467499, "grad_norm": 1.6801849603652954, "learning_rate": 3.872189665181125e-05, "loss": 5.0234, "step": 5856 }, { "epoch": 0.31516358157554886, "grad_norm": 1.0320470333099365, "learning_rate": 3.871836375361877e-05, "loss": 4.4541, "step": 5857 }, { "epoch": 0.31521739130434784, "grad_norm": 1.863136887550354, "learning_rate": 3.871483046339235e-05, "loss": 4.3145, "step": 5858 }, { "epoch": 0.3152712010331468, "grad_norm": 1.1412993669509888, "learning_rate": 3.871129678123297e-05, "loss": 4.7556, "step": 5859 }, { "epoch": 0.31532501076194575, "grad_norm": 1.4806628227233887, "learning_rate": 3.87077627072416e-05, "loss": 4.3281, "step": 5860 }, { "epoch": 0.3153788204907447, "grad_norm": 1.776580572128296, "learning_rate": 3.870422824151925e-05, "loss": 4.81, "step": 5861 }, { "epoch": 0.3154326302195437, "grad_norm": 2.1365256309509277, "learning_rate": 3.8700693384166915e-05, "loss": 4.5658, "step": 5862 }, { "epoch": 0.31548643994834263, "grad_norm": 2.3720901012420654, "learning_rate": 3.869715813528561e-05, "loss": 4.2445, "step": 5863 }, { "epoch": 0.3155402496771416, "grad_norm": 2.0898585319519043, "learning_rate": 3.869362249497637e-05, "loss": 4.2783, "step": 5864 }, { "epoch": 0.3155940594059406, "grad_norm": 1.2009114027023315, "learning_rate": 3.869008646334023e-05, "loss": 4.2655, "step": 5865 }, { "epoch": 0.3156478691347396, "grad_norm": 2.142055034637451, "learning_rate": 3.8686550040478234e-05, "loss": 4.4802, "step": 5866 }, { "epoch": 0.3157016788635385, "grad_norm": 1.2398337125778198, "learning_rate": 3.868301322649146e-05, "loss": 4.6638, "step": 5867 }, { "epoch": 0.3157554885923375, "grad_norm": 1.7402244806289673, "learning_rate": 3.867947602148097e-05, "loss": 4.2208, "step": 5868 }, { "epoch": 0.31580929832113647, "grad_norm": 1.1484771966934204, "learning_rate": 3.867593842554784e-05, "loss": 4.7769, "step": 5869 }, { "epoch": 0.31586310804993545, "grad_norm": 1.724454641342163, "learning_rate": 3.867240043879318e-05, "loss": 4.8647, "step": 5870 }, { "epoch": 0.3159169177787344, "grad_norm": 1.9053072929382324, "learning_rate": 3.866886206131809e-05, "loss": 4.4997, "step": 5871 }, { "epoch": 0.31597072750753336, "grad_norm": 2.393482208251953, "learning_rate": 3.866532329322369e-05, "loss": 4.5622, "step": 5872 }, { "epoch": 0.31602453723633234, "grad_norm": 1.2429953813552856, "learning_rate": 3.86617841346111e-05, "loss": 4.3893, "step": 5873 }, { "epoch": 0.3160783469651313, "grad_norm": 1.1967898607254028, "learning_rate": 3.8658244585581465e-05, "loss": 4.8978, "step": 5874 }, { "epoch": 0.31613215669393024, "grad_norm": 2.470327854156494, "learning_rate": 3.865470464623594e-05, "loss": 4.2451, "step": 5875 }, { "epoch": 0.3161859664227292, "grad_norm": 1.6825742721557617, "learning_rate": 3.865116431667568e-05, "loss": 4.3904, "step": 5876 }, { "epoch": 0.3162397761515282, "grad_norm": 2.6438345909118652, "learning_rate": 3.864762359700187e-05, "loss": 4.1802, "step": 5877 }, { "epoch": 0.3162935858803272, "grad_norm": 2.0848021507263184, "learning_rate": 3.864408248731567e-05, "loss": 4.369, "step": 5878 }, { "epoch": 0.3163473956091261, "grad_norm": 1.92995023727417, "learning_rate": 3.8640540987718296e-05, "loss": 4.2715, "step": 5879 }, { "epoch": 0.3164012053379251, "grad_norm": 1.5981454849243164, "learning_rate": 3.8636999098310954e-05, "loss": 4.5357, "step": 5880 }, { "epoch": 0.3164550150667241, "grad_norm": 2.2435429096221924, "learning_rate": 3.863345681919486e-05, "loss": 4.5234, "step": 5881 }, { "epoch": 0.31650882479552306, "grad_norm": 1.5240107774734497, "learning_rate": 3.8629914150471235e-05, "loss": 3.9221, "step": 5882 }, { "epoch": 0.316562634524322, "grad_norm": 1.7882808446884155, "learning_rate": 3.862637109224132e-05, "loss": 4.6792, "step": 5883 }, { "epoch": 0.31661644425312097, "grad_norm": 1.2318166494369507, "learning_rate": 3.862282764460638e-05, "loss": 4.6022, "step": 5884 }, { "epoch": 0.31667025398191995, "grad_norm": 2.437190055847168, "learning_rate": 3.861928380766766e-05, "loss": 3.9497, "step": 5885 }, { "epoch": 0.3167240637107189, "grad_norm": 1.4902008771896362, "learning_rate": 3.861573958152644e-05, "loss": 4.179, "step": 5886 }, { "epoch": 0.31677787343951785, "grad_norm": 1.6727137565612793, "learning_rate": 3.861219496628401e-05, "loss": 4.2588, "step": 5887 }, { "epoch": 0.31683168316831684, "grad_norm": 1.4551950693130493, "learning_rate": 3.8608649962041653e-05, "loss": 4.5517, "step": 5888 }, { "epoch": 0.3168854928971158, "grad_norm": 1.3587485551834106, "learning_rate": 3.8605104568900685e-05, "loss": 4.563, "step": 5889 }, { "epoch": 0.31693930262591474, "grad_norm": 1.4004886150360107, "learning_rate": 3.860155878696242e-05, "loss": 4.6523, "step": 5890 }, { "epoch": 0.3169931123547137, "grad_norm": 1.7263381481170654, "learning_rate": 3.8598012616328194e-05, "loss": 4.2456, "step": 5891 }, { "epoch": 0.3170469220835127, "grad_norm": 1.5751338005065918, "learning_rate": 3.859446605709934e-05, "loss": 4.4744, "step": 5892 }, { "epoch": 0.3171007318123117, "grad_norm": 2.530726194381714, "learning_rate": 3.859091910937721e-05, "loss": 4.1058, "step": 5893 }, { "epoch": 0.3171545415411106, "grad_norm": 1.6464306116104126, "learning_rate": 3.858737177326317e-05, "loss": 4.0714, "step": 5894 }, { "epoch": 0.3172083512699096, "grad_norm": 1.2931510210037231, "learning_rate": 3.858382404885859e-05, "loss": 4.4677, "step": 5895 }, { "epoch": 0.3172621609987086, "grad_norm": 2.1262905597686768, "learning_rate": 3.858027593626485e-05, "loss": 4.2518, "step": 5896 }, { "epoch": 0.31731597072750756, "grad_norm": 1.0619639158248901, "learning_rate": 3.857672743558335e-05, "loss": 4.4008, "step": 5897 }, { "epoch": 0.3173697804563065, "grad_norm": 1.3344918489456177, "learning_rate": 3.85731785469155e-05, "loss": 4.4651, "step": 5898 }, { "epoch": 0.31742359018510546, "grad_norm": 3.0580344200134277, "learning_rate": 3.856962927036272e-05, "loss": 4.3534, "step": 5899 }, { "epoch": 0.31747739991390445, "grad_norm": 2.719682216644287, "learning_rate": 3.856607960602643e-05, "loss": 4.4855, "step": 5900 }, { "epoch": 0.3175312096427034, "grad_norm": 1.4820700883865356, "learning_rate": 3.856252955400807e-05, "loss": 4.3543, "step": 5901 }, { "epoch": 0.31758501937150235, "grad_norm": 2.981558322906494, "learning_rate": 3.8558979114409096e-05, "loss": 4.3922, "step": 5902 }, { "epoch": 0.31763882910030133, "grad_norm": 1.2668867111206055, "learning_rate": 3.855542828733097e-05, "loss": 4.6777, "step": 5903 }, { "epoch": 0.3176926388291003, "grad_norm": 2.5367581844329834, "learning_rate": 3.855187707287517e-05, "loss": 4.5741, "step": 5904 }, { "epoch": 0.31774644855789924, "grad_norm": 2.138216495513916, "learning_rate": 3.854832547114315e-05, "loss": 4.4675, "step": 5905 }, { "epoch": 0.3178002582866982, "grad_norm": 2.502446413040161, "learning_rate": 3.8544773482236453e-05, "loss": 4.139, "step": 5906 }, { "epoch": 0.3178540680154972, "grad_norm": 1.661547303199768, "learning_rate": 3.854122110625655e-05, "loss": 4.5852, "step": 5907 }, { "epoch": 0.3179078777442962, "grad_norm": 1.7900124788284302, "learning_rate": 3.8537668343304975e-05, "loss": 4.5357, "step": 5908 }, { "epoch": 0.3179616874730951, "grad_norm": 1.8772914409637451, "learning_rate": 3.8534115193483245e-05, "loss": 4.6241, "step": 5909 }, { "epoch": 0.3180154972018941, "grad_norm": 1.6801373958587646, "learning_rate": 3.85305616568929e-05, "loss": 4.5725, "step": 5910 }, { "epoch": 0.3180693069306931, "grad_norm": 1.5677381753921509, "learning_rate": 3.8527007733635515e-05, "loss": 4.6781, "step": 5911 }, { "epoch": 0.31812311665949206, "grad_norm": 2.4118380546569824, "learning_rate": 3.852345342381262e-05, "loss": 4.3779, "step": 5912 }, { "epoch": 0.318176926388291, "grad_norm": 1.4305816888809204, "learning_rate": 3.851989872752579e-05, "loss": 4.4906, "step": 5913 }, { "epoch": 0.31823073611708996, "grad_norm": 1.9507135152816772, "learning_rate": 3.851634364487664e-05, "loss": 3.9486, "step": 5914 }, { "epoch": 0.31828454584588894, "grad_norm": 1.0757745504379272, "learning_rate": 3.851278817596673e-05, "loss": 4.6433, "step": 5915 }, { "epoch": 0.3183383555746879, "grad_norm": 2.124925136566162, "learning_rate": 3.850923232089768e-05, "loss": 4.6009, "step": 5916 }, { "epoch": 0.31839216530348685, "grad_norm": 1.266996145248413, "learning_rate": 3.850567607977111e-05, "loss": 4.4758, "step": 5917 }, { "epoch": 0.31844597503228583, "grad_norm": 2.6691908836364746, "learning_rate": 3.850211945268864e-05, "loss": 4.2292, "step": 5918 }, { "epoch": 0.3184997847610848, "grad_norm": 1.3329402208328247, "learning_rate": 3.8498562439751914e-05, "loss": 4.4457, "step": 5919 }, { "epoch": 0.3185535944898838, "grad_norm": 1.2320622205734253, "learning_rate": 3.849500504106258e-05, "loss": 4.6239, "step": 5920 }, { "epoch": 0.3186074042186827, "grad_norm": 1.8393787145614624, "learning_rate": 3.8491447256722294e-05, "loss": 4.381, "step": 5921 }, { "epoch": 0.3186612139474817, "grad_norm": 1.2512174844741821, "learning_rate": 3.848788908683275e-05, "loss": 4.8032, "step": 5922 }, { "epoch": 0.3187150236762807, "grad_norm": 1.5760964155197144, "learning_rate": 3.848433053149559e-05, "loss": 4.2326, "step": 5923 }, { "epoch": 0.31876883340507967, "grad_norm": 1.3839876651763916, "learning_rate": 3.848077159081255e-05, "loss": 4.6404, "step": 5924 }, { "epoch": 0.3188226431338786, "grad_norm": 2.9918055534362793, "learning_rate": 3.8477212264885306e-05, "loss": 4.2558, "step": 5925 }, { "epoch": 0.3188764528626776, "grad_norm": 1.3238800764083862, "learning_rate": 3.84736525538156e-05, "loss": 4.372, "step": 5926 }, { "epoch": 0.31893026259147655, "grad_norm": 2.1484198570251465, "learning_rate": 3.847009245770513e-05, "loss": 4.4474, "step": 5927 }, { "epoch": 0.3189840723202755, "grad_norm": 0.9770950078964233, "learning_rate": 3.846653197665565e-05, "loss": 4.5655, "step": 5928 }, { "epoch": 0.31903788204907446, "grad_norm": 0.995460033416748, "learning_rate": 3.8462971110768906e-05, "loss": 4.3892, "step": 5929 }, { "epoch": 0.31909169177787344, "grad_norm": 1.340610384941101, "learning_rate": 3.845940986014667e-05, "loss": 4.5526, "step": 5930 }, { "epoch": 0.3191455015066724, "grad_norm": 1.764818787574768, "learning_rate": 3.8455848224890686e-05, "loss": 4.6322, "step": 5931 }, { "epoch": 0.31919931123547135, "grad_norm": 2.389488697052002, "learning_rate": 3.845228620510276e-05, "loss": 4.1512, "step": 5932 }, { "epoch": 0.31925312096427033, "grad_norm": 1.0923619270324707, "learning_rate": 3.844872380088468e-05, "loss": 4.4761, "step": 5933 }, { "epoch": 0.3193069306930693, "grad_norm": 2.376838207244873, "learning_rate": 3.844516101233824e-05, "loss": 3.7406, "step": 5934 }, { "epoch": 0.3193607404218683, "grad_norm": 2.211886405944824, "learning_rate": 3.844159783956527e-05, "loss": 4.5008, "step": 5935 }, { "epoch": 0.3194145501506672, "grad_norm": 2.1935977935791016, "learning_rate": 3.843803428266758e-05, "loss": 4.1102, "step": 5936 }, { "epoch": 0.3194683598794662, "grad_norm": 1.737395167350769, "learning_rate": 3.8434470341747014e-05, "loss": 4.6122, "step": 5937 }, { "epoch": 0.3195221696082652, "grad_norm": 1.4976325035095215, "learning_rate": 3.8430906016905424e-05, "loss": 4.6228, "step": 5938 }, { "epoch": 0.31957597933706416, "grad_norm": 1.9357272386550903, "learning_rate": 3.842734130824466e-05, "loss": 4.6735, "step": 5939 }, { "epoch": 0.3196297890658631, "grad_norm": 2.0925779342651367, "learning_rate": 3.8423776215866595e-05, "loss": 4.6265, "step": 5940 }, { "epoch": 0.31968359879466207, "grad_norm": 1.3920869827270508, "learning_rate": 3.842021073987312e-05, "loss": 4.5842, "step": 5941 }, { "epoch": 0.31973740852346105, "grad_norm": 1.767632007598877, "learning_rate": 3.8416644880366114e-05, "loss": 4.8936, "step": 5942 }, { "epoch": 0.31979121825226003, "grad_norm": 2.0975303649902344, "learning_rate": 3.8413078637447485e-05, "loss": 4.0501, "step": 5943 }, { "epoch": 0.31984502798105896, "grad_norm": 2.5168159008026123, "learning_rate": 3.840951201121914e-05, "loss": 3.7944, "step": 5944 }, { "epoch": 0.31989883770985794, "grad_norm": 2.4772679805755615, "learning_rate": 3.840594500178302e-05, "loss": 4.4488, "step": 5945 }, { "epoch": 0.3199526474386569, "grad_norm": 1.7950657606124878, "learning_rate": 3.840237760924104e-05, "loss": 4.2101, "step": 5946 }, { "epoch": 0.32000645716745585, "grad_norm": 1.972762107849121, "learning_rate": 3.8398809833695153e-05, "loss": 4.458, "step": 5947 }, { "epoch": 0.32006026689625483, "grad_norm": 2.5178184509277344, "learning_rate": 3.8395241675247334e-05, "loss": 4.2484, "step": 5948 }, { "epoch": 0.3201140766250538, "grad_norm": 1.7916659116744995, "learning_rate": 3.839167313399952e-05, "loss": 4.3681, "step": 5949 }, { "epoch": 0.3201678863538528, "grad_norm": 2.0724613666534424, "learning_rate": 3.838810421005372e-05, "loss": 3.7511, "step": 5950 }, { "epoch": 0.3202216960826517, "grad_norm": 2.608760118484497, "learning_rate": 3.83845349035119e-05, "loss": 4.2485, "step": 5951 }, { "epoch": 0.3202755058114507, "grad_norm": 1.8656895160675049, "learning_rate": 3.838096521447609e-05, "loss": 4.3856, "step": 5952 }, { "epoch": 0.3203293155402497, "grad_norm": 2.401935338973999, "learning_rate": 3.8377395143048275e-05, "loss": 4.6945, "step": 5953 }, { "epoch": 0.32038312526904866, "grad_norm": 1.9996356964111328, "learning_rate": 3.8373824689330484e-05, "loss": 4.3382, "step": 5954 }, { "epoch": 0.3204369349978476, "grad_norm": 1.8577301502227783, "learning_rate": 3.837025385342475e-05, "loss": 4.5649, "step": 5955 }, { "epoch": 0.32049074472664657, "grad_norm": 1.5667228698730469, "learning_rate": 3.836668263543314e-05, "loss": 4.5183, "step": 5956 }, { "epoch": 0.32054455445544555, "grad_norm": 1.2833960056304932, "learning_rate": 3.8363111035457675e-05, "loss": 4.5124, "step": 5957 }, { "epoch": 0.32059836418424453, "grad_norm": 2.403235673904419, "learning_rate": 3.835953905360046e-05, "loss": 4.5737, "step": 5958 }, { "epoch": 0.32065217391304346, "grad_norm": 2.033900022506714, "learning_rate": 3.835596668996353e-05, "loss": 4.7916, "step": 5959 }, { "epoch": 0.32070598364184244, "grad_norm": 2.613910436630249, "learning_rate": 3.835239394464901e-05, "loss": 4.2866, "step": 5960 }, { "epoch": 0.3207597933706414, "grad_norm": 2.177612066268921, "learning_rate": 3.8348820817758976e-05, "loss": 4.1028, "step": 5961 }, { "epoch": 0.3208136030994404, "grad_norm": 2.9015822410583496, "learning_rate": 3.834524730939555e-05, "loss": 4.4902, "step": 5962 }, { "epoch": 0.32086741282823933, "grad_norm": 2.35746693611145, "learning_rate": 3.834167341966085e-05, "loss": 4.7791, "step": 5963 }, { "epoch": 0.3209212225570383, "grad_norm": 2.1354033946990967, "learning_rate": 3.8338099148657015e-05, "loss": 4.4794, "step": 5964 }, { "epoch": 0.3209750322858373, "grad_norm": 2.33495831489563, "learning_rate": 3.833452449648617e-05, "loss": 4.4934, "step": 5965 }, { "epoch": 0.3210288420146363, "grad_norm": 1.4114017486572266, "learning_rate": 3.833094946325049e-05, "loss": 4.4516, "step": 5966 }, { "epoch": 0.3210826517434352, "grad_norm": 1.4976475238800049, "learning_rate": 3.832737404905212e-05, "loss": 5.0905, "step": 5967 }, { "epoch": 0.3211364614722342, "grad_norm": 1.965991735458374, "learning_rate": 3.832379825399326e-05, "loss": 4.6886, "step": 5968 }, { "epoch": 0.32119027120103316, "grad_norm": 3.073484182357788, "learning_rate": 3.832022207817607e-05, "loss": 3.796, "step": 5969 }, { "epoch": 0.3212440809298321, "grad_norm": 2.552676200866699, "learning_rate": 3.8316645521702766e-05, "loss": 4.1927, "step": 5970 }, { "epoch": 0.32129789065863107, "grad_norm": 2.294508457183838, "learning_rate": 3.831306858467556e-05, "loss": 4.325, "step": 5971 }, { "epoch": 0.32135170038743005, "grad_norm": 2.424191474914551, "learning_rate": 3.830949126719664e-05, "loss": 4.0995, "step": 5972 }, { "epoch": 0.32140551011622903, "grad_norm": 1.3491917848587036, "learning_rate": 3.8305913569368274e-05, "loss": 4.7773, "step": 5973 }, { "epoch": 0.32145931984502796, "grad_norm": 2.0802769660949707, "learning_rate": 3.8302335491292686e-05, "loss": 4.0921, "step": 5974 }, { "epoch": 0.32151312957382694, "grad_norm": 1.9254817962646484, "learning_rate": 3.8298757033072126e-05, "loss": 4.2386, "step": 5975 }, { "epoch": 0.3215669393026259, "grad_norm": 1.3398734331130981, "learning_rate": 3.8295178194808855e-05, "loss": 4.6655, "step": 5976 }, { "epoch": 0.3216207490314249, "grad_norm": 1.538346529006958, "learning_rate": 3.829159897660516e-05, "loss": 4.4194, "step": 5977 }, { "epoch": 0.3216745587602238, "grad_norm": 1.4364489316940308, "learning_rate": 3.8288019378563305e-05, "loss": 4.5775, "step": 5978 }, { "epoch": 0.3217283684890228, "grad_norm": 1.7999696731567383, "learning_rate": 3.828443940078561e-05, "loss": 4.162, "step": 5979 }, { "epoch": 0.3217821782178218, "grad_norm": 1.1604143381118774, "learning_rate": 3.828085904337436e-05, "loss": 4.7036, "step": 5980 }, { "epoch": 0.32183598794662077, "grad_norm": 2.2010068893432617, "learning_rate": 3.827727830643188e-05, "loss": 4.2802, "step": 5981 }, { "epoch": 0.3218897976754197, "grad_norm": 1.4320755004882812, "learning_rate": 3.8273697190060496e-05, "loss": 4.3934, "step": 5982 }, { "epoch": 0.3219436074042187, "grad_norm": 1.7864818572998047, "learning_rate": 3.827011569436255e-05, "loss": 4.6286, "step": 5983 }, { "epoch": 0.32199741713301766, "grad_norm": 0.954317033290863, "learning_rate": 3.8266533819440396e-05, "loss": 4.8324, "step": 5984 }, { "epoch": 0.32205122686181664, "grad_norm": 2.349925994873047, "learning_rate": 3.8262951565396385e-05, "loss": 3.8055, "step": 5985 }, { "epoch": 0.32210503659061557, "grad_norm": 1.7720837593078613, "learning_rate": 3.8259368932332886e-05, "loss": 4.0715, "step": 5986 }, { "epoch": 0.32215884631941455, "grad_norm": 2.4565563201904297, "learning_rate": 3.8255785920352295e-05, "loss": 3.7926, "step": 5987 }, { "epoch": 0.32221265604821353, "grad_norm": 2.320812225341797, "learning_rate": 3.825220252955699e-05, "loss": 4.6235, "step": 5988 }, { "epoch": 0.32226646577701246, "grad_norm": 1.7956570386886597, "learning_rate": 3.824861876004938e-05, "loss": 4.2954, "step": 5989 }, { "epoch": 0.32232027550581144, "grad_norm": 1.9953521490097046, "learning_rate": 3.824503461193188e-05, "loss": 4.6746, "step": 5990 }, { "epoch": 0.3223740852346104, "grad_norm": 1.789602279663086, "learning_rate": 3.824145008530692e-05, "loss": 4.6685, "step": 5991 }, { "epoch": 0.3224278949634094, "grad_norm": 1.5265460014343262, "learning_rate": 3.8237865180276935e-05, "loss": 4.6125, "step": 5992 }, { "epoch": 0.3224817046922083, "grad_norm": 1.378718376159668, "learning_rate": 3.823427989694436e-05, "loss": 4.4089, "step": 5993 }, { "epoch": 0.3225355144210073, "grad_norm": 1.6334596872329712, "learning_rate": 3.823069423541167e-05, "loss": 4.6647, "step": 5994 }, { "epoch": 0.3225893241498063, "grad_norm": 1.8954110145568848, "learning_rate": 3.822710819578132e-05, "loss": 4.1878, "step": 5995 }, { "epoch": 0.32264313387860527, "grad_norm": 1.9983717203140259, "learning_rate": 3.8223521778155794e-05, "loss": 4.7082, "step": 5996 }, { "epoch": 0.3226969436074042, "grad_norm": 2.8155429363250732, "learning_rate": 3.8219934982637585e-05, "loss": 4.5336, "step": 5997 }, { "epoch": 0.3227507533362032, "grad_norm": 1.4329235553741455, "learning_rate": 3.821634780932919e-05, "loss": 4.2642, "step": 5998 }, { "epoch": 0.32280456306500216, "grad_norm": 1.5081636905670166, "learning_rate": 3.821276025833313e-05, "loss": 4.464, "step": 5999 }, { "epoch": 0.32285837279380114, "grad_norm": 2.1963324546813965, "learning_rate": 3.820917232975191e-05, "loss": 4.464, "step": 6000 }, { "epoch": 0.32291218252260007, "grad_norm": 2.086434841156006, "learning_rate": 3.820558402368807e-05, "loss": 4.202, "step": 6001 }, { "epoch": 0.32296599225139905, "grad_norm": 1.7468119859695435, "learning_rate": 3.820199534024417e-05, "loss": 4.5647, "step": 6002 }, { "epoch": 0.32301980198019803, "grad_norm": 1.8783658742904663, "learning_rate": 3.8198406279522736e-05, "loss": 4.4132, "step": 6003 }, { "epoch": 0.323073611708997, "grad_norm": 1.055688738822937, "learning_rate": 3.819481684162636e-05, "loss": 4.4596, "step": 6004 }, { "epoch": 0.32312742143779594, "grad_norm": 1.7786496877670288, "learning_rate": 3.819122702665762e-05, "loss": 4.4822, "step": 6005 }, { "epoch": 0.3231812311665949, "grad_norm": 2.6129214763641357, "learning_rate": 3.818763683471908e-05, "loss": 4.4001, "step": 6006 }, { "epoch": 0.3232350408953939, "grad_norm": 2.0149927139282227, "learning_rate": 3.818404626591334e-05, "loss": 4.2652, "step": 6007 }, { "epoch": 0.3232888506241929, "grad_norm": 1.9710890054702759, "learning_rate": 3.818045532034303e-05, "loss": 4.7882, "step": 6008 }, { "epoch": 0.3233426603529918, "grad_norm": 1.1750963926315308, "learning_rate": 3.8176863998110756e-05, "loss": 4.7702, "step": 6009 }, { "epoch": 0.3233964700817908, "grad_norm": 1.788608431816101, "learning_rate": 3.817327229931916e-05, "loss": 4.3891, "step": 6010 }, { "epoch": 0.32345027981058977, "grad_norm": 1.0886459350585938, "learning_rate": 3.816968022407086e-05, "loss": 4.6301, "step": 6011 }, { "epoch": 0.3235040895393887, "grad_norm": 1.1838278770446777, "learning_rate": 3.8166087772468527e-05, "loss": 4.6848, "step": 6012 }, { "epoch": 0.3235578992681877, "grad_norm": 1.488126516342163, "learning_rate": 3.8162494944614825e-05, "loss": 3.9382, "step": 6013 }, { "epoch": 0.32361170899698666, "grad_norm": 1.7238210439682007, "learning_rate": 3.8158901740612406e-05, "loss": 4.9329, "step": 6014 }, { "epoch": 0.32366551872578564, "grad_norm": 2.004840612411499, "learning_rate": 3.815530816056398e-05, "loss": 4.3237, "step": 6015 }, { "epoch": 0.32371932845458457, "grad_norm": 1.2998847961425781, "learning_rate": 3.815171420457222e-05, "loss": 4.3514, "step": 6016 }, { "epoch": 0.32377313818338355, "grad_norm": 1.2849156856536865, "learning_rate": 3.8148119872739855e-05, "loss": 4.6185, "step": 6017 }, { "epoch": 0.32382694791218253, "grad_norm": 1.655362606048584, "learning_rate": 3.8144525165169584e-05, "loss": 4.4881, "step": 6018 }, { "epoch": 0.3238807576409815, "grad_norm": 2.298292398452759, "learning_rate": 3.8140930081964134e-05, "loss": 4.3866, "step": 6019 }, { "epoch": 0.32393456736978044, "grad_norm": 2.618151903152466, "learning_rate": 3.813733462322625e-05, "loss": 4.0668, "step": 6020 }, { "epoch": 0.3239883770985794, "grad_norm": 2.4557979106903076, "learning_rate": 3.813373878905867e-05, "loss": 4.2441, "step": 6021 }, { "epoch": 0.3240421868273784, "grad_norm": 1.224327564239502, "learning_rate": 3.813014257956418e-05, "loss": 4.4439, "step": 6022 }, { "epoch": 0.3240959965561774, "grad_norm": 1.8001012802124023, "learning_rate": 3.8126545994845514e-05, "loss": 4.3749, "step": 6023 }, { "epoch": 0.3241498062849763, "grad_norm": 1.7087136507034302, "learning_rate": 3.8122949035005474e-05, "loss": 4.2011, "step": 6024 }, { "epoch": 0.3242036160137753, "grad_norm": 1.2271615266799927, "learning_rate": 3.811935170014685e-05, "loss": 4.4753, "step": 6025 }, { "epoch": 0.32425742574257427, "grad_norm": 0.9409238696098328, "learning_rate": 3.811575399037244e-05, "loss": 4.6462, "step": 6026 }, { "epoch": 0.32431123547137325, "grad_norm": 1.875493049621582, "learning_rate": 3.811215590578505e-05, "loss": 4.1635, "step": 6027 }, { "epoch": 0.3243650452001722, "grad_norm": 1.091260552406311, "learning_rate": 3.8108557446487525e-05, "loss": 4.683, "step": 6028 }, { "epoch": 0.32441885492897116, "grad_norm": 1.9750679731369019, "learning_rate": 3.810495861258268e-05, "loss": 4.2289, "step": 6029 }, { "epoch": 0.32447266465777014, "grad_norm": 1.3930679559707642, "learning_rate": 3.810135940417337e-05, "loss": 4.3721, "step": 6030 }, { "epoch": 0.3245264743865691, "grad_norm": 2.2778189182281494, "learning_rate": 3.8097759821362436e-05, "loss": 4.3161, "step": 6031 }, { "epoch": 0.32458028411536805, "grad_norm": 1.989937663078308, "learning_rate": 3.809415986425277e-05, "loss": 4.1481, "step": 6032 }, { "epoch": 0.324634093844167, "grad_norm": 2.0828373432159424, "learning_rate": 3.809055953294722e-05, "loss": 4.6698, "step": 6033 }, { "epoch": 0.324687903572966, "grad_norm": 1.7642841339111328, "learning_rate": 3.808695882754869e-05, "loss": 4.2441, "step": 6034 }, { "epoch": 0.32474171330176493, "grad_norm": 2.9796860218048096, "learning_rate": 3.808335774816009e-05, "loss": 4.0847, "step": 6035 }, { "epoch": 0.3247955230305639, "grad_norm": 1.6376307010650635, "learning_rate": 3.80797562948843e-05, "loss": 4.8816, "step": 6036 }, { "epoch": 0.3248493327593629, "grad_norm": 3.299987554550171, "learning_rate": 3.8076154467824266e-05, "loss": 4.3004, "step": 6037 }, { "epoch": 0.3249031424881619, "grad_norm": 1.0766180753707886, "learning_rate": 3.8072552267082906e-05, "loss": 4.5706, "step": 6038 }, { "epoch": 0.3249569522169608, "grad_norm": 0.9916957020759583, "learning_rate": 3.806894969276316e-05, "loss": 4.8547, "step": 6039 }, { "epoch": 0.3250107619457598, "grad_norm": 1.7394025325775146, "learning_rate": 3.8065346744967986e-05, "loss": 4.3105, "step": 6040 }, { "epoch": 0.32506457167455877, "grad_norm": 2.0389416217803955, "learning_rate": 3.8061743423800344e-05, "loss": 4.2795, "step": 6041 }, { "epoch": 0.32511838140335775, "grad_norm": 1.4880273342132568, "learning_rate": 3.80581397293632e-05, "loss": 4.8093, "step": 6042 }, { "epoch": 0.3251721911321567, "grad_norm": 2.78310489654541, "learning_rate": 3.805453566175955e-05, "loss": 4.1652, "step": 6043 }, { "epoch": 0.32522600086095566, "grad_norm": 1.5090997219085693, "learning_rate": 3.805093122109239e-05, "loss": 4.839, "step": 6044 }, { "epoch": 0.32527981058975464, "grad_norm": 3.0384316444396973, "learning_rate": 3.8047326407464707e-05, "loss": 4.461, "step": 6045 }, { "epoch": 0.3253336203185536, "grad_norm": 1.511658787727356, "learning_rate": 3.804372122097953e-05, "loss": 4.5755, "step": 6046 }, { "epoch": 0.32538743004735254, "grad_norm": 1.2712432146072388, "learning_rate": 3.8040115661739885e-05, "loss": 4.6682, "step": 6047 }, { "epoch": 0.3254412397761515, "grad_norm": 1.5371744632720947, "learning_rate": 3.803650972984882e-05, "loss": 4.217, "step": 6048 }, { "epoch": 0.3254950495049505, "grad_norm": 2.3219096660614014, "learning_rate": 3.803290342540936e-05, "loss": 4.3303, "step": 6049 }, { "epoch": 0.3255488592337495, "grad_norm": 1.4562058448791504, "learning_rate": 3.8029296748524575e-05, "loss": 4.7578, "step": 6050 }, { "epoch": 0.3256026689625484, "grad_norm": 1.6717959642410278, "learning_rate": 3.802568969929753e-05, "loss": 4.4448, "step": 6051 }, { "epoch": 0.3256564786913474, "grad_norm": 1.507275104522705, "learning_rate": 3.802208227783132e-05, "loss": 4.3041, "step": 6052 }, { "epoch": 0.3257102884201464, "grad_norm": 2.3588900566101074, "learning_rate": 3.8018474484229014e-05, "loss": 4.5636, "step": 6053 }, { "epoch": 0.3257640981489453, "grad_norm": 2.0326175689697266, "learning_rate": 3.8014866318593724e-05, "loss": 4.6447, "step": 6054 }, { "epoch": 0.3258179078777443, "grad_norm": 1.7306312322616577, "learning_rate": 3.8011257781028564e-05, "loss": 4.5026, "step": 6055 }, { "epoch": 0.32587171760654327, "grad_norm": 1.9858206510543823, "learning_rate": 3.8007648871636655e-05, "loss": 4.5061, "step": 6056 }, { "epoch": 0.32592552733534225, "grad_norm": 1.5936214923858643, "learning_rate": 3.8004039590521126e-05, "loss": 4.7924, "step": 6057 }, { "epoch": 0.3259793370641412, "grad_norm": 1.206916093826294, "learning_rate": 3.800042993778511e-05, "loss": 4.7302, "step": 6058 }, { "epoch": 0.32603314679294015, "grad_norm": 1.4539904594421387, "learning_rate": 3.799681991353179e-05, "loss": 4.7588, "step": 6059 }, { "epoch": 0.32608695652173914, "grad_norm": 2.2628209590911865, "learning_rate": 3.79932095178643e-05, "loss": 4.4045, "step": 6060 }, { "epoch": 0.3261407662505381, "grad_norm": 1.4845359325408936, "learning_rate": 3.798959875088584e-05, "loss": 3.979, "step": 6061 }, { "epoch": 0.32619457597933704, "grad_norm": 3.006537675857544, "learning_rate": 3.7985987612699585e-05, "loss": 4.0246, "step": 6062 }, { "epoch": 0.326248385708136, "grad_norm": 1.2248904705047607, "learning_rate": 3.7982376103408735e-05, "loss": 4.4764, "step": 6063 }, { "epoch": 0.326302195436935, "grad_norm": 2.44496488571167, "learning_rate": 3.7978764223116486e-05, "loss": 3.8874, "step": 6064 }, { "epoch": 0.326356005165734, "grad_norm": 1.2509632110595703, "learning_rate": 3.7975151971926066e-05, "loss": 4.705, "step": 6065 }, { "epoch": 0.3264098148945329, "grad_norm": 1.9885681867599487, "learning_rate": 3.79715393499407e-05, "loss": 4.548, "step": 6066 }, { "epoch": 0.3264636246233319, "grad_norm": 2.264915943145752, "learning_rate": 3.796792635726364e-05, "loss": 4.5031, "step": 6067 }, { "epoch": 0.3265174343521309, "grad_norm": 1.5156354904174805, "learning_rate": 3.796431299399811e-05, "loss": 4.5331, "step": 6068 }, { "epoch": 0.32657124408092986, "grad_norm": 2.149381637573242, "learning_rate": 3.796069926024739e-05, "loss": 4.2305, "step": 6069 }, { "epoch": 0.3266250538097288, "grad_norm": 1.8303738832473755, "learning_rate": 3.795708515611475e-05, "loss": 4.4979, "step": 6070 }, { "epoch": 0.32667886353852776, "grad_norm": 1.7314127683639526, "learning_rate": 3.795347068170346e-05, "loss": 4.391, "step": 6071 }, { "epoch": 0.32673267326732675, "grad_norm": 2.439548969268799, "learning_rate": 3.7949855837116825e-05, "loss": 4.4371, "step": 6072 }, { "epoch": 0.3267864829961257, "grad_norm": 2.483753204345703, "learning_rate": 3.7946240622458135e-05, "loss": 4.133, "step": 6073 }, { "epoch": 0.32684029272492465, "grad_norm": 1.436879277229309, "learning_rate": 3.7942625037830714e-05, "loss": 4.7285, "step": 6074 }, { "epoch": 0.32689410245372363, "grad_norm": 2.171264886856079, "learning_rate": 3.793900908333788e-05, "loss": 4.1014, "step": 6075 }, { "epoch": 0.3269479121825226, "grad_norm": 2.019706964492798, "learning_rate": 3.793539275908297e-05, "loss": 4.4624, "step": 6076 }, { "epoch": 0.32700172191132154, "grad_norm": 2.046428680419922, "learning_rate": 3.793177606516932e-05, "loss": 4.6777, "step": 6077 }, { "epoch": 0.3270555316401205, "grad_norm": 2.5257086753845215, "learning_rate": 3.79281590017003e-05, "loss": 4.2277, "step": 6078 }, { "epoch": 0.3271093413689195, "grad_norm": 2.1256260871887207, "learning_rate": 3.792454156877927e-05, "loss": 4.5494, "step": 6079 }, { "epoch": 0.3271631510977185, "grad_norm": 2.345693826675415, "learning_rate": 3.79209237665096e-05, "loss": 3.7681, "step": 6080 }, { "epoch": 0.3272169608265174, "grad_norm": 0.9899254441261292, "learning_rate": 3.791730559499468e-05, "loss": 4.4018, "step": 6081 }, { "epoch": 0.3272707705553164, "grad_norm": 1.7453579902648926, "learning_rate": 3.791368705433791e-05, "loss": 4.3959, "step": 6082 }, { "epoch": 0.3273245802841154, "grad_norm": 1.6604537963867188, "learning_rate": 3.7910068144642694e-05, "loss": 4.6805, "step": 6083 }, { "epoch": 0.32737839001291436, "grad_norm": 1.6198142766952515, "learning_rate": 3.790644886601247e-05, "loss": 4.4518, "step": 6084 }, { "epoch": 0.3274321997417133, "grad_norm": 1.4939734935760498, "learning_rate": 3.790282921855064e-05, "loss": 4.2346, "step": 6085 }, { "epoch": 0.32748600947051226, "grad_norm": 2.069533109664917, "learning_rate": 3.789920920236065e-05, "loss": 4.2989, "step": 6086 }, { "epoch": 0.32753981919931124, "grad_norm": 1.4788298606872559, "learning_rate": 3.7895588817545966e-05, "loss": 4.4872, "step": 6087 }, { "epoch": 0.3275936289281102, "grad_norm": 1.524762749671936, "learning_rate": 3.789196806421004e-05, "loss": 4.7184, "step": 6088 }, { "epoch": 0.32764743865690915, "grad_norm": 1.3633687496185303, "learning_rate": 3.788834694245633e-05, "loss": 4.6078, "step": 6089 }, { "epoch": 0.32770124838570813, "grad_norm": 2.3932368755340576, "learning_rate": 3.7884725452388346e-05, "loss": 4.193, "step": 6090 }, { "epoch": 0.3277550581145071, "grad_norm": 1.51537024974823, "learning_rate": 3.7881103594109553e-05, "loss": 4.3588, "step": 6091 }, { "epoch": 0.3278088678433061, "grad_norm": 2.151519775390625, "learning_rate": 3.787748136772347e-05, "loss": 4.504, "step": 6092 }, { "epoch": 0.327862677572105, "grad_norm": 1.7048269510269165, "learning_rate": 3.78738587733336e-05, "loss": 4.3211, "step": 6093 }, { "epoch": 0.327916487300904, "grad_norm": 1.976269245147705, "learning_rate": 3.7870235811043484e-05, "loss": 4.4434, "step": 6094 }, { "epoch": 0.327970297029703, "grad_norm": 2.0285260677337646, "learning_rate": 3.786661248095663e-05, "loss": 4.3626, "step": 6095 }, { "epoch": 0.3280241067585019, "grad_norm": 2.318601369857788, "learning_rate": 3.786298878317661e-05, "loss": 3.9474, "step": 6096 }, { "epoch": 0.3280779164873009, "grad_norm": 1.4919482469558716, "learning_rate": 3.7859364717806965e-05, "loss": 4.3149, "step": 6097 }, { "epoch": 0.3281317262160999, "grad_norm": 2.701831102371216, "learning_rate": 3.785574028495127e-05, "loss": 3.3979, "step": 6098 }, { "epoch": 0.32818553594489885, "grad_norm": 1.7172653675079346, "learning_rate": 3.785211548471308e-05, "loss": 4.2736, "step": 6099 }, { "epoch": 0.3282393456736978, "grad_norm": 2.3238303661346436, "learning_rate": 3.784849031719601e-05, "loss": 4.5315, "step": 6100 }, { "epoch": 0.32829315540249676, "grad_norm": 2.346338987350464, "learning_rate": 3.784486478250364e-05, "loss": 4.3227, "step": 6101 }, { "epoch": 0.32834696513129574, "grad_norm": 2.022812604904175, "learning_rate": 3.784123888073959e-05, "loss": 4.6323, "step": 6102 }, { "epoch": 0.3284007748600947, "grad_norm": 2.537001132965088, "learning_rate": 3.7837612612007465e-05, "loss": 3.8377, "step": 6103 }, { "epoch": 0.32845458458889365, "grad_norm": 1.0762360095977783, "learning_rate": 3.7833985976410904e-05, "loss": 4.598, "step": 6104 }, { "epoch": 0.32850839431769263, "grad_norm": 1.7775603532791138, "learning_rate": 3.783035897405354e-05, "loss": 3.7686, "step": 6105 }, { "epoch": 0.3285622040464916, "grad_norm": 1.834945559501648, "learning_rate": 3.782673160503903e-05, "loss": 4.2166, "step": 6106 }, { "epoch": 0.3286160137752906, "grad_norm": 1.8404384851455688, "learning_rate": 3.782310386947103e-05, "loss": 4.5566, "step": 6107 }, { "epoch": 0.3286698235040895, "grad_norm": 1.7700045108795166, "learning_rate": 3.78194757674532e-05, "loss": 4.7805, "step": 6108 }, { "epoch": 0.3287236332328885, "grad_norm": 1.2570576667785645, "learning_rate": 3.781584729908925e-05, "loss": 4.881, "step": 6109 }, { "epoch": 0.3287774429616875, "grad_norm": 2.288780927658081, "learning_rate": 3.781221846448285e-05, "loss": 4.1291, "step": 6110 }, { "epoch": 0.32883125269048646, "grad_norm": 2.6101415157318115, "learning_rate": 3.780858926373771e-05, "loss": 3.946, "step": 6111 }, { "epoch": 0.3288850624192854, "grad_norm": 1.712665319442749, "learning_rate": 3.780495969695753e-05, "loss": 4.5594, "step": 6112 }, { "epoch": 0.32893887214808437, "grad_norm": 2.1438798904418945, "learning_rate": 3.7801329764246054e-05, "loss": 4.0503, "step": 6113 }, { "epoch": 0.32899268187688335, "grad_norm": 1.8715732097625732, "learning_rate": 3.779769946570699e-05, "loss": 4.7819, "step": 6114 }, { "epoch": 0.32904649160568233, "grad_norm": 1.622451663017273, "learning_rate": 3.7794068801444106e-05, "loss": 4.4496, "step": 6115 }, { "epoch": 0.32910030133448126, "grad_norm": 2.016531229019165, "learning_rate": 3.779043777156115e-05, "loss": 3.8988, "step": 6116 }, { "epoch": 0.32915411106328024, "grad_norm": 2.6631367206573486, "learning_rate": 3.7786806376161876e-05, "loss": 4.2904, "step": 6117 }, { "epoch": 0.3292079207920792, "grad_norm": 3.3285768032073975, "learning_rate": 3.778317461535008e-05, "loss": 4.5041, "step": 6118 }, { "epoch": 0.32926173052087815, "grad_norm": 1.06769859790802, "learning_rate": 3.777954248922952e-05, "loss": 4.7746, "step": 6119 }, { "epoch": 0.32931554024967713, "grad_norm": 2.1523690223693848, "learning_rate": 3.777590999790403e-05, "loss": 4.6625, "step": 6120 }, { "epoch": 0.3293693499784761, "grad_norm": 2.085893154144287, "learning_rate": 3.777227714147739e-05, "loss": 4.3297, "step": 6121 }, { "epoch": 0.3294231597072751, "grad_norm": 1.8960758447647095, "learning_rate": 3.776864392005341e-05, "loss": 4.4386, "step": 6122 }, { "epoch": 0.329476969436074, "grad_norm": 1.155548334121704, "learning_rate": 3.776501033373594e-05, "loss": 4.7482, "step": 6123 }, { "epoch": 0.329530779164873, "grad_norm": 1.803748369216919, "learning_rate": 3.7761376382628806e-05, "loss": 4.6133, "step": 6124 }, { "epoch": 0.329584588893672, "grad_norm": 1.697087049484253, "learning_rate": 3.7757742066835854e-05, "loss": 4.6849, "step": 6125 }, { "epoch": 0.32963839862247096, "grad_norm": 1.2762634754180908, "learning_rate": 3.7754107386460955e-05, "loss": 4.55, "step": 6126 }, { "epoch": 0.3296922083512699, "grad_norm": 1.6591343879699707, "learning_rate": 3.775047234160797e-05, "loss": 4.194, "step": 6127 }, { "epoch": 0.32974601808006887, "grad_norm": 2.923739433288574, "learning_rate": 3.774683693238078e-05, "loss": 3.9055, "step": 6128 }, { "epoch": 0.32979982780886785, "grad_norm": 1.94625723361969, "learning_rate": 3.774320115888328e-05, "loss": 4.0187, "step": 6129 }, { "epoch": 0.32985363753766683, "grad_norm": 1.648091197013855, "learning_rate": 3.773956502121936e-05, "loss": 4.3234, "step": 6130 }, { "epoch": 0.32990744726646576, "grad_norm": 0.9295656085014343, "learning_rate": 3.773592851949294e-05, "loss": 4.4503, "step": 6131 }, { "epoch": 0.32996125699526474, "grad_norm": 1.7746210098266602, "learning_rate": 3.7732291653807934e-05, "loss": 4.5562, "step": 6132 }, { "epoch": 0.3300150667240637, "grad_norm": 2.6370787620544434, "learning_rate": 3.7728654424268284e-05, "loss": 4.0421, "step": 6133 }, { "epoch": 0.3300688764528627, "grad_norm": 2.489013671875, "learning_rate": 3.7725016830977925e-05, "loss": 4.7379, "step": 6134 }, { "epoch": 0.33012268618166163, "grad_norm": 1.3278969526290894, "learning_rate": 3.7721378874040804e-05, "loss": 4.8397, "step": 6135 }, { "epoch": 0.3301764959104606, "grad_norm": 2.605375289916992, "learning_rate": 3.7717740553560896e-05, "loss": 3.9829, "step": 6136 }, { "epoch": 0.3302303056392596, "grad_norm": 2.6053073406219482, "learning_rate": 3.771410186964217e-05, "loss": 4.0704, "step": 6137 }, { "epoch": 0.3302841153680585, "grad_norm": 1.1731594800949097, "learning_rate": 3.771046282238861e-05, "loss": 4.7509, "step": 6138 }, { "epoch": 0.3303379250968575, "grad_norm": 2.0727689266204834, "learning_rate": 3.770682341190422e-05, "loss": 4.0809, "step": 6139 }, { "epoch": 0.3303917348256565, "grad_norm": 3.5187480449676514, "learning_rate": 3.770318363829298e-05, "loss": 4.1257, "step": 6140 }, { "epoch": 0.33044554455445546, "grad_norm": 3.256829261779785, "learning_rate": 3.769954350165893e-05, "loss": 3.9325, "step": 6141 }, { "epoch": 0.3304993542832544, "grad_norm": 1.8503838777542114, "learning_rate": 3.769590300210607e-05, "loss": 4.6854, "step": 6142 }, { "epoch": 0.33055316401205337, "grad_norm": 1.5551522970199585, "learning_rate": 3.769226213973847e-05, "loss": 4.5732, "step": 6143 }, { "epoch": 0.33060697374085235, "grad_norm": 1.758212924003601, "learning_rate": 3.768862091466014e-05, "loss": 4.665, "step": 6144 }, { "epoch": 0.33066078346965133, "grad_norm": 1.9164533615112305, "learning_rate": 3.768497932697515e-05, "loss": 4.3681, "step": 6145 }, { "epoch": 0.33071459319845026, "grad_norm": 1.9038382768630981, "learning_rate": 3.768133737678758e-05, "loss": 4.4641, "step": 6146 }, { "epoch": 0.33076840292724924, "grad_norm": 1.8345140218734741, "learning_rate": 3.767769506420149e-05, "loss": 4.0825, "step": 6147 }, { "epoch": 0.3308222126560482, "grad_norm": 2.5528628826141357, "learning_rate": 3.767405238932098e-05, "loss": 4.3187, "step": 6148 }, { "epoch": 0.3308760223848472, "grad_norm": 2.071958541870117, "learning_rate": 3.767040935225013e-05, "loss": 4.4062, "step": 6149 }, { "epoch": 0.3309298321136461, "grad_norm": 2.3161473274230957, "learning_rate": 3.7666765953093074e-05, "loss": 4.3646, "step": 6150 }, { "epoch": 0.3309836418424451, "grad_norm": 1.856399655342102, "learning_rate": 3.766312219195392e-05, "loss": 4.4001, "step": 6151 }, { "epoch": 0.3310374515712441, "grad_norm": 2.4491965770721436, "learning_rate": 3.765947806893678e-05, "loss": 4.8806, "step": 6152 }, { "epoch": 0.33109126130004307, "grad_norm": 1.7828348875045776, "learning_rate": 3.765583358414582e-05, "loss": 4.1777, "step": 6153 }, { "epoch": 0.331145071028842, "grad_norm": 1.9813889265060425, "learning_rate": 3.765218873768516e-05, "loss": 4.2335, "step": 6154 }, { "epoch": 0.331198880757641, "grad_norm": 2.1469638347625732, "learning_rate": 3.764854352965899e-05, "loss": 4.3857, "step": 6155 }, { "epoch": 0.33125269048643996, "grad_norm": 0.9080457091331482, "learning_rate": 3.764489796017146e-05, "loss": 4.7945, "step": 6156 }, { "epoch": 0.33130650021523894, "grad_norm": 1.0453847646713257, "learning_rate": 3.764125202932676e-05, "loss": 4.656, "step": 6157 }, { "epoch": 0.33136030994403787, "grad_norm": 2.271423816680908, "learning_rate": 3.763760573722907e-05, "loss": 4.6454, "step": 6158 }, { "epoch": 0.33141411967283685, "grad_norm": 1.9913434982299805, "learning_rate": 3.763395908398261e-05, "loss": 3.8968, "step": 6159 }, { "epoch": 0.33146792940163583, "grad_norm": 1.329020619392395, "learning_rate": 3.763031206969158e-05, "loss": 4.41, "step": 6160 }, { "epoch": 0.33152173913043476, "grad_norm": 1.8194687366485596, "learning_rate": 3.7626664694460194e-05, "loss": 4.6989, "step": 6161 }, { "epoch": 0.33157554885923374, "grad_norm": 1.7903974056243896, "learning_rate": 3.762301695839271e-05, "loss": 4.5991, "step": 6162 }, { "epoch": 0.3316293585880327, "grad_norm": 1.1526885032653809, "learning_rate": 3.761936886159333e-05, "loss": 4.4479, "step": 6163 }, { "epoch": 0.3316831683168317, "grad_norm": 2.7186381816864014, "learning_rate": 3.7615720404166346e-05, "loss": 4.0833, "step": 6164 }, { "epoch": 0.3317369780456306, "grad_norm": 1.1942087411880493, "learning_rate": 3.7612071586216e-05, "loss": 4.6896, "step": 6165 }, { "epoch": 0.3317907877744296, "grad_norm": 1.694182276725769, "learning_rate": 3.7608422407846565e-05, "loss": 4.6651, "step": 6166 }, { "epoch": 0.3318445975032286, "grad_norm": 1.4018014669418335, "learning_rate": 3.760477286916234e-05, "loss": 4.5689, "step": 6167 }, { "epoch": 0.33189840723202757, "grad_norm": 2.0174179077148438, "learning_rate": 3.7601122970267596e-05, "loss": 4.3228, "step": 6168 }, { "epoch": 0.3319522169608265, "grad_norm": 1.437204122543335, "learning_rate": 3.759747271126667e-05, "loss": 4.681, "step": 6169 }, { "epoch": 0.3320060266896255, "grad_norm": 2.517345905303955, "learning_rate": 3.759382209226385e-05, "loss": 4.0855, "step": 6170 }, { "epoch": 0.33205983641842446, "grad_norm": 2.475695848464966, "learning_rate": 3.759017111336346e-05, "loss": 4.333, "step": 6171 }, { "epoch": 0.33211364614722344, "grad_norm": 1.5793622732162476, "learning_rate": 3.758651977466985e-05, "loss": 4.8011, "step": 6172 }, { "epoch": 0.33216745587602237, "grad_norm": 1.4159965515136719, "learning_rate": 3.758286807628736e-05, "loss": 4.605, "step": 6173 }, { "epoch": 0.33222126560482135, "grad_norm": 1.5628011226654053, "learning_rate": 3.757921601832034e-05, "loss": 4.6095, "step": 6174 }, { "epoch": 0.33227507533362033, "grad_norm": 1.4185658693313599, "learning_rate": 3.757556360087316e-05, "loss": 4.254, "step": 6175 }, { "epoch": 0.3323288850624193, "grad_norm": 2.0687642097473145, "learning_rate": 3.757191082405019e-05, "loss": 4.4727, "step": 6176 }, { "epoch": 0.33238269479121824, "grad_norm": 1.1297924518585205, "learning_rate": 3.756825768795583e-05, "loss": 4.6664, "step": 6177 }, { "epoch": 0.3324365045200172, "grad_norm": 1.689344048500061, "learning_rate": 3.756460419269447e-05, "loss": 4.2149, "step": 6178 }, { "epoch": 0.3324903142488162, "grad_norm": 1.3934673070907593, "learning_rate": 3.7560950338370524e-05, "loss": 4.4965, "step": 6179 }, { "epoch": 0.3325441239776152, "grad_norm": 1.7642747163772583, "learning_rate": 3.75572961250884e-05, "loss": 4.3443, "step": 6180 }, { "epoch": 0.3325979337064141, "grad_norm": 1.83952796459198, "learning_rate": 3.755364155295252e-05, "loss": 4.4661, "step": 6181 }, { "epoch": 0.3326517434352131, "grad_norm": 1.6101988554000854, "learning_rate": 3.754998662206733e-05, "loss": 4.7463, "step": 6182 }, { "epoch": 0.33270555316401207, "grad_norm": 1.2896714210510254, "learning_rate": 3.754633133253729e-05, "loss": 4.4187, "step": 6183 }, { "epoch": 0.332759362892811, "grad_norm": 1.8317971229553223, "learning_rate": 3.7542675684466834e-05, "loss": 4.5182, "step": 6184 }, { "epoch": 0.33281317262161, "grad_norm": 2.662795305252075, "learning_rate": 3.7539019677960454e-05, "loss": 4.9251, "step": 6185 }, { "epoch": 0.33286698235040896, "grad_norm": 1.3557051420211792, "learning_rate": 3.753536331312261e-05, "loss": 4.1096, "step": 6186 }, { "epoch": 0.33292079207920794, "grad_norm": 3.2434170246124268, "learning_rate": 3.753170659005779e-05, "loss": 3.7862, "step": 6187 }, { "epoch": 0.33297460180800686, "grad_norm": 1.8835057020187378, "learning_rate": 3.752804950887052e-05, "loss": 4.2521, "step": 6188 }, { "epoch": 0.33302841153680585, "grad_norm": 1.798918604850769, "learning_rate": 3.752439206966528e-05, "loss": 4.3495, "step": 6189 }, { "epoch": 0.3330822212656048, "grad_norm": 1.2837845087051392, "learning_rate": 3.75207342725466e-05, "loss": 4.5357, "step": 6190 }, { "epoch": 0.3331360309944038, "grad_norm": 1.2541905641555786, "learning_rate": 3.7517076117619024e-05, "loss": 4.523, "step": 6191 }, { "epoch": 0.33318984072320273, "grad_norm": 1.3804126977920532, "learning_rate": 3.751341760498706e-05, "loss": 4.5775, "step": 6192 }, { "epoch": 0.3332436504520017, "grad_norm": 1.9624642133712769, "learning_rate": 3.75097587347553e-05, "loss": 4.7131, "step": 6193 }, { "epoch": 0.3332974601808007, "grad_norm": 1.5040769577026367, "learning_rate": 3.7506099507028265e-05, "loss": 4.5921, "step": 6194 }, { "epoch": 0.3333512699095997, "grad_norm": 1.4291486740112305, "learning_rate": 3.7502439921910547e-05, "loss": 4.6408, "step": 6195 }, { "epoch": 0.3334050796383986, "grad_norm": 1.9947264194488525, "learning_rate": 3.749877997950673e-05, "loss": 4.3549, "step": 6196 }, { "epoch": 0.3334588893671976, "grad_norm": 1.5835572481155396, "learning_rate": 3.7495119679921395e-05, "loss": 4.4479, "step": 6197 }, { "epoch": 0.33351269909599657, "grad_norm": 1.3847965002059937, "learning_rate": 3.749145902325915e-05, "loss": 4.5921, "step": 6198 }, { "epoch": 0.33356650882479555, "grad_norm": 1.3775475025177002, "learning_rate": 3.7487798009624596e-05, "loss": 4.665, "step": 6199 }, { "epoch": 0.3336203185535945, "grad_norm": 1.3896105289459229, "learning_rate": 3.748413663912237e-05, "loss": 4.0911, "step": 6200 }, { "epoch": 0.33367412828239346, "grad_norm": 1.716955542564392, "learning_rate": 3.748047491185711e-05, "loss": 4.5305, "step": 6201 }, { "epoch": 0.33372793801119244, "grad_norm": 2.2189583778381348, "learning_rate": 3.7476812827933424e-05, "loss": 4.431, "step": 6202 }, { "epoch": 0.33378174773999136, "grad_norm": 1.447560429573059, "learning_rate": 3.747315038745599e-05, "loss": 4.786, "step": 6203 }, { "epoch": 0.33383555746879034, "grad_norm": 2.7070698738098145, "learning_rate": 3.746948759052947e-05, "loss": 4.0176, "step": 6204 }, { "epoch": 0.3338893671975893, "grad_norm": 2.783984661102295, "learning_rate": 3.746582443725854e-05, "loss": 3.7702, "step": 6205 }, { "epoch": 0.3339431769263883, "grad_norm": 2.0949535369873047, "learning_rate": 3.746216092774787e-05, "loss": 4.4587, "step": 6206 }, { "epoch": 0.33399698665518723, "grad_norm": 1.2611031532287598, "learning_rate": 3.745849706210216e-05, "loss": 4.6983, "step": 6207 }, { "epoch": 0.3340507963839862, "grad_norm": 1.5156726837158203, "learning_rate": 3.745483284042612e-05, "loss": 4.6502, "step": 6208 }, { "epoch": 0.3341046061127852, "grad_norm": 1.9495664834976196, "learning_rate": 3.745116826282444e-05, "loss": 4.0781, "step": 6209 }, { "epoch": 0.3341584158415842, "grad_norm": 1.6906081438064575, "learning_rate": 3.7447503329401875e-05, "loss": 4.1603, "step": 6210 }, { "epoch": 0.3342122255703831, "grad_norm": 2.516383647918701, "learning_rate": 3.744383804026315e-05, "loss": 4.2713, "step": 6211 }, { "epoch": 0.3342660352991821, "grad_norm": 1.4810813665390015, "learning_rate": 3.744017239551299e-05, "loss": 4.6691, "step": 6212 }, { "epoch": 0.33431984502798107, "grad_norm": 2.111518383026123, "learning_rate": 3.743650639525617e-05, "loss": 4.4603, "step": 6213 }, { "epoch": 0.33437365475678005, "grad_norm": 1.8539215326309204, "learning_rate": 3.743284003959745e-05, "loss": 4.407, "step": 6214 }, { "epoch": 0.334427464485579, "grad_norm": 1.326616883277893, "learning_rate": 3.742917332864159e-05, "loss": 4.5553, "step": 6215 }, { "epoch": 0.33448127421437795, "grad_norm": 2.791229009628296, "learning_rate": 3.74255062624934e-05, "loss": 3.6747, "step": 6216 }, { "epoch": 0.33453508394317694, "grad_norm": 1.2956784963607788, "learning_rate": 3.742183884125766e-05, "loss": 4.3721, "step": 6217 }, { "epoch": 0.3345888936719759, "grad_norm": 1.160665512084961, "learning_rate": 3.741817106503917e-05, "loss": 4.6576, "step": 6218 }, { "epoch": 0.33464270340077484, "grad_norm": 1.0760152339935303, "learning_rate": 3.741450293394276e-05, "loss": 4.6269, "step": 6219 }, { "epoch": 0.3346965131295738, "grad_norm": 1.6462475061416626, "learning_rate": 3.741083444807324e-05, "loss": 4.7892, "step": 6220 }, { "epoch": 0.3347503228583728, "grad_norm": 2.0498056411743164, "learning_rate": 3.740716560753545e-05, "loss": 4.7065, "step": 6221 }, { "epoch": 0.3348041325871718, "grad_norm": 2.555759906768799, "learning_rate": 3.7403496412434245e-05, "loss": 4.2147, "step": 6222 }, { "epoch": 0.3348579423159707, "grad_norm": 1.9174110889434814, "learning_rate": 3.7399826862874474e-05, "loss": 4.4909, "step": 6223 }, { "epoch": 0.3349117520447697, "grad_norm": 1.9321885108947754, "learning_rate": 3.739615695896101e-05, "loss": 4.5682, "step": 6224 }, { "epoch": 0.3349655617735687, "grad_norm": 1.0568108558654785, "learning_rate": 3.739248670079871e-05, "loss": 4.5181, "step": 6225 }, { "epoch": 0.3350193715023676, "grad_norm": 2.5200889110565186, "learning_rate": 3.7388816088492474e-05, "loss": 3.8052, "step": 6226 }, { "epoch": 0.3350731812311666, "grad_norm": 1.6889232397079468, "learning_rate": 3.7385145122147205e-05, "loss": 4.2456, "step": 6227 }, { "epoch": 0.33512699095996556, "grad_norm": 1.4296445846557617, "learning_rate": 3.738147380186779e-05, "loss": 4.8414, "step": 6228 }, { "epoch": 0.33518080068876455, "grad_norm": 1.52876615524292, "learning_rate": 3.737780212775916e-05, "loss": 4.6139, "step": 6229 }, { "epoch": 0.33523461041756347, "grad_norm": 0.9554725289344788, "learning_rate": 3.737413009992623e-05, "loss": 4.6939, "step": 6230 }, { "epoch": 0.33528842014636245, "grad_norm": 1.856410264968872, "learning_rate": 3.737045771847396e-05, "loss": 4.2759, "step": 6231 }, { "epoch": 0.33534222987516143, "grad_norm": 1.4063928127288818, "learning_rate": 3.7366784983507274e-05, "loss": 4.4981, "step": 6232 }, { "epoch": 0.3353960396039604, "grad_norm": 1.9204680919647217, "learning_rate": 3.736311189513113e-05, "loss": 4.4623, "step": 6233 }, { "epoch": 0.33544984933275934, "grad_norm": 1.6874010562896729, "learning_rate": 3.73594384534505e-05, "loss": 4.489, "step": 6234 }, { "epoch": 0.3355036590615583, "grad_norm": 2.2960305213928223, "learning_rate": 3.735576465857037e-05, "loss": 4.6046, "step": 6235 }, { "epoch": 0.3355574687903573, "grad_norm": 1.4060328006744385, "learning_rate": 3.735209051059571e-05, "loss": 4.5854, "step": 6236 }, { "epoch": 0.3356112785191563, "grad_norm": 2.3174238204956055, "learning_rate": 3.7348416009631544e-05, "loss": 4.1838, "step": 6237 }, { "epoch": 0.3356650882479552, "grad_norm": 1.984803318977356, "learning_rate": 3.7344741155782844e-05, "loss": 4.4189, "step": 6238 }, { "epoch": 0.3357188979767542, "grad_norm": 2.132375955581665, "learning_rate": 3.734106594915466e-05, "loss": 4.2021, "step": 6239 }, { "epoch": 0.3357727077055532, "grad_norm": 1.5396034717559814, "learning_rate": 3.733739038985199e-05, "loss": 4.1998, "step": 6240 }, { "epoch": 0.33582651743435216, "grad_norm": 2.301828145980835, "learning_rate": 3.733371447797989e-05, "loss": 4.2803, "step": 6241 }, { "epoch": 0.3358803271631511, "grad_norm": 1.5561057329177856, "learning_rate": 3.733003821364341e-05, "loss": 4.6583, "step": 6242 }, { "epoch": 0.33593413689195006, "grad_norm": 1.5319125652313232, "learning_rate": 3.7326361596947604e-05, "loss": 4.4633, "step": 6243 }, { "epoch": 0.33598794662074905, "grad_norm": 1.9889472723007202, "learning_rate": 3.732268462799753e-05, "loss": 4.6324, "step": 6244 }, { "epoch": 0.33604175634954797, "grad_norm": 1.9157570600509644, "learning_rate": 3.731900730689827e-05, "loss": 4.5169, "step": 6245 }, { "epoch": 0.33609556607834695, "grad_norm": 2.7045211791992188, "learning_rate": 3.731532963375493e-05, "loss": 4.5883, "step": 6246 }, { "epoch": 0.33614937580714593, "grad_norm": 2.2815182209014893, "learning_rate": 3.731165160867258e-05, "loss": 4.4965, "step": 6247 }, { "epoch": 0.3362031855359449, "grad_norm": 1.6011778116226196, "learning_rate": 3.730797323175634e-05, "loss": 4.4589, "step": 6248 }, { "epoch": 0.33625699526474384, "grad_norm": 1.634600043296814, "learning_rate": 3.730429450311134e-05, "loss": 4.4456, "step": 6249 }, { "epoch": 0.3363108049935428, "grad_norm": 2.2449896335601807, "learning_rate": 3.730061542284269e-05, "loss": 4.3784, "step": 6250 }, { "epoch": 0.3363646147223418, "grad_norm": 2.9309864044189453, "learning_rate": 3.7296935991055546e-05, "loss": 4.3021, "step": 6251 }, { "epoch": 0.3364184244511408, "grad_norm": 1.667709469795227, "learning_rate": 3.729325620785504e-05, "loss": 4.6476, "step": 6252 }, { "epoch": 0.3364722341799397, "grad_norm": 1.3323384523391724, "learning_rate": 3.728957607334633e-05, "loss": 4.6974, "step": 6253 }, { "epoch": 0.3365260439087387, "grad_norm": 1.1868094205856323, "learning_rate": 3.72858955876346e-05, "loss": 4.8282, "step": 6254 }, { "epoch": 0.3365798536375377, "grad_norm": 3.0275869369506836, "learning_rate": 3.728221475082502e-05, "loss": 4.0469, "step": 6255 }, { "epoch": 0.33663366336633666, "grad_norm": 1.880138874053955, "learning_rate": 3.727853356302277e-05, "loss": 4.3314, "step": 6256 }, { "epoch": 0.3366874730951356, "grad_norm": 1.8032948970794678, "learning_rate": 3.7274852024333054e-05, "loss": 4.5441, "step": 6257 }, { "epoch": 0.33674128282393456, "grad_norm": 1.8643770217895508, "learning_rate": 3.727117013486109e-05, "loss": 4.5547, "step": 6258 }, { "epoch": 0.33679509255273354, "grad_norm": 2.321605682373047, "learning_rate": 3.7267487894712086e-05, "loss": 3.6396, "step": 6259 }, { "epoch": 0.3368489022815325, "grad_norm": 1.773410677909851, "learning_rate": 3.726380530399128e-05, "loss": 3.9777, "step": 6260 }, { "epoch": 0.33690271201033145, "grad_norm": 2.0334513187408447, "learning_rate": 3.7260122362803896e-05, "loss": 4.4617, "step": 6261 }, { "epoch": 0.33695652173913043, "grad_norm": 1.9502419233322144, "learning_rate": 3.72564390712552e-05, "loss": 4.6198, "step": 6262 }, { "epoch": 0.3370103314679294, "grad_norm": 2.609186887741089, "learning_rate": 3.7252755429450434e-05, "loss": 4.357, "step": 6263 }, { "epoch": 0.3370641411967284, "grad_norm": 1.8156131505966187, "learning_rate": 3.724907143749488e-05, "loss": 4.1928, "step": 6264 }, { "epoch": 0.3371179509255273, "grad_norm": 1.6759178638458252, "learning_rate": 3.72453870954938e-05, "loss": 4.5406, "step": 6265 }, { "epoch": 0.3371717606543263, "grad_norm": 1.187415361404419, "learning_rate": 3.7241702403552495e-05, "loss": 4.6444, "step": 6266 }, { "epoch": 0.3372255703831253, "grad_norm": 1.5208520889282227, "learning_rate": 3.723801736177627e-05, "loss": 4.6961, "step": 6267 }, { "epoch": 0.3372793801119242, "grad_norm": 2.4951870441436768, "learning_rate": 3.723433197027042e-05, "loss": 4.3676, "step": 6268 }, { "epoch": 0.3373331898407232, "grad_norm": 2.14370059967041, "learning_rate": 3.723064622914027e-05, "loss": 4.6311, "step": 6269 }, { "epoch": 0.3373869995695222, "grad_norm": 2.322700262069702, "learning_rate": 3.722696013849115e-05, "loss": 4.0186, "step": 6270 }, { "epoch": 0.33744080929832115, "grad_norm": 1.9410450458526611, "learning_rate": 3.722327369842838e-05, "loss": 4.1715, "step": 6271 }, { "epoch": 0.3374946190271201, "grad_norm": 1.821783185005188, "learning_rate": 3.721958690905735e-05, "loss": 3.9633, "step": 6272 }, { "epoch": 0.33754842875591906, "grad_norm": 1.2007622718811035, "learning_rate": 3.721589977048338e-05, "loss": 4.7383, "step": 6273 }, { "epoch": 0.33760223848471804, "grad_norm": 1.3598552942276, "learning_rate": 3.721221228281185e-05, "loss": 4.8109, "step": 6274 }, { "epoch": 0.337656048213517, "grad_norm": 2.6449382305145264, "learning_rate": 3.7208524446148144e-05, "loss": 4.5626, "step": 6275 }, { "epoch": 0.33770985794231595, "grad_norm": 1.7998974323272705, "learning_rate": 3.720483626059764e-05, "loss": 4.7372, "step": 6276 }, { "epoch": 0.33776366767111493, "grad_norm": 1.5724990367889404, "learning_rate": 3.720114772626575e-05, "loss": 3.841, "step": 6277 }, { "epoch": 0.3378174773999139, "grad_norm": 1.6695661544799805, "learning_rate": 3.719745884325787e-05, "loss": 4.3588, "step": 6278 }, { "epoch": 0.3378712871287129, "grad_norm": 3.1688921451568604, "learning_rate": 3.719376961167943e-05, "loss": 3.6381, "step": 6279 }, { "epoch": 0.3379250968575118, "grad_norm": 1.6600850820541382, "learning_rate": 3.719008003163584e-05, "loss": 4.6673, "step": 6280 }, { "epoch": 0.3379789065863108, "grad_norm": 1.4843283891677856, "learning_rate": 3.718639010323256e-05, "loss": 4.3858, "step": 6281 }, { "epoch": 0.3380327163151098, "grad_norm": 2.016355276107788, "learning_rate": 3.718269982657503e-05, "loss": 4.5103, "step": 6282 }, { "epoch": 0.33808652604390876, "grad_norm": 1.5725677013397217, "learning_rate": 3.71790092017687e-05, "loss": 4.5283, "step": 6283 }, { "epoch": 0.3381403357727077, "grad_norm": 1.4861546754837036, "learning_rate": 3.717531822891904e-05, "loss": 4.5134, "step": 6284 }, { "epoch": 0.33819414550150667, "grad_norm": 1.7748823165893555, "learning_rate": 3.7171626908131554e-05, "loss": 4.4306, "step": 6285 }, { "epoch": 0.33824795523030565, "grad_norm": 2.2580783367156982, "learning_rate": 3.7167935239511694e-05, "loss": 4.0433, "step": 6286 }, { "epoch": 0.33830176495910463, "grad_norm": 1.736883521080017, "learning_rate": 3.716424322316496e-05, "loss": 4.8318, "step": 6287 }, { "epoch": 0.33835557468790356, "grad_norm": 1.5948493480682373, "learning_rate": 3.716055085919689e-05, "loss": 4.9105, "step": 6288 }, { "epoch": 0.33840938441670254, "grad_norm": 1.5795899629592896, "learning_rate": 3.715685814771298e-05, "loss": 4.4778, "step": 6289 }, { "epoch": 0.3384631941455015, "grad_norm": 1.6938087940216064, "learning_rate": 3.715316508881876e-05, "loss": 4.2463, "step": 6290 }, { "epoch": 0.33851700387430045, "grad_norm": 1.9013489484786987, "learning_rate": 3.714947168261978e-05, "loss": 4.2058, "step": 6291 }, { "epoch": 0.33857081360309943, "grad_norm": 1.4783778190612793, "learning_rate": 3.714577792922157e-05, "loss": 4.456, "step": 6292 }, { "epoch": 0.3386246233318984, "grad_norm": 1.806679606437683, "learning_rate": 3.71420838287297e-05, "loss": 5.0802, "step": 6293 }, { "epoch": 0.3386784330606974, "grad_norm": 0.9128906726837158, "learning_rate": 3.713838938124972e-05, "loss": 4.6807, "step": 6294 }, { "epoch": 0.3387322427894963, "grad_norm": 1.5186347961425781, "learning_rate": 3.7134694586887234e-05, "loss": 4.4853, "step": 6295 }, { "epoch": 0.3387860525182953, "grad_norm": 0.9727240800857544, "learning_rate": 3.7130999445747814e-05, "loss": 4.7497, "step": 6296 }, { "epoch": 0.3388398622470943, "grad_norm": 1.2607005834579468, "learning_rate": 3.7127303957937046e-05, "loss": 4.6213, "step": 6297 }, { "epoch": 0.33889367197589326, "grad_norm": 2.2615299224853516, "learning_rate": 3.712360812356056e-05, "loss": 4.3079, "step": 6298 }, { "epoch": 0.3389474817046922, "grad_norm": 2.327622890472412, "learning_rate": 3.711991194272396e-05, "loss": 4.5634, "step": 6299 }, { "epoch": 0.33900129143349117, "grad_norm": 1.3472360372543335, "learning_rate": 3.711621541553287e-05, "loss": 4.4305, "step": 6300 }, { "epoch": 0.33905510116229015, "grad_norm": 1.032271146774292, "learning_rate": 3.7112518542092945e-05, "loss": 4.4396, "step": 6301 }, { "epoch": 0.33910891089108913, "grad_norm": 1.304372787475586, "learning_rate": 3.7108821322509804e-05, "loss": 4.6051, "step": 6302 }, { "epoch": 0.33916272061988806, "grad_norm": 1.2721631526947021, "learning_rate": 3.710512375688913e-05, "loss": 4.6899, "step": 6303 }, { "epoch": 0.33921653034868704, "grad_norm": 2.650550127029419, "learning_rate": 3.7101425845336576e-05, "loss": 3.9736, "step": 6304 }, { "epoch": 0.339270340077486, "grad_norm": 1.161321997642517, "learning_rate": 3.709772758795781e-05, "loss": 4.7443, "step": 6305 }, { "epoch": 0.339324149806285, "grad_norm": 0.98756343126297, "learning_rate": 3.709402898485854e-05, "loss": 4.5217, "step": 6306 }, { "epoch": 0.33937795953508393, "grad_norm": 1.3351924419403076, "learning_rate": 3.709033003614445e-05, "loss": 4.6821, "step": 6307 }, { "epoch": 0.3394317692638829, "grad_norm": 2.106076717376709, "learning_rate": 3.708663074192125e-05, "loss": 4.612, "step": 6308 }, { "epoch": 0.3394855789926819, "grad_norm": 1.8254656791687012, "learning_rate": 3.7082931102294646e-05, "loss": 4.5903, "step": 6309 }, { "epoch": 0.3395393887214808, "grad_norm": 1.6948235034942627, "learning_rate": 3.707923111737036e-05, "loss": 4.61, "step": 6310 }, { "epoch": 0.3395931984502798, "grad_norm": 1.5839234590530396, "learning_rate": 3.7075530787254156e-05, "loss": 4.371, "step": 6311 }, { "epoch": 0.3396470081790788, "grad_norm": 1.7026033401489258, "learning_rate": 3.7071830112051754e-05, "loss": 4.6741, "step": 6312 }, { "epoch": 0.33970081790787776, "grad_norm": 1.1285269260406494, "learning_rate": 3.706812909186892e-05, "loss": 4.7153, "step": 6313 }, { "epoch": 0.3397546276366767, "grad_norm": 1.3950254917144775, "learning_rate": 3.706442772681141e-05, "loss": 4.2235, "step": 6314 }, { "epoch": 0.33980843736547567, "grad_norm": 1.8530884981155396, "learning_rate": 3.706072601698501e-05, "loss": 4.3628, "step": 6315 }, { "epoch": 0.33986224709427465, "grad_norm": 3.315505266189575, "learning_rate": 3.7057023962495495e-05, "loss": 4.1435, "step": 6316 }, { "epoch": 0.33991605682307363, "grad_norm": 2.349342107772827, "learning_rate": 3.705332156344867e-05, "loss": 4.0451, "step": 6317 }, { "epoch": 0.33996986655187256, "grad_norm": 1.807159662246704, "learning_rate": 3.704961881995033e-05, "loss": 4.402, "step": 6318 }, { "epoch": 0.34002367628067154, "grad_norm": 1.574537754058838, "learning_rate": 3.70459157321063e-05, "loss": 4.1837, "step": 6319 }, { "epoch": 0.3400774860094705, "grad_norm": 1.717856764793396, "learning_rate": 3.704221230002239e-05, "loss": 4.5643, "step": 6320 }, { "epoch": 0.3401312957382695, "grad_norm": 2.2746050357818604, "learning_rate": 3.703850852380445e-05, "loss": 3.8544, "step": 6321 }, { "epoch": 0.3401851054670684, "grad_norm": 1.7232060432434082, "learning_rate": 3.703480440355831e-05, "loss": 4.5164, "step": 6322 }, { "epoch": 0.3402389151958674, "grad_norm": 2.402977466583252, "learning_rate": 3.703109993938984e-05, "loss": 4.2114, "step": 6323 }, { "epoch": 0.3402927249246664, "grad_norm": 2.252368450164795, "learning_rate": 3.702739513140489e-05, "loss": 4.994, "step": 6324 }, { "epoch": 0.34034653465346537, "grad_norm": 1.3184922933578491, "learning_rate": 3.702368997970932e-05, "loss": 4.789, "step": 6325 }, { "epoch": 0.3404003443822643, "grad_norm": 1.9483898878097534, "learning_rate": 3.7019984484409046e-05, "loss": 4.223, "step": 6326 }, { "epoch": 0.3404541541110633, "grad_norm": 1.7466775178909302, "learning_rate": 3.701627864560995e-05, "loss": 4.6586, "step": 6327 }, { "epoch": 0.34050796383986226, "grad_norm": 1.188260793685913, "learning_rate": 3.7012572463417914e-05, "loss": 4.4351, "step": 6328 }, { "epoch": 0.34056177356866124, "grad_norm": 2.3287229537963867, "learning_rate": 3.700886593793888e-05, "loss": 4.3808, "step": 6329 }, { "epoch": 0.34061558329746017, "grad_norm": 2.48897385597229, "learning_rate": 3.7005159069278754e-05, "loss": 4.1528, "step": 6330 }, { "epoch": 0.34066939302625915, "grad_norm": 1.5849332809448242, "learning_rate": 3.7001451857543475e-05, "loss": 4.4704, "step": 6331 }, { "epoch": 0.34072320275505813, "grad_norm": 2.503584623336792, "learning_rate": 3.699774430283898e-05, "loss": 4.2081, "step": 6332 }, { "epoch": 0.34077701248385706, "grad_norm": 2.2328479290008545, "learning_rate": 3.699403640527122e-05, "loss": 4.4627, "step": 6333 }, { "epoch": 0.34083082221265604, "grad_norm": 2.514479875564575, "learning_rate": 3.699032816494616e-05, "loss": 4.4094, "step": 6334 }, { "epoch": 0.340884631941455, "grad_norm": 1.6049429178237915, "learning_rate": 3.6986619581969776e-05, "loss": 4.7149, "step": 6335 }, { "epoch": 0.340938441670254, "grad_norm": 1.2252740859985352, "learning_rate": 3.6982910656448036e-05, "loss": 4.3128, "step": 6336 }, { "epoch": 0.3409922513990529, "grad_norm": 2.709866762161255, "learning_rate": 3.697920138848695e-05, "loss": 4.3601, "step": 6337 }, { "epoch": 0.3410460611278519, "grad_norm": 1.6125531196594238, "learning_rate": 3.69754917781925e-05, "loss": 4.767, "step": 6338 }, { "epoch": 0.3410998708566509, "grad_norm": 0.9335963129997253, "learning_rate": 3.6971781825670714e-05, "loss": 4.6694, "step": 6339 }, { "epoch": 0.34115368058544987, "grad_norm": 0.8937689661979675, "learning_rate": 3.69680715310276e-05, "loss": 4.3572, "step": 6340 }, { "epoch": 0.3412074903142488, "grad_norm": 1.5903325080871582, "learning_rate": 3.696436089436918e-05, "loss": 4.5939, "step": 6341 }, { "epoch": 0.3412613000430478, "grad_norm": 1.3569260835647583, "learning_rate": 3.696064991580153e-05, "loss": 4.5304, "step": 6342 }, { "epoch": 0.34131510977184676, "grad_norm": 1.7286286354064941, "learning_rate": 3.6956938595430656e-05, "loss": 4.9486, "step": 6343 }, { "epoch": 0.34136891950064574, "grad_norm": 1.9954406023025513, "learning_rate": 3.695322693336264e-05, "loss": 4.8358, "step": 6344 }, { "epoch": 0.34142272922944467, "grad_norm": 2.1083555221557617, "learning_rate": 3.6949514929703553e-05, "loss": 4.5708, "step": 6345 }, { "epoch": 0.34147653895824365, "grad_norm": 1.5220792293548584, "learning_rate": 3.694580258455947e-05, "loss": 4.628, "step": 6346 }, { "epoch": 0.34153034868704263, "grad_norm": 1.899404525756836, "learning_rate": 3.6942089898036484e-05, "loss": 4.6494, "step": 6347 }, { "epoch": 0.3415841584158416, "grad_norm": 2.0820348262786865, "learning_rate": 3.693837687024068e-05, "loss": 3.9893, "step": 6348 }, { "epoch": 0.34163796814464054, "grad_norm": 2.284590482711792, "learning_rate": 3.693466350127818e-05, "loss": 4.5425, "step": 6349 }, { "epoch": 0.3416917778734395, "grad_norm": 1.6717883348464966, "learning_rate": 3.69309497912551e-05, "loss": 4.2016, "step": 6350 }, { "epoch": 0.3417455876022385, "grad_norm": 2.0308926105499268, "learning_rate": 3.692723574027755e-05, "loss": 4.3145, "step": 6351 }, { "epoch": 0.3417993973310374, "grad_norm": 1.8911687135696411, "learning_rate": 3.6923521348451706e-05, "loss": 3.9934, "step": 6352 }, { "epoch": 0.3418532070598364, "grad_norm": 1.4117792844772339, "learning_rate": 3.691980661588368e-05, "loss": 4.4906, "step": 6353 }, { "epoch": 0.3419070167886354, "grad_norm": 2.0021274089813232, "learning_rate": 3.691609154267964e-05, "loss": 4.0802, "step": 6354 }, { "epoch": 0.34196082651743437, "grad_norm": 2.2796292304992676, "learning_rate": 3.691237612894576e-05, "loss": 4.9459, "step": 6355 }, { "epoch": 0.3420146362462333, "grad_norm": 1.431821584701538, "learning_rate": 3.6908660374788205e-05, "loss": 4.3616, "step": 6356 }, { "epoch": 0.3420684459750323, "grad_norm": 1.1785786151885986, "learning_rate": 3.6904944280313174e-05, "loss": 4.8333, "step": 6357 }, { "epoch": 0.34212225570383126, "grad_norm": 1.8248754739761353, "learning_rate": 3.690122784562686e-05, "loss": 3.8005, "step": 6358 }, { "epoch": 0.34217606543263024, "grad_norm": 1.365291714668274, "learning_rate": 3.689751107083544e-05, "loss": 4.7959, "step": 6359 }, { "epoch": 0.34222987516142916, "grad_norm": 3.371701717376709, "learning_rate": 3.689379395604518e-05, "loss": 3.742, "step": 6360 }, { "epoch": 0.34228368489022815, "grad_norm": 0.983794093132019, "learning_rate": 3.6890076501362266e-05, "loss": 4.7137, "step": 6361 }, { "epoch": 0.3423374946190271, "grad_norm": 2.3279831409454346, "learning_rate": 3.688635870689296e-05, "loss": 4.66, "step": 6362 }, { "epoch": 0.3423913043478261, "grad_norm": 1.7412831783294678, "learning_rate": 3.688264057274348e-05, "loss": 4.6087, "step": 6363 }, { "epoch": 0.34244511407662503, "grad_norm": 1.3237152099609375, "learning_rate": 3.687892209902009e-05, "loss": 4.6415, "step": 6364 }, { "epoch": 0.342498923805424, "grad_norm": 1.9902409315109253, "learning_rate": 3.687520328582907e-05, "loss": 4.4214, "step": 6365 }, { "epoch": 0.342552733534223, "grad_norm": 1.4012417793273926, "learning_rate": 3.6871484133276674e-05, "loss": 4.4988, "step": 6366 }, { "epoch": 0.342606543263022, "grad_norm": 0.9893824458122253, "learning_rate": 3.6867764641469186e-05, "loss": 4.4303, "step": 6367 }, { "epoch": 0.3426603529918209, "grad_norm": 1.7616353034973145, "learning_rate": 3.686404481051291e-05, "loss": 4.8574, "step": 6368 }, { "epoch": 0.3427141627206199, "grad_norm": 1.9260177612304688, "learning_rate": 3.686032464051415e-05, "loss": 4.4784, "step": 6369 }, { "epoch": 0.34276797244941887, "grad_norm": 2.350454568862915, "learning_rate": 3.685660413157921e-05, "loss": 3.6979, "step": 6370 }, { "epoch": 0.34282178217821785, "grad_norm": 2.138685941696167, "learning_rate": 3.685288328381441e-05, "loss": 4.2205, "step": 6371 }, { "epoch": 0.3428755919070168, "grad_norm": 1.294052004814148, "learning_rate": 3.684916209732609e-05, "loss": 4.424, "step": 6372 }, { "epoch": 0.34292940163581576, "grad_norm": 2.1899213790893555, "learning_rate": 3.684544057222058e-05, "loss": 4.0239, "step": 6373 }, { "epoch": 0.34298321136461474, "grad_norm": 1.2499524354934692, "learning_rate": 3.684171870860424e-05, "loss": 4.4152, "step": 6374 }, { "epoch": 0.34303702109341366, "grad_norm": 2.3974640369415283, "learning_rate": 3.683799650658344e-05, "loss": 4.094, "step": 6375 }, { "epoch": 0.34309083082221264, "grad_norm": 2.1632962226867676, "learning_rate": 3.683427396626454e-05, "loss": 4.4118, "step": 6376 }, { "epoch": 0.3431446405510116, "grad_norm": 1.6877224445343018, "learning_rate": 3.6830551087753906e-05, "loss": 4.3192, "step": 6377 }, { "epoch": 0.3431984502798106, "grad_norm": 3.098268508911133, "learning_rate": 3.6826827871157955e-05, "loss": 4.3968, "step": 6378 }, { "epoch": 0.34325226000860953, "grad_norm": 1.8150686025619507, "learning_rate": 3.682310431658307e-05, "loss": 4.09, "step": 6379 }, { "epoch": 0.3433060697374085, "grad_norm": 1.1790752410888672, "learning_rate": 3.681938042413566e-05, "loss": 4.4286, "step": 6380 }, { "epoch": 0.3433598794662075, "grad_norm": 1.8607823848724365, "learning_rate": 3.681565619392216e-05, "loss": 4.4202, "step": 6381 }, { "epoch": 0.3434136891950065, "grad_norm": 1.2848308086395264, "learning_rate": 3.6811931626048974e-05, "loss": 4.8185, "step": 6382 }, { "epoch": 0.3434674989238054, "grad_norm": 0.9763439893722534, "learning_rate": 3.680820672062256e-05, "loss": 4.8179, "step": 6383 }, { "epoch": 0.3435213086526044, "grad_norm": 2.026956796646118, "learning_rate": 3.6804481477749355e-05, "loss": 4.6337, "step": 6384 }, { "epoch": 0.34357511838140337, "grad_norm": 2.238126754760742, "learning_rate": 3.680075589753582e-05, "loss": 4.4191, "step": 6385 }, { "epoch": 0.34362892811020235, "grad_norm": 2.7937257289886475, "learning_rate": 3.679702998008842e-05, "loss": 4.4792, "step": 6386 }, { "epoch": 0.3436827378390013, "grad_norm": 1.7752711772918701, "learning_rate": 3.679330372551363e-05, "loss": 4.6359, "step": 6387 }, { "epoch": 0.34373654756780025, "grad_norm": 2.493091583251953, "learning_rate": 3.678957713391795e-05, "loss": 3.8428, "step": 6388 }, { "epoch": 0.34379035729659924, "grad_norm": 1.2180365324020386, "learning_rate": 3.678585020540786e-05, "loss": 4.6099, "step": 6389 }, { "epoch": 0.3438441670253982, "grad_norm": 1.1337640285491943, "learning_rate": 3.678212294008987e-05, "loss": 4.5793, "step": 6390 }, { "epoch": 0.34389797675419714, "grad_norm": 1.8012088537216187, "learning_rate": 3.677839533807051e-05, "loss": 4.4906, "step": 6391 }, { "epoch": 0.3439517864829961, "grad_norm": 1.7535698413848877, "learning_rate": 3.677466739945627e-05, "loss": 4.4366, "step": 6392 }, { "epoch": 0.3440055962117951, "grad_norm": 1.802833914756775, "learning_rate": 3.677093912435372e-05, "loss": 4.7079, "step": 6393 }, { "epoch": 0.34405940594059403, "grad_norm": 1.390290379524231, "learning_rate": 3.676721051286938e-05, "loss": 4.4519, "step": 6394 }, { "epoch": 0.344113215669393, "grad_norm": 1.3015331029891968, "learning_rate": 3.6763481565109824e-05, "loss": 4.4721, "step": 6395 }, { "epoch": 0.344167025398192, "grad_norm": 1.755143642425537, "learning_rate": 3.67597522811816e-05, "loss": 4.6036, "step": 6396 }, { "epoch": 0.344220835126991, "grad_norm": 1.7439466714859009, "learning_rate": 3.675602266119128e-05, "loss": 4.3136, "step": 6397 }, { "epoch": 0.3442746448557899, "grad_norm": 2.204089641571045, "learning_rate": 3.675229270524546e-05, "loss": 4.7907, "step": 6398 }, { "epoch": 0.3443284545845889, "grad_norm": 2.484377145767212, "learning_rate": 3.674856241345073e-05, "loss": 3.8267, "step": 6399 }, { "epoch": 0.34438226431338786, "grad_norm": 2.5301361083984375, "learning_rate": 3.674483178591368e-05, "loss": 3.7785, "step": 6400 }, { "epoch": 0.34443607404218685, "grad_norm": 1.9212747812271118, "learning_rate": 3.674110082274092e-05, "loss": 4.7922, "step": 6401 }, { "epoch": 0.34448988377098577, "grad_norm": 1.4035815000534058, "learning_rate": 3.673736952403909e-05, "loss": 4.1922, "step": 6402 }, { "epoch": 0.34454369349978475, "grad_norm": 1.6368043422698975, "learning_rate": 3.67336378899148e-05, "loss": 4.7284, "step": 6403 }, { "epoch": 0.34459750322858373, "grad_norm": 1.8759729862213135, "learning_rate": 3.6729905920474704e-05, "loss": 4.7294, "step": 6404 }, { "epoch": 0.3446513129573827, "grad_norm": 1.5828030109405518, "learning_rate": 3.6726173615825445e-05, "loss": 4.7429, "step": 6405 }, { "epoch": 0.34470512268618164, "grad_norm": 2.2029061317443848, "learning_rate": 3.672244097607368e-05, "loss": 4.1274, "step": 6406 }, { "epoch": 0.3447589324149806, "grad_norm": 1.7068517208099365, "learning_rate": 3.6718708001326094e-05, "loss": 4.4576, "step": 6407 }, { "epoch": 0.3448127421437796, "grad_norm": 2.2925655841827393, "learning_rate": 3.671497469168934e-05, "loss": 4.4318, "step": 6408 }, { "epoch": 0.3448665518725786, "grad_norm": 1.7088559865951538, "learning_rate": 3.6711241047270124e-05, "loss": 4.2445, "step": 6409 }, { "epoch": 0.3449203616013775, "grad_norm": 1.1665303707122803, "learning_rate": 3.670750706817514e-05, "loss": 4.5006, "step": 6410 }, { "epoch": 0.3449741713301765, "grad_norm": 1.9065335988998413, "learning_rate": 3.670377275451109e-05, "loss": 3.9707, "step": 6411 }, { "epoch": 0.3450279810589755, "grad_norm": 2.3374478816986084, "learning_rate": 3.670003810638469e-05, "loss": 4.1887, "step": 6412 }, { "epoch": 0.34508179078777446, "grad_norm": 1.4791127443313599, "learning_rate": 3.6696303123902676e-05, "loss": 4.4552, "step": 6413 }, { "epoch": 0.3451356005165734, "grad_norm": 3.143592596054077, "learning_rate": 3.669256780717178e-05, "loss": 4.4075, "step": 6414 }, { "epoch": 0.34518941024537236, "grad_norm": 1.5583363771438599, "learning_rate": 3.668883215629874e-05, "loss": 4.6057, "step": 6415 }, { "epoch": 0.34524321997417134, "grad_norm": 1.641465425491333, "learning_rate": 3.668509617139032e-05, "loss": 4.5967, "step": 6416 }, { "epoch": 0.34529702970297027, "grad_norm": 2.24497389793396, "learning_rate": 3.668135985255328e-05, "loss": 3.6854, "step": 6417 }, { "epoch": 0.34535083943176925, "grad_norm": 2.192473888397217, "learning_rate": 3.66776231998944e-05, "loss": 4.0593, "step": 6418 }, { "epoch": 0.34540464916056823, "grad_norm": 1.7235559225082397, "learning_rate": 3.6673886213520455e-05, "loss": 4.5094, "step": 6419 }, { "epoch": 0.3454584588893672, "grad_norm": 2.7453765869140625, "learning_rate": 3.667014889353824e-05, "loss": 3.991, "step": 6420 }, { "epoch": 0.34551226861816614, "grad_norm": 2.349575996398926, "learning_rate": 3.666641124005455e-05, "loss": 4.3606, "step": 6421 }, { "epoch": 0.3455660783469651, "grad_norm": 2.325742483139038, "learning_rate": 3.666267325317621e-05, "loss": 4.5767, "step": 6422 }, { "epoch": 0.3456198880757641, "grad_norm": 1.9885278940200806, "learning_rate": 3.6658934933010046e-05, "loss": 4.0512, "step": 6423 }, { "epoch": 0.3456736978045631, "grad_norm": 1.9552839994430542, "learning_rate": 3.665519627966287e-05, "loss": 3.9365, "step": 6424 }, { "epoch": 0.345727507533362, "grad_norm": 2.1297781467437744, "learning_rate": 3.665145729324154e-05, "loss": 4.8034, "step": 6425 }, { "epoch": 0.345781317262161, "grad_norm": 1.9811241626739502, "learning_rate": 3.66477179738529e-05, "loss": 4.4447, "step": 6426 }, { "epoch": 0.34583512699096, "grad_norm": 1.4741246700286865, "learning_rate": 3.6643978321603804e-05, "loss": 4.7191, "step": 6427 }, { "epoch": 0.34588893671975895, "grad_norm": 1.7119693756103516, "learning_rate": 3.664023833660113e-05, "loss": 4.2603, "step": 6428 }, { "epoch": 0.3459427464485579, "grad_norm": 2.4745919704437256, "learning_rate": 3.663649801895175e-05, "loss": 4.4918, "step": 6429 }, { "epoch": 0.34599655617735686, "grad_norm": 1.5369081497192383, "learning_rate": 3.663275736876256e-05, "loss": 4.7841, "step": 6430 }, { "epoch": 0.34605036590615584, "grad_norm": 1.3439955711364746, "learning_rate": 3.662901638614045e-05, "loss": 4.6268, "step": 6431 }, { "epoch": 0.3461041756349548, "grad_norm": 3.1863789558410645, "learning_rate": 3.662527507119233e-05, "loss": 4.0062, "step": 6432 }, { "epoch": 0.34615798536375375, "grad_norm": 2.3101184368133545, "learning_rate": 3.662153342402511e-05, "loss": 4.3328, "step": 6433 }, { "epoch": 0.34621179509255273, "grad_norm": 1.9895164966583252, "learning_rate": 3.661779144474573e-05, "loss": 4.3305, "step": 6434 }, { "epoch": 0.3462656048213517, "grad_norm": 2.0275204181671143, "learning_rate": 3.6614049133461126e-05, "loss": 4.7608, "step": 6435 }, { "epoch": 0.3463194145501507, "grad_norm": 2.04018497467041, "learning_rate": 3.661030649027822e-05, "loss": 4.19, "step": 6436 }, { "epoch": 0.3463732242789496, "grad_norm": 2.833009719848633, "learning_rate": 3.6606563515303994e-05, "loss": 4.092, "step": 6437 }, { "epoch": 0.3464270340077486, "grad_norm": 2.1191179752349854, "learning_rate": 3.66028202086454e-05, "loss": 4.4081, "step": 6438 }, { "epoch": 0.3464808437365476, "grad_norm": 2.700007200241089, "learning_rate": 3.659907657040941e-05, "loss": 4.2117, "step": 6439 }, { "epoch": 0.3465346534653465, "grad_norm": 1.6424857378005981, "learning_rate": 3.6595332600703006e-05, "loss": 5.0473, "step": 6440 }, { "epoch": 0.3465884631941455, "grad_norm": 1.993839979171753, "learning_rate": 3.6591588299633186e-05, "loss": 4.5555, "step": 6441 }, { "epoch": 0.34664227292294447, "grad_norm": 1.2004165649414062, "learning_rate": 3.6587843667306955e-05, "loss": 4.7089, "step": 6442 }, { "epoch": 0.34669608265174345, "grad_norm": 1.7873873710632324, "learning_rate": 3.6584098703831316e-05, "loss": 4.7421, "step": 6443 }, { "epoch": 0.3467498923805424, "grad_norm": 1.4749349355697632, "learning_rate": 3.658035340931328e-05, "loss": 4.8477, "step": 6444 }, { "epoch": 0.34680370210934136, "grad_norm": 2.2471678256988525, "learning_rate": 3.657660778385992e-05, "loss": 4.4192, "step": 6445 }, { "epoch": 0.34685751183814034, "grad_norm": 1.4258732795715332, "learning_rate": 3.657286182757822e-05, "loss": 4.6175, "step": 6446 }, { "epoch": 0.3469113215669393, "grad_norm": 2.4377639293670654, "learning_rate": 3.656911554057527e-05, "loss": 4.5184, "step": 6447 }, { "epoch": 0.34696513129573825, "grad_norm": 1.4710882902145386, "learning_rate": 3.6565368922958114e-05, "loss": 4.5689, "step": 6448 }, { "epoch": 0.34701894102453723, "grad_norm": 2.1239545345306396, "learning_rate": 3.6561621974833824e-05, "loss": 4.4574, "step": 6449 }, { "epoch": 0.3470727507533362, "grad_norm": 1.2460283041000366, "learning_rate": 3.655787469630947e-05, "loss": 4.493, "step": 6450 }, { "epoch": 0.3471265604821352, "grad_norm": 1.3371942043304443, "learning_rate": 3.6554127087492144e-05, "loss": 4.5613, "step": 6451 }, { "epoch": 0.3471803702109341, "grad_norm": 1.4610209465026855, "learning_rate": 3.655037914848894e-05, "loss": 4.6982, "step": 6452 }, { "epoch": 0.3472341799397331, "grad_norm": 1.7859338521957397, "learning_rate": 3.654663087940698e-05, "loss": 4.0257, "step": 6453 }, { "epoch": 0.3472879896685321, "grad_norm": 1.234236717224121, "learning_rate": 3.654288228035335e-05, "loss": 4.7749, "step": 6454 }, { "epoch": 0.34734179939733106, "grad_norm": 2.293921709060669, "learning_rate": 3.6539133351435204e-05, "loss": 3.497, "step": 6455 }, { "epoch": 0.34739560912613, "grad_norm": 3.358236789703369, "learning_rate": 3.6535384092759654e-05, "loss": 4.4435, "step": 6456 }, { "epoch": 0.34744941885492897, "grad_norm": 1.747765302658081, "learning_rate": 3.653163450443386e-05, "loss": 4.5013, "step": 6457 }, { "epoch": 0.34750322858372795, "grad_norm": 1.3950612545013428, "learning_rate": 3.6527884586564965e-05, "loss": 4.4661, "step": 6458 }, { "epoch": 0.3475570383125269, "grad_norm": 1.896393895149231, "learning_rate": 3.652413433926013e-05, "loss": 4.2843, "step": 6459 }, { "epoch": 0.34761084804132586, "grad_norm": 1.7014904022216797, "learning_rate": 3.6520383762626545e-05, "loss": 3.9915, "step": 6460 }, { "epoch": 0.34766465777012484, "grad_norm": 1.2499958276748657, "learning_rate": 3.651663285677137e-05, "loss": 4.5409, "step": 6461 }, { "epoch": 0.3477184674989238, "grad_norm": 1.3633331060409546, "learning_rate": 3.65128816218018e-05, "loss": 4.4461, "step": 6462 }, { "epoch": 0.34777227722772275, "grad_norm": 1.0321111679077148, "learning_rate": 3.650913005782504e-05, "loss": 4.5643, "step": 6463 }, { "epoch": 0.34782608695652173, "grad_norm": 1.4969005584716797, "learning_rate": 3.650537816494831e-05, "loss": 4.0829, "step": 6464 }, { "epoch": 0.3478798966853207, "grad_norm": 2.9196810722351074, "learning_rate": 3.6501625943278805e-05, "loss": 4.0347, "step": 6465 }, { "epoch": 0.3479337064141197, "grad_norm": 1.3388980627059937, "learning_rate": 3.649787339292378e-05, "loss": 4.2795, "step": 6466 }, { "epoch": 0.3479875161429186, "grad_norm": 1.3692232370376587, "learning_rate": 3.6494120513990436e-05, "loss": 4.1893, "step": 6467 }, { "epoch": 0.3480413258717176, "grad_norm": 1.7392988204956055, "learning_rate": 3.649036730658607e-05, "loss": 4.8918, "step": 6468 }, { "epoch": 0.3480951356005166, "grad_norm": 1.510408878326416, "learning_rate": 3.64866137708179e-05, "loss": 4.3617, "step": 6469 }, { "epoch": 0.34814894532931556, "grad_norm": 1.628328800201416, "learning_rate": 3.64828599067932e-05, "loss": 4.396, "step": 6470 }, { "epoch": 0.3482027550581145, "grad_norm": 2.202606201171875, "learning_rate": 3.647910571461925e-05, "loss": 4.3384, "step": 6471 }, { "epoch": 0.34825656478691347, "grad_norm": 2.6440439224243164, "learning_rate": 3.647535119440334e-05, "loss": 3.1917, "step": 6472 }, { "epoch": 0.34831037451571245, "grad_norm": 2.3072781562805176, "learning_rate": 3.647159634625276e-05, "loss": 4.2108, "step": 6473 }, { "epoch": 0.34836418424451143, "grad_norm": 1.858234167098999, "learning_rate": 3.6467841170274794e-05, "loss": 4.2543, "step": 6474 }, { "epoch": 0.34841799397331036, "grad_norm": 1.5199428796768188, "learning_rate": 3.646408566657679e-05, "loss": 4.2186, "step": 6475 }, { "epoch": 0.34847180370210934, "grad_norm": 2.0409739017486572, "learning_rate": 3.646032983526605e-05, "loss": 4.3202, "step": 6476 }, { "epoch": 0.3485256134309083, "grad_norm": 1.9651726484298706, "learning_rate": 3.64565736764499e-05, "loss": 4.0539, "step": 6477 }, { "epoch": 0.3485794231597073, "grad_norm": 1.1774715185165405, "learning_rate": 3.6452817190235696e-05, "loss": 4.7213, "step": 6478 }, { "epoch": 0.34863323288850623, "grad_norm": 1.717049241065979, "learning_rate": 3.644906037673078e-05, "loss": 4.7998, "step": 6479 }, { "epoch": 0.3486870426173052, "grad_norm": 1.7580736875534058, "learning_rate": 3.6445303236042505e-05, "loss": 4.9222, "step": 6480 }, { "epoch": 0.3487408523461042, "grad_norm": 1.7524622678756714, "learning_rate": 3.644154576827826e-05, "loss": 4.3077, "step": 6481 }, { "epoch": 0.3487946620749031, "grad_norm": 1.4304542541503906, "learning_rate": 3.64377879735454e-05, "loss": 4.3708, "step": 6482 }, { "epoch": 0.3488484718037021, "grad_norm": 1.0248000621795654, "learning_rate": 3.643402985195133e-05, "loss": 3.9761, "step": 6483 }, { "epoch": 0.3489022815325011, "grad_norm": 1.80906343460083, "learning_rate": 3.6430271403603444e-05, "loss": 4.8101, "step": 6484 }, { "epoch": 0.34895609126130006, "grad_norm": 2.1854069232940674, "learning_rate": 3.642651262860913e-05, "loss": 4.5927, "step": 6485 }, { "epoch": 0.349009900990099, "grad_norm": 2.222580671310425, "learning_rate": 3.642275352707584e-05, "loss": 4.237, "step": 6486 }, { "epoch": 0.34906371071889797, "grad_norm": 2.5386462211608887, "learning_rate": 3.641899409911097e-05, "loss": 4.4853, "step": 6487 }, { "epoch": 0.34911752044769695, "grad_norm": 1.3990001678466797, "learning_rate": 3.641523434482195e-05, "loss": 4.3306, "step": 6488 }, { "epoch": 0.34917133017649593, "grad_norm": 1.8181204795837402, "learning_rate": 3.641147426431625e-05, "loss": 4.6213, "step": 6489 }, { "epoch": 0.34922513990529486, "grad_norm": 1.1302967071533203, "learning_rate": 3.6407713857701296e-05, "loss": 4.5573, "step": 6490 }, { "epoch": 0.34927894963409384, "grad_norm": 1.6143852472305298, "learning_rate": 3.640395312508458e-05, "loss": 4.4092, "step": 6491 }, { "epoch": 0.3493327593628928, "grad_norm": 1.7783904075622559, "learning_rate": 3.6400192066573546e-05, "loss": 4.4138, "step": 6492 }, { "epoch": 0.3493865690916918, "grad_norm": 1.414475679397583, "learning_rate": 3.6396430682275686e-05, "loss": 4.4693, "step": 6493 }, { "epoch": 0.3494403788204907, "grad_norm": 2.116617441177368, "learning_rate": 3.6392668972298495e-05, "loss": 4.3831, "step": 6494 }, { "epoch": 0.3494941885492897, "grad_norm": 1.0453766584396362, "learning_rate": 3.638890693674946e-05, "loss": 4.5081, "step": 6495 }, { "epoch": 0.3495479982780887, "grad_norm": 1.7372839450836182, "learning_rate": 3.6385144575736106e-05, "loss": 4.202, "step": 6496 }, { "epoch": 0.34960180800688767, "grad_norm": 1.9921212196350098, "learning_rate": 3.638138188936594e-05, "loss": 4.4693, "step": 6497 }, { "epoch": 0.3496556177356866, "grad_norm": 1.7017059326171875, "learning_rate": 3.637761887774648e-05, "loss": 4.6506, "step": 6498 }, { "epoch": 0.3497094274644856, "grad_norm": 2.3980484008789062, "learning_rate": 3.637385554098529e-05, "loss": 4.3584, "step": 6499 }, { "epoch": 0.34976323719328456, "grad_norm": 2.4661922454833984, "learning_rate": 3.637009187918989e-05, "loss": 4.1939, "step": 6500 }, { "epoch": 0.3498170469220835, "grad_norm": 1.1128801107406616, "learning_rate": 3.6366327892467854e-05, "loss": 4.8823, "step": 6501 }, { "epoch": 0.34987085665088247, "grad_norm": 2.6071553230285645, "learning_rate": 3.636256358092675e-05, "loss": 4.3212, "step": 6502 }, { "epoch": 0.34992466637968145, "grad_norm": 1.1081833839416504, "learning_rate": 3.635879894467411e-05, "loss": 4.3466, "step": 6503 }, { "epoch": 0.34997847610848043, "grad_norm": 2.1877987384796143, "learning_rate": 3.6355033983817564e-05, "loss": 4.272, "step": 6504 }, { "epoch": 0.35003228583727936, "grad_norm": 1.5686806440353394, "learning_rate": 3.6351268698464694e-05, "loss": 4.5118, "step": 6505 }, { "epoch": 0.35008609556607834, "grad_norm": 2.0401206016540527, "learning_rate": 3.634750308872309e-05, "loss": 4.4296, "step": 6506 }, { "epoch": 0.3501399052948773, "grad_norm": 1.449168086051941, "learning_rate": 3.6343737154700366e-05, "loss": 4.492, "step": 6507 }, { "epoch": 0.3501937150236763, "grad_norm": 1.6781275272369385, "learning_rate": 3.633997089650415e-05, "loss": 4.5414, "step": 6508 }, { "epoch": 0.3502475247524752, "grad_norm": 1.8487520217895508, "learning_rate": 3.6336204314242065e-05, "loss": 4.4084, "step": 6509 }, { "epoch": 0.3503013344812742, "grad_norm": 2.1066668033599854, "learning_rate": 3.633243740802176e-05, "loss": 4.1009, "step": 6510 }, { "epoch": 0.3503551442100732, "grad_norm": 2.330078363418579, "learning_rate": 3.6328670177950856e-05, "loss": 4.4029, "step": 6511 }, { "epoch": 0.35040895393887217, "grad_norm": 1.924689531326294, "learning_rate": 3.632490262413704e-05, "loss": 4.2911, "step": 6512 }, { "epoch": 0.3504627636676711, "grad_norm": 2.9608922004699707, "learning_rate": 3.632113474668797e-05, "loss": 3.8717, "step": 6513 }, { "epoch": 0.3505165733964701, "grad_norm": 2.1592769622802734, "learning_rate": 3.6317366545711316e-05, "loss": 4.7349, "step": 6514 }, { "epoch": 0.35057038312526906, "grad_norm": 1.0118825435638428, "learning_rate": 3.631359802131476e-05, "loss": 4.5049, "step": 6515 }, { "epoch": 0.35062419285406804, "grad_norm": 1.5107227563858032, "learning_rate": 3.630982917360601e-05, "loss": 4.37, "step": 6516 }, { "epoch": 0.35067800258286697, "grad_norm": 1.0946100950241089, "learning_rate": 3.630606000269276e-05, "loss": 4.2108, "step": 6517 }, { "epoch": 0.35073181231166595, "grad_norm": 1.2681607007980347, "learning_rate": 3.630229050868272e-05, "loss": 4.4385, "step": 6518 }, { "epoch": 0.35078562204046493, "grad_norm": 1.9444063901901245, "learning_rate": 3.629852069168363e-05, "loss": 4.8695, "step": 6519 }, { "epoch": 0.3508394317692639, "grad_norm": 3.870213508605957, "learning_rate": 3.6294750551803205e-05, "loss": 4.2489, "step": 6520 }, { "epoch": 0.35089324149806284, "grad_norm": 1.5963624715805054, "learning_rate": 3.6290980089149175e-05, "loss": 4.6117, "step": 6521 }, { "epoch": 0.3509470512268618, "grad_norm": 1.0434809923171997, "learning_rate": 3.6287209303829314e-05, "loss": 4.5023, "step": 6522 }, { "epoch": 0.3510008609556608, "grad_norm": 2.206352472305298, "learning_rate": 3.628343819595137e-05, "loss": 4.3637, "step": 6523 }, { "epoch": 0.3510546706844597, "grad_norm": 1.126470685005188, "learning_rate": 3.6279666765623104e-05, "loss": 4.6511, "step": 6524 }, { "epoch": 0.3511084804132587, "grad_norm": 1.9966447353363037, "learning_rate": 3.6275895012952315e-05, "loss": 3.9259, "step": 6525 }, { "epoch": 0.3511622901420577, "grad_norm": 2.034545421600342, "learning_rate": 3.627212293804676e-05, "loss": 4.2308, "step": 6526 }, { "epoch": 0.35121609987085667, "grad_norm": 1.675169825553894, "learning_rate": 3.626835054101426e-05, "loss": 4.4582, "step": 6527 }, { "epoch": 0.3512699095996556, "grad_norm": 2.4274911880493164, "learning_rate": 3.6264577821962604e-05, "loss": 3.7688, "step": 6528 }, { "epoch": 0.3513237193284546, "grad_norm": 1.3937445878982544, "learning_rate": 3.6260804780999615e-05, "loss": 4.5122, "step": 6529 }, { "epoch": 0.35137752905725356, "grad_norm": 1.3910918235778809, "learning_rate": 3.625703141823311e-05, "loss": 4.9708, "step": 6530 }, { "epoch": 0.35143133878605254, "grad_norm": 2.4298670291900635, "learning_rate": 3.625325773377092e-05, "loss": 3.7146, "step": 6531 }, { "epoch": 0.35148514851485146, "grad_norm": 1.530332088470459, "learning_rate": 3.624948372772091e-05, "loss": 4.8824, "step": 6532 }, { "epoch": 0.35153895824365045, "grad_norm": 1.0906540155410767, "learning_rate": 3.62457094001909e-05, "loss": 4.6852, "step": 6533 }, { "epoch": 0.3515927679724494, "grad_norm": 1.8995425701141357, "learning_rate": 3.6241934751288763e-05, "loss": 4.4161, "step": 6534 }, { "epoch": 0.3516465777012484, "grad_norm": 2.1828203201293945, "learning_rate": 3.623815978112237e-05, "loss": 4.1483, "step": 6535 }, { "epoch": 0.35170038743004733, "grad_norm": 1.7471281290054321, "learning_rate": 3.6234384489799596e-05, "loss": 4.3615, "step": 6536 }, { "epoch": 0.3517541971588463, "grad_norm": 2.4216885566711426, "learning_rate": 3.623060887742833e-05, "loss": 4.1446, "step": 6537 }, { "epoch": 0.3518080068876453, "grad_norm": 2.4629082679748535, "learning_rate": 3.622683294411647e-05, "loss": 4.2581, "step": 6538 }, { "epoch": 0.3518618166164443, "grad_norm": 1.317460536956787, "learning_rate": 3.622305668997192e-05, "loss": 4.2197, "step": 6539 }, { "epoch": 0.3519156263452432, "grad_norm": 1.7514960765838623, "learning_rate": 3.6219280115102595e-05, "loss": 4.2638, "step": 6540 }, { "epoch": 0.3519694360740422, "grad_norm": 2.495011568069458, "learning_rate": 3.621550321961643e-05, "loss": 4.3208, "step": 6541 }, { "epoch": 0.35202324580284117, "grad_norm": 1.7254778146743774, "learning_rate": 3.621172600362134e-05, "loss": 4.7875, "step": 6542 }, { "epoch": 0.3520770555316401, "grad_norm": 2.514777660369873, "learning_rate": 3.620794846722528e-05, "loss": 3.9172, "step": 6543 }, { "epoch": 0.3521308652604391, "grad_norm": 1.810725212097168, "learning_rate": 3.62041706105362e-05, "loss": 4.2135, "step": 6544 }, { "epoch": 0.35218467498923806, "grad_norm": 1.4347270727157593, "learning_rate": 3.6200392433662056e-05, "loss": 4.0489, "step": 6545 }, { "epoch": 0.35223848471803704, "grad_norm": 1.8235571384429932, "learning_rate": 3.619661393671082e-05, "loss": 4.2375, "step": 6546 }, { "epoch": 0.35229229444683596, "grad_norm": 1.6858152151107788, "learning_rate": 3.6192835119790475e-05, "loss": 4.8892, "step": 6547 }, { "epoch": 0.35234610417563494, "grad_norm": 1.2350964546203613, "learning_rate": 3.6189055983009016e-05, "loss": 4.4501, "step": 6548 }, { "epoch": 0.3523999139044339, "grad_norm": 1.0611292123794556, "learning_rate": 3.618527652647442e-05, "loss": 4.2467, "step": 6549 }, { "epoch": 0.3524537236332329, "grad_norm": 3.353468179702759, "learning_rate": 3.6181496750294705e-05, "loss": 3.7324, "step": 6550 }, { "epoch": 0.35250753336203183, "grad_norm": 1.731328010559082, "learning_rate": 3.6177716654577895e-05, "loss": 4.0465, "step": 6551 }, { "epoch": 0.3525613430908308, "grad_norm": 1.61906898021698, "learning_rate": 3.6173936239432004e-05, "loss": 4.7436, "step": 6552 }, { "epoch": 0.3526151528196298, "grad_norm": 1.8683615922927856, "learning_rate": 3.617015550496507e-05, "loss": 4.5044, "step": 6553 }, { "epoch": 0.3526689625484288, "grad_norm": 1.941290259361267, "learning_rate": 3.616637445128514e-05, "loss": 3.9875, "step": 6554 }, { "epoch": 0.3527227722772277, "grad_norm": 2.542952060699463, "learning_rate": 3.6162593078500255e-05, "loss": 3.9182, "step": 6555 }, { "epoch": 0.3527765820060267, "grad_norm": 0.9068372249603271, "learning_rate": 3.6158811386718496e-05, "loss": 4.7658, "step": 6556 }, { "epoch": 0.35283039173482567, "grad_norm": 1.1788220405578613, "learning_rate": 3.615502937604791e-05, "loss": 4.462, "step": 6557 }, { "epoch": 0.35288420146362465, "grad_norm": 2.443765640258789, "learning_rate": 3.615124704659659e-05, "loss": 4.6101, "step": 6558 }, { "epoch": 0.3529380111924236, "grad_norm": 1.2288061380386353, "learning_rate": 3.6147464398472624e-05, "loss": 4.5048, "step": 6559 }, { "epoch": 0.35299182092122255, "grad_norm": 1.0004260540008545, "learning_rate": 3.614368143178411e-05, "loss": 4.482, "step": 6560 }, { "epoch": 0.35304563065002154, "grad_norm": 1.3903014659881592, "learning_rate": 3.613989814663915e-05, "loss": 4.2742, "step": 6561 }, { "epoch": 0.3530994403788205, "grad_norm": 1.220458745956421, "learning_rate": 3.6136114543145864e-05, "loss": 4.5056, "step": 6562 }, { "epoch": 0.35315325010761944, "grad_norm": 2.4335498809814453, "learning_rate": 3.613233062141238e-05, "loss": 4.3569, "step": 6563 }, { "epoch": 0.3532070598364184, "grad_norm": 2.293911933898926, "learning_rate": 3.6128546381546835e-05, "loss": 3.8649, "step": 6564 }, { "epoch": 0.3532608695652174, "grad_norm": 2.039529800415039, "learning_rate": 3.6124761823657355e-05, "loss": 4.5943, "step": 6565 }, { "epoch": 0.35331467929401633, "grad_norm": 0.9941785335540771, "learning_rate": 3.612097694785211e-05, "loss": 4.5327, "step": 6566 }, { "epoch": 0.3533684890228153, "grad_norm": 1.104340672492981, "learning_rate": 3.611719175423926e-05, "loss": 4.6188, "step": 6567 }, { "epoch": 0.3534222987516143, "grad_norm": 2.451888084411621, "learning_rate": 3.6113406242926964e-05, "loss": 4.2069, "step": 6568 }, { "epoch": 0.3534761084804133, "grad_norm": 3.100680112838745, "learning_rate": 3.610962041402341e-05, "loss": 3.8494, "step": 6569 }, { "epoch": 0.3535299182092122, "grad_norm": 1.2497518062591553, "learning_rate": 3.6105834267636786e-05, "loss": 3.9056, "step": 6570 }, { "epoch": 0.3535837279380112, "grad_norm": 1.91123628616333, "learning_rate": 3.610204780387529e-05, "loss": 4.8751, "step": 6571 }, { "epoch": 0.35363753766681016, "grad_norm": 1.7906028032302856, "learning_rate": 3.6098261022847134e-05, "loss": 4.6834, "step": 6572 }, { "epoch": 0.35369134739560915, "grad_norm": 1.3719385862350464, "learning_rate": 3.609447392466052e-05, "loss": 4.5631, "step": 6573 }, { "epoch": 0.35374515712440807, "grad_norm": 3.104863166809082, "learning_rate": 3.6090686509423685e-05, "loss": 4.1124, "step": 6574 }, { "epoch": 0.35379896685320705, "grad_norm": 2.759422779083252, "learning_rate": 3.608689877724486e-05, "loss": 4.2318, "step": 6575 }, { "epoch": 0.35385277658200603, "grad_norm": 1.4547278881072998, "learning_rate": 3.6083110728232295e-05, "loss": 5.0177, "step": 6576 }, { "epoch": 0.353906586310805, "grad_norm": 2.3849785327911377, "learning_rate": 3.607932236249423e-05, "loss": 3.6658, "step": 6577 }, { "epoch": 0.35396039603960394, "grad_norm": 1.5319228172302246, "learning_rate": 3.607553368013893e-05, "loss": 4.6601, "step": 6578 }, { "epoch": 0.3540142057684029, "grad_norm": 2.0542635917663574, "learning_rate": 3.6071744681274674e-05, "loss": 4.4486, "step": 6579 }, { "epoch": 0.3540680154972019, "grad_norm": 1.1503057479858398, "learning_rate": 3.606795536600972e-05, "loss": 4.8135, "step": 6580 }, { "epoch": 0.3541218252260009, "grad_norm": 2.3022117614746094, "learning_rate": 3.606416573445238e-05, "loss": 4.1786, "step": 6581 }, { "epoch": 0.3541756349547998, "grad_norm": 2.3539249897003174, "learning_rate": 3.606037578671095e-05, "loss": 3.8065, "step": 6582 }, { "epoch": 0.3542294446835988, "grad_norm": 1.4245072603225708, "learning_rate": 3.605658552289372e-05, "loss": 4.5758, "step": 6583 }, { "epoch": 0.3542832544123978, "grad_norm": 1.7321397066116333, "learning_rate": 3.605279494310901e-05, "loss": 4.1141, "step": 6584 }, { "epoch": 0.35433706414119676, "grad_norm": 1.9238792657852173, "learning_rate": 3.604900404746516e-05, "loss": 4.005, "step": 6585 }, { "epoch": 0.3543908738699957, "grad_norm": 2.119523763656616, "learning_rate": 3.604521283607049e-05, "loss": 4.2408, "step": 6586 }, { "epoch": 0.35444468359879466, "grad_norm": 2.448960781097412, "learning_rate": 3.604142130903334e-05, "loss": 4.468, "step": 6587 }, { "epoch": 0.35449849332759364, "grad_norm": 2.8864119052886963, "learning_rate": 3.603762946646207e-05, "loss": 4.099, "step": 6588 }, { "epoch": 0.35455230305639257, "grad_norm": 1.6382783651351929, "learning_rate": 3.6033837308465034e-05, "loss": 4.4142, "step": 6589 }, { "epoch": 0.35460611278519155, "grad_norm": 1.5318433046340942, "learning_rate": 3.603004483515061e-05, "loss": 4.6045, "step": 6590 }, { "epoch": 0.35465992251399053, "grad_norm": 1.9296619892120361, "learning_rate": 3.602625204662717e-05, "loss": 4.456, "step": 6591 }, { "epoch": 0.3547137322427895, "grad_norm": 1.6594629287719727, "learning_rate": 3.602245894300311e-05, "loss": 4.1845, "step": 6592 }, { "epoch": 0.35476754197158844, "grad_norm": 3.8364479541778564, "learning_rate": 3.6018665524386814e-05, "loss": 3.7114, "step": 6593 }, { "epoch": 0.3548213517003874, "grad_norm": 1.48049795627594, "learning_rate": 3.60148717908867e-05, "loss": 4.3635, "step": 6594 }, { "epoch": 0.3548751614291864, "grad_norm": 1.3509254455566406, "learning_rate": 3.601107774261117e-05, "loss": 4.5449, "step": 6595 }, { "epoch": 0.3549289711579854, "grad_norm": 2.184087038040161, "learning_rate": 3.600728337966866e-05, "loss": 4.7536, "step": 6596 }, { "epoch": 0.3549827808867843, "grad_norm": 1.7542983293533325, "learning_rate": 3.600348870216759e-05, "loss": 4.7405, "step": 6597 }, { "epoch": 0.3550365906155833, "grad_norm": 2.3390886783599854, "learning_rate": 3.5999693710216406e-05, "loss": 4.5018, "step": 6598 }, { "epoch": 0.3550904003443823, "grad_norm": 1.9300925731658936, "learning_rate": 3.599589840392357e-05, "loss": 4.5758, "step": 6599 }, { "epoch": 0.35514421007318125, "grad_norm": 2.0777881145477295, "learning_rate": 3.599210278339753e-05, "loss": 4.3019, "step": 6600 }, { "epoch": 0.3551980198019802, "grad_norm": 1.1653941869735718, "learning_rate": 3.598830684874676e-05, "loss": 4.3494, "step": 6601 }, { "epoch": 0.35525182953077916, "grad_norm": 1.2173128128051758, "learning_rate": 3.5984510600079734e-05, "loss": 4.7606, "step": 6602 }, { "epoch": 0.35530563925957814, "grad_norm": 2.5663599967956543, "learning_rate": 3.5980714037504936e-05, "loss": 4.5528, "step": 6603 }, { "epoch": 0.3553594489883771, "grad_norm": 1.4740480184555054, "learning_rate": 3.597691716113087e-05, "loss": 4.7128, "step": 6604 }, { "epoch": 0.35541325871717605, "grad_norm": 1.766663670539856, "learning_rate": 3.5973119971066036e-05, "loss": 4.3806, "step": 6605 }, { "epoch": 0.35546706844597503, "grad_norm": 1.8081557750701904, "learning_rate": 3.5969322467418945e-05, "loss": 4.3248, "step": 6606 }, { "epoch": 0.355520878174774, "grad_norm": 1.543766736984253, "learning_rate": 3.5965524650298126e-05, "loss": 4.2855, "step": 6607 }, { "epoch": 0.35557468790357294, "grad_norm": 2.4574148654937744, "learning_rate": 3.596172651981211e-05, "loss": 4.0341, "step": 6608 }, { "epoch": 0.3556284976323719, "grad_norm": 2.6113219261169434, "learning_rate": 3.595792807606943e-05, "loss": 3.9131, "step": 6609 }, { "epoch": 0.3556823073611709, "grad_norm": 2.9873087406158447, "learning_rate": 3.595412931917863e-05, "loss": 3.7261, "step": 6610 }, { "epoch": 0.3557361170899699, "grad_norm": 1.8955163955688477, "learning_rate": 3.595033024924828e-05, "loss": 4.3136, "step": 6611 }, { "epoch": 0.3557899268187688, "grad_norm": 1.4931554794311523, "learning_rate": 3.5946530866386946e-05, "loss": 4.4433, "step": 6612 }, { "epoch": 0.3558437365475678, "grad_norm": 1.3259025812149048, "learning_rate": 3.594273117070321e-05, "loss": 4.6146, "step": 6613 }, { "epoch": 0.35589754627636677, "grad_norm": 2.6301918029785156, "learning_rate": 3.593893116230564e-05, "loss": 4.2167, "step": 6614 }, { "epoch": 0.35595135600516575, "grad_norm": 1.434895396232605, "learning_rate": 3.593513084130285e-05, "loss": 4.8864, "step": 6615 }, { "epoch": 0.3560051657339647, "grad_norm": 1.1022182703018188, "learning_rate": 3.593133020780342e-05, "loss": 4.8006, "step": 6616 }, { "epoch": 0.35605897546276366, "grad_norm": 2.081779718399048, "learning_rate": 3.592752926191598e-05, "loss": 4.3925, "step": 6617 }, { "epoch": 0.35611278519156264, "grad_norm": 2.5438344478607178, "learning_rate": 3.592372800374915e-05, "loss": 4.4799, "step": 6618 }, { "epoch": 0.3561665949203616, "grad_norm": 2.114502429962158, "learning_rate": 3.5919926433411546e-05, "loss": 4.3088, "step": 6619 }, { "epoch": 0.35622040464916055, "grad_norm": 1.8609689474105835, "learning_rate": 3.591612455101182e-05, "loss": 4.3851, "step": 6620 }, { "epoch": 0.35627421437795953, "grad_norm": 2.0757932662963867, "learning_rate": 3.591232235665862e-05, "loss": 3.8792, "step": 6621 }, { "epoch": 0.3563280241067585, "grad_norm": 2.1238200664520264, "learning_rate": 3.5908519850460594e-05, "loss": 4.0726, "step": 6622 }, { "epoch": 0.3563818338355575, "grad_norm": 1.22910475730896, "learning_rate": 3.590471703252641e-05, "loss": 4.5831, "step": 6623 }, { "epoch": 0.3564356435643564, "grad_norm": 1.010130524635315, "learning_rate": 3.590091390296474e-05, "loss": 4.3835, "step": 6624 }, { "epoch": 0.3564894532931554, "grad_norm": 1.1507699489593506, "learning_rate": 3.589711046188428e-05, "loss": 4.6884, "step": 6625 }, { "epoch": 0.3565432630219544, "grad_norm": 2.7071220874786377, "learning_rate": 3.589330670939371e-05, "loss": 4.5338, "step": 6626 }, { "epoch": 0.35659707275075336, "grad_norm": 2.818171501159668, "learning_rate": 3.5889502645601724e-05, "loss": 3.7766, "step": 6627 }, { "epoch": 0.3566508824795523, "grad_norm": 1.6358330249786377, "learning_rate": 3.5885698270617054e-05, "loss": 4.4577, "step": 6628 }, { "epoch": 0.35670469220835127, "grad_norm": 1.7989997863769531, "learning_rate": 3.58818935845484e-05, "loss": 4.4994, "step": 6629 }, { "epoch": 0.35675850193715025, "grad_norm": 2.030308723449707, "learning_rate": 3.58780885875045e-05, "loss": 4.0096, "step": 6630 }, { "epoch": 0.3568123116659492, "grad_norm": 2.5766029357910156, "learning_rate": 3.587428327959409e-05, "loss": 4.3102, "step": 6631 }, { "epoch": 0.35686612139474816, "grad_norm": 2.0333969593048096, "learning_rate": 3.58704776609259e-05, "loss": 4.5007, "step": 6632 }, { "epoch": 0.35691993112354714, "grad_norm": 2.3874661922454834, "learning_rate": 3.586667173160871e-05, "loss": 4.3144, "step": 6633 }, { "epoch": 0.3569737408523461, "grad_norm": 1.5935403108596802, "learning_rate": 3.5862865491751255e-05, "loss": 4.615, "step": 6634 }, { "epoch": 0.35702755058114505, "grad_norm": 2.5159480571746826, "learning_rate": 3.585905894146233e-05, "loss": 4.163, "step": 6635 }, { "epoch": 0.35708136030994403, "grad_norm": 1.8340510129928589, "learning_rate": 3.585525208085072e-05, "loss": 4.4001, "step": 6636 }, { "epoch": 0.357135170038743, "grad_norm": 1.0435937643051147, "learning_rate": 3.585144491002518e-05, "loss": 4.551, "step": 6637 }, { "epoch": 0.357188979767542, "grad_norm": 1.1975884437561035, "learning_rate": 3.584763742909455e-05, "loss": 4.6031, "step": 6638 }, { "epoch": 0.3572427894963409, "grad_norm": 1.5809245109558105, "learning_rate": 3.584382963816761e-05, "loss": 4.2745, "step": 6639 }, { "epoch": 0.3572965992251399, "grad_norm": 2.3770720958709717, "learning_rate": 3.584002153735319e-05, "loss": 4.1374, "step": 6640 }, { "epoch": 0.3573504089539389, "grad_norm": 1.4618372917175293, "learning_rate": 3.58362131267601e-05, "loss": 4.257, "step": 6641 }, { "epoch": 0.35740421868273786, "grad_norm": 2.0474958419799805, "learning_rate": 3.583240440649719e-05, "loss": 4.7824, "step": 6642 }, { "epoch": 0.3574580284115368, "grad_norm": 2.160811185836792, "learning_rate": 3.58285953766733e-05, "loss": 4.2002, "step": 6643 }, { "epoch": 0.35751183814033577, "grad_norm": 1.7748140096664429, "learning_rate": 3.582478603739729e-05, "loss": 4.3628, "step": 6644 }, { "epoch": 0.35756564786913475, "grad_norm": 1.6249287128448486, "learning_rate": 3.5820976388777995e-05, "loss": 4.2379, "step": 6645 }, { "epoch": 0.35761945759793373, "grad_norm": 2.190133810043335, "learning_rate": 3.581716643092431e-05, "loss": 4.5719, "step": 6646 }, { "epoch": 0.35767326732673266, "grad_norm": 1.2597646713256836, "learning_rate": 3.5813356163945095e-05, "loss": 4.6031, "step": 6647 }, { "epoch": 0.35772707705553164, "grad_norm": 2.1974105834960938, "learning_rate": 3.580954558794925e-05, "loss": 5.2013, "step": 6648 }, { "epoch": 0.3577808867843306, "grad_norm": 0.9622034430503845, "learning_rate": 3.580573470304567e-05, "loss": 4.7262, "step": 6649 }, { "epoch": 0.35783469651312955, "grad_norm": 2.390171766281128, "learning_rate": 3.580192350934324e-05, "loss": 4.345, "step": 6650 }, { "epoch": 0.35788850624192853, "grad_norm": 1.9797616004943848, "learning_rate": 3.579811200695091e-05, "loss": 3.9109, "step": 6651 }, { "epoch": 0.3579423159707275, "grad_norm": 1.3805817365646362, "learning_rate": 3.579430019597757e-05, "loss": 4.7382, "step": 6652 }, { "epoch": 0.3579961256995265, "grad_norm": 2.4228146076202393, "learning_rate": 3.579048807653216e-05, "loss": 3.9088, "step": 6653 }, { "epoch": 0.3580499354283254, "grad_norm": 1.7580660581588745, "learning_rate": 3.578667564872364e-05, "loss": 4.5834, "step": 6654 }, { "epoch": 0.3581037451571244, "grad_norm": 1.4539470672607422, "learning_rate": 3.578286291266093e-05, "loss": 4.6746, "step": 6655 }, { "epoch": 0.3581575548859234, "grad_norm": 1.1932095289230347, "learning_rate": 3.5779049868453006e-05, "loss": 4.1779, "step": 6656 }, { "epoch": 0.35821136461472236, "grad_norm": 1.9588655233383179, "learning_rate": 3.577523651620883e-05, "loss": 4.4173, "step": 6657 }, { "epoch": 0.3582651743435213, "grad_norm": 1.7676578760147095, "learning_rate": 3.577142285603737e-05, "loss": 4.1327, "step": 6658 }, { "epoch": 0.35831898407232027, "grad_norm": 2.1685383319854736, "learning_rate": 3.576760888804762e-05, "loss": 4.4098, "step": 6659 }, { "epoch": 0.35837279380111925, "grad_norm": 1.5633628368377686, "learning_rate": 3.5763794612348566e-05, "loss": 4.2763, "step": 6660 }, { "epoch": 0.35842660352991823, "grad_norm": 1.7428932189941406, "learning_rate": 3.575998002904922e-05, "loss": 4.1868, "step": 6661 }, { "epoch": 0.35848041325871716, "grad_norm": 2.5216453075408936, "learning_rate": 3.575616513825858e-05, "loss": 4.589, "step": 6662 }, { "epoch": 0.35853422298751614, "grad_norm": 1.517256259918213, "learning_rate": 3.575234994008567e-05, "loss": 4.4932, "step": 6663 }, { "epoch": 0.3585880327163151, "grad_norm": 2.4031450748443604, "learning_rate": 3.5748534434639525e-05, "loss": 4.4124, "step": 6664 }, { "epoch": 0.3586418424451141, "grad_norm": 2.181847333908081, "learning_rate": 3.5744718622029175e-05, "loss": 4.2347, "step": 6665 }, { "epoch": 0.358695652173913, "grad_norm": 1.241944432258606, "learning_rate": 3.574090250236366e-05, "loss": 4.4717, "step": 6666 }, { "epoch": 0.358749461902712, "grad_norm": 1.861761450767517, "learning_rate": 3.573708607575205e-05, "loss": 4.6003, "step": 6667 }, { "epoch": 0.358803271631511, "grad_norm": 2.1574995517730713, "learning_rate": 3.5733269342303396e-05, "loss": 4.2863, "step": 6668 }, { "epoch": 0.35885708136030997, "grad_norm": 1.8455520868301392, "learning_rate": 3.572945230212677e-05, "loss": 4.3459, "step": 6669 }, { "epoch": 0.3589108910891089, "grad_norm": 2.066124200820923, "learning_rate": 3.572563495533126e-05, "loss": 4.1647, "step": 6670 }, { "epoch": 0.3589647008179079, "grad_norm": 1.4984543323516846, "learning_rate": 3.572181730202595e-05, "loss": 4.5246, "step": 6671 }, { "epoch": 0.35901851054670686, "grad_norm": 2.285595417022705, "learning_rate": 3.571799934231994e-05, "loss": 4.0758, "step": 6672 }, { "epoch": 0.3590723202755058, "grad_norm": 1.7354367971420288, "learning_rate": 3.5714181076322336e-05, "loss": 4.5362, "step": 6673 }, { "epoch": 0.35912613000430477, "grad_norm": 1.8440290689468384, "learning_rate": 3.571036250414226e-05, "loss": 4.5109, "step": 6674 }, { "epoch": 0.35917993973310375, "grad_norm": 1.309904932975769, "learning_rate": 3.5706543625888825e-05, "loss": 4.82, "step": 6675 }, { "epoch": 0.35923374946190273, "grad_norm": 1.5770808458328247, "learning_rate": 3.570272444167117e-05, "loss": 4.2716, "step": 6676 }, { "epoch": 0.35928755919070166, "grad_norm": 1.540902018547058, "learning_rate": 3.569890495159844e-05, "loss": 4.4399, "step": 6677 }, { "epoch": 0.35934136891950064, "grad_norm": 2.5322468280792236, "learning_rate": 3.569508515577978e-05, "loss": 3.918, "step": 6678 }, { "epoch": 0.3593951786482996, "grad_norm": 2.3521063327789307, "learning_rate": 3.569126505432436e-05, "loss": 4.6053, "step": 6679 }, { "epoch": 0.3594489883770986, "grad_norm": 2.579681158065796, "learning_rate": 3.568744464734134e-05, "loss": 3.4666, "step": 6680 }, { "epoch": 0.3595027981058975, "grad_norm": 2.3668434619903564, "learning_rate": 3.5683623934939884e-05, "loss": 4.1734, "step": 6681 }, { "epoch": 0.3595566078346965, "grad_norm": 2.24552059173584, "learning_rate": 3.567980291722921e-05, "loss": 4.4522, "step": 6682 }, { "epoch": 0.3596104175634955, "grad_norm": 2.1334335803985596, "learning_rate": 3.567598159431848e-05, "loss": 4.2629, "step": 6683 }, { "epoch": 0.35966422729229447, "grad_norm": 2.3327088356018066, "learning_rate": 3.567215996631692e-05, "loss": 3.7818, "step": 6684 }, { "epoch": 0.3597180370210934, "grad_norm": 1.8326631784439087, "learning_rate": 3.5668338033333724e-05, "loss": 4.2986, "step": 6685 }, { "epoch": 0.3597718467498924, "grad_norm": 2.481184720993042, "learning_rate": 3.566451579547813e-05, "loss": 3.791, "step": 6686 }, { "epoch": 0.35982565647869136, "grad_norm": 2.2162883281707764, "learning_rate": 3.5660693252859355e-05, "loss": 4.3462, "step": 6687 }, { "epoch": 0.35987946620749034, "grad_norm": 1.7570765018463135, "learning_rate": 3.565687040558665e-05, "loss": 4.9972, "step": 6688 }, { "epoch": 0.35993327593628927, "grad_norm": 1.1233153343200684, "learning_rate": 3.5653047253769236e-05, "loss": 4.7189, "step": 6689 }, { "epoch": 0.35998708566508825, "grad_norm": 1.5403778553009033, "learning_rate": 3.56492237975164e-05, "loss": 4.3685, "step": 6690 }, { "epoch": 0.36004089539388723, "grad_norm": 2.266389846801758, "learning_rate": 3.5645400036937375e-05, "loss": 4.2663, "step": 6691 }, { "epoch": 0.36009470512268615, "grad_norm": 2.4681320190429688, "learning_rate": 3.564157597214146e-05, "loss": 4.3347, "step": 6692 }, { "epoch": 0.36014851485148514, "grad_norm": 1.948994517326355, "learning_rate": 3.5637751603237924e-05, "loss": 4.1653, "step": 6693 }, { "epoch": 0.3602023245802841, "grad_norm": 1.3785817623138428, "learning_rate": 3.563392693033606e-05, "loss": 4.5205, "step": 6694 }, { "epoch": 0.3602561343090831, "grad_norm": 2.122072458267212, "learning_rate": 3.563010195354517e-05, "loss": 4.4415, "step": 6695 }, { "epoch": 0.360309944037882, "grad_norm": 1.2293530702590942, "learning_rate": 3.5626276672974543e-05, "loss": 4.8633, "step": 6696 }, { "epoch": 0.360363753766681, "grad_norm": 2.3649778366088867, "learning_rate": 3.562245108873353e-05, "loss": 4.4859, "step": 6697 }, { "epoch": 0.36041756349548, "grad_norm": 1.1923820972442627, "learning_rate": 3.561862520093143e-05, "loss": 4.5534, "step": 6698 }, { "epoch": 0.36047137322427897, "grad_norm": 2.8924758434295654, "learning_rate": 3.5614799009677576e-05, "loss": 3.7403, "step": 6699 }, { "epoch": 0.3605251829530779, "grad_norm": 2.145653009414673, "learning_rate": 3.561097251508132e-05, "loss": 4.4444, "step": 6700 }, { "epoch": 0.3605789926818769, "grad_norm": 1.1291844844818115, "learning_rate": 3.560714571725201e-05, "loss": 4.798, "step": 6701 }, { "epoch": 0.36063280241067586, "grad_norm": 1.9945348501205444, "learning_rate": 3.5603318616299005e-05, "loss": 4.4262, "step": 6702 }, { "epoch": 0.36068661213947484, "grad_norm": 1.0565145015716553, "learning_rate": 3.559949121233167e-05, "loss": 4.3411, "step": 6703 }, { "epoch": 0.36074042186827376, "grad_norm": 2.2045090198516846, "learning_rate": 3.5595663505459384e-05, "loss": 3.7164, "step": 6704 }, { "epoch": 0.36079423159707275, "grad_norm": 1.4527148008346558, "learning_rate": 3.559183549579155e-05, "loss": 4.3978, "step": 6705 }, { "epoch": 0.3608480413258717, "grad_norm": 1.8873844146728516, "learning_rate": 3.5588007183437525e-05, "loss": 4.6062, "step": 6706 }, { "epoch": 0.3609018510546707, "grad_norm": 1.8713315725326538, "learning_rate": 3.5584178568506746e-05, "loss": 4.466, "step": 6707 }, { "epoch": 0.36095566078346963, "grad_norm": 2.1517841815948486, "learning_rate": 3.558034965110861e-05, "loss": 4.3592, "step": 6708 }, { "epoch": 0.3610094705122686, "grad_norm": 2.160094976425171, "learning_rate": 3.557652043135254e-05, "loss": 4.1719, "step": 6709 }, { "epoch": 0.3610632802410676, "grad_norm": 2.087143898010254, "learning_rate": 3.557269090934796e-05, "loss": 4.3204, "step": 6710 }, { "epoch": 0.3611170899698666, "grad_norm": 2.715801954269409, "learning_rate": 3.5568861085204316e-05, "loss": 3.3738, "step": 6711 }, { "epoch": 0.3611708996986655, "grad_norm": 1.7707910537719727, "learning_rate": 3.5565030959031036e-05, "loss": 4.4556, "step": 6712 }, { "epoch": 0.3612247094274645, "grad_norm": 2.5664432048797607, "learning_rate": 3.5561200530937606e-05, "loss": 3.8648, "step": 6713 }, { "epoch": 0.36127851915626347, "grad_norm": 1.7582019567489624, "learning_rate": 3.5557369801033456e-05, "loss": 4.8806, "step": 6714 }, { "epoch": 0.3613323288850624, "grad_norm": 2.0964395999908447, "learning_rate": 3.555353876942808e-05, "loss": 4.3143, "step": 6715 }, { "epoch": 0.3613861386138614, "grad_norm": 0.9882799386978149, "learning_rate": 3.5549707436230955e-05, "loss": 4.2705, "step": 6716 }, { "epoch": 0.36143994834266036, "grad_norm": 2.5467844009399414, "learning_rate": 3.554587580155156e-05, "loss": 5.1517, "step": 6717 }, { "epoch": 0.36149375807145934, "grad_norm": 1.4343550205230713, "learning_rate": 3.55420438654994e-05, "loss": 4.4996, "step": 6718 }, { "epoch": 0.36154756780025826, "grad_norm": 1.7144075632095337, "learning_rate": 3.553821162818399e-05, "loss": 4.3196, "step": 6719 }, { "epoch": 0.36160137752905724, "grad_norm": 2.334303855895996, "learning_rate": 3.553437908971483e-05, "loss": 4.6748, "step": 6720 }, { "epoch": 0.3616551872578562, "grad_norm": 3.1411831378936768, "learning_rate": 3.5530546250201444e-05, "loss": 3.8049, "step": 6721 }, { "epoch": 0.3617089969866552, "grad_norm": 1.7776082754135132, "learning_rate": 3.5526713109753375e-05, "loss": 4.1831, "step": 6722 }, { "epoch": 0.36176280671545413, "grad_norm": 1.0356191396713257, "learning_rate": 3.552287966848016e-05, "loss": 4.7972, "step": 6723 }, { "epoch": 0.3618166164442531, "grad_norm": 1.0726888179779053, "learning_rate": 3.5519045926491346e-05, "loss": 4.5093, "step": 6724 }, { "epoch": 0.3618704261730521, "grad_norm": 2.7763254642486572, "learning_rate": 3.551521188389649e-05, "loss": 4.4476, "step": 6725 }, { "epoch": 0.3619242359018511, "grad_norm": 1.879714012145996, "learning_rate": 3.551137754080517e-05, "loss": 4.2593, "step": 6726 }, { "epoch": 0.36197804563065, "grad_norm": 1.6613487005233765, "learning_rate": 3.550754289732694e-05, "loss": 4.4598, "step": 6727 }, { "epoch": 0.362031855359449, "grad_norm": 1.7351149320602417, "learning_rate": 3.5503707953571406e-05, "loss": 4.8185, "step": 6728 }, { "epoch": 0.36208566508824797, "grad_norm": 1.0376702547073364, "learning_rate": 3.5499872709648146e-05, "loss": 4.5847, "step": 6729 }, { "epoch": 0.36213947481704695, "grad_norm": 2.2561028003692627, "learning_rate": 3.5496037165666764e-05, "loss": 4.2768, "step": 6730 }, { "epoch": 0.3621932845458459, "grad_norm": 2.25258731842041, "learning_rate": 3.5492201321736874e-05, "loss": 3.9461, "step": 6731 }, { "epoch": 0.36224709427464485, "grad_norm": 1.528804898262024, "learning_rate": 3.548836517796809e-05, "loss": 4.1193, "step": 6732 }, { "epoch": 0.36230090400344384, "grad_norm": 1.1519883871078491, "learning_rate": 3.548452873447003e-05, "loss": 4.5023, "step": 6733 }, { "epoch": 0.3623547137322428, "grad_norm": 2.238192558288574, "learning_rate": 3.5480691991352355e-05, "loss": 4.0747, "step": 6734 }, { "epoch": 0.36240852346104174, "grad_norm": 1.5322074890136719, "learning_rate": 3.547685494872468e-05, "loss": 4.9562, "step": 6735 }, { "epoch": 0.3624623331898407, "grad_norm": 2.2240898609161377, "learning_rate": 3.547301760669668e-05, "loss": 4.58, "step": 6736 }, { "epoch": 0.3625161429186397, "grad_norm": 1.106575846672058, "learning_rate": 3.5469179965378004e-05, "loss": 4.6736, "step": 6737 }, { "epoch": 0.36256995264743863, "grad_norm": 2.021780014038086, "learning_rate": 3.5465342024878315e-05, "loss": 4.5154, "step": 6738 }, { "epoch": 0.3626237623762376, "grad_norm": 1.9786736965179443, "learning_rate": 3.546150378530731e-05, "loss": 4.7703, "step": 6739 }, { "epoch": 0.3626775721050366, "grad_norm": 2.296865701675415, "learning_rate": 3.545766524677466e-05, "loss": 4.5773, "step": 6740 }, { "epoch": 0.3627313818338356, "grad_norm": 1.6844688653945923, "learning_rate": 3.5453826409390065e-05, "loss": 4.0479, "step": 6741 }, { "epoch": 0.3627851915626345, "grad_norm": 2.2471091747283936, "learning_rate": 3.544998727326323e-05, "loss": 4.9015, "step": 6742 }, { "epoch": 0.3628390012914335, "grad_norm": 1.1501864194869995, "learning_rate": 3.544614783850386e-05, "loss": 4.451, "step": 6743 }, { "epoch": 0.36289281102023246, "grad_norm": 2.1833505630493164, "learning_rate": 3.544230810522169e-05, "loss": 4.2122, "step": 6744 }, { "epoch": 0.36294662074903145, "grad_norm": 2.149744749069214, "learning_rate": 3.543846807352643e-05, "loss": 4.3994, "step": 6745 }, { "epoch": 0.36300043047783037, "grad_norm": 1.7938507795333862, "learning_rate": 3.543462774352784e-05, "loss": 4.7794, "step": 6746 }, { "epoch": 0.36305424020662935, "grad_norm": 1.1569517850875854, "learning_rate": 3.5430787115335656e-05, "loss": 4.4683, "step": 6747 }, { "epoch": 0.36310804993542833, "grad_norm": 2.6106739044189453, "learning_rate": 3.542694618905962e-05, "loss": 4.3181, "step": 6748 }, { "epoch": 0.3631618596642273, "grad_norm": 1.3635528087615967, "learning_rate": 3.542310496480952e-05, "loss": 4.7814, "step": 6749 }, { "epoch": 0.36321566939302624, "grad_norm": 1.8256161212921143, "learning_rate": 3.54192634426951e-05, "loss": 4.2435, "step": 6750 }, { "epoch": 0.3632694791218252, "grad_norm": 1.9949456453323364, "learning_rate": 3.541542162282617e-05, "loss": 4.4554, "step": 6751 }, { "epoch": 0.3633232888506242, "grad_norm": 2.9584853649139404, "learning_rate": 3.54115795053125e-05, "loss": 4.234, "step": 6752 }, { "epoch": 0.3633770985794232, "grad_norm": 1.7399548292160034, "learning_rate": 3.540773709026389e-05, "loss": 4.3356, "step": 6753 }, { "epoch": 0.3634309083082221, "grad_norm": 1.2165237665176392, "learning_rate": 3.540389437779015e-05, "loss": 4.7409, "step": 6754 }, { "epoch": 0.3634847180370211, "grad_norm": 1.5317481756210327, "learning_rate": 3.540005136800109e-05, "loss": 4.4088, "step": 6755 }, { "epoch": 0.3635385277658201, "grad_norm": 2.303922653198242, "learning_rate": 3.539620806100653e-05, "loss": 4.5345, "step": 6756 }, { "epoch": 0.363592337494619, "grad_norm": 2.467430591583252, "learning_rate": 3.539236445691631e-05, "loss": 4.6716, "step": 6757 }, { "epoch": 0.363646147223418, "grad_norm": 2.0057122707366943, "learning_rate": 3.538852055584027e-05, "loss": 4.4377, "step": 6758 }, { "epoch": 0.36369995695221696, "grad_norm": 2.2527899742126465, "learning_rate": 3.538467635788825e-05, "loss": 4.3359, "step": 6759 }, { "epoch": 0.36375376668101594, "grad_norm": 1.3265058994293213, "learning_rate": 3.5380831863170114e-05, "loss": 4.5039, "step": 6760 }, { "epoch": 0.36380757640981487, "grad_norm": 1.2309848070144653, "learning_rate": 3.5376987071795713e-05, "loss": 4.2358, "step": 6761 }, { "epoch": 0.36386138613861385, "grad_norm": 1.4054838418960571, "learning_rate": 3.537314198387495e-05, "loss": 4.6995, "step": 6762 }, { "epoch": 0.36391519586741283, "grad_norm": 2.0293407440185547, "learning_rate": 3.536929659951768e-05, "loss": 4.0887, "step": 6763 }, { "epoch": 0.3639690055962118, "grad_norm": 2.515467405319214, "learning_rate": 3.53654509188338e-05, "loss": 4.5837, "step": 6764 }, { "epoch": 0.36402281532501074, "grad_norm": 1.457566499710083, "learning_rate": 3.536160494193321e-05, "loss": 4.6375, "step": 6765 }, { "epoch": 0.3640766250538097, "grad_norm": 1.8784867525100708, "learning_rate": 3.535775866892583e-05, "loss": 3.8493, "step": 6766 }, { "epoch": 0.3641304347826087, "grad_norm": 2.138287305831909, "learning_rate": 3.535391209992157e-05, "loss": 4.3407, "step": 6767 }, { "epoch": 0.3641842445114077, "grad_norm": 2.267935276031494, "learning_rate": 3.535006523503034e-05, "loss": 4.0386, "step": 6768 }, { "epoch": 0.3642380542402066, "grad_norm": 2.451411247253418, "learning_rate": 3.5346218074362086e-05, "loss": 4.144, "step": 6769 }, { "epoch": 0.3642918639690056, "grad_norm": 1.804764986038208, "learning_rate": 3.5342370618026755e-05, "loss": 4.427, "step": 6770 }, { "epoch": 0.3643456736978046, "grad_norm": 2.1058096885681152, "learning_rate": 3.533852286613428e-05, "loss": 4.395, "step": 6771 }, { "epoch": 0.36439948342660355, "grad_norm": 0.9963899254798889, "learning_rate": 3.533467481879463e-05, "loss": 4.5354, "step": 6772 }, { "epoch": 0.3644532931554025, "grad_norm": 1.2776591777801514, "learning_rate": 3.533082647611778e-05, "loss": 4.6724, "step": 6773 }, { "epoch": 0.36450710288420146, "grad_norm": 2.296024799346924, "learning_rate": 3.5326977838213694e-05, "loss": 4.3778, "step": 6774 }, { "epoch": 0.36456091261300044, "grad_norm": 2.136625289916992, "learning_rate": 3.532312890519235e-05, "loss": 4.5195, "step": 6775 }, { "epoch": 0.3646147223417994, "grad_norm": 1.4061864614486694, "learning_rate": 3.5319279677163744e-05, "loss": 4.6406, "step": 6776 }, { "epoch": 0.36466853207059835, "grad_norm": 2.461212158203125, "learning_rate": 3.5315430154237896e-05, "loss": 4.1553, "step": 6777 }, { "epoch": 0.36472234179939733, "grad_norm": 2.1825919151306152, "learning_rate": 3.531158033652479e-05, "loss": 4.5406, "step": 6778 }, { "epoch": 0.3647761515281963, "grad_norm": 2.4309756755828857, "learning_rate": 3.530773022413445e-05, "loss": 4.4443, "step": 6779 }, { "epoch": 0.36482996125699524, "grad_norm": 1.6144362688064575, "learning_rate": 3.530387981717691e-05, "loss": 4.2327, "step": 6780 }, { "epoch": 0.3648837709857942, "grad_norm": 2.419163942337036, "learning_rate": 3.53000291157622e-05, "loss": 4.1804, "step": 6781 }, { "epoch": 0.3649375807145932, "grad_norm": 1.3788384199142456, "learning_rate": 3.529617812000035e-05, "loss": 4.2852, "step": 6782 }, { "epoch": 0.3649913904433922, "grad_norm": 1.7467727661132812, "learning_rate": 3.5292326830001444e-05, "loss": 4.3331, "step": 6783 }, { "epoch": 0.3650452001721911, "grad_norm": 1.8844434022903442, "learning_rate": 3.52884752458755e-05, "loss": 4.8361, "step": 6784 }, { "epoch": 0.3650990099009901, "grad_norm": 2.372986078262329, "learning_rate": 3.528462336773262e-05, "loss": 3.898, "step": 6785 }, { "epoch": 0.36515281962978907, "grad_norm": 2.1579179763793945, "learning_rate": 3.528077119568286e-05, "loss": 4.3367, "step": 6786 }, { "epoch": 0.36520662935858805, "grad_norm": 2.428731679916382, "learning_rate": 3.5276918729836314e-05, "loss": 4.1299, "step": 6787 }, { "epoch": 0.365260439087387, "grad_norm": 1.6816164255142212, "learning_rate": 3.527306597030307e-05, "loss": 4.0277, "step": 6788 }, { "epoch": 0.36531424881618596, "grad_norm": 1.9235351085662842, "learning_rate": 3.526921291719323e-05, "loss": 4.3369, "step": 6789 }, { "epoch": 0.36536805854498494, "grad_norm": 1.2831509113311768, "learning_rate": 3.5265359570616915e-05, "loss": 4.2755, "step": 6790 }, { "epoch": 0.3654218682737839, "grad_norm": 1.8898745775222778, "learning_rate": 3.526150593068422e-05, "loss": 4.2458, "step": 6791 }, { "epoch": 0.36547567800258285, "grad_norm": 2.4330201148986816, "learning_rate": 3.525765199750529e-05, "loss": 4.2122, "step": 6792 }, { "epoch": 0.36552948773138183, "grad_norm": 1.4780981540679932, "learning_rate": 3.5253797771190264e-05, "loss": 4.8613, "step": 6793 }, { "epoch": 0.3655832974601808, "grad_norm": 1.8884209394454956, "learning_rate": 3.524994325184927e-05, "loss": 4.5255, "step": 6794 }, { "epoch": 0.3656371071889798, "grad_norm": 1.6066514253616333, "learning_rate": 3.524608843959247e-05, "loss": 4.7738, "step": 6795 }, { "epoch": 0.3656909169177787, "grad_norm": 2.5939784049987793, "learning_rate": 3.524223333453002e-05, "loss": 4.2215, "step": 6796 }, { "epoch": 0.3657447266465777, "grad_norm": 1.2742503881454468, "learning_rate": 3.523837793677209e-05, "loss": 4.339, "step": 6797 }, { "epoch": 0.3657985363753767, "grad_norm": 0.9581944346427917, "learning_rate": 3.5234522246428864e-05, "loss": 4.7554, "step": 6798 }, { "epoch": 0.3658523461041756, "grad_norm": 1.2962900400161743, "learning_rate": 3.5230666263610506e-05, "loss": 4.0721, "step": 6799 }, { "epoch": 0.3659061558329746, "grad_norm": 1.4339394569396973, "learning_rate": 3.522680998842723e-05, "loss": 4.5746, "step": 6800 }, { "epoch": 0.36595996556177357, "grad_norm": 1.2114551067352295, "learning_rate": 3.5222953420989235e-05, "loss": 4.6272, "step": 6801 }, { "epoch": 0.36601377529057255, "grad_norm": 2.4824955463409424, "learning_rate": 3.521909656140672e-05, "loss": 4.1106, "step": 6802 }, { "epoch": 0.3660675850193715, "grad_norm": 1.4002079963684082, "learning_rate": 3.521523940978992e-05, "loss": 4.6979, "step": 6803 }, { "epoch": 0.36612139474817046, "grad_norm": 2.002977132797241, "learning_rate": 3.521138196624905e-05, "loss": 3.5724, "step": 6804 }, { "epoch": 0.36617520447696944, "grad_norm": 1.9178009033203125, "learning_rate": 3.520752423089435e-05, "loss": 4.3713, "step": 6805 }, { "epoch": 0.3662290142057684, "grad_norm": 1.2399667501449585, "learning_rate": 3.5203666203836056e-05, "loss": 4.6427, "step": 6806 }, { "epoch": 0.36628282393456735, "grad_norm": 1.3642680644989014, "learning_rate": 3.519980788518443e-05, "loss": 4.464, "step": 6807 }, { "epoch": 0.36633663366336633, "grad_norm": 0.9085761308670044, "learning_rate": 3.519594927504973e-05, "loss": 4.501, "step": 6808 }, { "epoch": 0.3663904433921653, "grad_norm": 1.7739611864089966, "learning_rate": 3.519209037354222e-05, "loss": 4.5826, "step": 6809 }, { "epoch": 0.3664442531209643, "grad_norm": 1.3744914531707764, "learning_rate": 3.518823118077219e-05, "loss": 4.3302, "step": 6810 }, { "epoch": 0.3664980628497632, "grad_norm": 1.920839548110962, "learning_rate": 3.518437169684991e-05, "loss": 4.4416, "step": 6811 }, { "epoch": 0.3665518725785622, "grad_norm": 2.8741519451141357, "learning_rate": 3.518051192188568e-05, "loss": 4.3383, "step": 6812 }, { "epoch": 0.3666056823073612, "grad_norm": 1.8398569822311401, "learning_rate": 3.5176651855989796e-05, "loss": 4.9427, "step": 6813 }, { "epoch": 0.36665949203616016, "grad_norm": 2.1311137676239014, "learning_rate": 3.5172791499272585e-05, "loss": 4.0161, "step": 6814 }, { "epoch": 0.3667133017649591, "grad_norm": 1.6573786735534668, "learning_rate": 3.516893085184434e-05, "loss": 4.3011, "step": 6815 }, { "epoch": 0.36676711149375807, "grad_norm": 2.446536064147949, "learning_rate": 3.516506991381542e-05, "loss": 4.5259, "step": 6816 }, { "epoch": 0.36682092122255705, "grad_norm": 1.8434720039367676, "learning_rate": 3.5161208685296126e-05, "loss": 3.9484, "step": 6817 }, { "epoch": 0.36687473095135603, "grad_norm": 1.2900489568710327, "learning_rate": 3.515734716639683e-05, "loss": 4.7588, "step": 6818 }, { "epoch": 0.36692854068015496, "grad_norm": 1.9325079917907715, "learning_rate": 3.5153485357227865e-05, "loss": 4.1906, "step": 6819 }, { "epoch": 0.36698235040895394, "grad_norm": 1.9085499048233032, "learning_rate": 3.514962325789961e-05, "loss": 4.172, "step": 6820 }, { "epoch": 0.3670361601377529, "grad_norm": 2.0553202629089355, "learning_rate": 3.5145760868522406e-05, "loss": 4.1434, "step": 6821 }, { "epoch": 0.36708996986655185, "grad_norm": 1.8841608762741089, "learning_rate": 3.514189818920666e-05, "loss": 4.229, "step": 6822 }, { "epoch": 0.3671437795953508, "grad_norm": 2.1736860275268555, "learning_rate": 3.513803522006273e-05, "loss": 4.2772, "step": 6823 }, { "epoch": 0.3671975893241498, "grad_norm": 1.4196394681930542, "learning_rate": 3.513417196120102e-05, "loss": 4.5955, "step": 6824 }, { "epoch": 0.3672513990529488, "grad_norm": 0.9997062683105469, "learning_rate": 3.5130308412731935e-05, "loss": 4.6082, "step": 6825 }, { "epoch": 0.3673052087817477, "grad_norm": 1.3642445802688599, "learning_rate": 3.512644457476589e-05, "loss": 4.6183, "step": 6826 }, { "epoch": 0.3673590185105467, "grad_norm": 2.3701441287994385, "learning_rate": 3.512258044741329e-05, "loss": 4.43, "step": 6827 }, { "epoch": 0.3674128282393457, "grad_norm": 1.5375126600265503, "learning_rate": 3.5118716030784576e-05, "loss": 4.6041, "step": 6828 }, { "epoch": 0.36746663796814466, "grad_norm": 1.784458875656128, "learning_rate": 3.511485132499017e-05, "loss": 4.6691, "step": 6829 }, { "epoch": 0.3675204476969436, "grad_norm": 1.1459834575653076, "learning_rate": 3.511098633014051e-05, "loss": 4.8161, "step": 6830 }, { "epoch": 0.36757425742574257, "grad_norm": 2.7620692253112793, "learning_rate": 3.510712104634607e-05, "loss": 4.4185, "step": 6831 }, { "epoch": 0.36762806715454155, "grad_norm": 1.6576199531555176, "learning_rate": 3.510325547371729e-05, "loss": 4.4814, "step": 6832 }, { "epoch": 0.36768187688334053, "grad_norm": 1.7877901792526245, "learning_rate": 3.509938961236464e-05, "loss": 4.4224, "step": 6833 }, { "epoch": 0.36773568661213946, "grad_norm": 2.571202278137207, "learning_rate": 3.509552346239859e-05, "loss": 3.8053, "step": 6834 }, { "epoch": 0.36778949634093844, "grad_norm": 1.4108080863952637, "learning_rate": 3.5091657023929654e-05, "loss": 4.5083, "step": 6835 }, { "epoch": 0.3678433060697374, "grad_norm": 1.499219536781311, "learning_rate": 3.508779029706829e-05, "loss": 4.3006, "step": 6836 }, { "epoch": 0.3678971157985364, "grad_norm": 1.9321191310882568, "learning_rate": 3.508392328192502e-05, "loss": 4.1541, "step": 6837 }, { "epoch": 0.3679509255273353, "grad_norm": 2.3162131309509277, "learning_rate": 3.508005597861034e-05, "loss": 4.5638, "step": 6838 }, { "epoch": 0.3680047352561343, "grad_norm": 1.0316156148910522, "learning_rate": 3.5076188387234775e-05, "loss": 4.5583, "step": 6839 }, { "epoch": 0.3680585449849333, "grad_norm": 2.247068405151367, "learning_rate": 3.507232050790884e-05, "loss": 4.7741, "step": 6840 }, { "epoch": 0.36811235471373227, "grad_norm": 1.6385728120803833, "learning_rate": 3.5068452340743086e-05, "loss": 4.6738, "step": 6841 }, { "epoch": 0.3681661644425312, "grad_norm": 1.7558187246322632, "learning_rate": 3.506458388584804e-05, "loss": 4.3618, "step": 6842 }, { "epoch": 0.3682199741713302, "grad_norm": 1.8480042219161987, "learning_rate": 3.5060715143334254e-05, "loss": 4.8089, "step": 6843 }, { "epoch": 0.36827378390012916, "grad_norm": 1.6428885459899902, "learning_rate": 3.50568461133123e-05, "loss": 4.3207, "step": 6844 }, { "epoch": 0.3683275936289281, "grad_norm": 1.4141957759857178, "learning_rate": 3.505297679589272e-05, "loss": 4.2415, "step": 6845 }, { "epoch": 0.36838140335772707, "grad_norm": 1.0373470783233643, "learning_rate": 3.504910719118611e-05, "loss": 4.5312, "step": 6846 }, { "epoch": 0.36843521308652605, "grad_norm": 2.59865403175354, "learning_rate": 3.504523729930305e-05, "loss": 3.8899, "step": 6847 }, { "epoch": 0.36848902281532503, "grad_norm": 2.2213284969329834, "learning_rate": 3.504136712035412e-05, "loss": 4.3154, "step": 6848 }, { "epoch": 0.36854283254412395, "grad_norm": 2.651655673980713, "learning_rate": 3.503749665444993e-05, "loss": 3.9591, "step": 6849 }, { "epoch": 0.36859664227292294, "grad_norm": 1.3826701641082764, "learning_rate": 3.503362590170108e-05, "loss": 4.5173, "step": 6850 }, { "epoch": 0.3686504520017219, "grad_norm": 1.4302892684936523, "learning_rate": 3.502975486221819e-05, "loss": 4.7082, "step": 6851 }, { "epoch": 0.3687042617305209, "grad_norm": 1.700528860092163, "learning_rate": 3.502588353611188e-05, "loss": 4.2573, "step": 6852 }, { "epoch": 0.3687580714593198, "grad_norm": 1.351751685142517, "learning_rate": 3.502201192349279e-05, "loss": 4.6848, "step": 6853 }, { "epoch": 0.3688118811881188, "grad_norm": 2.123739242553711, "learning_rate": 3.501814002447156e-05, "loss": 4.3638, "step": 6854 }, { "epoch": 0.3688656909169178, "grad_norm": 1.9228200912475586, "learning_rate": 3.501426783915882e-05, "loss": 4.0041, "step": 6855 }, { "epoch": 0.36891950064571677, "grad_norm": 1.9831246137619019, "learning_rate": 3.501039536766525e-05, "loss": 4.6751, "step": 6856 }, { "epoch": 0.3689733103745157, "grad_norm": 1.7313438653945923, "learning_rate": 3.50065226101015e-05, "loss": 4.5065, "step": 6857 }, { "epoch": 0.3690271201033147, "grad_norm": 1.7060785293579102, "learning_rate": 3.500264956657825e-05, "loss": 4.7276, "step": 6858 }, { "epoch": 0.36908092983211366, "grad_norm": 2.390657901763916, "learning_rate": 3.4998776237206185e-05, "loss": 3.7391, "step": 6859 }, { "epoch": 0.36913473956091264, "grad_norm": 1.4426593780517578, "learning_rate": 3.499490262209598e-05, "loss": 4.6448, "step": 6860 }, { "epoch": 0.36918854928971157, "grad_norm": 2.2328906059265137, "learning_rate": 3.4991028721358344e-05, "loss": 3.9777, "step": 6861 }, { "epoch": 0.36924235901851055, "grad_norm": 1.3876463174819946, "learning_rate": 3.498715453510398e-05, "loss": 4.7115, "step": 6862 }, { "epoch": 0.36929616874730953, "grad_norm": 1.96440589427948, "learning_rate": 3.498328006344361e-05, "loss": 4.0702, "step": 6863 }, { "epoch": 0.36934997847610845, "grad_norm": 1.1732016801834106, "learning_rate": 3.4979405306487935e-05, "loss": 4.6394, "step": 6864 }, { "epoch": 0.36940378820490744, "grad_norm": 0.9776656627655029, "learning_rate": 3.497553026434771e-05, "loss": 4.4441, "step": 6865 }, { "epoch": 0.3694575979337064, "grad_norm": 2.7464826107025146, "learning_rate": 3.497165493713365e-05, "loss": 3.3759, "step": 6866 }, { "epoch": 0.3695114076625054, "grad_norm": 1.9437540769577026, "learning_rate": 3.496777932495651e-05, "loss": 4.2536, "step": 6867 }, { "epoch": 0.3695652173913043, "grad_norm": 2.044172525405884, "learning_rate": 3.4963903427927056e-05, "loss": 4.362, "step": 6868 }, { "epoch": 0.3696190271201033, "grad_norm": 1.7900190353393555, "learning_rate": 3.496002724615604e-05, "loss": 4.6304, "step": 6869 }, { "epoch": 0.3696728368489023, "grad_norm": 2.35343861579895, "learning_rate": 3.495615077975424e-05, "loss": 4.1154, "step": 6870 }, { "epoch": 0.36972664657770127, "grad_norm": 2.60831356048584, "learning_rate": 3.4952274028832415e-05, "loss": 3.8902, "step": 6871 }, { "epoch": 0.3697804563065002, "grad_norm": 2.0072226524353027, "learning_rate": 3.494839699350138e-05, "loss": 4.4964, "step": 6872 }, { "epoch": 0.3698342660352992, "grad_norm": 1.5303610563278198, "learning_rate": 3.494451967387191e-05, "loss": 4.1553, "step": 6873 }, { "epoch": 0.36988807576409816, "grad_norm": 1.486019492149353, "learning_rate": 3.494064207005482e-05, "loss": 4.7761, "step": 6874 }, { "epoch": 0.36994188549289714, "grad_norm": 2.2837421894073486, "learning_rate": 3.493676418216091e-05, "loss": 4.3875, "step": 6875 }, { "epoch": 0.36999569522169606, "grad_norm": 2.043473243713379, "learning_rate": 3.493288601030101e-05, "loss": 4.0151, "step": 6876 }, { "epoch": 0.37004950495049505, "grad_norm": 1.637345314025879, "learning_rate": 3.492900755458595e-05, "loss": 4.2822, "step": 6877 }, { "epoch": 0.370103314679294, "grad_norm": 1.5310395956039429, "learning_rate": 3.492512881512655e-05, "loss": 4.6531, "step": 6878 }, { "epoch": 0.370157124408093, "grad_norm": 1.9472529888153076, "learning_rate": 3.492124979203367e-05, "loss": 4.1066, "step": 6879 }, { "epoch": 0.37021093413689193, "grad_norm": 1.9687927961349487, "learning_rate": 3.491737048541815e-05, "loss": 4.5162, "step": 6880 }, { "epoch": 0.3702647438656909, "grad_norm": 1.7108101844787598, "learning_rate": 3.491349089539087e-05, "loss": 4.081, "step": 6881 }, { "epoch": 0.3703185535944899, "grad_norm": 0.969792902469635, "learning_rate": 3.490961102206267e-05, "loss": 4.8139, "step": 6882 }, { "epoch": 0.3703723633232889, "grad_norm": 1.7644643783569336, "learning_rate": 3.490573086554445e-05, "loss": 4.0927, "step": 6883 }, { "epoch": 0.3704261730520878, "grad_norm": 1.375672459602356, "learning_rate": 3.4901850425947074e-05, "loss": 4.5005, "step": 6884 }, { "epoch": 0.3704799827808868, "grad_norm": 2.557331085205078, "learning_rate": 3.4897969703381464e-05, "loss": 4.3096, "step": 6885 }, { "epoch": 0.37053379250968577, "grad_norm": 1.1874879598617554, "learning_rate": 3.4894088697958485e-05, "loss": 4.5721, "step": 6886 }, { "epoch": 0.3705876022384847, "grad_norm": 2.1324894428253174, "learning_rate": 3.4890207409789064e-05, "loss": 4.7976, "step": 6887 }, { "epoch": 0.3706414119672837, "grad_norm": 1.3699045181274414, "learning_rate": 3.488632583898413e-05, "loss": 4.8173, "step": 6888 }, { "epoch": 0.37069522169608266, "grad_norm": 2.334594249725342, "learning_rate": 3.4882443985654586e-05, "loss": 4.3234, "step": 6889 }, { "epoch": 0.37074903142488164, "grad_norm": 1.445148229598999, "learning_rate": 3.487856184991137e-05, "loss": 4.7041, "step": 6890 }, { "epoch": 0.37080284115368056, "grad_norm": 1.9838154315948486, "learning_rate": 3.487467943186543e-05, "loss": 4.2853, "step": 6891 }, { "epoch": 0.37085665088247954, "grad_norm": 1.7185040712356567, "learning_rate": 3.487079673162771e-05, "loss": 4.2048, "step": 6892 }, { "epoch": 0.3709104606112785, "grad_norm": 1.2420413494110107, "learning_rate": 3.4866913749309176e-05, "loss": 4.5191, "step": 6893 }, { "epoch": 0.3709642703400775, "grad_norm": 1.8996312618255615, "learning_rate": 3.486303048502078e-05, "loss": 4.91, "step": 6894 }, { "epoch": 0.37101808006887643, "grad_norm": 1.6118789911270142, "learning_rate": 3.4859146938873496e-05, "loss": 4.3946, "step": 6895 }, { "epoch": 0.3710718897976754, "grad_norm": 1.2834129333496094, "learning_rate": 3.485526311097833e-05, "loss": 4.5585, "step": 6896 }, { "epoch": 0.3711256995264744, "grad_norm": 1.633543848991394, "learning_rate": 3.485137900144623e-05, "loss": 4.3071, "step": 6897 }, { "epoch": 0.3711795092552734, "grad_norm": 2.524049758911133, "learning_rate": 3.484749461038822e-05, "loss": 4.1683, "step": 6898 }, { "epoch": 0.3712333189840723, "grad_norm": 1.0637078285217285, "learning_rate": 3.484360993791531e-05, "loss": 4.4155, "step": 6899 }, { "epoch": 0.3712871287128713, "grad_norm": 1.5506664514541626, "learning_rate": 3.48397249841385e-05, "loss": 4.3588, "step": 6900 }, { "epoch": 0.37134093844167027, "grad_norm": 1.4975571632385254, "learning_rate": 3.4835839749168817e-05, "loss": 4.3737, "step": 6901 }, { "epoch": 0.37139474817046925, "grad_norm": 1.963207483291626, "learning_rate": 3.483195423311728e-05, "loss": 4.0522, "step": 6902 }, { "epoch": 0.3714485578992682, "grad_norm": 1.6779528856277466, "learning_rate": 3.482806843609494e-05, "loss": 4.2935, "step": 6903 }, { "epoch": 0.37150236762806715, "grad_norm": 2.0012142658233643, "learning_rate": 3.482418235821285e-05, "loss": 4.4717, "step": 6904 }, { "epoch": 0.37155617735686614, "grad_norm": 1.386324167251587, "learning_rate": 3.482029599958204e-05, "loss": 4.6933, "step": 6905 }, { "epoch": 0.37160998708566506, "grad_norm": 1.591030240058899, "learning_rate": 3.4816409360313584e-05, "loss": 4.6188, "step": 6906 }, { "epoch": 0.37166379681446404, "grad_norm": 1.3390270471572876, "learning_rate": 3.481252244051855e-05, "loss": 4.5376, "step": 6907 }, { "epoch": 0.371717606543263, "grad_norm": 1.2860181331634521, "learning_rate": 3.480863524030803e-05, "loss": 4.5207, "step": 6908 }, { "epoch": 0.371771416272062, "grad_norm": 2.451746940612793, "learning_rate": 3.480474775979309e-05, "loss": 4.3475, "step": 6909 }, { "epoch": 0.37182522600086093, "grad_norm": 1.3994152545928955, "learning_rate": 3.480085999908482e-05, "loss": 4.3089, "step": 6910 }, { "epoch": 0.3718790357296599, "grad_norm": 2.921841621398926, "learning_rate": 3.479697195829434e-05, "loss": 3.8691, "step": 6911 }, { "epoch": 0.3719328454584589, "grad_norm": 1.901922583580017, "learning_rate": 3.4793083637532755e-05, "loss": 4.5047, "step": 6912 }, { "epoch": 0.3719866551872579, "grad_norm": 2.4038684368133545, "learning_rate": 3.4789195036911184e-05, "loss": 4.1922, "step": 6913 }, { "epoch": 0.3720404649160568, "grad_norm": 1.1804251670837402, "learning_rate": 3.4785306156540745e-05, "loss": 4.2051, "step": 6914 }, { "epoch": 0.3720942746448558, "grad_norm": 1.7027438879013062, "learning_rate": 3.478141699653257e-05, "loss": 4.7215, "step": 6915 }, { "epoch": 0.37214808437365476, "grad_norm": 1.660919189453125, "learning_rate": 3.477752755699781e-05, "loss": 4.4392, "step": 6916 }, { "epoch": 0.37220189410245375, "grad_norm": 2.644979476928711, "learning_rate": 3.477363783804761e-05, "loss": 4.6661, "step": 6917 }, { "epoch": 0.37225570383125267, "grad_norm": 1.699452519416809, "learning_rate": 3.476974783979313e-05, "loss": 4.1104, "step": 6918 }, { "epoch": 0.37230951356005165, "grad_norm": 2.2527859210968018, "learning_rate": 3.476585756234554e-05, "loss": 4.8511, "step": 6919 }, { "epoch": 0.37236332328885063, "grad_norm": 2.4125823974609375, "learning_rate": 3.476196700581599e-05, "loss": 4.2306, "step": 6920 }, { "epoch": 0.3724171330176496, "grad_norm": 3.2301275730133057, "learning_rate": 3.4758076170315696e-05, "loss": 3.7904, "step": 6921 }, { "epoch": 0.37247094274644854, "grad_norm": 1.0532324314117432, "learning_rate": 3.475418505595583e-05, "loss": 4.403, "step": 6922 }, { "epoch": 0.3725247524752475, "grad_norm": 2.4864730834960938, "learning_rate": 3.475029366284759e-05, "loss": 4.5501, "step": 6923 }, { "epoch": 0.3725785622040465, "grad_norm": 2.1806509494781494, "learning_rate": 3.474640199110217e-05, "loss": 4.2976, "step": 6924 }, { "epoch": 0.3726323719328455, "grad_norm": 1.819743275642395, "learning_rate": 3.474251004083081e-05, "loss": 4.7615, "step": 6925 }, { "epoch": 0.3726861816616444, "grad_norm": 1.608228087425232, "learning_rate": 3.473861781214472e-05, "loss": 4.1497, "step": 6926 }, { "epoch": 0.3727399913904434, "grad_norm": 1.8383113145828247, "learning_rate": 3.473472530515511e-05, "loss": 4.4155, "step": 6927 }, { "epoch": 0.3727938011192424, "grad_norm": 3.1942226886749268, "learning_rate": 3.473083251997324e-05, "loss": 4.0737, "step": 6928 }, { "epoch": 0.3728476108480413, "grad_norm": 2.3317830562591553, "learning_rate": 3.472693945671036e-05, "loss": 4.5404, "step": 6929 }, { "epoch": 0.3729014205768403, "grad_norm": 2.2038960456848145, "learning_rate": 3.47230461154777e-05, "loss": 3.9003, "step": 6930 }, { "epoch": 0.37295523030563926, "grad_norm": 1.8101937770843506, "learning_rate": 3.471915249638654e-05, "loss": 4.7391, "step": 6931 }, { "epoch": 0.37300904003443824, "grad_norm": 2.5254580974578857, "learning_rate": 3.471525859954815e-05, "loss": 3.7527, "step": 6932 }, { "epoch": 0.37306284976323717, "grad_norm": 1.960589051246643, "learning_rate": 3.471136442507379e-05, "loss": 4.5611, "step": 6933 }, { "epoch": 0.37311665949203615, "grad_norm": 1.232918620109558, "learning_rate": 3.470746997307476e-05, "loss": 4.4424, "step": 6934 }, { "epoch": 0.37317046922083513, "grad_norm": 2.6987173557281494, "learning_rate": 3.4703575243662345e-05, "loss": 4.1498, "step": 6935 }, { "epoch": 0.3732242789496341, "grad_norm": 1.945183277130127, "learning_rate": 3.469968023694785e-05, "loss": 4.4756, "step": 6936 }, { "epoch": 0.37327808867843304, "grad_norm": 1.7252705097198486, "learning_rate": 3.469578495304258e-05, "loss": 4.4103, "step": 6937 }, { "epoch": 0.373331898407232, "grad_norm": 2.1145598888397217, "learning_rate": 3.469188939205786e-05, "loss": 4.3291, "step": 6938 }, { "epoch": 0.373385708136031, "grad_norm": 1.3740907907485962, "learning_rate": 3.468799355410501e-05, "loss": 4.2684, "step": 6939 }, { "epoch": 0.37343951786483, "grad_norm": 2.099287986755371, "learning_rate": 3.468409743929536e-05, "loss": 4.2193, "step": 6940 }, { "epoch": 0.3734933275936289, "grad_norm": 2.8710925579071045, "learning_rate": 3.4680201047740244e-05, "loss": 3.8171, "step": 6941 }, { "epoch": 0.3735471373224279, "grad_norm": 1.5163434743881226, "learning_rate": 3.4676304379551035e-05, "loss": 4.8446, "step": 6942 }, { "epoch": 0.3736009470512269, "grad_norm": 2.2954232692718506, "learning_rate": 3.467240743483906e-05, "loss": 3.777, "step": 6943 }, { "epoch": 0.37365475678002585, "grad_norm": 1.927728295326233, "learning_rate": 3.46685102137157e-05, "loss": 4.134, "step": 6944 }, { "epoch": 0.3737085665088248, "grad_norm": 1.8755130767822266, "learning_rate": 3.466461271629233e-05, "loss": 4.1937, "step": 6945 }, { "epoch": 0.37376237623762376, "grad_norm": 1.7652698755264282, "learning_rate": 3.466071494268032e-05, "loss": 4.7267, "step": 6946 }, { "epoch": 0.37381618596642274, "grad_norm": 3.085905075073242, "learning_rate": 3.465681689299105e-05, "loss": 3.7632, "step": 6947 }, { "epoch": 0.37386999569522167, "grad_norm": 1.686882495880127, "learning_rate": 3.4652918567335943e-05, "loss": 4.3477, "step": 6948 }, { "epoch": 0.37392380542402065, "grad_norm": 1.4686002731323242, "learning_rate": 3.4649019965826376e-05, "loss": 4.9969, "step": 6949 }, { "epoch": 0.37397761515281963, "grad_norm": 2.5380988121032715, "learning_rate": 3.464512108857377e-05, "loss": 3.85, "step": 6950 }, { "epoch": 0.3740314248816186, "grad_norm": 1.2949153184890747, "learning_rate": 3.464122193568955e-05, "loss": 4.1849, "step": 6951 }, { "epoch": 0.37408523461041754, "grad_norm": 1.9874366521835327, "learning_rate": 3.463732250728514e-05, "loss": 4.7043, "step": 6952 }, { "epoch": 0.3741390443392165, "grad_norm": 1.1912230253219604, "learning_rate": 3.4633422803471974e-05, "loss": 4.3395, "step": 6953 }, { "epoch": 0.3741928540680155, "grad_norm": 3.8858659267425537, "learning_rate": 3.462952282436149e-05, "loss": 3.988, "step": 6954 }, { "epoch": 0.3742466637968145, "grad_norm": 1.5166012048721313, "learning_rate": 3.462562257006515e-05, "loss": 4.6679, "step": 6955 }, { "epoch": 0.3743004735256134, "grad_norm": 2.7813568115234375, "learning_rate": 3.4621722040694405e-05, "loss": 4.272, "step": 6956 }, { "epoch": 0.3743542832544124, "grad_norm": 1.4531320333480835, "learning_rate": 3.4617821236360725e-05, "loss": 4.4364, "step": 6957 }, { "epoch": 0.37440809298321137, "grad_norm": 2.2814724445343018, "learning_rate": 3.461392015717558e-05, "loss": 4.4654, "step": 6958 }, { "epoch": 0.37446190271201035, "grad_norm": 1.7022614479064941, "learning_rate": 3.4610018803250456e-05, "loss": 4.7949, "step": 6959 }, { "epoch": 0.3745157124408093, "grad_norm": 1.248529076576233, "learning_rate": 3.4606117174696846e-05, "loss": 4.6473, "step": 6960 }, { "epoch": 0.37456952216960826, "grad_norm": 2.356023073196411, "learning_rate": 3.4602215271626234e-05, "loss": 4.2179, "step": 6961 }, { "epoch": 0.37462333189840724, "grad_norm": 1.522220492362976, "learning_rate": 3.459831309415015e-05, "loss": 4.4317, "step": 6962 }, { "epoch": 0.3746771416272062, "grad_norm": 1.6318687200546265, "learning_rate": 3.459441064238009e-05, "loss": 4.3716, "step": 6963 }, { "epoch": 0.37473095135600515, "grad_norm": 1.3625643253326416, "learning_rate": 3.459050791642757e-05, "loss": 4.8545, "step": 6964 }, { "epoch": 0.37478476108480413, "grad_norm": 1.4612013101577759, "learning_rate": 3.458660491640415e-05, "loss": 4.7875, "step": 6965 }, { "epoch": 0.3748385708136031, "grad_norm": 1.71518874168396, "learning_rate": 3.458270164242133e-05, "loss": 4.5785, "step": 6966 }, { "epoch": 0.3748923805424021, "grad_norm": 1.3797568082809448, "learning_rate": 3.457879809459067e-05, "loss": 4.5339, "step": 6967 }, { "epoch": 0.374946190271201, "grad_norm": 1.8449482917785645, "learning_rate": 3.4574894273023734e-05, "loss": 4.7783, "step": 6968 }, { "epoch": 0.375, "grad_norm": 1.8158231973648071, "learning_rate": 3.457099017783207e-05, "loss": 4.875, "step": 6969 }, { "epoch": 0.375053809728799, "grad_norm": 1.882753849029541, "learning_rate": 3.456708580912725e-05, "loss": 4.573, "step": 6970 }, { "epoch": 0.3751076194575979, "grad_norm": 1.549521565437317, "learning_rate": 3.4563181167020846e-05, "loss": 4.6893, "step": 6971 }, { "epoch": 0.3751614291863969, "grad_norm": 1.0714176893234253, "learning_rate": 3.455927625162445e-05, "loss": 4.4085, "step": 6972 }, { "epoch": 0.37521523891519587, "grad_norm": 1.2163972854614258, "learning_rate": 3.455537106304965e-05, "loss": 4.4617, "step": 6973 }, { "epoch": 0.37526904864399485, "grad_norm": 1.2296429872512817, "learning_rate": 3.4551465601408036e-05, "loss": 4.3438, "step": 6974 }, { "epoch": 0.3753228583727938, "grad_norm": 3.2362654209136963, "learning_rate": 3.454755986681124e-05, "loss": 3.4512, "step": 6975 }, { "epoch": 0.37537666810159276, "grad_norm": 1.1117494106292725, "learning_rate": 3.454365385937086e-05, "loss": 4.6335, "step": 6976 }, { "epoch": 0.37543047783039174, "grad_norm": 1.2986279726028442, "learning_rate": 3.453974757919852e-05, "loss": 4.2711, "step": 6977 }, { "epoch": 0.3754842875591907, "grad_norm": 1.2917509078979492, "learning_rate": 3.453584102640585e-05, "loss": 4.5219, "step": 6978 }, { "epoch": 0.37553809728798965, "grad_norm": 2.596921920776367, "learning_rate": 3.4531934201104494e-05, "loss": 4.2213, "step": 6979 }, { "epoch": 0.37559190701678863, "grad_norm": 1.6539651155471802, "learning_rate": 3.452802710340609e-05, "loss": 4.3139, "step": 6980 }, { "epoch": 0.3756457167455876, "grad_norm": 1.6178821325302124, "learning_rate": 3.452411973342231e-05, "loss": 4.596, "step": 6981 }, { "epoch": 0.3756995264743866, "grad_norm": 2.23540997505188, "learning_rate": 3.4520212091264806e-05, "loss": 4.0974, "step": 6982 }, { "epoch": 0.3757533362031855, "grad_norm": 2.1165459156036377, "learning_rate": 3.451630417704523e-05, "loss": 4.2421, "step": 6983 }, { "epoch": 0.3758071459319845, "grad_norm": 1.3933110237121582, "learning_rate": 3.451239599087529e-05, "loss": 4.1056, "step": 6984 }, { "epoch": 0.3758609556607835, "grad_norm": 2.43271541595459, "learning_rate": 3.450848753286666e-05, "loss": 4.2932, "step": 6985 }, { "epoch": 0.37591476538958246, "grad_norm": 1.2443335056304932, "learning_rate": 3.450457880313103e-05, "loss": 4.4177, "step": 6986 }, { "epoch": 0.3759685751183814, "grad_norm": 1.4400361776351929, "learning_rate": 3.450066980178009e-05, "loss": 4.5006, "step": 6987 }, { "epoch": 0.37602238484718037, "grad_norm": 1.5443949699401855, "learning_rate": 3.449676052892558e-05, "loss": 4.6836, "step": 6988 }, { "epoch": 0.37607619457597935, "grad_norm": 1.8858617544174194, "learning_rate": 3.449285098467919e-05, "loss": 4.2052, "step": 6989 }, { "epoch": 0.37613000430477833, "grad_norm": 1.9937357902526855, "learning_rate": 3.448894116915264e-05, "loss": 4.1063, "step": 6990 }, { "epoch": 0.37618381403357726, "grad_norm": 1.8312793970108032, "learning_rate": 3.448503108245768e-05, "loss": 4.4067, "step": 6991 }, { "epoch": 0.37623762376237624, "grad_norm": 1.4989911317825317, "learning_rate": 3.4481120724706054e-05, "loss": 4.5343, "step": 6992 }, { "epoch": 0.3762914334911752, "grad_norm": 1.8981103897094727, "learning_rate": 3.447721009600949e-05, "loss": 4.69, "step": 6993 }, { "epoch": 0.37634524321997415, "grad_norm": 1.3982292413711548, "learning_rate": 3.4473299196479746e-05, "loss": 4.8822, "step": 6994 }, { "epoch": 0.3763990529487731, "grad_norm": 2.5143039226531982, "learning_rate": 3.44693880262286e-05, "loss": 4.424, "step": 6995 }, { "epoch": 0.3764528626775721, "grad_norm": 3.1334402561187744, "learning_rate": 3.446547658536782e-05, "loss": 4.5151, "step": 6996 }, { "epoch": 0.3765066724063711, "grad_norm": 1.3079018592834473, "learning_rate": 3.446156487400917e-05, "loss": 4.4598, "step": 6997 }, { "epoch": 0.37656048213517, "grad_norm": 1.25110924243927, "learning_rate": 3.4457652892264435e-05, "loss": 4.3101, "step": 6998 }, { "epoch": 0.376614291863969, "grad_norm": 1.703813076019287, "learning_rate": 3.445374064024543e-05, "loss": 4.3172, "step": 6999 }, { "epoch": 0.376668101592768, "grad_norm": 1.363983392715454, "learning_rate": 3.4449828118063945e-05, "loss": 4.6938, "step": 7000 }, { "epoch": 0.37672191132156696, "grad_norm": 1.4648808240890503, "learning_rate": 3.4445915325831785e-05, "loss": 4.4754, "step": 7001 }, { "epoch": 0.3767757210503659, "grad_norm": 1.416914463043213, "learning_rate": 3.4442002263660776e-05, "loss": 4.4584, "step": 7002 }, { "epoch": 0.37682953077916487, "grad_norm": 1.8495423793792725, "learning_rate": 3.443808893166274e-05, "loss": 4.5661, "step": 7003 }, { "epoch": 0.37688334050796385, "grad_norm": 1.6052824258804321, "learning_rate": 3.44341753299495e-05, "loss": 4.56, "step": 7004 }, { "epoch": 0.37693715023676283, "grad_norm": 1.5256626605987549, "learning_rate": 3.443026145863291e-05, "loss": 4.6839, "step": 7005 }, { "epoch": 0.37699095996556176, "grad_norm": 1.6630953550338745, "learning_rate": 3.442634731782481e-05, "loss": 4.008, "step": 7006 }, { "epoch": 0.37704476969436074, "grad_norm": 1.4718151092529297, "learning_rate": 3.442243290763706e-05, "loss": 4.3092, "step": 7007 }, { "epoch": 0.3770985794231597, "grad_norm": 1.41474187374115, "learning_rate": 3.441851822818152e-05, "loss": 4.614, "step": 7008 }, { "epoch": 0.3771523891519587, "grad_norm": 2.2417595386505127, "learning_rate": 3.441460327957006e-05, "loss": 4.3305, "step": 7009 }, { "epoch": 0.3772061988807576, "grad_norm": 1.4478099346160889, "learning_rate": 3.441068806191456e-05, "loss": 4.3905, "step": 7010 }, { "epoch": 0.3772600086095566, "grad_norm": 2.4137988090515137, "learning_rate": 3.440677257532691e-05, "loss": 4.169, "step": 7011 }, { "epoch": 0.3773138183383556, "grad_norm": 1.4160789251327515, "learning_rate": 3.440285681991899e-05, "loss": 4.5393, "step": 7012 }, { "epoch": 0.3773676280671545, "grad_norm": 2.5786831378936768, "learning_rate": 3.4398940795802724e-05, "loss": 3.9368, "step": 7013 }, { "epoch": 0.3774214377959535, "grad_norm": 1.6846044063568115, "learning_rate": 3.439502450309001e-05, "loss": 4.5239, "step": 7014 }, { "epoch": 0.3774752475247525, "grad_norm": 1.7028402090072632, "learning_rate": 3.4391107941892766e-05, "loss": 4.0561, "step": 7015 }, { "epoch": 0.37752905725355146, "grad_norm": 2.1878349781036377, "learning_rate": 3.4387191112322915e-05, "loss": 4.1494, "step": 7016 }, { "epoch": 0.3775828669823504, "grad_norm": 2.369276762008667, "learning_rate": 3.4383274014492384e-05, "loss": 4.1033, "step": 7017 }, { "epoch": 0.37763667671114937, "grad_norm": 2.0434069633483887, "learning_rate": 3.437935664851313e-05, "loss": 4.6971, "step": 7018 }, { "epoch": 0.37769048643994835, "grad_norm": 1.0104498863220215, "learning_rate": 3.437543901449709e-05, "loss": 4.7834, "step": 7019 }, { "epoch": 0.37774429616874733, "grad_norm": 1.8628910779953003, "learning_rate": 3.437152111255621e-05, "loss": 4.2556, "step": 7020 }, { "epoch": 0.37779810589754625, "grad_norm": 1.675428032875061, "learning_rate": 3.436760294280246e-05, "loss": 4.6454, "step": 7021 }, { "epoch": 0.37785191562634524, "grad_norm": 2.803342342376709, "learning_rate": 3.436368450534783e-05, "loss": 4.23, "step": 7022 }, { "epoch": 0.3779057253551442, "grad_norm": 1.836426854133606, "learning_rate": 3.4359765800304274e-05, "loss": 4.5742, "step": 7023 }, { "epoch": 0.3779595350839432, "grad_norm": 2.554830551147461, "learning_rate": 3.4355846827783784e-05, "loss": 3.9474, "step": 7024 }, { "epoch": 0.3780133448127421, "grad_norm": 1.584956407546997, "learning_rate": 3.435192758789836e-05, "loss": 4.4143, "step": 7025 }, { "epoch": 0.3780671545415411, "grad_norm": 1.7253087759017944, "learning_rate": 3.4348008080759996e-05, "loss": 3.6353, "step": 7026 }, { "epoch": 0.3781209642703401, "grad_norm": 2.443298101425171, "learning_rate": 3.434408830648071e-05, "loss": 3.9977, "step": 7027 }, { "epoch": 0.37817477399913907, "grad_norm": 1.2132667303085327, "learning_rate": 3.4340168265172507e-05, "loss": 4.6039, "step": 7028 }, { "epoch": 0.378228583727938, "grad_norm": 2.7240421772003174, "learning_rate": 3.433624795694741e-05, "loss": 4.1927, "step": 7029 }, { "epoch": 0.378282393456737, "grad_norm": 0.9861341714859009, "learning_rate": 3.4332327381917476e-05, "loss": 4.4989, "step": 7030 }, { "epoch": 0.37833620318553596, "grad_norm": 1.9406567811965942, "learning_rate": 3.432840654019471e-05, "loss": 4.2326, "step": 7031 }, { "epoch": 0.37839001291433494, "grad_norm": 1.999891757965088, "learning_rate": 3.432448543189119e-05, "loss": 4.4736, "step": 7032 }, { "epoch": 0.37844382264313386, "grad_norm": 1.5614615678787231, "learning_rate": 3.432056405711895e-05, "loss": 4.7825, "step": 7033 }, { "epoch": 0.37849763237193285, "grad_norm": 2.1908223628997803, "learning_rate": 3.4316642415990055e-05, "loss": 4.1918, "step": 7034 }, { "epoch": 0.3785514421007318, "grad_norm": 2.4582674503326416, "learning_rate": 3.431272050861659e-05, "loss": 3.8955, "step": 7035 }, { "epoch": 0.37860525182953075, "grad_norm": 2.023678779602051, "learning_rate": 3.43087983351106e-05, "loss": 4.3786, "step": 7036 }, { "epoch": 0.37865906155832973, "grad_norm": 2.0884757041931152, "learning_rate": 3.430487589558421e-05, "loss": 4.2116, "step": 7037 }, { "epoch": 0.3787128712871287, "grad_norm": 3.0307631492614746, "learning_rate": 3.4300953190149485e-05, "loss": 3.8521, "step": 7038 }, { "epoch": 0.3787666810159277, "grad_norm": 2.189438581466675, "learning_rate": 3.4297030218918534e-05, "loss": 3.8012, "step": 7039 }, { "epoch": 0.3788204907447266, "grad_norm": 1.7095732688903809, "learning_rate": 3.4293106982003475e-05, "loss": 5.018, "step": 7040 }, { "epoch": 0.3788743004735256, "grad_norm": 1.8974822759628296, "learning_rate": 3.428918347951641e-05, "loss": 4.7463, "step": 7041 }, { "epoch": 0.3789281102023246, "grad_norm": 2.8511157035827637, "learning_rate": 3.4285259711569465e-05, "loss": 3.7501, "step": 7042 }, { "epoch": 0.37898191993112357, "grad_norm": 2.6455278396606445, "learning_rate": 3.428133567827477e-05, "loss": 4.6335, "step": 7043 }, { "epoch": 0.3790357296599225, "grad_norm": 1.9418715238571167, "learning_rate": 3.427741137974446e-05, "loss": 4.6936, "step": 7044 }, { "epoch": 0.3790895393887215, "grad_norm": 1.894243597984314, "learning_rate": 3.4273486816090696e-05, "loss": 3.8754, "step": 7045 }, { "epoch": 0.37914334911752046, "grad_norm": 2.366438627243042, "learning_rate": 3.426956198742561e-05, "loss": 4.4815, "step": 7046 }, { "epoch": 0.37919715884631944, "grad_norm": 1.5608367919921875, "learning_rate": 3.4265636893861385e-05, "loss": 4.5809, "step": 7047 }, { "epoch": 0.37925096857511836, "grad_norm": 2.0531179904937744, "learning_rate": 3.4261711535510175e-05, "loss": 4.0974, "step": 7048 }, { "epoch": 0.37930477830391734, "grad_norm": 1.7785961627960205, "learning_rate": 3.425778591248417e-05, "loss": 4.2517, "step": 7049 }, { "epoch": 0.3793585880327163, "grad_norm": 1.4034842252731323, "learning_rate": 3.4253860024895536e-05, "loss": 4.4689, "step": 7050 }, { "epoch": 0.3794123977615153, "grad_norm": 1.1039237976074219, "learning_rate": 3.424993387285647e-05, "loss": 4.474, "step": 7051 }, { "epoch": 0.37946620749031423, "grad_norm": 1.9769164323806763, "learning_rate": 3.424600745647917e-05, "loss": 4.469, "step": 7052 }, { "epoch": 0.3795200172191132, "grad_norm": 2.035170793533325, "learning_rate": 3.424208077587586e-05, "loss": 4.3216, "step": 7053 }, { "epoch": 0.3795738269479122, "grad_norm": 2.21182918548584, "learning_rate": 3.423815383115873e-05, "loss": 4.3389, "step": 7054 }, { "epoch": 0.3796276366767111, "grad_norm": 1.857877254486084, "learning_rate": 3.423422662244001e-05, "loss": 4.6006, "step": 7055 }, { "epoch": 0.3796814464055101, "grad_norm": 1.3621408939361572, "learning_rate": 3.4230299149831936e-05, "loss": 4.5149, "step": 7056 }, { "epoch": 0.3797352561343091, "grad_norm": 1.7245666980743408, "learning_rate": 3.422637141344673e-05, "loss": 4.4959, "step": 7057 }, { "epoch": 0.37978906586310807, "grad_norm": 2.5199477672576904, "learning_rate": 3.4222443413396656e-05, "loss": 3.6576, "step": 7058 }, { "epoch": 0.379842875591907, "grad_norm": 1.146685004234314, "learning_rate": 3.421851514979395e-05, "loss": 4.5026, "step": 7059 }, { "epoch": 0.379896685320706, "grad_norm": 1.4128750562667847, "learning_rate": 3.421458662275087e-05, "loss": 4.4504, "step": 7060 }, { "epoch": 0.37995049504950495, "grad_norm": 1.5710042715072632, "learning_rate": 3.42106578323797e-05, "loss": 4.5594, "step": 7061 }, { "epoch": 0.38000430477830394, "grad_norm": 1.5142474174499512, "learning_rate": 3.420672877879269e-05, "loss": 4.5294, "step": 7062 }, { "epoch": 0.38005811450710286, "grad_norm": 1.3966419696807861, "learning_rate": 3.420279946210214e-05, "loss": 4.5073, "step": 7063 }, { "epoch": 0.38011192423590184, "grad_norm": 2.053368330001831, "learning_rate": 3.4198869882420334e-05, "loss": 4.5823, "step": 7064 }, { "epoch": 0.3801657339647008, "grad_norm": 1.2066504955291748, "learning_rate": 3.419494003985957e-05, "loss": 4.5376, "step": 7065 }, { "epoch": 0.3802195436934998, "grad_norm": 1.1118866205215454, "learning_rate": 3.419100993453216e-05, "loss": 4.599, "step": 7066 }, { "epoch": 0.38027335342229873, "grad_norm": 2.1255035400390625, "learning_rate": 3.4187079566550387e-05, "loss": 4.1599, "step": 7067 }, { "epoch": 0.3803271631510977, "grad_norm": 1.7029143571853638, "learning_rate": 3.418314893602661e-05, "loss": 4.7094, "step": 7068 }, { "epoch": 0.3803809728798967, "grad_norm": 2.4931180477142334, "learning_rate": 3.417921804307313e-05, "loss": 4.3022, "step": 7069 }, { "epoch": 0.3804347826086957, "grad_norm": 2.147596597671509, "learning_rate": 3.417528688780228e-05, "loss": 4.1184, "step": 7070 }, { "epoch": 0.3804885923374946, "grad_norm": 2.6363320350646973, "learning_rate": 3.4171355470326414e-05, "loss": 3.5868, "step": 7071 }, { "epoch": 0.3805424020662936, "grad_norm": 2.772479772567749, "learning_rate": 3.416742379075788e-05, "loss": 3.6768, "step": 7072 }, { "epoch": 0.38059621179509256, "grad_norm": 1.6391841173171997, "learning_rate": 3.416349184920903e-05, "loss": 4.7837, "step": 7073 }, { "epoch": 0.38065002152389155, "grad_norm": 1.5166910886764526, "learning_rate": 3.415955964579223e-05, "loss": 4.5344, "step": 7074 }, { "epoch": 0.38070383125269047, "grad_norm": 2.5366339683532715, "learning_rate": 3.4155627180619845e-05, "loss": 4.0001, "step": 7075 }, { "epoch": 0.38075764098148945, "grad_norm": 3.136254072189331, "learning_rate": 3.4151694453804275e-05, "loss": 4.0606, "step": 7076 }, { "epoch": 0.38081145071028843, "grad_norm": 2.1462230682373047, "learning_rate": 3.414776146545787e-05, "loss": 4.9351, "step": 7077 }, { "epoch": 0.38086526043908736, "grad_norm": 2.2248001098632812, "learning_rate": 3.414382821569307e-05, "loss": 3.7069, "step": 7078 }, { "epoch": 0.38091907016788634, "grad_norm": 2.7225186824798584, "learning_rate": 3.4139894704622245e-05, "loss": 2.9937, "step": 7079 }, { "epoch": 0.3809728798966853, "grad_norm": 1.2833967208862305, "learning_rate": 3.413596093235781e-05, "loss": 4.5807, "step": 7080 }, { "epoch": 0.3810266896254843, "grad_norm": 2.2207024097442627, "learning_rate": 3.413202689901219e-05, "loss": 4.2398, "step": 7081 }, { "epoch": 0.38108049935428323, "grad_norm": 2.44356369972229, "learning_rate": 3.41280926046978e-05, "loss": 4.2393, "step": 7082 }, { "epoch": 0.3811343090830822, "grad_norm": 1.5914119482040405, "learning_rate": 3.412415804952708e-05, "loss": 4.5086, "step": 7083 }, { "epoch": 0.3811881188118812, "grad_norm": 2.464878559112549, "learning_rate": 3.4120223233612455e-05, "loss": 4.2406, "step": 7084 }, { "epoch": 0.3812419285406802, "grad_norm": 2.8445942401885986, "learning_rate": 3.411628815706638e-05, "loss": 4.0762, "step": 7085 }, { "epoch": 0.3812957382694791, "grad_norm": 1.9813108444213867, "learning_rate": 3.411235282000131e-05, "loss": 4.8632, "step": 7086 }, { "epoch": 0.3813495479982781, "grad_norm": 1.6528611183166504, "learning_rate": 3.410841722252972e-05, "loss": 4.7643, "step": 7087 }, { "epoch": 0.38140335772707706, "grad_norm": 1.7224496603012085, "learning_rate": 3.410448136476405e-05, "loss": 4.644, "step": 7088 }, { "epoch": 0.38145716745587605, "grad_norm": 0.9747599959373474, "learning_rate": 3.4100545246816795e-05, "loss": 4.6347, "step": 7089 }, { "epoch": 0.38151097718467497, "grad_norm": 1.361510992050171, "learning_rate": 3.409660886880043e-05, "loss": 4.7474, "step": 7090 }, { "epoch": 0.38156478691347395, "grad_norm": 1.974542260169983, "learning_rate": 3.409267223082746e-05, "loss": 4.3275, "step": 7091 }, { "epoch": 0.38161859664227293, "grad_norm": 1.8203750848770142, "learning_rate": 3.408873533301037e-05, "loss": 4.384, "step": 7092 }, { "epoch": 0.3816724063710719, "grad_norm": 1.1171000003814697, "learning_rate": 3.4084798175461666e-05, "loss": 4.495, "step": 7093 }, { "epoch": 0.38172621609987084, "grad_norm": 1.593612790107727, "learning_rate": 3.408086075829387e-05, "loss": 4.7363, "step": 7094 }, { "epoch": 0.3817800258286698, "grad_norm": 1.1873056888580322, "learning_rate": 3.40769230816195e-05, "loss": 4.8398, "step": 7095 }, { "epoch": 0.3818338355574688, "grad_norm": 2.4755632877349854, "learning_rate": 3.407298514555108e-05, "loss": 4.4671, "step": 7096 }, { "epoch": 0.38188764528626773, "grad_norm": 1.9708302021026611, "learning_rate": 3.406904695020114e-05, "loss": 4.3237, "step": 7097 }, { "epoch": 0.3819414550150667, "grad_norm": 2.7270655632019043, "learning_rate": 3.4065108495682246e-05, "loss": 4.0, "step": 7098 }, { "epoch": 0.3819952647438657, "grad_norm": 1.503503680229187, "learning_rate": 3.406116978210693e-05, "loss": 4.5054, "step": 7099 }, { "epoch": 0.3820490744726647, "grad_norm": 1.4317413568496704, "learning_rate": 3.405723080958775e-05, "loss": 4.2043, "step": 7100 }, { "epoch": 0.3821028842014636, "grad_norm": 1.8462718725204468, "learning_rate": 3.405329157823727e-05, "loss": 4.4701, "step": 7101 }, { "epoch": 0.3821566939302626, "grad_norm": 1.2076687812805176, "learning_rate": 3.4049352088168075e-05, "loss": 4.4544, "step": 7102 }, { "epoch": 0.38221050365906156, "grad_norm": 2.4019601345062256, "learning_rate": 3.404541233949272e-05, "loss": 4.2359, "step": 7103 }, { "epoch": 0.38226431338786054, "grad_norm": 1.85711669921875, "learning_rate": 3.404147233232383e-05, "loss": 4.1075, "step": 7104 }, { "epoch": 0.38231812311665947, "grad_norm": 1.3414080142974854, "learning_rate": 3.403753206677397e-05, "loss": 4.5063, "step": 7105 }, { "epoch": 0.38237193284545845, "grad_norm": 1.611065149307251, "learning_rate": 3.403359154295576e-05, "loss": 4.4639, "step": 7106 }, { "epoch": 0.38242574257425743, "grad_norm": 1.1209065914154053, "learning_rate": 3.402965076098179e-05, "loss": 4.3044, "step": 7107 }, { "epoch": 0.3824795523030564, "grad_norm": 1.8984310626983643, "learning_rate": 3.402570972096469e-05, "loss": 4.02, "step": 7108 }, { "epoch": 0.38253336203185534, "grad_norm": 1.9627869129180908, "learning_rate": 3.402176842301709e-05, "loss": 4.0565, "step": 7109 }, { "epoch": 0.3825871717606543, "grad_norm": 2.828964948654175, "learning_rate": 3.401782686725161e-05, "loss": 3.9539, "step": 7110 }, { "epoch": 0.3826409814894533, "grad_norm": 1.2348140478134155, "learning_rate": 3.401388505378089e-05, "loss": 4.7766, "step": 7111 }, { "epoch": 0.3826947912182523, "grad_norm": 1.238490104675293, "learning_rate": 3.400994298271758e-05, "loss": 4.3018, "step": 7112 }, { "epoch": 0.3827486009470512, "grad_norm": 1.8021833896636963, "learning_rate": 3.400600065417434e-05, "loss": 3.866, "step": 7113 }, { "epoch": 0.3828024106758502, "grad_norm": 1.3868457078933716, "learning_rate": 3.400205806826382e-05, "loss": 4.8119, "step": 7114 }, { "epoch": 0.3828562204046492, "grad_norm": 2.571619987487793, "learning_rate": 3.39981152250987e-05, "loss": 4.0973, "step": 7115 }, { "epoch": 0.38291003013344815, "grad_norm": 2.6884007453918457, "learning_rate": 3.3994172124791633e-05, "loss": 4.489, "step": 7116 }, { "epoch": 0.3829638398622471, "grad_norm": 1.9904468059539795, "learning_rate": 3.399022876745533e-05, "loss": 3.8906, "step": 7117 }, { "epoch": 0.38301764959104606, "grad_norm": 2.7354602813720703, "learning_rate": 3.3986285153202465e-05, "loss": 4.2415, "step": 7118 }, { "epoch": 0.38307145931984504, "grad_norm": 1.3483282327651978, "learning_rate": 3.398234128214575e-05, "loss": 4.2671, "step": 7119 }, { "epoch": 0.38312526904864397, "grad_norm": 2.310321092605591, "learning_rate": 3.3978397154397875e-05, "loss": 4.8455, "step": 7120 }, { "epoch": 0.38317907877744295, "grad_norm": 2.122427463531494, "learning_rate": 3.3974452770071554e-05, "loss": 4.3802, "step": 7121 }, { "epoch": 0.38323288850624193, "grad_norm": 1.889866590499878, "learning_rate": 3.397050812927951e-05, "loss": 4.5744, "step": 7122 }, { "epoch": 0.3832866982350409, "grad_norm": 2.7094438076019287, "learning_rate": 3.396656323213449e-05, "loss": 4.237, "step": 7123 }, { "epoch": 0.38334050796383984, "grad_norm": 1.7969881296157837, "learning_rate": 3.396261807874918e-05, "loss": 4.4426, "step": 7124 }, { "epoch": 0.3833943176926388, "grad_norm": 2.1345736980438232, "learning_rate": 3.395867266923638e-05, "loss": 4.0406, "step": 7125 }, { "epoch": 0.3834481274214378, "grad_norm": 1.6336097717285156, "learning_rate": 3.3954727003708794e-05, "loss": 4.5752, "step": 7126 }, { "epoch": 0.3835019371502368, "grad_norm": 2.99298095703125, "learning_rate": 3.39507810822792e-05, "loss": 4.1301, "step": 7127 }, { "epoch": 0.3835557468790357, "grad_norm": 2.416215658187866, "learning_rate": 3.394683490506036e-05, "loss": 4.548, "step": 7128 }, { "epoch": 0.3836095566078347, "grad_norm": 1.3147187232971191, "learning_rate": 3.394288847216504e-05, "loss": 4.5722, "step": 7129 }, { "epoch": 0.38366336633663367, "grad_norm": 2.899994134902954, "learning_rate": 3.3938941783706027e-05, "loss": 3.8042, "step": 7130 }, { "epoch": 0.38371717606543265, "grad_norm": 2.4787282943725586, "learning_rate": 3.39349948397961e-05, "loss": 4.3539, "step": 7131 }, { "epoch": 0.3837709857942316, "grad_norm": 2.684445381164551, "learning_rate": 3.393104764054804e-05, "loss": 3.9874, "step": 7132 }, { "epoch": 0.38382479552303056, "grad_norm": 2.4108760356903076, "learning_rate": 3.3927100186074676e-05, "loss": 4.247, "step": 7133 }, { "epoch": 0.38387860525182954, "grad_norm": 1.501041293144226, "learning_rate": 3.3923152476488785e-05, "loss": 4.776, "step": 7134 }, { "epoch": 0.3839324149806285, "grad_norm": 1.8597681522369385, "learning_rate": 3.39192045119032e-05, "loss": 4.2033, "step": 7135 }, { "epoch": 0.38398622470942745, "grad_norm": 2.0944433212280273, "learning_rate": 3.391525629243075e-05, "loss": 4.587, "step": 7136 }, { "epoch": 0.38404003443822643, "grad_norm": 2.243116617202759, "learning_rate": 3.3911307818184246e-05, "loss": 3.8888, "step": 7137 }, { "epoch": 0.3840938441670254, "grad_norm": 1.873695969581604, "learning_rate": 3.3907359089276535e-05, "loss": 4.2887, "step": 7138 }, { "epoch": 0.3841476538958244, "grad_norm": 1.4943177700042725, "learning_rate": 3.390341010582046e-05, "loss": 4.9974, "step": 7139 }, { "epoch": 0.3842014636246233, "grad_norm": 1.8212724924087524, "learning_rate": 3.3899460867928864e-05, "loss": 4.407, "step": 7140 }, { "epoch": 0.3842552733534223, "grad_norm": 1.3473602533340454, "learning_rate": 3.3895511375714635e-05, "loss": 4.4956, "step": 7141 }, { "epoch": 0.3843090830822213, "grad_norm": 1.7190279960632324, "learning_rate": 3.38915616292906e-05, "loss": 3.68, "step": 7142 }, { "epoch": 0.3843628928110202, "grad_norm": 2.4412171840667725, "learning_rate": 3.388761162876965e-05, "loss": 4.0795, "step": 7143 }, { "epoch": 0.3844167025398192, "grad_norm": 2.3955039978027344, "learning_rate": 3.388366137426466e-05, "loss": 4.335, "step": 7144 }, { "epoch": 0.38447051226861817, "grad_norm": 2.062617301940918, "learning_rate": 3.387971086588853e-05, "loss": 4.2149, "step": 7145 }, { "epoch": 0.38452432199741715, "grad_norm": 2.3208463191986084, "learning_rate": 3.387576010375415e-05, "loss": 3.7851, "step": 7146 }, { "epoch": 0.3845781317262161, "grad_norm": 2.4691290855407715, "learning_rate": 3.387180908797441e-05, "loss": 4.4054, "step": 7147 }, { "epoch": 0.38463194145501506, "grad_norm": 1.524461030960083, "learning_rate": 3.386785781866224e-05, "loss": 4.3333, "step": 7148 }, { "epoch": 0.38468575118381404, "grad_norm": 2.3921303749084473, "learning_rate": 3.386390629593053e-05, "loss": 4.084, "step": 7149 }, { "epoch": 0.384739560912613, "grad_norm": 1.6266742944717407, "learning_rate": 3.3859954519892226e-05, "loss": 4.3952, "step": 7150 }, { "epoch": 0.38479337064141195, "grad_norm": 2.5831964015960693, "learning_rate": 3.385600249066026e-05, "loss": 4.4339, "step": 7151 }, { "epoch": 0.38484718037021093, "grad_norm": 1.6744667291641235, "learning_rate": 3.385205020834755e-05, "loss": 4.4387, "step": 7152 }, { "epoch": 0.3849009900990099, "grad_norm": 2.3081815242767334, "learning_rate": 3.384809767306707e-05, "loss": 4.5826, "step": 7153 }, { "epoch": 0.3849547998278089, "grad_norm": 2.051492691040039, "learning_rate": 3.3844144884931746e-05, "loss": 4.1389, "step": 7154 }, { "epoch": 0.3850086095566078, "grad_norm": 2.186497926712036, "learning_rate": 3.3840191844054546e-05, "loss": 4.1119, "step": 7155 }, { "epoch": 0.3850624192854068, "grad_norm": 1.6621524095535278, "learning_rate": 3.383623855054845e-05, "loss": 4.7322, "step": 7156 }, { "epoch": 0.3851162290142058, "grad_norm": 2.1194028854370117, "learning_rate": 3.383228500452641e-05, "loss": 4.3277, "step": 7157 }, { "epoch": 0.38517003874300476, "grad_norm": 2.406514883041382, "learning_rate": 3.382833120610144e-05, "loss": 4.1319, "step": 7158 }, { "epoch": 0.3852238484718037, "grad_norm": 2.4341259002685547, "learning_rate": 3.382437715538649e-05, "loss": 4.4947, "step": 7159 }, { "epoch": 0.38527765820060267, "grad_norm": 1.1454863548278809, "learning_rate": 3.382042285249459e-05, "loss": 4.5686, "step": 7160 }, { "epoch": 0.38533146792940165, "grad_norm": 1.3964378833770752, "learning_rate": 3.381646829753872e-05, "loss": 4.2947, "step": 7161 }, { "epoch": 0.3853852776582006, "grad_norm": 1.85612952709198, "learning_rate": 3.3812513490631906e-05, "loss": 4.5183, "step": 7162 }, { "epoch": 0.38543908738699956, "grad_norm": 2.2901430130004883, "learning_rate": 3.3808558431887164e-05, "loss": 3.9598, "step": 7163 }, { "epoch": 0.38549289711579854, "grad_norm": 1.7241979837417603, "learning_rate": 3.38046031214175e-05, "loss": 4.2387, "step": 7164 }, { "epoch": 0.3855467068445975, "grad_norm": 2.3521361351013184, "learning_rate": 3.380064755933596e-05, "loss": 3.9983, "step": 7165 }, { "epoch": 0.38560051657339645, "grad_norm": 2.044961452484131, "learning_rate": 3.379669174575559e-05, "loss": 4.6432, "step": 7166 }, { "epoch": 0.3856543263021954, "grad_norm": 2.7039778232574463, "learning_rate": 3.379273568078943e-05, "loss": 4.596, "step": 7167 }, { "epoch": 0.3857081360309944, "grad_norm": 1.3105690479278564, "learning_rate": 3.378877936455054e-05, "loss": 4.427, "step": 7168 }, { "epoch": 0.3857619457597934, "grad_norm": 2.5092079639434814, "learning_rate": 3.378482279715197e-05, "loss": 3.8838, "step": 7169 }, { "epoch": 0.3858157554885923, "grad_norm": 1.5550616979599, "learning_rate": 3.3780865978706785e-05, "loss": 4.3362, "step": 7170 }, { "epoch": 0.3858695652173913, "grad_norm": 2.1344428062438965, "learning_rate": 3.377690890932809e-05, "loss": 4.2852, "step": 7171 }, { "epoch": 0.3859233749461903, "grad_norm": 1.7289127111434937, "learning_rate": 3.377295158912893e-05, "loss": 4.7439, "step": 7172 }, { "epoch": 0.38597718467498926, "grad_norm": 2.231992721557617, "learning_rate": 3.37689940182224e-05, "loss": 4.2148, "step": 7173 }, { "epoch": 0.3860309944037882, "grad_norm": 2.4515435695648193, "learning_rate": 3.3765036196721625e-05, "loss": 4.5897, "step": 7174 }, { "epoch": 0.38608480413258717, "grad_norm": 1.5641635656356812, "learning_rate": 3.376107812473968e-05, "loss": 4.5733, "step": 7175 }, { "epoch": 0.38613861386138615, "grad_norm": 2.326876401901245, "learning_rate": 3.375711980238969e-05, "loss": 3.9439, "step": 7176 }, { "epoch": 0.38619242359018513, "grad_norm": 1.6736563444137573, "learning_rate": 3.3753161229784766e-05, "loss": 3.9704, "step": 7177 }, { "epoch": 0.38624623331898406, "grad_norm": 1.1311314105987549, "learning_rate": 3.374920240703804e-05, "loss": 4.6251, "step": 7178 }, { "epoch": 0.38630004304778304, "grad_norm": 2.158743381500244, "learning_rate": 3.374524333426265e-05, "loss": 4.1693, "step": 7179 }, { "epoch": 0.386353852776582, "grad_norm": 2.868833303451538, "learning_rate": 3.3741284011571715e-05, "loss": 4.0141, "step": 7180 }, { "epoch": 0.386407662505381, "grad_norm": 1.4339309930801392, "learning_rate": 3.3737324439078406e-05, "loss": 4.2782, "step": 7181 }, { "epoch": 0.3864614722341799, "grad_norm": 1.2361040115356445, "learning_rate": 3.373336461689586e-05, "loss": 4.5564, "step": 7182 }, { "epoch": 0.3865152819629789, "grad_norm": 2.677926778793335, "learning_rate": 3.372940454513724e-05, "loss": 4.7891, "step": 7183 }, { "epoch": 0.3865690916917779, "grad_norm": 2.5275871753692627, "learning_rate": 3.372544422391572e-05, "loss": 4.5769, "step": 7184 }, { "epoch": 0.3866229014205768, "grad_norm": 1.7662016153335571, "learning_rate": 3.372148365334447e-05, "loss": 4.4625, "step": 7185 }, { "epoch": 0.3866767111493758, "grad_norm": 2.048365354537964, "learning_rate": 3.371752283353668e-05, "loss": 3.9393, "step": 7186 }, { "epoch": 0.3867305208781748, "grad_norm": 3.3629567623138428, "learning_rate": 3.371356176460553e-05, "loss": 3.9407, "step": 7187 }, { "epoch": 0.38678433060697376, "grad_norm": 2.1089582443237305, "learning_rate": 3.3709600446664224e-05, "loss": 4.645, "step": 7188 }, { "epoch": 0.3868381403357727, "grad_norm": 2.5249271392822266, "learning_rate": 3.3705638879825965e-05, "loss": 4.346, "step": 7189 }, { "epoch": 0.38689195006457167, "grad_norm": 2.0790207386016846, "learning_rate": 3.3701677064203966e-05, "loss": 4.7052, "step": 7190 }, { "epoch": 0.38694575979337065, "grad_norm": 2.009350538253784, "learning_rate": 3.3697714999911436e-05, "loss": 4.2637, "step": 7191 }, { "epoch": 0.38699956952216963, "grad_norm": 1.8508421182632446, "learning_rate": 3.3693752687061595e-05, "loss": 4.1456, "step": 7192 }, { "epoch": 0.38705337925096855, "grad_norm": 1.2533336877822876, "learning_rate": 3.368979012576769e-05, "loss": 4.2033, "step": 7193 }, { "epoch": 0.38710718897976754, "grad_norm": 1.8149166107177734, "learning_rate": 3.3685827316142975e-05, "loss": 4.3664, "step": 7194 }, { "epoch": 0.3871609987085665, "grad_norm": 1.9212061166763306, "learning_rate": 3.3681864258300666e-05, "loss": 4.1878, "step": 7195 }, { "epoch": 0.3872148084373655, "grad_norm": 1.9557381868362427, "learning_rate": 3.367790095235402e-05, "loss": 3.5789, "step": 7196 }, { "epoch": 0.3872686181661644, "grad_norm": 2.0868592262268066, "learning_rate": 3.367393739841631e-05, "loss": 4.409, "step": 7197 }, { "epoch": 0.3873224278949634, "grad_norm": 1.6152451038360596, "learning_rate": 3.36699735966008e-05, "loss": 4.1504, "step": 7198 }, { "epoch": 0.3873762376237624, "grad_norm": 1.4733220338821411, "learning_rate": 3.366600954702077e-05, "loss": 4.3091, "step": 7199 }, { "epoch": 0.38743004735256137, "grad_norm": 1.8577661514282227, "learning_rate": 3.3662045249789495e-05, "loss": 4.2739, "step": 7200 }, { "epoch": 0.3874838570813603, "grad_norm": 1.2506390810012817, "learning_rate": 3.365808070502026e-05, "loss": 4.4594, "step": 7201 }, { "epoch": 0.3875376668101593, "grad_norm": 1.419188380241394, "learning_rate": 3.365411591282637e-05, "loss": 4.6364, "step": 7202 }, { "epoch": 0.38759147653895826, "grad_norm": 1.6605538129806519, "learning_rate": 3.365015087332112e-05, "loss": 4.6259, "step": 7203 }, { "epoch": 0.3876452862677572, "grad_norm": 0.9321752190589905, "learning_rate": 3.364618558661782e-05, "loss": 4.2547, "step": 7204 }, { "epoch": 0.38769909599655616, "grad_norm": 1.4807655811309814, "learning_rate": 3.364222005282981e-05, "loss": 4.6134, "step": 7205 }, { "epoch": 0.38775290572535515, "grad_norm": 3.2989633083343506, "learning_rate": 3.363825427207037e-05, "loss": 3.9314, "step": 7206 }, { "epoch": 0.3878067154541541, "grad_norm": 1.7395107746124268, "learning_rate": 3.363428824445287e-05, "loss": 4.2147, "step": 7207 }, { "epoch": 0.38786052518295305, "grad_norm": 1.3577861785888672, "learning_rate": 3.363032197009064e-05, "loss": 4.4387, "step": 7208 }, { "epoch": 0.38791433491175203, "grad_norm": 1.0538328886032104, "learning_rate": 3.3626355449097015e-05, "loss": 4.6632, "step": 7209 }, { "epoch": 0.387968144640551, "grad_norm": 1.3302698135375977, "learning_rate": 3.3622388681585355e-05, "loss": 4.6086, "step": 7210 }, { "epoch": 0.38802195436935, "grad_norm": 1.7433477640151978, "learning_rate": 3.361842166766901e-05, "loss": 4.4322, "step": 7211 }, { "epoch": 0.3880757640981489, "grad_norm": 1.8841748237609863, "learning_rate": 3.3614454407461366e-05, "loss": 3.8656, "step": 7212 }, { "epoch": 0.3881295738269479, "grad_norm": 1.3287913799285889, "learning_rate": 3.3610486901075785e-05, "loss": 4.6468, "step": 7213 }, { "epoch": 0.3881833835557469, "grad_norm": 1.2121388912200928, "learning_rate": 3.3606519148625635e-05, "loss": 4.5765, "step": 7214 }, { "epoch": 0.38823719328454587, "grad_norm": 2.102931022644043, "learning_rate": 3.360255115022433e-05, "loss": 4.9838, "step": 7215 }, { "epoch": 0.3882910030133448, "grad_norm": 1.8902294635772705, "learning_rate": 3.3598582905985246e-05, "loss": 4.0698, "step": 7216 }, { "epoch": 0.3883448127421438, "grad_norm": 2.5064029693603516, "learning_rate": 3.3594614416021794e-05, "loss": 4.4544, "step": 7217 }, { "epoch": 0.38839862247094276, "grad_norm": 3.20035719871521, "learning_rate": 3.359064568044738e-05, "loss": 4.2466, "step": 7218 }, { "epoch": 0.38845243219974174, "grad_norm": 1.3139057159423828, "learning_rate": 3.358667669937541e-05, "loss": 4.7746, "step": 7219 }, { "epoch": 0.38850624192854066, "grad_norm": 1.905795693397522, "learning_rate": 3.3582707472919317e-05, "loss": 4.4854, "step": 7220 }, { "epoch": 0.38856005165733964, "grad_norm": 2.1147267818450928, "learning_rate": 3.3578738001192536e-05, "loss": 4.4318, "step": 7221 }, { "epoch": 0.3886138613861386, "grad_norm": 1.1144418716430664, "learning_rate": 3.357476828430849e-05, "loss": 4.5242, "step": 7222 }, { "epoch": 0.3886676711149376, "grad_norm": 1.9393806457519531, "learning_rate": 3.357079832238063e-05, "loss": 4.6552, "step": 7223 }, { "epoch": 0.38872148084373653, "grad_norm": 1.0105154514312744, "learning_rate": 3.356682811552241e-05, "loss": 4.3625, "step": 7224 }, { "epoch": 0.3887752905725355, "grad_norm": 2.3919553756713867, "learning_rate": 3.3562857663847286e-05, "loss": 4.6939, "step": 7225 }, { "epoch": 0.3888291003013345, "grad_norm": 1.0122158527374268, "learning_rate": 3.355888696746872e-05, "loss": 4.6828, "step": 7226 }, { "epoch": 0.3888829100301334, "grad_norm": 2.182870388031006, "learning_rate": 3.355491602650018e-05, "loss": 4.2247, "step": 7227 }, { "epoch": 0.3889367197589324, "grad_norm": 1.0541398525238037, "learning_rate": 3.355094484105516e-05, "loss": 4.8245, "step": 7228 }, { "epoch": 0.3889905294877314, "grad_norm": 3.563000202178955, "learning_rate": 3.354697341124713e-05, "loss": 4.9107, "step": 7229 }, { "epoch": 0.38904433921653037, "grad_norm": 2.698350667953491, "learning_rate": 3.354300173718958e-05, "loss": 4.6583, "step": 7230 }, { "epoch": 0.3890981489453293, "grad_norm": 2.8734662532806396, "learning_rate": 3.353902981899604e-05, "loss": 4.1341, "step": 7231 }, { "epoch": 0.3891519586741283, "grad_norm": 1.345000147819519, "learning_rate": 3.3535057656779975e-05, "loss": 4.5547, "step": 7232 }, { "epoch": 0.38920576840292725, "grad_norm": 1.4361281394958496, "learning_rate": 3.3531085250654925e-05, "loss": 4.7684, "step": 7233 }, { "epoch": 0.38925957813172624, "grad_norm": 2.0179476737976074, "learning_rate": 3.3527112600734414e-05, "loss": 4.6299, "step": 7234 }, { "epoch": 0.38931338786052516, "grad_norm": 1.2058746814727783, "learning_rate": 3.352313970713195e-05, "loss": 4.731, "step": 7235 }, { "epoch": 0.38936719758932414, "grad_norm": 2.068432092666626, "learning_rate": 3.351916656996108e-05, "loss": 4.346, "step": 7236 }, { "epoch": 0.3894210073181231, "grad_norm": 2.1330771446228027, "learning_rate": 3.351519318933534e-05, "loss": 3.9311, "step": 7237 }, { "epoch": 0.3894748170469221, "grad_norm": 1.8273932933807373, "learning_rate": 3.351121956536828e-05, "loss": 4.5764, "step": 7238 }, { "epoch": 0.38952862677572103, "grad_norm": 3.1752805709838867, "learning_rate": 3.350724569817346e-05, "loss": 3.802, "step": 7239 }, { "epoch": 0.38958243650452, "grad_norm": 2.52919602394104, "learning_rate": 3.350327158786445e-05, "loss": 3.9197, "step": 7240 }, { "epoch": 0.389636246233319, "grad_norm": 1.266653060913086, "learning_rate": 3.349929723455479e-05, "loss": 4.5349, "step": 7241 }, { "epoch": 0.389690055962118, "grad_norm": 2.3723576068878174, "learning_rate": 3.349532263835809e-05, "loss": 3.9982, "step": 7242 }, { "epoch": 0.3897438656909169, "grad_norm": 2.1562349796295166, "learning_rate": 3.349134779938791e-05, "loss": 4.4021, "step": 7243 }, { "epoch": 0.3897976754197159, "grad_norm": 2.434051990509033, "learning_rate": 3.348737271775786e-05, "loss": 3.993, "step": 7244 }, { "epoch": 0.38985148514851486, "grad_norm": 2.369542121887207, "learning_rate": 3.348339739358152e-05, "loss": 4.1369, "step": 7245 }, { "epoch": 0.38990529487731385, "grad_norm": 2.4536867141723633, "learning_rate": 3.3479421826972504e-05, "loss": 3.9219, "step": 7246 }, { "epoch": 0.38995910460611277, "grad_norm": 2.6307783126831055, "learning_rate": 3.347544601804441e-05, "loss": 3.5746, "step": 7247 }, { "epoch": 0.39001291433491175, "grad_norm": 1.9156562089920044, "learning_rate": 3.347146996691087e-05, "loss": 4.2193, "step": 7248 }, { "epoch": 0.39006672406371073, "grad_norm": 2.273475170135498, "learning_rate": 3.3467493673685505e-05, "loss": 4.2828, "step": 7249 }, { "epoch": 0.39012053379250966, "grad_norm": 1.5977579355239868, "learning_rate": 3.346351713848194e-05, "loss": 4.4891, "step": 7250 }, { "epoch": 0.39017434352130864, "grad_norm": 2.2793571949005127, "learning_rate": 3.345954036141383e-05, "loss": 4.4031, "step": 7251 }, { "epoch": 0.3902281532501076, "grad_norm": 2.1934585571289062, "learning_rate": 3.34555633425948e-05, "loss": 4.2623, "step": 7252 }, { "epoch": 0.3902819629789066, "grad_norm": 1.9710384607315063, "learning_rate": 3.345158608213852e-05, "loss": 4.2482, "step": 7253 }, { "epoch": 0.39033577270770553, "grad_norm": 1.252945899963379, "learning_rate": 3.344760858015864e-05, "loss": 4.3265, "step": 7254 }, { "epoch": 0.3903895824365045, "grad_norm": 2.7210559844970703, "learning_rate": 3.344363083676883e-05, "loss": 4.4516, "step": 7255 }, { "epoch": 0.3904433921653035, "grad_norm": 2.3366763591766357, "learning_rate": 3.3439652852082754e-05, "loss": 3.8992, "step": 7256 }, { "epoch": 0.3904972018941025, "grad_norm": 1.6846444606781006, "learning_rate": 3.3435674626214105e-05, "loss": 4.5125, "step": 7257 }, { "epoch": 0.3905510116229014, "grad_norm": 1.9262313842773438, "learning_rate": 3.343169615927656e-05, "loss": 4.6159, "step": 7258 }, { "epoch": 0.3906048213517004, "grad_norm": 1.8555598258972168, "learning_rate": 3.342771745138382e-05, "loss": 4.7858, "step": 7259 }, { "epoch": 0.39065863108049936, "grad_norm": 1.909203052520752, "learning_rate": 3.3423738502649585e-05, "loss": 4.5096, "step": 7260 }, { "epoch": 0.39071244080929834, "grad_norm": 2.913055419921875, "learning_rate": 3.341975931318756e-05, "loss": 3.2552, "step": 7261 }, { "epoch": 0.39076625053809727, "grad_norm": 2.2384040355682373, "learning_rate": 3.341577988311146e-05, "loss": 4.3191, "step": 7262 }, { "epoch": 0.39082006026689625, "grad_norm": 3.259467124938965, "learning_rate": 3.3411800212535004e-05, "loss": 3.7041, "step": 7263 }, { "epoch": 0.39087386999569523, "grad_norm": 1.9194345474243164, "learning_rate": 3.340782030157192e-05, "loss": 4.347, "step": 7264 }, { "epoch": 0.3909276797244942, "grad_norm": 2.0598230361938477, "learning_rate": 3.340384015033595e-05, "loss": 4.0889, "step": 7265 }, { "epoch": 0.39098148945329314, "grad_norm": 2.187364339828491, "learning_rate": 3.3399859758940836e-05, "loss": 4.4485, "step": 7266 }, { "epoch": 0.3910352991820921, "grad_norm": 1.3583651781082153, "learning_rate": 3.339587912750033e-05, "loss": 4.5129, "step": 7267 }, { "epoch": 0.3910891089108911, "grad_norm": 2.2367961406707764, "learning_rate": 3.339189825612816e-05, "loss": 4.8224, "step": 7268 }, { "epoch": 0.39114291863969003, "grad_norm": 1.6272021532058716, "learning_rate": 3.3387917144938124e-05, "loss": 4.1223, "step": 7269 }, { "epoch": 0.391196728368489, "grad_norm": 1.654746413230896, "learning_rate": 3.3383935794043975e-05, "loss": 4.7136, "step": 7270 }, { "epoch": 0.391250538097288, "grad_norm": 1.3599131107330322, "learning_rate": 3.3379954203559496e-05, "loss": 4.7916, "step": 7271 }, { "epoch": 0.391304347826087, "grad_norm": 1.8682280778884888, "learning_rate": 3.337597237359846e-05, "loss": 4.2147, "step": 7272 }, { "epoch": 0.3913581575548859, "grad_norm": 1.5840585231781006, "learning_rate": 3.3371990304274656e-05, "loss": 4.2892, "step": 7273 }, { "epoch": 0.3914119672836849, "grad_norm": 1.4279224872589111, "learning_rate": 3.3368007995701896e-05, "loss": 4.7698, "step": 7274 }, { "epoch": 0.39146577701248386, "grad_norm": 1.6330221891403198, "learning_rate": 3.3364025447993974e-05, "loss": 4.41, "step": 7275 }, { "epoch": 0.39151958674128284, "grad_norm": 1.4661072492599487, "learning_rate": 3.336004266126469e-05, "loss": 4.2096, "step": 7276 }, { "epoch": 0.39157339647008177, "grad_norm": 1.9727556705474854, "learning_rate": 3.335605963562788e-05, "loss": 4.6422, "step": 7277 }, { "epoch": 0.39162720619888075, "grad_norm": 1.7881019115447998, "learning_rate": 3.3352076371197366e-05, "loss": 4.6066, "step": 7278 }, { "epoch": 0.39168101592767973, "grad_norm": 2.636552095413208, "learning_rate": 3.334809286808697e-05, "loss": 4.1994, "step": 7279 }, { "epoch": 0.3917348256564787, "grad_norm": 3.1559977531433105, "learning_rate": 3.3344109126410536e-05, "loss": 3.9998, "step": 7280 }, { "epoch": 0.39178863538527764, "grad_norm": 1.852390170097351, "learning_rate": 3.33401251462819e-05, "loss": 4.3137, "step": 7281 }, { "epoch": 0.3918424451140766, "grad_norm": 2.3490138053894043, "learning_rate": 3.333614092781493e-05, "loss": 4.1671, "step": 7282 }, { "epoch": 0.3918962548428756, "grad_norm": 1.954825758934021, "learning_rate": 3.333215647112346e-05, "loss": 4.6721, "step": 7283 }, { "epoch": 0.3919500645716746, "grad_norm": 0.9839850664138794, "learning_rate": 3.3328171776321374e-05, "loss": 4.5372, "step": 7284 }, { "epoch": 0.3920038743004735, "grad_norm": 1.0520793199539185, "learning_rate": 3.332418684352254e-05, "loss": 4.758, "step": 7285 }, { "epoch": 0.3920576840292725, "grad_norm": 1.7019314765930176, "learning_rate": 3.332020167284084e-05, "loss": 4.2559, "step": 7286 }, { "epoch": 0.39211149375807147, "grad_norm": 2.8983688354492188, "learning_rate": 3.3316216264390155e-05, "loss": 3.9263, "step": 7287 }, { "epoch": 0.39216530348687045, "grad_norm": 1.113808512687683, "learning_rate": 3.3312230618284366e-05, "loss": 4.8388, "step": 7288 }, { "epoch": 0.3922191132156694, "grad_norm": 1.112499475479126, "learning_rate": 3.330824473463739e-05, "loss": 4.3707, "step": 7289 }, { "epoch": 0.39227292294446836, "grad_norm": 2.245776414871216, "learning_rate": 3.330425861356313e-05, "loss": 4.2921, "step": 7290 }, { "epoch": 0.39232673267326734, "grad_norm": 2.000934362411499, "learning_rate": 3.330027225517549e-05, "loss": 4.1172, "step": 7291 }, { "epoch": 0.39238054240206627, "grad_norm": 1.8553804159164429, "learning_rate": 3.329628565958839e-05, "loss": 4.3852, "step": 7292 }, { "epoch": 0.39243435213086525, "grad_norm": 2.9767367839813232, "learning_rate": 3.3292298826915767e-05, "loss": 4.0547, "step": 7293 }, { "epoch": 0.39248816185966423, "grad_norm": 2.1226491928100586, "learning_rate": 3.328831175727155e-05, "loss": 3.8254, "step": 7294 }, { "epoch": 0.3925419715884632, "grad_norm": 1.177735447883606, "learning_rate": 3.328432445076967e-05, "loss": 4.6863, "step": 7295 }, { "epoch": 0.39259578131726214, "grad_norm": 2.405670642852783, "learning_rate": 3.328033690752408e-05, "loss": 4.0243, "step": 7296 }, { "epoch": 0.3926495910460611, "grad_norm": 2.02601957321167, "learning_rate": 3.327634912764874e-05, "loss": 4.1597, "step": 7297 }, { "epoch": 0.3927034007748601, "grad_norm": 1.9596261978149414, "learning_rate": 3.32723611112576e-05, "loss": 4.3414, "step": 7298 }, { "epoch": 0.3927572105036591, "grad_norm": 2.3238422870635986, "learning_rate": 3.326837285846462e-05, "loss": 4.1417, "step": 7299 }, { "epoch": 0.392811020232458, "grad_norm": 1.6668795347213745, "learning_rate": 3.3264384369383786e-05, "loss": 4.7401, "step": 7300 }, { "epoch": 0.392864829961257, "grad_norm": 1.3383766412734985, "learning_rate": 3.326039564412908e-05, "loss": 4.7048, "step": 7301 }, { "epoch": 0.39291863969005597, "grad_norm": 1.5293149948120117, "learning_rate": 3.325640668281448e-05, "loss": 4.7417, "step": 7302 }, { "epoch": 0.39297244941885495, "grad_norm": 1.8379902839660645, "learning_rate": 3.325241748555399e-05, "loss": 4.1927, "step": 7303 }, { "epoch": 0.3930262591476539, "grad_norm": 1.640313744544983, "learning_rate": 3.32484280524616e-05, "loss": 4.5363, "step": 7304 }, { "epoch": 0.39308006887645286, "grad_norm": 1.2726582288742065, "learning_rate": 3.324443838365133e-05, "loss": 4.515, "step": 7305 }, { "epoch": 0.39313387860525184, "grad_norm": 2.63214111328125, "learning_rate": 3.324044847923717e-05, "loss": 3.7738, "step": 7306 }, { "epoch": 0.3931876883340508, "grad_norm": 1.969890832901001, "learning_rate": 3.323645833933317e-05, "loss": 4.6013, "step": 7307 }, { "epoch": 0.39324149806284975, "grad_norm": 1.4305453300476074, "learning_rate": 3.3232467964053334e-05, "loss": 4.4041, "step": 7308 }, { "epoch": 0.39329530779164873, "grad_norm": 1.0940275192260742, "learning_rate": 3.3228477353511714e-05, "loss": 4.5788, "step": 7309 }, { "epoch": 0.3933491175204477, "grad_norm": 1.3251007795333862, "learning_rate": 3.322448650782234e-05, "loss": 4.5864, "step": 7310 }, { "epoch": 0.39340292724924664, "grad_norm": 1.1619410514831543, "learning_rate": 3.322049542709927e-05, "loss": 4.5472, "step": 7311 }, { "epoch": 0.3934567369780456, "grad_norm": 2.032788038253784, "learning_rate": 3.3216504111456546e-05, "loss": 4.2042, "step": 7312 }, { "epoch": 0.3935105467068446, "grad_norm": 1.6080548763275146, "learning_rate": 3.321251256100824e-05, "loss": 3.8605, "step": 7313 }, { "epoch": 0.3935643564356436, "grad_norm": 1.6236835718154907, "learning_rate": 3.32085207758684e-05, "loss": 4.2342, "step": 7314 }, { "epoch": 0.3936181661644425, "grad_norm": 2.009397268295288, "learning_rate": 3.3204528756151123e-05, "loss": 4.294, "step": 7315 }, { "epoch": 0.3936719758932415, "grad_norm": 1.814597487449646, "learning_rate": 3.320053650197049e-05, "loss": 4.8708, "step": 7316 }, { "epoch": 0.39372578562204047, "grad_norm": 2.0411760807037354, "learning_rate": 3.319654401344056e-05, "loss": 4.4964, "step": 7317 }, { "epoch": 0.39377959535083945, "grad_norm": 2.828110694885254, "learning_rate": 3.319255129067547e-05, "loss": 4.5031, "step": 7318 }, { "epoch": 0.3938334050796384, "grad_norm": 2.166053056716919, "learning_rate": 3.3188558333789285e-05, "loss": 4.1133, "step": 7319 }, { "epoch": 0.39388721480843736, "grad_norm": 1.6058179140090942, "learning_rate": 3.318456514289613e-05, "loss": 4.5825, "step": 7320 }, { "epoch": 0.39394102453723634, "grad_norm": 2.071331024169922, "learning_rate": 3.318057171811012e-05, "loss": 4.1377, "step": 7321 }, { "epoch": 0.3939948342660353, "grad_norm": 1.2860820293426514, "learning_rate": 3.317657805954537e-05, "loss": 4.652, "step": 7322 }, { "epoch": 0.39404864399483425, "grad_norm": 1.8446872234344482, "learning_rate": 3.3172584167316015e-05, "loss": 4.0901, "step": 7323 }, { "epoch": 0.39410245372363323, "grad_norm": 1.2743504047393799, "learning_rate": 3.3168590041536184e-05, "loss": 4.6352, "step": 7324 }, { "epoch": 0.3941562634524322, "grad_norm": 1.8514987230300903, "learning_rate": 3.316459568232002e-05, "loss": 4.3888, "step": 7325 }, { "epoch": 0.3942100731812312, "grad_norm": 2.6263840198516846, "learning_rate": 3.3160601089781676e-05, "loss": 4.1352, "step": 7326 }, { "epoch": 0.3942638829100301, "grad_norm": 1.5748932361602783, "learning_rate": 3.31566062640353e-05, "loss": 4.0961, "step": 7327 }, { "epoch": 0.3943176926388291, "grad_norm": 2.297060966491699, "learning_rate": 3.3152611205195055e-05, "loss": 4.1234, "step": 7328 }, { "epoch": 0.3943715023676281, "grad_norm": 1.790695309638977, "learning_rate": 3.314861591337511e-05, "loss": 4.3337, "step": 7329 }, { "epoch": 0.39442531209642706, "grad_norm": 1.296176552772522, "learning_rate": 3.314462038868964e-05, "loss": 4.3563, "step": 7330 }, { "epoch": 0.394479121825226, "grad_norm": 1.8798974752426147, "learning_rate": 3.314062463125283e-05, "loss": 4.2921, "step": 7331 }, { "epoch": 0.39453293155402497, "grad_norm": 1.4498543739318848, "learning_rate": 3.313662864117885e-05, "loss": 4.2932, "step": 7332 }, { "epoch": 0.39458674128282395, "grad_norm": 1.8827317953109741, "learning_rate": 3.313263241858192e-05, "loss": 4.4555, "step": 7333 }, { "epoch": 0.3946405510116229, "grad_norm": 1.0803282260894775, "learning_rate": 3.3128635963576226e-05, "loss": 4.712, "step": 7334 }, { "epoch": 0.39469436074042186, "grad_norm": 2.5246803760528564, "learning_rate": 3.312463927627598e-05, "loss": 4.0381, "step": 7335 }, { "epoch": 0.39474817046922084, "grad_norm": 2.0473556518554688, "learning_rate": 3.31206423567954e-05, "loss": 4.38, "step": 7336 }, { "epoch": 0.3948019801980198, "grad_norm": 1.2388715744018555, "learning_rate": 3.3116645205248704e-05, "loss": 4.4594, "step": 7337 }, { "epoch": 0.39485578992681875, "grad_norm": 3.3314273357391357, "learning_rate": 3.311264782175011e-05, "loss": 3.7824, "step": 7338 }, { "epoch": 0.3949095996556177, "grad_norm": 2.683093786239624, "learning_rate": 3.310865020641387e-05, "loss": 4.3889, "step": 7339 }, { "epoch": 0.3949634093844167, "grad_norm": 1.5901262760162354, "learning_rate": 3.310465235935421e-05, "loss": 4.5497, "step": 7340 }, { "epoch": 0.3950172191132157, "grad_norm": 2.3453564643859863, "learning_rate": 3.310065428068539e-05, "loss": 4.3659, "step": 7341 }, { "epoch": 0.3950710288420146, "grad_norm": 2.2081985473632812, "learning_rate": 3.309665597052166e-05, "loss": 4.3855, "step": 7342 }, { "epoch": 0.3951248385708136, "grad_norm": 1.0377695560455322, "learning_rate": 3.309265742897728e-05, "loss": 4.3681, "step": 7343 }, { "epoch": 0.3951786482996126, "grad_norm": 1.503462553024292, "learning_rate": 3.308865865616651e-05, "loss": 4.7587, "step": 7344 }, { "epoch": 0.39523245802841156, "grad_norm": 2.097852945327759, "learning_rate": 3.308465965220363e-05, "loss": 4.6964, "step": 7345 }, { "epoch": 0.3952862677572105, "grad_norm": 1.989730715751648, "learning_rate": 3.3080660417202934e-05, "loss": 4.2523, "step": 7346 }, { "epoch": 0.39534007748600947, "grad_norm": 2.6556849479675293, "learning_rate": 3.30766609512787e-05, "loss": 4.0981, "step": 7347 }, { "epoch": 0.39539388721480845, "grad_norm": 1.7418123483657837, "learning_rate": 3.3072661254545204e-05, "loss": 4.7403, "step": 7348 }, { "epoch": 0.39544769694360743, "grad_norm": 1.4741950035095215, "learning_rate": 3.306866132711677e-05, "loss": 4.095, "step": 7349 }, { "epoch": 0.39550150667240636, "grad_norm": 1.8139034509658813, "learning_rate": 3.3064661169107704e-05, "loss": 4.151, "step": 7350 }, { "epoch": 0.39555531640120534, "grad_norm": 2.307424783706665, "learning_rate": 3.3060660780632304e-05, "loss": 4.324, "step": 7351 }, { "epoch": 0.3956091261300043, "grad_norm": 1.4942059516906738, "learning_rate": 3.3056660161804905e-05, "loss": 4.205, "step": 7352 }, { "epoch": 0.39566293585880324, "grad_norm": 1.9876465797424316, "learning_rate": 3.305265931273982e-05, "loss": 4.2178, "step": 7353 }, { "epoch": 0.3957167455876022, "grad_norm": 2.387504816055298, "learning_rate": 3.30486582335514e-05, "loss": 4.0795, "step": 7354 }, { "epoch": 0.3957705553164012, "grad_norm": 2.0891435146331787, "learning_rate": 3.304465692435397e-05, "loss": 4.1512, "step": 7355 }, { "epoch": 0.3958243650452002, "grad_norm": 2.849668264389038, "learning_rate": 3.3040655385261885e-05, "loss": 3.9809, "step": 7356 }, { "epoch": 0.3958781747739991, "grad_norm": 1.374096393585205, "learning_rate": 3.3036653616389494e-05, "loss": 4.9175, "step": 7357 }, { "epoch": 0.3959319845027981, "grad_norm": 1.683158278465271, "learning_rate": 3.303265161785116e-05, "loss": 4.5063, "step": 7358 }, { "epoch": 0.3959857942315971, "grad_norm": 1.5758247375488281, "learning_rate": 3.3028649389761253e-05, "loss": 4.413, "step": 7359 }, { "epoch": 0.39603960396039606, "grad_norm": 1.4445925951004028, "learning_rate": 3.3024646932234136e-05, "loss": 4.8247, "step": 7360 }, { "epoch": 0.396093413689195, "grad_norm": 3.0507779121398926, "learning_rate": 3.302064424538419e-05, "loss": 4.2914, "step": 7361 }, { "epoch": 0.39614722341799397, "grad_norm": 1.6521178483963013, "learning_rate": 3.301664132932582e-05, "loss": 4.4555, "step": 7362 }, { "epoch": 0.39620103314679295, "grad_norm": 2.5148372650146484, "learning_rate": 3.301263818417338e-05, "loss": 4.0447, "step": 7363 }, { "epoch": 0.39625484287559193, "grad_norm": 2.0585901737213135, "learning_rate": 3.3008634810041305e-05, "loss": 3.9103, "step": 7364 }, { "epoch": 0.39630865260439085, "grad_norm": 0.985188364982605, "learning_rate": 3.300463120704399e-05, "loss": 4.6954, "step": 7365 }, { "epoch": 0.39636246233318984, "grad_norm": 1.6329172849655151, "learning_rate": 3.300062737529585e-05, "loss": 4.5364, "step": 7366 }, { "epoch": 0.3964162720619888, "grad_norm": 2.9081642627716064, "learning_rate": 3.299662331491128e-05, "loss": 4.1837, "step": 7367 }, { "epoch": 0.3964700817907878, "grad_norm": 2.682396650314331, "learning_rate": 3.299261902600474e-05, "loss": 4.0883, "step": 7368 }, { "epoch": 0.3965238915195867, "grad_norm": 1.1538227796554565, "learning_rate": 3.2988614508690633e-05, "loss": 4.2171, "step": 7369 }, { "epoch": 0.3965777012483857, "grad_norm": 1.931251049041748, "learning_rate": 3.298460976308343e-05, "loss": 4.3545, "step": 7370 }, { "epoch": 0.3966315109771847, "grad_norm": 2.299669027328491, "learning_rate": 3.298060478929754e-05, "loss": 4.2437, "step": 7371 }, { "epoch": 0.39668532070598367, "grad_norm": 2.5982797145843506, "learning_rate": 3.297659958744743e-05, "loss": 3.2664, "step": 7372 }, { "epoch": 0.3967391304347826, "grad_norm": 1.9585232734680176, "learning_rate": 3.297259415764756e-05, "loss": 4.2235, "step": 7373 }, { "epoch": 0.3967929401635816, "grad_norm": 2.2267298698425293, "learning_rate": 3.29685885000124e-05, "loss": 4.3149, "step": 7374 }, { "epoch": 0.39684674989238056, "grad_norm": 1.7671093940734863, "learning_rate": 3.296458261465641e-05, "loss": 4.3648, "step": 7375 }, { "epoch": 0.3969005596211795, "grad_norm": 1.884087324142456, "learning_rate": 3.296057650169406e-05, "loss": 4.3985, "step": 7376 }, { "epoch": 0.39695436934997846, "grad_norm": 2.7439849376678467, "learning_rate": 3.2956570161239864e-05, "loss": 3.8758, "step": 7377 }, { "epoch": 0.39700817907877745, "grad_norm": 1.6233209371566772, "learning_rate": 3.295256359340828e-05, "loss": 4.5967, "step": 7378 }, { "epoch": 0.3970619888075764, "grad_norm": 2.5027382373809814, "learning_rate": 3.2948556798313826e-05, "loss": 3.7208, "step": 7379 }, { "epoch": 0.39711579853637535, "grad_norm": 1.7832444906234741, "learning_rate": 3.294454977607099e-05, "loss": 4.2128, "step": 7380 }, { "epoch": 0.39716960826517433, "grad_norm": 1.9299521446228027, "learning_rate": 3.29405425267943e-05, "loss": 4.6372, "step": 7381 }, { "epoch": 0.3972234179939733, "grad_norm": 3.180284261703491, "learning_rate": 3.293653505059826e-05, "loss": 3.9462, "step": 7382 }, { "epoch": 0.3972772277227723, "grad_norm": 2.134211540222168, "learning_rate": 3.293252734759739e-05, "loss": 4.6978, "step": 7383 }, { "epoch": 0.3973310374515712, "grad_norm": 1.748953938484192, "learning_rate": 3.292851941790622e-05, "loss": 4.2763, "step": 7384 }, { "epoch": 0.3973848471803702, "grad_norm": 1.645950198173523, "learning_rate": 3.29245112616393e-05, "loss": 3.9931, "step": 7385 }, { "epoch": 0.3974386569091692, "grad_norm": 1.4490478038787842, "learning_rate": 3.292050287891116e-05, "loss": 4.5947, "step": 7386 }, { "epoch": 0.39749246663796817, "grad_norm": 1.1821781396865845, "learning_rate": 3.291649426983635e-05, "loss": 4.6587, "step": 7387 }, { "epoch": 0.3975462763667671, "grad_norm": 2.1287636756896973, "learning_rate": 3.2912485434529426e-05, "loss": 4.5457, "step": 7388 }, { "epoch": 0.3976000860955661, "grad_norm": 2.223884344100952, "learning_rate": 3.2908476373104955e-05, "loss": 4.1277, "step": 7389 }, { "epoch": 0.39765389582436506, "grad_norm": 2.977794885635376, "learning_rate": 3.290446708567749e-05, "loss": 3.7905, "step": 7390 }, { "epoch": 0.39770770555316404, "grad_norm": 1.3494250774383545, "learning_rate": 3.2900457572361626e-05, "loss": 4.5955, "step": 7391 }, { "epoch": 0.39776151528196296, "grad_norm": 2.262367010116577, "learning_rate": 3.289644783327193e-05, "loss": 4.217, "step": 7392 }, { "epoch": 0.39781532501076194, "grad_norm": 2.1707937717437744, "learning_rate": 3.2892437868523e-05, "loss": 5.0482, "step": 7393 }, { "epoch": 0.3978691347395609, "grad_norm": 2.3370635509490967, "learning_rate": 3.2888427678229414e-05, "loss": 3.9044, "step": 7394 }, { "epoch": 0.3979229444683599, "grad_norm": 1.8737679719924927, "learning_rate": 3.288441726250578e-05, "loss": 4.6387, "step": 7395 }, { "epoch": 0.39797675419715883, "grad_norm": 2.639080762863159, "learning_rate": 3.2880406621466726e-05, "loss": 4.3942, "step": 7396 }, { "epoch": 0.3980305639259578, "grad_norm": 2.1791465282440186, "learning_rate": 3.287639575522683e-05, "loss": 3.5801, "step": 7397 }, { "epoch": 0.3980843736547568, "grad_norm": 2.131802797317505, "learning_rate": 3.2872384663900735e-05, "loss": 3.9704, "step": 7398 }, { "epoch": 0.3981381833835557, "grad_norm": 1.6962507963180542, "learning_rate": 3.2868373347603055e-05, "loss": 4.3182, "step": 7399 }, { "epoch": 0.3981919931123547, "grad_norm": 1.3435362577438354, "learning_rate": 3.286436180644844e-05, "loss": 4.4301, "step": 7400 }, { "epoch": 0.3982458028411537, "grad_norm": 1.4961307048797607, "learning_rate": 3.286035004055151e-05, "loss": 4.2875, "step": 7401 }, { "epoch": 0.39829961256995267, "grad_norm": 1.19411039352417, "learning_rate": 3.2856338050026914e-05, "loss": 4.3827, "step": 7402 }, { "epoch": 0.3983534222987516, "grad_norm": 1.1441938877105713, "learning_rate": 3.285232583498931e-05, "loss": 4.8425, "step": 7403 }, { "epoch": 0.3984072320275506, "grad_norm": 2.353243350982666, "learning_rate": 3.284831339555335e-05, "loss": 4.4855, "step": 7404 }, { "epoch": 0.39846104175634955, "grad_norm": 2.3395564556121826, "learning_rate": 3.284430073183371e-05, "loss": 4.2771, "step": 7405 }, { "epoch": 0.39851485148514854, "grad_norm": 1.7496235370635986, "learning_rate": 3.2840287843945054e-05, "loss": 3.9902, "step": 7406 }, { "epoch": 0.39856866121394746, "grad_norm": 1.0116100311279297, "learning_rate": 3.2836274732002056e-05, "loss": 4.6068, "step": 7407 }, { "epoch": 0.39862247094274644, "grad_norm": 1.7527815103530884, "learning_rate": 3.2832261396119404e-05, "loss": 4.2986, "step": 7408 }, { "epoch": 0.3986762806715454, "grad_norm": 1.6098817586898804, "learning_rate": 3.282824783641179e-05, "loss": 4.3676, "step": 7409 }, { "epoch": 0.3987300904003444, "grad_norm": 1.3291575908660889, "learning_rate": 3.28242340529939e-05, "loss": 4.5987, "step": 7410 }, { "epoch": 0.39878390012914333, "grad_norm": 1.7929198741912842, "learning_rate": 3.2820220045980454e-05, "loss": 4.098, "step": 7411 }, { "epoch": 0.3988377098579423, "grad_norm": 3.198122024536133, "learning_rate": 3.2816205815486153e-05, "loss": 4.3269, "step": 7412 }, { "epoch": 0.3988915195867413, "grad_norm": 1.502790927886963, "learning_rate": 3.281219136162571e-05, "loss": 4.1322, "step": 7413 }, { "epoch": 0.3989453293155403, "grad_norm": 2.3172647953033447, "learning_rate": 3.280817668451385e-05, "loss": 4.7691, "step": 7414 }, { "epoch": 0.3989991390443392, "grad_norm": 1.0234665870666504, "learning_rate": 3.28041617842653e-05, "loss": 4.3788, "step": 7415 }, { "epoch": 0.3990529487731382, "grad_norm": 2.9138338565826416, "learning_rate": 3.28001466609948e-05, "loss": 3.6746, "step": 7416 }, { "epoch": 0.39910675850193716, "grad_norm": 2.0207536220550537, "learning_rate": 3.279613131481708e-05, "loss": 4.1661, "step": 7417 }, { "epoch": 0.3991605682307361, "grad_norm": 2.7459475994110107, "learning_rate": 3.279211574584691e-05, "loss": 3.5819, "step": 7418 }, { "epoch": 0.39921437795953507, "grad_norm": 2.2590444087982178, "learning_rate": 3.278809995419902e-05, "loss": 4.4705, "step": 7419 }, { "epoch": 0.39926818768833405, "grad_norm": 1.2149823904037476, "learning_rate": 3.278408393998818e-05, "loss": 4.7076, "step": 7420 }, { "epoch": 0.39932199741713303, "grad_norm": 1.0385103225708008, "learning_rate": 3.278006770332917e-05, "loss": 4.3605, "step": 7421 }, { "epoch": 0.39937580714593196, "grad_norm": 1.4455205202102661, "learning_rate": 3.277605124433675e-05, "loss": 4.6752, "step": 7422 }, { "epoch": 0.39942961687473094, "grad_norm": 1.8390789031982422, "learning_rate": 3.277203456312569e-05, "loss": 4.5975, "step": 7423 }, { "epoch": 0.3994834266035299, "grad_norm": 1.145579218864441, "learning_rate": 3.276801765981079e-05, "loss": 4.5821, "step": 7424 }, { "epoch": 0.3995372363323289, "grad_norm": 2.0280890464782715, "learning_rate": 3.276400053450683e-05, "loss": 4.5027, "step": 7425 }, { "epoch": 0.39959104606112783, "grad_norm": 1.2237167358398438, "learning_rate": 3.275998318732863e-05, "loss": 4.6071, "step": 7426 }, { "epoch": 0.3996448557899268, "grad_norm": 2.038165807723999, "learning_rate": 3.275596561839098e-05, "loss": 4.3559, "step": 7427 }, { "epoch": 0.3996986655187258, "grad_norm": 2.128243923187256, "learning_rate": 3.275194782780869e-05, "loss": 4.3883, "step": 7428 }, { "epoch": 0.3997524752475248, "grad_norm": 2.348832845687866, "learning_rate": 3.274792981569659e-05, "loss": 4.6253, "step": 7429 }, { "epoch": 0.3998062849763237, "grad_norm": 1.766829490661621, "learning_rate": 3.2743911582169485e-05, "loss": 4.4897, "step": 7430 }, { "epoch": 0.3998600947051227, "grad_norm": 2.1525204181671143, "learning_rate": 3.2739893127342224e-05, "loss": 4.546, "step": 7431 }, { "epoch": 0.39991390443392166, "grad_norm": 1.5943899154663086, "learning_rate": 3.2735874451329636e-05, "loss": 4.7019, "step": 7432 }, { "epoch": 0.39996771416272064, "grad_norm": 2.4139068126678467, "learning_rate": 3.273185555424655e-05, "loss": 4.1233, "step": 7433 }, { "epoch": 0.40002152389151957, "grad_norm": 2.7461366653442383, "learning_rate": 3.272783643620784e-05, "loss": 4.1089, "step": 7434 }, { "epoch": 0.40007533362031855, "grad_norm": 1.903737187385559, "learning_rate": 3.272381709732835e-05, "loss": 4.594, "step": 7435 }, { "epoch": 0.40012914334911753, "grad_norm": 2.379263401031494, "learning_rate": 3.271979753772294e-05, "loss": 3.8364, "step": 7436 }, { "epoch": 0.4001829530779165, "grad_norm": 2.1420910358428955, "learning_rate": 3.271577775750648e-05, "loss": 4.3907, "step": 7437 }, { "epoch": 0.40023676280671544, "grad_norm": 2.2657222747802734, "learning_rate": 3.2711757756793835e-05, "loss": 4.2016, "step": 7438 }, { "epoch": 0.4002905725355144, "grad_norm": 1.7449101209640503, "learning_rate": 3.270773753569991e-05, "loss": 4.4128, "step": 7439 }, { "epoch": 0.4003443822643134, "grad_norm": 2.740997076034546, "learning_rate": 3.270371709433958e-05, "loss": 3.8591, "step": 7440 }, { "epoch": 0.40039819199311233, "grad_norm": 2.3443453311920166, "learning_rate": 3.269969643282772e-05, "loss": 3.9678, "step": 7441 }, { "epoch": 0.4004520017219113, "grad_norm": 1.3160076141357422, "learning_rate": 3.269567555127926e-05, "loss": 4.334, "step": 7442 }, { "epoch": 0.4005058114507103, "grad_norm": 2.309173583984375, "learning_rate": 3.2691654449809086e-05, "loss": 3.9723, "step": 7443 }, { "epoch": 0.4005596211795093, "grad_norm": 1.035834550857544, "learning_rate": 3.268763312853211e-05, "loss": 4.5351, "step": 7444 }, { "epoch": 0.4006134309083082, "grad_norm": 2.363945484161377, "learning_rate": 3.268361158756326e-05, "loss": 4.26, "step": 7445 }, { "epoch": 0.4006672406371072, "grad_norm": 1.5016893148422241, "learning_rate": 3.2679589827017465e-05, "loss": 4.6133, "step": 7446 }, { "epoch": 0.40072105036590616, "grad_norm": 1.592471957206726, "learning_rate": 3.267556784700964e-05, "loss": 4.2923, "step": 7447 }, { "epoch": 0.40077486009470514, "grad_norm": 1.1200402975082397, "learning_rate": 3.267154564765473e-05, "loss": 4.4237, "step": 7448 }, { "epoch": 0.40082866982350407, "grad_norm": 1.6141098737716675, "learning_rate": 3.266752322906769e-05, "loss": 4.4254, "step": 7449 }, { "epoch": 0.40088247955230305, "grad_norm": 1.3329521417617798, "learning_rate": 3.2663500591363455e-05, "loss": 4.5312, "step": 7450 }, { "epoch": 0.40093628928110203, "grad_norm": 1.2856628894805908, "learning_rate": 3.2659477734656976e-05, "loss": 4.6121, "step": 7451 }, { "epoch": 0.400990099009901, "grad_norm": 2.457395553588867, "learning_rate": 3.265545465906323e-05, "loss": 3.9081, "step": 7452 }, { "epoch": 0.40104390873869994, "grad_norm": 1.979380488395691, "learning_rate": 3.2651431364697186e-05, "loss": 4.6637, "step": 7453 }, { "epoch": 0.4010977184674989, "grad_norm": 1.7547870874404907, "learning_rate": 3.2647407851673815e-05, "loss": 4.5594, "step": 7454 }, { "epoch": 0.4011515281962979, "grad_norm": 1.3958799839019775, "learning_rate": 3.264338412010809e-05, "loss": 4.3113, "step": 7455 }, { "epoch": 0.4012053379250969, "grad_norm": 1.9914706945419312, "learning_rate": 3.2639360170115e-05, "loss": 4.6936, "step": 7456 }, { "epoch": 0.4012591476538958, "grad_norm": 2.8139379024505615, "learning_rate": 3.2635336001809555e-05, "loss": 3.4139, "step": 7457 }, { "epoch": 0.4013129573826948, "grad_norm": 1.9452898502349854, "learning_rate": 3.263131161530674e-05, "loss": 4.0353, "step": 7458 }, { "epoch": 0.40136676711149377, "grad_norm": 2.57607364654541, "learning_rate": 3.262728701072156e-05, "loss": 3.5504, "step": 7459 }, { "epoch": 0.4014205768402927, "grad_norm": 1.327516794204712, "learning_rate": 3.262326218816904e-05, "loss": 4.8834, "step": 7460 }, { "epoch": 0.4014743865690917, "grad_norm": 2.369719982147217, "learning_rate": 3.261923714776419e-05, "loss": 4.4188, "step": 7461 }, { "epoch": 0.40152819629789066, "grad_norm": 1.9529730081558228, "learning_rate": 3.261521188962203e-05, "loss": 4.2563, "step": 7462 }, { "epoch": 0.40158200602668964, "grad_norm": 1.11591374874115, "learning_rate": 3.26111864138576e-05, "loss": 4.2541, "step": 7463 }, { "epoch": 0.40163581575548857, "grad_norm": 2.0294125080108643, "learning_rate": 3.260716072058593e-05, "loss": 4.3581, "step": 7464 }, { "epoch": 0.40168962548428755, "grad_norm": 2.2200334072113037, "learning_rate": 3.2603134809922075e-05, "loss": 3.8514, "step": 7465 }, { "epoch": 0.40174343521308653, "grad_norm": 1.0728905200958252, "learning_rate": 3.259910868198107e-05, "loss": 4.6349, "step": 7466 }, { "epoch": 0.4017972449418855, "grad_norm": 1.2902112007141113, "learning_rate": 3.259508233687798e-05, "loss": 4.3635, "step": 7467 }, { "epoch": 0.40185105467068444, "grad_norm": 3.4552271366119385, "learning_rate": 3.259105577472787e-05, "loss": 3.7244, "step": 7468 }, { "epoch": 0.4019048643994834, "grad_norm": 2.201000213623047, "learning_rate": 3.2587028995645794e-05, "loss": 4.5409, "step": 7469 }, { "epoch": 0.4019586741282824, "grad_norm": 0.9579575061798096, "learning_rate": 3.258300199974685e-05, "loss": 4.513, "step": 7470 }, { "epoch": 0.4020124838570814, "grad_norm": 1.8455336093902588, "learning_rate": 3.257897478714609e-05, "loss": 4.1502, "step": 7471 }, { "epoch": 0.4020662935858803, "grad_norm": 1.8090250492095947, "learning_rate": 3.2574947357958625e-05, "loss": 4.1141, "step": 7472 }, { "epoch": 0.4021201033146793, "grad_norm": 1.6437422037124634, "learning_rate": 3.257091971229954e-05, "loss": 4.4802, "step": 7473 }, { "epoch": 0.40217391304347827, "grad_norm": 1.869679570198059, "learning_rate": 3.256689185028392e-05, "loss": 4.5759, "step": 7474 }, { "epoch": 0.40222772277227725, "grad_norm": 2.689197063446045, "learning_rate": 3.25628637720269e-05, "loss": 3.9829, "step": 7475 }, { "epoch": 0.4022815325010762, "grad_norm": 1.7460319995880127, "learning_rate": 3.2558835477643566e-05, "loss": 4.536, "step": 7476 }, { "epoch": 0.40233534222987516, "grad_norm": 2.505558729171753, "learning_rate": 3.2554806967249045e-05, "loss": 4.1392, "step": 7477 }, { "epoch": 0.40238915195867414, "grad_norm": 1.6634334325790405, "learning_rate": 3.2550778240958464e-05, "loss": 4.3203, "step": 7478 }, { "epoch": 0.4024429616874731, "grad_norm": 1.8197131156921387, "learning_rate": 3.2546749298886945e-05, "loss": 4.0424, "step": 7479 }, { "epoch": 0.40249677141627205, "grad_norm": 1.9284889698028564, "learning_rate": 3.254272014114963e-05, "loss": 4.2209, "step": 7480 }, { "epoch": 0.40255058114507103, "grad_norm": 1.4910119771957397, "learning_rate": 3.253869076786167e-05, "loss": 4.1197, "step": 7481 }, { "epoch": 0.40260439087387, "grad_norm": 1.1989474296569824, "learning_rate": 3.25346611791382e-05, "loss": 4.3068, "step": 7482 }, { "epoch": 0.40265820060266894, "grad_norm": 2.091294288635254, "learning_rate": 3.253063137509438e-05, "loss": 4.6673, "step": 7483 }, { "epoch": 0.4027120103314679, "grad_norm": 1.374018669128418, "learning_rate": 3.252660135584536e-05, "loss": 4.7076, "step": 7484 }, { "epoch": 0.4027658200602669, "grad_norm": 2.9415552616119385, "learning_rate": 3.252257112150633e-05, "loss": 3.9835, "step": 7485 }, { "epoch": 0.4028196297890659, "grad_norm": 2.113368034362793, "learning_rate": 3.2518540672192445e-05, "loss": 3.8079, "step": 7486 }, { "epoch": 0.4028734395178648, "grad_norm": 1.691383957862854, "learning_rate": 3.251451000801889e-05, "loss": 4.2418, "step": 7487 }, { "epoch": 0.4029272492466638, "grad_norm": 1.9090579748153687, "learning_rate": 3.2510479129100854e-05, "loss": 4.4468, "step": 7488 }, { "epoch": 0.40298105897546277, "grad_norm": 2.200836420059204, "learning_rate": 3.250644803555352e-05, "loss": 3.903, "step": 7489 }, { "epoch": 0.40303486870426175, "grad_norm": 1.303019404411316, "learning_rate": 3.2502416727492095e-05, "loss": 4.7277, "step": 7490 }, { "epoch": 0.4030886784330607, "grad_norm": 2.3232202529907227, "learning_rate": 3.249838520503178e-05, "loss": 4.4841, "step": 7491 }, { "epoch": 0.40314248816185966, "grad_norm": 1.591664433479309, "learning_rate": 3.2494353468287786e-05, "loss": 4.693, "step": 7492 }, { "epoch": 0.40319629789065864, "grad_norm": 2.6079986095428467, "learning_rate": 3.249032151737532e-05, "loss": 4.2676, "step": 7493 }, { "epoch": 0.4032501076194576, "grad_norm": 2.797196626663208, "learning_rate": 3.2486289352409614e-05, "loss": 3.715, "step": 7494 }, { "epoch": 0.40330391734825655, "grad_norm": 1.5127724409103394, "learning_rate": 3.2482256973505895e-05, "loss": 4.2529, "step": 7495 }, { "epoch": 0.40335772707705553, "grad_norm": 2.871924638748169, "learning_rate": 3.24782243807794e-05, "loss": 4.2734, "step": 7496 }, { "epoch": 0.4034115368058545, "grad_norm": 2.3474559783935547, "learning_rate": 3.247419157434536e-05, "loss": 4.6889, "step": 7497 }, { "epoch": 0.4034653465346535, "grad_norm": 1.4939883947372437, "learning_rate": 3.247015855431903e-05, "loss": 4.6681, "step": 7498 }, { "epoch": 0.4035191562634524, "grad_norm": 2.119504690170288, "learning_rate": 3.2466125320815666e-05, "loss": 4.3025, "step": 7499 }, { "epoch": 0.4035729659922514, "grad_norm": 1.799484372138977, "learning_rate": 3.246209187395052e-05, "loss": 4.5571, "step": 7500 }, { "epoch": 0.4036267757210504, "grad_norm": 2.2318758964538574, "learning_rate": 3.245805821383886e-05, "loss": 4.2309, "step": 7501 }, { "epoch": 0.4036805854498493, "grad_norm": 1.3771520853042603, "learning_rate": 3.245402434059594e-05, "loss": 4.2967, "step": 7502 }, { "epoch": 0.4037343951786483, "grad_norm": 3.1579484939575195, "learning_rate": 3.2449990254337074e-05, "loss": 3.2633, "step": 7503 }, { "epoch": 0.40378820490744727, "grad_norm": 2.381932258605957, "learning_rate": 3.244595595517752e-05, "loss": 4.4619, "step": 7504 }, { "epoch": 0.40384201463624625, "grad_norm": 2.3517324924468994, "learning_rate": 3.2441921443232564e-05, "loss": 3.5935, "step": 7505 }, { "epoch": 0.4038958243650452, "grad_norm": 1.3245203495025635, "learning_rate": 3.243788671861752e-05, "loss": 4.503, "step": 7506 }, { "epoch": 0.40394963409384416, "grad_norm": 2.3575315475463867, "learning_rate": 3.2433851781447675e-05, "loss": 4.4312, "step": 7507 }, { "epoch": 0.40400344382264314, "grad_norm": 2.160081386566162, "learning_rate": 3.242981663183834e-05, "loss": 4.1263, "step": 7508 }, { "epoch": 0.4040572535514421, "grad_norm": 0.9954797029495239, "learning_rate": 3.2425781269904824e-05, "loss": 4.5677, "step": 7509 }, { "epoch": 0.40411106328024105, "grad_norm": 2.7434089183807373, "learning_rate": 3.2421745695762456e-05, "loss": 4.2513, "step": 7510 }, { "epoch": 0.40416487300904, "grad_norm": 1.2188217639923096, "learning_rate": 3.241770990952657e-05, "loss": 4.6626, "step": 7511 }, { "epoch": 0.404218682737839, "grad_norm": 2.148972988128662, "learning_rate": 3.241367391131247e-05, "loss": 3.6654, "step": 7512 }, { "epoch": 0.404272492466638, "grad_norm": 1.6510639190673828, "learning_rate": 3.2409637701235514e-05, "loss": 4.4528, "step": 7513 }, { "epoch": 0.4043263021954369, "grad_norm": 1.567831039428711, "learning_rate": 3.2405601279411046e-05, "loss": 4.5085, "step": 7514 }, { "epoch": 0.4043801119242359, "grad_norm": 2.333272933959961, "learning_rate": 3.2401564645954407e-05, "loss": 3.8947, "step": 7515 }, { "epoch": 0.4044339216530349, "grad_norm": 1.2044892311096191, "learning_rate": 3.239752780098096e-05, "loss": 4.7336, "step": 7516 }, { "epoch": 0.40448773138183386, "grad_norm": 1.520811676979065, "learning_rate": 3.239349074460607e-05, "loss": 4.4487, "step": 7517 }, { "epoch": 0.4045415411106328, "grad_norm": 2.240492105484009, "learning_rate": 3.23894534769451e-05, "loss": 3.788, "step": 7518 }, { "epoch": 0.40459535083943177, "grad_norm": 1.4864637851715088, "learning_rate": 3.238541599811342e-05, "loss": 4.2352, "step": 7519 }, { "epoch": 0.40464916056823075, "grad_norm": 1.4315863847732544, "learning_rate": 3.238137830822642e-05, "loss": 4.5209, "step": 7520 }, { "epoch": 0.40470297029702973, "grad_norm": 1.9106963872909546, "learning_rate": 3.237734040739948e-05, "loss": 4.0133, "step": 7521 }, { "epoch": 0.40475678002582866, "grad_norm": 2.3792800903320312, "learning_rate": 3.237330229574799e-05, "loss": 3.7803, "step": 7522 }, { "epoch": 0.40481058975462764, "grad_norm": 1.4969557523727417, "learning_rate": 3.236926397338735e-05, "loss": 4.4183, "step": 7523 }, { "epoch": 0.4048643994834266, "grad_norm": 1.9605993032455444, "learning_rate": 3.236522544043298e-05, "loss": 4.0536, "step": 7524 }, { "epoch": 0.40491820921222554, "grad_norm": 1.5434163808822632, "learning_rate": 3.236118669700027e-05, "loss": 4.5725, "step": 7525 }, { "epoch": 0.4049720189410245, "grad_norm": 1.6906969547271729, "learning_rate": 3.235714774320464e-05, "loss": 4.5045, "step": 7526 }, { "epoch": 0.4050258286698235, "grad_norm": 2.33255672454834, "learning_rate": 3.235310857916152e-05, "loss": 4.8895, "step": 7527 }, { "epoch": 0.4050796383986225, "grad_norm": 2.038696050643921, "learning_rate": 3.2349069204986324e-05, "loss": 3.9827, "step": 7528 }, { "epoch": 0.4051334481274214, "grad_norm": 2.0589425563812256, "learning_rate": 3.234502962079451e-05, "loss": 3.6683, "step": 7529 }, { "epoch": 0.4051872578562204, "grad_norm": 1.9846254587173462, "learning_rate": 3.2340989826701504e-05, "loss": 3.4239, "step": 7530 }, { "epoch": 0.4052410675850194, "grad_norm": 2.6193385124206543, "learning_rate": 3.2336949822822746e-05, "loss": 3.9637, "step": 7531 }, { "epoch": 0.40529487731381836, "grad_norm": 2.0612294673919678, "learning_rate": 3.23329096092737e-05, "loss": 4.1715, "step": 7532 }, { "epoch": 0.4053486870426173, "grad_norm": 1.3550978899002075, "learning_rate": 3.232886918616982e-05, "loss": 4.617, "step": 7533 }, { "epoch": 0.40540249677141627, "grad_norm": 1.4119118452072144, "learning_rate": 3.232482855362657e-05, "loss": 4.634, "step": 7534 }, { "epoch": 0.40545630650021525, "grad_norm": 1.5467809438705444, "learning_rate": 3.232078771175943e-05, "loss": 4.9249, "step": 7535 }, { "epoch": 0.40551011622901423, "grad_norm": 1.40690279006958, "learning_rate": 3.2316746660683863e-05, "loss": 4.0321, "step": 7536 }, { "epoch": 0.40556392595781315, "grad_norm": 1.9173765182495117, "learning_rate": 3.2312705400515355e-05, "loss": 4.06, "step": 7537 }, { "epoch": 0.40561773568661214, "grad_norm": 1.4456769227981567, "learning_rate": 3.230866393136939e-05, "loss": 4.6617, "step": 7538 }, { "epoch": 0.4056715454154111, "grad_norm": 1.9377050399780273, "learning_rate": 3.230462225336147e-05, "loss": 4.8546, "step": 7539 }, { "epoch": 0.4057253551442101, "grad_norm": 1.7425552606582642, "learning_rate": 3.23005803666071e-05, "loss": 4.4982, "step": 7540 }, { "epoch": 0.405779164873009, "grad_norm": 1.1305056810379028, "learning_rate": 3.229653827122177e-05, "loss": 4.3028, "step": 7541 }, { "epoch": 0.405832974601808, "grad_norm": 1.4159362316131592, "learning_rate": 3.2292495967321013e-05, "loss": 4.9047, "step": 7542 }, { "epoch": 0.405886784330607, "grad_norm": 2.298013210296631, "learning_rate": 3.228845345502033e-05, "loss": 3.9556, "step": 7543 }, { "epoch": 0.40594059405940597, "grad_norm": 1.404572606086731, "learning_rate": 3.228441073443525e-05, "loss": 4.4287, "step": 7544 }, { "epoch": 0.4059944037882049, "grad_norm": 1.5793565511703491, "learning_rate": 3.228036780568131e-05, "loss": 4.754, "step": 7545 }, { "epoch": 0.4060482135170039, "grad_norm": 1.9964195489883423, "learning_rate": 3.227632466887403e-05, "loss": 4.2435, "step": 7546 }, { "epoch": 0.40610202324580286, "grad_norm": 1.7330654859542847, "learning_rate": 3.227228132412897e-05, "loss": 4.6186, "step": 7547 }, { "epoch": 0.4061558329746018, "grad_norm": 1.6016379594802856, "learning_rate": 3.226823777156166e-05, "loss": 4.3961, "step": 7548 }, { "epoch": 0.40620964270340076, "grad_norm": 1.9337998628616333, "learning_rate": 3.2264194011287675e-05, "loss": 4.4393, "step": 7549 }, { "epoch": 0.40626345243219975, "grad_norm": 2.2497565746307373, "learning_rate": 3.226015004342256e-05, "loss": 4.512, "step": 7550 }, { "epoch": 0.4063172621609987, "grad_norm": 1.2833092212677002, "learning_rate": 3.225610586808188e-05, "loss": 4.7259, "step": 7551 }, { "epoch": 0.40637107188979765, "grad_norm": 1.1457130908966064, "learning_rate": 3.2252061485381215e-05, "loss": 4.6047, "step": 7552 }, { "epoch": 0.40642488161859663, "grad_norm": 1.8618930578231812, "learning_rate": 3.224801689543614e-05, "loss": 4.1497, "step": 7553 }, { "epoch": 0.4064786913473956, "grad_norm": 1.683746337890625, "learning_rate": 3.224397209836223e-05, "loss": 4.5206, "step": 7554 }, { "epoch": 0.4065325010761946, "grad_norm": 2.0820963382720947, "learning_rate": 3.223992709427508e-05, "loss": 4.1126, "step": 7555 }, { "epoch": 0.4065863108049935, "grad_norm": 2.7715342044830322, "learning_rate": 3.2235881883290296e-05, "loss": 3.8047, "step": 7556 }, { "epoch": 0.4066401205337925, "grad_norm": 1.5108470916748047, "learning_rate": 3.223183646552347e-05, "loss": 4.2853, "step": 7557 }, { "epoch": 0.4066939302625915, "grad_norm": 1.3210210800170898, "learning_rate": 3.222779084109021e-05, "loss": 4.5096, "step": 7558 }, { "epoch": 0.40674773999139047, "grad_norm": 1.5107954740524292, "learning_rate": 3.222374501010612e-05, "loss": 4.6986, "step": 7559 }, { "epoch": 0.4068015497201894, "grad_norm": 1.6134470701217651, "learning_rate": 3.221969897268683e-05, "loss": 4.4697, "step": 7560 }, { "epoch": 0.4068553594489884, "grad_norm": 2.364490509033203, "learning_rate": 3.221565272894797e-05, "loss": 3.9427, "step": 7561 }, { "epoch": 0.40690916917778736, "grad_norm": 2.162407875061035, "learning_rate": 3.221160627900515e-05, "loss": 4.5413, "step": 7562 }, { "epoch": 0.40696297890658634, "grad_norm": 1.6319025754928589, "learning_rate": 3.2207559622974024e-05, "loss": 4.4268, "step": 7563 }, { "epoch": 0.40701678863538526, "grad_norm": 1.5344337224960327, "learning_rate": 3.220351276097023e-05, "loss": 4.7443, "step": 7564 }, { "epoch": 0.40707059836418424, "grad_norm": 1.5284689664840698, "learning_rate": 3.219946569310942e-05, "loss": 4.4518, "step": 7565 }, { "epoch": 0.4071244080929832, "grad_norm": 1.7717756032943726, "learning_rate": 3.2195418419507246e-05, "loss": 4.0192, "step": 7566 }, { "epoch": 0.40717821782178215, "grad_norm": 1.9630191326141357, "learning_rate": 3.219137094027936e-05, "loss": 4.2971, "step": 7567 }, { "epoch": 0.40723202755058113, "grad_norm": 2.6189093589782715, "learning_rate": 3.218732325554144e-05, "loss": 3.8469, "step": 7568 }, { "epoch": 0.4072858372793801, "grad_norm": 2.364377737045288, "learning_rate": 3.218327536540915e-05, "loss": 4.4229, "step": 7569 }, { "epoch": 0.4073396470081791, "grad_norm": 2.6056394577026367, "learning_rate": 3.2179227269998175e-05, "loss": 3.6586, "step": 7570 }, { "epoch": 0.407393456736978, "grad_norm": 1.5166922807693481, "learning_rate": 3.217517896942419e-05, "loss": 4.4671, "step": 7571 }, { "epoch": 0.407447266465777, "grad_norm": 2.216038227081299, "learning_rate": 3.2171130463802895e-05, "loss": 4.13, "step": 7572 }, { "epoch": 0.407501076194576, "grad_norm": 1.6481010913848877, "learning_rate": 3.2167081753249975e-05, "loss": 4.6589, "step": 7573 }, { "epoch": 0.40755488592337497, "grad_norm": 1.1082279682159424, "learning_rate": 3.2163032837881133e-05, "loss": 4.7237, "step": 7574 }, { "epoch": 0.4076086956521739, "grad_norm": 2.0725514888763428, "learning_rate": 3.215898371781208e-05, "loss": 4.2197, "step": 7575 }, { "epoch": 0.4076625053809729, "grad_norm": 1.6423742771148682, "learning_rate": 3.2154934393158534e-05, "loss": 4.2111, "step": 7576 }, { "epoch": 0.40771631510977185, "grad_norm": 1.7704750299453735, "learning_rate": 3.21508848640362e-05, "loss": 4.2096, "step": 7577 }, { "epoch": 0.40777012483857084, "grad_norm": 3.0374343395233154, "learning_rate": 3.2146835130560816e-05, "loss": 4.0229, "step": 7578 }, { "epoch": 0.40782393456736976, "grad_norm": 2.0681679248809814, "learning_rate": 3.214278519284811e-05, "loss": 4.2105, "step": 7579 }, { "epoch": 0.40787774429616874, "grad_norm": 1.7449158430099487, "learning_rate": 3.2138735051013806e-05, "loss": 4.3666, "step": 7580 }, { "epoch": 0.4079315540249677, "grad_norm": 1.8064147233963013, "learning_rate": 3.213468470517366e-05, "loss": 4.6986, "step": 7581 }, { "epoch": 0.4079853637537667, "grad_norm": 2.55680775642395, "learning_rate": 3.213063415544341e-05, "loss": 4.3391, "step": 7582 }, { "epoch": 0.40803917348256563, "grad_norm": 1.6297128200531006, "learning_rate": 3.212658340193882e-05, "loss": 4.5706, "step": 7583 }, { "epoch": 0.4080929832113646, "grad_norm": 1.7876187562942505, "learning_rate": 3.212253244477565e-05, "loss": 4.4166, "step": 7584 }, { "epoch": 0.4081467929401636, "grad_norm": 2.278938055038452, "learning_rate": 3.2118481284069645e-05, "loss": 4.5401, "step": 7585 }, { "epoch": 0.4082006026689626, "grad_norm": 1.0353513956069946, "learning_rate": 3.2114429919936603e-05, "loss": 4.439, "step": 7586 }, { "epoch": 0.4082544123977615, "grad_norm": 1.3989514112472534, "learning_rate": 3.211037835249229e-05, "loss": 4.7102, "step": 7587 }, { "epoch": 0.4083082221265605, "grad_norm": 1.2801294326782227, "learning_rate": 3.2106326581852484e-05, "loss": 4.2003, "step": 7588 }, { "epoch": 0.40836203185535946, "grad_norm": 1.809834599494934, "learning_rate": 3.210227460813298e-05, "loss": 4.5777, "step": 7589 }, { "epoch": 0.4084158415841584, "grad_norm": 2.0804622173309326, "learning_rate": 3.209822243144956e-05, "loss": 4.9138, "step": 7590 }, { "epoch": 0.40846965131295737, "grad_norm": 1.8692352771759033, "learning_rate": 3.209417005191805e-05, "loss": 4.2801, "step": 7591 }, { "epoch": 0.40852346104175635, "grad_norm": 2.019120693206787, "learning_rate": 3.209011746965423e-05, "loss": 4.2981, "step": 7592 }, { "epoch": 0.40857727077055533, "grad_norm": 3.173550605773926, "learning_rate": 3.208606468477393e-05, "loss": 3.8565, "step": 7593 }, { "epoch": 0.40863108049935426, "grad_norm": 2.0009102821350098, "learning_rate": 3.208201169739296e-05, "loss": 4.4006, "step": 7594 }, { "epoch": 0.40868489022815324, "grad_norm": 2.3942160606384277, "learning_rate": 3.207795850762714e-05, "loss": 4.2194, "step": 7595 }, { "epoch": 0.4087386999569522, "grad_norm": 1.027704119682312, "learning_rate": 3.207390511559231e-05, "loss": 4.4288, "step": 7596 }, { "epoch": 0.4087925096857512, "grad_norm": 1.5448774099349976, "learning_rate": 3.206985152140429e-05, "loss": 4.6472, "step": 7597 }, { "epoch": 0.40884631941455013, "grad_norm": 3.228194236755371, "learning_rate": 3.2065797725178936e-05, "loss": 4.2447, "step": 7598 }, { "epoch": 0.4089001291433491, "grad_norm": 1.7646539211273193, "learning_rate": 3.206174372703209e-05, "loss": 4.7196, "step": 7599 }, { "epoch": 0.4089539388721481, "grad_norm": 1.6138325929641724, "learning_rate": 3.2057689527079594e-05, "loss": 4.5424, "step": 7600 }, { "epoch": 0.4090077486009471, "grad_norm": 1.9409235715866089, "learning_rate": 3.2053635125437316e-05, "loss": 4.7011, "step": 7601 }, { "epoch": 0.409061558329746, "grad_norm": 2.6972432136535645, "learning_rate": 3.2049580522221126e-05, "loss": 4.2347, "step": 7602 }, { "epoch": 0.409115368058545, "grad_norm": 2.0426127910614014, "learning_rate": 3.204552571754688e-05, "loss": 4.6616, "step": 7603 }, { "epoch": 0.40916917778734396, "grad_norm": 2.1659162044525146, "learning_rate": 3.204147071153045e-05, "loss": 4.3002, "step": 7604 }, { "epoch": 0.40922298751614294, "grad_norm": 1.8562830686569214, "learning_rate": 3.203741550428774e-05, "loss": 4.4062, "step": 7605 }, { "epoch": 0.40927679724494187, "grad_norm": 1.0181934833526611, "learning_rate": 3.2033360095934614e-05, "loss": 4.7691, "step": 7606 }, { "epoch": 0.40933060697374085, "grad_norm": 1.3247967958450317, "learning_rate": 3.202930448658699e-05, "loss": 4.5505, "step": 7607 }, { "epoch": 0.40938441670253983, "grad_norm": 1.1131373643875122, "learning_rate": 3.202524867636073e-05, "loss": 4.6316, "step": 7608 }, { "epoch": 0.40943822643133876, "grad_norm": 1.5755846500396729, "learning_rate": 3.2021192665371765e-05, "loss": 4.8487, "step": 7609 }, { "epoch": 0.40949203616013774, "grad_norm": 1.9772614240646362, "learning_rate": 3.201713645373601e-05, "loss": 4.5821, "step": 7610 }, { "epoch": 0.4095458458889367, "grad_norm": 1.0213196277618408, "learning_rate": 3.2013080041569354e-05, "loss": 4.5902, "step": 7611 }, { "epoch": 0.4095996556177357, "grad_norm": 2.2749860286712646, "learning_rate": 3.200902342898774e-05, "loss": 4.4346, "step": 7612 }, { "epoch": 0.40965346534653463, "grad_norm": 1.894412875175476, "learning_rate": 3.200496661610708e-05, "loss": 4.5031, "step": 7613 }, { "epoch": 0.4097072750753336, "grad_norm": 1.4069416522979736, "learning_rate": 3.200090960304333e-05, "loss": 4.5486, "step": 7614 }, { "epoch": 0.4097610848041326, "grad_norm": 2.624342203140259, "learning_rate": 3.1996852389912414e-05, "loss": 4.2648, "step": 7615 }, { "epoch": 0.4098148945329316, "grad_norm": 2.099907875061035, "learning_rate": 3.199279497683026e-05, "loss": 4.6853, "step": 7616 }, { "epoch": 0.4098687042617305, "grad_norm": 2.5291659832000732, "learning_rate": 3.198873736391285e-05, "loss": 4.1948, "step": 7617 }, { "epoch": 0.4099225139905295, "grad_norm": 1.8024895191192627, "learning_rate": 3.198467955127611e-05, "loss": 4.3454, "step": 7618 }, { "epoch": 0.40997632371932846, "grad_norm": 2.2945098876953125, "learning_rate": 3.198062153903603e-05, "loss": 4.3793, "step": 7619 }, { "epoch": 0.41003013344812744, "grad_norm": 1.6493093967437744, "learning_rate": 3.1976563327308554e-05, "loss": 4.5148, "step": 7620 }, { "epoch": 0.41008394317692637, "grad_norm": 1.9712198972702026, "learning_rate": 3.197250491620965e-05, "loss": 4.841, "step": 7621 }, { "epoch": 0.41013775290572535, "grad_norm": 2.5261828899383545, "learning_rate": 3.1968446305855326e-05, "loss": 4.212, "step": 7622 }, { "epoch": 0.41019156263452433, "grad_norm": 1.8626562356948853, "learning_rate": 3.1964387496361544e-05, "loss": 3.8462, "step": 7623 }, { "epoch": 0.4102453723633233, "grad_norm": 2.308403491973877, "learning_rate": 3.1960328487844306e-05, "loss": 4.2835, "step": 7624 }, { "epoch": 0.41029918209212224, "grad_norm": 1.9323817491531372, "learning_rate": 3.1956269280419594e-05, "loss": 4.6611, "step": 7625 }, { "epoch": 0.4103529918209212, "grad_norm": 1.6688581705093384, "learning_rate": 3.195220987420341e-05, "loss": 4.4537, "step": 7626 }, { "epoch": 0.4104068015497202, "grad_norm": 2.606492519378662, "learning_rate": 3.1948150269311784e-05, "loss": 4.7339, "step": 7627 }, { "epoch": 0.4104606112785192, "grad_norm": 1.5128850936889648, "learning_rate": 3.19440904658607e-05, "loss": 4.7417, "step": 7628 }, { "epoch": 0.4105144210073181, "grad_norm": 2.0245349407196045, "learning_rate": 3.1940030463966184e-05, "loss": 4.1997, "step": 7629 }, { "epoch": 0.4105682307361171, "grad_norm": 2.4779486656188965, "learning_rate": 3.193597026374427e-05, "loss": 4.3514, "step": 7630 }, { "epoch": 0.41062204046491607, "grad_norm": 2.574880838394165, "learning_rate": 3.193190986531098e-05, "loss": 3.8802, "step": 7631 }, { "epoch": 0.410675850193715, "grad_norm": 1.0978803634643555, "learning_rate": 3.1927849268782355e-05, "loss": 4.6276, "step": 7632 }, { "epoch": 0.410729659922514, "grad_norm": 3.0543322563171387, "learning_rate": 3.192378847427443e-05, "loss": 3.782, "step": 7633 }, { "epoch": 0.41078346965131296, "grad_norm": 1.559569001197815, "learning_rate": 3.1919727481903253e-05, "loss": 4.9407, "step": 7634 }, { "epoch": 0.41083727938011194, "grad_norm": 1.7158719301223755, "learning_rate": 3.191566629178488e-05, "loss": 4.4745, "step": 7635 }, { "epoch": 0.41089108910891087, "grad_norm": 1.3377145528793335, "learning_rate": 3.191160490403535e-05, "loss": 4.3986, "step": 7636 }, { "epoch": 0.41094489883770985, "grad_norm": 1.5673960447311401, "learning_rate": 3.190754331877076e-05, "loss": 4.3554, "step": 7637 }, { "epoch": 0.41099870856650883, "grad_norm": 1.643751859664917, "learning_rate": 3.1903481536107154e-05, "loss": 4.8247, "step": 7638 }, { "epoch": 0.4110525182953078, "grad_norm": 2.846083879470825, "learning_rate": 3.1899419556160614e-05, "loss": 3.8865, "step": 7639 }, { "epoch": 0.41110632802410674, "grad_norm": 1.9748716354370117, "learning_rate": 3.189535737904722e-05, "loss": 3.9046, "step": 7640 }, { "epoch": 0.4111601377529057, "grad_norm": 1.150442361831665, "learning_rate": 3.189129500488306e-05, "loss": 4.6541, "step": 7641 }, { "epoch": 0.4112139474817047, "grad_norm": 2.3301913738250732, "learning_rate": 3.1887232433784217e-05, "loss": 3.6988, "step": 7642 }, { "epoch": 0.4112677572105037, "grad_norm": 1.6954039335250854, "learning_rate": 3.1883169665866805e-05, "loss": 4.8591, "step": 7643 }, { "epoch": 0.4113215669393026, "grad_norm": 1.7221224308013916, "learning_rate": 3.187910670124691e-05, "loss": 4.3525, "step": 7644 }, { "epoch": 0.4113753766681016, "grad_norm": 2.279554605484009, "learning_rate": 3.1875043540040655e-05, "loss": 4.0393, "step": 7645 }, { "epoch": 0.41142918639690057, "grad_norm": 2.3681976795196533, "learning_rate": 3.1870980182364146e-05, "loss": 4.0246, "step": 7646 }, { "epoch": 0.41148299612569955, "grad_norm": 3.70290207862854, "learning_rate": 3.18669166283335e-05, "loss": 3.3196, "step": 7647 }, { "epoch": 0.4115368058544985, "grad_norm": 2.8756985664367676, "learning_rate": 3.1862852878064844e-05, "loss": 3.8973, "step": 7648 }, { "epoch": 0.41159061558329746, "grad_norm": 1.3262298107147217, "learning_rate": 3.185878893167432e-05, "loss": 4.196, "step": 7649 }, { "epoch": 0.41164442531209644, "grad_norm": 1.8103866577148438, "learning_rate": 3.185472478927806e-05, "loss": 4.0379, "step": 7650 }, { "epoch": 0.41169823504089537, "grad_norm": 2.3054580688476562, "learning_rate": 3.185066045099219e-05, "loss": 4.2215, "step": 7651 }, { "epoch": 0.41175204476969435, "grad_norm": 2.1360089778900146, "learning_rate": 3.184659591693288e-05, "loss": 4.2941, "step": 7652 }, { "epoch": 0.41180585449849333, "grad_norm": 2.2321743965148926, "learning_rate": 3.184253118721627e-05, "loss": 3.5115, "step": 7653 }, { "epoch": 0.4118596642272923, "grad_norm": 1.409950613975525, "learning_rate": 3.1838466261958516e-05, "loss": 4.5623, "step": 7654 }, { "epoch": 0.41191347395609124, "grad_norm": 2.2700581550598145, "learning_rate": 3.1834401141275796e-05, "loss": 3.9216, "step": 7655 }, { "epoch": 0.4119672836848902, "grad_norm": 2.4970040321350098, "learning_rate": 3.183033582528428e-05, "loss": 3.8262, "step": 7656 }, { "epoch": 0.4120210934136892, "grad_norm": 2.686312437057495, "learning_rate": 3.182627031410013e-05, "loss": 5.0129, "step": 7657 }, { "epoch": 0.4120749031424882, "grad_norm": 2.5569875240325928, "learning_rate": 3.1822204607839536e-05, "loss": 3.5896, "step": 7658 }, { "epoch": 0.4121287128712871, "grad_norm": 2.222010374069214, "learning_rate": 3.1818138706618686e-05, "loss": 4.2936, "step": 7659 }, { "epoch": 0.4121825226000861, "grad_norm": 2.4495909214019775, "learning_rate": 3.1814072610553763e-05, "loss": 4.0988, "step": 7660 }, { "epoch": 0.41223633232888507, "grad_norm": 1.480828881263733, "learning_rate": 3.181000631976098e-05, "loss": 4.7469, "step": 7661 }, { "epoch": 0.41229014205768405, "grad_norm": 2.4904675483703613, "learning_rate": 3.180593983435652e-05, "loss": 4.0407, "step": 7662 }, { "epoch": 0.412343951786483, "grad_norm": 2.546926975250244, "learning_rate": 3.1801873154456625e-05, "loss": 4.2544, "step": 7663 }, { "epoch": 0.41239776151528196, "grad_norm": 1.961453914642334, "learning_rate": 3.1797806280177485e-05, "loss": 4.689, "step": 7664 }, { "epoch": 0.41245157124408094, "grad_norm": 1.8080229759216309, "learning_rate": 3.179373921163532e-05, "loss": 4.3228, "step": 7665 }, { "epoch": 0.4125053809728799, "grad_norm": 2.4062674045562744, "learning_rate": 3.1789671948946365e-05, "loss": 4.2027, "step": 7666 }, { "epoch": 0.41255919070167885, "grad_norm": 2.014411687850952, "learning_rate": 3.178560449222684e-05, "loss": 4.4543, "step": 7667 }, { "epoch": 0.4126130004304778, "grad_norm": 2.2029573917388916, "learning_rate": 3.1781536841593e-05, "loss": 4.3034, "step": 7668 }, { "epoch": 0.4126668101592768, "grad_norm": 2.8119559288024902, "learning_rate": 3.177746899716108e-05, "loss": 3.8294, "step": 7669 }, { "epoch": 0.4127206198880758, "grad_norm": 1.7058075666427612, "learning_rate": 3.177340095904731e-05, "loss": 4.2983, "step": 7670 }, { "epoch": 0.4127744296168747, "grad_norm": 2.0457262992858887, "learning_rate": 3.176933272736797e-05, "loss": 4.3231, "step": 7671 }, { "epoch": 0.4128282393456737, "grad_norm": 1.8393548727035522, "learning_rate": 3.1765264302239306e-05, "loss": 4.3165, "step": 7672 }, { "epoch": 0.4128820490744727, "grad_norm": 1.474108099937439, "learning_rate": 3.176119568377758e-05, "loss": 4.5221, "step": 7673 }, { "epoch": 0.4129358588032716, "grad_norm": 3.1476171016693115, "learning_rate": 3.175712687209908e-05, "loss": 4.6428, "step": 7674 }, { "epoch": 0.4129896685320706, "grad_norm": 1.4530270099639893, "learning_rate": 3.175305786732006e-05, "loss": 4.3602, "step": 7675 }, { "epoch": 0.41304347826086957, "grad_norm": 2.7252140045166016, "learning_rate": 3.174898866955681e-05, "loss": 4.2241, "step": 7676 }, { "epoch": 0.41309728798966855, "grad_norm": 1.397002100944519, "learning_rate": 3.1744919278925605e-05, "loss": 4.5003, "step": 7677 }, { "epoch": 0.4131510977184675, "grad_norm": 2.2336244583129883, "learning_rate": 3.1740849695542765e-05, "loss": 4.2266, "step": 7678 }, { "epoch": 0.41320490744726646, "grad_norm": 2.995375633239746, "learning_rate": 3.173677991952457e-05, "loss": 3.3624, "step": 7679 }, { "epoch": 0.41325871717606544, "grad_norm": 1.7607669830322266, "learning_rate": 3.1732709950987315e-05, "loss": 4.5812, "step": 7680 }, { "epoch": 0.4133125269048644, "grad_norm": 1.795411467552185, "learning_rate": 3.172863979004733e-05, "loss": 4.3319, "step": 7681 }, { "epoch": 0.41336633663366334, "grad_norm": 2.3567962646484375, "learning_rate": 3.172456943682091e-05, "loss": 3.9411, "step": 7682 }, { "epoch": 0.4134201463624623, "grad_norm": 1.8196760416030884, "learning_rate": 3.172049889142438e-05, "loss": 4.0084, "step": 7683 }, { "epoch": 0.4134739560912613, "grad_norm": 2.104854106903076, "learning_rate": 3.171642815397407e-05, "loss": 4.757, "step": 7684 }, { "epoch": 0.4135277658200603, "grad_norm": 4.22448205947876, "learning_rate": 3.171235722458631e-05, "loss": 3.2185, "step": 7685 }, { "epoch": 0.4135815755488592, "grad_norm": 1.2774730920791626, "learning_rate": 3.1708286103377435e-05, "loss": 4.3934, "step": 7686 }, { "epoch": 0.4136353852776582, "grad_norm": 1.396666407585144, "learning_rate": 3.1704214790463796e-05, "loss": 4.5429, "step": 7687 }, { "epoch": 0.4136891950064572, "grad_norm": 1.0477705001831055, "learning_rate": 3.1700143285961714e-05, "loss": 4.6573, "step": 7688 }, { "epoch": 0.41374300473525616, "grad_norm": 2.02142333984375, "learning_rate": 3.169607158998756e-05, "loss": 3.9013, "step": 7689 }, { "epoch": 0.4137968144640551, "grad_norm": 2.2549874782562256, "learning_rate": 3.1691999702657704e-05, "loss": 4.0476, "step": 7690 }, { "epoch": 0.41385062419285407, "grad_norm": 1.7266889810562134, "learning_rate": 3.168792762408849e-05, "loss": 4.0618, "step": 7691 }, { "epoch": 0.41390443392165305, "grad_norm": 2.5068490505218506, "learning_rate": 3.168385535439629e-05, "loss": 4.4644, "step": 7692 }, { "epoch": 0.41395824365045203, "grad_norm": 2.016174077987671, "learning_rate": 3.1679782893697475e-05, "loss": 4.0877, "step": 7693 }, { "epoch": 0.41401205337925095, "grad_norm": 2.0603671073913574, "learning_rate": 3.167571024210844e-05, "loss": 4.4659, "step": 7694 }, { "epoch": 0.41406586310804994, "grad_norm": 1.457231879234314, "learning_rate": 3.1671637399745556e-05, "loss": 4.1273, "step": 7695 }, { "epoch": 0.4141196728368489, "grad_norm": 2.1490046977996826, "learning_rate": 3.166756436672523e-05, "loss": 3.8717, "step": 7696 }, { "epoch": 0.41417348256564784, "grad_norm": 1.6471492052078247, "learning_rate": 3.1663491143163836e-05, "loss": 4.6887, "step": 7697 }, { "epoch": 0.4142272922944468, "grad_norm": 2.7357311248779297, "learning_rate": 3.1659417729177796e-05, "loss": 4.1703, "step": 7698 }, { "epoch": 0.4142811020232458, "grad_norm": 2.2011566162109375, "learning_rate": 3.1655344124883504e-05, "loss": 4.0861, "step": 7699 }, { "epoch": 0.4143349117520448, "grad_norm": 2.192819595336914, "learning_rate": 3.165127033039739e-05, "loss": 4.3634, "step": 7700 }, { "epoch": 0.4143887214808437, "grad_norm": 1.9350720643997192, "learning_rate": 3.164719634583584e-05, "loss": 4.0644, "step": 7701 }, { "epoch": 0.4144425312096427, "grad_norm": 1.1239800453186035, "learning_rate": 3.164312217131531e-05, "loss": 4.6054, "step": 7702 }, { "epoch": 0.4144963409384417, "grad_norm": 1.7458672523498535, "learning_rate": 3.163904780695221e-05, "loss": 3.9947, "step": 7703 }, { "epoch": 0.41455015066724066, "grad_norm": 2.519869089126587, "learning_rate": 3.163497325286299e-05, "loss": 4.4008, "step": 7704 }, { "epoch": 0.4146039603960396, "grad_norm": 2.915044069290161, "learning_rate": 3.163089850916407e-05, "loss": 4.2961, "step": 7705 }, { "epoch": 0.41465777012483857, "grad_norm": 2.392146587371826, "learning_rate": 3.162682357597191e-05, "loss": 4.2263, "step": 7706 }, { "epoch": 0.41471157985363755, "grad_norm": 1.8676457405090332, "learning_rate": 3.162274845340296e-05, "loss": 4.4325, "step": 7707 }, { "epoch": 0.41476538958243653, "grad_norm": 2.236632823944092, "learning_rate": 3.1618673141573665e-05, "loss": 4.4791, "step": 7708 }, { "epoch": 0.41481919931123545, "grad_norm": 1.4849581718444824, "learning_rate": 3.1614597640600493e-05, "loss": 4.4642, "step": 7709 }, { "epoch": 0.41487300904003444, "grad_norm": 1.9785571098327637, "learning_rate": 3.1610521950599926e-05, "loss": 4.4971, "step": 7710 }, { "epoch": 0.4149268187688334, "grad_norm": 1.9958065748214722, "learning_rate": 3.1606446071688405e-05, "loss": 4.4914, "step": 7711 }, { "epoch": 0.4149806284976324, "grad_norm": 1.8538457155227661, "learning_rate": 3.1602370003982436e-05, "loss": 4.3586, "step": 7712 }, { "epoch": 0.4150344382264313, "grad_norm": 2.9349308013916016, "learning_rate": 3.159829374759848e-05, "loss": 3.4364, "step": 7713 }, { "epoch": 0.4150882479552303, "grad_norm": 1.9876506328582764, "learning_rate": 3.159421730265305e-05, "loss": 4.4734, "step": 7714 }, { "epoch": 0.4151420576840293, "grad_norm": 2.7190847396850586, "learning_rate": 3.1590140669262616e-05, "loss": 4.3899, "step": 7715 }, { "epoch": 0.4151958674128282, "grad_norm": 2.3282570838928223, "learning_rate": 3.1586063847543686e-05, "loss": 4.3222, "step": 7716 }, { "epoch": 0.4152496771416272, "grad_norm": 2.39058518409729, "learning_rate": 3.158198683761277e-05, "loss": 4.3267, "step": 7717 }, { "epoch": 0.4153034868704262, "grad_norm": 2.001087188720703, "learning_rate": 3.157790963958637e-05, "loss": 4.4604, "step": 7718 }, { "epoch": 0.41535729659922516, "grad_norm": 2.3821604251861572, "learning_rate": 3.1573832253581004e-05, "loss": 4.6153, "step": 7719 }, { "epoch": 0.4154111063280241, "grad_norm": 2.970623016357422, "learning_rate": 3.15697546797132e-05, "loss": 3.5377, "step": 7720 }, { "epoch": 0.41546491605682306, "grad_norm": 1.6415199041366577, "learning_rate": 3.1565676918099475e-05, "loss": 4.0982, "step": 7721 }, { "epoch": 0.41551872578562205, "grad_norm": 1.5893604755401611, "learning_rate": 3.1561598968856364e-05, "loss": 4.3062, "step": 7722 }, { "epoch": 0.415572535514421, "grad_norm": 1.9614198207855225, "learning_rate": 3.15575208321004e-05, "loss": 4.5232, "step": 7723 }, { "epoch": 0.41562634524321995, "grad_norm": 2.190674066543579, "learning_rate": 3.1553442507948125e-05, "loss": 4.5107, "step": 7724 }, { "epoch": 0.41568015497201893, "grad_norm": 1.402666687965393, "learning_rate": 3.154936399651611e-05, "loss": 4.6679, "step": 7725 }, { "epoch": 0.4157339647008179, "grad_norm": 3.2645881175994873, "learning_rate": 3.1545285297920864e-05, "loss": 4.426, "step": 7726 }, { "epoch": 0.4157877744296169, "grad_norm": 2.243260622024536, "learning_rate": 3.154120641227898e-05, "loss": 3.7379, "step": 7727 }, { "epoch": 0.4158415841584158, "grad_norm": 2.0383317470550537, "learning_rate": 3.153712733970701e-05, "loss": 4.4506, "step": 7728 }, { "epoch": 0.4158953938872148, "grad_norm": 2.5689194202423096, "learning_rate": 3.153304808032152e-05, "loss": 4.1551, "step": 7729 }, { "epoch": 0.4159492036160138, "grad_norm": 2.3823134899139404, "learning_rate": 3.152896863423909e-05, "loss": 4.2916, "step": 7730 }, { "epoch": 0.41600301334481277, "grad_norm": 2.060271739959717, "learning_rate": 3.15248890015763e-05, "loss": 4.5264, "step": 7731 }, { "epoch": 0.4160568230736117, "grad_norm": 1.6176426410675049, "learning_rate": 3.152080918244972e-05, "loss": 4.5152, "step": 7732 }, { "epoch": 0.4161106328024107, "grad_norm": 1.8197345733642578, "learning_rate": 3.151672917697597e-05, "loss": 4.5072, "step": 7733 }, { "epoch": 0.41616444253120966, "grad_norm": 1.3925485610961914, "learning_rate": 3.1512648985271616e-05, "loss": 4.5895, "step": 7734 }, { "epoch": 0.41621825226000864, "grad_norm": 1.6830940246582031, "learning_rate": 3.150856860745327e-05, "loss": 4.0579, "step": 7735 }, { "epoch": 0.41627206198880756, "grad_norm": 2.149829864501953, "learning_rate": 3.150448804363755e-05, "loss": 4.2988, "step": 7736 }, { "epoch": 0.41632587171760654, "grad_norm": 2.532444953918457, "learning_rate": 3.1500407293941046e-05, "loss": 4.4077, "step": 7737 }, { "epoch": 0.4163796814464055, "grad_norm": 1.606649398803711, "learning_rate": 3.149632635848039e-05, "loss": 4.927, "step": 7738 }, { "epoch": 0.41643349117520445, "grad_norm": 1.7919918298721313, "learning_rate": 3.14922452373722e-05, "loss": 4.1788, "step": 7739 }, { "epoch": 0.41648730090400343, "grad_norm": 2.234147071838379, "learning_rate": 3.1488163930733104e-05, "loss": 4.6248, "step": 7740 }, { "epoch": 0.4165411106328024, "grad_norm": 1.4592527151107788, "learning_rate": 3.1484082438679735e-05, "loss": 4.3417, "step": 7741 }, { "epoch": 0.4165949203616014, "grad_norm": 2.0380561351776123, "learning_rate": 3.148000076132873e-05, "loss": 4.6188, "step": 7742 }, { "epoch": 0.4166487300904003, "grad_norm": 2.671133518218994, "learning_rate": 3.147591889879673e-05, "loss": 4.3992, "step": 7743 }, { "epoch": 0.4167025398191993, "grad_norm": 2.271618127822876, "learning_rate": 3.147183685120039e-05, "loss": 3.9633, "step": 7744 }, { "epoch": 0.4167563495479983, "grad_norm": 2.274280309677124, "learning_rate": 3.1467754618656356e-05, "loss": 4.4246, "step": 7745 }, { "epoch": 0.41681015927679727, "grad_norm": 1.8897675275802612, "learning_rate": 3.1463672201281285e-05, "loss": 4.6856, "step": 7746 }, { "epoch": 0.4168639690055962, "grad_norm": 2.0419387817382812, "learning_rate": 3.1459589599191855e-05, "loss": 4.2044, "step": 7747 }, { "epoch": 0.4169177787343952, "grad_norm": 3.0503952503204346, "learning_rate": 3.1455506812504734e-05, "loss": 4.3326, "step": 7748 }, { "epoch": 0.41697158846319415, "grad_norm": 1.1050004959106445, "learning_rate": 3.145142384133658e-05, "loss": 4.5078, "step": 7749 }, { "epoch": 0.41702539819199314, "grad_norm": 1.765629768371582, "learning_rate": 3.144734068580409e-05, "loss": 4.0996, "step": 7750 }, { "epoch": 0.41707920792079206, "grad_norm": 1.3013670444488525, "learning_rate": 3.144325734602394e-05, "loss": 4.4849, "step": 7751 }, { "epoch": 0.41713301764959104, "grad_norm": 1.0194522142410278, "learning_rate": 3.143917382211283e-05, "loss": 4.8121, "step": 7752 }, { "epoch": 0.41718682737839, "grad_norm": 2.9958279132843018, "learning_rate": 3.143509011418746e-05, "loss": 4.2006, "step": 7753 }, { "epoch": 0.417240637107189, "grad_norm": 1.3053646087646484, "learning_rate": 3.143100622236451e-05, "loss": 4.3031, "step": 7754 }, { "epoch": 0.41729444683598793, "grad_norm": 1.9117285013198853, "learning_rate": 3.14269221467607e-05, "loss": 3.9598, "step": 7755 }, { "epoch": 0.4173482565647869, "grad_norm": 1.1492137908935547, "learning_rate": 3.142283788749275e-05, "loss": 4.3814, "step": 7756 }, { "epoch": 0.4174020662935859, "grad_norm": 0.9362396597862244, "learning_rate": 3.1418753444677365e-05, "loss": 4.5648, "step": 7757 }, { "epoch": 0.4174558760223848, "grad_norm": 3.027519464492798, "learning_rate": 3.141466881843127e-05, "loss": 4.0358, "step": 7758 }, { "epoch": 0.4175096857511838, "grad_norm": 1.6452516317367554, "learning_rate": 3.14105840088712e-05, "loss": 4.0029, "step": 7759 }, { "epoch": 0.4175634954799828, "grad_norm": 3.0844526290893555, "learning_rate": 3.140649901611387e-05, "loss": 3.6342, "step": 7760 }, { "epoch": 0.41761730520878176, "grad_norm": 2.4514291286468506, "learning_rate": 3.1402413840276035e-05, "loss": 4.1159, "step": 7761 }, { "epoch": 0.4176711149375807, "grad_norm": 2.24812912940979, "learning_rate": 3.139832848147443e-05, "loss": 4.4811, "step": 7762 }, { "epoch": 0.41772492466637967, "grad_norm": 1.9201174974441528, "learning_rate": 3.139424293982581e-05, "loss": 4.249, "step": 7763 }, { "epoch": 0.41777873439517865, "grad_norm": 2.130183458328247, "learning_rate": 3.139015721544693e-05, "loss": 4.0208, "step": 7764 }, { "epoch": 0.41783254412397763, "grad_norm": 2.0569612979888916, "learning_rate": 3.138607130845454e-05, "loss": 4.4423, "step": 7765 }, { "epoch": 0.41788635385277656, "grad_norm": 3.1709580421447754, "learning_rate": 3.13819852189654e-05, "loss": 4.4088, "step": 7766 }, { "epoch": 0.41794016358157554, "grad_norm": 1.8134958744049072, "learning_rate": 3.1377898947096294e-05, "loss": 4.4399, "step": 7767 }, { "epoch": 0.4179939733103745, "grad_norm": 2.187471628189087, "learning_rate": 3.1373812492963994e-05, "loss": 4.2158, "step": 7768 }, { "epoch": 0.4180477830391735, "grad_norm": 2.914700508117676, "learning_rate": 3.136972585668528e-05, "loss": 4.235, "step": 7769 }, { "epoch": 0.41810159276797243, "grad_norm": 1.6032599210739136, "learning_rate": 3.136563903837692e-05, "loss": 4.2484, "step": 7770 }, { "epoch": 0.4181554024967714, "grad_norm": 2.0645182132720947, "learning_rate": 3.136155203815573e-05, "loss": 4.558, "step": 7771 }, { "epoch": 0.4182092122255704, "grad_norm": 1.7477182149887085, "learning_rate": 3.135746485613849e-05, "loss": 4.6181, "step": 7772 }, { "epoch": 0.4182630219543694, "grad_norm": 2.4123282432556152, "learning_rate": 3.1353377492442e-05, "loss": 4.3698, "step": 7773 }, { "epoch": 0.4183168316831683, "grad_norm": 2.3930788040161133, "learning_rate": 3.134928994718307e-05, "loss": 3.7753, "step": 7774 }, { "epoch": 0.4183706414119673, "grad_norm": 2.242370128631592, "learning_rate": 3.134520222047852e-05, "loss": 4.2463, "step": 7775 }, { "epoch": 0.41842445114076626, "grad_norm": 2.6779682636260986, "learning_rate": 3.1341114312445154e-05, "loss": 3.6645, "step": 7776 }, { "epoch": 0.41847826086956524, "grad_norm": 1.7259889841079712, "learning_rate": 3.133702622319979e-05, "loss": 4.2116, "step": 7777 }, { "epoch": 0.41853207059836417, "grad_norm": 1.7881470918655396, "learning_rate": 3.133293795285926e-05, "loss": 4.6119, "step": 7778 }, { "epoch": 0.41858588032716315, "grad_norm": 1.2301260232925415, "learning_rate": 3.132884950154041e-05, "loss": 4.3307, "step": 7779 }, { "epoch": 0.41863969005596213, "grad_norm": 1.6851160526275635, "learning_rate": 3.132476086936005e-05, "loss": 4.3706, "step": 7780 }, { "epoch": 0.41869349978476106, "grad_norm": 1.5987253189086914, "learning_rate": 3.1320672056435044e-05, "loss": 4.3807, "step": 7781 }, { "epoch": 0.41874730951356004, "grad_norm": 1.887136459350586, "learning_rate": 3.131658306288223e-05, "loss": 4.444, "step": 7782 }, { "epoch": 0.418801119242359, "grad_norm": 2.3364806175231934, "learning_rate": 3.1312493888818454e-05, "loss": 4.5633, "step": 7783 }, { "epoch": 0.418854928971158, "grad_norm": 1.9990622997283936, "learning_rate": 3.130840453436059e-05, "loss": 4.3238, "step": 7784 }, { "epoch": 0.41890873869995693, "grad_norm": 2.138409376144409, "learning_rate": 3.130431499962549e-05, "loss": 3.9086, "step": 7785 }, { "epoch": 0.4189625484287559, "grad_norm": 1.20184326171875, "learning_rate": 3.130022528473002e-05, "loss": 4.3616, "step": 7786 }, { "epoch": 0.4190163581575549, "grad_norm": 0.9200431704521179, "learning_rate": 3.1296135389791067e-05, "loss": 4.7392, "step": 7787 }, { "epoch": 0.4190701678863539, "grad_norm": 2.4434115886688232, "learning_rate": 3.129204531492549e-05, "loss": 4.1415, "step": 7788 }, { "epoch": 0.4191239776151528, "grad_norm": 1.486417293548584, "learning_rate": 3.1287955060250185e-05, "loss": 4.3703, "step": 7789 }, { "epoch": 0.4191777873439518, "grad_norm": 1.8860217332839966, "learning_rate": 3.1283864625882045e-05, "loss": 4.8202, "step": 7790 }, { "epoch": 0.41923159707275076, "grad_norm": 3.0183303356170654, "learning_rate": 3.1279774011937934e-05, "loss": 3.8337, "step": 7791 }, { "epoch": 0.41928540680154974, "grad_norm": 1.2665129899978638, "learning_rate": 3.127568321853479e-05, "loss": 4.8135, "step": 7792 }, { "epoch": 0.41933921653034867, "grad_norm": 1.9263660907745361, "learning_rate": 3.127159224578949e-05, "loss": 4.3905, "step": 7793 }, { "epoch": 0.41939302625914765, "grad_norm": 2.629556894302368, "learning_rate": 3.126750109381896e-05, "loss": 3.7465, "step": 7794 }, { "epoch": 0.41944683598794663, "grad_norm": 1.1821181774139404, "learning_rate": 3.1263409762740105e-05, "loss": 4.6039, "step": 7795 }, { "epoch": 0.4195006457167456, "grad_norm": 2.5377843379974365, "learning_rate": 3.125931825266984e-05, "loss": 3.4541, "step": 7796 }, { "epoch": 0.41955445544554454, "grad_norm": 2.8079421520233154, "learning_rate": 3.1255226563725095e-05, "loss": 4.0125, "step": 7797 }, { "epoch": 0.4196082651743435, "grad_norm": 1.910062313079834, "learning_rate": 3.1251134696022805e-05, "loss": 4.2879, "step": 7798 }, { "epoch": 0.4196620749031425, "grad_norm": 2.501386880874634, "learning_rate": 3.12470426496799e-05, "loss": 4.1202, "step": 7799 }, { "epoch": 0.4197158846319415, "grad_norm": 1.5562608242034912, "learning_rate": 3.124295042481331e-05, "loss": 4.8361, "step": 7800 }, { "epoch": 0.4197696943607404, "grad_norm": 1.2543140649795532, "learning_rate": 3.123885802153999e-05, "loss": 4.6293, "step": 7801 }, { "epoch": 0.4198235040895394, "grad_norm": 1.9111814498901367, "learning_rate": 3.12347654399769e-05, "loss": 4.3511, "step": 7802 }, { "epoch": 0.41987731381833837, "grad_norm": 2.4205987453460693, "learning_rate": 3.1230672680240975e-05, "loss": 3.6057, "step": 7803 }, { "epoch": 0.4199311235471373, "grad_norm": 3.012753486633301, "learning_rate": 3.122657974244918e-05, "loss": 4.3025, "step": 7804 }, { "epoch": 0.4199849332759363, "grad_norm": 1.6105083227157593, "learning_rate": 3.1222486626718495e-05, "loss": 4.8319, "step": 7805 }, { "epoch": 0.42003874300473526, "grad_norm": 1.4734090566635132, "learning_rate": 3.121839333316586e-05, "loss": 4.6931, "step": 7806 }, { "epoch": 0.42009255273353424, "grad_norm": 1.8096553087234497, "learning_rate": 3.121429986190828e-05, "loss": 4.1935, "step": 7807 }, { "epoch": 0.42014636246233317, "grad_norm": 1.795575499534607, "learning_rate": 3.121020621306273e-05, "loss": 4.3602, "step": 7808 }, { "epoch": 0.42020017219113215, "grad_norm": 1.909574031829834, "learning_rate": 3.120611238674619e-05, "loss": 4.5882, "step": 7809 }, { "epoch": 0.42025398191993113, "grad_norm": 1.7736455202102661, "learning_rate": 3.1202018383075644e-05, "loss": 4.6312, "step": 7810 }, { "epoch": 0.4203077916487301, "grad_norm": 2.4583606719970703, "learning_rate": 3.119792420216809e-05, "loss": 4.2832, "step": 7811 }, { "epoch": 0.42036160137752904, "grad_norm": 1.4333796501159668, "learning_rate": 3.119382984414054e-05, "loss": 4.4219, "step": 7812 }, { "epoch": 0.420415411106328, "grad_norm": 3.8581676483154297, "learning_rate": 3.118973530910999e-05, "loss": 2.9429, "step": 7813 }, { "epoch": 0.420469220835127, "grad_norm": 1.4445103406906128, "learning_rate": 3.118564059719345e-05, "loss": 4.4242, "step": 7814 }, { "epoch": 0.420523030563926, "grad_norm": 1.7554525136947632, "learning_rate": 3.118154570850794e-05, "loss": 4.4877, "step": 7815 }, { "epoch": 0.4205768402927249, "grad_norm": 1.7673590183258057, "learning_rate": 3.117745064317049e-05, "loss": 4.4732, "step": 7816 }, { "epoch": 0.4206306500215239, "grad_norm": 1.7335103750228882, "learning_rate": 3.117335540129811e-05, "loss": 4.8323, "step": 7817 }, { "epoch": 0.42068445975032287, "grad_norm": 2.8396048545837402, "learning_rate": 3.116925998300783e-05, "loss": 4.384, "step": 7818 }, { "epoch": 0.42073826947912185, "grad_norm": 1.3810120820999146, "learning_rate": 3.1165164388416695e-05, "loss": 4.5813, "step": 7819 }, { "epoch": 0.4207920792079208, "grad_norm": 2.452906370162964, "learning_rate": 3.1161068617641756e-05, "loss": 4.2027, "step": 7820 }, { "epoch": 0.42084588893671976, "grad_norm": 1.7091572284698486, "learning_rate": 3.115697267080004e-05, "loss": 4.2552, "step": 7821 }, { "epoch": 0.42089969866551874, "grad_norm": 1.959160327911377, "learning_rate": 3.1152876548008605e-05, "loss": 4.1926, "step": 7822 }, { "epoch": 0.42095350839431767, "grad_norm": 1.428297519683838, "learning_rate": 3.11487802493845e-05, "loss": 4.5941, "step": 7823 }, { "epoch": 0.42100731812311665, "grad_norm": 1.3718883991241455, "learning_rate": 3.11446837750448e-05, "loss": 4.6973, "step": 7824 }, { "epoch": 0.42106112785191563, "grad_norm": 2.609700918197632, "learning_rate": 3.1140587125106565e-05, "loss": 3.84, "step": 7825 }, { "epoch": 0.4211149375807146, "grad_norm": 1.348023772239685, "learning_rate": 3.113649029968687e-05, "loss": 4.6164, "step": 7826 }, { "epoch": 0.42116874730951354, "grad_norm": 3.173771381378174, "learning_rate": 3.113239329890278e-05, "loss": 3.7978, "step": 7827 }, { "epoch": 0.4212225570383125, "grad_norm": 1.3038519620895386, "learning_rate": 3.11282961228714e-05, "loss": 4.6175, "step": 7828 }, { "epoch": 0.4212763667671115, "grad_norm": 2.387678384780884, "learning_rate": 3.112419877170978e-05, "loss": 4.0784, "step": 7829 }, { "epoch": 0.4213301764959105, "grad_norm": 3.046877861022949, "learning_rate": 3.112010124553504e-05, "loss": 4.7119, "step": 7830 }, { "epoch": 0.4213839862247094, "grad_norm": 1.2700825929641724, "learning_rate": 3.111600354446427e-05, "loss": 4.462, "step": 7831 }, { "epoch": 0.4214377959535084, "grad_norm": 1.815476894378662, "learning_rate": 3.111190566861457e-05, "loss": 4.3929, "step": 7832 }, { "epoch": 0.42149160568230737, "grad_norm": 1.9180030822753906, "learning_rate": 3.1107807618103035e-05, "loss": 4.7741, "step": 7833 }, { "epoch": 0.42154541541110635, "grad_norm": 2.740043878555298, "learning_rate": 3.110370939304679e-05, "loss": 4.2677, "step": 7834 }, { "epoch": 0.4215992251399053, "grad_norm": 1.7809633016586304, "learning_rate": 3.109961099356295e-05, "loss": 4.5261, "step": 7835 }, { "epoch": 0.42165303486870426, "grad_norm": 1.0484485626220703, "learning_rate": 3.109551241976864e-05, "loss": 4.4325, "step": 7836 }, { "epoch": 0.42170684459750324, "grad_norm": 2.4622714519500732, "learning_rate": 3.1091413671780964e-05, "loss": 3.7265, "step": 7837 }, { "epoch": 0.4217606543263022, "grad_norm": 2.6692912578582764, "learning_rate": 3.108731474971708e-05, "loss": 3.6868, "step": 7838 }, { "epoch": 0.42181446405510115, "grad_norm": 2.9990193843841553, "learning_rate": 3.1083215653694115e-05, "loss": 4.0789, "step": 7839 }, { "epoch": 0.4218682737839001, "grad_norm": 2.741379976272583, "learning_rate": 3.107911638382921e-05, "loss": 4.1621, "step": 7840 }, { "epoch": 0.4219220835126991, "grad_norm": 2.117125988006592, "learning_rate": 3.1075016940239504e-05, "loss": 3.8976, "step": 7841 }, { "epoch": 0.4219758932414981, "grad_norm": 1.45473313331604, "learning_rate": 3.107091732304215e-05, "loss": 4.5532, "step": 7842 }, { "epoch": 0.422029702970297, "grad_norm": 2.5152111053466797, "learning_rate": 3.106681753235432e-05, "loss": 3.9457, "step": 7843 }, { "epoch": 0.422083512699096, "grad_norm": 1.7246114015579224, "learning_rate": 3.106271756829315e-05, "loss": 4.4005, "step": 7844 }, { "epoch": 0.422137322427895, "grad_norm": 2.3905081748962402, "learning_rate": 3.1058617430975826e-05, "loss": 4.5327, "step": 7845 }, { "epoch": 0.4221911321566939, "grad_norm": 1.3242824077606201, "learning_rate": 3.105451712051951e-05, "loss": 4.3658, "step": 7846 }, { "epoch": 0.4222449418854929, "grad_norm": 2.6871535778045654, "learning_rate": 3.105041663704138e-05, "loss": 3.8331, "step": 7847 }, { "epoch": 0.42229875161429187, "grad_norm": 1.0874693393707275, "learning_rate": 3.104631598065862e-05, "loss": 4.3736, "step": 7848 }, { "epoch": 0.42235256134309085, "grad_norm": 2.943402051925659, "learning_rate": 3.104221515148841e-05, "loss": 3.7998, "step": 7849 }, { "epoch": 0.4224063710718898, "grad_norm": 3.0376341342926025, "learning_rate": 3.103811414964793e-05, "loss": 3.9743, "step": 7850 }, { "epoch": 0.42246018080068876, "grad_norm": 1.8772906064987183, "learning_rate": 3.1034012975254404e-05, "loss": 4.1769, "step": 7851 }, { "epoch": 0.42251399052948774, "grad_norm": 1.5198845863342285, "learning_rate": 3.102991162842501e-05, "loss": 4.5807, "step": 7852 }, { "epoch": 0.4225678002582867, "grad_norm": 2.9412758350372314, "learning_rate": 3.102581010927696e-05, "loss": 4.3015, "step": 7853 }, { "epoch": 0.42262160998708564, "grad_norm": 1.4967396259307861, "learning_rate": 3.102170841792746e-05, "loss": 4.7282, "step": 7854 }, { "epoch": 0.4226754197158846, "grad_norm": 2.2101619243621826, "learning_rate": 3.101760655449374e-05, "loss": 4.3191, "step": 7855 }, { "epoch": 0.4227292294446836, "grad_norm": 1.6201387643814087, "learning_rate": 3.101350451909301e-05, "loss": 4.8059, "step": 7856 }, { "epoch": 0.4227830391734826, "grad_norm": 1.9833228588104248, "learning_rate": 3.100940231184249e-05, "loss": 4.2945, "step": 7857 }, { "epoch": 0.4228368489022815, "grad_norm": 3.193904161453247, "learning_rate": 3.100529993285942e-05, "loss": 4.0222, "step": 7858 }, { "epoch": 0.4228906586310805, "grad_norm": 1.6238645315170288, "learning_rate": 3.1001197382261025e-05, "loss": 4.3059, "step": 7859 }, { "epoch": 0.4229444683598795, "grad_norm": 2.501298427581787, "learning_rate": 3.099709466016455e-05, "loss": 4.1938, "step": 7860 }, { "epoch": 0.42299827808867846, "grad_norm": 1.3931423425674438, "learning_rate": 3.099299176668724e-05, "loss": 4.6572, "step": 7861 }, { "epoch": 0.4230520878174774, "grad_norm": 1.610975980758667, "learning_rate": 3.098888870194635e-05, "loss": 4.3374, "step": 7862 }, { "epoch": 0.42310589754627637, "grad_norm": 1.6549431085586548, "learning_rate": 3.0984785466059124e-05, "loss": 4.4613, "step": 7863 }, { "epoch": 0.42315970727507535, "grad_norm": 1.4712074995040894, "learning_rate": 3.098068205914283e-05, "loss": 4.4125, "step": 7864 }, { "epoch": 0.4232135170038743, "grad_norm": 1.573573112487793, "learning_rate": 3.0976578481314726e-05, "loss": 3.9803, "step": 7865 }, { "epoch": 0.42326732673267325, "grad_norm": 1.7191050052642822, "learning_rate": 3.097247473269209e-05, "loss": 4.3829, "step": 7866 }, { "epoch": 0.42332113646147224, "grad_norm": 2.1970064640045166, "learning_rate": 3.0968370813392184e-05, "loss": 4.0058, "step": 7867 }, { "epoch": 0.4233749461902712, "grad_norm": 1.891951084136963, "learning_rate": 3.0964266723532296e-05, "loss": 4.5293, "step": 7868 }, { "epoch": 0.42342875591907014, "grad_norm": 1.386512279510498, "learning_rate": 3.09601624632297e-05, "loss": 4.5152, "step": 7869 }, { "epoch": 0.4234825656478691, "grad_norm": 1.8777682781219482, "learning_rate": 3.09560580326017e-05, "loss": 4.3367, "step": 7870 }, { "epoch": 0.4235363753766681, "grad_norm": 1.0836637020111084, "learning_rate": 3.095195343176558e-05, "loss": 4.7134, "step": 7871 }, { "epoch": 0.4235901851054671, "grad_norm": 1.4197081327438354, "learning_rate": 3.094784866083864e-05, "loss": 4.299, "step": 7872 }, { "epoch": 0.423643994834266, "grad_norm": 3.0380585193634033, "learning_rate": 3.094374371993817e-05, "loss": 4.339, "step": 7873 }, { "epoch": 0.423697804563065, "grad_norm": 2.3852994441986084, "learning_rate": 3.0939638609181517e-05, "loss": 4.2681, "step": 7874 }, { "epoch": 0.423751614291864, "grad_norm": 1.2469892501831055, "learning_rate": 3.093553332868595e-05, "loss": 4.5958, "step": 7875 }, { "epoch": 0.42380542402066296, "grad_norm": 1.2611078023910522, "learning_rate": 3.093142787856881e-05, "loss": 4.2865, "step": 7876 }, { "epoch": 0.4238592337494619, "grad_norm": 1.1936911344528198, "learning_rate": 3.092732225894741e-05, "loss": 4.4797, "step": 7877 }, { "epoch": 0.42391304347826086, "grad_norm": 1.4321599006652832, "learning_rate": 3.092321646993909e-05, "loss": 4.043, "step": 7878 }, { "epoch": 0.42396685320705985, "grad_norm": 2.207191228866577, "learning_rate": 3.091911051166117e-05, "loss": 4.1292, "step": 7879 }, { "epoch": 0.4240206629358588, "grad_norm": 1.8348652124404907, "learning_rate": 3.091500438423099e-05, "loss": 4.2143, "step": 7880 }, { "epoch": 0.42407447266465775, "grad_norm": 1.4659273624420166, "learning_rate": 3.09108980877659e-05, "loss": 4.6225, "step": 7881 }, { "epoch": 0.42412828239345673, "grad_norm": 2.5801515579223633, "learning_rate": 3.0906791622383244e-05, "loss": 3.8531, "step": 7882 }, { "epoch": 0.4241820921222557, "grad_norm": 2.604902982711792, "learning_rate": 3.090268498820036e-05, "loss": 4.1638, "step": 7883 }, { "epoch": 0.4242359018510547, "grad_norm": 1.8010023832321167, "learning_rate": 3.0898578185334626e-05, "loss": 4.4418, "step": 7884 }, { "epoch": 0.4242897115798536, "grad_norm": 2.1424221992492676, "learning_rate": 3.0894471213903386e-05, "loss": 4.119, "step": 7885 }, { "epoch": 0.4243435213086526, "grad_norm": 1.24790358543396, "learning_rate": 3.089036407402401e-05, "loss": 4.4877, "step": 7886 }, { "epoch": 0.4243973310374516, "grad_norm": 3.05612850189209, "learning_rate": 3.088625676581388e-05, "loss": 4.669, "step": 7887 }, { "epoch": 0.4244511407662505, "grad_norm": 1.3041813373565674, "learning_rate": 3.0882149289390366e-05, "loss": 4.4292, "step": 7888 }, { "epoch": 0.4245049504950495, "grad_norm": 2.63228702545166, "learning_rate": 3.0878041644870845e-05, "loss": 4.5785, "step": 7889 }, { "epoch": 0.4245587602238485, "grad_norm": 1.3876127004623413, "learning_rate": 3.08739338323727e-05, "loss": 4.6351, "step": 7890 }, { "epoch": 0.42461256995264746, "grad_norm": 2.2794485092163086, "learning_rate": 3.086982585201332e-05, "loss": 4.6138, "step": 7891 }, { "epoch": 0.4246663796814464, "grad_norm": 2.7715487480163574, "learning_rate": 3.086571770391011e-05, "loss": 4.418, "step": 7892 }, { "epoch": 0.42472018941024536, "grad_norm": 2.0032501220703125, "learning_rate": 3.086160938818047e-05, "loss": 4.3535, "step": 7893 }, { "epoch": 0.42477399913904434, "grad_norm": 2.0459303855895996, "learning_rate": 3.0857500904941785e-05, "loss": 4.1799, "step": 7894 }, { "epoch": 0.4248278088678433, "grad_norm": 2.020432472229004, "learning_rate": 3.0853392254311495e-05, "loss": 4.4614, "step": 7895 }, { "epoch": 0.42488161859664225, "grad_norm": 1.470392107963562, "learning_rate": 3.0849283436407e-05, "loss": 4.5774, "step": 7896 }, { "epoch": 0.42493542832544123, "grad_norm": 1.640518307685852, "learning_rate": 3.0845174451345703e-05, "loss": 4.3844, "step": 7897 }, { "epoch": 0.4249892380542402, "grad_norm": 2.572998046875, "learning_rate": 3.084106529924505e-05, "loss": 4.2198, "step": 7898 }, { "epoch": 0.4250430477830392, "grad_norm": 1.6737580299377441, "learning_rate": 3.0836955980222454e-05, "loss": 4.5555, "step": 7899 }, { "epoch": 0.4250968575118381, "grad_norm": 3.720938205718994, "learning_rate": 3.0832846494395364e-05, "loss": 3.0536, "step": 7900 }, { "epoch": 0.4251506672406371, "grad_norm": 1.6451514959335327, "learning_rate": 3.08287368418812e-05, "loss": 4.4512, "step": 7901 }, { "epoch": 0.4252044769694361, "grad_norm": 1.0266691446304321, "learning_rate": 3.082462702279743e-05, "loss": 4.4328, "step": 7902 }, { "epoch": 0.42525828669823507, "grad_norm": 1.6157374382019043, "learning_rate": 3.0820517037261475e-05, "loss": 4.1802, "step": 7903 }, { "epoch": 0.425312096427034, "grad_norm": 1.316183090209961, "learning_rate": 3.081640688539079e-05, "loss": 4.4002, "step": 7904 }, { "epoch": 0.425365906155833, "grad_norm": 2.2251079082489014, "learning_rate": 3.081229656730286e-05, "loss": 4.0569, "step": 7905 }, { "epoch": 0.42541971588463195, "grad_norm": 1.402490496635437, "learning_rate": 3.080818608311512e-05, "loss": 4.6909, "step": 7906 }, { "epoch": 0.4254735256134309, "grad_norm": 2.666658639907837, "learning_rate": 3.080407543294504e-05, "loss": 3.8796, "step": 7907 }, { "epoch": 0.42552733534222986, "grad_norm": 2.3205244541168213, "learning_rate": 3.0799964616910106e-05, "loss": 4.3602, "step": 7908 }, { "epoch": 0.42558114507102884, "grad_norm": 2.234452486038208, "learning_rate": 3.0795853635127766e-05, "loss": 4.3703, "step": 7909 }, { "epoch": 0.4256349547998278, "grad_norm": 2.3473215103149414, "learning_rate": 3.0791742487715534e-05, "loss": 3.8421, "step": 7910 }, { "epoch": 0.42568876452862675, "grad_norm": 1.8520188331604004, "learning_rate": 3.078763117479087e-05, "loss": 4.2791, "step": 7911 }, { "epoch": 0.42574257425742573, "grad_norm": 1.3917419910430908, "learning_rate": 3.0783519696471275e-05, "loss": 4.3061, "step": 7912 }, { "epoch": 0.4257963839862247, "grad_norm": 2.322824001312256, "learning_rate": 3.077940805287425e-05, "loss": 3.5121, "step": 7913 }, { "epoch": 0.4258501937150237, "grad_norm": 1.938993215560913, "learning_rate": 3.077529624411727e-05, "loss": 4.3805, "step": 7914 }, { "epoch": 0.4259040034438226, "grad_norm": 2.523768186569214, "learning_rate": 3.077118427031788e-05, "loss": 3.4987, "step": 7915 }, { "epoch": 0.4259578131726216, "grad_norm": 1.6616575717926025, "learning_rate": 3.076707213159356e-05, "loss": 4.7174, "step": 7916 }, { "epoch": 0.4260116229014206, "grad_norm": 1.6573779582977295, "learning_rate": 3.076295982806181e-05, "loss": 4.1711, "step": 7917 }, { "epoch": 0.42606543263021956, "grad_norm": 2.1328814029693604, "learning_rate": 3.075884735984019e-05, "loss": 4.0795, "step": 7918 }, { "epoch": 0.4261192423590185, "grad_norm": 1.7754944562911987, "learning_rate": 3.0754734727046195e-05, "loss": 4.2325, "step": 7919 }, { "epoch": 0.42617305208781747, "grad_norm": 3.498116970062256, "learning_rate": 3.0750621929797364e-05, "loss": 3.438, "step": 7920 }, { "epoch": 0.42622686181661645, "grad_norm": 2.187920570373535, "learning_rate": 3.0746508968211225e-05, "loss": 3.5387, "step": 7921 }, { "epoch": 0.42628067154541543, "grad_norm": 2.508326292037964, "learning_rate": 3.074239584240531e-05, "loss": 3.8998, "step": 7922 }, { "epoch": 0.42633448127421436, "grad_norm": 1.022263765335083, "learning_rate": 3.073828255249717e-05, "loss": 4.5997, "step": 7923 }, { "epoch": 0.42638829100301334, "grad_norm": 1.320311188697815, "learning_rate": 3.0734169098604355e-05, "loss": 4.2948, "step": 7924 }, { "epoch": 0.4264421007318123, "grad_norm": 2.500183582305908, "learning_rate": 3.07300554808444e-05, "loss": 4.2754, "step": 7925 }, { "epoch": 0.4264959104606113, "grad_norm": 2.705739974975586, "learning_rate": 3.072594169933487e-05, "loss": 4.1851, "step": 7926 }, { "epoch": 0.42654972018941023, "grad_norm": 1.443051815032959, "learning_rate": 3.072182775419335e-05, "loss": 4.0941, "step": 7927 }, { "epoch": 0.4266035299182092, "grad_norm": 1.3585203886032104, "learning_rate": 3.071771364553736e-05, "loss": 4.6365, "step": 7928 }, { "epoch": 0.4266573396470082, "grad_norm": 2.162348508834839, "learning_rate": 3.0713599373484495e-05, "loss": 4.3625, "step": 7929 }, { "epoch": 0.4267111493758071, "grad_norm": 3.050870656967163, "learning_rate": 3.070948493815233e-05, "loss": 3.7668, "step": 7930 }, { "epoch": 0.4267649591046061, "grad_norm": 2.136667251586914, "learning_rate": 3.0705370339658454e-05, "loss": 4.1963, "step": 7931 }, { "epoch": 0.4268187688334051, "grad_norm": 3.030428409576416, "learning_rate": 3.070125557812042e-05, "loss": 3.8953, "step": 7932 }, { "epoch": 0.42687257856220406, "grad_norm": 1.4864076375961304, "learning_rate": 3.069714065365585e-05, "loss": 4.2333, "step": 7933 }, { "epoch": 0.426926388291003, "grad_norm": 2.366347074508667, "learning_rate": 3.0693025566382316e-05, "loss": 4.3607, "step": 7934 }, { "epoch": 0.42698019801980197, "grad_norm": 1.9142110347747803, "learning_rate": 3.068891031641743e-05, "loss": 4.3131, "step": 7935 }, { "epoch": 0.42703400774860095, "grad_norm": 2.4505324363708496, "learning_rate": 3.0684794903878783e-05, "loss": 4.2159, "step": 7936 }, { "epoch": 0.42708781747739993, "grad_norm": 2.3494343757629395, "learning_rate": 3.0680679328883996e-05, "loss": 4.4128, "step": 7937 }, { "epoch": 0.42714162720619886, "grad_norm": 1.1200917959213257, "learning_rate": 3.067656359155066e-05, "loss": 4.0488, "step": 7938 }, { "epoch": 0.42719543693499784, "grad_norm": 3.115509033203125, "learning_rate": 3.067244769199642e-05, "loss": 4.0363, "step": 7939 }, { "epoch": 0.4272492466637968, "grad_norm": 3.2745397090911865, "learning_rate": 3.0668331630338864e-05, "loss": 4.3273, "step": 7940 }, { "epoch": 0.4273030563925958, "grad_norm": 1.625555157661438, "learning_rate": 3.066421540669565e-05, "loss": 4.5339, "step": 7941 }, { "epoch": 0.42735686612139473, "grad_norm": 1.5151548385620117, "learning_rate": 3.066009902118439e-05, "loss": 4.1868, "step": 7942 }, { "epoch": 0.4274106758501937, "grad_norm": 2.2523679733276367, "learning_rate": 3.065598247392273e-05, "loss": 3.8842, "step": 7943 }, { "epoch": 0.4274644855789927, "grad_norm": 2.8452131748199463, "learning_rate": 3.06518657650283e-05, "loss": 3.5719, "step": 7944 }, { "epoch": 0.4275182953077917, "grad_norm": 3.323526620864868, "learning_rate": 3.0647748894618736e-05, "loss": 3.7089, "step": 7945 }, { "epoch": 0.4275721050365906, "grad_norm": 1.989214301109314, "learning_rate": 3.064363186281171e-05, "loss": 4.153, "step": 7946 }, { "epoch": 0.4276259147653896, "grad_norm": 1.602710485458374, "learning_rate": 3.063951466972487e-05, "loss": 4.3889, "step": 7947 }, { "epoch": 0.42767972449418856, "grad_norm": 2.289893627166748, "learning_rate": 3.063539731547586e-05, "loss": 3.8568, "step": 7948 }, { "epoch": 0.42773353422298754, "grad_norm": 2.316962718963623, "learning_rate": 3.063127980018236e-05, "loss": 4.7192, "step": 7949 }, { "epoch": 0.42778734395178647, "grad_norm": 1.8850358724594116, "learning_rate": 3.0627162123962025e-05, "loss": 4.7733, "step": 7950 }, { "epoch": 0.42784115368058545, "grad_norm": 1.306546688079834, "learning_rate": 3.0623044286932535e-05, "loss": 4.7268, "step": 7951 }, { "epoch": 0.42789496340938443, "grad_norm": 1.8783354759216309, "learning_rate": 3.061892628921156e-05, "loss": 4.5122, "step": 7952 }, { "epoch": 0.42794877313818336, "grad_norm": 1.7927982807159424, "learning_rate": 3.061480813091678e-05, "loss": 4.4777, "step": 7953 }, { "epoch": 0.42800258286698234, "grad_norm": 1.9648815393447876, "learning_rate": 3.06106898121659e-05, "loss": 4.0411, "step": 7954 }, { "epoch": 0.4280563925957813, "grad_norm": 2.903308629989624, "learning_rate": 3.0606571333076584e-05, "loss": 3.9678, "step": 7955 }, { "epoch": 0.4281102023245803, "grad_norm": 1.8446853160858154, "learning_rate": 3.060245269376654e-05, "loss": 4.5493, "step": 7956 }, { "epoch": 0.42816401205337923, "grad_norm": 2.2017838954925537, "learning_rate": 3.059833389435347e-05, "loss": 4.3889, "step": 7957 }, { "epoch": 0.4282178217821782, "grad_norm": 1.5104621648788452, "learning_rate": 3.059421493495508e-05, "loss": 4.4417, "step": 7958 }, { "epoch": 0.4282716315109772, "grad_norm": 3.340968370437622, "learning_rate": 3.0590095815689066e-05, "loss": 3.2059, "step": 7959 }, { "epoch": 0.4283254412397762, "grad_norm": 1.9590568542480469, "learning_rate": 3.058597653667315e-05, "loss": 4.1751, "step": 7960 }, { "epoch": 0.4283792509685751, "grad_norm": 2.36578369140625, "learning_rate": 3.0581857098025044e-05, "loss": 3.9635, "step": 7961 }, { "epoch": 0.4284330606973741, "grad_norm": 3.636460542678833, "learning_rate": 3.057773749986249e-05, "loss": 4.28, "step": 7962 }, { "epoch": 0.42848687042617306, "grad_norm": 0.9807708859443665, "learning_rate": 3.057361774230319e-05, "loss": 4.5082, "step": 7963 }, { "epoch": 0.42854068015497204, "grad_norm": 3.8119640350341797, "learning_rate": 3.056949782546489e-05, "loss": 3.6181, "step": 7964 }, { "epoch": 0.42859448988377097, "grad_norm": 2.9213767051696777, "learning_rate": 3.0565377749465324e-05, "loss": 4.2171, "step": 7965 }, { "epoch": 0.42864829961256995, "grad_norm": 1.7090694904327393, "learning_rate": 3.056125751442223e-05, "loss": 4.3874, "step": 7966 }, { "epoch": 0.42870210934136893, "grad_norm": 1.258954644203186, "learning_rate": 3.055713712045335e-05, "loss": 4.4813, "step": 7967 }, { "epoch": 0.4287559190701679, "grad_norm": 2.135493040084839, "learning_rate": 3.055301656767644e-05, "loss": 4.2547, "step": 7968 }, { "epoch": 0.42880972879896684, "grad_norm": 2.4827048778533936, "learning_rate": 3.0548895856209256e-05, "loss": 4.0547, "step": 7969 }, { "epoch": 0.4288635385277658, "grad_norm": 1.9859447479248047, "learning_rate": 3.0544774986169556e-05, "loss": 4.1834, "step": 7970 }, { "epoch": 0.4289173482565648, "grad_norm": 1.650333285331726, "learning_rate": 3.054065395767508e-05, "loss": 4.5703, "step": 7971 }, { "epoch": 0.4289711579853637, "grad_norm": 1.9400280714035034, "learning_rate": 3.053653277084364e-05, "loss": 4.2663, "step": 7972 }, { "epoch": 0.4290249677141627, "grad_norm": 1.1893564462661743, "learning_rate": 3.0532411425792976e-05, "loss": 4.3284, "step": 7973 }, { "epoch": 0.4290787774429617, "grad_norm": 1.8213773965835571, "learning_rate": 3.052828992264087e-05, "loss": 4.5717, "step": 7974 }, { "epoch": 0.42913258717176067, "grad_norm": 1.576227068901062, "learning_rate": 3.052416826150511e-05, "loss": 4.4607, "step": 7975 }, { "epoch": 0.4291863969005596, "grad_norm": 1.7936067581176758, "learning_rate": 3.052004644250349e-05, "loss": 4.2056, "step": 7976 }, { "epoch": 0.4292402066293586, "grad_norm": 1.717180848121643, "learning_rate": 3.051592446575378e-05, "loss": 4.307, "step": 7977 }, { "epoch": 0.42929401635815756, "grad_norm": 1.9138916730880737, "learning_rate": 3.0511802331373784e-05, "loss": 4.186, "step": 7978 }, { "epoch": 0.42934782608695654, "grad_norm": 2.4978551864624023, "learning_rate": 3.05076800394813e-05, "loss": 4.279, "step": 7979 }, { "epoch": 0.42940163581575547, "grad_norm": 2.0238635540008545, "learning_rate": 3.0503557590194143e-05, "loss": 4.2019, "step": 7980 }, { "epoch": 0.42945544554455445, "grad_norm": 1.6558458805084229, "learning_rate": 3.049943498363011e-05, "loss": 4.7137, "step": 7981 }, { "epoch": 0.42950925527335343, "grad_norm": 2.488100528717041, "learning_rate": 3.0495312219907014e-05, "loss": 3.9647, "step": 7982 }, { "epoch": 0.4295630650021524, "grad_norm": 1.892801284790039, "learning_rate": 3.0491189299142676e-05, "loss": 4.3699, "step": 7983 }, { "epoch": 0.42961687473095134, "grad_norm": 1.3655422925949097, "learning_rate": 3.0487066221454913e-05, "loss": 4.222, "step": 7984 }, { "epoch": 0.4296706844597503, "grad_norm": 1.6846461296081543, "learning_rate": 3.048294298696157e-05, "loss": 4.2959, "step": 7985 }, { "epoch": 0.4297244941885493, "grad_norm": 2.4262633323669434, "learning_rate": 3.047881959578045e-05, "loss": 3.615, "step": 7986 }, { "epoch": 0.4297783039173483, "grad_norm": 2.2107980251312256, "learning_rate": 3.0474696048029405e-05, "loss": 4.0357, "step": 7987 }, { "epoch": 0.4298321136461472, "grad_norm": 1.9041355848312378, "learning_rate": 3.0470572343826275e-05, "loss": 4.1252, "step": 7988 }, { "epoch": 0.4298859233749462, "grad_norm": 2.341703414916992, "learning_rate": 3.04664484832889e-05, "loss": 4.3214, "step": 7989 }, { "epoch": 0.42993973310374517, "grad_norm": 1.4144436120986938, "learning_rate": 3.0462324466535136e-05, "loss": 4.5164, "step": 7990 }, { "epoch": 0.42999354283254415, "grad_norm": 2.9773905277252197, "learning_rate": 3.0458200293682826e-05, "loss": 3.3224, "step": 7991 }, { "epoch": 0.4300473525613431, "grad_norm": 1.3368862867355347, "learning_rate": 3.0454075964849825e-05, "loss": 4.3651, "step": 7992 }, { "epoch": 0.43010116229014206, "grad_norm": 1.675589680671692, "learning_rate": 3.0449951480154017e-05, "loss": 4.1141, "step": 7993 }, { "epoch": 0.43015497201894104, "grad_norm": 2.2800159454345703, "learning_rate": 3.0445826839713245e-05, "loss": 3.9123, "step": 7994 }, { "epoch": 0.43020878174773997, "grad_norm": 2.0410852432250977, "learning_rate": 3.044170204364539e-05, "loss": 4.0877, "step": 7995 }, { "epoch": 0.43026259147653895, "grad_norm": 1.4322350025177002, "learning_rate": 3.0437577092068336e-05, "loss": 4.6641, "step": 7996 }, { "epoch": 0.43031640120533793, "grad_norm": 1.5118881464004517, "learning_rate": 3.0433451985099943e-05, "loss": 4.273, "step": 7997 }, { "epoch": 0.4303702109341369, "grad_norm": 2.001950979232788, "learning_rate": 3.0429326722858108e-05, "loss": 4.6553, "step": 7998 }, { "epoch": 0.43042402066293584, "grad_norm": 2.357844829559326, "learning_rate": 3.0425201305460725e-05, "loss": 4.6634, "step": 7999 }, { "epoch": 0.4304778303917348, "grad_norm": 1.8836010694503784, "learning_rate": 3.0421075733025678e-05, "loss": 4.3439, "step": 8000 }, { "epoch": 0.4305316401205338, "grad_norm": 2.5270652770996094, "learning_rate": 3.0416950005670862e-05, "loss": 4.5441, "step": 8001 }, { "epoch": 0.4305854498493328, "grad_norm": 1.5144144296646118, "learning_rate": 3.041282412351419e-05, "loss": 4.491, "step": 8002 }, { "epoch": 0.4306392595781317, "grad_norm": 2.300931453704834, "learning_rate": 3.0408698086673558e-05, "loss": 4.3118, "step": 8003 }, { "epoch": 0.4306930693069307, "grad_norm": 1.055647611618042, "learning_rate": 3.0404571895266887e-05, "loss": 4.6738, "step": 8004 }, { "epoch": 0.43074687903572967, "grad_norm": 1.7685092687606812, "learning_rate": 3.0400445549412093e-05, "loss": 3.966, "step": 8005 }, { "epoch": 0.43080068876452865, "grad_norm": 1.475021243095398, "learning_rate": 3.0396319049227086e-05, "loss": 4.2224, "step": 8006 }, { "epoch": 0.4308544984933276, "grad_norm": 2.1400225162506104, "learning_rate": 3.0392192394829787e-05, "loss": 4.2111, "step": 8007 }, { "epoch": 0.43090830822212656, "grad_norm": 1.8836376667022705, "learning_rate": 3.0388065586338143e-05, "loss": 4.6892, "step": 8008 }, { "epoch": 0.43096211795092554, "grad_norm": 1.7651183605194092, "learning_rate": 3.038393862387008e-05, "loss": 4.6391, "step": 8009 }, { "epoch": 0.4310159276797245, "grad_norm": 1.7638112306594849, "learning_rate": 3.0379811507543514e-05, "loss": 4.5276, "step": 8010 }, { "epoch": 0.43106973740852345, "grad_norm": 1.6829169988632202, "learning_rate": 3.037568423747642e-05, "loss": 4.0323, "step": 8011 }, { "epoch": 0.4311235471373224, "grad_norm": 1.6189318895339966, "learning_rate": 3.0371556813786727e-05, "loss": 4.441, "step": 8012 }, { "epoch": 0.4311773568661214, "grad_norm": 1.9247233867645264, "learning_rate": 3.036742923659239e-05, "loss": 4.2529, "step": 8013 }, { "epoch": 0.43123116659492033, "grad_norm": 2.1369030475616455, "learning_rate": 3.036330150601136e-05, "loss": 4.1842, "step": 8014 }, { "epoch": 0.4312849763237193, "grad_norm": 1.9403789043426514, "learning_rate": 3.0359173622161595e-05, "loss": 3.9582, "step": 8015 }, { "epoch": 0.4313387860525183, "grad_norm": 1.7829217910766602, "learning_rate": 3.035504558516107e-05, "loss": 4.2675, "step": 8016 }, { "epoch": 0.4313925957813173, "grad_norm": 2.601151466369629, "learning_rate": 3.035091739512773e-05, "loss": 3.2752, "step": 8017 }, { "epoch": 0.4314464055101162, "grad_norm": 2.3328723907470703, "learning_rate": 3.034678905217958e-05, "loss": 3.5734, "step": 8018 }, { "epoch": 0.4315002152389152, "grad_norm": 2.248889923095703, "learning_rate": 3.034266055643458e-05, "loss": 4.5619, "step": 8019 }, { "epoch": 0.43155402496771417, "grad_norm": 1.1121068000793457, "learning_rate": 3.03385319080107e-05, "loss": 4.4588, "step": 8020 }, { "epoch": 0.43160783469651315, "grad_norm": 1.7031093835830688, "learning_rate": 3.0334403107025944e-05, "loss": 4.387, "step": 8021 }, { "epoch": 0.4316616444253121, "grad_norm": 1.203536033630371, "learning_rate": 3.0330274153598294e-05, "loss": 4.7342, "step": 8022 }, { "epoch": 0.43171545415411106, "grad_norm": 1.9696433544158936, "learning_rate": 3.0326145047845744e-05, "loss": 4.0649, "step": 8023 }, { "epoch": 0.43176926388291004, "grad_norm": 1.7806167602539062, "learning_rate": 3.0322015789886294e-05, "loss": 3.6921, "step": 8024 }, { "epoch": 0.431823073611709, "grad_norm": 1.159612774848938, "learning_rate": 3.0317886379837944e-05, "loss": 4.1729, "step": 8025 }, { "epoch": 0.43187688334050794, "grad_norm": 1.71338951587677, "learning_rate": 3.031375681781871e-05, "loss": 4.3332, "step": 8026 }, { "epoch": 0.4319306930693069, "grad_norm": 3.3611831665039062, "learning_rate": 3.0309627103946602e-05, "loss": 3.5182, "step": 8027 }, { "epoch": 0.4319845027981059, "grad_norm": 1.0757910013198853, "learning_rate": 3.0305497238339626e-05, "loss": 4.5057, "step": 8028 }, { "epoch": 0.4320383125269049, "grad_norm": 2.7587907314300537, "learning_rate": 3.030136722111581e-05, "loss": 3.8292, "step": 8029 }, { "epoch": 0.4320921222557038, "grad_norm": 1.9811227321624756, "learning_rate": 3.029723705239318e-05, "loss": 4.5302, "step": 8030 }, { "epoch": 0.4321459319845028, "grad_norm": 2.280808448791504, "learning_rate": 3.0293106732289767e-05, "loss": 4.3601, "step": 8031 }, { "epoch": 0.4321997417133018, "grad_norm": 2.87249755859375, "learning_rate": 3.0288976260923592e-05, "loss": 3.8571, "step": 8032 }, { "epoch": 0.43225355144210076, "grad_norm": 2.191880464553833, "learning_rate": 3.02848456384127e-05, "loss": 4.4735, "step": 8033 }, { "epoch": 0.4323073611708997, "grad_norm": 1.176808476448059, "learning_rate": 3.028071486487514e-05, "loss": 4.4132, "step": 8034 }, { "epoch": 0.43236117089969867, "grad_norm": 2.369868516921997, "learning_rate": 3.027658394042895e-05, "loss": 3.7716, "step": 8035 }, { "epoch": 0.43241498062849765, "grad_norm": 1.9507145881652832, "learning_rate": 3.0272452865192186e-05, "loss": 4.4512, "step": 8036 }, { "epoch": 0.4324687903572966, "grad_norm": 2.1364195346832275, "learning_rate": 3.0268321639282898e-05, "loss": 4.9459, "step": 8037 }, { "epoch": 0.43252260008609555, "grad_norm": 2.3403732776641846, "learning_rate": 3.026419026281915e-05, "loss": 4.0453, "step": 8038 }, { "epoch": 0.43257640981489454, "grad_norm": 2.309265613555908, "learning_rate": 3.0260058735919006e-05, "loss": 4.0311, "step": 8039 }, { "epoch": 0.4326302195436935, "grad_norm": 2.6502914428710938, "learning_rate": 3.025592705870053e-05, "loss": 3.6066, "step": 8040 }, { "epoch": 0.43268402927249244, "grad_norm": 2.4718565940856934, "learning_rate": 3.025179523128178e-05, "loss": 4.3457, "step": 8041 }, { "epoch": 0.4327378390012914, "grad_norm": 2.196133613586426, "learning_rate": 3.0247663253780873e-05, "loss": 4.1739, "step": 8042 }, { "epoch": 0.4327916487300904, "grad_norm": 1.793365240097046, "learning_rate": 3.0243531126315842e-05, "loss": 4.6794, "step": 8043 }, { "epoch": 0.4328454584588894, "grad_norm": 2.194955587387085, "learning_rate": 3.0239398849004808e-05, "loss": 4.1359, "step": 8044 }, { "epoch": 0.4328992681876883, "grad_norm": 1.985924482345581, "learning_rate": 3.0235266421965846e-05, "loss": 4.2946, "step": 8045 }, { "epoch": 0.4329530779164873, "grad_norm": 2.681698799133301, "learning_rate": 3.023113384531705e-05, "loss": 4.0307, "step": 8046 }, { "epoch": 0.4330068876452863, "grad_norm": 1.2041687965393066, "learning_rate": 3.022700111917652e-05, "loss": 4.3086, "step": 8047 }, { "epoch": 0.43306069737408526, "grad_norm": 1.6516271829605103, "learning_rate": 3.022286824366235e-05, "loss": 4.4539, "step": 8048 }, { "epoch": 0.4331145071028842, "grad_norm": 2.549175977706909, "learning_rate": 3.0218735218892658e-05, "loss": 4.668, "step": 8049 }, { "epoch": 0.43316831683168316, "grad_norm": 1.1763181686401367, "learning_rate": 3.0214602044985556e-05, "loss": 4.4926, "step": 8050 }, { "epoch": 0.43322212656048215, "grad_norm": 1.6337833404541016, "learning_rate": 3.0210468722059142e-05, "loss": 4.1504, "step": 8051 }, { "epoch": 0.4332759362892811, "grad_norm": 2.164358139038086, "learning_rate": 3.0206335250231556e-05, "loss": 3.6982, "step": 8052 }, { "epoch": 0.43332974601808005, "grad_norm": 1.4600504636764526, "learning_rate": 3.0202201629620907e-05, "loss": 4.1246, "step": 8053 }, { "epoch": 0.43338355574687903, "grad_norm": 1.4762177467346191, "learning_rate": 3.019806786034533e-05, "loss": 4.3481, "step": 8054 }, { "epoch": 0.433437365475678, "grad_norm": 1.679988145828247, "learning_rate": 3.0193933942522955e-05, "loss": 4.2643, "step": 8055 }, { "epoch": 0.43349117520447694, "grad_norm": 2.274900436401367, "learning_rate": 3.0189799876271912e-05, "loss": 4.1786, "step": 8056 }, { "epoch": 0.4335449849332759, "grad_norm": 1.6934711933135986, "learning_rate": 3.0185665661710354e-05, "loss": 4.0666, "step": 8057 }, { "epoch": 0.4335987946620749, "grad_norm": 1.8221983909606934, "learning_rate": 3.0181531298956417e-05, "loss": 4.6223, "step": 8058 }, { "epoch": 0.4336526043908739, "grad_norm": 2.327305793762207, "learning_rate": 3.0177396788128253e-05, "loss": 4.8094, "step": 8059 }, { "epoch": 0.4337064141196728, "grad_norm": 1.9358391761779785, "learning_rate": 3.0173262129344015e-05, "loss": 4.6588, "step": 8060 }, { "epoch": 0.4337602238484718, "grad_norm": 1.1132100820541382, "learning_rate": 3.0169127322721856e-05, "loss": 4.5294, "step": 8061 }, { "epoch": 0.4338140335772708, "grad_norm": 2.3884079456329346, "learning_rate": 3.0164992368379946e-05, "loss": 4.231, "step": 8062 }, { "epoch": 0.43386784330606976, "grad_norm": 1.5720887184143066, "learning_rate": 3.0160857266436443e-05, "loss": 4.7787, "step": 8063 }, { "epoch": 0.4339216530348687, "grad_norm": 1.7271186113357544, "learning_rate": 3.0156722017009518e-05, "loss": 4.3972, "step": 8064 }, { "epoch": 0.43397546276366766, "grad_norm": 1.2113674879074097, "learning_rate": 3.015258662021736e-05, "loss": 4.5223, "step": 8065 }, { "epoch": 0.43402927249246664, "grad_norm": 2.0434346199035645, "learning_rate": 3.014845107617812e-05, "loss": 4.3619, "step": 8066 }, { "epoch": 0.4340830822212656, "grad_norm": 1.873612403869629, "learning_rate": 3.0144315385010003e-05, "loss": 4.134, "step": 8067 }, { "epoch": 0.43413689195006455, "grad_norm": 1.3549509048461914, "learning_rate": 3.014017954683119e-05, "loss": 4.6706, "step": 8068 }, { "epoch": 0.43419070167886353, "grad_norm": 1.4243699312210083, "learning_rate": 3.013604356175987e-05, "loss": 4.7313, "step": 8069 }, { "epoch": 0.4342445114076625, "grad_norm": 2.028878927230835, "learning_rate": 3.013190742991424e-05, "loss": 4.1931, "step": 8070 }, { "epoch": 0.4342983211364615, "grad_norm": 1.5214389562606812, "learning_rate": 3.01277711514125e-05, "loss": 4.7373, "step": 8071 }, { "epoch": 0.4343521308652604, "grad_norm": 0.904979944229126, "learning_rate": 3.012363472637284e-05, "loss": 4.3048, "step": 8072 }, { "epoch": 0.4344059405940594, "grad_norm": 1.038140892982483, "learning_rate": 3.01194981549135e-05, "loss": 4.588, "step": 8073 }, { "epoch": 0.4344597503228584, "grad_norm": 1.9229161739349365, "learning_rate": 3.0115361437152657e-05, "loss": 3.9825, "step": 8074 }, { "epoch": 0.43451356005165737, "grad_norm": 1.8857691287994385, "learning_rate": 3.011122457320855e-05, "loss": 4.4152, "step": 8075 }, { "epoch": 0.4345673697804563, "grad_norm": 3.397775650024414, "learning_rate": 3.0107087563199392e-05, "loss": 3.8769, "step": 8076 }, { "epoch": 0.4346211795092553, "grad_norm": 3.327883005142212, "learning_rate": 3.0102950407243408e-05, "loss": 3.7879, "step": 8077 }, { "epoch": 0.43467498923805425, "grad_norm": 2.5635197162628174, "learning_rate": 3.0098813105458827e-05, "loss": 4.0801, "step": 8078 }, { "epoch": 0.4347287989668532, "grad_norm": 1.7104113101959229, "learning_rate": 3.0094675657963877e-05, "loss": 4.3624, "step": 8079 }, { "epoch": 0.43478260869565216, "grad_norm": 1.6069661378860474, "learning_rate": 3.009053806487681e-05, "loss": 3.8834, "step": 8080 }, { "epoch": 0.43483641842445114, "grad_norm": 3.407318115234375, "learning_rate": 3.008640032631585e-05, "loss": 4.0914, "step": 8081 }, { "epoch": 0.4348902281532501, "grad_norm": 1.0669236183166504, "learning_rate": 3.0082262442399245e-05, "loss": 4.3337, "step": 8082 }, { "epoch": 0.43494403788204905, "grad_norm": 2.516645908355713, "learning_rate": 3.0078124413245255e-05, "loss": 4.2142, "step": 8083 }, { "epoch": 0.43499784761084803, "grad_norm": 2.086012125015259, "learning_rate": 3.007398623897213e-05, "loss": 4.6876, "step": 8084 }, { "epoch": 0.435051657339647, "grad_norm": 1.9963352680206299, "learning_rate": 3.0069847919698125e-05, "loss": 4.706, "step": 8085 }, { "epoch": 0.435105467068446, "grad_norm": 1.471107006072998, "learning_rate": 3.0065709455541496e-05, "loss": 4.3153, "step": 8086 }, { "epoch": 0.4351592767972449, "grad_norm": 2.228409767150879, "learning_rate": 3.006157084662052e-05, "loss": 3.7453, "step": 8087 }, { "epoch": 0.4352130865260439, "grad_norm": 2.4342806339263916, "learning_rate": 3.0057432093053466e-05, "loss": 4.2672, "step": 8088 }, { "epoch": 0.4352668962548429, "grad_norm": 2.6331698894500732, "learning_rate": 3.00532931949586e-05, "loss": 4.1855, "step": 8089 }, { "epoch": 0.43532070598364186, "grad_norm": 2.500244617462158, "learning_rate": 3.0049154152454205e-05, "loss": 4.2903, "step": 8090 }, { "epoch": 0.4353745157124408, "grad_norm": 2.6528499126434326, "learning_rate": 3.0045014965658576e-05, "loss": 3.4132, "step": 8091 }, { "epoch": 0.43542832544123977, "grad_norm": 2.2860419750213623, "learning_rate": 3.004087563468998e-05, "loss": 4.2654, "step": 8092 }, { "epoch": 0.43548213517003875, "grad_norm": 1.8357936143875122, "learning_rate": 3.0036736159666722e-05, "loss": 4.7492, "step": 8093 }, { "epoch": 0.43553594489883773, "grad_norm": 3.034017562866211, "learning_rate": 3.0032596540707087e-05, "loss": 3.144, "step": 8094 }, { "epoch": 0.43558975462763666, "grad_norm": 2.149897813796997, "learning_rate": 3.0028456777929376e-05, "loss": 4.3939, "step": 8095 }, { "epoch": 0.43564356435643564, "grad_norm": 1.8781229257583618, "learning_rate": 3.0024316871451908e-05, "loss": 4.4789, "step": 8096 }, { "epoch": 0.4356973740852346, "grad_norm": 2.9599506855010986, "learning_rate": 3.0020176821392964e-05, "loss": 3.805, "step": 8097 }, { "epoch": 0.4357511838140336, "grad_norm": 2.1859419345855713, "learning_rate": 3.0016036627870874e-05, "loss": 4.4355, "step": 8098 }, { "epoch": 0.43580499354283253, "grad_norm": 1.8972365856170654, "learning_rate": 3.0011896291003948e-05, "loss": 4.2867, "step": 8099 }, { "epoch": 0.4358588032716315, "grad_norm": 2.274451494216919, "learning_rate": 3.000775581091051e-05, "loss": 4.0983, "step": 8100 }, { "epoch": 0.4359126130004305, "grad_norm": 2.061635732650757, "learning_rate": 3.0003615187708877e-05, "loss": 4.0293, "step": 8101 }, { "epoch": 0.4359664227292294, "grad_norm": 1.522255778312683, "learning_rate": 2.9999474421517383e-05, "loss": 4.4982, "step": 8102 }, { "epoch": 0.4360202324580284, "grad_norm": 2.4230692386627197, "learning_rate": 2.9995333512454355e-05, "loss": 4.4587, "step": 8103 }, { "epoch": 0.4360740421868274, "grad_norm": 2.0440773963928223, "learning_rate": 2.9991192460638133e-05, "loss": 3.9479, "step": 8104 }, { "epoch": 0.43612785191562636, "grad_norm": 1.4641640186309814, "learning_rate": 2.9987051266187048e-05, "loss": 4.6437, "step": 8105 }, { "epoch": 0.4361816616444253, "grad_norm": 1.687890648841858, "learning_rate": 2.998290992921946e-05, "loss": 4.3897, "step": 8106 }, { "epoch": 0.43623547137322427, "grad_norm": 1.5678019523620605, "learning_rate": 2.9978768449853707e-05, "loss": 3.7141, "step": 8107 }, { "epoch": 0.43628928110202325, "grad_norm": 2.6561594009399414, "learning_rate": 2.9974626828208142e-05, "loss": 4.1141, "step": 8108 }, { "epoch": 0.43634309083082223, "grad_norm": 2.0012295246124268, "learning_rate": 2.997048506440112e-05, "loss": 3.655, "step": 8109 }, { "epoch": 0.43639690055962116, "grad_norm": 0.9136086106300354, "learning_rate": 2.9966343158551004e-05, "loss": 4.5278, "step": 8110 }, { "epoch": 0.43645071028842014, "grad_norm": 3.3410680294036865, "learning_rate": 2.996220111077616e-05, "loss": 4.2654, "step": 8111 }, { "epoch": 0.4365045200172191, "grad_norm": 1.1603020429611206, "learning_rate": 2.995805892119496e-05, "loss": 4.6479, "step": 8112 }, { "epoch": 0.4365583297460181, "grad_norm": 2.890566349029541, "learning_rate": 2.995391658992576e-05, "loss": 3.8995, "step": 8113 }, { "epoch": 0.43661213947481703, "grad_norm": 0.9855936765670776, "learning_rate": 2.9949774117086958e-05, "loss": 4.4527, "step": 8114 }, { "epoch": 0.436665949203616, "grad_norm": 2.9926698207855225, "learning_rate": 2.9945631502796923e-05, "loss": 4.3461, "step": 8115 }, { "epoch": 0.436719758932415, "grad_norm": 2.71403169631958, "learning_rate": 2.994148874717404e-05, "loss": 4.0496, "step": 8116 }, { "epoch": 0.436773568661214, "grad_norm": 1.4500014781951904, "learning_rate": 2.99373458503367e-05, "loss": 4.6477, "step": 8117 }, { "epoch": 0.4368273783900129, "grad_norm": 2.579205274581909, "learning_rate": 2.9933202812403295e-05, "loss": 4.1849, "step": 8118 }, { "epoch": 0.4368811881188119, "grad_norm": 2.571688652038574, "learning_rate": 2.992905963349223e-05, "loss": 3.8709, "step": 8119 }, { "epoch": 0.43693499784761086, "grad_norm": 1.6754143238067627, "learning_rate": 2.9924916313721884e-05, "loss": 4.0017, "step": 8120 }, { "epoch": 0.4369888075764098, "grad_norm": 2.2257633209228516, "learning_rate": 2.9920772853210687e-05, "loss": 4.1238, "step": 8121 }, { "epoch": 0.43704261730520877, "grad_norm": 2.2288169860839844, "learning_rate": 2.991662925207704e-05, "loss": 4.2239, "step": 8122 }, { "epoch": 0.43709642703400775, "grad_norm": 2.229034900665283, "learning_rate": 2.991248551043934e-05, "loss": 4.178, "step": 8123 }, { "epoch": 0.43715023676280673, "grad_norm": 3.0459144115448, "learning_rate": 2.9908341628416026e-05, "loss": 3.9534, "step": 8124 }, { "epoch": 0.43720404649160566, "grad_norm": 1.7555761337280273, "learning_rate": 2.990419760612551e-05, "loss": 4.1899, "step": 8125 }, { "epoch": 0.43725785622040464, "grad_norm": 1.0465503931045532, "learning_rate": 2.9900053443686215e-05, "loss": 4.5009, "step": 8126 }, { "epoch": 0.4373116659492036, "grad_norm": 2.1425039768218994, "learning_rate": 2.9895909141216578e-05, "loss": 4.4096, "step": 8127 }, { "epoch": 0.4373654756780026, "grad_norm": 2.4563193321228027, "learning_rate": 2.989176469883501e-05, "loss": 4.3944, "step": 8128 }, { "epoch": 0.43741928540680153, "grad_norm": 1.7255233526229858, "learning_rate": 2.988762011665998e-05, "loss": 4.0061, "step": 8129 }, { "epoch": 0.4374730951356005, "grad_norm": 2.0782227516174316, "learning_rate": 2.988347539480991e-05, "loss": 4.0482, "step": 8130 }, { "epoch": 0.4375269048643995, "grad_norm": 2.5269384384155273, "learning_rate": 2.987933053340325e-05, "loss": 3.3839, "step": 8131 }, { "epoch": 0.43758071459319847, "grad_norm": 1.9162088632583618, "learning_rate": 2.987518553255844e-05, "loss": 4.4247, "step": 8132 }, { "epoch": 0.4376345243219974, "grad_norm": 2.09061598777771, "learning_rate": 2.9871040392393944e-05, "loss": 4.329, "step": 8133 }, { "epoch": 0.4376883340507964, "grad_norm": 1.6910173892974854, "learning_rate": 2.986689511302822e-05, "loss": 4.7912, "step": 8134 }, { "epoch": 0.43774214377959536, "grad_norm": 1.6838743686676025, "learning_rate": 2.9862749694579717e-05, "loss": 4.0571, "step": 8135 }, { "epoch": 0.43779595350839434, "grad_norm": 2.0377960205078125, "learning_rate": 2.9858604137166906e-05, "loss": 3.9643, "step": 8136 }, { "epoch": 0.43784976323719327, "grad_norm": 2.202256441116333, "learning_rate": 2.985445844090826e-05, "loss": 4.4402, "step": 8137 }, { "epoch": 0.43790357296599225, "grad_norm": 1.1792752742767334, "learning_rate": 2.9850312605922255e-05, "loss": 4.4973, "step": 8138 }, { "epoch": 0.43795738269479123, "grad_norm": 2.095147132873535, "learning_rate": 2.9846166632327354e-05, "loss": 4.7454, "step": 8139 }, { "epoch": 0.4380111924235902, "grad_norm": 1.4622663259506226, "learning_rate": 2.9842020520242047e-05, "loss": 4.5844, "step": 8140 }, { "epoch": 0.43806500215238914, "grad_norm": 2.764901876449585, "learning_rate": 2.983787426978481e-05, "loss": 4.3364, "step": 8141 }, { "epoch": 0.4381188118811881, "grad_norm": 1.9956843852996826, "learning_rate": 2.9833727881074154e-05, "loss": 4.5818, "step": 8142 }, { "epoch": 0.4381726216099871, "grad_norm": 1.372288703918457, "learning_rate": 2.9829581354228546e-05, "loss": 4.3396, "step": 8143 }, { "epoch": 0.438226431338786, "grad_norm": 2.045017719268799, "learning_rate": 2.9825434689366492e-05, "loss": 3.7943, "step": 8144 }, { "epoch": 0.438280241067585, "grad_norm": 3.503831386566162, "learning_rate": 2.9821287886606502e-05, "loss": 3.6376, "step": 8145 }, { "epoch": 0.438334050796384, "grad_norm": 2.1455373764038086, "learning_rate": 2.9817140946067063e-05, "loss": 4.244, "step": 8146 }, { "epoch": 0.43838786052518297, "grad_norm": 2.931006908416748, "learning_rate": 2.9812993867866697e-05, "loss": 3.863, "step": 8147 }, { "epoch": 0.4384416702539819, "grad_norm": 1.6768766641616821, "learning_rate": 2.980884665212391e-05, "loss": 4.347, "step": 8148 }, { "epoch": 0.4384954799827809, "grad_norm": 2.053433895111084, "learning_rate": 2.9804699298957223e-05, "loss": 4.1753, "step": 8149 }, { "epoch": 0.43854928971157986, "grad_norm": 2.550360918045044, "learning_rate": 2.980055180848515e-05, "loss": 4.3344, "step": 8150 }, { "epoch": 0.43860309944037884, "grad_norm": 2.0616703033447266, "learning_rate": 2.9796404180826216e-05, "loss": 4.4295, "step": 8151 }, { "epoch": 0.43865690916917777, "grad_norm": 1.9555310010910034, "learning_rate": 2.979225641609895e-05, "loss": 4.3204, "step": 8152 }, { "epoch": 0.43871071889797675, "grad_norm": 1.505582571029663, "learning_rate": 2.9788108514421898e-05, "loss": 4.5411, "step": 8153 }, { "epoch": 0.43876452862677573, "grad_norm": 2.1120636463165283, "learning_rate": 2.9783960475913568e-05, "loss": 4.5163, "step": 8154 }, { "epoch": 0.4388183383555747, "grad_norm": 1.912103533744812, "learning_rate": 2.977981230069252e-05, "loss": 4.1956, "step": 8155 }, { "epoch": 0.43887214808437364, "grad_norm": 2.179706335067749, "learning_rate": 2.97756639888773e-05, "loss": 4.4325, "step": 8156 }, { "epoch": 0.4389259578131726, "grad_norm": 2.385593891143799, "learning_rate": 2.977151554058644e-05, "loss": 4.5919, "step": 8157 }, { "epoch": 0.4389797675419716, "grad_norm": 1.8222882747650146, "learning_rate": 2.9767366955938504e-05, "loss": 4.385, "step": 8158 }, { "epoch": 0.4390335772707706, "grad_norm": 2.3101656436920166, "learning_rate": 2.976321823505204e-05, "loss": 4.0261, "step": 8159 }, { "epoch": 0.4390873869995695, "grad_norm": 1.9966986179351807, "learning_rate": 2.9759069378045613e-05, "loss": 4.4059, "step": 8160 }, { "epoch": 0.4391411967283685, "grad_norm": 1.0610668659210205, "learning_rate": 2.9754920385037783e-05, "loss": 4.5299, "step": 8161 }, { "epoch": 0.43919500645716747, "grad_norm": 2.0723400115966797, "learning_rate": 2.9750771256147114e-05, "loss": 4.3622, "step": 8162 }, { "epoch": 0.4392488161859664, "grad_norm": 1.6967675685882568, "learning_rate": 2.9746621991492185e-05, "loss": 4.3546, "step": 8163 }, { "epoch": 0.4393026259147654, "grad_norm": 1.9717426300048828, "learning_rate": 2.9742472591191567e-05, "loss": 3.9524, "step": 8164 }, { "epoch": 0.43935643564356436, "grad_norm": 1.7235755920410156, "learning_rate": 2.9738323055363838e-05, "loss": 4.4214, "step": 8165 }, { "epoch": 0.43941024537236334, "grad_norm": 1.759392499923706, "learning_rate": 2.9734173384127578e-05, "loss": 4.4792, "step": 8166 }, { "epoch": 0.43946405510116227, "grad_norm": 2.642359495162964, "learning_rate": 2.9730023577601367e-05, "loss": 4.5281, "step": 8167 }, { "epoch": 0.43951786482996125, "grad_norm": 2.6164896488189697, "learning_rate": 2.972587363590382e-05, "loss": 4.5496, "step": 8168 }, { "epoch": 0.43957167455876023, "grad_norm": 2.372809648513794, "learning_rate": 2.972172355915351e-05, "loss": 4.1391, "step": 8169 }, { "epoch": 0.4396254842875592, "grad_norm": 1.9222286939620972, "learning_rate": 2.971757334746904e-05, "loss": 4.4641, "step": 8170 }, { "epoch": 0.43967929401635814, "grad_norm": 1.814850091934204, "learning_rate": 2.9713423000969015e-05, "loss": 4.3669, "step": 8171 }, { "epoch": 0.4397331037451571, "grad_norm": 3.219305992126465, "learning_rate": 2.9709272519772034e-05, "loss": 4.5524, "step": 8172 }, { "epoch": 0.4397869134739561, "grad_norm": 1.4358742237091064, "learning_rate": 2.9705121903996715e-05, "loss": 4.6928, "step": 8173 }, { "epoch": 0.4398407232027551, "grad_norm": 1.7353566884994507, "learning_rate": 2.9700971153761664e-05, "loss": 4.3257, "step": 8174 }, { "epoch": 0.439894532931554, "grad_norm": 1.717756748199463, "learning_rate": 2.96968202691855e-05, "loss": 4.5571, "step": 8175 }, { "epoch": 0.439948342660353, "grad_norm": 1.4520291090011597, "learning_rate": 2.9692669250386852e-05, "loss": 4.0251, "step": 8176 }, { "epoch": 0.44000215238915197, "grad_norm": 2.55067777633667, "learning_rate": 2.968851809748433e-05, "loss": 4.2302, "step": 8177 }, { "epoch": 0.44005596211795095, "grad_norm": 2.1604435443878174, "learning_rate": 2.9684366810596582e-05, "loss": 4.0266, "step": 8178 }, { "epoch": 0.4401097718467499, "grad_norm": 1.4231771230697632, "learning_rate": 2.9680215389842227e-05, "loss": 4.3201, "step": 8179 }, { "epoch": 0.44016358157554886, "grad_norm": 1.6963791847229004, "learning_rate": 2.9676063835339895e-05, "loss": 4.313, "step": 8180 }, { "epoch": 0.44021739130434784, "grad_norm": 2.149078607559204, "learning_rate": 2.9671912147208247e-05, "loss": 4.4875, "step": 8181 }, { "epoch": 0.4402712010331468, "grad_norm": 1.8429535627365112, "learning_rate": 2.9667760325565907e-05, "loss": 4.4539, "step": 8182 }, { "epoch": 0.44032501076194575, "grad_norm": 1.600569486618042, "learning_rate": 2.9663608370531537e-05, "loss": 4.9403, "step": 8183 }, { "epoch": 0.4403788204907447, "grad_norm": 2.424941062927246, "learning_rate": 2.9659456282223784e-05, "loss": 4.5505, "step": 8184 }, { "epoch": 0.4404326302195437, "grad_norm": 1.1615900993347168, "learning_rate": 2.9655304060761303e-05, "loss": 4.3369, "step": 8185 }, { "epoch": 0.44048643994834263, "grad_norm": 2.5591046810150146, "learning_rate": 2.9651151706262747e-05, "loss": 4.3976, "step": 8186 }, { "epoch": 0.4405402496771416, "grad_norm": 1.9668474197387695, "learning_rate": 2.9646999218846794e-05, "loss": 4.6132, "step": 8187 }, { "epoch": 0.4405940594059406, "grad_norm": 1.6694040298461914, "learning_rate": 2.9642846598632102e-05, "loss": 3.954, "step": 8188 }, { "epoch": 0.4406478691347396, "grad_norm": 2.4909024238586426, "learning_rate": 2.9638693845737338e-05, "loss": 3.8126, "step": 8189 }, { "epoch": 0.4407016788635385, "grad_norm": 1.3207591772079468, "learning_rate": 2.9634540960281176e-05, "loss": 4.6504, "step": 8190 }, { "epoch": 0.4407554885923375, "grad_norm": 2.473240613937378, "learning_rate": 2.963038794238231e-05, "loss": 3.3647, "step": 8191 }, { "epoch": 0.44080929832113647, "grad_norm": 1.1367783546447754, "learning_rate": 2.9626234792159396e-05, "loss": 4.1494, "step": 8192 }, { "epoch": 0.44086310804993545, "grad_norm": 1.3404066562652588, "learning_rate": 2.9622081509731146e-05, "loss": 4.3692, "step": 8193 }, { "epoch": 0.4409169177787344, "grad_norm": 2.1361963748931885, "learning_rate": 2.9617928095216234e-05, "loss": 4.3688, "step": 8194 }, { "epoch": 0.44097072750753336, "grad_norm": 1.2747952938079834, "learning_rate": 2.9613774548733364e-05, "loss": 4.5728, "step": 8195 }, { "epoch": 0.44102453723633234, "grad_norm": 2.116492986679077, "learning_rate": 2.960962087040122e-05, "loss": 4.0998, "step": 8196 }, { "epoch": 0.4410783469651313, "grad_norm": 2.741577625274658, "learning_rate": 2.9605467060338517e-05, "loss": 3.8429, "step": 8197 }, { "epoch": 0.44113215669393024, "grad_norm": 2.6632115840911865, "learning_rate": 2.9601313118663942e-05, "loss": 5.0437, "step": 8198 }, { "epoch": 0.4411859664227292, "grad_norm": 1.7637706995010376, "learning_rate": 2.9597159045496226e-05, "loss": 4.5252, "step": 8199 }, { "epoch": 0.4412397761515282, "grad_norm": 1.7910377979278564, "learning_rate": 2.959300484095406e-05, "loss": 4.4314, "step": 8200 }, { "epoch": 0.4412935858803272, "grad_norm": 1.709335446357727, "learning_rate": 2.9588850505156173e-05, "loss": 4.6014, "step": 8201 }, { "epoch": 0.4413473956091261, "grad_norm": 1.4715582132339478, "learning_rate": 2.958469603822128e-05, "loss": 4.7033, "step": 8202 }, { "epoch": 0.4414012053379251, "grad_norm": 1.3394533395767212, "learning_rate": 2.9580541440268107e-05, "loss": 4.3888, "step": 8203 }, { "epoch": 0.4414550150667241, "grad_norm": 3.256897211074829, "learning_rate": 2.957638671141538e-05, "loss": 3.2976, "step": 8204 }, { "epoch": 0.44150882479552306, "grad_norm": 2.356074333190918, "learning_rate": 2.957223185178183e-05, "loss": 4.2719, "step": 8205 }, { "epoch": 0.441562634524322, "grad_norm": 1.2084580659866333, "learning_rate": 2.956807686148619e-05, "loss": 4.3664, "step": 8206 }, { "epoch": 0.44161644425312097, "grad_norm": 1.5118191242218018, "learning_rate": 2.9563921740647206e-05, "loss": 4.6539, "step": 8207 }, { "epoch": 0.44167025398191995, "grad_norm": 3.761568307876587, "learning_rate": 2.95597664893836e-05, "loss": 3.7672, "step": 8208 }, { "epoch": 0.4417240637107189, "grad_norm": 1.5123107433319092, "learning_rate": 2.9555611107814147e-05, "loss": 4.4595, "step": 8209 }, { "epoch": 0.44177787343951785, "grad_norm": 2.4669275283813477, "learning_rate": 2.9551455596057576e-05, "loss": 4.5224, "step": 8210 }, { "epoch": 0.44183168316831684, "grad_norm": 2.2165815830230713, "learning_rate": 2.9547299954232642e-05, "loss": 4.1212, "step": 8211 }, { "epoch": 0.4418854928971158, "grad_norm": 1.6840189695358276, "learning_rate": 2.9543144182458116e-05, "loss": 4.7444, "step": 8212 }, { "epoch": 0.44193930262591474, "grad_norm": 2.4307167530059814, "learning_rate": 2.9538988280852737e-05, "loss": 3.961, "step": 8213 }, { "epoch": 0.4419931123547137, "grad_norm": 2.571227788925171, "learning_rate": 2.9534832249535294e-05, "loss": 4.3286, "step": 8214 }, { "epoch": 0.4420469220835127, "grad_norm": 2.128085136413574, "learning_rate": 2.9530676088624538e-05, "loss": 4.4707, "step": 8215 }, { "epoch": 0.4421007318123117, "grad_norm": 1.2696644067764282, "learning_rate": 2.952651979823924e-05, "loss": 4.6682, "step": 8216 }, { "epoch": 0.4421545415411106, "grad_norm": 3.9020802974700928, "learning_rate": 2.952236337849818e-05, "loss": 3.2829, "step": 8217 }, { "epoch": 0.4422083512699096, "grad_norm": 3.0840823650360107, "learning_rate": 2.9518206829520146e-05, "loss": 3.6972, "step": 8218 }, { "epoch": 0.4422621609987086, "grad_norm": 2.6152641773223877, "learning_rate": 2.951405015142391e-05, "loss": 3.9787, "step": 8219 }, { "epoch": 0.44231597072750756, "grad_norm": 3.211113214492798, "learning_rate": 2.950989334432826e-05, "loss": 4.002, "step": 8220 }, { "epoch": 0.4423697804563065, "grad_norm": 2.6862595081329346, "learning_rate": 2.9505736408351985e-05, "loss": 3.9738, "step": 8221 }, { "epoch": 0.44242359018510546, "grad_norm": 2.551635980606079, "learning_rate": 2.9501579343613895e-05, "loss": 4.445, "step": 8222 }, { "epoch": 0.44247739991390445, "grad_norm": 1.7105516195297241, "learning_rate": 2.949742215023277e-05, "loss": 4.3284, "step": 8223 }, { "epoch": 0.4425312096427034, "grad_norm": 2.287935256958008, "learning_rate": 2.949326482832741e-05, "loss": 4.3992, "step": 8224 }, { "epoch": 0.44258501937150235, "grad_norm": 1.9187474250793457, "learning_rate": 2.9489107378016633e-05, "loss": 4.4211, "step": 8225 }, { "epoch": 0.44263882910030133, "grad_norm": 2.069157838821411, "learning_rate": 2.9484949799419243e-05, "loss": 4.3758, "step": 8226 }, { "epoch": 0.4426926388291003, "grad_norm": 3.6093270778656006, "learning_rate": 2.9480792092654046e-05, "loss": 3.1644, "step": 8227 }, { "epoch": 0.44274644855789924, "grad_norm": 2.508183717727661, "learning_rate": 2.9476634257839863e-05, "loss": 3.8254, "step": 8228 }, { "epoch": 0.4428002582866982, "grad_norm": 2.3393495082855225, "learning_rate": 2.947247629509552e-05, "loss": 3.1787, "step": 8229 }, { "epoch": 0.4428540680154972, "grad_norm": 2.4656195640563965, "learning_rate": 2.946831820453983e-05, "loss": 4.2846, "step": 8230 }, { "epoch": 0.4429078777442962, "grad_norm": 1.924957275390625, "learning_rate": 2.9464159986291618e-05, "loss": 4.8729, "step": 8231 }, { "epoch": 0.4429616874730951, "grad_norm": 1.32045316696167, "learning_rate": 2.9460001640469725e-05, "loss": 4.6824, "step": 8232 }, { "epoch": 0.4430154972018941, "grad_norm": 2.2034752368927, "learning_rate": 2.9455843167192982e-05, "loss": 4.1173, "step": 8233 }, { "epoch": 0.4430693069306931, "grad_norm": 2.1742522716522217, "learning_rate": 2.9451684566580227e-05, "loss": 4.1771, "step": 8234 }, { "epoch": 0.44312311665949206, "grad_norm": 1.6944737434387207, "learning_rate": 2.94475258387503e-05, "loss": 4.8665, "step": 8235 }, { "epoch": 0.443176926388291, "grad_norm": 2.190838098526001, "learning_rate": 2.9443366983822047e-05, "loss": 4.3262, "step": 8236 }, { "epoch": 0.44323073611708996, "grad_norm": 2.0211799144744873, "learning_rate": 2.943920800191432e-05, "loss": 4.4116, "step": 8237 }, { "epoch": 0.44328454584588894, "grad_norm": 2.782611846923828, "learning_rate": 2.9435048893145966e-05, "loss": 3.8631, "step": 8238 }, { "epoch": 0.4433383555746879, "grad_norm": 2.223890542984009, "learning_rate": 2.943088965763584e-05, "loss": 4.3185, "step": 8239 }, { "epoch": 0.44339216530348685, "grad_norm": 1.429000973701477, "learning_rate": 2.9426730295502808e-05, "loss": 4.1885, "step": 8240 }, { "epoch": 0.44344597503228583, "grad_norm": 1.823170781135559, "learning_rate": 2.942257080686573e-05, "loss": 4.39, "step": 8241 }, { "epoch": 0.4434997847610848, "grad_norm": 2.3507747650146484, "learning_rate": 2.9418411191843475e-05, "loss": 4.2147, "step": 8242 }, { "epoch": 0.4435535944898838, "grad_norm": 1.7530192136764526, "learning_rate": 2.9414251450554914e-05, "loss": 4.2342, "step": 8243 }, { "epoch": 0.4436074042186827, "grad_norm": 1.4251513481140137, "learning_rate": 2.9410091583118914e-05, "loss": 4.4641, "step": 8244 }, { "epoch": 0.4436612139474817, "grad_norm": 1.6070804595947266, "learning_rate": 2.9405931589654367e-05, "loss": 4.7481, "step": 8245 }, { "epoch": 0.4437150236762807, "grad_norm": 1.5759515762329102, "learning_rate": 2.9401771470280137e-05, "loss": 4.2605, "step": 8246 }, { "epoch": 0.44376883340507967, "grad_norm": 1.937179446220398, "learning_rate": 2.9397611225115118e-05, "loss": 4.8564, "step": 8247 }, { "epoch": 0.4438226431338786, "grad_norm": 2.501211404800415, "learning_rate": 2.9393450854278205e-05, "loss": 4.1338, "step": 8248 }, { "epoch": 0.4438764528626776, "grad_norm": 2.2026185989379883, "learning_rate": 2.938929035788828e-05, "loss": 4.1927, "step": 8249 }, { "epoch": 0.44393026259147655, "grad_norm": 2.0270848274230957, "learning_rate": 2.9385129736064242e-05, "loss": 4.4768, "step": 8250 }, { "epoch": 0.4439840723202755, "grad_norm": 2.219879627227783, "learning_rate": 2.938096898892499e-05, "loss": 4.1332, "step": 8251 }, { "epoch": 0.44403788204907446, "grad_norm": 2.741189479827881, "learning_rate": 2.937680811658943e-05, "loss": 3.8859, "step": 8252 }, { "epoch": 0.44409169177787344, "grad_norm": 2.782139539718628, "learning_rate": 2.9372647119176468e-05, "loss": 4.0975, "step": 8253 }, { "epoch": 0.4441455015066724, "grad_norm": 0.9763374328613281, "learning_rate": 2.9368485996805002e-05, "loss": 4.5588, "step": 8254 }, { "epoch": 0.44419931123547135, "grad_norm": 2.0978214740753174, "learning_rate": 2.936432474959396e-05, "loss": 4.6878, "step": 8255 }, { "epoch": 0.44425312096427033, "grad_norm": 2.0041747093200684, "learning_rate": 2.936016337766227e-05, "loss": 4.2473, "step": 8256 }, { "epoch": 0.4443069306930693, "grad_norm": 1.1501182317733765, "learning_rate": 2.935600188112882e-05, "loss": 4.4139, "step": 8257 }, { "epoch": 0.4443607404218683, "grad_norm": 1.5311410427093506, "learning_rate": 2.935184026011256e-05, "loss": 4.8442, "step": 8258 }, { "epoch": 0.4444145501506672, "grad_norm": 2.444347620010376, "learning_rate": 2.934767851473241e-05, "loss": 4.3362, "step": 8259 }, { "epoch": 0.4444683598794662, "grad_norm": 1.3243696689605713, "learning_rate": 2.9343516645107304e-05, "loss": 4.1815, "step": 8260 }, { "epoch": 0.4445221696082652, "grad_norm": 2.3481390476226807, "learning_rate": 2.9339354651356176e-05, "loss": 3.2683, "step": 8261 }, { "epoch": 0.44457597933706416, "grad_norm": 2.439455032348633, "learning_rate": 2.9335192533597954e-05, "loss": 4.3116, "step": 8262 }, { "epoch": 0.4446297890658631, "grad_norm": 1.0923545360565186, "learning_rate": 2.9331030291951596e-05, "loss": 4.6842, "step": 8263 }, { "epoch": 0.44468359879466207, "grad_norm": 2.6998181343078613, "learning_rate": 2.9326867926536044e-05, "loss": 4.1771, "step": 8264 }, { "epoch": 0.44473740852346105, "grad_norm": 2.467008113861084, "learning_rate": 2.9322705437470244e-05, "loss": 4.2112, "step": 8265 }, { "epoch": 0.44479121825226003, "grad_norm": 1.3728362321853638, "learning_rate": 2.9318542824873148e-05, "loss": 4.5571, "step": 8266 }, { "epoch": 0.44484502798105896, "grad_norm": 1.7181785106658936, "learning_rate": 2.93143800888637e-05, "loss": 4.5719, "step": 8267 }, { "epoch": 0.44489883770985794, "grad_norm": 1.3347078561782837, "learning_rate": 2.93102172295609e-05, "loss": 4.5889, "step": 8268 }, { "epoch": 0.4449526474386569, "grad_norm": 1.3953232765197754, "learning_rate": 2.930605424708367e-05, "loss": 4.4116, "step": 8269 }, { "epoch": 0.44500645716745585, "grad_norm": 2.639740228652954, "learning_rate": 2.9301891141550986e-05, "loss": 3.9661, "step": 8270 }, { "epoch": 0.44506026689625483, "grad_norm": 2.281787395477295, "learning_rate": 2.9297727913081835e-05, "loss": 3.9859, "step": 8271 }, { "epoch": 0.4451140766250538, "grad_norm": 1.5663788318634033, "learning_rate": 2.9293564561795173e-05, "loss": 4.5311, "step": 8272 }, { "epoch": 0.4451678863538528, "grad_norm": 2.132274627685547, "learning_rate": 2.9289401087809985e-05, "loss": 4.1106, "step": 8273 }, { "epoch": 0.4452216960826517, "grad_norm": 1.2687952518463135, "learning_rate": 2.9285237491245255e-05, "loss": 4.5276, "step": 8274 }, { "epoch": 0.4452755058114507, "grad_norm": 1.0905271768569946, "learning_rate": 2.9281073772219958e-05, "loss": 4.476, "step": 8275 }, { "epoch": 0.4453293155402497, "grad_norm": 1.7498886585235596, "learning_rate": 2.927690993085309e-05, "loss": 4.1774, "step": 8276 }, { "epoch": 0.44538312526904866, "grad_norm": 3.0670387744903564, "learning_rate": 2.927274596726364e-05, "loss": 4.0408, "step": 8277 }, { "epoch": 0.4454369349978476, "grad_norm": 2.6333980560302734, "learning_rate": 2.92685818815706e-05, "loss": 3.8673, "step": 8278 }, { "epoch": 0.44549074472664657, "grad_norm": 1.6053922176361084, "learning_rate": 2.926441767389298e-05, "loss": 4.4048, "step": 8279 }, { "epoch": 0.44554455445544555, "grad_norm": 1.6954227685928345, "learning_rate": 2.9260253344349766e-05, "loss": 4.4332, "step": 8280 }, { "epoch": 0.44559836418424453, "grad_norm": 3.9567527770996094, "learning_rate": 2.925608889305997e-05, "loss": 3.207, "step": 8281 }, { "epoch": 0.44565217391304346, "grad_norm": 2.401146173477173, "learning_rate": 2.92519243201426e-05, "loss": 4.6514, "step": 8282 }, { "epoch": 0.44570598364184244, "grad_norm": 1.4455286264419556, "learning_rate": 2.924775962571667e-05, "loss": 4.7253, "step": 8283 }, { "epoch": 0.4457597933706414, "grad_norm": 1.4587231874465942, "learning_rate": 2.9243594809901197e-05, "loss": 4.5021, "step": 8284 }, { "epoch": 0.4458136030994404, "grad_norm": 1.592446208000183, "learning_rate": 2.9239429872815193e-05, "loss": 4.4423, "step": 8285 }, { "epoch": 0.44586741282823933, "grad_norm": 1.2564703226089478, "learning_rate": 2.923526481457769e-05, "loss": 4.7407, "step": 8286 }, { "epoch": 0.4459212225570383, "grad_norm": 1.295100212097168, "learning_rate": 2.9231099635307714e-05, "loss": 4.7923, "step": 8287 }, { "epoch": 0.4459750322858373, "grad_norm": 1.0426687002182007, "learning_rate": 2.9226934335124285e-05, "loss": 4.6353, "step": 8288 }, { "epoch": 0.4460288420146363, "grad_norm": 1.220265507698059, "learning_rate": 2.922276891414644e-05, "loss": 4.6355, "step": 8289 }, { "epoch": 0.4460826517434352, "grad_norm": 1.6796494722366333, "learning_rate": 2.9218603372493225e-05, "loss": 4.3251, "step": 8290 }, { "epoch": 0.4461364614722342, "grad_norm": 1.9254173040390015, "learning_rate": 2.9214437710283666e-05, "loss": 4.2186, "step": 8291 }, { "epoch": 0.44619027120103316, "grad_norm": 2.0044772624969482, "learning_rate": 2.9210271927636817e-05, "loss": 4.3062, "step": 8292 }, { "epoch": 0.4462440809298321, "grad_norm": 2.0180861949920654, "learning_rate": 2.9206106024671713e-05, "loss": 4.19, "step": 8293 }, { "epoch": 0.44629789065863107, "grad_norm": 1.9865258932113647, "learning_rate": 2.9201940001507422e-05, "loss": 4.3934, "step": 8294 }, { "epoch": 0.44635170038743005, "grad_norm": 1.647340178489685, "learning_rate": 2.9197773858262978e-05, "loss": 4.4991, "step": 8295 }, { "epoch": 0.44640551011622903, "grad_norm": 2.021575927734375, "learning_rate": 2.9193607595057454e-05, "loss": 3.3675, "step": 8296 }, { "epoch": 0.44645931984502796, "grad_norm": 1.8837984800338745, "learning_rate": 2.9189441212009905e-05, "loss": 4.3016, "step": 8297 }, { "epoch": 0.44651312957382694, "grad_norm": 1.2205742597579956, "learning_rate": 2.9185274709239395e-05, "loss": 4.3096, "step": 8298 }, { "epoch": 0.4465669393026259, "grad_norm": 1.2449933290481567, "learning_rate": 2.918110808686499e-05, "loss": 4.5357, "step": 8299 }, { "epoch": 0.4466207490314249, "grad_norm": 1.6437970399856567, "learning_rate": 2.917694134500576e-05, "loss": 4.5662, "step": 8300 }, { "epoch": 0.4466745587602238, "grad_norm": 1.481838583946228, "learning_rate": 2.9172774483780772e-05, "loss": 4.2434, "step": 8301 }, { "epoch": 0.4467283684890228, "grad_norm": 3.3873093128204346, "learning_rate": 2.9168607503309132e-05, "loss": 3.7532, "step": 8302 }, { "epoch": 0.4467821782178218, "grad_norm": 3.4583537578582764, "learning_rate": 2.9164440403709886e-05, "loss": 3.6028, "step": 8303 }, { "epoch": 0.44683598794662077, "grad_norm": 1.2445592880249023, "learning_rate": 2.9160273185102143e-05, "loss": 4.2392, "step": 8304 }, { "epoch": 0.4468897976754197, "grad_norm": 1.9928282499313354, "learning_rate": 2.915610584760498e-05, "loss": 3.7933, "step": 8305 }, { "epoch": 0.4469436074042187, "grad_norm": 3.1230809688568115, "learning_rate": 2.915193839133749e-05, "loss": 4.157, "step": 8306 }, { "epoch": 0.44699741713301766, "grad_norm": 1.9618631601333618, "learning_rate": 2.9147770816418768e-05, "loss": 4.1153, "step": 8307 }, { "epoch": 0.44705122686181664, "grad_norm": 2.557594060897827, "learning_rate": 2.914360312296791e-05, "loss": 3.4224, "step": 8308 }, { "epoch": 0.44710503659061557, "grad_norm": 1.4437905550003052, "learning_rate": 2.9139435311104017e-05, "loss": 4.1919, "step": 8309 }, { "epoch": 0.44715884631941455, "grad_norm": 1.7253056764602661, "learning_rate": 2.9135267380946212e-05, "loss": 4.4952, "step": 8310 }, { "epoch": 0.44721265604821353, "grad_norm": 1.4784753322601318, "learning_rate": 2.9131099332613572e-05, "loss": 4.4371, "step": 8311 }, { "epoch": 0.44726646577701246, "grad_norm": 2.076855421066284, "learning_rate": 2.912693116622523e-05, "loss": 4.6457, "step": 8312 }, { "epoch": 0.44732027550581144, "grad_norm": 1.903172492980957, "learning_rate": 2.9122762881900294e-05, "loss": 4.4176, "step": 8313 }, { "epoch": 0.4473740852346104, "grad_norm": 2.075307846069336, "learning_rate": 2.911859447975789e-05, "loss": 3.9557, "step": 8314 }, { "epoch": 0.4474278949634094, "grad_norm": 1.035718321800232, "learning_rate": 2.9114425959917125e-05, "loss": 4.7643, "step": 8315 }, { "epoch": 0.4474817046922083, "grad_norm": 1.4630990028381348, "learning_rate": 2.9110257322497136e-05, "loss": 4.415, "step": 8316 }, { "epoch": 0.4475355144210073, "grad_norm": 2.087355613708496, "learning_rate": 2.9106088567617052e-05, "loss": 3.8678, "step": 8317 }, { "epoch": 0.4475893241498063, "grad_norm": 1.7563189268112183, "learning_rate": 2.9101919695395996e-05, "loss": 5.0417, "step": 8318 }, { "epoch": 0.44764313387860527, "grad_norm": 2.52584171295166, "learning_rate": 2.9097750705953102e-05, "loss": 3.7067, "step": 8319 }, { "epoch": 0.4476969436074042, "grad_norm": 1.2646058797836304, "learning_rate": 2.9093581599407527e-05, "loss": 4.5844, "step": 8320 }, { "epoch": 0.4477507533362032, "grad_norm": 2.3715996742248535, "learning_rate": 2.9089412375878395e-05, "loss": 4.1611, "step": 8321 }, { "epoch": 0.44780456306500216, "grad_norm": 1.8503620624542236, "learning_rate": 2.9085243035484855e-05, "loss": 4.3014, "step": 8322 }, { "epoch": 0.44785837279380114, "grad_norm": 2.4496567249298096, "learning_rate": 2.9081073578346058e-05, "loss": 3.9849, "step": 8323 }, { "epoch": 0.44791218252260007, "grad_norm": 2.3132269382476807, "learning_rate": 2.907690400458115e-05, "loss": 4.4845, "step": 8324 }, { "epoch": 0.44796599225139905, "grad_norm": 2.7011451721191406, "learning_rate": 2.9072734314309302e-05, "loss": 4.2398, "step": 8325 }, { "epoch": 0.44801980198019803, "grad_norm": 1.7673735618591309, "learning_rate": 2.9068564507649654e-05, "loss": 4.2191, "step": 8326 }, { "epoch": 0.448073611708997, "grad_norm": 1.287084698677063, "learning_rate": 2.9064394584721378e-05, "loss": 4.367, "step": 8327 }, { "epoch": 0.44812742143779594, "grad_norm": 2.0655455589294434, "learning_rate": 2.9060224545643638e-05, "loss": 4.3661, "step": 8328 }, { "epoch": 0.4481812311665949, "grad_norm": 1.5994987487792969, "learning_rate": 2.9056054390535598e-05, "loss": 4.5064, "step": 8329 }, { "epoch": 0.4482350408953939, "grad_norm": 1.2044004201889038, "learning_rate": 2.905188411951644e-05, "loss": 4.4954, "step": 8330 }, { "epoch": 0.4482888506241929, "grad_norm": 2.1330924034118652, "learning_rate": 2.9047713732705324e-05, "loss": 4.0388, "step": 8331 }, { "epoch": 0.4483426603529918, "grad_norm": 2.8370730876922607, "learning_rate": 2.9043543230221432e-05, "loss": 3.9721, "step": 8332 }, { "epoch": 0.4483964700817908, "grad_norm": 1.9618796110153198, "learning_rate": 2.9039372612183964e-05, "loss": 3.9635, "step": 8333 }, { "epoch": 0.44845027981058977, "grad_norm": 1.2059931755065918, "learning_rate": 2.9035201878712083e-05, "loss": 4.644, "step": 8334 }, { "epoch": 0.4485040895393887, "grad_norm": 4.1979241371154785, "learning_rate": 2.9031031029924988e-05, "loss": 4.0272, "step": 8335 }, { "epoch": 0.4485578992681877, "grad_norm": 1.260809063911438, "learning_rate": 2.902686006594187e-05, "loss": 4.6799, "step": 8336 }, { "epoch": 0.44861170899698666, "grad_norm": 1.869689702987671, "learning_rate": 2.902268898688192e-05, "loss": 4.2793, "step": 8337 }, { "epoch": 0.44866551872578564, "grad_norm": 3.0530643463134766, "learning_rate": 2.9018517792864336e-05, "loss": 4.0748, "step": 8338 }, { "epoch": 0.44871932845458457, "grad_norm": 2.024752378463745, "learning_rate": 2.901434648400832e-05, "loss": 4.432, "step": 8339 }, { "epoch": 0.44877313818338355, "grad_norm": 2.566380500793457, "learning_rate": 2.901017506043309e-05, "loss": 3.2962, "step": 8340 }, { "epoch": 0.44882694791218253, "grad_norm": 2.755376100540161, "learning_rate": 2.900600352225784e-05, "loss": 4.1711, "step": 8341 }, { "epoch": 0.4488807576409815, "grad_norm": 1.9702703952789307, "learning_rate": 2.9001831869601776e-05, "loss": 4.0534, "step": 8342 }, { "epoch": 0.44893456736978044, "grad_norm": 1.7094471454620361, "learning_rate": 2.8997660102584122e-05, "loss": 4.1372, "step": 8343 }, { "epoch": 0.4489883770985794, "grad_norm": 1.0684157609939575, "learning_rate": 2.89934882213241e-05, "loss": 4.6273, "step": 8344 }, { "epoch": 0.4490421868273784, "grad_norm": 1.4992091655731201, "learning_rate": 2.8989316225940927e-05, "loss": 4.2775, "step": 8345 }, { "epoch": 0.4490959965561774, "grad_norm": 1.121753215789795, "learning_rate": 2.8985144116553826e-05, "loss": 4.531, "step": 8346 }, { "epoch": 0.4491498062849763, "grad_norm": 1.8894339799880981, "learning_rate": 2.8980971893282017e-05, "loss": 3.8129, "step": 8347 }, { "epoch": 0.4492036160137753, "grad_norm": 2.7081120014190674, "learning_rate": 2.8976799556244748e-05, "loss": 3.9568, "step": 8348 }, { "epoch": 0.44925742574257427, "grad_norm": 2.063730239868164, "learning_rate": 2.897262710556124e-05, "loss": 4.2765, "step": 8349 }, { "epoch": 0.44931123547137325, "grad_norm": 1.6331501007080078, "learning_rate": 2.896845454135073e-05, "loss": 4.3337, "step": 8350 }, { "epoch": 0.4493650452001722, "grad_norm": 1.8265135288238525, "learning_rate": 2.8964281863732467e-05, "loss": 4.2079, "step": 8351 }, { "epoch": 0.44941885492897116, "grad_norm": 1.6755990982055664, "learning_rate": 2.8960109072825693e-05, "loss": 3.8038, "step": 8352 }, { "epoch": 0.44947266465777014, "grad_norm": 2.9810967445373535, "learning_rate": 2.8955936168749655e-05, "loss": 4.4367, "step": 8353 }, { "epoch": 0.4495264743865691, "grad_norm": 2.2153658866882324, "learning_rate": 2.8951763151623602e-05, "loss": 3.8281, "step": 8354 }, { "epoch": 0.44958028411536805, "grad_norm": 1.5086654424667358, "learning_rate": 2.8947590021566773e-05, "loss": 4.7286, "step": 8355 }, { "epoch": 0.449634093844167, "grad_norm": 2.103956699371338, "learning_rate": 2.8943416778698458e-05, "loss": 3.9977, "step": 8356 }, { "epoch": 0.449687903572966, "grad_norm": 2.2418880462646484, "learning_rate": 2.8939243423137884e-05, "loss": 4.1114, "step": 8357 }, { "epoch": 0.44974171330176493, "grad_norm": 1.718350887298584, "learning_rate": 2.8935069955004334e-05, "loss": 3.5048, "step": 8358 }, { "epoch": 0.4497955230305639, "grad_norm": 1.824702501296997, "learning_rate": 2.8930896374417077e-05, "loss": 4.0745, "step": 8359 }, { "epoch": 0.4498493327593629, "grad_norm": 2.889631509780884, "learning_rate": 2.892672268149536e-05, "loss": 3.7674, "step": 8360 }, { "epoch": 0.4499031424881619, "grad_norm": 1.3425335884094238, "learning_rate": 2.8922548876358472e-05, "loss": 4.3604, "step": 8361 }, { "epoch": 0.4499569522169608, "grad_norm": 2.1142258644104004, "learning_rate": 2.89183749591257e-05, "loss": 4.5831, "step": 8362 }, { "epoch": 0.4500107619457598, "grad_norm": 2.0421228408813477, "learning_rate": 2.8914200929916302e-05, "loss": 4.3909, "step": 8363 }, { "epoch": 0.45006457167455877, "grad_norm": 1.9746111631393433, "learning_rate": 2.891002678884957e-05, "loss": 4.3138, "step": 8364 }, { "epoch": 0.45011838140335775, "grad_norm": 2.145890712738037, "learning_rate": 2.8905852536044786e-05, "loss": 4.4296, "step": 8365 }, { "epoch": 0.4501721911321567, "grad_norm": 1.9872443675994873, "learning_rate": 2.8901678171621243e-05, "loss": 4.5111, "step": 8366 }, { "epoch": 0.45022600086095566, "grad_norm": 2.352177619934082, "learning_rate": 2.8897503695698237e-05, "loss": 4.3016, "step": 8367 }, { "epoch": 0.45027981058975464, "grad_norm": 1.2050317525863647, "learning_rate": 2.8893329108395056e-05, "loss": 4.7495, "step": 8368 }, { "epoch": 0.4503336203185536, "grad_norm": 2.8159592151641846, "learning_rate": 2.8889154409830998e-05, "loss": 3.6262, "step": 8369 }, { "epoch": 0.45038743004735254, "grad_norm": 2.8322699069976807, "learning_rate": 2.888497960012537e-05, "loss": 4.2831, "step": 8370 }, { "epoch": 0.4504412397761515, "grad_norm": 2.773958683013916, "learning_rate": 2.8880804679397477e-05, "loss": 3.6588, "step": 8371 }, { "epoch": 0.4504950495049505, "grad_norm": 1.9918766021728516, "learning_rate": 2.8876629647766624e-05, "loss": 4.2476, "step": 8372 }, { "epoch": 0.4505488592337495, "grad_norm": 2.426461696624756, "learning_rate": 2.887245450535212e-05, "loss": 3.7776, "step": 8373 }, { "epoch": 0.4506026689625484, "grad_norm": 1.8153549432754517, "learning_rate": 2.8868279252273278e-05, "loss": 4.276, "step": 8374 }, { "epoch": 0.4506564786913474, "grad_norm": 2.1378579139709473, "learning_rate": 2.886410388864943e-05, "loss": 4.1693, "step": 8375 }, { "epoch": 0.4507102884201464, "grad_norm": 2.7067956924438477, "learning_rate": 2.885992841459988e-05, "loss": 4.1556, "step": 8376 }, { "epoch": 0.4507640981489453, "grad_norm": 2.1280877590179443, "learning_rate": 2.8855752830243952e-05, "loss": 3.8119, "step": 8377 }, { "epoch": 0.4508179078777443, "grad_norm": 1.778901219367981, "learning_rate": 2.885157713570099e-05, "loss": 4.0421, "step": 8378 }, { "epoch": 0.45087171760654327, "grad_norm": 1.5883095264434814, "learning_rate": 2.8847401331090306e-05, "loss": 4.451, "step": 8379 }, { "epoch": 0.45092552733534225, "grad_norm": 2.9458811283111572, "learning_rate": 2.8843225416531244e-05, "loss": 4.538, "step": 8380 }, { "epoch": 0.4509793370641412, "grad_norm": 2.867797374725342, "learning_rate": 2.883904939214313e-05, "loss": 4.3035, "step": 8381 }, { "epoch": 0.45103314679294015, "grad_norm": 1.9339351654052734, "learning_rate": 2.8834873258045325e-05, "loss": 3.5076, "step": 8382 }, { "epoch": 0.45108695652173914, "grad_norm": 2.262606382369995, "learning_rate": 2.8830697014357137e-05, "loss": 4.4278, "step": 8383 }, { "epoch": 0.4511407662505381, "grad_norm": 2.0292367935180664, "learning_rate": 2.8826520661197948e-05, "loss": 3.9739, "step": 8384 }, { "epoch": 0.45119457597933704, "grad_norm": 3.2035465240478516, "learning_rate": 2.8822344198687086e-05, "loss": 3.8802, "step": 8385 }, { "epoch": 0.451248385708136, "grad_norm": 2.4531352519989014, "learning_rate": 2.8818167626943905e-05, "loss": 3.7393, "step": 8386 }, { "epoch": 0.451302195436935, "grad_norm": 2.6270110607147217, "learning_rate": 2.8813990946087767e-05, "loss": 3.4825, "step": 8387 }, { "epoch": 0.451356005165734, "grad_norm": 1.7008246183395386, "learning_rate": 2.8809814156238014e-05, "loss": 4.2776, "step": 8388 }, { "epoch": 0.4514098148945329, "grad_norm": 2.8057916164398193, "learning_rate": 2.880563725751403e-05, "loss": 3.8896, "step": 8389 }, { "epoch": 0.4514636246233319, "grad_norm": 1.9512473344802856, "learning_rate": 2.8801460250035174e-05, "loss": 4.2332, "step": 8390 }, { "epoch": 0.4515174343521309, "grad_norm": 2.0713584423065186, "learning_rate": 2.8797283133920794e-05, "loss": 3.6747, "step": 8391 }, { "epoch": 0.45157124408092986, "grad_norm": 3.6420204639434814, "learning_rate": 2.8793105909290286e-05, "loss": 3.4118, "step": 8392 }, { "epoch": 0.4516250538097288, "grad_norm": 3.2436094284057617, "learning_rate": 2.8788928576263014e-05, "loss": 3.8339, "step": 8393 }, { "epoch": 0.45167886353852776, "grad_norm": 1.3233921527862549, "learning_rate": 2.8784751134958354e-05, "loss": 4.5066, "step": 8394 }, { "epoch": 0.45173267326732675, "grad_norm": 2.3994863033294678, "learning_rate": 2.8780573585495685e-05, "loss": 3.8981, "step": 8395 }, { "epoch": 0.4517864829961257, "grad_norm": 3.8622636795043945, "learning_rate": 2.8776395927994383e-05, "loss": 4.3385, "step": 8396 }, { "epoch": 0.45184029272492465, "grad_norm": 2.1375982761383057, "learning_rate": 2.877221816257385e-05, "loss": 4.6759, "step": 8397 }, { "epoch": 0.45189410245372363, "grad_norm": 2.877875566482544, "learning_rate": 2.876804028935347e-05, "loss": 4.011, "step": 8398 }, { "epoch": 0.4519479121825226, "grad_norm": 1.8649213314056396, "learning_rate": 2.876386230845263e-05, "loss": 4.0901, "step": 8399 }, { "epoch": 0.45200172191132154, "grad_norm": 1.5368810892105103, "learning_rate": 2.8759684219990734e-05, "loss": 4.4485, "step": 8400 }, { "epoch": 0.4520555316401205, "grad_norm": 2.1122450828552246, "learning_rate": 2.8755506024087177e-05, "loss": 4.0125, "step": 8401 }, { "epoch": 0.4521093413689195, "grad_norm": 3.7725820541381836, "learning_rate": 2.875132772086135e-05, "loss": 3.9229, "step": 8402 }, { "epoch": 0.4521631510977185, "grad_norm": 2.855648994445801, "learning_rate": 2.8747149310432668e-05, "loss": 4.6045, "step": 8403 }, { "epoch": 0.4522169608265174, "grad_norm": 3.346790313720703, "learning_rate": 2.8742970792920536e-05, "loss": 3.6945, "step": 8404 }, { "epoch": 0.4522707705553164, "grad_norm": 1.5381388664245605, "learning_rate": 2.873879216844438e-05, "loss": 4.5706, "step": 8405 }, { "epoch": 0.4523245802841154, "grad_norm": 2.2168660163879395, "learning_rate": 2.873461343712358e-05, "loss": 4.0502, "step": 8406 }, { "epoch": 0.45237839001291436, "grad_norm": 1.87886643409729, "learning_rate": 2.873043459907759e-05, "loss": 4.2633, "step": 8407 }, { "epoch": 0.4524321997417133, "grad_norm": 2.249697208404541, "learning_rate": 2.8726255654425803e-05, "loss": 4.0598, "step": 8408 }, { "epoch": 0.45248600947051226, "grad_norm": 2.263742208480835, "learning_rate": 2.8722076603287658e-05, "loss": 4.0413, "step": 8409 }, { "epoch": 0.45253981919931124, "grad_norm": 1.2615565061569214, "learning_rate": 2.871789744578257e-05, "loss": 4.3302, "step": 8410 }, { "epoch": 0.4525936289281102, "grad_norm": 1.7730263471603394, "learning_rate": 2.8713718182029974e-05, "loss": 4.6124, "step": 8411 }, { "epoch": 0.45264743865690915, "grad_norm": 2.052676200866699, "learning_rate": 2.8709538812149295e-05, "loss": 4.2822, "step": 8412 }, { "epoch": 0.45270124838570813, "grad_norm": 3.2103826999664307, "learning_rate": 2.870535933625999e-05, "loss": 3.638, "step": 8413 }, { "epoch": 0.4527550581145071, "grad_norm": 2.2147514820098877, "learning_rate": 2.8701179754481467e-05, "loss": 4.0232, "step": 8414 }, { "epoch": 0.4528088678433061, "grad_norm": 1.392622947692871, "learning_rate": 2.8697000066933187e-05, "loss": 4.1174, "step": 8415 }, { "epoch": 0.452862677572105, "grad_norm": 4.221388816833496, "learning_rate": 2.869282027373459e-05, "loss": 3.5795, "step": 8416 }, { "epoch": 0.452916487300904, "grad_norm": 1.6126681566238403, "learning_rate": 2.8688640375005123e-05, "loss": 4.424, "step": 8417 }, { "epoch": 0.452970297029703, "grad_norm": 1.6856778860092163, "learning_rate": 2.868446037086423e-05, "loss": 4.4504, "step": 8418 }, { "epoch": 0.4530241067585019, "grad_norm": 1.661993145942688, "learning_rate": 2.868028026143137e-05, "loss": 4.4524, "step": 8419 }, { "epoch": 0.4530779164873009, "grad_norm": 2.5687053203582764, "learning_rate": 2.8676100046826005e-05, "loss": 3.9733, "step": 8420 }, { "epoch": 0.4531317262160999, "grad_norm": 1.645320177078247, "learning_rate": 2.8671919727167585e-05, "loss": 4.3002, "step": 8421 }, { "epoch": 0.45318553594489885, "grad_norm": 2.210984945297241, "learning_rate": 2.8667739302575568e-05, "loss": 4.5086, "step": 8422 }, { "epoch": 0.4532393456736978, "grad_norm": 3.579622745513916, "learning_rate": 2.866355877316944e-05, "loss": 4.5582, "step": 8423 }, { "epoch": 0.45329315540249676, "grad_norm": 2.3897204399108887, "learning_rate": 2.865937813906865e-05, "loss": 4.0082, "step": 8424 }, { "epoch": 0.45334696513129574, "grad_norm": 1.351839542388916, "learning_rate": 2.8655197400392676e-05, "loss": 4.3679, "step": 8425 }, { "epoch": 0.4534007748600947, "grad_norm": 1.456312656402588, "learning_rate": 2.865101655726099e-05, "loss": 4.6285, "step": 8426 }, { "epoch": 0.45345458458889365, "grad_norm": 1.5528689622879028, "learning_rate": 2.8646835609793067e-05, "loss": 4.0473, "step": 8427 }, { "epoch": 0.45350839431769263, "grad_norm": 2.304821729660034, "learning_rate": 2.8642654558108407e-05, "loss": 4.0277, "step": 8428 }, { "epoch": 0.4535622040464916, "grad_norm": 1.1586099863052368, "learning_rate": 2.863847340232646e-05, "loss": 4.536, "step": 8429 }, { "epoch": 0.4536160137752906, "grad_norm": 2.607988119125366, "learning_rate": 2.8634292142566734e-05, "loss": 4.3906, "step": 8430 }, { "epoch": 0.4536698235040895, "grad_norm": 2.572892427444458, "learning_rate": 2.8630110778948716e-05, "loss": 4.6838, "step": 8431 }, { "epoch": 0.4537236332328885, "grad_norm": 1.5555171966552734, "learning_rate": 2.8625929311591897e-05, "loss": 4.1549, "step": 8432 }, { "epoch": 0.4537774429616875, "grad_norm": 2.3534047603607178, "learning_rate": 2.862174774061577e-05, "loss": 4.1516, "step": 8433 }, { "epoch": 0.45383125269048646, "grad_norm": 2.499126672744751, "learning_rate": 2.8617566066139835e-05, "loss": 4.395, "step": 8434 }, { "epoch": 0.4538850624192854, "grad_norm": 3.365144729614258, "learning_rate": 2.8613384288283583e-05, "loss": 3.824, "step": 8435 }, { "epoch": 0.45393887214808437, "grad_norm": 1.703370213508606, "learning_rate": 2.860920240716654e-05, "loss": 3.9594, "step": 8436 }, { "epoch": 0.45399268187688335, "grad_norm": 2.529283285140991, "learning_rate": 2.860502042290819e-05, "loss": 4.2654, "step": 8437 }, { "epoch": 0.45404649160568233, "grad_norm": 1.7887794971466064, "learning_rate": 2.8600838335628057e-05, "loss": 4.3154, "step": 8438 }, { "epoch": 0.45410030133448126, "grad_norm": 1.768429160118103, "learning_rate": 2.859665614544565e-05, "loss": 4.2918, "step": 8439 }, { "epoch": 0.45415411106328024, "grad_norm": 1.7522032260894775, "learning_rate": 2.8592473852480484e-05, "loss": 4.4085, "step": 8440 }, { "epoch": 0.4542079207920792, "grad_norm": 2.344890594482422, "learning_rate": 2.858829145685208e-05, "loss": 4.496, "step": 8441 }, { "epoch": 0.45426173052087815, "grad_norm": 1.4106738567352295, "learning_rate": 2.8584108958679945e-05, "loss": 4.7255, "step": 8442 }, { "epoch": 0.45431554024967713, "grad_norm": 1.965079665184021, "learning_rate": 2.8579926358083638e-05, "loss": 4.1187, "step": 8443 }, { "epoch": 0.4543693499784761, "grad_norm": 1.3034662008285522, "learning_rate": 2.857574365518265e-05, "loss": 4.3796, "step": 8444 }, { "epoch": 0.4544231597072751, "grad_norm": 1.9967288970947266, "learning_rate": 2.8571560850096523e-05, "loss": 4.1556, "step": 8445 }, { "epoch": 0.454476969436074, "grad_norm": 1.196926236152649, "learning_rate": 2.85673779429448e-05, "loss": 4.2577, "step": 8446 }, { "epoch": 0.454530779164873, "grad_norm": 2.1949737071990967, "learning_rate": 2.856319493384701e-05, "loss": 4.3818, "step": 8447 }, { "epoch": 0.454584588893672, "grad_norm": 3.612746000289917, "learning_rate": 2.8559011822922692e-05, "loss": 3.7995, "step": 8448 }, { "epoch": 0.45463839862247096, "grad_norm": 2.483623743057251, "learning_rate": 2.855482861029139e-05, "loss": 4.4106, "step": 8449 }, { "epoch": 0.4546922083512699, "grad_norm": 2.2756383419036865, "learning_rate": 2.8550645296072642e-05, "loss": 3.8915, "step": 8450 }, { "epoch": 0.45474601808006887, "grad_norm": 1.9177507162094116, "learning_rate": 2.854646188038601e-05, "loss": 4.2425, "step": 8451 }, { "epoch": 0.45479982780886785, "grad_norm": 2.540827989578247, "learning_rate": 2.854227836335103e-05, "loss": 3.9568, "step": 8452 }, { "epoch": 0.45485363753766683, "grad_norm": 2.672584056854248, "learning_rate": 2.8538094745087264e-05, "loss": 4.0253, "step": 8453 }, { "epoch": 0.45490744726646576, "grad_norm": 1.9902665615081787, "learning_rate": 2.8533911025714265e-05, "loss": 4.4449, "step": 8454 }, { "epoch": 0.45496125699526474, "grad_norm": 1.7390825748443604, "learning_rate": 2.8529727205351598e-05, "loss": 3.68, "step": 8455 }, { "epoch": 0.4550150667240637, "grad_norm": 1.4120107889175415, "learning_rate": 2.8525543284118816e-05, "loss": 4.7784, "step": 8456 }, { "epoch": 0.4550688764528627, "grad_norm": 2.2166781425476074, "learning_rate": 2.8521359262135493e-05, "loss": 4.2644, "step": 8457 }, { "epoch": 0.45512268618166163, "grad_norm": 1.7613804340362549, "learning_rate": 2.851717513952119e-05, "loss": 4.7784, "step": 8458 }, { "epoch": 0.4551764959104606, "grad_norm": 2.5897603034973145, "learning_rate": 2.8512990916395488e-05, "loss": 3.8861, "step": 8459 }, { "epoch": 0.4552303056392596, "grad_norm": 2.7522265911102295, "learning_rate": 2.850880659287795e-05, "loss": 4.0717, "step": 8460 }, { "epoch": 0.4552841153680585, "grad_norm": 2.1170437335968018, "learning_rate": 2.8504622169088158e-05, "loss": 4.0946, "step": 8461 }, { "epoch": 0.4553379250968575, "grad_norm": 2.893606662750244, "learning_rate": 2.8500437645145694e-05, "loss": 3.7605, "step": 8462 }, { "epoch": 0.4553917348256565, "grad_norm": 2.828273296356201, "learning_rate": 2.8496253021170133e-05, "loss": 4.0397, "step": 8463 }, { "epoch": 0.45544554455445546, "grad_norm": 2.4036829471588135, "learning_rate": 2.8492068297281067e-05, "loss": 4.2207, "step": 8464 }, { "epoch": 0.4554993542832544, "grad_norm": 2.4452552795410156, "learning_rate": 2.848788347359808e-05, "loss": 4.5051, "step": 8465 }, { "epoch": 0.45555316401205337, "grad_norm": 2.036644458770752, "learning_rate": 2.848369855024077e-05, "loss": 4.2076, "step": 8466 }, { "epoch": 0.45560697374085235, "grad_norm": 1.947702169418335, "learning_rate": 2.8479513527328716e-05, "loss": 4.0928, "step": 8467 }, { "epoch": 0.45566078346965133, "grad_norm": 2.267515182495117, "learning_rate": 2.847532840498152e-05, "loss": 4.7599, "step": 8468 }, { "epoch": 0.45571459319845026, "grad_norm": 2.6476664543151855, "learning_rate": 2.84711431833188e-05, "loss": 3.7572, "step": 8469 }, { "epoch": 0.45576840292724924, "grad_norm": 1.0656508207321167, "learning_rate": 2.8466957862460137e-05, "loss": 4.6689, "step": 8470 }, { "epoch": 0.4558222126560482, "grad_norm": 1.8753591775894165, "learning_rate": 2.8462772442525145e-05, "loss": 4.0714, "step": 8471 }, { "epoch": 0.4558760223848472, "grad_norm": 2.336778402328491, "learning_rate": 2.8458586923633434e-05, "loss": 4.084, "step": 8472 }, { "epoch": 0.4559298321136461, "grad_norm": 2.1582653522491455, "learning_rate": 2.84544013059046e-05, "loss": 4.0649, "step": 8473 }, { "epoch": 0.4559836418424451, "grad_norm": 1.719075322151184, "learning_rate": 2.8450215589458283e-05, "loss": 4.7193, "step": 8474 }, { "epoch": 0.4560374515712441, "grad_norm": 1.033760905265808, "learning_rate": 2.8446029774414073e-05, "loss": 4.1739, "step": 8475 }, { "epoch": 0.45609126130004307, "grad_norm": 1.6562402248382568, "learning_rate": 2.8441843860891603e-05, "loss": 4.2487, "step": 8476 }, { "epoch": 0.456145071028842, "grad_norm": 1.859548807144165, "learning_rate": 2.8437657849010498e-05, "loss": 4.3096, "step": 8477 }, { "epoch": 0.456198880757641, "grad_norm": 1.584762692451477, "learning_rate": 2.8433471738890373e-05, "loss": 4.7034, "step": 8478 }, { "epoch": 0.45625269048643996, "grad_norm": 2.0796070098876953, "learning_rate": 2.8429285530650862e-05, "loss": 4.1357, "step": 8479 }, { "epoch": 0.45630650021523894, "grad_norm": 1.4062776565551758, "learning_rate": 2.8425099224411595e-05, "loss": 4.7153, "step": 8480 }, { "epoch": 0.45636030994403787, "grad_norm": 2.7916736602783203, "learning_rate": 2.84209128202922e-05, "loss": 3.4534, "step": 8481 }, { "epoch": 0.45641411967283685, "grad_norm": 1.6565800905227661, "learning_rate": 2.8416726318412322e-05, "loss": 4.3434, "step": 8482 }, { "epoch": 0.45646792940163583, "grad_norm": 1.1097356081008911, "learning_rate": 2.84125397188916e-05, "loss": 4.6841, "step": 8483 }, { "epoch": 0.45652173913043476, "grad_norm": 2.6307880878448486, "learning_rate": 2.840835302184966e-05, "loss": 4.329, "step": 8484 }, { "epoch": 0.45657554885923374, "grad_norm": 1.817204475402832, "learning_rate": 2.840416622740617e-05, "loss": 4.5212, "step": 8485 }, { "epoch": 0.4566293585880327, "grad_norm": 2.7952256202697754, "learning_rate": 2.839997933568076e-05, "loss": 4.4073, "step": 8486 }, { "epoch": 0.4566831683168317, "grad_norm": 1.837409257888794, "learning_rate": 2.839579234679308e-05, "loss": 4.4841, "step": 8487 }, { "epoch": 0.4567369780456306, "grad_norm": 1.3946737051010132, "learning_rate": 2.8391605260862798e-05, "loss": 4.8267, "step": 8488 }, { "epoch": 0.4567907877744296, "grad_norm": 3.5901176929473877, "learning_rate": 2.8387418078009554e-05, "loss": 3.8159, "step": 8489 }, { "epoch": 0.4568445975032286, "grad_norm": 3.118048906326294, "learning_rate": 2.8383230798353017e-05, "loss": 3.7922, "step": 8490 }, { "epoch": 0.45689840723202757, "grad_norm": 2.957064390182495, "learning_rate": 2.8379043422012836e-05, "loss": 3.9539, "step": 8491 }, { "epoch": 0.4569522169608265, "grad_norm": 1.895259141921997, "learning_rate": 2.8374855949108686e-05, "loss": 4.3635, "step": 8492 }, { "epoch": 0.4570060266896255, "grad_norm": 3.019540309906006, "learning_rate": 2.837066837976024e-05, "loss": 3.5664, "step": 8493 }, { "epoch": 0.45705983641842446, "grad_norm": 1.4852283000946045, "learning_rate": 2.8366480714087147e-05, "loss": 4.3346, "step": 8494 }, { "epoch": 0.45711364614722344, "grad_norm": 2.054124593734741, "learning_rate": 2.8362292952209092e-05, "loss": 4.1368, "step": 8495 }, { "epoch": 0.45716745587602237, "grad_norm": 2.0593349933624268, "learning_rate": 2.8358105094245747e-05, "loss": 3.5105, "step": 8496 }, { "epoch": 0.45722126560482135, "grad_norm": 2.7736878395080566, "learning_rate": 2.8353917140316794e-05, "loss": 4.0798, "step": 8497 }, { "epoch": 0.45727507533362033, "grad_norm": 1.8435330390930176, "learning_rate": 2.834972909054191e-05, "loss": 4.7324, "step": 8498 }, { "epoch": 0.4573288850624193, "grad_norm": 2.5103795528411865, "learning_rate": 2.8345540945040772e-05, "loss": 4.1992, "step": 8499 }, { "epoch": 0.45738269479121824, "grad_norm": 2.9487504959106445, "learning_rate": 2.8341352703933078e-05, "loss": 3.8823, "step": 8500 }, { "epoch": 0.4574365045200172, "grad_norm": 1.194087028503418, "learning_rate": 2.833716436733851e-05, "loss": 4.5902, "step": 8501 }, { "epoch": 0.4574903142488162, "grad_norm": 2.7144534587860107, "learning_rate": 2.833297593537676e-05, "loss": 3.5376, "step": 8502 }, { "epoch": 0.4575441239776152, "grad_norm": 2.0191962718963623, "learning_rate": 2.8328787408167522e-05, "loss": 4.154, "step": 8503 }, { "epoch": 0.4575979337064141, "grad_norm": 1.6565043926239014, "learning_rate": 2.8324598785830488e-05, "loss": 4.161, "step": 8504 }, { "epoch": 0.4576517434352131, "grad_norm": 1.5586812496185303, "learning_rate": 2.8320410068485377e-05, "loss": 4.4504, "step": 8505 }, { "epoch": 0.45770555316401207, "grad_norm": 2.1305415630340576, "learning_rate": 2.8316221256251867e-05, "loss": 4.4774, "step": 8506 }, { "epoch": 0.457759362892811, "grad_norm": 1.2685340642929077, "learning_rate": 2.831203234924967e-05, "loss": 4.1219, "step": 8507 }, { "epoch": 0.45781317262161, "grad_norm": 2.5191712379455566, "learning_rate": 2.8307843347598508e-05, "loss": 3.5222, "step": 8508 }, { "epoch": 0.45786698235040896, "grad_norm": 2.3882741928100586, "learning_rate": 2.8303654251418067e-05, "loss": 4.1996, "step": 8509 }, { "epoch": 0.45792079207920794, "grad_norm": 2.1247832775115967, "learning_rate": 2.829946506082808e-05, "loss": 4.287, "step": 8510 }, { "epoch": 0.45797460180800686, "grad_norm": 1.9625849723815918, "learning_rate": 2.8295275775948253e-05, "loss": 4.3452, "step": 8511 }, { "epoch": 0.45802841153680585, "grad_norm": 2.8700191974639893, "learning_rate": 2.8291086396898313e-05, "loss": 3.7576, "step": 8512 }, { "epoch": 0.4580822212656048, "grad_norm": 2.3560476303100586, "learning_rate": 2.828689692379798e-05, "loss": 4.1874, "step": 8513 }, { "epoch": 0.4581360309944038, "grad_norm": 2.5906128883361816, "learning_rate": 2.8282707356766962e-05, "loss": 4.3285, "step": 8514 }, { "epoch": 0.45818984072320273, "grad_norm": 2.530350923538208, "learning_rate": 2.8278517695925e-05, "loss": 3.6957, "step": 8515 }, { "epoch": 0.4582436504520017, "grad_norm": 2.389195680618286, "learning_rate": 2.8274327941391827e-05, "loss": 4.5396, "step": 8516 }, { "epoch": 0.4582974601808007, "grad_norm": 2.0961079597473145, "learning_rate": 2.8270138093287157e-05, "loss": 4.3403, "step": 8517 }, { "epoch": 0.4583512699095997, "grad_norm": 2.6259758472442627, "learning_rate": 2.8265948151730748e-05, "loss": 3.5717, "step": 8518 }, { "epoch": 0.4584050796383986, "grad_norm": 2.1251118183135986, "learning_rate": 2.826175811684232e-05, "loss": 4.2236, "step": 8519 }, { "epoch": 0.4584588893671976, "grad_norm": 1.1102980375289917, "learning_rate": 2.825756798874162e-05, "loss": 4.312, "step": 8520 }, { "epoch": 0.45851269909599657, "grad_norm": 2.176027536392212, "learning_rate": 2.8253377767548385e-05, "loss": 4.3391, "step": 8521 }, { "epoch": 0.45856650882479555, "grad_norm": 2.419811725616455, "learning_rate": 2.824918745338236e-05, "loss": 4.0391, "step": 8522 }, { "epoch": 0.4586203185535945, "grad_norm": 1.8473293781280518, "learning_rate": 2.8244997046363304e-05, "loss": 4.0948, "step": 8523 }, { "epoch": 0.45867412828239346, "grad_norm": 2.312875270843506, "learning_rate": 2.8240806546610966e-05, "loss": 3.9132, "step": 8524 }, { "epoch": 0.45872793801119244, "grad_norm": 2.380215883255005, "learning_rate": 2.8236615954245083e-05, "loss": 4.3993, "step": 8525 }, { "epoch": 0.45878174773999136, "grad_norm": 4.655886173248291, "learning_rate": 2.823242526938542e-05, "loss": 3.2204, "step": 8526 }, { "epoch": 0.45883555746879034, "grad_norm": 3.4525816440582275, "learning_rate": 2.8228234492151745e-05, "loss": 3.2145, "step": 8527 }, { "epoch": 0.4588893671975893, "grad_norm": 2.3409342765808105, "learning_rate": 2.822404362266381e-05, "loss": 4.7725, "step": 8528 }, { "epoch": 0.4589431769263883, "grad_norm": 2.146515369415283, "learning_rate": 2.821985266104138e-05, "loss": 4.3483, "step": 8529 }, { "epoch": 0.45899698665518723, "grad_norm": 3.414069652557373, "learning_rate": 2.8215661607404214e-05, "loss": 4.186, "step": 8530 }, { "epoch": 0.4590507963839862, "grad_norm": 2.017490863800049, "learning_rate": 2.8211470461872098e-05, "loss": 4.0488, "step": 8531 }, { "epoch": 0.4591046061127852, "grad_norm": 1.922316551208496, "learning_rate": 2.8207279224564788e-05, "loss": 4.1932, "step": 8532 }, { "epoch": 0.4591584158415842, "grad_norm": 2.264357805252075, "learning_rate": 2.8203087895602066e-05, "loss": 4.4418, "step": 8533 }, { "epoch": 0.4592122255703831, "grad_norm": 1.3963053226470947, "learning_rate": 2.819889647510371e-05, "loss": 4.336, "step": 8534 }, { "epoch": 0.4592660352991821, "grad_norm": 2.4312775135040283, "learning_rate": 2.8194704963189493e-05, "loss": 4.3526, "step": 8535 }, { "epoch": 0.45931984502798107, "grad_norm": 2.3625600337982178, "learning_rate": 2.8190513359979204e-05, "loss": 4.348, "step": 8536 }, { "epoch": 0.45937365475678005, "grad_norm": 2.1568334102630615, "learning_rate": 2.8186321665592617e-05, "loss": 4.6387, "step": 8537 }, { "epoch": 0.459427464485579, "grad_norm": 1.8243932723999023, "learning_rate": 2.8182129880149532e-05, "loss": 4.3275, "step": 8538 }, { "epoch": 0.45948127421437795, "grad_norm": 1.4069361686706543, "learning_rate": 2.8177938003769745e-05, "loss": 4.2943, "step": 8539 }, { "epoch": 0.45953508394317694, "grad_norm": 2.0742032527923584, "learning_rate": 2.817374603657302e-05, "loss": 3.962, "step": 8540 }, { "epoch": 0.4595888936719759, "grad_norm": 2.711087226867676, "learning_rate": 2.8169553978679174e-05, "loss": 4.1056, "step": 8541 }, { "epoch": 0.45964270340077484, "grad_norm": 2.8372914791107178, "learning_rate": 2.8165361830208003e-05, "loss": 4.0468, "step": 8542 }, { "epoch": 0.4596965131295738, "grad_norm": 2.1654646396636963, "learning_rate": 2.8161169591279307e-05, "loss": 4.1221, "step": 8543 }, { "epoch": 0.4597503228583728, "grad_norm": 2.53326678276062, "learning_rate": 2.8156977262012883e-05, "loss": 3.8961, "step": 8544 }, { "epoch": 0.4598041325871718, "grad_norm": 1.8183660507202148, "learning_rate": 2.815278484252854e-05, "loss": 4.5136, "step": 8545 }, { "epoch": 0.4598579423159707, "grad_norm": 2.106776475906372, "learning_rate": 2.8148592332946088e-05, "loss": 3.9838, "step": 8546 }, { "epoch": 0.4599117520447697, "grad_norm": 1.3641234636306763, "learning_rate": 2.8144399733385346e-05, "loss": 4.947, "step": 8547 }, { "epoch": 0.4599655617735687, "grad_norm": 1.4928290843963623, "learning_rate": 2.81402070439661e-05, "loss": 4.386, "step": 8548 }, { "epoch": 0.4600193715023676, "grad_norm": 1.7090466022491455, "learning_rate": 2.8136014264808193e-05, "loss": 4.1665, "step": 8549 }, { "epoch": 0.4600731812311666, "grad_norm": 2.3902218341827393, "learning_rate": 2.8131821396031428e-05, "loss": 3.792, "step": 8550 }, { "epoch": 0.46012699095996556, "grad_norm": 1.0028451681137085, "learning_rate": 2.812762843775563e-05, "loss": 4.6623, "step": 8551 }, { "epoch": 0.46018080068876455, "grad_norm": 1.341037392616272, "learning_rate": 2.8123435390100632e-05, "loss": 4.6053, "step": 8552 }, { "epoch": 0.46023461041756347, "grad_norm": 2.6323866844177246, "learning_rate": 2.811924225318624e-05, "loss": 3.2913, "step": 8553 }, { "epoch": 0.46028842014636245, "grad_norm": 2.433250665664673, "learning_rate": 2.8115049027132307e-05, "loss": 4.2261, "step": 8554 }, { "epoch": 0.46034222987516143, "grad_norm": 2.0081191062927246, "learning_rate": 2.811085571205865e-05, "loss": 4.4144, "step": 8555 }, { "epoch": 0.4603960396039604, "grad_norm": 2.042304277420044, "learning_rate": 2.810666230808509e-05, "loss": 4.3873, "step": 8556 }, { "epoch": 0.46044984933275934, "grad_norm": 2.1436123847961426, "learning_rate": 2.8102468815331485e-05, "loss": 4.0436, "step": 8557 }, { "epoch": 0.4605036590615583, "grad_norm": 3.0152385234832764, "learning_rate": 2.809827523391767e-05, "loss": 3.7068, "step": 8558 }, { "epoch": 0.4605574687903573, "grad_norm": 2.7159183025360107, "learning_rate": 2.8094081563963475e-05, "loss": 4.0045, "step": 8559 }, { "epoch": 0.4606112785191563, "grad_norm": 2.09086537361145, "learning_rate": 2.808988780558876e-05, "loss": 4.7973, "step": 8560 }, { "epoch": 0.4606650882479552, "grad_norm": 2.148754358291626, "learning_rate": 2.808569395891335e-05, "loss": 3.8327, "step": 8561 }, { "epoch": 0.4607188979767542, "grad_norm": 1.8919224739074707, "learning_rate": 2.8081500024057124e-05, "loss": 4.2086, "step": 8562 }, { "epoch": 0.4607727077055532, "grad_norm": 1.2087284326553345, "learning_rate": 2.8077306001139896e-05, "loss": 4.5913, "step": 8563 }, { "epoch": 0.46082651743435216, "grad_norm": 1.9864521026611328, "learning_rate": 2.807311189028155e-05, "loss": 3.8547, "step": 8564 }, { "epoch": 0.4608803271631511, "grad_norm": 2.5016908645629883, "learning_rate": 2.8068917691601932e-05, "loss": 4.5766, "step": 8565 }, { "epoch": 0.46093413689195006, "grad_norm": 1.9809538125991821, "learning_rate": 2.80647234052209e-05, "loss": 4.2037, "step": 8566 }, { "epoch": 0.46098794662074905, "grad_norm": 1.6748409271240234, "learning_rate": 2.8060529031258314e-05, "loss": 4.3984, "step": 8567 }, { "epoch": 0.46104175634954797, "grad_norm": 2.811797857284546, "learning_rate": 2.8056334569834043e-05, "loss": 4.3036, "step": 8568 }, { "epoch": 0.46109556607834695, "grad_norm": 1.87080717086792, "learning_rate": 2.805214002106795e-05, "loss": 4.8219, "step": 8569 }, { "epoch": 0.46114937580714593, "grad_norm": 2.2850682735443115, "learning_rate": 2.8047945385079903e-05, "loss": 3.8184, "step": 8570 }, { "epoch": 0.4612031855359449, "grad_norm": 1.0183136463165283, "learning_rate": 2.804375066198977e-05, "loss": 4.6004, "step": 8571 }, { "epoch": 0.46125699526474384, "grad_norm": 2.3105149269104004, "learning_rate": 2.8039555851917436e-05, "loss": 3.8492, "step": 8572 }, { "epoch": 0.4613108049935428, "grad_norm": 1.9583014249801636, "learning_rate": 2.8035360954982776e-05, "loss": 4.6129, "step": 8573 }, { "epoch": 0.4613646147223418, "grad_norm": 1.4646217823028564, "learning_rate": 2.8031165971305655e-05, "loss": 4.2283, "step": 8574 }, { "epoch": 0.4614184244511408, "grad_norm": 1.6477264165878296, "learning_rate": 2.8026970901005967e-05, "loss": 4.4765, "step": 8575 }, { "epoch": 0.4614722341799397, "grad_norm": 2.3895657062530518, "learning_rate": 2.8022775744203588e-05, "loss": 4.6121, "step": 8576 }, { "epoch": 0.4615260439087387, "grad_norm": 1.6463627815246582, "learning_rate": 2.801858050101842e-05, "loss": 4.8079, "step": 8577 }, { "epoch": 0.4615798536375377, "grad_norm": 1.352832555770874, "learning_rate": 2.8014385171570335e-05, "loss": 3.8831, "step": 8578 }, { "epoch": 0.46163366336633666, "grad_norm": 3.539674997329712, "learning_rate": 2.801018975597922e-05, "loss": 3.2893, "step": 8579 }, { "epoch": 0.4616874730951356, "grad_norm": 1.5295506715774536, "learning_rate": 2.8005994254364986e-05, "loss": 4.4635, "step": 8580 }, { "epoch": 0.46174128282393456, "grad_norm": 2.6791269779205322, "learning_rate": 2.8001798666847523e-05, "loss": 4.6032, "step": 8581 }, { "epoch": 0.46179509255273354, "grad_norm": 2.2960598468780518, "learning_rate": 2.799760299354673e-05, "loss": 4.1956, "step": 8582 }, { "epoch": 0.4618489022815325, "grad_norm": 1.7843680381774902, "learning_rate": 2.7993407234582503e-05, "loss": 4.239, "step": 8583 }, { "epoch": 0.46190271201033145, "grad_norm": 1.9647724628448486, "learning_rate": 2.7989211390074742e-05, "loss": 4.4628, "step": 8584 }, { "epoch": 0.46195652173913043, "grad_norm": 2.6546454429626465, "learning_rate": 2.7985015460143373e-05, "loss": 3.9765, "step": 8585 }, { "epoch": 0.4620103314679294, "grad_norm": 2.585319995880127, "learning_rate": 2.798081944490828e-05, "loss": 3.9787, "step": 8586 }, { "epoch": 0.4620641411967284, "grad_norm": 2.001875877380371, "learning_rate": 2.7976623344489383e-05, "loss": 3.7935, "step": 8587 }, { "epoch": 0.4621179509255273, "grad_norm": 1.9193841218948364, "learning_rate": 2.7972427159006604e-05, "loss": 4.5047, "step": 8588 }, { "epoch": 0.4621717606543263, "grad_norm": 2.5139126777648926, "learning_rate": 2.796823088857985e-05, "loss": 4.0922, "step": 8589 }, { "epoch": 0.4622255703831253, "grad_norm": 2.289835214614868, "learning_rate": 2.7964034533329042e-05, "loss": 4.8002, "step": 8590 }, { "epoch": 0.4622793801119242, "grad_norm": 2.8623239994049072, "learning_rate": 2.7959838093374097e-05, "loss": 3.6183, "step": 8591 }, { "epoch": 0.4623331898407232, "grad_norm": 2.0641467571258545, "learning_rate": 2.7955641568834946e-05, "loss": 4.6438, "step": 8592 }, { "epoch": 0.4623869995695222, "grad_norm": 2.023118257522583, "learning_rate": 2.7951444959831503e-05, "loss": 4.2967, "step": 8593 }, { "epoch": 0.46244080929832115, "grad_norm": 1.9422365427017212, "learning_rate": 2.7947248266483694e-05, "loss": 4.1122, "step": 8594 }, { "epoch": 0.4624946190271201, "grad_norm": 1.8673179149627686, "learning_rate": 2.794305148891147e-05, "loss": 4.361, "step": 8595 }, { "epoch": 0.46254842875591906, "grad_norm": 2.5273513793945312, "learning_rate": 2.793885462723475e-05, "loss": 3.8366, "step": 8596 }, { "epoch": 0.46260223848471804, "grad_norm": 1.9957224130630493, "learning_rate": 2.793465768157346e-05, "loss": 3.3024, "step": 8597 }, { "epoch": 0.462656048213517, "grad_norm": 1.4765361547470093, "learning_rate": 2.7930460652047552e-05, "loss": 4.6571, "step": 8598 }, { "epoch": 0.46270985794231595, "grad_norm": 1.715303659439087, "learning_rate": 2.792626353877696e-05, "loss": 4.6913, "step": 8599 }, { "epoch": 0.46276366767111493, "grad_norm": 1.5931921005249023, "learning_rate": 2.7922066341881632e-05, "loss": 4.9918, "step": 8600 }, { "epoch": 0.4628174773999139, "grad_norm": 1.4867371320724487, "learning_rate": 2.79178690614815e-05, "loss": 4.9492, "step": 8601 }, { "epoch": 0.4628712871287129, "grad_norm": 1.950222373008728, "learning_rate": 2.7913671697696513e-05, "loss": 4.7511, "step": 8602 }, { "epoch": 0.4629250968575118, "grad_norm": 1.7692049741744995, "learning_rate": 2.7909474250646637e-05, "loss": 4.5581, "step": 8603 }, { "epoch": 0.4629789065863108, "grad_norm": 2.052835464477539, "learning_rate": 2.790527672045181e-05, "loss": 3.5325, "step": 8604 }, { "epoch": 0.4630327163151098, "grad_norm": 2.526780843734741, "learning_rate": 2.7901079107231988e-05, "loss": 4.3827, "step": 8605 }, { "epoch": 0.46308652604390876, "grad_norm": 2.121060848236084, "learning_rate": 2.7896881411107128e-05, "loss": 4.4941, "step": 8606 }, { "epoch": 0.4631403357727077, "grad_norm": 2.579718589782715, "learning_rate": 2.789268363219718e-05, "loss": 4.0933, "step": 8607 }, { "epoch": 0.46319414550150667, "grad_norm": 2.5203306674957275, "learning_rate": 2.788848577062213e-05, "loss": 3.0404, "step": 8608 }, { "epoch": 0.46324795523030565, "grad_norm": 1.6398988962173462, "learning_rate": 2.788428782650192e-05, "loss": 4.3827, "step": 8609 }, { "epoch": 0.46330176495910463, "grad_norm": 1.519210696220398, "learning_rate": 2.7880089799956517e-05, "loss": 4.4294, "step": 8610 }, { "epoch": 0.46335557468790356, "grad_norm": 1.3507364988327026, "learning_rate": 2.78758916911059e-05, "loss": 4.3734, "step": 8611 }, { "epoch": 0.46340938441670254, "grad_norm": 0.9373726844787598, "learning_rate": 2.7871693500070028e-05, "loss": 4.5569, "step": 8612 }, { "epoch": 0.4634631941455015, "grad_norm": 2.1588151454925537, "learning_rate": 2.786749522696889e-05, "loss": 4.5852, "step": 8613 }, { "epoch": 0.46351700387430045, "grad_norm": 2.5428054332733154, "learning_rate": 2.7863296871922438e-05, "loss": 3.6894, "step": 8614 }, { "epoch": 0.46357081360309943, "grad_norm": 2.2975080013275146, "learning_rate": 2.7859098435050667e-05, "loss": 4.1202, "step": 8615 }, { "epoch": 0.4636246233318984, "grad_norm": 2.4698965549468994, "learning_rate": 2.785489991647356e-05, "loss": 4.1858, "step": 8616 }, { "epoch": 0.4636784330606974, "grad_norm": 2.5113608837127686, "learning_rate": 2.7850701316311078e-05, "loss": 4.3454, "step": 8617 }, { "epoch": 0.4637322427894963, "grad_norm": 4.22238826751709, "learning_rate": 2.784650263468323e-05, "loss": 4.2823, "step": 8618 }, { "epoch": 0.4637860525182953, "grad_norm": 1.145476222038269, "learning_rate": 2.7842303871709996e-05, "loss": 4.4118, "step": 8619 }, { "epoch": 0.4638398622470943, "grad_norm": 1.7696282863616943, "learning_rate": 2.7838105027511356e-05, "loss": 4.4819, "step": 8620 }, { "epoch": 0.46389367197589326, "grad_norm": 3.2127492427825928, "learning_rate": 2.7833906102207306e-05, "loss": 3.9562, "step": 8621 }, { "epoch": 0.4639474817046922, "grad_norm": 1.5273092985153198, "learning_rate": 2.782970709591785e-05, "loss": 4.6299, "step": 8622 }, { "epoch": 0.46400129143349117, "grad_norm": 1.301396131515503, "learning_rate": 2.7825508008762974e-05, "loss": 4.6791, "step": 8623 }, { "epoch": 0.46405510116229015, "grad_norm": 1.7588169574737549, "learning_rate": 2.7821308840862674e-05, "loss": 4.4147, "step": 8624 }, { "epoch": 0.46410891089108913, "grad_norm": 1.5951902866363525, "learning_rate": 2.7817109592336953e-05, "loss": 4.5441, "step": 8625 }, { "epoch": 0.46416272061988806, "grad_norm": 2.568070888519287, "learning_rate": 2.7812910263305826e-05, "loss": 4.3514, "step": 8626 }, { "epoch": 0.46421653034868704, "grad_norm": 1.6870146989822388, "learning_rate": 2.780871085388929e-05, "loss": 4.5625, "step": 8627 }, { "epoch": 0.464270340077486, "grad_norm": 2.2483818531036377, "learning_rate": 2.7804511364207343e-05, "loss": 4.2529, "step": 8628 }, { "epoch": 0.464324149806285, "grad_norm": 2.8941707611083984, "learning_rate": 2.7800311794380013e-05, "loss": 4.0202, "step": 8629 }, { "epoch": 0.46437795953508393, "grad_norm": 2.010327100753784, "learning_rate": 2.7796112144527296e-05, "loss": 4.1475, "step": 8630 }, { "epoch": 0.4644317692638829, "grad_norm": 2.108072519302368, "learning_rate": 2.7791912414769222e-05, "loss": 4.2292, "step": 8631 }, { "epoch": 0.4644855789926819, "grad_norm": 2.330850839614868, "learning_rate": 2.7787712605225798e-05, "loss": 4.1487, "step": 8632 }, { "epoch": 0.4645393887214808, "grad_norm": 2.969071626663208, "learning_rate": 2.778351271601704e-05, "loss": 3.7068, "step": 8633 }, { "epoch": 0.4645931984502798, "grad_norm": 1.821309208869934, "learning_rate": 2.7779312747262986e-05, "loss": 4.4916, "step": 8634 }, { "epoch": 0.4646470081790788, "grad_norm": 1.4814249277114868, "learning_rate": 2.7775112699083638e-05, "loss": 4.2816, "step": 8635 }, { "epoch": 0.46470081790787776, "grad_norm": 2.4963276386260986, "learning_rate": 2.777091257159904e-05, "loss": 3.969, "step": 8636 }, { "epoch": 0.4647546276366767, "grad_norm": 1.493788480758667, "learning_rate": 2.7766712364929216e-05, "loss": 4.6907, "step": 8637 }, { "epoch": 0.46480843736547567, "grad_norm": 1.7609856128692627, "learning_rate": 2.7762512079194193e-05, "loss": 4.1883, "step": 8638 }, { "epoch": 0.46486224709427465, "grad_norm": 2.263157367706299, "learning_rate": 2.7758311714514e-05, "loss": 4.9192, "step": 8639 }, { "epoch": 0.46491605682307363, "grad_norm": 1.6323257684707642, "learning_rate": 2.7754111271008682e-05, "loss": 3.8592, "step": 8640 }, { "epoch": 0.46496986655187256, "grad_norm": 1.9086099863052368, "learning_rate": 2.7749910748798265e-05, "loss": 4.3862, "step": 8641 }, { "epoch": 0.46502367628067154, "grad_norm": 2.3557937145233154, "learning_rate": 2.7745710148002807e-05, "loss": 4.3777, "step": 8642 }, { "epoch": 0.4650774860094705, "grad_norm": 2.334108591079712, "learning_rate": 2.7741509468742327e-05, "loss": 4.0273, "step": 8643 }, { "epoch": 0.4651312957382695, "grad_norm": 2.6633198261260986, "learning_rate": 2.7737308711136883e-05, "loss": 4.364, "step": 8644 }, { "epoch": 0.4651851054670684, "grad_norm": 1.6796382665634155, "learning_rate": 2.773310787530652e-05, "loss": 4.4257, "step": 8645 }, { "epoch": 0.4652389151958674, "grad_norm": 2.54911208152771, "learning_rate": 2.7728906961371287e-05, "loss": 3.6941, "step": 8646 }, { "epoch": 0.4652927249246664, "grad_norm": 2.5158815383911133, "learning_rate": 2.772470596945123e-05, "loss": 4.1283, "step": 8647 }, { "epoch": 0.46534653465346537, "grad_norm": 3.2248611450195312, "learning_rate": 2.77205048996664e-05, "loss": 3.511, "step": 8648 }, { "epoch": 0.4654003443822643, "grad_norm": 2.0714495182037354, "learning_rate": 2.7716303752136864e-05, "loss": 4.8452, "step": 8649 }, { "epoch": 0.4654541541110633, "grad_norm": 1.7282077074050903, "learning_rate": 2.7712102526982674e-05, "loss": 4.2401, "step": 8650 }, { "epoch": 0.46550796383986226, "grad_norm": 2.533140182495117, "learning_rate": 2.7707901224323885e-05, "loss": 3.769, "step": 8651 }, { "epoch": 0.46556177356866124, "grad_norm": 2.083601236343384, "learning_rate": 2.7703699844280562e-05, "loss": 4.1627, "step": 8652 }, { "epoch": 0.46561558329746017, "grad_norm": 1.6926124095916748, "learning_rate": 2.769949838697277e-05, "loss": 4.8737, "step": 8653 }, { "epoch": 0.46566939302625915, "grad_norm": 2.390904426574707, "learning_rate": 2.769529685252058e-05, "loss": 3.2706, "step": 8654 }, { "epoch": 0.46572320275505813, "grad_norm": 2.1223666667938232, "learning_rate": 2.769109524104405e-05, "loss": 4.5603, "step": 8655 }, { "epoch": 0.46577701248385706, "grad_norm": 2.039243221282959, "learning_rate": 2.7686893552663257e-05, "loss": 4.0485, "step": 8656 }, { "epoch": 0.46583082221265604, "grad_norm": 2.6374683380126953, "learning_rate": 2.7682691787498278e-05, "loss": 3.8689, "step": 8657 }, { "epoch": 0.465884631941455, "grad_norm": 2.3489925861358643, "learning_rate": 2.7678489945669178e-05, "loss": 4.1447, "step": 8658 }, { "epoch": 0.465938441670254, "grad_norm": 1.6594698429107666, "learning_rate": 2.7674288027296037e-05, "loss": 4.0493, "step": 8659 }, { "epoch": 0.4659922513990529, "grad_norm": 2.4676036834716797, "learning_rate": 2.7670086032498943e-05, "loss": 3.9544, "step": 8660 }, { "epoch": 0.4660460611278519, "grad_norm": 2.330049753189087, "learning_rate": 2.766588396139797e-05, "loss": 4.1918, "step": 8661 }, { "epoch": 0.4660998708566509, "grad_norm": 1.3275715112686157, "learning_rate": 2.7661681814113206e-05, "loss": 4.1029, "step": 8662 }, { "epoch": 0.46615368058544987, "grad_norm": 1.4020602703094482, "learning_rate": 2.7657479590764728e-05, "loss": 4.2724, "step": 8663 }, { "epoch": 0.4662074903142488, "grad_norm": 2.746657371520996, "learning_rate": 2.7653277291472635e-05, "loss": 4.4293, "step": 8664 }, { "epoch": 0.4662613000430478, "grad_norm": 2.5295486450195312, "learning_rate": 2.7649074916357022e-05, "loss": 4.7463, "step": 8665 }, { "epoch": 0.46631510977184676, "grad_norm": 2.9303677082061768, "learning_rate": 2.7644872465537958e-05, "loss": 4.2085, "step": 8666 }, { "epoch": 0.46636891950064574, "grad_norm": 1.5853031873703003, "learning_rate": 2.764066993913556e-05, "loss": 4.5429, "step": 8667 }, { "epoch": 0.46642272922944467, "grad_norm": 1.478366732597351, "learning_rate": 2.7636467337269917e-05, "loss": 4.5093, "step": 8668 }, { "epoch": 0.46647653895824365, "grad_norm": 1.305909514427185, "learning_rate": 2.763226466006113e-05, "loss": 4.4612, "step": 8669 }, { "epoch": 0.46653034868704263, "grad_norm": 2.16357421875, "learning_rate": 2.76280619076293e-05, "loss": 4.321, "step": 8670 }, { "epoch": 0.4665841584158416, "grad_norm": 3.0512428283691406, "learning_rate": 2.7623859080094527e-05, "loss": 3.7897, "step": 8671 }, { "epoch": 0.46663796814464054, "grad_norm": 1.9353514909744263, "learning_rate": 2.7619656177576912e-05, "loss": 4.4033, "step": 8672 }, { "epoch": 0.4666917778734395, "grad_norm": 3.1783814430236816, "learning_rate": 2.7615453200196588e-05, "loss": 4.1083, "step": 8673 }, { "epoch": 0.4667455876022385, "grad_norm": 2.892932415008545, "learning_rate": 2.7611250148073632e-05, "loss": 4.0561, "step": 8674 }, { "epoch": 0.4667993973310374, "grad_norm": 1.7871428728103638, "learning_rate": 2.7607047021328168e-05, "loss": 4.1696, "step": 8675 }, { "epoch": 0.4668532070598364, "grad_norm": 1.7572530508041382, "learning_rate": 2.7602843820080322e-05, "loss": 4.4828, "step": 8676 }, { "epoch": 0.4669070167886354, "grad_norm": 1.2963913679122925, "learning_rate": 2.7598640544450193e-05, "loss": 4.2501, "step": 8677 }, { "epoch": 0.46696082651743437, "grad_norm": 1.4722647666931152, "learning_rate": 2.7594437194557914e-05, "loss": 4.2435, "step": 8678 }, { "epoch": 0.4670146362462333, "grad_norm": 2.590419054031372, "learning_rate": 2.7590233770523588e-05, "loss": 3.5706, "step": 8679 }, { "epoch": 0.4670684459750323, "grad_norm": 1.7050925493240356, "learning_rate": 2.758603027246736e-05, "loss": 4.5283, "step": 8680 }, { "epoch": 0.46712225570383126, "grad_norm": 2.3601794242858887, "learning_rate": 2.7581826700509338e-05, "loss": 3.9324, "step": 8681 }, { "epoch": 0.46717606543263024, "grad_norm": 1.8175954818725586, "learning_rate": 2.7577623054769646e-05, "loss": 4.7324, "step": 8682 }, { "epoch": 0.46722987516142916, "grad_norm": 2.1511287689208984, "learning_rate": 2.757341933536843e-05, "loss": 4.2301, "step": 8683 }, { "epoch": 0.46728368489022815, "grad_norm": 2.014885663986206, "learning_rate": 2.7569215542425803e-05, "loss": 4.3909, "step": 8684 }, { "epoch": 0.4673374946190271, "grad_norm": 2.1818971633911133, "learning_rate": 2.7565011676061913e-05, "loss": 4.4361, "step": 8685 }, { "epoch": 0.4673913043478261, "grad_norm": 2.253781318664551, "learning_rate": 2.7560807736396886e-05, "loss": 4.7916, "step": 8686 }, { "epoch": 0.46744511407662503, "grad_norm": 2.400521755218506, "learning_rate": 2.7556603723550856e-05, "loss": 4.169, "step": 8687 }, { "epoch": 0.467498923805424, "grad_norm": 3.0996899604797363, "learning_rate": 2.7552399637643978e-05, "loss": 3.9313, "step": 8688 }, { "epoch": 0.467552733534223, "grad_norm": 1.9808140993118286, "learning_rate": 2.754819547879638e-05, "loss": 4.2962, "step": 8689 }, { "epoch": 0.467606543263022, "grad_norm": 1.2560735940933228, "learning_rate": 2.7543991247128203e-05, "loss": 4.5381, "step": 8690 }, { "epoch": 0.4676603529918209, "grad_norm": 1.9089752435684204, "learning_rate": 2.7539786942759605e-05, "loss": 4.4874, "step": 8691 }, { "epoch": 0.4677141627206199, "grad_norm": 1.4547412395477295, "learning_rate": 2.7535582565810726e-05, "loss": 4.0751, "step": 8692 }, { "epoch": 0.46776797244941887, "grad_norm": 1.1838741302490234, "learning_rate": 2.7531378116401712e-05, "loss": 4.5853, "step": 8693 }, { "epoch": 0.46782178217821785, "grad_norm": 1.5956717729568481, "learning_rate": 2.7527173594652727e-05, "loss": 4.4337, "step": 8694 }, { "epoch": 0.4678755919070168, "grad_norm": 1.835646152496338, "learning_rate": 2.7522969000683914e-05, "loss": 4.1586, "step": 8695 }, { "epoch": 0.46792940163581576, "grad_norm": 1.3358982801437378, "learning_rate": 2.751876433461544e-05, "loss": 4.8471, "step": 8696 }, { "epoch": 0.46798321136461474, "grad_norm": 1.9933840036392212, "learning_rate": 2.7514559596567446e-05, "loss": 4.0918, "step": 8697 }, { "epoch": 0.46803702109341366, "grad_norm": 1.7981743812561035, "learning_rate": 2.751035478666011e-05, "loss": 4.492, "step": 8698 }, { "epoch": 0.46809083082221264, "grad_norm": 1.3966203927993774, "learning_rate": 2.7506149905013584e-05, "loss": 4.5313, "step": 8699 }, { "epoch": 0.4681446405510116, "grad_norm": 2.074612855911255, "learning_rate": 2.750194495174803e-05, "loss": 4.0413, "step": 8700 }, { "epoch": 0.4681984502798106, "grad_norm": 1.169783592224121, "learning_rate": 2.7497739926983624e-05, "loss": 4.1383, "step": 8701 }, { "epoch": 0.46825226000860953, "grad_norm": 1.8367290496826172, "learning_rate": 2.7493534830840527e-05, "loss": 4.1444, "step": 8702 }, { "epoch": 0.4683060697374085, "grad_norm": 1.3707963228225708, "learning_rate": 2.7489329663438912e-05, "loss": 4.3631, "step": 8703 }, { "epoch": 0.4683598794662075, "grad_norm": 1.6088683605194092, "learning_rate": 2.748512442489895e-05, "loss": 3.8921, "step": 8704 }, { "epoch": 0.4684136891950065, "grad_norm": 1.1336003541946411, "learning_rate": 2.7480919115340814e-05, "loss": 4.5862, "step": 8705 }, { "epoch": 0.4684674989238054, "grad_norm": 2.5595009326934814, "learning_rate": 2.7476713734884683e-05, "loss": 4.3062, "step": 8706 }, { "epoch": 0.4685213086526044, "grad_norm": 2.5800113677978516, "learning_rate": 2.7472508283650738e-05, "loss": 4.1826, "step": 8707 }, { "epoch": 0.46857511838140337, "grad_norm": 1.654699444770813, "learning_rate": 2.7468302761759157e-05, "loss": 4.2671, "step": 8708 }, { "epoch": 0.46862892811020235, "grad_norm": 1.6924115419387817, "learning_rate": 2.746409716933012e-05, "loss": 4.437, "step": 8709 }, { "epoch": 0.4686827378390013, "grad_norm": 2.338782787322998, "learning_rate": 2.7459891506483808e-05, "loss": 4.2826, "step": 8710 }, { "epoch": 0.46873654756780025, "grad_norm": 1.7199434041976929, "learning_rate": 2.7455685773340428e-05, "loss": 4.3815, "step": 8711 }, { "epoch": 0.46879035729659924, "grad_norm": 2.096041679382324, "learning_rate": 2.7451479970020145e-05, "loss": 3.5496, "step": 8712 }, { "epoch": 0.4688441670253982, "grad_norm": 1.733934760093689, "learning_rate": 2.7447274096643155e-05, "loss": 4.4637, "step": 8713 }, { "epoch": 0.46889797675419714, "grad_norm": 2.0473179817199707, "learning_rate": 2.7443068153329654e-05, "loss": 4.0736, "step": 8714 }, { "epoch": 0.4689517864829961, "grad_norm": 2.2698440551757812, "learning_rate": 2.7438862140199845e-05, "loss": 3.2741, "step": 8715 }, { "epoch": 0.4690055962117951, "grad_norm": 2.6867709159851074, "learning_rate": 2.743465605737391e-05, "loss": 3.7827, "step": 8716 }, { "epoch": 0.46905940594059403, "grad_norm": 2.8106436729431152, "learning_rate": 2.743044990497205e-05, "loss": 4.4138, "step": 8717 }, { "epoch": 0.469113215669393, "grad_norm": 1.5865837335586548, "learning_rate": 2.7426243683114473e-05, "loss": 4.8308, "step": 8718 }, { "epoch": 0.469167025398192, "grad_norm": 2.2707016468048096, "learning_rate": 2.742203739192138e-05, "loss": 4.0662, "step": 8719 }, { "epoch": 0.469220835126991, "grad_norm": 1.993377923965454, "learning_rate": 2.7417831031512965e-05, "loss": 4.5256, "step": 8720 }, { "epoch": 0.4692746448557899, "grad_norm": 1.2479324340820312, "learning_rate": 2.7413624602009447e-05, "loss": 4.2457, "step": 8721 }, { "epoch": 0.4693284545845889, "grad_norm": 1.7971160411834717, "learning_rate": 2.7409418103531033e-05, "loss": 4.6394, "step": 8722 }, { "epoch": 0.46938226431338786, "grad_norm": 3.080897808074951, "learning_rate": 2.7405211536197924e-05, "loss": 4.358, "step": 8723 }, { "epoch": 0.46943607404218685, "grad_norm": 2.909428834915161, "learning_rate": 2.740100490013034e-05, "loss": 4.0618, "step": 8724 }, { "epoch": 0.46948988377098577, "grad_norm": 1.7571817636489868, "learning_rate": 2.73967981954485e-05, "loss": 4.3921, "step": 8725 }, { "epoch": 0.46954369349978475, "grad_norm": 2.685241937637329, "learning_rate": 2.7392591422272607e-05, "loss": 3.448, "step": 8726 }, { "epoch": 0.46959750322858373, "grad_norm": 1.6343995332717896, "learning_rate": 2.7388384580722888e-05, "loss": 4.3306, "step": 8727 }, { "epoch": 0.4696513129573827, "grad_norm": 1.7505539655685425, "learning_rate": 2.738417767091956e-05, "loss": 4.3611, "step": 8728 }, { "epoch": 0.46970512268618164, "grad_norm": 2.3072779178619385, "learning_rate": 2.737997069298285e-05, "loss": 4.5795, "step": 8729 }, { "epoch": 0.4697589324149806, "grad_norm": 1.2715579271316528, "learning_rate": 2.7375763647032983e-05, "loss": 4.4846, "step": 8730 }, { "epoch": 0.4698127421437796, "grad_norm": 1.6128528118133545, "learning_rate": 2.7371556533190168e-05, "loss": 4.4305, "step": 8731 }, { "epoch": 0.4698665518725786, "grad_norm": 2.2767815589904785, "learning_rate": 2.7367349351574657e-05, "loss": 3.4687, "step": 8732 }, { "epoch": 0.4699203616013775, "grad_norm": 1.9033067226409912, "learning_rate": 2.7363142102306666e-05, "loss": 4.4956, "step": 8733 }, { "epoch": 0.4699741713301765, "grad_norm": 2.7578682899475098, "learning_rate": 2.735893478550643e-05, "loss": 3.7562, "step": 8734 }, { "epoch": 0.4700279810589755, "grad_norm": 2.2400104999542236, "learning_rate": 2.7354727401294183e-05, "loss": 4.0904, "step": 8735 }, { "epoch": 0.47008179078777446, "grad_norm": 2.8680412769317627, "learning_rate": 2.7350519949790153e-05, "loss": 3.6675, "step": 8736 }, { "epoch": 0.4701356005165734, "grad_norm": 2.1897451877593994, "learning_rate": 2.7346312431114595e-05, "loss": 4.3868, "step": 8737 }, { "epoch": 0.47018941024537236, "grad_norm": 2.51904296875, "learning_rate": 2.7342104845387733e-05, "loss": 4.0203, "step": 8738 }, { "epoch": 0.47024321997417134, "grad_norm": 2.3619637489318848, "learning_rate": 2.733789719272982e-05, "loss": 4.3114, "step": 8739 }, { "epoch": 0.47029702970297027, "grad_norm": 2.9902477264404297, "learning_rate": 2.733368947326109e-05, "loss": 4.2744, "step": 8740 }, { "epoch": 0.47035083943176925, "grad_norm": 2.187154531478882, "learning_rate": 2.7329481687101795e-05, "loss": 4.3579, "step": 8741 }, { "epoch": 0.47040464916056823, "grad_norm": 2.462338924407959, "learning_rate": 2.7325273834372173e-05, "loss": 4.5435, "step": 8742 }, { "epoch": 0.4704584588893672, "grad_norm": 1.3828516006469727, "learning_rate": 2.7321065915192485e-05, "loss": 4.2583, "step": 8743 }, { "epoch": 0.47051226861816614, "grad_norm": 2.4266910552978516, "learning_rate": 2.7316857929682965e-05, "loss": 3.6519, "step": 8744 }, { "epoch": 0.4705660783469651, "grad_norm": 1.987865686416626, "learning_rate": 2.731264987796389e-05, "loss": 4.33, "step": 8745 }, { "epoch": 0.4706198880757641, "grad_norm": 1.6485595703125, "learning_rate": 2.7308441760155495e-05, "loss": 4.7186, "step": 8746 }, { "epoch": 0.4706736978045631, "grad_norm": 1.506515622138977, "learning_rate": 2.7304233576378045e-05, "loss": 4.9947, "step": 8747 }, { "epoch": 0.470727507533362, "grad_norm": 1.8171364068984985, "learning_rate": 2.73000253267518e-05, "loss": 4.2944, "step": 8748 }, { "epoch": 0.470781317262161, "grad_norm": 3.027620315551758, "learning_rate": 2.729581701139701e-05, "loss": 3.7131, "step": 8749 }, { "epoch": 0.47083512699096, "grad_norm": 2.520235061645508, "learning_rate": 2.729160863043395e-05, "loss": 4.3789, "step": 8750 }, { "epoch": 0.47088893671975895, "grad_norm": 2.460829019546509, "learning_rate": 2.7287400183982877e-05, "loss": 3.842, "step": 8751 }, { "epoch": 0.4709427464485579, "grad_norm": 2.7734804153442383, "learning_rate": 2.728319167216406e-05, "loss": 3.8867, "step": 8752 }, { "epoch": 0.47099655617735686, "grad_norm": 1.6889503002166748, "learning_rate": 2.7278983095097772e-05, "loss": 4.1656, "step": 8753 }, { "epoch": 0.47105036590615584, "grad_norm": 2.3748621940612793, "learning_rate": 2.7274774452904265e-05, "loss": 4.2018, "step": 8754 }, { "epoch": 0.4711041756349548, "grad_norm": 2.271610736846924, "learning_rate": 2.727056574570383e-05, "loss": 4.4181, "step": 8755 }, { "epoch": 0.47115798536375375, "grad_norm": 2.0530331134796143, "learning_rate": 2.7266356973616736e-05, "loss": 4.3174, "step": 8756 }, { "epoch": 0.47121179509255273, "grad_norm": 1.1946898698806763, "learning_rate": 2.726214813676325e-05, "loss": 4.3198, "step": 8757 }, { "epoch": 0.4712656048213517, "grad_norm": 1.060631513595581, "learning_rate": 2.7257939235263657e-05, "loss": 4.3388, "step": 8758 }, { "epoch": 0.4713194145501507, "grad_norm": 2.762061357498169, "learning_rate": 2.725373026923823e-05, "loss": 4.2887, "step": 8759 }, { "epoch": 0.4713732242789496, "grad_norm": 2.53891658782959, "learning_rate": 2.7249521238807256e-05, "loss": 4.4636, "step": 8760 }, { "epoch": 0.4714270340077486, "grad_norm": 2.0335516929626465, "learning_rate": 2.7245312144091022e-05, "loss": 4.4166, "step": 8761 }, { "epoch": 0.4714808437365476, "grad_norm": 2.651282548904419, "learning_rate": 2.72411029852098e-05, "loss": 3.6725, "step": 8762 }, { "epoch": 0.4715346534653465, "grad_norm": 2.3714799880981445, "learning_rate": 2.7236893762283883e-05, "loss": 4.349, "step": 8763 }, { "epoch": 0.4715884631941455, "grad_norm": 1.8859678506851196, "learning_rate": 2.7232684475433556e-05, "loss": 3.9533, "step": 8764 }, { "epoch": 0.47164227292294447, "grad_norm": 2.531278133392334, "learning_rate": 2.7228475124779117e-05, "loss": 3.7635, "step": 8765 }, { "epoch": 0.47169608265174345, "grad_norm": 2.201986312866211, "learning_rate": 2.722426571044085e-05, "loss": 3.5671, "step": 8766 }, { "epoch": 0.4717498923805424, "grad_norm": 3.3433151245117188, "learning_rate": 2.722005623253905e-05, "loss": 2.6942, "step": 8767 }, { "epoch": 0.47180370210934136, "grad_norm": 1.410282015800476, "learning_rate": 2.721584669119402e-05, "loss": 4.5106, "step": 8768 }, { "epoch": 0.47185751183814034, "grad_norm": 1.8639169931411743, "learning_rate": 2.7211637086526042e-05, "loss": 3.7027, "step": 8769 }, { "epoch": 0.4719113215669393, "grad_norm": 2.1475870609283447, "learning_rate": 2.7207427418655433e-05, "loss": 4.4053, "step": 8770 }, { "epoch": 0.47196513129573825, "grad_norm": 1.9064337015151978, "learning_rate": 2.7203217687702483e-05, "loss": 4.4828, "step": 8771 }, { "epoch": 0.47201894102453723, "grad_norm": 1.1769851446151733, "learning_rate": 2.71990078937875e-05, "loss": 4.4453, "step": 8772 }, { "epoch": 0.4720727507533362, "grad_norm": 1.2297314405441284, "learning_rate": 2.7194798037030783e-05, "loss": 4.2368, "step": 8773 }, { "epoch": 0.4721265604821352, "grad_norm": 2.5194284915924072, "learning_rate": 2.719058811755264e-05, "loss": 3.915, "step": 8774 }, { "epoch": 0.4721803702109341, "grad_norm": 2.5228524208068848, "learning_rate": 2.718637813547338e-05, "loss": 4.2111, "step": 8775 }, { "epoch": 0.4722341799397331, "grad_norm": 2.304041862487793, "learning_rate": 2.7182168090913325e-05, "loss": 4.2843, "step": 8776 }, { "epoch": 0.4722879896685321, "grad_norm": 3.6153512001037598, "learning_rate": 2.717795798399276e-05, "loss": 3.0706, "step": 8777 }, { "epoch": 0.47234179939733106, "grad_norm": 2.945082902908325, "learning_rate": 2.7173747814832016e-05, "loss": 4.2453, "step": 8778 }, { "epoch": 0.47239560912613, "grad_norm": 2.8073806762695312, "learning_rate": 2.7169537583551412e-05, "loss": 4.0689, "step": 8779 }, { "epoch": 0.47244941885492897, "grad_norm": 1.6636749505996704, "learning_rate": 2.716532729027126e-05, "loss": 4.3601, "step": 8780 }, { "epoch": 0.47250322858372795, "grad_norm": 2.228118896484375, "learning_rate": 2.7161116935111875e-05, "loss": 4.0007, "step": 8781 }, { "epoch": 0.4725570383125269, "grad_norm": 1.6157194375991821, "learning_rate": 2.7156906518193582e-05, "loss": 4.6694, "step": 8782 }, { "epoch": 0.47261084804132586, "grad_norm": 4.232249736785889, "learning_rate": 2.7152696039636704e-05, "loss": 3.0803, "step": 8783 }, { "epoch": 0.47266465777012484, "grad_norm": 2.270515203475952, "learning_rate": 2.714848549956156e-05, "loss": 4.4495, "step": 8784 }, { "epoch": 0.4727184674989238, "grad_norm": 1.7524951696395874, "learning_rate": 2.7144274898088477e-05, "loss": 4.6987, "step": 8785 }, { "epoch": 0.47277227722772275, "grad_norm": 3.095374584197998, "learning_rate": 2.7140064235337787e-05, "loss": 4.3417, "step": 8786 }, { "epoch": 0.47282608695652173, "grad_norm": 2.58149790763855, "learning_rate": 2.713585351142982e-05, "loss": 4.1011, "step": 8787 }, { "epoch": 0.4728798966853207, "grad_norm": 1.9266468286514282, "learning_rate": 2.7131642726484903e-05, "loss": 4.4264, "step": 8788 }, { "epoch": 0.4729337064141197, "grad_norm": 1.8456079959869385, "learning_rate": 2.7127431880623372e-05, "loss": 4.5578, "step": 8789 }, { "epoch": 0.4729875161429186, "grad_norm": 2.425028085708618, "learning_rate": 2.712322097396555e-05, "loss": 4.0354, "step": 8790 }, { "epoch": 0.4730413258717176, "grad_norm": 1.525771975517273, "learning_rate": 2.71190100066318e-05, "loss": 3.8391, "step": 8791 }, { "epoch": 0.4730951356005166, "grad_norm": 2.1385374069213867, "learning_rate": 2.7114798978742435e-05, "loss": 4.2649, "step": 8792 }, { "epoch": 0.47314894532931556, "grad_norm": 2.1233391761779785, "learning_rate": 2.71105878904178e-05, "loss": 4.3044, "step": 8793 }, { "epoch": 0.4732027550581145, "grad_norm": 1.927225112915039, "learning_rate": 2.7106376741778237e-05, "loss": 4.4541, "step": 8794 }, { "epoch": 0.47325656478691347, "grad_norm": 2.897277355194092, "learning_rate": 2.71021655329441e-05, "loss": 3.896, "step": 8795 }, { "epoch": 0.47331037451571245, "grad_norm": 3.466534376144409, "learning_rate": 2.709795426403573e-05, "loss": 3.7231, "step": 8796 }, { "epoch": 0.47336418424451143, "grad_norm": 1.393762230873108, "learning_rate": 2.709374293517346e-05, "loss": 4.6038, "step": 8797 }, { "epoch": 0.47341799397331036, "grad_norm": 2.6899068355560303, "learning_rate": 2.7089531546477648e-05, "loss": 3.3111, "step": 8798 }, { "epoch": 0.47347180370210934, "grad_norm": 2.239222526550293, "learning_rate": 2.7085320098068656e-05, "loss": 3.9874, "step": 8799 }, { "epoch": 0.4735256134309083, "grad_norm": 1.7442318201065063, "learning_rate": 2.7081108590066816e-05, "loss": 3.9897, "step": 8800 }, { "epoch": 0.4735794231597073, "grad_norm": 2.95512318611145, "learning_rate": 2.707689702259249e-05, "loss": 4.4572, "step": 8801 }, { "epoch": 0.47363323288850623, "grad_norm": 2.872551679611206, "learning_rate": 2.7072685395766036e-05, "loss": 3.9706, "step": 8802 }, { "epoch": 0.4736870426173052, "grad_norm": 2.395432472229004, "learning_rate": 2.7068473709707808e-05, "loss": 5.0447, "step": 8803 }, { "epoch": 0.4737408523461042, "grad_norm": 3.4431681632995605, "learning_rate": 2.7064261964538163e-05, "loss": 3.9421, "step": 8804 }, { "epoch": 0.4737946620749031, "grad_norm": 1.2236592769622803, "learning_rate": 2.7060050160377464e-05, "loss": 4.5032, "step": 8805 }, { "epoch": 0.4738484718037021, "grad_norm": 1.8501428365707397, "learning_rate": 2.7055838297346074e-05, "loss": 4.4863, "step": 8806 }, { "epoch": 0.4739022815325011, "grad_norm": 1.0415695905685425, "learning_rate": 2.705162637556436e-05, "loss": 4.4379, "step": 8807 }, { "epoch": 0.47395609126130006, "grad_norm": 1.4623234272003174, "learning_rate": 2.704741439515267e-05, "loss": 4.8419, "step": 8808 }, { "epoch": 0.474009900990099, "grad_norm": 1.818769097328186, "learning_rate": 2.704320235623139e-05, "loss": 4.5147, "step": 8809 }, { "epoch": 0.47406371071889797, "grad_norm": 1.7802180051803589, "learning_rate": 2.703899025892088e-05, "loss": 4.0743, "step": 8810 }, { "epoch": 0.47411752044769695, "grad_norm": 3.4713313579559326, "learning_rate": 2.7034778103341517e-05, "loss": 4.0477, "step": 8811 }, { "epoch": 0.47417133017649593, "grad_norm": 1.8875725269317627, "learning_rate": 2.703056588961367e-05, "loss": 4.935, "step": 8812 }, { "epoch": 0.47422513990529486, "grad_norm": 1.3957703113555908, "learning_rate": 2.7026353617857698e-05, "loss": 4.3118, "step": 8813 }, { "epoch": 0.47427894963409384, "grad_norm": 1.4909400939941406, "learning_rate": 2.7022141288194008e-05, "loss": 4.7899, "step": 8814 }, { "epoch": 0.4743327593628928, "grad_norm": 1.437402606010437, "learning_rate": 2.701792890074295e-05, "loss": 4.3885, "step": 8815 }, { "epoch": 0.4743865690916918, "grad_norm": 2.3319990634918213, "learning_rate": 2.7013716455624903e-05, "loss": 4.2256, "step": 8816 }, { "epoch": 0.4744403788204907, "grad_norm": 1.9267339706420898, "learning_rate": 2.700950395296027e-05, "loss": 4.0447, "step": 8817 }, { "epoch": 0.4744941885492897, "grad_norm": 2.3455426692962646, "learning_rate": 2.7005291392869415e-05, "loss": 4.6882, "step": 8818 }, { "epoch": 0.4745479982780887, "grad_norm": 1.5863542556762695, "learning_rate": 2.7001078775472725e-05, "loss": 4.6395, "step": 8819 }, { "epoch": 0.47460180800688767, "grad_norm": 1.367337942123413, "learning_rate": 2.699686610089058e-05, "loss": 4.4863, "step": 8820 }, { "epoch": 0.4746556177356866, "grad_norm": 2.634662389755249, "learning_rate": 2.699265336924338e-05, "loss": 4.4336, "step": 8821 }, { "epoch": 0.4747094274644856, "grad_norm": 1.4039043188095093, "learning_rate": 2.6988440580651507e-05, "loss": 4.8005, "step": 8822 }, { "epoch": 0.47476323719328456, "grad_norm": 2.397625684738159, "learning_rate": 2.6984227735235344e-05, "loss": 4.1029, "step": 8823 }, { "epoch": 0.4748170469220835, "grad_norm": 1.669076681137085, "learning_rate": 2.6980014833115296e-05, "loss": 4.6547, "step": 8824 }, { "epoch": 0.47487085665088247, "grad_norm": 3.184732675552368, "learning_rate": 2.6975801874411755e-05, "loss": 4.0802, "step": 8825 }, { "epoch": 0.47492466637968145, "grad_norm": 1.603007435798645, "learning_rate": 2.6971588859245094e-05, "loss": 3.9066, "step": 8826 }, { "epoch": 0.47497847610848043, "grad_norm": 2.555021286010742, "learning_rate": 2.696737578773574e-05, "loss": 3.8051, "step": 8827 }, { "epoch": 0.47503228583727936, "grad_norm": 1.7295101881027222, "learning_rate": 2.696316266000407e-05, "loss": 4.5251, "step": 8828 }, { "epoch": 0.47508609556607834, "grad_norm": 2.670224905014038, "learning_rate": 2.69589494761705e-05, "loss": 3.8538, "step": 8829 }, { "epoch": 0.4751399052948773, "grad_norm": 1.392958641052246, "learning_rate": 2.6954736236355416e-05, "loss": 4.6508, "step": 8830 }, { "epoch": 0.4751937150236763, "grad_norm": 1.1045353412628174, "learning_rate": 2.6950522940679225e-05, "loss": 4.6488, "step": 8831 }, { "epoch": 0.4752475247524752, "grad_norm": 2.6529948711395264, "learning_rate": 2.6946309589262337e-05, "loss": 3.8037, "step": 8832 }, { "epoch": 0.4753013344812742, "grad_norm": 1.5562407970428467, "learning_rate": 2.6942096182225162e-05, "loss": 4.3411, "step": 8833 }, { "epoch": 0.4753551442100732, "grad_norm": 1.8354333639144897, "learning_rate": 2.6937882719688095e-05, "loss": 3.9128, "step": 8834 }, { "epoch": 0.47540895393887217, "grad_norm": 1.9774467945098877, "learning_rate": 2.6933669201771557e-05, "loss": 4.4285, "step": 8835 }, { "epoch": 0.4754627636676711, "grad_norm": 1.5509215593338013, "learning_rate": 2.692945562859595e-05, "loss": 4.2561, "step": 8836 }, { "epoch": 0.4755165733964701, "grad_norm": 2.7632195949554443, "learning_rate": 2.6925242000281692e-05, "loss": 3.6347, "step": 8837 }, { "epoch": 0.47557038312526906, "grad_norm": 1.8694652318954468, "learning_rate": 2.6921028316949197e-05, "loss": 4.4119, "step": 8838 }, { "epoch": 0.47562419285406804, "grad_norm": 1.8408042192459106, "learning_rate": 2.6916814578718874e-05, "loss": 3.9264, "step": 8839 }, { "epoch": 0.47567800258286697, "grad_norm": 2.4305813312530518, "learning_rate": 2.691260078571115e-05, "loss": 4.3033, "step": 8840 }, { "epoch": 0.47573181231166595, "grad_norm": 1.3556337356567383, "learning_rate": 2.6908386938046444e-05, "loss": 4.3114, "step": 8841 }, { "epoch": 0.47578562204046493, "grad_norm": 2.7335641384124756, "learning_rate": 2.690417303584517e-05, "loss": 4.2562, "step": 8842 }, { "epoch": 0.4758394317692639, "grad_norm": 1.030324935913086, "learning_rate": 2.689995907922775e-05, "loss": 4.459, "step": 8843 }, { "epoch": 0.47589324149806284, "grad_norm": 2.1001036167144775, "learning_rate": 2.6895745068314604e-05, "loss": 3.8833, "step": 8844 }, { "epoch": 0.4759470512268618, "grad_norm": 2.3204336166381836, "learning_rate": 2.689153100322618e-05, "loss": 4.7416, "step": 8845 }, { "epoch": 0.4760008609556608, "grad_norm": 2.6066346168518066, "learning_rate": 2.6887316884082876e-05, "loss": 4.716, "step": 8846 }, { "epoch": 0.4760546706844597, "grad_norm": 2.1628215312957764, "learning_rate": 2.688310271100513e-05, "loss": 4.0301, "step": 8847 }, { "epoch": 0.4761084804132587, "grad_norm": 1.316308856010437, "learning_rate": 2.6878888484113385e-05, "loss": 4.0411, "step": 8848 }, { "epoch": 0.4761622901420577, "grad_norm": 1.6149133443832397, "learning_rate": 2.6874674203528045e-05, "loss": 4.3808, "step": 8849 }, { "epoch": 0.47621609987085667, "grad_norm": 1.3027430772781372, "learning_rate": 2.687045986936957e-05, "loss": 4.3324, "step": 8850 }, { "epoch": 0.4762699095996556, "grad_norm": 2.7064318656921387, "learning_rate": 2.6866245481758378e-05, "loss": 3.9435, "step": 8851 }, { "epoch": 0.4763237193284546, "grad_norm": 2.448460817337036, "learning_rate": 2.6862031040814912e-05, "loss": 3.9313, "step": 8852 }, { "epoch": 0.47637752905725356, "grad_norm": 2.511183023452759, "learning_rate": 2.6857816546659603e-05, "loss": 3.8112, "step": 8853 }, { "epoch": 0.47643133878605254, "grad_norm": 1.2405811548233032, "learning_rate": 2.6853601999412893e-05, "loss": 4.6305, "step": 8854 }, { "epoch": 0.47648514851485146, "grad_norm": 2.2306718826293945, "learning_rate": 2.684938739919523e-05, "loss": 4.4406, "step": 8855 }, { "epoch": 0.47653895824365045, "grad_norm": 1.9212373495101929, "learning_rate": 2.684517274612705e-05, "loss": 4.4833, "step": 8856 }, { "epoch": 0.4765927679724494, "grad_norm": 2.742844581604004, "learning_rate": 2.6840958040328788e-05, "loss": 4.0859, "step": 8857 }, { "epoch": 0.4766465777012484, "grad_norm": 1.975253701210022, "learning_rate": 2.68367432819209e-05, "loss": 4.0347, "step": 8858 }, { "epoch": 0.47670038743004733, "grad_norm": 2.5817477703094482, "learning_rate": 2.6832528471023832e-05, "loss": 4.0004, "step": 8859 }, { "epoch": 0.4767541971588463, "grad_norm": 2.0763778686523438, "learning_rate": 2.6828313607758033e-05, "loss": 3.89, "step": 8860 }, { "epoch": 0.4768080068876453, "grad_norm": 2.3400959968566895, "learning_rate": 2.682409869224394e-05, "loss": 4.602, "step": 8861 }, { "epoch": 0.4768618166164443, "grad_norm": 2.47461199760437, "learning_rate": 2.6819883724602013e-05, "loss": 4.0258, "step": 8862 }, { "epoch": 0.4769156263452432, "grad_norm": 1.1453479528427124, "learning_rate": 2.6815668704952705e-05, "loss": 4.3675, "step": 8863 }, { "epoch": 0.4769694360740422, "grad_norm": 2.548715591430664, "learning_rate": 2.6811453633416476e-05, "loss": 4.4584, "step": 8864 }, { "epoch": 0.47702324580284117, "grad_norm": 2.313249111175537, "learning_rate": 2.6807238510113768e-05, "loss": 3.8249, "step": 8865 }, { "epoch": 0.4770770555316401, "grad_norm": 2.14168381690979, "learning_rate": 2.6803023335165046e-05, "loss": 4.0834, "step": 8866 }, { "epoch": 0.4771308652604391, "grad_norm": 2.434770107269287, "learning_rate": 2.679880810869077e-05, "loss": 4.3463, "step": 8867 }, { "epoch": 0.47718467498923806, "grad_norm": 0.9839892983436584, "learning_rate": 2.6794592830811393e-05, "loss": 4.586, "step": 8868 }, { "epoch": 0.47723848471803704, "grad_norm": 1.8826830387115479, "learning_rate": 2.679037750164738e-05, "loss": 4.2601, "step": 8869 }, { "epoch": 0.47729229444683596, "grad_norm": 1.8082205057144165, "learning_rate": 2.6786162121319184e-05, "loss": 4.5368, "step": 8870 }, { "epoch": 0.47734610417563494, "grad_norm": 1.9616270065307617, "learning_rate": 2.6781946689947297e-05, "loss": 4.1604, "step": 8871 }, { "epoch": 0.4773999139044339, "grad_norm": 3.1141090393066406, "learning_rate": 2.6777731207652157e-05, "loss": 3.1295, "step": 8872 }, { "epoch": 0.4774537236332329, "grad_norm": 1.7554234266281128, "learning_rate": 2.677351567455424e-05, "loss": 4.0307, "step": 8873 }, { "epoch": 0.47750753336203183, "grad_norm": 1.848936676979065, "learning_rate": 2.676930009077402e-05, "loss": 4.0694, "step": 8874 }, { "epoch": 0.4775613430908308, "grad_norm": 2.1452295780181885, "learning_rate": 2.6765084456431956e-05, "loss": 4.419, "step": 8875 }, { "epoch": 0.4776151528196298, "grad_norm": 2.957968235015869, "learning_rate": 2.676086877164853e-05, "loss": 3.5501, "step": 8876 }, { "epoch": 0.4776689625484288, "grad_norm": 2.481509208679199, "learning_rate": 2.675665303654421e-05, "loss": 3.3715, "step": 8877 }, { "epoch": 0.4777227722772277, "grad_norm": 1.0877814292907715, "learning_rate": 2.6752437251239465e-05, "loss": 4.5225, "step": 8878 }, { "epoch": 0.4777765820060267, "grad_norm": 2.009352684020996, "learning_rate": 2.6748221415854786e-05, "loss": 4.3493, "step": 8879 }, { "epoch": 0.47783039173482567, "grad_norm": 2.3370845317840576, "learning_rate": 2.6744005530510637e-05, "loss": 4.2944, "step": 8880 }, { "epoch": 0.47788420146362465, "grad_norm": 3.5538527965545654, "learning_rate": 2.6739789595327496e-05, "loss": 3.6404, "step": 8881 }, { "epoch": 0.4779380111924236, "grad_norm": 2.766450881958008, "learning_rate": 2.673557361042586e-05, "loss": 3.7934, "step": 8882 }, { "epoch": 0.47799182092122255, "grad_norm": 2.6055519580841064, "learning_rate": 2.6731357575926187e-05, "loss": 3.9946, "step": 8883 }, { "epoch": 0.47804563065002154, "grad_norm": 1.7619080543518066, "learning_rate": 2.6727141491948976e-05, "loss": 3.7426, "step": 8884 }, { "epoch": 0.4780994403788205, "grad_norm": 2.114851951599121, "learning_rate": 2.6722925358614705e-05, "loss": 4.2249, "step": 8885 }, { "epoch": 0.47815325010761944, "grad_norm": 1.4186975955963135, "learning_rate": 2.6718709176043862e-05, "loss": 4.3343, "step": 8886 }, { "epoch": 0.4782070598364184, "grad_norm": 2.521407127380371, "learning_rate": 2.671449294435694e-05, "loss": 3.9539, "step": 8887 }, { "epoch": 0.4782608695652174, "grad_norm": 1.0326018333435059, "learning_rate": 2.6710276663674406e-05, "loss": 4.4512, "step": 8888 }, { "epoch": 0.47831467929401633, "grad_norm": 2.0676791667938232, "learning_rate": 2.6706060334116777e-05, "loss": 3.9664, "step": 8889 }, { "epoch": 0.4783684890228153, "grad_norm": 1.5170319080352783, "learning_rate": 2.6701843955804527e-05, "loss": 4.0819, "step": 8890 }, { "epoch": 0.4784222987516143, "grad_norm": 2.280726909637451, "learning_rate": 2.669762752885816e-05, "loss": 4.1849, "step": 8891 }, { "epoch": 0.4784761084804133, "grad_norm": 1.6152304410934448, "learning_rate": 2.669341105339816e-05, "loss": 4.7563, "step": 8892 }, { "epoch": 0.4785299182092122, "grad_norm": 1.327933430671692, "learning_rate": 2.6689194529545024e-05, "loss": 4.0282, "step": 8893 }, { "epoch": 0.4785837279380112, "grad_norm": 1.9745454788208008, "learning_rate": 2.668497795741926e-05, "loss": 4.6059, "step": 8894 }, { "epoch": 0.47863753766681016, "grad_norm": 3.5234298706054688, "learning_rate": 2.6680761337141356e-05, "loss": 3.7599, "step": 8895 }, { "epoch": 0.47869134739560915, "grad_norm": 2.1937484741210938, "learning_rate": 2.6676544668831806e-05, "loss": 4.0669, "step": 8896 }, { "epoch": 0.47874515712440807, "grad_norm": 2.2557363510131836, "learning_rate": 2.6672327952611124e-05, "loss": 4.018, "step": 8897 }, { "epoch": 0.47879896685320705, "grad_norm": 2.347052812576294, "learning_rate": 2.666811118859981e-05, "loss": 4.342, "step": 8898 }, { "epoch": 0.47885277658200603, "grad_norm": 2.2389183044433594, "learning_rate": 2.6663894376918363e-05, "loss": 4.7394, "step": 8899 }, { "epoch": 0.478906586310805, "grad_norm": 1.5041102170944214, "learning_rate": 2.6659677517687288e-05, "loss": 4.3626, "step": 8900 }, { "epoch": 0.47896039603960394, "grad_norm": 1.6299307346343994, "learning_rate": 2.6655460611027088e-05, "loss": 4.1579, "step": 8901 }, { "epoch": 0.4790142057684029, "grad_norm": 1.5417070388793945, "learning_rate": 2.6651243657058295e-05, "loss": 4.6864, "step": 8902 }, { "epoch": 0.4790680154972019, "grad_norm": 1.7745859622955322, "learning_rate": 2.664702665590138e-05, "loss": 3.9381, "step": 8903 }, { "epoch": 0.4791218252260009, "grad_norm": 2.4883668422698975, "learning_rate": 2.6642809607676883e-05, "loss": 3.9193, "step": 8904 }, { "epoch": 0.4791756349547998, "grad_norm": 2.355463743209839, "learning_rate": 2.6638592512505302e-05, "loss": 3.7947, "step": 8905 }, { "epoch": 0.4792294446835988, "grad_norm": 1.3986870050430298, "learning_rate": 2.6634375370507158e-05, "loss": 4.6785, "step": 8906 }, { "epoch": 0.4792832544123978, "grad_norm": 1.6076886653900146, "learning_rate": 2.663015818180296e-05, "loss": 4.5207, "step": 8907 }, { "epoch": 0.47933706414119676, "grad_norm": 2.870551586151123, "learning_rate": 2.6625940946513228e-05, "loss": 3.4038, "step": 8908 }, { "epoch": 0.4793908738699957, "grad_norm": 1.528640866279602, "learning_rate": 2.662172366475847e-05, "loss": 4.4659, "step": 8909 }, { "epoch": 0.47944468359879466, "grad_norm": 1.489349603652954, "learning_rate": 2.6617506336659222e-05, "loss": 4.1272, "step": 8910 }, { "epoch": 0.47949849332759364, "grad_norm": 2.8947489261627197, "learning_rate": 2.661328896233598e-05, "loss": 3.306, "step": 8911 }, { "epoch": 0.47955230305639257, "grad_norm": 2.8859479427337646, "learning_rate": 2.660907154190929e-05, "loss": 4.0541, "step": 8912 }, { "epoch": 0.47960611278519155, "grad_norm": 2.024365186691284, "learning_rate": 2.6604854075499663e-05, "loss": 4.6146, "step": 8913 }, { "epoch": 0.47965992251399053, "grad_norm": 3.8840227127075195, "learning_rate": 2.6600636563227622e-05, "loss": 3.6292, "step": 8914 }, { "epoch": 0.4797137322427895, "grad_norm": 2.232004165649414, "learning_rate": 2.659641900521369e-05, "loss": 3.8961, "step": 8915 }, { "epoch": 0.47976754197158844, "grad_norm": 1.9792819023132324, "learning_rate": 2.6592201401578393e-05, "loss": 4.2867, "step": 8916 }, { "epoch": 0.4798213517003874, "grad_norm": 2.674166679382324, "learning_rate": 2.6587983752442268e-05, "loss": 3.9603, "step": 8917 }, { "epoch": 0.4798751614291864, "grad_norm": 1.4515981674194336, "learning_rate": 2.658376605792584e-05, "loss": 4.1836, "step": 8918 }, { "epoch": 0.4799289711579854, "grad_norm": 1.74684476852417, "learning_rate": 2.6579548318149634e-05, "loss": 4.1363, "step": 8919 }, { "epoch": 0.4799827808867843, "grad_norm": 1.7193692922592163, "learning_rate": 2.6575330533234188e-05, "loss": 3.8437, "step": 8920 }, { "epoch": 0.4800365906155833, "grad_norm": 1.4715886116027832, "learning_rate": 2.657111270330003e-05, "loss": 4.5752, "step": 8921 }, { "epoch": 0.4800904003443823, "grad_norm": 2.5434532165527344, "learning_rate": 2.6566894828467704e-05, "loss": 4.3039, "step": 8922 }, { "epoch": 0.48014421007318125, "grad_norm": 2.384138345718384, "learning_rate": 2.656267690885773e-05, "loss": 4.3451, "step": 8923 }, { "epoch": 0.4801980198019802, "grad_norm": 1.2095191478729248, "learning_rate": 2.6558458944590653e-05, "loss": 4.3818, "step": 8924 }, { "epoch": 0.48025182953077916, "grad_norm": 1.4627578258514404, "learning_rate": 2.6554240935787018e-05, "loss": 4.5648, "step": 8925 }, { "epoch": 0.48030563925957814, "grad_norm": 2.6002256870269775, "learning_rate": 2.655002288256735e-05, "loss": 4.0697, "step": 8926 }, { "epoch": 0.4803594489883771, "grad_norm": 2.199357509613037, "learning_rate": 2.6545804785052196e-05, "loss": 4.7822, "step": 8927 }, { "epoch": 0.48041325871717605, "grad_norm": 1.8225229978561401, "learning_rate": 2.654158664336211e-05, "loss": 4.3388, "step": 8928 }, { "epoch": 0.48046706844597503, "grad_norm": 1.6767228841781616, "learning_rate": 2.6537368457617617e-05, "loss": 4.1647, "step": 8929 }, { "epoch": 0.480520878174774, "grad_norm": 2.2992682456970215, "learning_rate": 2.653315022793927e-05, "loss": 4.1314, "step": 8930 }, { "epoch": 0.48057468790357294, "grad_norm": 1.3657097816467285, "learning_rate": 2.6528931954447612e-05, "loss": 4.3204, "step": 8931 }, { "epoch": 0.4806284976323719, "grad_norm": 1.9326671361923218, "learning_rate": 2.6524713637263194e-05, "loss": 4.0923, "step": 8932 }, { "epoch": 0.4806823073611709, "grad_norm": 2.0953519344329834, "learning_rate": 2.6520495276506558e-05, "loss": 3.8297, "step": 8933 }, { "epoch": 0.4807361170899699, "grad_norm": 1.3858530521392822, "learning_rate": 2.6516276872298253e-05, "loss": 4.4173, "step": 8934 }, { "epoch": 0.4807899268187688, "grad_norm": 3.5874218940734863, "learning_rate": 2.6512058424758835e-05, "loss": 4.0585, "step": 8935 }, { "epoch": 0.4808437365475678, "grad_norm": 2.4251761436462402, "learning_rate": 2.6507839934008866e-05, "loss": 3.7848, "step": 8936 }, { "epoch": 0.48089754627636677, "grad_norm": 2.495438814163208, "learning_rate": 2.650362140016887e-05, "loss": 4.1864, "step": 8937 }, { "epoch": 0.48095135600516575, "grad_norm": 1.3370459079742432, "learning_rate": 2.649940282335943e-05, "loss": 4.4855, "step": 8938 }, { "epoch": 0.4810051657339647, "grad_norm": 2.16538667678833, "learning_rate": 2.649518420370109e-05, "loss": 4.0031, "step": 8939 }, { "epoch": 0.48105897546276366, "grad_norm": 2.112144708633423, "learning_rate": 2.64909655413144e-05, "loss": 3.8031, "step": 8940 }, { "epoch": 0.48111278519156264, "grad_norm": 2.2342331409454346, "learning_rate": 2.648674683631993e-05, "loss": 4.335, "step": 8941 }, { "epoch": 0.4811665949203616, "grad_norm": 3.657244920730591, "learning_rate": 2.648252808883823e-05, "loss": 4.2295, "step": 8942 }, { "epoch": 0.48122040464916055, "grad_norm": 2.931556463241577, "learning_rate": 2.647830929898987e-05, "loss": 3.8706, "step": 8943 }, { "epoch": 0.48127421437795953, "grad_norm": 2.0302767753601074, "learning_rate": 2.6474090466895403e-05, "loss": 4.729, "step": 8944 }, { "epoch": 0.4813280241067585, "grad_norm": 2.0553791522979736, "learning_rate": 2.64698715926754e-05, "loss": 4.6892, "step": 8945 }, { "epoch": 0.4813818338355575, "grad_norm": 2.7115888595581055, "learning_rate": 2.6465652676450414e-05, "loss": 4.2661, "step": 8946 }, { "epoch": 0.4814356435643564, "grad_norm": 1.140852928161621, "learning_rate": 2.6461433718341016e-05, "loss": 4.3029, "step": 8947 }, { "epoch": 0.4814894532931554, "grad_norm": 1.8400628566741943, "learning_rate": 2.6457214718467782e-05, "loss": 3.4951, "step": 8948 }, { "epoch": 0.4815432630219544, "grad_norm": 1.2737630605697632, "learning_rate": 2.645299567695127e-05, "loss": 4.5701, "step": 8949 }, { "epoch": 0.48159707275075336, "grad_norm": 2.828856945037842, "learning_rate": 2.644877659391204e-05, "loss": 4.1477, "step": 8950 }, { "epoch": 0.4816508824795523, "grad_norm": 1.9156105518341064, "learning_rate": 2.6444557469470677e-05, "loss": 4.4799, "step": 8951 }, { "epoch": 0.48170469220835127, "grad_norm": 2.33284854888916, "learning_rate": 2.644033830374775e-05, "loss": 4.517, "step": 8952 }, { "epoch": 0.48175850193715025, "grad_norm": 0.9970821142196655, "learning_rate": 2.6436119096863826e-05, "loss": 4.7653, "step": 8953 }, { "epoch": 0.4818123116659492, "grad_norm": 1.4427661895751953, "learning_rate": 2.643189984893948e-05, "loss": 4.3217, "step": 8954 }, { "epoch": 0.48186612139474816, "grad_norm": 1.1734097003936768, "learning_rate": 2.6427680560095284e-05, "loss": 4.6759, "step": 8955 }, { "epoch": 0.48191993112354714, "grad_norm": 1.5046401023864746, "learning_rate": 2.6423461230451822e-05, "loss": 4.3193, "step": 8956 }, { "epoch": 0.4819737408523461, "grad_norm": 2.550865411758423, "learning_rate": 2.641924186012966e-05, "loss": 3.4921, "step": 8957 }, { "epoch": 0.48202755058114505, "grad_norm": 1.8602855205535889, "learning_rate": 2.6415022449249393e-05, "loss": 4.1793, "step": 8958 }, { "epoch": 0.48208136030994403, "grad_norm": 2.8370721340179443, "learning_rate": 2.6410802997931592e-05, "loss": 3.5659, "step": 8959 }, { "epoch": 0.482135170038743, "grad_norm": 1.2167882919311523, "learning_rate": 2.6406583506296826e-05, "loss": 4.2572, "step": 8960 }, { "epoch": 0.482188979767542, "grad_norm": 1.763787031173706, "learning_rate": 2.6402363974465695e-05, "loss": 3.772, "step": 8961 }, { "epoch": 0.4822427894963409, "grad_norm": 1.6813489198684692, "learning_rate": 2.6398144402558765e-05, "loss": 4.2833, "step": 8962 }, { "epoch": 0.4822965992251399, "grad_norm": 1.5739706754684448, "learning_rate": 2.639392479069664e-05, "loss": 3.9852, "step": 8963 }, { "epoch": 0.4823504089539389, "grad_norm": 1.53818678855896, "learning_rate": 2.6389705138999888e-05, "loss": 4.2673, "step": 8964 }, { "epoch": 0.48240421868273786, "grad_norm": 1.7441526651382446, "learning_rate": 2.638548544758909e-05, "loss": 4.4975, "step": 8965 }, { "epoch": 0.4824580284115368, "grad_norm": 3.4424619674682617, "learning_rate": 2.6381265716584857e-05, "loss": 3.6149, "step": 8966 }, { "epoch": 0.48251183814033577, "grad_norm": 1.8929996490478516, "learning_rate": 2.637704594610777e-05, "loss": 4.2108, "step": 8967 }, { "epoch": 0.48256564786913475, "grad_norm": 3.517129421234131, "learning_rate": 2.63728261362784e-05, "loss": 3.9364, "step": 8968 }, { "epoch": 0.48261945759793373, "grad_norm": 1.5379763841629028, "learning_rate": 2.6368606287217356e-05, "loss": 4.5002, "step": 8969 }, { "epoch": 0.48267326732673266, "grad_norm": 0.9720116853713989, "learning_rate": 2.636438639904523e-05, "loss": 4.4033, "step": 8970 }, { "epoch": 0.48272707705553164, "grad_norm": 2.6628165245056152, "learning_rate": 2.636016647188261e-05, "loss": 3.783, "step": 8971 }, { "epoch": 0.4827808867843306, "grad_norm": 1.7545253038406372, "learning_rate": 2.6355946505850087e-05, "loss": 4.1734, "step": 8972 }, { "epoch": 0.48283469651312955, "grad_norm": 1.523621916770935, "learning_rate": 2.6351726501068257e-05, "loss": 4.6006, "step": 8973 }, { "epoch": 0.48288850624192853, "grad_norm": 2.954301118850708, "learning_rate": 2.6347506457657727e-05, "loss": 4.2531, "step": 8974 }, { "epoch": 0.4829423159707275, "grad_norm": 2.554391384124756, "learning_rate": 2.634328637573908e-05, "loss": 4.2265, "step": 8975 }, { "epoch": 0.4829961256995265, "grad_norm": 1.5584102869033813, "learning_rate": 2.6339066255432926e-05, "loss": 4.5718, "step": 8976 }, { "epoch": 0.4830499354283254, "grad_norm": 1.8970856666564941, "learning_rate": 2.6334846096859854e-05, "loss": 4.0167, "step": 8977 }, { "epoch": 0.4831037451571244, "grad_norm": 3.222006320953369, "learning_rate": 2.6330625900140483e-05, "loss": 3.2606, "step": 8978 }, { "epoch": 0.4831575548859234, "grad_norm": 1.0854947566986084, "learning_rate": 2.632640566539539e-05, "loss": 4.7786, "step": 8979 }, { "epoch": 0.48321136461472236, "grad_norm": 1.6929088830947876, "learning_rate": 2.6322185392745196e-05, "loss": 4.5255, "step": 8980 }, { "epoch": 0.4832651743435213, "grad_norm": 1.1401164531707764, "learning_rate": 2.6317965082310496e-05, "loss": 4.6875, "step": 8981 }, { "epoch": 0.48331898407232027, "grad_norm": 1.355163335800171, "learning_rate": 2.6313744734211908e-05, "loss": 4.5313, "step": 8982 }, { "epoch": 0.48337279380111925, "grad_norm": 1.6956357955932617, "learning_rate": 2.6309524348570018e-05, "loss": 4.6457, "step": 8983 }, { "epoch": 0.48342660352991823, "grad_norm": 1.1544324159622192, "learning_rate": 2.6305303925505453e-05, "loss": 4.4816, "step": 8984 }, { "epoch": 0.48348041325871716, "grad_norm": 2.0416016578674316, "learning_rate": 2.630108346513881e-05, "loss": 4.089, "step": 8985 }, { "epoch": 0.48353422298751614, "grad_norm": 1.5106711387634277, "learning_rate": 2.62968629675907e-05, "loss": 4.371, "step": 8986 }, { "epoch": 0.4835880327163151, "grad_norm": 2.7309165000915527, "learning_rate": 2.629264243298174e-05, "loss": 2.8457, "step": 8987 }, { "epoch": 0.4836418424451141, "grad_norm": 1.9278877973556519, "learning_rate": 2.6288421861432522e-05, "loss": 4.0757, "step": 8988 }, { "epoch": 0.483695652173913, "grad_norm": 1.9924136400222778, "learning_rate": 2.6284201253063684e-05, "loss": 3.7861, "step": 8989 }, { "epoch": 0.483749461902712, "grad_norm": 2.402639865875244, "learning_rate": 2.6279980607995836e-05, "loss": 4.611, "step": 8990 }, { "epoch": 0.483803271631511, "grad_norm": 2.4375994205474854, "learning_rate": 2.6275759926349568e-05, "loss": 4.3214, "step": 8991 }, { "epoch": 0.48385708136030997, "grad_norm": 2.2153921127319336, "learning_rate": 2.627153920824552e-05, "loss": 3.6439, "step": 8992 }, { "epoch": 0.4839108910891089, "grad_norm": 2.3690836429595947, "learning_rate": 2.6267318453804303e-05, "loss": 4.2657, "step": 8993 }, { "epoch": 0.4839647008179079, "grad_norm": 2.247251033782959, "learning_rate": 2.626309766314653e-05, "loss": 4.0113, "step": 8994 }, { "epoch": 0.48401851054670686, "grad_norm": 1.331322193145752, "learning_rate": 2.6258876836392826e-05, "loss": 4.4586, "step": 8995 }, { "epoch": 0.4840723202755058, "grad_norm": 1.2377592325210571, "learning_rate": 2.62546559736638e-05, "loss": 4.1301, "step": 8996 }, { "epoch": 0.48412613000430477, "grad_norm": 1.8338744640350342, "learning_rate": 2.6250435075080093e-05, "loss": 3.8509, "step": 8997 }, { "epoch": 0.48417993973310375, "grad_norm": 1.5379183292388916, "learning_rate": 2.6246214140762315e-05, "loss": 3.7783, "step": 8998 }, { "epoch": 0.48423374946190273, "grad_norm": 1.5916277170181274, "learning_rate": 2.6241993170831077e-05, "loss": 4.3202, "step": 8999 }, { "epoch": 0.48428755919070166, "grad_norm": 1.613945484161377, "learning_rate": 2.623777216540702e-05, "loss": 4.3229, "step": 9000 }, { "epoch": 0.48434136891950064, "grad_norm": 2.119084119796753, "learning_rate": 2.6233551124610766e-05, "loss": 4.0987, "step": 9001 }, { "epoch": 0.4843951786482996, "grad_norm": 3.2335238456726074, "learning_rate": 2.622933004856294e-05, "loss": 3.866, "step": 9002 }, { "epoch": 0.4844489883770986, "grad_norm": 1.0726995468139648, "learning_rate": 2.6225108937384162e-05, "loss": 4.5738, "step": 9003 }, { "epoch": 0.4845027981058975, "grad_norm": 1.323866844177246, "learning_rate": 2.6220887791195064e-05, "loss": 4.476, "step": 9004 }, { "epoch": 0.4845566078346965, "grad_norm": 2.8307034969329834, "learning_rate": 2.6216666610116293e-05, "loss": 3.8675, "step": 9005 }, { "epoch": 0.4846104175634955, "grad_norm": 3.526731491088867, "learning_rate": 2.6212445394268443e-05, "loss": 3.9385, "step": 9006 }, { "epoch": 0.48466422729229447, "grad_norm": 2.0529427528381348, "learning_rate": 2.6208224143772174e-05, "loss": 4.4199, "step": 9007 }, { "epoch": 0.4847180370210934, "grad_norm": 2.2965376377105713, "learning_rate": 2.6204002858748105e-05, "loss": 4.3556, "step": 9008 }, { "epoch": 0.4847718467498924, "grad_norm": 2.41746187210083, "learning_rate": 2.619978153931688e-05, "loss": 3.81, "step": 9009 }, { "epoch": 0.48482565647869136, "grad_norm": 2.7342581748962402, "learning_rate": 2.6195560185599123e-05, "loss": 4.5081, "step": 9010 }, { "epoch": 0.48487946620749034, "grad_norm": 2.1233298778533936, "learning_rate": 2.619133879771547e-05, "loss": 4.228, "step": 9011 }, { "epoch": 0.48493327593628927, "grad_norm": 1.4790534973144531, "learning_rate": 2.6187117375786552e-05, "loss": 4.2508, "step": 9012 }, { "epoch": 0.48498708566508825, "grad_norm": 2.190573215484619, "learning_rate": 2.6182895919933027e-05, "loss": 4.0601, "step": 9013 }, { "epoch": 0.48504089539388723, "grad_norm": 2.2958600521087646, "learning_rate": 2.61786744302755e-05, "loss": 4.3427, "step": 9014 }, { "epoch": 0.48509470512268615, "grad_norm": 2.9454383850097656, "learning_rate": 2.6174452906934636e-05, "loss": 4.0058, "step": 9015 }, { "epoch": 0.48514851485148514, "grad_norm": 2.4270856380462646, "learning_rate": 2.617023135003107e-05, "loss": 4.3404, "step": 9016 }, { "epoch": 0.4852023245802841, "grad_norm": 1.1860220432281494, "learning_rate": 2.616600975968544e-05, "loss": 4.6859, "step": 9017 }, { "epoch": 0.4852561343090831, "grad_norm": 2.1115849018096924, "learning_rate": 2.616178813601839e-05, "loss": 4.4809, "step": 9018 }, { "epoch": 0.485309944037882, "grad_norm": 2.4027161598205566, "learning_rate": 2.615756647915055e-05, "loss": 4.0303, "step": 9019 }, { "epoch": 0.485363753766681, "grad_norm": 2.4733896255493164, "learning_rate": 2.6153344789202582e-05, "loss": 3.2338, "step": 9020 }, { "epoch": 0.48541756349548, "grad_norm": 1.895408272743225, "learning_rate": 2.6149123066295124e-05, "loss": 4.2274, "step": 9021 }, { "epoch": 0.48547137322427897, "grad_norm": 1.1613863706588745, "learning_rate": 2.6144901310548808e-05, "loss": 4.3653, "step": 9022 }, { "epoch": 0.4855251829530779, "grad_norm": 2.401834726333618, "learning_rate": 2.61406795220843e-05, "loss": 4.0371, "step": 9023 }, { "epoch": 0.4855789926818769, "grad_norm": 1.8471059799194336, "learning_rate": 2.6136457701022236e-05, "loss": 4.3224, "step": 9024 }, { "epoch": 0.48563280241067586, "grad_norm": 2.2832558155059814, "learning_rate": 2.6132235847483273e-05, "loss": 4.6004, "step": 9025 }, { "epoch": 0.48568661213947484, "grad_norm": 2.155973196029663, "learning_rate": 2.6128013961588048e-05, "loss": 4.3871, "step": 9026 }, { "epoch": 0.48574042186827376, "grad_norm": 2.7881014347076416, "learning_rate": 2.612379204345722e-05, "loss": 4.1249, "step": 9027 }, { "epoch": 0.48579423159707275, "grad_norm": 1.9874067306518555, "learning_rate": 2.6119570093211444e-05, "loss": 4.3015, "step": 9028 }, { "epoch": 0.4858480413258717, "grad_norm": 1.2881203889846802, "learning_rate": 2.6115348110971354e-05, "loss": 4.2837, "step": 9029 }, { "epoch": 0.4859018510546707, "grad_norm": 2.3726961612701416, "learning_rate": 2.6111126096857624e-05, "loss": 3.6951, "step": 9030 }, { "epoch": 0.48595566078346963, "grad_norm": 1.2037400007247925, "learning_rate": 2.61069040509909e-05, "loss": 4.6991, "step": 9031 }, { "epoch": 0.4860094705122686, "grad_norm": 3.6710824966430664, "learning_rate": 2.6102681973491827e-05, "loss": 4.3788, "step": 9032 }, { "epoch": 0.4860632802410676, "grad_norm": 1.1821955442428589, "learning_rate": 2.609845986448108e-05, "loss": 4.6716, "step": 9033 }, { "epoch": 0.4861170899698666, "grad_norm": 2.572512149810791, "learning_rate": 2.6094237724079294e-05, "loss": 4.6678, "step": 9034 }, { "epoch": 0.4861708996986655, "grad_norm": 2.7552905082702637, "learning_rate": 2.6090015552407136e-05, "loss": 4.4787, "step": 9035 }, { "epoch": 0.4862247094274645, "grad_norm": 1.8455467224121094, "learning_rate": 2.608579334958528e-05, "loss": 4.6788, "step": 9036 }, { "epoch": 0.48627851915626347, "grad_norm": 1.7348076105117798, "learning_rate": 2.608157111573436e-05, "loss": 4.2099, "step": 9037 }, { "epoch": 0.4863323288850624, "grad_norm": 1.5262274742126465, "learning_rate": 2.607734885097505e-05, "loss": 4.5365, "step": 9038 }, { "epoch": 0.4863861386138614, "grad_norm": 1.8328317403793335, "learning_rate": 2.607312655542801e-05, "loss": 3.9774, "step": 9039 }, { "epoch": 0.48643994834266036, "grad_norm": 3.01836895942688, "learning_rate": 2.6068904229213893e-05, "loss": 4.3642, "step": 9040 }, { "epoch": 0.48649375807145934, "grad_norm": 2.758915901184082, "learning_rate": 2.6064681872453368e-05, "loss": 4.2007, "step": 9041 }, { "epoch": 0.48654756780025826, "grad_norm": 2.315516471862793, "learning_rate": 2.6060459485267103e-05, "loss": 4.1367, "step": 9042 }, { "epoch": 0.48660137752905724, "grad_norm": 1.6840713024139404, "learning_rate": 2.605623706777576e-05, "loss": 4.3288, "step": 9043 }, { "epoch": 0.4866551872578562, "grad_norm": 2.2363600730895996, "learning_rate": 2.6052014620099995e-05, "loss": 3.9953, "step": 9044 }, { "epoch": 0.4867089969866552, "grad_norm": 1.4558383226394653, "learning_rate": 2.604779214236048e-05, "loss": 4.5924, "step": 9045 }, { "epoch": 0.48676280671545413, "grad_norm": 1.3238111734390259, "learning_rate": 2.6043569634677895e-05, "loss": 4.8185, "step": 9046 }, { "epoch": 0.4868166164442531, "grad_norm": 2.1338114738464355, "learning_rate": 2.603934709717289e-05, "loss": 4.3718, "step": 9047 }, { "epoch": 0.4868704261730521, "grad_norm": 1.5120078325271606, "learning_rate": 2.6035124529966143e-05, "loss": 4.4784, "step": 9048 }, { "epoch": 0.4869242359018511, "grad_norm": 2.1199073791503906, "learning_rate": 2.603090193317832e-05, "loss": 4.3792, "step": 9049 }, { "epoch": 0.48697804563065, "grad_norm": 1.8342903852462769, "learning_rate": 2.6026679306930085e-05, "loss": 4.1868, "step": 9050 }, { "epoch": 0.487031855359449, "grad_norm": 1.4549368619918823, "learning_rate": 2.602245665134213e-05, "loss": 4.387, "step": 9051 }, { "epoch": 0.48708566508824797, "grad_norm": 2.2375857830047607, "learning_rate": 2.601823396653511e-05, "loss": 4.3055, "step": 9052 }, { "epoch": 0.48713947481704695, "grad_norm": 2.2500216960906982, "learning_rate": 2.6014011252629693e-05, "loss": 3.8475, "step": 9053 }, { "epoch": 0.4871932845458459, "grad_norm": 2.71500563621521, "learning_rate": 2.6009788509746576e-05, "loss": 3.4159, "step": 9054 }, { "epoch": 0.48724709427464485, "grad_norm": 2.0577452182769775, "learning_rate": 2.600556573800641e-05, "loss": 4.3605, "step": 9055 }, { "epoch": 0.48730090400344384, "grad_norm": 1.9442778825759888, "learning_rate": 2.6001342937529882e-05, "loss": 3.9269, "step": 9056 }, { "epoch": 0.4873547137322428, "grad_norm": 1.703464388847351, "learning_rate": 2.5997120108437666e-05, "loss": 5.0202, "step": 9057 }, { "epoch": 0.48740852346104174, "grad_norm": 2.4554355144500732, "learning_rate": 2.5992897250850435e-05, "loss": 3.9276, "step": 9058 }, { "epoch": 0.4874623331898407, "grad_norm": 2.783726453781128, "learning_rate": 2.598867436488888e-05, "loss": 3.8378, "step": 9059 }, { "epoch": 0.4875161429186397, "grad_norm": 1.396342158317566, "learning_rate": 2.5984451450673662e-05, "loss": 4.194, "step": 9060 }, { "epoch": 0.48756995264743863, "grad_norm": 1.2895737886428833, "learning_rate": 2.5980228508325477e-05, "loss": 4.3728, "step": 9061 }, { "epoch": 0.4876237623762376, "grad_norm": 1.4069093465805054, "learning_rate": 2.5976005537965004e-05, "loss": 4.4129, "step": 9062 }, { "epoch": 0.4876775721050366, "grad_norm": 1.2234407663345337, "learning_rate": 2.5971782539712902e-05, "loss": 4.2084, "step": 9063 }, { "epoch": 0.4877313818338356, "grad_norm": 1.6715033054351807, "learning_rate": 2.5967559513689876e-05, "loss": 3.933, "step": 9064 }, { "epoch": 0.4877851915626345, "grad_norm": 2.764359712600708, "learning_rate": 2.59633364600166e-05, "loss": 3.732, "step": 9065 }, { "epoch": 0.4878390012914335, "grad_norm": 1.734660267829895, "learning_rate": 2.595911337881376e-05, "loss": 4.4474, "step": 9066 }, { "epoch": 0.48789281102023246, "grad_norm": 1.8452314138412476, "learning_rate": 2.5954890270202044e-05, "loss": 3.9844, "step": 9067 }, { "epoch": 0.48794662074903145, "grad_norm": 1.7582420110702515, "learning_rate": 2.595066713430212e-05, "loss": 4.4886, "step": 9068 }, { "epoch": 0.48800043047783037, "grad_norm": 2.3831417560577393, "learning_rate": 2.5946443971234697e-05, "loss": 4.0567, "step": 9069 }, { "epoch": 0.48805424020662935, "grad_norm": 1.6583372354507446, "learning_rate": 2.5942220781120453e-05, "loss": 4.6666, "step": 9070 }, { "epoch": 0.48810804993542833, "grad_norm": 1.6137183904647827, "learning_rate": 2.5937997564080063e-05, "loss": 4.1387, "step": 9071 }, { "epoch": 0.4881618596642273, "grad_norm": 2.2547197341918945, "learning_rate": 2.5933774320234234e-05, "loss": 4.0359, "step": 9072 }, { "epoch": 0.48821566939302624, "grad_norm": 2.311521291732788, "learning_rate": 2.5929551049703642e-05, "loss": 4.5334, "step": 9073 }, { "epoch": 0.4882694791218252, "grad_norm": 1.8827288150787354, "learning_rate": 2.5925327752608985e-05, "loss": 4.3116, "step": 9074 }, { "epoch": 0.4883232888506242, "grad_norm": 2.3869197368621826, "learning_rate": 2.5921104429070946e-05, "loss": 4.3581, "step": 9075 }, { "epoch": 0.4883770985794232, "grad_norm": 1.857639193534851, "learning_rate": 2.5916881079210215e-05, "loss": 4.2001, "step": 9076 }, { "epoch": 0.4884309083082221, "grad_norm": 2.5809550285339355, "learning_rate": 2.5912657703147497e-05, "loss": 3.7819, "step": 9077 }, { "epoch": 0.4884847180370211, "grad_norm": 3.9086620807647705, "learning_rate": 2.5908434301003475e-05, "loss": 3.6068, "step": 9078 }, { "epoch": 0.4885385277658201, "grad_norm": 1.8762528896331787, "learning_rate": 2.5904210872898842e-05, "loss": 4.0394, "step": 9079 }, { "epoch": 0.488592337494619, "grad_norm": 1.7186464071273804, "learning_rate": 2.5899987418954297e-05, "loss": 4.0827, "step": 9080 }, { "epoch": 0.488646147223418, "grad_norm": 1.9412364959716797, "learning_rate": 2.5895763939290535e-05, "loss": 4.3681, "step": 9081 }, { "epoch": 0.48869995695221696, "grad_norm": 2.653235673904419, "learning_rate": 2.5891540434028244e-05, "loss": 3.7733, "step": 9082 }, { "epoch": 0.48875376668101594, "grad_norm": 1.8108137845993042, "learning_rate": 2.5887316903288128e-05, "loss": 3.8272, "step": 9083 }, { "epoch": 0.48880757640981487, "grad_norm": 1.5425851345062256, "learning_rate": 2.5883093347190874e-05, "loss": 4.5294, "step": 9084 }, { "epoch": 0.48886138613861385, "grad_norm": 2.2474772930145264, "learning_rate": 2.58788697658572e-05, "loss": 4.2019, "step": 9085 }, { "epoch": 0.48891519586741283, "grad_norm": 1.848551869392395, "learning_rate": 2.5874646159407783e-05, "loss": 4.0748, "step": 9086 }, { "epoch": 0.4889690055962118, "grad_norm": 1.2609549760818481, "learning_rate": 2.5870422527963333e-05, "loss": 4.2814, "step": 9087 }, { "epoch": 0.48902281532501074, "grad_norm": 2.6772689819335938, "learning_rate": 2.5866198871644548e-05, "loss": 3.9883, "step": 9088 }, { "epoch": 0.4890766250538097, "grad_norm": 1.429736852645874, "learning_rate": 2.586197519057213e-05, "loss": 4.4218, "step": 9089 }, { "epoch": 0.4891304347826087, "grad_norm": 1.710471272468567, "learning_rate": 2.5857751484866783e-05, "loss": 4.0403, "step": 9090 }, { "epoch": 0.4891842445114077, "grad_norm": 2.464487075805664, "learning_rate": 2.5853527754649198e-05, "loss": 4.2729, "step": 9091 }, { "epoch": 0.4892380542402066, "grad_norm": 2.6136434078216553, "learning_rate": 2.5849304000040086e-05, "loss": 3.9323, "step": 9092 }, { "epoch": 0.4892918639690056, "grad_norm": 2.13887882232666, "learning_rate": 2.5845080221160163e-05, "loss": 4.2518, "step": 9093 }, { "epoch": 0.4893456736978046, "grad_norm": 2.241638660430908, "learning_rate": 2.5840856418130105e-05, "loss": 4.1484, "step": 9094 }, { "epoch": 0.48939948342660355, "grad_norm": 3.692342758178711, "learning_rate": 2.5836632591070643e-05, "loss": 3.0405, "step": 9095 }, { "epoch": 0.4894532931554025, "grad_norm": 1.103546380996704, "learning_rate": 2.5832408740102467e-05, "loss": 4.747, "step": 9096 }, { "epoch": 0.48950710288420146, "grad_norm": 1.708031177520752, "learning_rate": 2.5828184865346288e-05, "loss": 4.2398, "step": 9097 }, { "epoch": 0.48956091261300044, "grad_norm": 1.5492850542068481, "learning_rate": 2.582396096692281e-05, "loss": 4.6153, "step": 9098 }, { "epoch": 0.4896147223417994, "grad_norm": 2.435467004776001, "learning_rate": 2.5819737044952747e-05, "loss": 4.2179, "step": 9099 }, { "epoch": 0.48966853207059835, "grad_norm": 2.502365827560425, "learning_rate": 2.5815513099556803e-05, "loss": 3.8062, "step": 9100 }, { "epoch": 0.48972234179939733, "grad_norm": 1.976331114768982, "learning_rate": 2.581128913085569e-05, "loss": 4.0718, "step": 9101 }, { "epoch": 0.4897761515281963, "grad_norm": 2.3504762649536133, "learning_rate": 2.5807065138970117e-05, "loss": 3.9989, "step": 9102 }, { "epoch": 0.48982996125699524, "grad_norm": 1.6627311706542969, "learning_rate": 2.5802841124020787e-05, "loss": 3.9656, "step": 9103 }, { "epoch": 0.4898837709857942, "grad_norm": 3.0331013202667236, "learning_rate": 2.5798617086128425e-05, "loss": 3.6254, "step": 9104 }, { "epoch": 0.4899375807145932, "grad_norm": 1.9476207494735718, "learning_rate": 2.5794393025413732e-05, "loss": 3.4278, "step": 9105 }, { "epoch": 0.4899913904433922, "grad_norm": 2.5673561096191406, "learning_rate": 2.579016894199742e-05, "loss": 4.1465, "step": 9106 }, { "epoch": 0.4900452001721911, "grad_norm": 1.3281667232513428, "learning_rate": 2.5785944836000204e-05, "loss": 4.6646, "step": 9107 }, { "epoch": 0.4900990099009901, "grad_norm": 2.7323691844940186, "learning_rate": 2.5781720707542805e-05, "loss": 4.2841, "step": 9108 }, { "epoch": 0.49015281962978907, "grad_norm": 1.4758644104003906, "learning_rate": 2.5777496556745924e-05, "loss": 4.9026, "step": 9109 }, { "epoch": 0.49020662935858805, "grad_norm": 2.576402187347412, "learning_rate": 2.5773272383730285e-05, "loss": 4.4954, "step": 9110 }, { "epoch": 0.490260439087387, "grad_norm": 2.4009077548980713, "learning_rate": 2.57690481886166e-05, "loss": 3.7145, "step": 9111 }, { "epoch": 0.49031424881618596, "grad_norm": 2.6463184356689453, "learning_rate": 2.576482397152559e-05, "loss": 4.2483, "step": 9112 }, { "epoch": 0.49036805854498494, "grad_norm": 3.075059413909912, "learning_rate": 2.576059973257797e-05, "loss": 3.8406, "step": 9113 }, { "epoch": 0.4904218682737839, "grad_norm": 1.8920371532440186, "learning_rate": 2.575637547189445e-05, "loss": 4.3371, "step": 9114 }, { "epoch": 0.49047567800258285, "grad_norm": 2.824068069458008, "learning_rate": 2.5752151189595752e-05, "loss": 3.8969, "step": 9115 }, { "epoch": 0.49052948773138183, "grad_norm": 1.3650339841842651, "learning_rate": 2.5747926885802603e-05, "loss": 4.3453, "step": 9116 }, { "epoch": 0.4905832974601808, "grad_norm": 1.5135318040847778, "learning_rate": 2.5743702560635706e-05, "loss": 3.7423, "step": 9117 }, { "epoch": 0.4906371071889798, "grad_norm": 2.191441535949707, "learning_rate": 2.57394782142158e-05, "loss": 4.4587, "step": 9118 }, { "epoch": 0.4906909169177787, "grad_norm": 1.7712785005569458, "learning_rate": 2.573525384666359e-05, "loss": 4.6452, "step": 9119 }, { "epoch": 0.4907447266465777, "grad_norm": 1.446279764175415, "learning_rate": 2.5731029458099803e-05, "loss": 4.5498, "step": 9120 }, { "epoch": 0.4907985363753767, "grad_norm": 2.5645220279693604, "learning_rate": 2.5726805048645163e-05, "loss": 4.4543, "step": 9121 }, { "epoch": 0.4908523461041756, "grad_norm": 1.4982094764709473, "learning_rate": 2.5722580618420383e-05, "loss": 4.6544, "step": 9122 }, { "epoch": 0.4909061558329746, "grad_norm": 1.6539156436920166, "learning_rate": 2.5718356167546204e-05, "loss": 4.1461, "step": 9123 }, { "epoch": 0.49095996556177357, "grad_norm": 2.2142975330352783, "learning_rate": 2.5714131696143328e-05, "loss": 4.145, "step": 9124 }, { "epoch": 0.49101377529057255, "grad_norm": 1.4700700044631958, "learning_rate": 2.570990720433249e-05, "loss": 4.2435, "step": 9125 }, { "epoch": 0.4910675850193715, "grad_norm": 2.9457802772521973, "learning_rate": 2.5705682692234418e-05, "loss": 3.7073, "step": 9126 }, { "epoch": 0.49112139474817046, "grad_norm": 1.6592413187026978, "learning_rate": 2.5701458159969825e-05, "loss": 4.4493, "step": 9127 }, { "epoch": 0.49117520447696944, "grad_norm": 1.5058761835098267, "learning_rate": 2.5697233607659453e-05, "loss": 4.8697, "step": 9128 }, { "epoch": 0.4912290142057684, "grad_norm": 2.7442822456359863, "learning_rate": 2.5693009035424016e-05, "loss": 3.9344, "step": 9129 }, { "epoch": 0.49128282393456735, "grad_norm": 1.2685099840164185, "learning_rate": 2.5688784443384238e-05, "loss": 4.5331, "step": 9130 }, { "epoch": 0.49133663366336633, "grad_norm": 1.6116325855255127, "learning_rate": 2.568455983166087e-05, "loss": 4.3727, "step": 9131 }, { "epoch": 0.4913904433921653, "grad_norm": 1.5539638996124268, "learning_rate": 2.568033520037461e-05, "loss": 4.4626, "step": 9132 }, { "epoch": 0.4914442531209643, "grad_norm": 1.473527193069458, "learning_rate": 2.5676110549646205e-05, "loss": 4.2549, "step": 9133 }, { "epoch": 0.4914980628497632, "grad_norm": 2.2308974266052246, "learning_rate": 2.5671885879596373e-05, "loss": 4.7171, "step": 9134 }, { "epoch": 0.4915518725785622, "grad_norm": 2.0518229007720947, "learning_rate": 2.566766119034586e-05, "loss": 3.8303, "step": 9135 }, { "epoch": 0.4916056823073612, "grad_norm": 2.4976582527160645, "learning_rate": 2.566343648201538e-05, "loss": 3.9843, "step": 9136 }, { "epoch": 0.49165949203616016, "grad_norm": 2.8550145626068115, "learning_rate": 2.5659211754725672e-05, "loss": 3.7038, "step": 9137 }, { "epoch": 0.4917133017649591, "grad_norm": 2.576076030731201, "learning_rate": 2.5654987008597454e-05, "loss": 4.015, "step": 9138 }, { "epoch": 0.49176711149375807, "grad_norm": 2.162365674972534, "learning_rate": 2.5650762243751486e-05, "loss": 4.4517, "step": 9139 }, { "epoch": 0.49182092122255705, "grad_norm": 2.185281991958618, "learning_rate": 2.564653746030847e-05, "loss": 3.9365, "step": 9140 }, { "epoch": 0.49187473095135603, "grad_norm": 3.173542022705078, "learning_rate": 2.5642312658389162e-05, "loss": 3.6443, "step": 9141 }, { "epoch": 0.49192854068015496, "grad_norm": 3.0616366863250732, "learning_rate": 2.563808783811428e-05, "loss": 3.7221, "step": 9142 }, { "epoch": 0.49198235040895394, "grad_norm": 1.7014926671981812, "learning_rate": 2.5633862999604562e-05, "loss": 4.3512, "step": 9143 }, { "epoch": 0.4920361601377529, "grad_norm": 1.6922777891159058, "learning_rate": 2.562963814298075e-05, "loss": 4.3492, "step": 9144 }, { "epoch": 0.49208996986655185, "grad_norm": 2.0849063396453857, "learning_rate": 2.5625413268363574e-05, "loss": 3.7822, "step": 9145 }, { "epoch": 0.4921437795953508, "grad_norm": 2.3589072227478027, "learning_rate": 2.5621188375873766e-05, "loss": 4.128, "step": 9146 }, { "epoch": 0.4921975893241498, "grad_norm": 1.8560019731521606, "learning_rate": 2.5616963465632064e-05, "loss": 3.7695, "step": 9147 }, { "epoch": 0.4922513990529488, "grad_norm": 2.158841609954834, "learning_rate": 2.5612738537759206e-05, "loss": 3.5488, "step": 9148 }, { "epoch": 0.4923052087817477, "grad_norm": 1.1968612670898438, "learning_rate": 2.5608513592375933e-05, "loss": 4.2644, "step": 9149 }, { "epoch": 0.4923590185105467, "grad_norm": 1.4839516878128052, "learning_rate": 2.5604288629602973e-05, "loss": 4.6003, "step": 9150 }, { "epoch": 0.4924128282393457, "grad_norm": 2.2050909996032715, "learning_rate": 2.5600063649561074e-05, "loss": 4.2505, "step": 9151 }, { "epoch": 0.49246663796814466, "grad_norm": 1.638308048248291, "learning_rate": 2.5595838652370963e-05, "loss": 4.5211, "step": 9152 }, { "epoch": 0.4925204476969436, "grad_norm": 1.6138637065887451, "learning_rate": 2.559161363815339e-05, "loss": 4.5043, "step": 9153 }, { "epoch": 0.49257425742574257, "grad_norm": 1.6727384328842163, "learning_rate": 2.5587388607029095e-05, "loss": 4.4243, "step": 9154 }, { "epoch": 0.49262806715454155, "grad_norm": 1.2016521692276, "learning_rate": 2.5583163559118806e-05, "loss": 4.593, "step": 9155 }, { "epoch": 0.49268187688334053, "grad_norm": 2.211604118347168, "learning_rate": 2.557893849454327e-05, "loss": 3.8702, "step": 9156 }, { "epoch": 0.49273568661213946, "grad_norm": 1.5013095140457153, "learning_rate": 2.5574713413423236e-05, "loss": 4.115, "step": 9157 }, { "epoch": 0.49278949634093844, "grad_norm": 1.2346256971359253, "learning_rate": 2.5570488315879432e-05, "loss": 4.5424, "step": 9158 }, { "epoch": 0.4928433060697374, "grad_norm": 3.160764694213867, "learning_rate": 2.5566263202032613e-05, "loss": 4.0399, "step": 9159 }, { "epoch": 0.4928971157985364, "grad_norm": 1.8171017169952393, "learning_rate": 2.5562038072003514e-05, "loss": 4.0974, "step": 9160 }, { "epoch": 0.4929509255273353, "grad_norm": 2.103349447250366, "learning_rate": 2.5557812925912867e-05, "loss": 4.3364, "step": 9161 }, { "epoch": 0.4930047352561343, "grad_norm": 2.5785696506500244, "learning_rate": 2.5553587763881444e-05, "loss": 3.7228, "step": 9162 }, { "epoch": 0.4930585449849333, "grad_norm": 2.948045253753662, "learning_rate": 2.5549362586029955e-05, "loss": 3.8843, "step": 9163 }, { "epoch": 0.49311235471373227, "grad_norm": 2.0528907775878906, "learning_rate": 2.5545137392479172e-05, "loss": 4.2274, "step": 9164 }, { "epoch": 0.4931661644425312, "grad_norm": 1.719050407409668, "learning_rate": 2.554091218334983e-05, "loss": 3.7985, "step": 9165 }, { "epoch": 0.4932199741713302, "grad_norm": 3.316972494125366, "learning_rate": 2.553668695876267e-05, "loss": 4.1057, "step": 9166 }, { "epoch": 0.49327378390012916, "grad_norm": 1.849381446838379, "learning_rate": 2.553246171883844e-05, "loss": 4.1897, "step": 9167 }, { "epoch": 0.4933275936289281, "grad_norm": 3.130061626434326, "learning_rate": 2.5528236463697886e-05, "loss": 4.2874, "step": 9168 }, { "epoch": 0.49338140335772707, "grad_norm": 1.7943243980407715, "learning_rate": 2.552401119346175e-05, "loss": 4.6829, "step": 9169 }, { "epoch": 0.49343521308652605, "grad_norm": 2.0636825561523438, "learning_rate": 2.551978590825079e-05, "loss": 4.4859, "step": 9170 }, { "epoch": 0.49348902281532503, "grad_norm": 2.212667226791382, "learning_rate": 2.551556060818574e-05, "loss": 4.3688, "step": 9171 }, { "epoch": 0.49354283254412395, "grad_norm": 2.284562587738037, "learning_rate": 2.551133529338736e-05, "loss": 4.0754, "step": 9172 }, { "epoch": 0.49359664227292294, "grad_norm": 0.9749579429626465, "learning_rate": 2.5507109963976396e-05, "loss": 4.5606, "step": 9173 }, { "epoch": 0.4936504520017219, "grad_norm": 2.6963930130004883, "learning_rate": 2.5502884620073585e-05, "loss": 3.9137, "step": 9174 }, { "epoch": 0.4937042617305209, "grad_norm": 2.4742624759674072, "learning_rate": 2.549865926179969e-05, "loss": 4.4138, "step": 9175 }, { "epoch": 0.4937580714593198, "grad_norm": 1.543682336807251, "learning_rate": 2.5494433889275447e-05, "loss": 4.173, "step": 9176 }, { "epoch": 0.4938118811881188, "grad_norm": 2.7948858737945557, "learning_rate": 2.549020850262162e-05, "loss": 4.0042, "step": 9177 }, { "epoch": 0.4938656909169178, "grad_norm": 2.18568754196167, "learning_rate": 2.5485983101958955e-05, "loss": 3.8059, "step": 9178 }, { "epoch": 0.49391950064571677, "grad_norm": 1.8309900760650635, "learning_rate": 2.5481757687408192e-05, "loss": 4.4555, "step": 9179 }, { "epoch": 0.4939733103745157, "grad_norm": 1.6261106729507446, "learning_rate": 2.547753225909009e-05, "loss": 4.3901, "step": 9180 }, { "epoch": 0.4940271201033147, "grad_norm": 3.3150670528411865, "learning_rate": 2.547330681712541e-05, "loss": 4.5054, "step": 9181 }, { "epoch": 0.49408092983211366, "grad_norm": 1.932987093925476, "learning_rate": 2.546908136163489e-05, "loss": 4.2834, "step": 9182 }, { "epoch": 0.49413473956091264, "grad_norm": 1.5028325319290161, "learning_rate": 2.5464855892739287e-05, "loss": 4.4377, "step": 9183 }, { "epoch": 0.49418854928971157, "grad_norm": 2.7236738204956055, "learning_rate": 2.5460630410559343e-05, "loss": 4.1334, "step": 9184 }, { "epoch": 0.49424235901851055, "grad_norm": 2.4647605419158936, "learning_rate": 2.5456404915215837e-05, "loss": 4.4754, "step": 9185 }, { "epoch": 0.49429616874730953, "grad_norm": 2.1434786319732666, "learning_rate": 2.5452179406829497e-05, "loss": 3.5522, "step": 9186 }, { "epoch": 0.49434997847610845, "grad_norm": 1.541013240814209, "learning_rate": 2.544795388552108e-05, "loss": 4.3371, "step": 9187 }, { "epoch": 0.49440378820490744, "grad_norm": 2.6414570808410645, "learning_rate": 2.5443728351411362e-05, "loss": 3.8198, "step": 9188 }, { "epoch": 0.4944575979337064, "grad_norm": 1.9782257080078125, "learning_rate": 2.5439502804621067e-05, "loss": 4.0409, "step": 9189 }, { "epoch": 0.4945114076625054, "grad_norm": 2.0697710514068604, "learning_rate": 2.543527724527097e-05, "loss": 4.1772, "step": 9190 }, { "epoch": 0.4945652173913043, "grad_norm": 2.89687442779541, "learning_rate": 2.543105167348182e-05, "loss": 4.37, "step": 9191 }, { "epoch": 0.4946190271201033, "grad_norm": 2.678321361541748, "learning_rate": 2.5426826089374373e-05, "loss": 3.9897, "step": 9192 }, { "epoch": 0.4946728368489023, "grad_norm": 2.400423288345337, "learning_rate": 2.542260049306938e-05, "loss": 3.9379, "step": 9193 }, { "epoch": 0.49472664657770127, "grad_norm": 2.4313080310821533, "learning_rate": 2.54183748846876e-05, "loss": 3.9214, "step": 9194 }, { "epoch": 0.4947804563065002, "grad_norm": 1.0679916143417358, "learning_rate": 2.5414149264349796e-05, "loss": 4.5758, "step": 9195 }, { "epoch": 0.4948342660352992, "grad_norm": 2.478517770767212, "learning_rate": 2.540992363217673e-05, "loss": 4.078, "step": 9196 }, { "epoch": 0.49488807576409816, "grad_norm": 2.4732134342193604, "learning_rate": 2.5405697988289133e-05, "loss": 2.9087, "step": 9197 }, { "epoch": 0.49494188549289714, "grad_norm": 1.9563981294631958, "learning_rate": 2.5401472332807784e-05, "loss": 4.2596, "step": 9198 }, { "epoch": 0.49499569522169606, "grad_norm": 1.6431313753128052, "learning_rate": 2.5397246665853437e-05, "loss": 4.3989, "step": 9199 }, { "epoch": 0.49504950495049505, "grad_norm": 2.3541135787963867, "learning_rate": 2.539302098754685e-05, "loss": 4.2349, "step": 9200 }, { "epoch": 0.495103314679294, "grad_norm": 2.0395073890686035, "learning_rate": 2.5388795298008776e-05, "loss": 4.1697, "step": 9201 }, { "epoch": 0.495157124408093, "grad_norm": 2.4136505126953125, "learning_rate": 2.5384569597359974e-05, "loss": 4.7022, "step": 9202 }, { "epoch": 0.49521093413689193, "grad_norm": 1.34235417842865, "learning_rate": 2.5380343885721214e-05, "loss": 4.7192, "step": 9203 }, { "epoch": 0.4952647438656909, "grad_norm": 1.3412452936172485, "learning_rate": 2.5376118163213252e-05, "loss": 4.5855, "step": 9204 }, { "epoch": 0.4953185535944899, "grad_norm": 2.9357492923736572, "learning_rate": 2.537189242995684e-05, "loss": 3.3, "step": 9205 }, { "epoch": 0.4953723633232889, "grad_norm": 2.7554938793182373, "learning_rate": 2.5367666686072745e-05, "loss": 4.5203, "step": 9206 }, { "epoch": 0.4954261730520878, "grad_norm": 2.980790376663208, "learning_rate": 2.5363440931681715e-05, "loss": 3.7517, "step": 9207 }, { "epoch": 0.4954799827808868, "grad_norm": 2.584301233291626, "learning_rate": 2.5359215166904536e-05, "loss": 3.4126, "step": 9208 }, { "epoch": 0.49553379250968577, "grad_norm": 1.9566665887832642, "learning_rate": 2.5354989391861948e-05, "loss": 3.8362, "step": 9209 }, { "epoch": 0.4955876022384847, "grad_norm": 2.87630295753479, "learning_rate": 2.535076360667471e-05, "loss": 4.4223, "step": 9210 }, { "epoch": 0.4956414119672837, "grad_norm": 3.1831212043762207, "learning_rate": 2.5346537811463604e-05, "loss": 3.7969, "step": 9211 }, { "epoch": 0.49569522169608266, "grad_norm": 1.8773729801177979, "learning_rate": 2.534231200634937e-05, "loss": 4.1372, "step": 9212 }, { "epoch": 0.49574903142488164, "grad_norm": 3.620887041091919, "learning_rate": 2.5338086191452786e-05, "loss": 4.4085, "step": 9213 }, { "epoch": 0.49580284115368056, "grad_norm": 1.3467825651168823, "learning_rate": 2.5333860366894607e-05, "loss": 4.8671, "step": 9214 }, { "epoch": 0.49585665088247954, "grad_norm": 2.073455572128296, "learning_rate": 2.5329634532795594e-05, "loss": 4.087, "step": 9215 }, { "epoch": 0.4959104606112785, "grad_norm": 3.2879528999328613, "learning_rate": 2.5325408689276515e-05, "loss": 3.9792, "step": 9216 }, { "epoch": 0.4959642703400775, "grad_norm": 1.5659822225570679, "learning_rate": 2.532118283645813e-05, "loss": 4.588, "step": 9217 }, { "epoch": 0.49601808006887643, "grad_norm": 2.261708974838257, "learning_rate": 2.53169569744612e-05, "loss": 4.3119, "step": 9218 }, { "epoch": 0.4960718897976754, "grad_norm": 2.4140512943267822, "learning_rate": 2.53127311034065e-05, "loss": 4.0402, "step": 9219 }, { "epoch": 0.4961256995264744, "grad_norm": 1.978613257408142, "learning_rate": 2.5308505223414776e-05, "loss": 3.8668, "step": 9220 }, { "epoch": 0.4961795092552734, "grad_norm": 2.421477794647217, "learning_rate": 2.5304279334606807e-05, "loss": 4.676, "step": 9221 }, { "epoch": 0.4962333189840723, "grad_norm": 2.236664056777954, "learning_rate": 2.5300053437103356e-05, "loss": 4.4346, "step": 9222 }, { "epoch": 0.4962871287128713, "grad_norm": 3.17175030708313, "learning_rate": 2.5295827531025185e-05, "loss": 4.4651, "step": 9223 }, { "epoch": 0.49634093844167027, "grad_norm": 2.028719663619995, "learning_rate": 2.5291601616493056e-05, "loss": 4.5677, "step": 9224 }, { "epoch": 0.49639474817046925, "grad_norm": 2.067885637283325, "learning_rate": 2.5287375693627735e-05, "loss": 4.1837, "step": 9225 }, { "epoch": 0.4964485578992682, "grad_norm": 4.429241180419922, "learning_rate": 2.528314976254999e-05, "loss": 4.368, "step": 9226 }, { "epoch": 0.49650236762806715, "grad_norm": 1.5104950666427612, "learning_rate": 2.5278923823380595e-05, "loss": 4.4637, "step": 9227 }, { "epoch": 0.49655617735686614, "grad_norm": 1.069130301475525, "learning_rate": 2.5274697876240296e-05, "loss": 4.2068, "step": 9228 }, { "epoch": 0.49660998708566506, "grad_norm": 1.596271276473999, "learning_rate": 2.5270471921249878e-05, "loss": 4.4565, "step": 9229 }, { "epoch": 0.49666379681446404, "grad_norm": 2.054304599761963, "learning_rate": 2.5266245958530098e-05, "loss": 4.1123, "step": 9230 }, { "epoch": 0.496717606543263, "grad_norm": 1.9937444925308228, "learning_rate": 2.5262019988201723e-05, "loss": 4.0476, "step": 9231 }, { "epoch": 0.496771416272062, "grad_norm": 2.1259264945983887, "learning_rate": 2.5257794010385523e-05, "loss": 4.7405, "step": 9232 }, { "epoch": 0.49682522600086093, "grad_norm": 1.8450226783752441, "learning_rate": 2.5253568025202257e-05, "loss": 4.3324, "step": 9233 }, { "epoch": 0.4968790357296599, "grad_norm": 1.2301225662231445, "learning_rate": 2.5249342032772715e-05, "loss": 4.5935, "step": 9234 }, { "epoch": 0.4969328454584589, "grad_norm": 2.699542760848999, "learning_rate": 2.524511603321763e-05, "loss": 4.5219, "step": 9235 }, { "epoch": 0.4969866551872579, "grad_norm": 3.1901938915252686, "learning_rate": 2.5240890026657797e-05, "loss": 4.2515, "step": 9236 }, { "epoch": 0.4970404649160568, "grad_norm": 3.074202060699463, "learning_rate": 2.5236664013213978e-05, "loss": 3.6109, "step": 9237 }, { "epoch": 0.4970942746448558, "grad_norm": 1.3801703453063965, "learning_rate": 2.5232437993006936e-05, "loss": 4.7212, "step": 9238 }, { "epoch": 0.49714808437365476, "grad_norm": 2.6921982765197754, "learning_rate": 2.522821196615744e-05, "loss": 3.7173, "step": 9239 }, { "epoch": 0.49720189410245375, "grad_norm": 1.0934380292892456, "learning_rate": 2.5223985932786258e-05, "loss": 4.6226, "step": 9240 }, { "epoch": 0.49725570383125267, "grad_norm": 1.9972676038742065, "learning_rate": 2.521975989301416e-05, "loss": 4.0911, "step": 9241 }, { "epoch": 0.49730951356005165, "grad_norm": 3.1407244205474854, "learning_rate": 2.5215533846961918e-05, "loss": 3.5041, "step": 9242 }, { "epoch": 0.49736332328885063, "grad_norm": 2.468107223510742, "learning_rate": 2.52113077947503e-05, "loss": 3.9275, "step": 9243 }, { "epoch": 0.4974171330176496, "grad_norm": 1.7164112329483032, "learning_rate": 2.520708173650007e-05, "loss": 4.1185, "step": 9244 }, { "epoch": 0.49747094274644854, "grad_norm": 2.974209785461426, "learning_rate": 2.5202855672332005e-05, "loss": 3.1632, "step": 9245 }, { "epoch": 0.4975247524752475, "grad_norm": 1.3965229988098145, "learning_rate": 2.5198629602366863e-05, "loss": 4.179, "step": 9246 }, { "epoch": 0.4975785622040465, "grad_norm": 1.9021929502487183, "learning_rate": 2.519440352672543e-05, "loss": 3.9478, "step": 9247 }, { "epoch": 0.4976323719328455, "grad_norm": 1.4285110235214233, "learning_rate": 2.5190177445528463e-05, "loss": 4.7254, "step": 9248 }, { "epoch": 0.4976861816616444, "grad_norm": 2.105219602584839, "learning_rate": 2.518595135889673e-05, "loss": 5.0001, "step": 9249 }, { "epoch": 0.4977399913904434, "grad_norm": 2.6934092044830322, "learning_rate": 2.5181725266951024e-05, "loss": 4.5836, "step": 9250 }, { "epoch": 0.4977938011192424, "grad_norm": 1.7689546346664429, "learning_rate": 2.517749916981208e-05, "loss": 4.2189, "step": 9251 }, { "epoch": 0.4978476108480413, "grad_norm": 3.6337811946868896, "learning_rate": 2.5173273067600694e-05, "loss": 3.5147, "step": 9252 }, { "epoch": 0.4979014205768403, "grad_norm": 2.164496421813965, "learning_rate": 2.5169046960437637e-05, "loss": 4.1507, "step": 9253 }, { "epoch": 0.49795523030563926, "grad_norm": 1.4309046268463135, "learning_rate": 2.5164820848443665e-05, "loss": 4.4379, "step": 9254 }, { "epoch": 0.49800904003443824, "grad_norm": 3.617617607116699, "learning_rate": 2.516059473173956e-05, "loss": 3.7937, "step": 9255 }, { "epoch": 0.49806284976323717, "grad_norm": 2.1579041481018066, "learning_rate": 2.515636861044608e-05, "loss": 4.4112, "step": 9256 }, { "epoch": 0.49811665949203615, "grad_norm": 1.7891758680343628, "learning_rate": 2.515214248468402e-05, "loss": 4.7122, "step": 9257 }, { "epoch": 0.49817046922083513, "grad_norm": 3.1228582859039307, "learning_rate": 2.5147916354574132e-05, "loss": 4.0879, "step": 9258 }, { "epoch": 0.4982242789496341, "grad_norm": 1.8677482604980469, "learning_rate": 2.5143690220237186e-05, "loss": 4.3761, "step": 9259 }, { "epoch": 0.49827808867843304, "grad_norm": 2.881852865219116, "learning_rate": 2.5139464081793967e-05, "loss": 4.0258, "step": 9260 }, { "epoch": 0.498331898407232, "grad_norm": 1.3316670656204224, "learning_rate": 2.5135237939365235e-05, "loss": 4.406, "step": 9261 }, { "epoch": 0.498385708136031, "grad_norm": 2.619554281234741, "learning_rate": 2.5131011793071772e-05, "loss": 3.8778, "step": 9262 }, { "epoch": 0.49843951786483, "grad_norm": 1.8345296382904053, "learning_rate": 2.512678564303434e-05, "loss": 4.4734, "step": 9263 }, { "epoch": 0.4984933275936289, "grad_norm": 2.1643877029418945, "learning_rate": 2.5122559489373716e-05, "loss": 4.0228, "step": 9264 }, { "epoch": 0.4985471373224279, "grad_norm": 2.256197452545166, "learning_rate": 2.5118333332210676e-05, "loss": 4.8993, "step": 9265 }, { "epoch": 0.4986009470512269, "grad_norm": 1.918533444404602, "learning_rate": 2.511410717166598e-05, "loss": 4.2764, "step": 9266 }, { "epoch": 0.49865475678002585, "grad_norm": 1.593012809753418, "learning_rate": 2.5109881007860415e-05, "loss": 4.2752, "step": 9267 }, { "epoch": 0.4987085665088248, "grad_norm": 1.5770834684371948, "learning_rate": 2.5105654840914737e-05, "loss": 4.0134, "step": 9268 }, { "epoch": 0.49876237623762376, "grad_norm": 2.6490323543548584, "learning_rate": 2.510142867094974e-05, "loss": 4.1293, "step": 9269 }, { "epoch": 0.49881618596642274, "grad_norm": 1.8482009172439575, "learning_rate": 2.5097202498086174e-05, "loss": 4.6177, "step": 9270 }, { "epoch": 0.49886999569522167, "grad_norm": 1.2285903692245483, "learning_rate": 2.509297632244483e-05, "loss": 4.4569, "step": 9271 }, { "epoch": 0.49892380542402065, "grad_norm": 2.1194167137145996, "learning_rate": 2.5088750144146467e-05, "loss": 4.3266, "step": 9272 }, { "epoch": 0.49897761515281963, "grad_norm": 1.5582184791564941, "learning_rate": 2.5084523963311868e-05, "loss": 4.0761, "step": 9273 }, { "epoch": 0.4990314248816186, "grad_norm": 1.7291747331619263, "learning_rate": 2.5080297780061796e-05, "loss": 3.995, "step": 9274 }, { "epoch": 0.49908523461041754, "grad_norm": 2.659562826156616, "learning_rate": 2.507607159451703e-05, "loss": 3.9552, "step": 9275 }, { "epoch": 0.4991390443392165, "grad_norm": 2.070685863494873, "learning_rate": 2.5071845406798356e-05, "loss": 4.2491, "step": 9276 }, { "epoch": 0.4991928540680155, "grad_norm": 2.3949129581451416, "learning_rate": 2.5067619217026516e-05, "loss": 3.6372, "step": 9277 }, { "epoch": 0.4992466637968145, "grad_norm": 1.9459437131881714, "learning_rate": 2.5063393025322306e-05, "loss": 4.2251, "step": 9278 }, { "epoch": 0.4993004735256134, "grad_norm": 2.720635175704956, "learning_rate": 2.5059166831806496e-05, "loss": 4.1944, "step": 9279 }, { "epoch": 0.4993542832544124, "grad_norm": 2.3228516578674316, "learning_rate": 2.5054940636599855e-05, "loss": 4.522, "step": 9280 }, { "epoch": 0.49940809298321137, "grad_norm": 3.3087551593780518, "learning_rate": 2.5050714439823165e-05, "loss": 4.2248, "step": 9281 }, { "epoch": 0.49946190271201035, "grad_norm": 2.326519250869751, "learning_rate": 2.5046488241597177e-05, "loss": 4.3194, "step": 9282 }, { "epoch": 0.4995157124408093, "grad_norm": 1.9942281246185303, "learning_rate": 2.5042262042042692e-05, "loss": 4.3381, "step": 9283 }, { "epoch": 0.49956952216960826, "grad_norm": 2.173677444458008, "learning_rate": 2.503803584128047e-05, "loss": 3.7362, "step": 9284 }, { "epoch": 0.49962333189840724, "grad_norm": 2.7495312690734863, "learning_rate": 2.503380963943129e-05, "loss": 3.5121, "step": 9285 }, { "epoch": 0.4996771416272062, "grad_norm": 1.762474536895752, "learning_rate": 2.5029583436615918e-05, "loss": 4.494, "step": 9286 }, { "epoch": 0.49973095135600515, "grad_norm": 2.541440725326538, "learning_rate": 2.502535723295512e-05, "loss": 4.4896, "step": 9287 }, { "epoch": 0.49978476108480413, "grad_norm": 2.3094193935394287, "learning_rate": 2.50211310285697e-05, "loss": 4.6163, "step": 9288 }, { "epoch": 0.4998385708136031, "grad_norm": 1.103143334388733, "learning_rate": 2.50169048235804e-05, "loss": 4.9879, "step": 9289 }, { "epoch": 0.4998923805424021, "grad_norm": 1.3998799324035645, "learning_rate": 2.5012678618108004e-05, "loss": 4.4413, "step": 9290 }, { "epoch": 0.499946190271201, "grad_norm": 2.7103946208953857, "learning_rate": 2.5008452412273292e-05, "loss": 4.1337, "step": 9291 }, { "epoch": 0.5, "grad_norm": 1.4139982461929321, "learning_rate": 2.5004226206197033e-05, "loss": 4.5348, "step": 9292 }, { "epoch": 0.500053809728799, "grad_norm": 2.213920831680298, "learning_rate": 2.5e-05, "loss": 4.0509, "step": 9293 }, { "epoch": 0.500107619457598, "grad_norm": 2.9254047870635986, "learning_rate": 2.499577379380297e-05, "loss": 3.2891, "step": 9294 }, { "epoch": 0.5001614291863969, "grad_norm": 2.2273898124694824, "learning_rate": 2.4991547587726704e-05, "loss": 4.3036, "step": 9295 }, { "epoch": 0.5002152389151958, "grad_norm": 1.5901591777801514, "learning_rate": 2.4987321381891992e-05, "loss": 4.5392, "step": 9296 }, { "epoch": 0.5002690486439948, "grad_norm": 2.024702548980713, "learning_rate": 2.4983095176419607e-05, "loss": 4.2789, "step": 9297 }, { "epoch": 0.5003228583727938, "grad_norm": 1.7772464752197266, "learning_rate": 2.497886897143031e-05, "loss": 4.0529, "step": 9298 }, { "epoch": 0.5003766681015928, "grad_norm": 1.881083369255066, "learning_rate": 2.4974642767044883e-05, "loss": 4.0972, "step": 9299 }, { "epoch": 0.5004304778303917, "grad_norm": 2.3846187591552734, "learning_rate": 2.4970416563384088e-05, "loss": 4.4225, "step": 9300 }, { "epoch": 0.5004842875591907, "grad_norm": 2.2932584285736084, "learning_rate": 2.4966190360568716e-05, "loss": 3.7927, "step": 9301 }, { "epoch": 0.5005380972879897, "grad_norm": 1.7124361991882324, "learning_rate": 2.4961964158719535e-05, "loss": 4.3731, "step": 9302 }, { "epoch": 0.5005919070167887, "grad_norm": 2.622528076171875, "learning_rate": 2.4957737957957307e-05, "loss": 4.355, "step": 9303 }, { "epoch": 0.5006457167455876, "grad_norm": 2.178908586502075, "learning_rate": 2.495351175840282e-05, "loss": 4.1917, "step": 9304 }, { "epoch": 0.5006995264743865, "grad_norm": 3.274754762649536, "learning_rate": 2.4949285560176848e-05, "loss": 3.7846, "step": 9305 }, { "epoch": 0.5007533362031855, "grad_norm": 2.4407012462615967, "learning_rate": 2.4945059363400154e-05, "loss": 3.42, "step": 9306 }, { "epoch": 0.5008071459319845, "grad_norm": 1.930580496788025, "learning_rate": 2.494083316819351e-05, "loss": 3.9303, "step": 9307 }, { "epoch": 0.5008609556607835, "grad_norm": 2.2359230518341064, "learning_rate": 2.49366069746777e-05, "loss": 4.1738, "step": 9308 }, { "epoch": 0.5009147653895825, "grad_norm": 1.355941891670227, "learning_rate": 2.4932380782973493e-05, "loss": 4.2607, "step": 9309 }, { "epoch": 0.5009685751183814, "grad_norm": 1.4947797060012817, "learning_rate": 2.4928154593201653e-05, "loss": 4.0337, "step": 9310 }, { "epoch": 0.5010223848471804, "grad_norm": 2.604090929031372, "learning_rate": 2.492392840548297e-05, "loss": 4.6697, "step": 9311 }, { "epoch": 0.5010761945759793, "grad_norm": 2.5518057346343994, "learning_rate": 2.4919702219938203e-05, "loss": 3.4414, "step": 9312 }, { "epoch": 0.5011300043047783, "grad_norm": 1.8418469429016113, "learning_rate": 2.4915476036688144e-05, "loss": 3.9611, "step": 9313 }, { "epoch": 0.5011838140335773, "grad_norm": 1.480658769607544, "learning_rate": 2.4911249855853542e-05, "loss": 4.5581, "step": 9314 }, { "epoch": 0.5012376237623762, "grad_norm": 1.6608335971832275, "learning_rate": 2.4907023677555177e-05, "loss": 3.7761, "step": 9315 }, { "epoch": 0.5012914334911752, "grad_norm": 2.245305061340332, "learning_rate": 2.4902797501913828e-05, "loss": 4.0239, "step": 9316 }, { "epoch": 0.5013452432199742, "grad_norm": 3.2755234241485596, "learning_rate": 2.489857132905027e-05, "loss": 2.6989, "step": 9317 }, { "epoch": 0.5013990529487732, "grad_norm": 3.0545310974121094, "learning_rate": 2.4894345159085262e-05, "loss": 3.7167, "step": 9318 }, { "epoch": 0.501452862677572, "grad_norm": 2.0010783672332764, "learning_rate": 2.4890118992139588e-05, "loss": 3.679, "step": 9319 }, { "epoch": 0.501506672406371, "grad_norm": 2.4660210609436035, "learning_rate": 2.4885892828334027e-05, "loss": 4.3097, "step": 9320 }, { "epoch": 0.50156048213517, "grad_norm": 1.4901820421218872, "learning_rate": 2.4881666667789337e-05, "loss": 4.4756, "step": 9321 }, { "epoch": 0.501614291863969, "grad_norm": 2.165626049041748, "learning_rate": 2.487744051062629e-05, "loss": 4.2116, "step": 9322 }, { "epoch": 0.501668101592768, "grad_norm": 1.2287700176239014, "learning_rate": 2.4873214356965663e-05, "loss": 4.6054, "step": 9323 }, { "epoch": 0.501721911321567, "grad_norm": 1.5054911375045776, "learning_rate": 2.4868988206928234e-05, "loss": 4.157, "step": 9324 }, { "epoch": 0.5017757210503659, "grad_norm": 2.4042837619781494, "learning_rate": 2.4864762060634768e-05, "loss": 4.5296, "step": 9325 }, { "epoch": 0.5018295307791649, "grad_norm": 2.4513299465179443, "learning_rate": 2.4860535918206035e-05, "loss": 3.7956, "step": 9326 }, { "epoch": 0.5018833405079638, "grad_norm": 3.12088680267334, "learning_rate": 2.4856309779762813e-05, "loss": 3.9034, "step": 9327 }, { "epoch": 0.5019371502367628, "grad_norm": 2.84480619430542, "learning_rate": 2.4852083645425877e-05, "loss": 3.6787, "step": 9328 }, { "epoch": 0.5019909599655618, "grad_norm": 2.1500651836395264, "learning_rate": 2.484785751531599e-05, "loss": 4.3139, "step": 9329 }, { "epoch": 0.5020447696943607, "grad_norm": 1.6823629140853882, "learning_rate": 2.4843631389553924e-05, "loss": 4.3397, "step": 9330 }, { "epoch": 0.5020985794231597, "grad_norm": 2.1729397773742676, "learning_rate": 2.4839405268260445e-05, "loss": 4.2487, "step": 9331 }, { "epoch": 0.5021523891519587, "grad_norm": 3.366400957107544, "learning_rate": 2.483517915155634e-05, "loss": 3.5723, "step": 9332 }, { "epoch": 0.5022061988807577, "grad_norm": 2.1596381664276123, "learning_rate": 2.4830953039562373e-05, "loss": 3.9598, "step": 9333 }, { "epoch": 0.5022600086095567, "grad_norm": 2.1555228233337402, "learning_rate": 2.48267269323993e-05, "loss": 3.9302, "step": 9334 }, { "epoch": 0.5023138183383555, "grad_norm": 1.9629409313201904, "learning_rate": 2.482250083018792e-05, "loss": 4.0969, "step": 9335 }, { "epoch": 0.5023676280671545, "grad_norm": 2.0591769218444824, "learning_rate": 2.4818274733048992e-05, "loss": 3.7143, "step": 9336 }, { "epoch": 0.5024214377959535, "grad_norm": 2.4465384483337402, "learning_rate": 2.4814048641103274e-05, "loss": 4.3816, "step": 9337 }, { "epoch": 0.5024752475247525, "grad_norm": 2.8434276580810547, "learning_rate": 2.4809822554471543e-05, "loss": 4.0111, "step": 9338 }, { "epoch": 0.5025290572535515, "grad_norm": 2.5880284309387207, "learning_rate": 2.4805596473274575e-05, "loss": 3.6554, "step": 9339 }, { "epoch": 0.5025828669823504, "grad_norm": 1.947755217552185, "learning_rate": 2.480137039763314e-05, "loss": 4.7753, "step": 9340 }, { "epoch": 0.5026366767111494, "grad_norm": 2.3896024227142334, "learning_rate": 2.4797144327667998e-05, "loss": 4.284, "step": 9341 }, { "epoch": 0.5026904864399483, "grad_norm": 1.7231371402740479, "learning_rate": 2.4792918263499933e-05, "loss": 4.2662, "step": 9342 }, { "epoch": 0.5027442961687473, "grad_norm": 2.547755718231201, "learning_rate": 2.4788692205249707e-05, "loss": 3.6854, "step": 9343 }, { "epoch": 0.5027981058975463, "grad_norm": 2.1673388481140137, "learning_rate": 2.4784466153038088e-05, "loss": 3.9538, "step": 9344 }, { "epoch": 0.5028519156263452, "grad_norm": 2.100446939468384, "learning_rate": 2.4780240106985848e-05, "loss": 3.9338, "step": 9345 }, { "epoch": 0.5029057253551442, "grad_norm": 3.056130886077881, "learning_rate": 2.4776014067213744e-05, "loss": 3.8633, "step": 9346 }, { "epoch": 0.5029595350839432, "grad_norm": 2.5771377086639404, "learning_rate": 2.4771788033842567e-05, "loss": 4.5467, "step": 9347 }, { "epoch": 0.5030133448127422, "grad_norm": 2.342040777206421, "learning_rate": 2.4767562006993073e-05, "loss": 4.1803, "step": 9348 }, { "epoch": 0.5030671545415412, "grad_norm": 1.5986294746398926, "learning_rate": 2.4763335986786024e-05, "loss": 4.2686, "step": 9349 }, { "epoch": 0.50312096427034, "grad_norm": 2.976834297180176, "learning_rate": 2.47591099733422e-05, "loss": 3.8826, "step": 9350 }, { "epoch": 0.503174773999139, "grad_norm": 1.081220269203186, "learning_rate": 2.4754883966782375e-05, "loss": 4.3929, "step": 9351 }, { "epoch": 0.503228583727938, "grad_norm": 2.914435863494873, "learning_rate": 2.4750657967227298e-05, "loss": 4.0216, "step": 9352 }, { "epoch": 0.503282393456737, "grad_norm": 1.9333134889602661, "learning_rate": 2.4746431974797746e-05, "loss": 4.3883, "step": 9353 }, { "epoch": 0.503336203185536, "grad_norm": 1.5540050268173218, "learning_rate": 2.474220598961448e-05, "loss": 4.2138, "step": 9354 }, { "epoch": 0.5033900129143349, "grad_norm": 2.1551756858825684, "learning_rate": 2.4737980011798283e-05, "loss": 3.2926, "step": 9355 }, { "epoch": 0.5034438226431339, "grad_norm": 2.216719150543213, "learning_rate": 2.4733754041469907e-05, "loss": 4.3137, "step": 9356 }, { "epoch": 0.5034976323719328, "grad_norm": 1.3026843070983887, "learning_rate": 2.472952807875012e-05, "loss": 4.4004, "step": 9357 }, { "epoch": 0.5035514421007318, "grad_norm": 2.885498523712158, "learning_rate": 2.4725302123759714e-05, "loss": 4.3885, "step": 9358 }, { "epoch": 0.5036052518295308, "grad_norm": 2.744051694869995, "learning_rate": 2.4721076176619414e-05, "loss": 3.4225, "step": 9359 }, { "epoch": 0.5036590615583297, "grad_norm": 2.2051165103912354, "learning_rate": 2.4716850237450014e-05, "loss": 4.1001, "step": 9360 }, { "epoch": 0.5037128712871287, "grad_norm": 2.3650527000427246, "learning_rate": 2.471262430637227e-05, "loss": 3.4973, "step": 9361 }, { "epoch": 0.5037666810159277, "grad_norm": 2.369807004928589, "learning_rate": 2.470839838350695e-05, "loss": 4.2276, "step": 9362 }, { "epoch": 0.5038204907447267, "grad_norm": 1.3304576873779297, "learning_rate": 2.4704172468974824e-05, "loss": 4.3964, "step": 9363 }, { "epoch": 0.5038743004735257, "grad_norm": 2.2054226398468018, "learning_rate": 2.469994656289665e-05, "loss": 4.6529, "step": 9364 }, { "epoch": 0.5039281102023245, "grad_norm": 2.7074782848358154, "learning_rate": 2.469572066539319e-05, "loss": 4.0039, "step": 9365 }, { "epoch": 0.5039819199311235, "grad_norm": 2.2087676525115967, "learning_rate": 2.469149477658523e-05, "loss": 4.054, "step": 9366 }, { "epoch": 0.5040357296599225, "grad_norm": 1.3547413349151611, "learning_rate": 2.468726889659351e-05, "loss": 4.2331, "step": 9367 }, { "epoch": 0.5040895393887215, "grad_norm": 1.6463797092437744, "learning_rate": 2.4683043025538807e-05, "loss": 3.9776, "step": 9368 }, { "epoch": 0.5041433491175205, "grad_norm": 2.7618327140808105, "learning_rate": 2.4678817163541877e-05, "loss": 4.4804, "step": 9369 }, { "epoch": 0.5041971588463194, "grad_norm": 2.2210593223571777, "learning_rate": 2.467459131072349e-05, "loss": 4.2334, "step": 9370 }, { "epoch": 0.5042509685751184, "grad_norm": 2.5293703079223633, "learning_rate": 2.467036546720441e-05, "loss": 4.0766, "step": 9371 }, { "epoch": 0.5043047783039174, "grad_norm": 2.4422740936279297, "learning_rate": 2.4666139633105396e-05, "loss": 3.9263, "step": 9372 }, { "epoch": 0.5043585880327163, "grad_norm": 2.5622761249542236, "learning_rate": 2.4661913808547213e-05, "loss": 3.8933, "step": 9373 }, { "epoch": 0.5044123977615153, "grad_norm": 2.971139430999756, "learning_rate": 2.4657687993650634e-05, "loss": 3.8575, "step": 9374 }, { "epoch": 0.5044662074903142, "grad_norm": 1.2035328149795532, "learning_rate": 2.46534621885364e-05, "loss": 4.1689, "step": 9375 }, { "epoch": 0.5045200172191132, "grad_norm": 1.3245638608932495, "learning_rate": 2.464923639332529e-05, "loss": 4.5187, "step": 9376 }, { "epoch": 0.5045738269479122, "grad_norm": 3.231322765350342, "learning_rate": 2.4645010608138054e-05, "loss": 3.5207, "step": 9377 }, { "epoch": 0.5046276366767112, "grad_norm": 2.161109685897827, "learning_rate": 2.4640784833095467e-05, "loss": 3.7914, "step": 9378 }, { "epoch": 0.5046814464055102, "grad_norm": 1.973152995109558, "learning_rate": 2.463655906831828e-05, "loss": 4.4014, "step": 9379 }, { "epoch": 0.504735256134309, "grad_norm": 1.0327043533325195, "learning_rate": 2.4632333313927254e-05, "loss": 4.8443, "step": 9380 }, { "epoch": 0.504789065863108, "grad_norm": 2.3591527938842773, "learning_rate": 2.462810757004317e-05, "loss": 3.7392, "step": 9381 }, { "epoch": 0.504842875591907, "grad_norm": 3.4409759044647217, "learning_rate": 2.4623881836786757e-05, "loss": 4.129, "step": 9382 }, { "epoch": 0.504896685320706, "grad_norm": 1.8298338651657104, "learning_rate": 2.461965611427879e-05, "loss": 4.4327, "step": 9383 }, { "epoch": 0.504950495049505, "grad_norm": 2.0320334434509277, "learning_rate": 2.461543040264003e-05, "loss": 4.2161, "step": 9384 }, { "epoch": 0.5050043047783039, "grad_norm": 1.2276581525802612, "learning_rate": 2.4611204701991227e-05, "loss": 4.3382, "step": 9385 }, { "epoch": 0.5050581145071029, "grad_norm": 2.602588653564453, "learning_rate": 2.460697901245316e-05, "loss": 4.5669, "step": 9386 }, { "epoch": 0.5051119242359019, "grad_norm": 3.04093337059021, "learning_rate": 2.460275333414657e-05, "loss": 3.8248, "step": 9387 }, { "epoch": 0.5051657339647008, "grad_norm": 2.1847662925720215, "learning_rate": 2.459852766719222e-05, "loss": 3.7521, "step": 9388 }, { "epoch": 0.5052195436934998, "grad_norm": 2.0342063903808594, "learning_rate": 2.459430201171088e-05, "loss": 4.2326, "step": 9389 }, { "epoch": 0.5052733534222987, "grad_norm": 3.2956345081329346, "learning_rate": 2.4590076367823283e-05, "loss": 3.7186, "step": 9390 }, { "epoch": 0.5053271631510977, "grad_norm": 2.112239360809326, "learning_rate": 2.4585850735650206e-05, "loss": 3.8242, "step": 9391 }, { "epoch": 0.5053809728798967, "grad_norm": 1.5652128458023071, "learning_rate": 2.4581625115312403e-05, "loss": 4.2311, "step": 9392 }, { "epoch": 0.5054347826086957, "grad_norm": 1.7017284631729126, "learning_rate": 2.4577399506930625e-05, "loss": 4.3612, "step": 9393 }, { "epoch": 0.5054885923374947, "grad_norm": 2.018660068511963, "learning_rate": 2.4573173910625633e-05, "loss": 4.6372, "step": 9394 }, { "epoch": 0.5055424020662936, "grad_norm": 1.796107292175293, "learning_rate": 2.4568948326518183e-05, "loss": 4.0885, "step": 9395 }, { "epoch": 0.5055962117950925, "grad_norm": 2.209718704223633, "learning_rate": 2.4564722754729032e-05, "loss": 4.102, "step": 9396 }, { "epoch": 0.5056500215238915, "grad_norm": 2.4453933238983154, "learning_rate": 2.456049719537894e-05, "loss": 4.0122, "step": 9397 }, { "epoch": 0.5057038312526905, "grad_norm": 1.5586975812911987, "learning_rate": 2.455627164858865e-05, "loss": 4.1319, "step": 9398 }, { "epoch": 0.5057576409814895, "grad_norm": 2.541804790496826, "learning_rate": 2.4552046114478923e-05, "loss": 4.0012, "step": 9399 }, { "epoch": 0.5058114507102884, "grad_norm": 3.111957550048828, "learning_rate": 2.4547820593170506e-05, "loss": 4.2869, "step": 9400 }, { "epoch": 0.5058652604390874, "grad_norm": 3.0705435276031494, "learning_rate": 2.454359508478417e-05, "loss": 4.0174, "step": 9401 }, { "epoch": 0.5059190701678864, "grad_norm": 1.765897512435913, "learning_rate": 2.4539369589440656e-05, "loss": 4.4259, "step": 9402 }, { "epoch": 0.5059728798966853, "grad_norm": 2.651179313659668, "learning_rate": 2.4535144107260716e-05, "loss": 4.3927, "step": 9403 }, { "epoch": 0.5060266896254842, "grad_norm": 1.7364797592163086, "learning_rate": 2.4530918638365122e-05, "loss": 4.4694, "step": 9404 }, { "epoch": 0.5060804993542832, "grad_norm": 2.33091139793396, "learning_rate": 2.4526693182874597e-05, "loss": 3.505, "step": 9405 }, { "epoch": 0.5061343090830822, "grad_norm": 2.948460102081299, "learning_rate": 2.452246774090991e-05, "loss": 3.0782, "step": 9406 }, { "epoch": 0.5061881188118812, "grad_norm": 2.528069496154785, "learning_rate": 2.4518242312591814e-05, "loss": 3.8527, "step": 9407 }, { "epoch": 0.5062419285406802, "grad_norm": 2.6318306922912598, "learning_rate": 2.451401689804105e-05, "loss": 4.2229, "step": 9408 }, { "epoch": 0.5062957382694792, "grad_norm": 2.5417280197143555, "learning_rate": 2.4509791497378383e-05, "loss": 3.8243, "step": 9409 }, { "epoch": 0.5063495479982781, "grad_norm": 1.7588835954666138, "learning_rate": 2.4505566110724555e-05, "loss": 4.385, "step": 9410 }, { "epoch": 0.506403357727077, "grad_norm": 1.7037818431854248, "learning_rate": 2.450134073820031e-05, "loss": 4.1701, "step": 9411 }, { "epoch": 0.506457167455876, "grad_norm": 2.032012462615967, "learning_rate": 2.4497115379926428e-05, "loss": 4.7715, "step": 9412 }, { "epoch": 0.506510977184675, "grad_norm": 2.1631240844726562, "learning_rate": 2.4492890036023613e-05, "loss": 4.2168, "step": 9413 }, { "epoch": 0.506564786913474, "grad_norm": 2.161799669265747, "learning_rate": 2.4488664706612645e-05, "loss": 4.1363, "step": 9414 }, { "epoch": 0.5066185966422729, "grad_norm": 2.3771770000457764, "learning_rate": 2.4484439391814265e-05, "loss": 4.4771, "step": 9415 }, { "epoch": 0.5066724063710719, "grad_norm": 2.571552276611328, "learning_rate": 2.4480214091749214e-05, "loss": 3.5211, "step": 9416 }, { "epoch": 0.5067262160998709, "grad_norm": 1.0518687963485718, "learning_rate": 2.447598880653825e-05, "loss": 4.401, "step": 9417 }, { "epoch": 0.5067800258286699, "grad_norm": 2.8082468509674072, "learning_rate": 2.4471763536302123e-05, "loss": 3.4458, "step": 9418 }, { "epoch": 0.5068338355574687, "grad_norm": 2.5654637813568115, "learning_rate": 2.446753828116156e-05, "loss": 3.9427, "step": 9419 }, { "epoch": 0.5068876452862677, "grad_norm": 2.1131296157836914, "learning_rate": 2.4463313041237344e-05, "loss": 4.371, "step": 9420 }, { "epoch": 0.5069414550150667, "grad_norm": 2.3298532962799072, "learning_rate": 2.445908781665018e-05, "loss": 4.5253, "step": 9421 }, { "epoch": 0.5069952647438657, "grad_norm": 2.0057260990142822, "learning_rate": 2.445486260752083e-05, "loss": 4.1307, "step": 9422 }, { "epoch": 0.5070490744726647, "grad_norm": 2.5873489379882812, "learning_rate": 2.4450637413970047e-05, "loss": 3.7502, "step": 9423 }, { "epoch": 0.5071028842014637, "grad_norm": 1.1613807678222656, "learning_rate": 2.4446412236118562e-05, "loss": 4.1201, "step": 9424 }, { "epoch": 0.5071566939302626, "grad_norm": 2.9459197521209717, "learning_rate": 2.444218707408713e-05, "loss": 3.6787, "step": 9425 }, { "epoch": 0.5072105036590615, "grad_norm": 1.7477360963821411, "learning_rate": 2.4437961927996495e-05, "loss": 4.013, "step": 9426 }, { "epoch": 0.5072643133878605, "grad_norm": 2.354085683822632, "learning_rate": 2.44337367979674e-05, "loss": 4.4033, "step": 9427 }, { "epoch": 0.5073181231166595, "grad_norm": 2.1283864974975586, "learning_rate": 2.442951168412057e-05, "loss": 4.3384, "step": 9428 }, { "epoch": 0.5073719328454585, "grad_norm": 1.5566537380218506, "learning_rate": 2.442528658657677e-05, "loss": 4.2832, "step": 9429 }, { "epoch": 0.5074257425742574, "grad_norm": 1.9050880670547485, "learning_rate": 2.4421061505456736e-05, "loss": 4.4462, "step": 9430 }, { "epoch": 0.5074795523030564, "grad_norm": 1.5661497116088867, "learning_rate": 2.4416836440881196e-05, "loss": 4.5168, "step": 9431 }, { "epoch": 0.5075333620318554, "grad_norm": 1.227147102355957, "learning_rate": 2.4412611392970915e-05, "loss": 4.644, "step": 9432 }, { "epoch": 0.5075871717606544, "grad_norm": 1.3034778833389282, "learning_rate": 2.4408386361846614e-05, "loss": 4.4167, "step": 9433 }, { "epoch": 0.5076409814894532, "grad_norm": 2.139657735824585, "learning_rate": 2.4404161347629033e-05, "loss": 4.4575, "step": 9434 }, { "epoch": 0.5076947912182522, "grad_norm": 2.4794657230377197, "learning_rate": 2.439993635043894e-05, "loss": 3.8764, "step": 9435 }, { "epoch": 0.5077486009470512, "grad_norm": 1.8730241060256958, "learning_rate": 2.4395711370397033e-05, "loss": 4.1581, "step": 9436 }, { "epoch": 0.5078024106758502, "grad_norm": 2.266279458999634, "learning_rate": 2.4391486407624076e-05, "loss": 3.3776, "step": 9437 }, { "epoch": 0.5078562204046492, "grad_norm": 2.081857204437256, "learning_rate": 2.43872614622408e-05, "loss": 4.8153, "step": 9438 }, { "epoch": 0.5079100301334482, "grad_norm": 1.6347190141677856, "learning_rate": 2.438303653436794e-05, "loss": 4.0279, "step": 9439 }, { "epoch": 0.5079638398622471, "grad_norm": 2.42694354057312, "learning_rate": 2.4378811624126237e-05, "loss": 4.2911, "step": 9440 }, { "epoch": 0.5080176495910461, "grad_norm": 1.7373857498168945, "learning_rate": 2.437458673163643e-05, "loss": 4.7568, "step": 9441 }, { "epoch": 0.508071459319845, "grad_norm": 2.2989501953125, "learning_rate": 2.437036185701925e-05, "loss": 4.2177, "step": 9442 }, { "epoch": 0.508125269048644, "grad_norm": 1.6644304990768433, "learning_rate": 2.4366137000395444e-05, "loss": 4.4951, "step": 9443 }, { "epoch": 0.508179078777443, "grad_norm": 1.449560523033142, "learning_rate": 2.4361912161885724e-05, "loss": 4.3264, "step": 9444 }, { "epoch": 0.5082328885062419, "grad_norm": 1.2460355758666992, "learning_rate": 2.4357687341610847e-05, "loss": 4.3751, "step": 9445 }, { "epoch": 0.5082866982350409, "grad_norm": 1.468765139579773, "learning_rate": 2.4353462539691534e-05, "loss": 4.3303, "step": 9446 }, { "epoch": 0.5083405079638399, "grad_norm": 2.250190496444702, "learning_rate": 2.434923775624852e-05, "loss": 4.2281, "step": 9447 }, { "epoch": 0.5083943176926389, "grad_norm": 2.3280980587005615, "learning_rate": 2.4345012991402545e-05, "loss": 4.2111, "step": 9448 }, { "epoch": 0.5084481274214377, "grad_norm": 2.8321948051452637, "learning_rate": 2.4340788245274334e-05, "loss": 4.6629, "step": 9449 }, { "epoch": 0.5085019371502367, "grad_norm": 1.5719494819641113, "learning_rate": 2.433656351798463e-05, "loss": 3.9263, "step": 9450 }, { "epoch": 0.5085557468790357, "grad_norm": 2.896965265274048, "learning_rate": 2.4332338809654154e-05, "loss": 4.2606, "step": 9451 }, { "epoch": 0.5086095566078347, "grad_norm": 1.874277114868164, "learning_rate": 2.432811412040363e-05, "loss": 4.4932, "step": 9452 }, { "epoch": 0.5086633663366337, "grad_norm": 1.8487385511398315, "learning_rate": 2.43238894503538e-05, "loss": 4.1959, "step": 9453 }, { "epoch": 0.5087171760654327, "grad_norm": 3.2133874893188477, "learning_rate": 2.4319664799625396e-05, "loss": 3.2966, "step": 9454 }, { "epoch": 0.5087709857942316, "grad_norm": 2.1895487308502197, "learning_rate": 2.4315440168339135e-05, "loss": 4.2292, "step": 9455 }, { "epoch": 0.5088247955230306, "grad_norm": 2.8503952026367188, "learning_rate": 2.4311215556615758e-05, "loss": 4.3378, "step": 9456 }, { "epoch": 0.5088786052518295, "grad_norm": 1.5020004510879517, "learning_rate": 2.4306990964575986e-05, "loss": 4.2109, "step": 9457 }, { "epoch": 0.5089324149806285, "grad_norm": 2.6753342151641846, "learning_rate": 2.4302766392340556e-05, "loss": 4.314, "step": 9458 }, { "epoch": 0.5089862247094274, "grad_norm": 1.222580909729004, "learning_rate": 2.4298541840030177e-05, "loss": 4.5143, "step": 9459 }, { "epoch": 0.5090400344382264, "grad_norm": 1.699059009552002, "learning_rate": 2.429431730776559e-05, "loss": 4.0768, "step": 9460 }, { "epoch": 0.5090938441670254, "grad_norm": 1.4176619052886963, "learning_rate": 2.4290092795667515e-05, "loss": 4.1711, "step": 9461 }, { "epoch": 0.5091476538958244, "grad_norm": 2.0060882568359375, "learning_rate": 2.4285868303856674e-05, "loss": 4.26, "step": 9462 }, { "epoch": 0.5092014636246234, "grad_norm": 2.358276605606079, "learning_rate": 2.42816438324538e-05, "loss": 4.7282, "step": 9463 }, { "epoch": 0.5092552733534222, "grad_norm": 2.5657830238342285, "learning_rate": 2.4277419381579616e-05, "loss": 4.2545, "step": 9464 }, { "epoch": 0.5093090830822212, "grad_norm": 2.564117908477783, "learning_rate": 2.4273194951354847e-05, "loss": 4.5562, "step": 9465 }, { "epoch": 0.5093628928110202, "grad_norm": 2.125831365585327, "learning_rate": 2.4268970541900206e-05, "loss": 3.9879, "step": 9466 }, { "epoch": 0.5094167025398192, "grad_norm": 3.227083921432495, "learning_rate": 2.4264746153336414e-05, "loss": 3.4786, "step": 9467 }, { "epoch": 0.5094705122686182, "grad_norm": 2.805016279220581, "learning_rate": 2.4260521785784208e-05, "loss": 3.7502, "step": 9468 }, { "epoch": 0.5095243219974172, "grad_norm": 2.8783609867095947, "learning_rate": 2.42562974393643e-05, "loss": 3.7529, "step": 9469 }, { "epoch": 0.5095781317262161, "grad_norm": 2.354875326156616, "learning_rate": 2.4252073114197403e-05, "loss": 4.2659, "step": 9470 }, { "epoch": 0.5096319414550151, "grad_norm": 2.3674416542053223, "learning_rate": 2.4247848810404247e-05, "loss": 4.0882, "step": 9471 }, { "epoch": 0.509685751183814, "grad_norm": 2.6052627563476562, "learning_rate": 2.4243624528105556e-05, "loss": 4.5456, "step": 9472 }, { "epoch": 0.509739560912613, "grad_norm": 3.2403314113616943, "learning_rate": 2.423940026742204e-05, "loss": 4.1498, "step": 9473 }, { "epoch": 0.509793370641412, "grad_norm": 2.3506953716278076, "learning_rate": 2.4235176028474418e-05, "loss": 4.1548, "step": 9474 }, { "epoch": 0.5098471803702109, "grad_norm": 0.9821784496307373, "learning_rate": 2.4230951811383402e-05, "loss": 4.4408, "step": 9475 }, { "epoch": 0.5099009900990099, "grad_norm": 1.623188853263855, "learning_rate": 2.4226727616269717e-05, "loss": 4.4895, "step": 9476 }, { "epoch": 0.5099547998278089, "grad_norm": 1.999216914176941, "learning_rate": 2.422250344325408e-05, "loss": 4.2505, "step": 9477 }, { "epoch": 0.5100086095566079, "grad_norm": 2.5882368087768555, "learning_rate": 2.42182792924572e-05, "loss": 3.8533, "step": 9478 }, { "epoch": 0.5100624192854069, "grad_norm": 1.773142695426941, "learning_rate": 2.4214055163999798e-05, "loss": 4.4233, "step": 9479 }, { "epoch": 0.5101162290142057, "grad_norm": 2.4563746452331543, "learning_rate": 2.420983105800258e-05, "loss": 4.1924, "step": 9480 }, { "epoch": 0.5101700387430047, "grad_norm": 1.514401912689209, "learning_rate": 2.420560697458628e-05, "loss": 4.5071, "step": 9481 }, { "epoch": 0.5102238484718037, "grad_norm": 2.526414394378662, "learning_rate": 2.420138291387158e-05, "loss": 4.0911, "step": 9482 }, { "epoch": 0.5102776582006027, "grad_norm": 1.5224521160125732, "learning_rate": 2.4197158875979215e-05, "loss": 4.447, "step": 9483 }, { "epoch": 0.5103314679294016, "grad_norm": 2.4700889587402344, "learning_rate": 2.419293486102989e-05, "loss": 3.4954, "step": 9484 }, { "epoch": 0.5103852776582006, "grad_norm": 3.5494508743286133, "learning_rate": 2.4188710869144314e-05, "loss": 4.1862, "step": 9485 }, { "epoch": 0.5104390873869996, "grad_norm": 2.2053189277648926, "learning_rate": 2.41844869004432e-05, "loss": 3.5933, "step": 9486 }, { "epoch": 0.5104928971157985, "grad_norm": 1.1572606563568115, "learning_rate": 2.4180262955047255e-05, "loss": 4.5433, "step": 9487 }, { "epoch": 0.5105467068445975, "grad_norm": 1.5228766202926636, "learning_rate": 2.4176039033077196e-05, "loss": 4.5877, "step": 9488 }, { "epoch": 0.5106005165733964, "grad_norm": 1.9042913913726807, "learning_rate": 2.4171815134653724e-05, "loss": 4.2231, "step": 9489 }, { "epoch": 0.5106543263021954, "grad_norm": 1.8828716278076172, "learning_rate": 2.416759125989754e-05, "loss": 4.1778, "step": 9490 }, { "epoch": 0.5107081360309944, "grad_norm": 1.3553298711776733, "learning_rate": 2.4163367408929366e-05, "loss": 4.3546, "step": 9491 }, { "epoch": 0.5107619457597934, "grad_norm": 2.618791341781616, "learning_rate": 2.41591435818699e-05, "loss": 3.8255, "step": 9492 }, { "epoch": 0.5108157554885924, "grad_norm": 2.2028164863586426, "learning_rate": 2.4154919778839843e-05, "loss": 4.2756, "step": 9493 }, { "epoch": 0.5108695652173914, "grad_norm": 1.3723974227905273, "learning_rate": 2.415069599995991e-05, "loss": 4.4158, "step": 9494 }, { "epoch": 0.5109233749461902, "grad_norm": 1.7074576616287231, "learning_rate": 2.4146472245350805e-05, "loss": 3.9614, "step": 9495 }, { "epoch": 0.5109771846749892, "grad_norm": 2.580415964126587, "learning_rate": 2.414224851513323e-05, "loss": 4.2567, "step": 9496 }, { "epoch": 0.5110309944037882, "grad_norm": 1.5811752080917358, "learning_rate": 2.4138024809427877e-05, "loss": 4.3573, "step": 9497 }, { "epoch": 0.5110848041325872, "grad_norm": 3.084519147872925, "learning_rate": 2.4133801128355455e-05, "loss": 3.6487, "step": 9498 }, { "epoch": 0.5111386138613861, "grad_norm": 2.7674343585968018, "learning_rate": 2.4129577472036673e-05, "loss": 4.2987, "step": 9499 }, { "epoch": 0.5111924235901851, "grad_norm": 2.1003477573394775, "learning_rate": 2.4125353840592223e-05, "loss": 3.6699, "step": 9500 }, { "epoch": 0.5112462333189841, "grad_norm": 3.5944087505340576, "learning_rate": 2.4121130234142804e-05, "loss": 3.527, "step": 9501 }, { "epoch": 0.5113000430477831, "grad_norm": 2.6837899684906006, "learning_rate": 2.4116906652809125e-05, "loss": 4.0233, "step": 9502 }, { "epoch": 0.511353852776582, "grad_norm": 1.9785183668136597, "learning_rate": 2.4112683096711878e-05, "loss": 4.6309, "step": 9503 }, { "epoch": 0.5114076625053809, "grad_norm": 2.0656468868255615, "learning_rate": 2.4108459565971768e-05, "loss": 4.1597, "step": 9504 }, { "epoch": 0.5114614722341799, "grad_norm": 2.9886059761047363, "learning_rate": 2.4104236060709474e-05, "loss": 4.5924, "step": 9505 }, { "epoch": 0.5115152819629789, "grad_norm": 2.559907913208008, "learning_rate": 2.4100012581045705e-05, "loss": 4.2328, "step": 9506 }, { "epoch": 0.5115690916917779, "grad_norm": 3.2394859790802, "learning_rate": 2.4095789127101163e-05, "loss": 4.0444, "step": 9507 }, { "epoch": 0.5116229014205769, "grad_norm": 1.0097194910049438, "learning_rate": 2.409156569899653e-05, "loss": 4.6871, "step": 9508 }, { "epoch": 0.5116767111493759, "grad_norm": 2.083923101425171, "learning_rate": 2.4087342296852502e-05, "loss": 3.8065, "step": 9509 }, { "epoch": 0.5117305208781747, "grad_norm": 4.301025390625, "learning_rate": 2.4083118920789784e-05, "loss": 3.302, "step": 9510 }, { "epoch": 0.5117843306069737, "grad_norm": 2.8274221420288086, "learning_rate": 2.4078895570929067e-05, "loss": 3.5129, "step": 9511 }, { "epoch": 0.5118381403357727, "grad_norm": 1.4343925714492798, "learning_rate": 2.4074672247391028e-05, "loss": 4.3248, "step": 9512 }, { "epoch": 0.5118919500645717, "grad_norm": 1.793027639389038, "learning_rate": 2.4070448950296364e-05, "loss": 4.5166, "step": 9513 }, { "epoch": 0.5119457597933706, "grad_norm": 2.8290865421295166, "learning_rate": 2.4066225679765775e-05, "loss": 4.0409, "step": 9514 }, { "epoch": 0.5119995695221696, "grad_norm": 3.020984649658203, "learning_rate": 2.4062002435919943e-05, "loss": 3.9002, "step": 9515 }, { "epoch": 0.5120533792509686, "grad_norm": 1.9077643156051636, "learning_rate": 2.4057779218879552e-05, "loss": 4.3334, "step": 9516 }, { "epoch": 0.5121071889797676, "grad_norm": 1.2948696613311768, "learning_rate": 2.4053556028765302e-05, "loss": 4.7791, "step": 9517 }, { "epoch": 0.5121609987085665, "grad_norm": 2.5015926361083984, "learning_rate": 2.404933286569788e-05, "loss": 4.2466, "step": 9518 }, { "epoch": 0.5122148084373654, "grad_norm": 2.212881326675415, "learning_rate": 2.404510972979797e-05, "loss": 4.1971, "step": 9519 }, { "epoch": 0.5122686181661644, "grad_norm": 1.4408929347991943, "learning_rate": 2.404088662118625e-05, "loss": 4.2151, "step": 9520 }, { "epoch": 0.5123224278949634, "grad_norm": 0.9487324953079224, "learning_rate": 2.4036663539983404e-05, "loss": 4.5503, "step": 9521 }, { "epoch": 0.5123762376237624, "grad_norm": 1.7128266096115112, "learning_rate": 2.403244048631013e-05, "loss": 4.3908, "step": 9522 }, { "epoch": 0.5124300473525614, "grad_norm": 2.698753595352173, "learning_rate": 2.4028217460287104e-05, "loss": 4.0268, "step": 9523 }, { "epoch": 0.5124838570813603, "grad_norm": 2.3761696815490723, "learning_rate": 2.4023994462035005e-05, "loss": 4.2252, "step": 9524 }, { "epoch": 0.5125376668101593, "grad_norm": 2.6054275035858154, "learning_rate": 2.4019771491674522e-05, "loss": 3.9833, "step": 9525 }, { "epoch": 0.5125914765389582, "grad_norm": 1.0979961156845093, "learning_rate": 2.4015548549326337e-05, "loss": 4.5514, "step": 9526 }, { "epoch": 0.5126452862677572, "grad_norm": 2.950939893722534, "learning_rate": 2.4011325635111128e-05, "loss": 3.6316, "step": 9527 }, { "epoch": 0.5126990959965562, "grad_norm": 2.2039289474487305, "learning_rate": 2.4007102749149567e-05, "loss": 4.3068, "step": 9528 }, { "epoch": 0.5127529057253551, "grad_norm": 3.3287930488586426, "learning_rate": 2.400287989156234e-05, "loss": 4.0422, "step": 9529 }, { "epoch": 0.5128067154541541, "grad_norm": 2.5452470779418945, "learning_rate": 2.3998657062470123e-05, "loss": 3.7997, "step": 9530 }, { "epoch": 0.5128605251829531, "grad_norm": 9.359071731567383, "learning_rate": 2.3994434261993594e-05, "loss": 3.4052, "step": 9531 }, { "epoch": 0.5129143349117521, "grad_norm": 2.01741623878479, "learning_rate": 2.3990211490253427e-05, "loss": 4.3463, "step": 9532 }, { "epoch": 0.512968144640551, "grad_norm": 2.5520174503326416, "learning_rate": 2.3985988747370303e-05, "loss": 4.1292, "step": 9533 }, { "epoch": 0.5130219543693499, "grad_norm": 2.631744384765625, "learning_rate": 2.39817660334649e-05, "loss": 3.8516, "step": 9534 }, { "epoch": 0.5130757640981489, "grad_norm": 1.6853193044662476, "learning_rate": 2.397754334865788e-05, "loss": 4.2603, "step": 9535 }, { "epoch": 0.5131295738269479, "grad_norm": 1.318770408630371, "learning_rate": 2.397332069306992e-05, "loss": 4.344, "step": 9536 }, { "epoch": 0.5131833835557469, "grad_norm": 1.5467168092727661, "learning_rate": 2.3969098066821686e-05, "loss": 4.1564, "step": 9537 }, { "epoch": 0.5132371932845459, "grad_norm": 2.7148027420043945, "learning_rate": 2.3964875470033866e-05, "loss": 3.1811, "step": 9538 }, { "epoch": 0.5132910030133448, "grad_norm": 2.8811230659484863, "learning_rate": 2.3960652902827117e-05, "loss": 4.0174, "step": 9539 }, { "epoch": 0.5133448127421438, "grad_norm": 1.6021207571029663, "learning_rate": 2.3956430365322107e-05, "loss": 4.5723, "step": 9540 }, { "epoch": 0.5133986224709427, "grad_norm": 1.9948699474334717, "learning_rate": 2.395220785763952e-05, "loss": 4.2558, "step": 9541 }, { "epoch": 0.5134524321997417, "grad_norm": 2.215970277786255, "learning_rate": 2.3947985379900014e-05, "loss": 4.0013, "step": 9542 }, { "epoch": 0.5135062419285407, "grad_norm": 2.116286277770996, "learning_rate": 2.3943762932224254e-05, "loss": 3.966, "step": 9543 }, { "epoch": 0.5135600516573396, "grad_norm": 2.7120659351348877, "learning_rate": 2.3939540514732902e-05, "loss": 3.7589, "step": 9544 }, { "epoch": 0.5136138613861386, "grad_norm": 1.9785816669464111, "learning_rate": 2.3935318127546638e-05, "loss": 4.2069, "step": 9545 }, { "epoch": 0.5136676711149376, "grad_norm": 2.7426466941833496, "learning_rate": 2.3931095770786116e-05, "loss": 3.6768, "step": 9546 }, { "epoch": 0.5137214808437366, "grad_norm": 1.5344756841659546, "learning_rate": 2.3926873444571994e-05, "loss": 4.2376, "step": 9547 }, { "epoch": 0.5137752905725355, "grad_norm": 2.290334939956665, "learning_rate": 2.3922651149024954e-05, "loss": 4.3904, "step": 9548 }, { "epoch": 0.5138291003013344, "grad_norm": 2.317476511001587, "learning_rate": 2.3918428884265647e-05, "loss": 3.7619, "step": 9549 }, { "epoch": 0.5138829100301334, "grad_norm": 3.043531656265259, "learning_rate": 2.3914206650414732e-05, "loss": 4.2652, "step": 9550 }, { "epoch": 0.5139367197589324, "grad_norm": 2.8375906944274902, "learning_rate": 2.3909984447592866e-05, "loss": 4.2578, "step": 9551 }, { "epoch": 0.5139905294877314, "grad_norm": 1.422664999961853, "learning_rate": 2.3905762275920708e-05, "loss": 4.6346, "step": 9552 }, { "epoch": 0.5140443392165304, "grad_norm": 2.143009662628174, "learning_rate": 2.3901540135518926e-05, "loss": 4.0811, "step": 9553 }, { "epoch": 0.5140981489453293, "grad_norm": 2.698578357696533, "learning_rate": 2.3897318026508176e-05, "loss": 4.15, "step": 9554 }, { "epoch": 0.5141519586741283, "grad_norm": 2.005476713180542, "learning_rate": 2.3893095949009103e-05, "loss": 3.7224, "step": 9555 }, { "epoch": 0.5142057684029272, "grad_norm": 2.917560577392578, "learning_rate": 2.388887390314238e-05, "loss": 3.9196, "step": 9556 }, { "epoch": 0.5142595781317262, "grad_norm": 2.7289915084838867, "learning_rate": 2.388465188902865e-05, "loss": 4.3305, "step": 9557 }, { "epoch": 0.5143133878605252, "grad_norm": 1.594234585762024, "learning_rate": 2.388042990678857e-05, "loss": 4.5208, "step": 9558 }, { "epoch": 0.5143671975893241, "grad_norm": 1.7547930479049683, "learning_rate": 2.387620795654279e-05, "loss": 4.3435, "step": 9559 }, { "epoch": 0.5144210073181231, "grad_norm": 2.100896120071411, "learning_rate": 2.3871986038411958e-05, "loss": 4.4864, "step": 9560 }, { "epoch": 0.5144748170469221, "grad_norm": 3.0007338523864746, "learning_rate": 2.3867764152516736e-05, "loss": 3.7741, "step": 9561 }, { "epoch": 0.5145286267757211, "grad_norm": 1.7586534023284912, "learning_rate": 2.386354229897777e-05, "loss": 4.2455, "step": 9562 }, { "epoch": 0.5145824365045201, "grad_norm": 2.116947650909424, "learning_rate": 2.3859320477915703e-05, "loss": 4.4556, "step": 9563 }, { "epoch": 0.5146362462333189, "grad_norm": 1.6275526285171509, "learning_rate": 2.3855098689451194e-05, "loss": 3.7609, "step": 9564 }, { "epoch": 0.5146900559621179, "grad_norm": 2.0307586193084717, "learning_rate": 2.3850876933704892e-05, "loss": 4.2595, "step": 9565 }, { "epoch": 0.5147438656909169, "grad_norm": 1.37645423412323, "learning_rate": 2.3846655210797427e-05, "loss": 4.3852, "step": 9566 }, { "epoch": 0.5147976754197159, "grad_norm": 2.5927257537841797, "learning_rate": 2.3842433520849457e-05, "loss": 3.7832, "step": 9567 }, { "epoch": 0.5148514851485149, "grad_norm": 2.3874473571777344, "learning_rate": 2.3838211863981617e-05, "loss": 4.0804, "step": 9568 }, { "epoch": 0.5149052948773138, "grad_norm": 2.2908973693847656, "learning_rate": 2.3833990240314562e-05, "loss": 4.033, "step": 9569 }, { "epoch": 0.5149591046061128, "grad_norm": 1.524333119392395, "learning_rate": 2.3829768649968932e-05, "loss": 4.5601, "step": 9570 }, { "epoch": 0.5150129143349117, "grad_norm": 1.7904423475265503, "learning_rate": 2.382554709306536e-05, "loss": 4.0699, "step": 9571 }, { "epoch": 0.5150667240637107, "grad_norm": 2.0494120121002197, "learning_rate": 2.3821325569724505e-05, "loss": 4.4347, "step": 9572 }, { "epoch": 0.5151205337925097, "grad_norm": 1.0066092014312744, "learning_rate": 2.381710408006699e-05, "loss": 4.3333, "step": 9573 }, { "epoch": 0.5151743435213086, "grad_norm": 1.6237728595733643, "learning_rate": 2.3812882624213457e-05, "loss": 4.587, "step": 9574 }, { "epoch": 0.5152281532501076, "grad_norm": 2.0026354789733887, "learning_rate": 2.3808661202284537e-05, "loss": 4.4047, "step": 9575 }, { "epoch": 0.5152819629789066, "grad_norm": 1.9279247522354126, "learning_rate": 2.3804439814400886e-05, "loss": 3.8337, "step": 9576 }, { "epoch": 0.5153357727077056, "grad_norm": 2.1048383712768555, "learning_rate": 2.3800218460683126e-05, "loss": 3.6823, "step": 9577 }, { "epoch": 0.5153895824365046, "grad_norm": 1.7171233892440796, "learning_rate": 2.379599714125189e-05, "loss": 4.1888, "step": 9578 }, { "epoch": 0.5154433921653034, "grad_norm": 2.364556312561035, "learning_rate": 2.379177585622783e-05, "loss": 3.5976, "step": 9579 }, { "epoch": 0.5154972018941024, "grad_norm": 2.5391085147857666, "learning_rate": 2.3787554605731563e-05, "loss": 4.3126, "step": 9580 }, { "epoch": 0.5155510116229014, "grad_norm": 1.6422146558761597, "learning_rate": 2.3783333389883723e-05, "loss": 4.4913, "step": 9581 }, { "epoch": 0.5156048213517004, "grad_norm": 1.5845420360565186, "learning_rate": 2.377911220880494e-05, "loss": 3.8848, "step": 9582 }, { "epoch": 0.5156586310804994, "grad_norm": 2.22463059425354, "learning_rate": 2.3774891062615844e-05, "loss": 4.3857, "step": 9583 }, { "epoch": 0.5157124408092983, "grad_norm": 2.1722962856292725, "learning_rate": 2.3770669951437067e-05, "loss": 3.9171, "step": 9584 }, { "epoch": 0.5157662505380973, "grad_norm": 2.9980618953704834, "learning_rate": 2.376644887538924e-05, "loss": 3.6868, "step": 9585 }, { "epoch": 0.5158200602668963, "grad_norm": 3.6415786743164062, "learning_rate": 2.376222783459298e-05, "loss": 4.403, "step": 9586 }, { "epoch": 0.5158738699956952, "grad_norm": 2.1121058464050293, "learning_rate": 2.3758006829168926e-05, "loss": 3.9901, "step": 9587 }, { "epoch": 0.5159276797244942, "grad_norm": 2.4548580646514893, "learning_rate": 2.3753785859237698e-05, "loss": 4.251, "step": 9588 }, { "epoch": 0.5159814894532931, "grad_norm": 1.6816933155059814, "learning_rate": 2.3749564924919916e-05, "loss": 4.1399, "step": 9589 }, { "epoch": 0.5160352991820921, "grad_norm": 2.3195278644561768, "learning_rate": 2.3745344026336204e-05, "loss": 4.0435, "step": 9590 }, { "epoch": 0.5160891089108911, "grad_norm": 3.1562469005584717, "learning_rate": 2.374112316360718e-05, "loss": 3.7049, "step": 9591 }, { "epoch": 0.5161429186396901, "grad_norm": 2.760219097137451, "learning_rate": 2.3736902336853475e-05, "loss": 3.5478, "step": 9592 }, { "epoch": 0.5161967283684891, "grad_norm": 0.9432382583618164, "learning_rate": 2.3732681546195703e-05, "loss": 4.6251, "step": 9593 }, { "epoch": 0.5162505380972879, "grad_norm": 1.4566558599472046, "learning_rate": 2.372846079175448e-05, "loss": 4.7266, "step": 9594 }, { "epoch": 0.5163043478260869, "grad_norm": 1.47506844997406, "learning_rate": 2.3724240073650445e-05, "loss": 4.3569, "step": 9595 }, { "epoch": 0.5163581575548859, "grad_norm": 1.5155118703842163, "learning_rate": 2.3720019392004177e-05, "loss": 4.1251, "step": 9596 }, { "epoch": 0.5164119672836849, "grad_norm": 2.872586727142334, "learning_rate": 2.371579874693632e-05, "loss": 4.1504, "step": 9597 }, { "epoch": 0.5164657770124839, "grad_norm": 1.9819601774215698, "learning_rate": 2.371157813856748e-05, "loss": 4.1151, "step": 9598 }, { "epoch": 0.5165195867412828, "grad_norm": 1.4302403926849365, "learning_rate": 2.3707357567018266e-05, "loss": 4.0093, "step": 9599 }, { "epoch": 0.5165733964700818, "grad_norm": 2.1748228073120117, "learning_rate": 2.3703137032409305e-05, "loss": 4.1775, "step": 9600 }, { "epoch": 0.5166272061988808, "grad_norm": 2.7539255619049072, "learning_rate": 2.3698916534861196e-05, "loss": 4.2445, "step": 9601 }, { "epoch": 0.5166810159276797, "grad_norm": 1.8844070434570312, "learning_rate": 2.3694696074494546e-05, "loss": 4.4817, "step": 9602 }, { "epoch": 0.5167348256564787, "grad_norm": 1.6913448572158813, "learning_rate": 2.3690475651429985e-05, "loss": 4.5833, "step": 9603 }, { "epoch": 0.5167886353852776, "grad_norm": 3.4958510398864746, "learning_rate": 2.36862552657881e-05, "loss": 4.0622, "step": 9604 }, { "epoch": 0.5168424451140766, "grad_norm": 1.8668404817581177, "learning_rate": 2.368203491768951e-05, "loss": 4.5874, "step": 9605 }, { "epoch": 0.5168962548428756, "grad_norm": 1.4457929134368896, "learning_rate": 2.3677814607254807e-05, "loss": 4.5163, "step": 9606 }, { "epoch": 0.5169500645716746, "grad_norm": 1.1723629236221313, "learning_rate": 2.367359433460461e-05, "loss": 4.3269, "step": 9607 }, { "epoch": 0.5170038743004736, "grad_norm": 2.8704473972320557, "learning_rate": 2.3669374099859526e-05, "loss": 3.9217, "step": 9608 }, { "epoch": 0.5170576840292725, "grad_norm": 3.348074197769165, "learning_rate": 2.3665153903140142e-05, "loss": 3.6646, "step": 9609 }, { "epoch": 0.5171114937580714, "grad_norm": 2.870914936065674, "learning_rate": 2.3660933744567076e-05, "loss": 5.0169, "step": 9610 }, { "epoch": 0.5171653034868704, "grad_norm": 2.289372682571411, "learning_rate": 2.3656713624260926e-05, "loss": 3.6524, "step": 9611 }, { "epoch": 0.5172191132156694, "grad_norm": 1.5284643173217773, "learning_rate": 2.3652493542342282e-05, "loss": 4.2654, "step": 9612 }, { "epoch": 0.5172729229444684, "grad_norm": 2.517542600631714, "learning_rate": 2.364827349893175e-05, "loss": 3.9786, "step": 9613 }, { "epoch": 0.5173267326732673, "grad_norm": 1.756983757019043, "learning_rate": 2.3644053494149922e-05, "loss": 4.4579, "step": 9614 }, { "epoch": 0.5173805424020663, "grad_norm": 1.0526355504989624, "learning_rate": 2.3639833528117396e-05, "loss": 4.5128, "step": 9615 }, { "epoch": 0.5174343521308653, "grad_norm": 3.3333749771118164, "learning_rate": 2.3635613600954775e-05, "loss": 3.4833, "step": 9616 }, { "epoch": 0.5174881618596642, "grad_norm": 1.6007838249206543, "learning_rate": 2.3631393712782643e-05, "loss": 4.3853, "step": 9617 }, { "epoch": 0.5175419715884632, "grad_norm": 1.3061742782592773, "learning_rate": 2.362717386372161e-05, "loss": 4.5917, "step": 9618 }, { "epoch": 0.5175957813172621, "grad_norm": 2.9278018474578857, "learning_rate": 2.3622954053892242e-05, "loss": 4.1963, "step": 9619 }, { "epoch": 0.5176495910460611, "grad_norm": 1.5451347827911377, "learning_rate": 2.3618734283415148e-05, "loss": 4.3025, "step": 9620 }, { "epoch": 0.5177034007748601, "grad_norm": 2.2249722480773926, "learning_rate": 2.3614514552410914e-05, "loss": 4.0123, "step": 9621 }, { "epoch": 0.5177572105036591, "grad_norm": 3.2672743797302246, "learning_rate": 2.361029486100012e-05, "loss": 3.1514, "step": 9622 }, { "epoch": 0.5178110202324581, "grad_norm": 2.664687395095825, "learning_rate": 2.360607520930337e-05, "loss": 3.86, "step": 9623 }, { "epoch": 0.517864829961257, "grad_norm": 2.6987037658691406, "learning_rate": 2.3601855597441237e-05, "loss": 4.1686, "step": 9624 }, { "epoch": 0.5179186396900559, "grad_norm": 1.9050596952438354, "learning_rate": 2.3597636025534307e-05, "loss": 5.0308, "step": 9625 }, { "epoch": 0.5179724494188549, "grad_norm": 1.371506690979004, "learning_rate": 2.3593416493703183e-05, "loss": 4.3119, "step": 9626 }, { "epoch": 0.5180262591476539, "grad_norm": 3.392825126647949, "learning_rate": 2.3589197002068417e-05, "loss": 3.6149, "step": 9627 }, { "epoch": 0.5180800688764529, "grad_norm": 3.012016534805298, "learning_rate": 2.3584977550750613e-05, "loss": 3.7444, "step": 9628 }, { "epoch": 0.5181338786052518, "grad_norm": 1.3268579244613647, "learning_rate": 2.3580758139870342e-05, "loss": 4.6164, "step": 9629 }, { "epoch": 0.5181876883340508, "grad_norm": 2.492781400680542, "learning_rate": 2.357653876954818e-05, "loss": 4.2417, "step": 9630 }, { "epoch": 0.5182414980628498, "grad_norm": 2.1539766788482666, "learning_rate": 2.3572319439904718e-05, "loss": 4.5213, "step": 9631 }, { "epoch": 0.5182953077916488, "grad_norm": 1.6855393648147583, "learning_rate": 2.3568100151060526e-05, "loss": 4.1468, "step": 9632 }, { "epoch": 0.5183491175204477, "grad_norm": 3.3682761192321777, "learning_rate": 2.3563880903136176e-05, "loss": 4.5553, "step": 9633 }, { "epoch": 0.5184029272492466, "grad_norm": 2.059781551361084, "learning_rate": 2.3559661696252257e-05, "loss": 4.2915, "step": 9634 }, { "epoch": 0.5184567369780456, "grad_norm": 1.0103353261947632, "learning_rate": 2.355544253052933e-05, "loss": 4.2677, "step": 9635 }, { "epoch": 0.5185105467068446, "grad_norm": 1.944833517074585, "learning_rate": 2.3551223406087966e-05, "loss": 4.5484, "step": 9636 }, { "epoch": 0.5185643564356436, "grad_norm": 2.298156499862671, "learning_rate": 2.3547004323048738e-05, "loss": 3.6244, "step": 9637 }, { "epoch": 0.5186181661644426, "grad_norm": 2.117048978805542, "learning_rate": 2.354278528153222e-05, "loss": 3.8869, "step": 9638 }, { "epoch": 0.5186719758932415, "grad_norm": 1.9952082633972168, "learning_rate": 2.3538566281658983e-05, "loss": 3.8075, "step": 9639 }, { "epoch": 0.5187257856220404, "grad_norm": 1.7506117820739746, "learning_rate": 2.3534347323549582e-05, "loss": 4.3985, "step": 9640 }, { "epoch": 0.5187795953508394, "grad_norm": 1.158732295036316, "learning_rate": 2.3530128407324612e-05, "loss": 4.9605, "step": 9641 }, { "epoch": 0.5188334050796384, "grad_norm": 1.1900355815887451, "learning_rate": 2.35259095331046e-05, "loss": 4.5674, "step": 9642 }, { "epoch": 0.5188872148084374, "grad_norm": 2.3041510581970215, "learning_rate": 2.3521690701010137e-05, "loss": 4.4908, "step": 9643 }, { "epoch": 0.5189410245372363, "grad_norm": 1.7680444717407227, "learning_rate": 2.3517471911161775e-05, "loss": 4.0957, "step": 9644 }, { "epoch": 0.5189948342660353, "grad_norm": 2.825885534286499, "learning_rate": 2.3513253163680073e-05, "loss": 3.9954, "step": 9645 }, { "epoch": 0.5190486439948343, "grad_norm": 2.803865432739258, "learning_rate": 2.35090344586856e-05, "loss": 4.2869, "step": 9646 }, { "epoch": 0.5191024537236333, "grad_norm": 2.9290783405303955, "learning_rate": 2.350481579629892e-05, "loss": 4.2221, "step": 9647 }, { "epoch": 0.5191562634524322, "grad_norm": 1.4712477922439575, "learning_rate": 2.350059717664057e-05, "loss": 4.4787, "step": 9648 }, { "epoch": 0.5192100731812311, "grad_norm": 2.5244619846343994, "learning_rate": 2.349637859983114e-05, "loss": 3.6905, "step": 9649 }, { "epoch": 0.5192638829100301, "grad_norm": 1.688317894935608, "learning_rate": 2.3492160065991147e-05, "loss": 4.6808, "step": 9650 }, { "epoch": 0.5193176926388291, "grad_norm": 2.0688130855560303, "learning_rate": 2.3487941575241167e-05, "loss": 3.8691, "step": 9651 }, { "epoch": 0.5193715023676281, "grad_norm": 2.1389243602752686, "learning_rate": 2.3483723127701753e-05, "loss": 4.1111, "step": 9652 }, { "epoch": 0.5194253120964271, "grad_norm": 1.7831151485443115, "learning_rate": 2.3479504723493448e-05, "loss": 4.358, "step": 9653 }, { "epoch": 0.519479121825226, "grad_norm": 3.1836726665496826, "learning_rate": 2.3475286362736812e-05, "loss": 3.3975, "step": 9654 }, { "epoch": 0.5195329315540249, "grad_norm": 1.4445366859436035, "learning_rate": 2.3471068045552394e-05, "loss": 4.2813, "step": 9655 }, { "epoch": 0.5195867412828239, "grad_norm": 2.825921058654785, "learning_rate": 2.346684977206074e-05, "loss": 4.1625, "step": 9656 }, { "epoch": 0.5196405510116229, "grad_norm": 1.8071576356887817, "learning_rate": 2.3462631542382392e-05, "loss": 4.402, "step": 9657 }, { "epoch": 0.5196943607404219, "grad_norm": 2.1137454509735107, "learning_rate": 2.3458413356637897e-05, "loss": 4.5073, "step": 9658 }, { "epoch": 0.5197481704692208, "grad_norm": 2.700608015060425, "learning_rate": 2.3454195214947807e-05, "loss": 3.5966, "step": 9659 }, { "epoch": 0.5198019801980198, "grad_norm": 2.729721784591675, "learning_rate": 2.3449977117432656e-05, "loss": 4.101, "step": 9660 }, { "epoch": 0.5198557899268188, "grad_norm": 1.632867455482483, "learning_rate": 2.3445759064212988e-05, "loss": 4.2367, "step": 9661 }, { "epoch": 0.5199095996556178, "grad_norm": 1.596332311630249, "learning_rate": 2.344154105540935e-05, "loss": 4.6493, "step": 9662 }, { "epoch": 0.5199634093844167, "grad_norm": 1.8684117794036865, "learning_rate": 2.3437323091142273e-05, "loss": 4.4712, "step": 9663 }, { "epoch": 0.5200172191132156, "grad_norm": 1.3427702188491821, "learning_rate": 2.343310517153231e-05, "loss": 4.2736, "step": 9664 }, { "epoch": 0.5200710288420146, "grad_norm": 2.8001201152801514, "learning_rate": 2.3428887296699974e-05, "loss": 4.1337, "step": 9665 }, { "epoch": 0.5201248385708136, "grad_norm": 2.7945399284362793, "learning_rate": 2.3424669466765818e-05, "loss": 3.7714, "step": 9666 }, { "epoch": 0.5201786482996126, "grad_norm": 2.5956201553344727, "learning_rate": 2.3420451681850372e-05, "loss": 4.2216, "step": 9667 }, { "epoch": 0.5202324580284116, "grad_norm": 3.3722729682922363, "learning_rate": 2.3416233942074162e-05, "loss": 3.5432, "step": 9668 }, { "epoch": 0.5202862677572105, "grad_norm": 2.11852765083313, "learning_rate": 2.3412016247557735e-05, "loss": 4.1468, "step": 9669 }, { "epoch": 0.5203400774860095, "grad_norm": 2.9704792499542236, "learning_rate": 2.340779859842161e-05, "loss": 3.9298, "step": 9670 }, { "epoch": 0.5203938872148084, "grad_norm": 3.0281035900115967, "learning_rate": 2.340358099478631e-05, "loss": 3.9071, "step": 9671 }, { "epoch": 0.5204476969436074, "grad_norm": 2.302964448928833, "learning_rate": 2.3399363436772394e-05, "loss": 3.9665, "step": 9672 }, { "epoch": 0.5205015066724064, "grad_norm": 1.7634588479995728, "learning_rate": 2.3395145924500343e-05, "loss": 4.3145, "step": 9673 }, { "epoch": 0.5205553164012053, "grad_norm": 1.7049568891525269, "learning_rate": 2.3390928458090715e-05, "loss": 4.5136, "step": 9674 }, { "epoch": 0.5206091261300043, "grad_norm": 1.85687255859375, "learning_rate": 2.3386711037664022e-05, "loss": 3.8194, "step": 9675 }, { "epoch": 0.5206629358588033, "grad_norm": 1.7383570671081543, "learning_rate": 2.338249366334078e-05, "loss": 3.94, "step": 9676 }, { "epoch": 0.5207167455876023, "grad_norm": 1.7558625936508179, "learning_rate": 2.337827633524153e-05, "loss": 4.4726, "step": 9677 }, { "epoch": 0.5207705553164012, "grad_norm": 1.8373205661773682, "learning_rate": 2.3374059053486778e-05, "loss": 3.9344, "step": 9678 }, { "epoch": 0.5208243650452001, "grad_norm": 2.4062466621398926, "learning_rate": 2.336984181819705e-05, "loss": 3.6842, "step": 9679 }, { "epoch": 0.5208781747739991, "grad_norm": 2.413437843322754, "learning_rate": 2.336562462949285e-05, "loss": 4.2696, "step": 9680 }, { "epoch": 0.5209319845027981, "grad_norm": 1.4779952764511108, "learning_rate": 2.33614074874947e-05, "loss": 4.471, "step": 9681 }, { "epoch": 0.5209857942315971, "grad_norm": 2.4808502197265625, "learning_rate": 2.3357190392323127e-05, "loss": 4.0702, "step": 9682 }, { "epoch": 0.5210396039603961, "grad_norm": 2.5746264457702637, "learning_rate": 2.3352973344098625e-05, "loss": 4.0875, "step": 9683 }, { "epoch": 0.521093413689195, "grad_norm": 2.9070684909820557, "learning_rate": 2.3348756342941714e-05, "loss": 4.5414, "step": 9684 }, { "epoch": 0.521147223417994, "grad_norm": 3.7218527793884277, "learning_rate": 2.3344539388972908e-05, "loss": 3.6185, "step": 9685 }, { "epoch": 0.5212010331467929, "grad_norm": 3.483506679534912, "learning_rate": 2.3340322482312714e-05, "loss": 3.7296, "step": 9686 }, { "epoch": 0.5212548428755919, "grad_norm": 3.5170981884002686, "learning_rate": 2.333610562308165e-05, "loss": 4.1018, "step": 9687 }, { "epoch": 0.5213086526043909, "grad_norm": 2.1933951377868652, "learning_rate": 2.3331888811400195e-05, "loss": 3.9013, "step": 9688 }, { "epoch": 0.5213624623331898, "grad_norm": 1.880613923072815, "learning_rate": 2.3327672047388878e-05, "loss": 4.2221, "step": 9689 }, { "epoch": 0.5214162720619888, "grad_norm": 3.678112268447876, "learning_rate": 2.3323455331168196e-05, "loss": 4.272, "step": 9690 }, { "epoch": 0.5214700817907878, "grad_norm": 3.034705877304077, "learning_rate": 2.331923866285865e-05, "loss": 3.4449, "step": 9691 }, { "epoch": 0.5215238915195868, "grad_norm": 1.2564176321029663, "learning_rate": 2.3315022042580742e-05, "loss": 4.3554, "step": 9692 }, { "epoch": 0.5215777012483858, "grad_norm": 1.6942299604415894, "learning_rate": 2.3310805470454975e-05, "loss": 3.9998, "step": 9693 }, { "epoch": 0.5216315109771846, "grad_norm": 2.733452081680298, "learning_rate": 2.330658894660184e-05, "loss": 4.0055, "step": 9694 }, { "epoch": 0.5216853207059836, "grad_norm": 1.8902174234390259, "learning_rate": 2.3302372471141852e-05, "loss": 3.7969, "step": 9695 }, { "epoch": 0.5217391304347826, "grad_norm": 2.0116429328918457, "learning_rate": 2.3298156044195475e-05, "loss": 3.9731, "step": 9696 }, { "epoch": 0.5217929401635816, "grad_norm": 1.3190646171569824, "learning_rate": 2.329393966588323e-05, "loss": 5.0261, "step": 9697 }, { "epoch": 0.5218467498923806, "grad_norm": 2.1950643062591553, "learning_rate": 2.3289723336325597e-05, "loss": 4.311, "step": 9698 }, { "epoch": 0.5219005596211795, "grad_norm": 2.246255874633789, "learning_rate": 2.328550705564307e-05, "loss": 3.8713, "step": 9699 }, { "epoch": 0.5219543693499785, "grad_norm": 3.1994781494140625, "learning_rate": 2.328129082395614e-05, "loss": 4.111, "step": 9700 }, { "epoch": 0.5220081790787774, "grad_norm": 2.3727428913116455, "learning_rate": 2.3277074641385298e-05, "loss": 3.1569, "step": 9701 }, { "epoch": 0.5220619888075764, "grad_norm": 2.0898396968841553, "learning_rate": 2.3272858508051033e-05, "loss": 3.9333, "step": 9702 }, { "epoch": 0.5221157985363754, "grad_norm": 1.8386865854263306, "learning_rate": 2.3268642424073826e-05, "loss": 3.9953, "step": 9703 }, { "epoch": 0.5221696082651743, "grad_norm": 1.3970818519592285, "learning_rate": 2.326442638957415e-05, "loss": 4.2081, "step": 9704 }, { "epoch": 0.5222234179939733, "grad_norm": 3.742990493774414, "learning_rate": 2.326021040467251e-05, "loss": 4.252, "step": 9705 }, { "epoch": 0.5222772277227723, "grad_norm": 3.3928630352020264, "learning_rate": 2.3255994469489372e-05, "loss": 4.0126, "step": 9706 }, { "epoch": 0.5223310374515713, "grad_norm": 1.5859827995300293, "learning_rate": 2.3251778584145216e-05, "loss": 4.4541, "step": 9707 }, { "epoch": 0.5223848471803703, "grad_norm": 2.3643078804016113, "learning_rate": 2.3247562748760537e-05, "loss": 4.1141, "step": 9708 }, { "epoch": 0.5224386569091691, "grad_norm": 3.2380170822143555, "learning_rate": 2.3243346963455797e-05, "loss": 3.4965, "step": 9709 }, { "epoch": 0.5224924666379681, "grad_norm": 2.772820234298706, "learning_rate": 2.323913122835148e-05, "loss": 4.0293, "step": 9710 }, { "epoch": 0.5225462763667671, "grad_norm": 3.5310728549957275, "learning_rate": 2.3234915543568057e-05, "loss": 3.6639, "step": 9711 }, { "epoch": 0.5226000860955661, "grad_norm": 1.5196995735168457, "learning_rate": 2.323069990922599e-05, "loss": 4.0613, "step": 9712 }, { "epoch": 0.5226538958243651, "grad_norm": 2.6074724197387695, "learning_rate": 2.3226484325445767e-05, "loss": 3.5492, "step": 9713 }, { "epoch": 0.522707705553164, "grad_norm": 1.2584813833236694, "learning_rate": 2.3222268792347852e-05, "loss": 4.224, "step": 9714 }, { "epoch": 0.522761515281963, "grad_norm": 3.407914161682129, "learning_rate": 2.3218053310052706e-05, "loss": 3.5539, "step": 9715 }, { "epoch": 0.522815325010762, "grad_norm": 2.0499725341796875, "learning_rate": 2.321383787868081e-05, "loss": 4.3634, "step": 9716 }, { "epoch": 0.5228691347395609, "grad_norm": 2.823955535888672, "learning_rate": 2.3209622498352626e-05, "loss": 3.6957, "step": 9717 }, { "epoch": 0.5229229444683599, "grad_norm": 2.8681938648223877, "learning_rate": 2.320540716918862e-05, "loss": 3.7546, "step": 9718 }, { "epoch": 0.5229767541971588, "grad_norm": 2.608181953430176, "learning_rate": 2.3201191891309236e-05, "loss": 3.8062, "step": 9719 }, { "epoch": 0.5230305639259578, "grad_norm": 1.9569056034088135, "learning_rate": 2.3196976664834957e-05, "loss": 4.2337, "step": 9720 }, { "epoch": 0.5230843736547568, "grad_norm": 3.25224232673645, "learning_rate": 2.3192761489886238e-05, "loss": 3.2825, "step": 9721 }, { "epoch": 0.5231381833835558, "grad_norm": 2.9364542961120605, "learning_rate": 2.3188546366583526e-05, "loss": 4.205, "step": 9722 }, { "epoch": 0.5231919931123548, "grad_norm": 2.4972431659698486, "learning_rate": 2.3184331295047294e-05, "loss": 4.1963, "step": 9723 }, { "epoch": 0.5232458028411536, "grad_norm": 2.625715732574463, "learning_rate": 2.3180116275397986e-05, "loss": 4.2593, "step": 9724 }, { "epoch": 0.5232996125699526, "grad_norm": 2.395611047744751, "learning_rate": 2.317590130775607e-05, "loss": 3.4627, "step": 9725 }, { "epoch": 0.5233534222987516, "grad_norm": 1.9590201377868652, "learning_rate": 2.317168639224198e-05, "loss": 4.1342, "step": 9726 }, { "epoch": 0.5234072320275506, "grad_norm": 1.34657883644104, "learning_rate": 2.316747152897617e-05, "loss": 4.6746, "step": 9727 }, { "epoch": 0.5234610417563496, "grad_norm": 2.6559836864471436, "learning_rate": 2.31632567180791e-05, "loss": 3.5698, "step": 9728 }, { "epoch": 0.5235148514851485, "grad_norm": 1.9073350429534912, "learning_rate": 2.3159041959671214e-05, "loss": 4.7081, "step": 9729 }, { "epoch": 0.5235686612139475, "grad_norm": 1.7507680654525757, "learning_rate": 2.3154827253872953e-05, "loss": 4.6216, "step": 9730 }, { "epoch": 0.5236224709427465, "grad_norm": 2.6346230506896973, "learning_rate": 2.3150612600804773e-05, "loss": 4.004, "step": 9731 }, { "epoch": 0.5236762806715454, "grad_norm": 2.2873642444610596, "learning_rate": 2.314639800058711e-05, "loss": 3.9078, "step": 9732 }, { "epoch": 0.5237300904003444, "grad_norm": 1.750076413154602, "learning_rate": 2.314218345334041e-05, "loss": 4.281, "step": 9733 }, { "epoch": 0.5237839001291433, "grad_norm": 2.7810192108154297, "learning_rate": 2.3137968959185104e-05, "loss": 3.9842, "step": 9734 }, { "epoch": 0.5238377098579423, "grad_norm": 2.2342336177825928, "learning_rate": 2.3133754518241628e-05, "loss": 3.7714, "step": 9735 }, { "epoch": 0.5238915195867413, "grad_norm": 1.930282473564148, "learning_rate": 2.312954013063044e-05, "loss": 4.3805, "step": 9736 }, { "epoch": 0.5239453293155403, "grad_norm": 3.42846941947937, "learning_rate": 2.312532579647196e-05, "loss": 3.79, "step": 9737 }, { "epoch": 0.5239991390443393, "grad_norm": 2.1842782497406006, "learning_rate": 2.3121111515886624e-05, "loss": 3.5528, "step": 9738 }, { "epoch": 0.5240529487731382, "grad_norm": 2.164700508117676, "learning_rate": 2.3116897288994872e-05, "loss": 4.4688, "step": 9739 }, { "epoch": 0.5241067585019371, "grad_norm": 3.5803279876708984, "learning_rate": 2.3112683115917126e-05, "loss": 4.2369, "step": 9740 }, { "epoch": 0.5241605682307361, "grad_norm": 3.0957694053649902, "learning_rate": 2.3108468996773834e-05, "loss": 4.0997, "step": 9741 }, { "epoch": 0.5242143779595351, "grad_norm": 1.0764315128326416, "learning_rate": 2.31042549316854e-05, "loss": 4.6803, "step": 9742 }, { "epoch": 0.524268187688334, "grad_norm": 1.2198410034179688, "learning_rate": 2.3100040920772256e-05, "loss": 3.8434, "step": 9743 }, { "epoch": 0.524321997417133, "grad_norm": 2.0493602752685547, "learning_rate": 2.3095826964154837e-05, "loss": 3.9728, "step": 9744 }, { "epoch": 0.524375807145932, "grad_norm": 2.2906179428100586, "learning_rate": 2.3091613061953562e-05, "loss": 3.7748, "step": 9745 }, { "epoch": 0.524429616874731, "grad_norm": 1.9635021686553955, "learning_rate": 2.308739921428885e-05, "loss": 4.4432, "step": 9746 }, { "epoch": 0.5244834266035299, "grad_norm": 1.7235804796218872, "learning_rate": 2.3083185421281125e-05, "loss": 4.5896, "step": 9747 }, { "epoch": 0.5245372363323288, "grad_norm": 2.3721933364868164, "learning_rate": 2.3078971683050816e-05, "loss": 4.4968, "step": 9748 }, { "epoch": 0.5245910460611278, "grad_norm": 2.3299665451049805, "learning_rate": 2.3074757999718317e-05, "loss": 4.291, "step": 9749 }, { "epoch": 0.5246448557899268, "grad_norm": 2.1531529426574707, "learning_rate": 2.3070544371404058e-05, "loss": 3.9953, "step": 9750 }, { "epoch": 0.5246986655187258, "grad_norm": 1.7295860052108765, "learning_rate": 2.3066330798228452e-05, "loss": 4.3163, "step": 9751 }, { "epoch": 0.5247524752475248, "grad_norm": 3.2712435722351074, "learning_rate": 2.3062117280311914e-05, "loss": 3.7044, "step": 9752 }, { "epoch": 0.5248062849763238, "grad_norm": 2.839230537414551, "learning_rate": 2.3057903817774843e-05, "loss": 3.9863, "step": 9753 }, { "epoch": 0.5248600947051227, "grad_norm": 2.6645054817199707, "learning_rate": 2.3053690410737662e-05, "loss": 3.8432, "step": 9754 }, { "epoch": 0.5249139044339216, "grad_norm": 2.1750776767730713, "learning_rate": 2.3049477059320777e-05, "loss": 4.2555, "step": 9755 }, { "epoch": 0.5249677141627206, "grad_norm": 2.2856075763702393, "learning_rate": 2.3045263763644596e-05, "loss": 4.1212, "step": 9756 }, { "epoch": 0.5250215238915196, "grad_norm": 2.7564632892608643, "learning_rate": 2.3041050523829517e-05, "loss": 3.6337, "step": 9757 }, { "epoch": 0.5250753336203186, "grad_norm": 2.7191967964172363, "learning_rate": 2.3036837339995936e-05, "loss": 4.7914, "step": 9758 }, { "epoch": 0.5251291433491175, "grad_norm": 3.4678895473480225, "learning_rate": 2.3032624212264267e-05, "loss": 4.1724, "step": 9759 }, { "epoch": 0.5251829530779165, "grad_norm": 2.487056255340576, "learning_rate": 2.302841114075491e-05, "loss": 4.1521, "step": 9760 }, { "epoch": 0.5252367628067155, "grad_norm": 1.8726969957351685, "learning_rate": 2.3024198125588254e-05, "loss": 3.6289, "step": 9761 }, { "epoch": 0.5252905725355144, "grad_norm": 2.493285894393921, "learning_rate": 2.3019985166884703e-05, "loss": 4.0074, "step": 9762 }, { "epoch": 0.5253443822643133, "grad_norm": 1.626699686050415, "learning_rate": 2.3015772264764658e-05, "loss": 4.2556, "step": 9763 }, { "epoch": 0.5253981919931123, "grad_norm": 2.5646891593933105, "learning_rate": 2.30115594193485e-05, "loss": 4.0582, "step": 9764 }, { "epoch": 0.5254520017219113, "grad_norm": 2.1777665615081787, "learning_rate": 2.3007346630756628e-05, "loss": 3.8272, "step": 9765 }, { "epoch": 0.5255058114507103, "grad_norm": 2.281069278717041, "learning_rate": 2.300313389910942e-05, "loss": 4.0209, "step": 9766 }, { "epoch": 0.5255596211795093, "grad_norm": 1.2531640529632568, "learning_rate": 2.299892122452728e-05, "loss": 4.719, "step": 9767 }, { "epoch": 0.5256134309083083, "grad_norm": 1.5526010990142822, "learning_rate": 2.299470860713059e-05, "loss": 4.6548, "step": 9768 }, { "epoch": 0.5256672406371072, "grad_norm": 1.3732120990753174, "learning_rate": 2.299049604703973e-05, "loss": 4.3849, "step": 9769 }, { "epoch": 0.5257210503659061, "grad_norm": 1.643906593322754, "learning_rate": 2.2986283544375093e-05, "loss": 3.8897, "step": 9770 }, { "epoch": 0.5257748600947051, "grad_norm": 2.427706718444824, "learning_rate": 2.298207109925706e-05, "loss": 4.2146, "step": 9771 }, { "epoch": 0.5258286698235041, "grad_norm": 2.68318247795105, "learning_rate": 2.2977858711806005e-05, "loss": 3.8213, "step": 9772 }, { "epoch": 0.525882479552303, "grad_norm": 2.3865609169006348, "learning_rate": 2.2973646382142305e-05, "loss": 3.8783, "step": 9773 }, { "epoch": 0.525936289281102, "grad_norm": 1.625225305557251, "learning_rate": 2.296943411038634e-05, "loss": 3.7471, "step": 9774 }, { "epoch": 0.525990099009901, "grad_norm": 1.9910565614700317, "learning_rate": 2.296522189665849e-05, "loss": 3.9041, "step": 9775 }, { "epoch": 0.5260439087387, "grad_norm": 2.2836923599243164, "learning_rate": 2.2961009741079124e-05, "loss": 4.2249, "step": 9776 }, { "epoch": 0.526097718467499, "grad_norm": 2.7996482849121094, "learning_rate": 2.295679764376861e-05, "loss": 3.888, "step": 9777 }, { "epoch": 0.5261515281962978, "grad_norm": 1.6731358766555786, "learning_rate": 2.2952585604847332e-05, "loss": 4.3727, "step": 9778 }, { "epoch": 0.5262053379250968, "grad_norm": 3.9967527389526367, "learning_rate": 2.2948373624435655e-05, "loss": 3.7871, "step": 9779 }, { "epoch": 0.5262591476538958, "grad_norm": 2.3327813148498535, "learning_rate": 2.2944161702653935e-05, "loss": 3.9833, "step": 9780 }, { "epoch": 0.5263129573826948, "grad_norm": 1.981705665588379, "learning_rate": 2.2939949839622538e-05, "loss": 4.3155, "step": 9781 }, { "epoch": 0.5263667671114938, "grad_norm": 2.021273136138916, "learning_rate": 2.293573803546184e-05, "loss": 4.6739, "step": 9782 }, { "epoch": 0.5264205768402928, "grad_norm": 2.2603747844696045, "learning_rate": 2.2931526290292198e-05, "loss": 4.1031, "step": 9783 }, { "epoch": 0.5264743865690917, "grad_norm": 2.229776620864868, "learning_rate": 2.2927314604233963e-05, "loss": 3.6719, "step": 9784 }, { "epoch": 0.5265281962978906, "grad_norm": 1.9555034637451172, "learning_rate": 2.292310297740751e-05, "loss": 4.2509, "step": 9785 }, { "epoch": 0.5265820060266896, "grad_norm": 1.6491800546646118, "learning_rate": 2.291889140993319e-05, "loss": 4.5592, "step": 9786 }, { "epoch": 0.5266358157554886, "grad_norm": 3.4414730072021484, "learning_rate": 2.2914679901931353e-05, "loss": 2.8099, "step": 9787 }, { "epoch": 0.5266896254842875, "grad_norm": 1.899208664894104, "learning_rate": 2.2910468453522354e-05, "loss": 4.505, "step": 9788 }, { "epoch": 0.5267434352130865, "grad_norm": 2.562330484390259, "learning_rate": 2.2906257064826542e-05, "loss": 3.382, "step": 9789 }, { "epoch": 0.5267972449418855, "grad_norm": 3.079049587249756, "learning_rate": 2.2902045735964277e-05, "loss": 3.6881, "step": 9790 }, { "epoch": 0.5268510546706845, "grad_norm": 2.8332290649414062, "learning_rate": 2.2897834467055904e-05, "loss": 3.6594, "step": 9791 }, { "epoch": 0.5269048643994835, "grad_norm": 2.086832284927368, "learning_rate": 2.2893623258221758e-05, "loss": 4.7885, "step": 9792 }, { "epoch": 0.5269586741282823, "grad_norm": 3.000549077987671, "learning_rate": 2.2889412109582202e-05, "loss": 3.7526, "step": 9793 }, { "epoch": 0.5270124838570813, "grad_norm": 2.221877098083496, "learning_rate": 2.2885201021257578e-05, "loss": 4.6351, "step": 9794 }, { "epoch": 0.5270662935858803, "grad_norm": 2.4912285804748535, "learning_rate": 2.2880989993368212e-05, "loss": 3.8511, "step": 9795 }, { "epoch": 0.5271201033146793, "grad_norm": 2.472783327102661, "learning_rate": 2.2876779026034452e-05, "loss": 4.3587, "step": 9796 }, { "epoch": 0.5271739130434783, "grad_norm": 3.502717971801758, "learning_rate": 2.2872568119376637e-05, "loss": 3.3959, "step": 9797 }, { "epoch": 0.5272277227722773, "grad_norm": 1.5044032335281372, "learning_rate": 2.28683572735151e-05, "loss": 4.2501, "step": 9798 }, { "epoch": 0.5272815325010762, "grad_norm": 2.19108247756958, "learning_rate": 2.2864146488570186e-05, "loss": 3.3829, "step": 9799 }, { "epoch": 0.5273353422298752, "grad_norm": 0.9898444414138794, "learning_rate": 2.285993576466221e-05, "loss": 4.5204, "step": 9800 }, { "epoch": 0.5273891519586741, "grad_norm": 1.6674319505691528, "learning_rate": 2.2855725101911525e-05, "loss": 4.1234, "step": 9801 }, { "epoch": 0.5274429616874731, "grad_norm": 2.788996934890747, "learning_rate": 2.2851514500438447e-05, "loss": 4.4914, "step": 9802 }, { "epoch": 0.527496771416272, "grad_norm": 2.4028053283691406, "learning_rate": 2.2847303960363305e-05, "loss": 4.201, "step": 9803 }, { "epoch": 0.527550581145071, "grad_norm": 1.8587486743927002, "learning_rate": 2.2843093481806427e-05, "loss": 3.4106, "step": 9804 }, { "epoch": 0.52760439087387, "grad_norm": 1.7292852401733398, "learning_rate": 2.2838883064888127e-05, "loss": 4.4248, "step": 9805 }, { "epoch": 0.527658200602669, "grad_norm": 1.832603096961975, "learning_rate": 2.2834672709728744e-05, "loss": 4.4396, "step": 9806 }, { "epoch": 0.527712010331468, "grad_norm": 1.521822214126587, "learning_rate": 2.283046241644859e-05, "loss": 4.6433, "step": 9807 }, { "epoch": 0.5277658200602668, "grad_norm": 1.9727154970169067, "learning_rate": 2.282625218516798e-05, "loss": 4.0444, "step": 9808 }, { "epoch": 0.5278196297890658, "grad_norm": 1.0944139957427979, "learning_rate": 2.2822042016007247e-05, "loss": 4.4155, "step": 9809 }, { "epoch": 0.5278734395178648, "grad_norm": 2.599013566970825, "learning_rate": 2.281783190908669e-05, "loss": 4.5819, "step": 9810 }, { "epoch": 0.5279272492466638, "grad_norm": 2.726382255554199, "learning_rate": 2.2813621864526623e-05, "loss": 4.326, "step": 9811 }, { "epoch": 0.5279810589754628, "grad_norm": 1.6897130012512207, "learning_rate": 2.2809411882447363e-05, "loss": 4.3063, "step": 9812 }, { "epoch": 0.5280348687042618, "grad_norm": 2.629189968109131, "learning_rate": 2.2805201962969222e-05, "loss": 4.7003, "step": 9813 }, { "epoch": 0.5280886784330607, "grad_norm": 1.5647591352462769, "learning_rate": 2.2800992106212506e-05, "loss": 4.2905, "step": 9814 }, { "epoch": 0.5281424881618597, "grad_norm": 3.0504796504974365, "learning_rate": 2.2796782312297516e-05, "loss": 4.5145, "step": 9815 }, { "epoch": 0.5281962978906586, "grad_norm": 1.42494797706604, "learning_rate": 2.279257258134457e-05, "loss": 4.8036, "step": 9816 }, { "epoch": 0.5282501076194576, "grad_norm": 1.7303504943847656, "learning_rate": 2.2788362913473964e-05, "loss": 4.1822, "step": 9817 }, { "epoch": 0.5283039173482565, "grad_norm": 2.21256160736084, "learning_rate": 2.2784153308805992e-05, "loss": 4.4346, "step": 9818 }, { "epoch": 0.5283577270770555, "grad_norm": 1.9589428901672363, "learning_rate": 2.2779943767460957e-05, "loss": 4.0042, "step": 9819 }, { "epoch": 0.5284115368058545, "grad_norm": 2.034741163253784, "learning_rate": 2.2775734289559157e-05, "loss": 4.4077, "step": 9820 }, { "epoch": 0.5284653465346535, "grad_norm": 2.506601095199585, "learning_rate": 2.277152487522089e-05, "loss": 4.3946, "step": 9821 }, { "epoch": 0.5285191562634525, "grad_norm": 2.5163803100585938, "learning_rate": 2.276731552456645e-05, "loss": 4.058, "step": 9822 }, { "epoch": 0.5285729659922515, "grad_norm": 1.7699527740478516, "learning_rate": 2.276310623771612e-05, "loss": 4.6196, "step": 9823 }, { "epoch": 0.5286267757210503, "grad_norm": 2.898080587387085, "learning_rate": 2.2758897014790203e-05, "loss": 4.4301, "step": 9824 }, { "epoch": 0.5286805854498493, "grad_norm": 1.8125553131103516, "learning_rate": 2.2754687855908987e-05, "loss": 4.09, "step": 9825 }, { "epoch": 0.5287343951786483, "grad_norm": 1.649796962738037, "learning_rate": 2.2750478761192746e-05, "loss": 3.7386, "step": 9826 }, { "epoch": 0.5287882049074473, "grad_norm": 2.668942928314209, "learning_rate": 2.2746269730761776e-05, "loss": 3.8093, "step": 9827 }, { "epoch": 0.5288420146362462, "grad_norm": 1.867004632949829, "learning_rate": 2.274206076473635e-05, "loss": 4.2029, "step": 9828 }, { "epoch": 0.5288958243650452, "grad_norm": 2.412003993988037, "learning_rate": 2.2737851863236752e-05, "loss": 3.5144, "step": 9829 }, { "epoch": 0.5289496340938442, "grad_norm": 1.9137136936187744, "learning_rate": 2.2733643026383273e-05, "loss": 4.3633, "step": 9830 }, { "epoch": 0.5290034438226431, "grad_norm": 2.816082239151001, "learning_rate": 2.2729434254296166e-05, "loss": 4.2919, "step": 9831 }, { "epoch": 0.5290572535514421, "grad_norm": 1.1915363073349, "learning_rate": 2.2725225547095744e-05, "loss": 4.3897, "step": 9832 }, { "epoch": 0.529111063280241, "grad_norm": 2.6355535984039307, "learning_rate": 2.2721016904902237e-05, "loss": 3.8075, "step": 9833 }, { "epoch": 0.52916487300904, "grad_norm": 1.6530559062957764, "learning_rate": 2.2716808327835945e-05, "loss": 4.7109, "step": 9834 }, { "epoch": 0.529218682737839, "grad_norm": 2.344428062438965, "learning_rate": 2.271259981601713e-05, "loss": 4.2681, "step": 9835 }, { "epoch": 0.529272492466638, "grad_norm": 3.003566265106201, "learning_rate": 2.2708391369566055e-05, "loss": 3.9209, "step": 9836 }, { "epoch": 0.529326302195437, "grad_norm": 2.8044016361236572, "learning_rate": 2.2704182988602994e-05, "loss": 4.3098, "step": 9837 }, { "epoch": 0.529380111924236, "grad_norm": 2.008732318878174, "learning_rate": 2.269997467324821e-05, "loss": 4.3856, "step": 9838 }, { "epoch": 0.5294339216530348, "grad_norm": 1.8244839906692505, "learning_rate": 2.2695766423621957e-05, "loss": 4.291, "step": 9839 }, { "epoch": 0.5294877313818338, "grad_norm": 3.480557918548584, "learning_rate": 2.2691558239844514e-05, "loss": 3.473, "step": 9840 }, { "epoch": 0.5295415411106328, "grad_norm": 2.676527976989746, "learning_rate": 2.2687350122036118e-05, "loss": 3.955, "step": 9841 }, { "epoch": 0.5295953508394318, "grad_norm": 1.664554238319397, "learning_rate": 2.268314207031704e-05, "loss": 4.5665, "step": 9842 }, { "epoch": 0.5296491605682307, "grad_norm": 2.009711265563965, "learning_rate": 2.2678934084807524e-05, "loss": 3.961, "step": 9843 }, { "epoch": 0.5297029702970297, "grad_norm": 2.4243221282958984, "learning_rate": 2.2674726165627833e-05, "loss": 3.8918, "step": 9844 }, { "epoch": 0.5297567800258287, "grad_norm": 2.840622663497925, "learning_rate": 2.267051831289821e-05, "loss": 4.1958, "step": 9845 }, { "epoch": 0.5298105897546277, "grad_norm": 2.494321584701538, "learning_rate": 2.266631052673891e-05, "loss": 3.8008, "step": 9846 }, { "epoch": 0.5298643994834266, "grad_norm": 1.9800047874450684, "learning_rate": 2.266210280727018e-05, "loss": 4.4795, "step": 9847 }, { "epoch": 0.5299182092122255, "grad_norm": 2.15141224861145, "learning_rate": 2.265789515461227e-05, "loss": 4.1816, "step": 9848 }, { "epoch": 0.5299720189410245, "grad_norm": 1.7954903841018677, "learning_rate": 2.265368756888541e-05, "loss": 4.1459, "step": 9849 }, { "epoch": 0.5300258286698235, "grad_norm": 1.6100249290466309, "learning_rate": 2.2649480050209852e-05, "loss": 4.4257, "step": 9850 }, { "epoch": 0.5300796383986225, "grad_norm": 2.4553940296173096, "learning_rate": 2.2645272598705823e-05, "loss": 3.6875, "step": 9851 }, { "epoch": 0.5301334481274215, "grad_norm": 1.831483244895935, "learning_rate": 2.2641065214493577e-05, "loss": 3.9479, "step": 9852 }, { "epoch": 0.5301872578562205, "grad_norm": 2.9442431926727295, "learning_rate": 2.263685789769334e-05, "loss": 3.9676, "step": 9853 }, { "epoch": 0.5302410675850193, "grad_norm": 2.5499019622802734, "learning_rate": 2.2632650648425345e-05, "loss": 4.0845, "step": 9854 }, { "epoch": 0.5302948773138183, "grad_norm": 1.2019383907318115, "learning_rate": 2.262844346680984e-05, "loss": 4.2463, "step": 9855 }, { "epoch": 0.5303486870426173, "grad_norm": 2.288119316101074, "learning_rate": 2.262423635296703e-05, "loss": 3.9486, "step": 9856 }, { "epoch": 0.5304024967714163, "grad_norm": 1.4881446361541748, "learning_rate": 2.262002930701716e-05, "loss": 4.0872, "step": 9857 }, { "epoch": 0.5304563065002152, "grad_norm": 2.5850746631622314, "learning_rate": 2.261582232908045e-05, "loss": 3.7922, "step": 9858 }, { "epoch": 0.5305101162290142, "grad_norm": 2.014418840408325, "learning_rate": 2.2611615419277118e-05, "loss": 4.4611, "step": 9859 }, { "epoch": 0.5305639259578132, "grad_norm": 1.4385944604873657, "learning_rate": 2.2607408577727402e-05, "loss": 4.8517, "step": 9860 }, { "epoch": 0.5306177356866122, "grad_norm": 2.657428741455078, "learning_rate": 2.260320180455151e-05, "loss": 4.0865, "step": 9861 }, { "epoch": 0.5306715454154111, "grad_norm": 1.2685421705245972, "learning_rate": 2.259899509986966e-05, "loss": 4.4373, "step": 9862 }, { "epoch": 0.53072535514421, "grad_norm": 1.8005818128585815, "learning_rate": 2.2594788463802082e-05, "loss": 3.8697, "step": 9863 }, { "epoch": 0.530779164873009, "grad_norm": 2.456303358078003, "learning_rate": 2.2590581896468976e-05, "loss": 4.2398, "step": 9864 }, { "epoch": 0.530832974601808, "grad_norm": 2.7238094806671143, "learning_rate": 2.2586375397990563e-05, "loss": 3.3051, "step": 9865 }, { "epoch": 0.530886784330607, "grad_norm": 3.6738078594207764, "learning_rate": 2.2582168968487044e-05, "loss": 3.9557, "step": 9866 }, { "epoch": 0.530940594059406, "grad_norm": 2.083444356918335, "learning_rate": 2.2577962608078626e-05, "loss": 4.697, "step": 9867 }, { "epoch": 0.530994403788205, "grad_norm": 3.460055351257324, "learning_rate": 2.257375631688553e-05, "loss": 3.3784, "step": 9868 }, { "epoch": 0.5310482135170038, "grad_norm": 3.1234660148620605, "learning_rate": 2.2569550095027954e-05, "loss": 3.9415, "step": 9869 }, { "epoch": 0.5311020232458028, "grad_norm": 2.684597969055176, "learning_rate": 2.25653439426261e-05, "loss": 4.1373, "step": 9870 }, { "epoch": 0.5311558329746018, "grad_norm": 3.526895523071289, "learning_rate": 2.2561137859800164e-05, "loss": 3.6211, "step": 9871 }, { "epoch": 0.5312096427034008, "grad_norm": 2.3939969539642334, "learning_rate": 2.255693184667035e-05, "loss": 4.339, "step": 9872 }, { "epoch": 0.5312634524321997, "grad_norm": 2.446197748184204, "learning_rate": 2.255272590335685e-05, "loss": 3.4703, "step": 9873 }, { "epoch": 0.5313172621609987, "grad_norm": 3.531893491744995, "learning_rate": 2.2548520029979858e-05, "loss": 3.4009, "step": 9874 }, { "epoch": 0.5313710718897977, "grad_norm": 2.218106746673584, "learning_rate": 2.2544314226659578e-05, "loss": 3.8398, "step": 9875 }, { "epoch": 0.5314248816185967, "grad_norm": 2.4582624435424805, "learning_rate": 2.2540108493516188e-05, "loss": 4.3373, "step": 9876 }, { "epoch": 0.5314786913473956, "grad_norm": 2.7362585067749023, "learning_rate": 2.2535902830669878e-05, "loss": 4.4533, "step": 9877 }, { "epoch": 0.5315325010761945, "grad_norm": 1.353895902633667, "learning_rate": 2.2531697238240852e-05, "loss": 4.228, "step": 9878 }, { "epoch": 0.5315863108049935, "grad_norm": 1.4611055850982666, "learning_rate": 2.2527491716349268e-05, "loss": 4.595, "step": 9879 }, { "epoch": 0.5316401205337925, "grad_norm": 1.1623908281326294, "learning_rate": 2.252328626511532e-05, "loss": 4.5647, "step": 9880 }, { "epoch": 0.5316939302625915, "grad_norm": 1.307963490486145, "learning_rate": 2.2519080884659192e-05, "loss": 4.4684, "step": 9881 }, { "epoch": 0.5317477399913905, "grad_norm": 1.74490487575531, "learning_rate": 2.2514875575101055e-05, "loss": 4.1924, "step": 9882 }, { "epoch": 0.5318015497201894, "grad_norm": 2.6552395820617676, "learning_rate": 2.2510670336561094e-05, "loss": 3.6643, "step": 9883 }, { "epoch": 0.5318553594489884, "grad_norm": 1.68148934841156, "learning_rate": 2.250646516915948e-05, "loss": 4.2703, "step": 9884 }, { "epoch": 0.5319091691777873, "grad_norm": 2.4083924293518066, "learning_rate": 2.2502260073016375e-05, "loss": 4.0865, "step": 9885 }, { "epoch": 0.5319629789065863, "grad_norm": 2.806457281112671, "learning_rate": 2.249805504825198e-05, "loss": 3.653, "step": 9886 }, { "epoch": 0.5320167886353853, "grad_norm": 2.7808926105499268, "learning_rate": 2.2493850094986425e-05, "loss": 4.0798, "step": 9887 }, { "epoch": 0.5320705983641842, "grad_norm": 1.838316559791565, "learning_rate": 2.24896452133399e-05, "loss": 4.4409, "step": 9888 }, { "epoch": 0.5321244080929832, "grad_norm": 2.3060550689697266, "learning_rate": 2.2485440403432563e-05, "loss": 4.5641, "step": 9889 }, { "epoch": 0.5321782178217822, "grad_norm": 4.143411636352539, "learning_rate": 2.2481235665384567e-05, "loss": 4.4329, "step": 9890 }, { "epoch": 0.5322320275505812, "grad_norm": 2.177539110183716, "learning_rate": 2.247703099931609e-05, "loss": 4.5058, "step": 9891 }, { "epoch": 0.5322858372793801, "grad_norm": 2.6415646076202393, "learning_rate": 2.247282640534728e-05, "loss": 3.8578, "step": 9892 }, { "epoch": 0.532339647008179, "grad_norm": 1.365630030632019, "learning_rate": 2.2468621883598297e-05, "loss": 4.6784, "step": 9893 }, { "epoch": 0.532393456736978, "grad_norm": 2.583151340484619, "learning_rate": 2.2464417434189283e-05, "loss": 4.0402, "step": 9894 }, { "epoch": 0.532447266465777, "grad_norm": 1.918487310409546, "learning_rate": 2.2460213057240404e-05, "loss": 4.407, "step": 9895 }, { "epoch": 0.532501076194576, "grad_norm": 3.0118024349212646, "learning_rate": 2.2456008752871803e-05, "loss": 3.9588, "step": 9896 }, { "epoch": 0.532554885923375, "grad_norm": 2.8322112560272217, "learning_rate": 2.2451804521203626e-05, "loss": 4.3832, "step": 9897 }, { "epoch": 0.532608695652174, "grad_norm": 3.4759979248046875, "learning_rate": 2.2447600362356028e-05, "loss": 3.5441, "step": 9898 }, { "epoch": 0.5326625053809729, "grad_norm": 1.5597336292266846, "learning_rate": 2.2443396276449143e-05, "loss": 4.0591, "step": 9899 }, { "epoch": 0.5327163151097718, "grad_norm": 2.636469841003418, "learning_rate": 2.2439192263603116e-05, "loss": 4.1939, "step": 9900 }, { "epoch": 0.5327701248385708, "grad_norm": 2.7067606449127197, "learning_rate": 2.24349883239381e-05, "loss": 3.4544, "step": 9901 }, { "epoch": 0.5328239345673698, "grad_norm": 1.639837384223938, "learning_rate": 2.24307844575742e-05, "loss": 3.9846, "step": 9902 }, { "epoch": 0.5328777442961687, "grad_norm": 2.09798002243042, "learning_rate": 2.2426580664631576e-05, "loss": 4.4561, "step": 9903 }, { "epoch": 0.5329315540249677, "grad_norm": 2.161377191543579, "learning_rate": 2.242237694523036e-05, "loss": 4.0717, "step": 9904 }, { "epoch": 0.5329853637537667, "grad_norm": 2.3610153198242188, "learning_rate": 2.2418173299490665e-05, "loss": 4.2227, "step": 9905 }, { "epoch": 0.5330391734825657, "grad_norm": 2.8541617393493652, "learning_rate": 2.2413969727532642e-05, "loss": 3.6129, "step": 9906 }, { "epoch": 0.5330929832113647, "grad_norm": 1.8947017192840576, "learning_rate": 2.240976622947641e-05, "loss": 4.0786, "step": 9907 }, { "epoch": 0.5331467929401635, "grad_norm": 1.9414161443710327, "learning_rate": 2.240556280544209e-05, "loss": 4.4873, "step": 9908 }, { "epoch": 0.5332006026689625, "grad_norm": 1.221932053565979, "learning_rate": 2.2401359455549813e-05, "loss": 4.3018, "step": 9909 }, { "epoch": 0.5332544123977615, "grad_norm": 2.414536952972412, "learning_rate": 2.2397156179919684e-05, "loss": 4.2375, "step": 9910 }, { "epoch": 0.5333082221265605, "grad_norm": 1.4950164556503296, "learning_rate": 2.2392952978671834e-05, "loss": 4.3102, "step": 9911 }, { "epoch": 0.5333620318553595, "grad_norm": 2.0577480792999268, "learning_rate": 2.2388749851926377e-05, "loss": 4.4038, "step": 9912 }, { "epoch": 0.5334158415841584, "grad_norm": 2.8729400634765625, "learning_rate": 2.2384546799803418e-05, "loss": 3.8298, "step": 9913 }, { "epoch": 0.5334696513129574, "grad_norm": 2.868272304534912, "learning_rate": 2.2380343822423083e-05, "loss": 4.1754, "step": 9914 }, { "epoch": 0.5335234610417563, "grad_norm": 2.70182466506958, "learning_rate": 2.237614091990548e-05, "loss": 3.957, "step": 9915 }, { "epoch": 0.5335772707705553, "grad_norm": 2.6047580242156982, "learning_rate": 2.237193809237071e-05, "loss": 3.4078, "step": 9916 }, { "epoch": 0.5336310804993543, "grad_norm": 2.136892795562744, "learning_rate": 2.236773533993888e-05, "loss": 3.0933, "step": 9917 }, { "epoch": 0.5336848902281532, "grad_norm": 2.495333433151245, "learning_rate": 2.236353266273009e-05, "loss": 3.9517, "step": 9918 }, { "epoch": 0.5337386999569522, "grad_norm": 3.2254045009613037, "learning_rate": 2.2359330060864447e-05, "loss": 3.3644, "step": 9919 }, { "epoch": 0.5337925096857512, "grad_norm": 3.6200504302978516, "learning_rate": 2.2355127534462048e-05, "loss": 3.1103, "step": 9920 }, { "epoch": 0.5338463194145502, "grad_norm": 2.678980827331543, "learning_rate": 2.2350925083642987e-05, "loss": 4.3692, "step": 9921 }, { "epoch": 0.5339001291433492, "grad_norm": 2.261125087738037, "learning_rate": 2.2346722708527364e-05, "loss": 3.5405, "step": 9922 }, { "epoch": 0.533953938872148, "grad_norm": 2.6843864917755127, "learning_rate": 2.2342520409235274e-05, "loss": 3.756, "step": 9923 }, { "epoch": 0.534007748600947, "grad_norm": 3.045905590057373, "learning_rate": 2.233831818588681e-05, "loss": 3.4661, "step": 9924 }, { "epoch": 0.534061558329746, "grad_norm": 2.9174342155456543, "learning_rate": 2.2334116038602036e-05, "loss": 4.2393, "step": 9925 }, { "epoch": 0.534115368058545, "grad_norm": 3.5568292140960693, "learning_rate": 2.2329913967501063e-05, "loss": 3.4304, "step": 9926 }, { "epoch": 0.534169177787344, "grad_norm": 2.7581543922424316, "learning_rate": 2.2325711972703965e-05, "loss": 3.698, "step": 9927 }, { "epoch": 0.5342229875161429, "grad_norm": 2.9734435081481934, "learning_rate": 2.2321510054330825e-05, "loss": 3.7969, "step": 9928 }, { "epoch": 0.5342767972449419, "grad_norm": 1.7820005416870117, "learning_rate": 2.2317308212501728e-05, "loss": 4.4973, "step": 9929 }, { "epoch": 0.5343306069737409, "grad_norm": 2.114966869354248, "learning_rate": 2.2313106447336746e-05, "loss": 3.6653, "step": 9930 }, { "epoch": 0.5343844167025398, "grad_norm": 1.5573136806488037, "learning_rate": 2.2308904758955947e-05, "loss": 4.6239, "step": 9931 }, { "epoch": 0.5344382264313388, "grad_norm": 3.1470799446105957, "learning_rate": 2.230470314747943e-05, "loss": 3.9883, "step": 9932 }, { "epoch": 0.5344920361601377, "grad_norm": 1.1825683116912842, "learning_rate": 2.230050161302723e-05, "loss": 4.6431, "step": 9933 }, { "epoch": 0.5345458458889367, "grad_norm": 3.291346549987793, "learning_rate": 2.229630015571944e-05, "loss": 3.4089, "step": 9934 }, { "epoch": 0.5345996556177357, "grad_norm": 3.191009283065796, "learning_rate": 2.229209877567612e-05, "loss": 4.1771, "step": 9935 }, { "epoch": 0.5346534653465347, "grad_norm": 1.5643750429153442, "learning_rate": 2.228789747301733e-05, "loss": 4.0651, "step": 9936 }, { "epoch": 0.5347072750753337, "grad_norm": 2.886603355407715, "learning_rate": 2.2283696247863135e-05, "loss": 4.2087, "step": 9937 }, { "epoch": 0.5347610848041325, "grad_norm": 2.7480742931365967, "learning_rate": 2.22794951003336e-05, "loss": 4.3702, "step": 9938 }, { "epoch": 0.5348148945329315, "grad_norm": 1.809619426727295, "learning_rate": 2.2275294030548782e-05, "loss": 4.4727, "step": 9939 }, { "epoch": 0.5348687042617305, "grad_norm": 1.940142035484314, "learning_rate": 2.2271093038628726e-05, "loss": 4.6683, "step": 9940 }, { "epoch": 0.5349225139905295, "grad_norm": 2.199327230453491, "learning_rate": 2.2266892124693485e-05, "loss": 4.0523, "step": 9941 }, { "epoch": 0.5349763237193285, "grad_norm": 3.150306224822998, "learning_rate": 2.2262691288863126e-05, "loss": 3.463, "step": 9942 }, { "epoch": 0.5350301334481274, "grad_norm": 2.705294132232666, "learning_rate": 2.2258490531257682e-05, "loss": 3.9764, "step": 9943 }, { "epoch": 0.5350839431769264, "grad_norm": 1.8113398551940918, "learning_rate": 2.2254289851997202e-05, "loss": 3.8701, "step": 9944 }, { "epoch": 0.5351377529057254, "grad_norm": 2.9217593669891357, "learning_rate": 2.2250089251201738e-05, "loss": 4.6273, "step": 9945 }, { "epoch": 0.5351915626345243, "grad_norm": 2.588224172592163, "learning_rate": 2.2245888728991324e-05, "loss": 4.1745, "step": 9946 }, { "epoch": 0.5352453723633233, "grad_norm": 1.762587070465088, "learning_rate": 2.224168828548601e-05, "loss": 3.9669, "step": 9947 }, { "epoch": 0.5352991820921222, "grad_norm": 2.1194915771484375, "learning_rate": 2.2237487920805823e-05, "loss": 4.3201, "step": 9948 }, { "epoch": 0.5353529918209212, "grad_norm": 1.5941816568374634, "learning_rate": 2.223328763507079e-05, "loss": 4.5787, "step": 9949 }, { "epoch": 0.5354068015497202, "grad_norm": 1.7323846817016602, "learning_rate": 2.2229087428400962e-05, "loss": 4.3845, "step": 9950 }, { "epoch": 0.5354606112785192, "grad_norm": 1.6653534173965454, "learning_rate": 2.2224887300916365e-05, "loss": 4.2781, "step": 9951 }, { "epoch": 0.5355144210073182, "grad_norm": 1.1125508546829224, "learning_rate": 2.222068725273702e-05, "loss": 4.4394, "step": 9952 }, { "epoch": 0.535568230736117, "grad_norm": 2.8335001468658447, "learning_rate": 2.221648728398296e-05, "loss": 3.7451, "step": 9953 }, { "epoch": 0.535622040464916, "grad_norm": 2.9098598957061768, "learning_rate": 2.221228739477421e-05, "loss": 4.002, "step": 9954 }, { "epoch": 0.535675850193715, "grad_norm": 3.0593161582946777, "learning_rate": 2.2208087585230787e-05, "loss": 3.7262, "step": 9955 }, { "epoch": 0.535729659922514, "grad_norm": 2.749966621398926, "learning_rate": 2.2203887855472706e-05, "loss": 3.9608, "step": 9956 }, { "epoch": 0.535783469651313, "grad_norm": 2.1454288959503174, "learning_rate": 2.2199688205619996e-05, "loss": 4.4862, "step": 9957 }, { "epoch": 0.5358372793801119, "grad_norm": 3.177949905395508, "learning_rate": 2.2195488635792663e-05, "loss": 3.0627, "step": 9958 }, { "epoch": 0.5358910891089109, "grad_norm": 1.7626700401306152, "learning_rate": 2.2191289146110716e-05, "loss": 4.317, "step": 9959 }, { "epoch": 0.5359448988377099, "grad_norm": 2.9253756999969482, "learning_rate": 2.2187089736694176e-05, "loss": 4.2883, "step": 9960 }, { "epoch": 0.5359987085665088, "grad_norm": 1.855671763420105, "learning_rate": 2.2182890407663046e-05, "loss": 4.428, "step": 9961 }, { "epoch": 0.5360525182953078, "grad_norm": 2.923969268798828, "learning_rate": 2.2178691159137335e-05, "loss": 3.4967, "step": 9962 }, { "epoch": 0.5361063280241067, "grad_norm": 2.2268521785736084, "learning_rate": 2.2174491991237038e-05, "loss": 4.0005, "step": 9963 }, { "epoch": 0.5361601377529057, "grad_norm": 2.5401294231414795, "learning_rate": 2.2170292904082156e-05, "loss": 3.5911, "step": 9964 }, { "epoch": 0.5362139474817047, "grad_norm": 2.22971510887146, "learning_rate": 2.2166093897792696e-05, "loss": 3.6202, "step": 9965 }, { "epoch": 0.5362677572105037, "grad_norm": 1.5464742183685303, "learning_rate": 2.216189497248865e-05, "loss": 4.4194, "step": 9966 }, { "epoch": 0.5363215669393027, "grad_norm": 3.439840316772461, "learning_rate": 2.2157696128290006e-05, "loss": 4.237, "step": 9967 }, { "epoch": 0.5363753766681016, "grad_norm": 3.251699686050415, "learning_rate": 2.2153497365316768e-05, "loss": 3.7134, "step": 9968 }, { "epoch": 0.5364291863969005, "grad_norm": 1.1948792934417725, "learning_rate": 2.2149298683688918e-05, "loss": 4.3055, "step": 9969 }, { "epoch": 0.5364829961256995, "grad_norm": 1.9967288970947266, "learning_rate": 2.214510008352645e-05, "loss": 3.8201, "step": 9970 }, { "epoch": 0.5365368058544985, "grad_norm": 2.219546318054199, "learning_rate": 2.214090156494934e-05, "loss": 4.2501, "step": 9971 }, { "epoch": 0.5365906155832975, "grad_norm": 3.249915838241577, "learning_rate": 2.2136703128077564e-05, "loss": 3.9162, "step": 9972 }, { "epoch": 0.5366444253120964, "grad_norm": 1.7838839292526245, "learning_rate": 2.213250477303112e-05, "loss": 4.586, "step": 9973 }, { "epoch": 0.5366982350408954, "grad_norm": 2.268237590789795, "learning_rate": 2.2128306499929978e-05, "loss": 3.7563, "step": 9974 }, { "epoch": 0.5367520447696944, "grad_norm": 2.5092101097106934, "learning_rate": 2.2124108308894104e-05, "loss": 3.9186, "step": 9975 }, { "epoch": 0.5368058544984933, "grad_norm": 1.818803071975708, "learning_rate": 2.2119910200043485e-05, "loss": 4.1736, "step": 9976 }, { "epoch": 0.5368596642272923, "grad_norm": 2.5663352012634277, "learning_rate": 2.211571217349809e-05, "loss": 3.9605, "step": 9977 }, { "epoch": 0.5369134739560912, "grad_norm": 2.4047021865844727, "learning_rate": 2.211151422937788e-05, "loss": 4.2755, "step": 9978 }, { "epoch": 0.5369672836848902, "grad_norm": 1.155434250831604, "learning_rate": 2.2107316367802822e-05, "loss": 4.5497, "step": 9979 }, { "epoch": 0.5370210934136892, "grad_norm": 3.07320499420166, "learning_rate": 2.2103118588892878e-05, "loss": 4.3901, "step": 9980 }, { "epoch": 0.5370749031424882, "grad_norm": 2.4049088954925537, "learning_rate": 2.2098920892768018e-05, "loss": 4.0107, "step": 9981 }, { "epoch": 0.5371287128712872, "grad_norm": 1.116424560546875, "learning_rate": 2.2094723279548198e-05, "loss": 4.6359, "step": 9982 }, { "epoch": 0.5371825226000861, "grad_norm": 3.173285961151123, "learning_rate": 2.2090525749353365e-05, "loss": 3.6621, "step": 9983 }, { "epoch": 0.537236332328885, "grad_norm": 1.2461447715759277, "learning_rate": 2.2086328302303483e-05, "loss": 4.4564, "step": 9984 }, { "epoch": 0.537290142057684, "grad_norm": 2.7287802696228027, "learning_rate": 2.208213093851851e-05, "loss": 3.2362, "step": 9985 }, { "epoch": 0.537343951786483, "grad_norm": 2.9270341396331787, "learning_rate": 2.2077933658118384e-05, "loss": 3.6705, "step": 9986 }, { "epoch": 0.537397761515282, "grad_norm": 2.2676496505737305, "learning_rate": 2.2073736461223043e-05, "loss": 4.1353, "step": 9987 }, { "epoch": 0.5374515712440809, "grad_norm": 3.038809061050415, "learning_rate": 2.2069539347952454e-05, "loss": 3.8089, "step": 9988 }, { "epoch": 0.5375053809728799, "grad_norm": 1.57586669921875, "learning_rate": 2.2065342318426548e-05, "loss": 3.4586, "step": 9989 }, { "epoch": 0.5375591907016789, "grad_norm": 3.203357219696045, "learning_rate": 2.2061145372765256e-05, "loss": 3.5919, "step": 9990 }, { "epoch": 0.5376130004304779, "grad_norm": 1.9334580898284912, "learning_rate": 2.2056948511088534e-05, "loss": 4.1452, "step": 9991 }, { "epoch": 0.5376668101592768, "grad_norm": 1.7774202823638916, "learning_rate": 2.20527517335163e-05, "loss": 4.348, "step": 9992 }, { "epoch": 0.5377206198880757, "grad_norm": 2.7833077907562256, "learning_rate": 2.204855504016851e-05, "loss": 3.9588, "step": 9993 }, { "epoch": 0.5377744296168747, "grad_norm": 2.4947433471679688, "learning_rate": 2.2044358431165066e-05, "loss": 4.2904, "step": 9994 }, { "epoch": 0.5378282393456737, "grad_norm": 1.116014838218689, "learning_rate": 2.2040161906625906e-05, "loss": 4.6029, "step": 9995 }, { "epoch": 0.5378820490744727, "grad_norm": 2.755842924118042, "learning_rate": 2.2035965466670964e-05, "loss": 3.9538, "step": 9996 }, { "epoch": 0.5379358588032717, "grad_norm": 1.2352302074432373, "learning_rate": 2.2031769111420154e-05, "loss": 4.6276, "step": 9997 }, { "epoch": 0.5379896685320706, "grad_norm": 2.034005641937256, "learning_rate": 2.2027572840993395e-05, "loss": 4.0812, "step": 9998 }, { "epoch": 0.5380434782608695, "grad_norm": 1.222117304801941, "learning_rate": 2.2023376655510613e-05, "loss": 4.2875, "step": 9999 }, { "epoch": 0.5380972879896685, "grad_norm": 2.132627487182617, "learning_rate": 2.201918055509173e-05, "loss": 4.0413, "step": 10000 }, { "epoch": 0.5381510977184675, "grad_norm": 1.7833091020584106, "learning_rate": 2.201498453985664e-05, "loss": 4.1443, "step": 10001 }, { "epoch": 0.5382049074472665, "grad_norm": 1.7054710388183594, "learning_rate": 2.2010788609925264e-05, "loss": 4.2193, "step": 10002 }, { "epoch": 0.5382587171760654, "grad_norm": 2.3920950889587402, "learning_rate": 2.2006592765417506e-05, "loss": 4.0077, "step": 10003 }, { "epoch": 0.5383125269048644, "grad_norm": 2.595451831817627, "learning_rate": 2.2002397006453276e-05, "loss": 4.4276, "step": 10004 }, { "epoch": 0.5383663366336634, "grad_norm": 1.8539987802505493, "learning_rate": 2.199820133315248e-05, "loss": 4.2573, "step": 10005 }, { "epoch": 0.5384201463624624, "grad_norm": 2.9778635501861572, "learning_rate": 2.199400574563501e-05, "loss": 3.9427, "step": 10006 }, { "epoch": 0.5384739560912613, "grad_norm": 1.076421856880188, "learning_rate": 2.1989810244020778e-05, "loss": 4.377, "step": 10007 }, { "epoch": 0.5385277658200602, "grad_norm": 3.5064032077789307, "learning_rate": 2.1985614828429678e-05, "loss": 3.8607, "step": 10008 }, { "epoch": 0.5385815755488592, "grad_norm": 1.768541932106018, "learning_rate": 2.198141949898159e-05, "loss": 4.0396, "step": 10009 }, { "epoch": 0.5386353852776582, "grad_norm": 2.5123040676116943, "learning_rate": 2.1977224255796417e-05, "loss": 4.6197, "step": 10010 }, { "epoch": 0.5386891950064572, "grad_norm": 3.1024796962738037, "learning_rate": 2.1973029098994035e-05, "loss": 3.0306, "step": 10011 }, { "epoch": 0.5387430047352562, "grad_norm": 1.0921430587768555, "learning_rate": 2.1968834028694347e-05, "loss": 4.4478, "step": 10012 }, { "epoch": 0.5387968144640551, "grad_norm": 2.09547758102417, "learning_rate": 2.1964639045017233e-05, "loss": 4.569, "step": 10013 }, { "epoch": 0.5388506241928541, "grad_norm": 2.4458203315734863, "learning_rate": 2.1960444148082563e-05, "loss": 4.2061, "step": 10014 }, { "epoch": 0.538904433921653, "grad_norm": 3.002187728881836, "learning_rate": 2.1956249338010228e-05, "loss": 3.65, "step": 10015 }, { "epoch": 0.538958243650452, "grad_norm": 2.1685903072357178, "learning_rate": 2.1952054614920106e-05, "loss": 3.6759, "step": 10016 }, { "epoch": 0.539012053379251, "grad_norm": 2.5841219425201416, "learning_rate": 2.1947859978932062e-05, "loss": 3.378, "step": 10017 }, { "epoch": 0.5390658631080499, "grad_norm": 2.2142250537872314, "learning_rate": 2.1943665430165962e-05, "loss": 4.2734, "step": 10018 }, { "epoch": 0.5391196728368489, "grad_norm": 2.322072982788086, "learning_rate": 2.1939470968741692e-05, "loss": 4.2996, "step": 10019 }, { "epoch": 0.5391734825656479, "grad_norm": 1.6350537538528442, "learning_rate": 2.1935276594779106e-05, "loss": 4.6105, "step": 10020 }, { "epoch": 0.5392272922944469, "grad_norm": 2.8659238815307617, "learning_rate": 2.1931082308398067e-05, "loss": 4.6734, "step": 10021 }, { "epoch": 0.5392811020232458, "grad_norm": 1.9407062530517578, "learning_rate": 2.192688810971845e-05, "loss": 3.8695, "step": 10022 }, { "epoch": 0.5393349117520447, "grad_norm": 2.60923433303833, "learning_rate": 2.1922693998860107e-05, "loss": 4.5272, "step": 10023 }, { "epoch": 0.5393887214808437, "grad_norm": 2.109463930130005, "learning_rate": 2.1918499975942892e-05, "loss": 4.0416, "step": 10024 }, { "epoch": 0.5394425312096427, "grad_norm": 3.083810567855835, "learning_rate": 2.1914306041086655e-05, "loss": 4.5073, "step": 10025 }, { "epoch": 0.5394963409384417, "grad_norm": 3.6038525104522705, "learning_rate": 2.1910112194411248e-05, "loss": 3.1032, "step": 10026 }, { "epoch": 0.5395501506672407, "grad_norm": 2.997112274169922, "learning_rate": 2.1905918436036528e-05, "loss": 3.7507, "step": 10027 }, { "epoch": 0.5396039603960396, "grad_norm": 1.8553601503372192, "learning_rate": 2.1901724766082337e-05, "loss": 3.9713, "step": 10028 }, { "epoch": 0.5396577701248386, "grad_norm": 1.1648046970367432, "learning_rate": 2.1897531184668517e-05, "loss": 4.4651, "step": 10029 }, { "epoch": 0.5397115798536375, "grad_norm": 2.013970136642456, "learning_rate": 2.1893337691914913e-05, "loss": 4.1854, "step": 10030 }, { "epoch": 0.5397653895824365, "grad_norm": 2.649974822998047, "learning_rate": 2.1889144287941367e-05, "loss": 4.1435, "step": 10031 }, { "epoch": 0.5398191993112355, "grad_norm": 2.005641460418701, "learning_rate": 2.1884950972867706e-05, "loss": 3.8668, "step": 10032 }, { "epoch": 0.5398730090400344, "grad_norm": 1.186907172203064, "learning_rate": 2.1880757746813765e-05, "loss": 4.2818, "step": 10033 }, { "epoch": 0.5399268187688334, "grad_norm": 2.2402563095092773, "learning_rate": 2.1876564609899373e-05, "loss": 4.3082, "step": 10034 }, { "epoch": 0.5399806284976324, "grad_norm": 2.8342013359069824, "learning_rate": 2.187237156224437e-05, "loss": 4.4581, "step": 10035 }, { "epoch": 0.5400344382264314, "grad_norm": 1.4987863302230835, "learning_rate": 2.1868178603968578e-05, "loss": 4.4094, "step": 10036 }, { "epoch": 0.5400882479552304, "grad_norm": 2.6158127784729004, "learning_rate": 2.186398573519181e-05, "loss": 4.0929, "step": 10037 }, { "epoch": 0.5401420576840292, "grad_norm": 2.0361714363098145, "learning_rate": 2.18597929560339e-05, "loss": 4.3445, "step": 10038 }, { "epoch": 0.5401958674128282, "grad_norm": 1.0490248203277588, "learning_rate": 2.1855600266614667e-05, "loss": 4.4149, "step": 10039 }, { "epoch": 0.5402496771416272, "grad_norm": 2.215331554412842, "learning_rate": 2.1851407667053918e-05, "loss": 3.5655, "step": 10040 }, { "epoch": 0.5403034868704262, "grad_norm": 2.018996477127075, "learning_rate": 2.1847215157471466e-05, "loss": 4.3854, "step": 10041 }, { "epoch": 0.5403572965992252, "grad_norm": 1.117900013923645, "learning_rate": 2.184302273798712e-05, "loss": 4.5666, "step": 10042 }, { "epoch": 0.5404111063280241, "grad_norm": 2.8217082023620605, "learning_rate": 2.1838830408720696e-05, "loss": 3.6897, "step": 10043 }, { "epoch": 0.5404649160568231, "grad_norm": 2.1847941875457764, "learning_rate": 2.1834638169792e-05, "loss": 4.5802, "step": 10044 }, { "epoch": 0.540518725785622, "grad_norm": 1.090822696685791, "learning_rate": 2.1830446021320825e-05, "loss": 4.482, "step": 10045 }, { "epoch": 0.540572535514421, "grad_norm": 2.001786708831787, "learning_rate": 2.1826253963426986e-05, "loss": 4.1343, "step": 10046 }, { "epoch": 0.54062634524322, "grad_norm": 3.274502992630005, "learning_rate": 2.1822061996230268e-05, "loss": 3.6897, "step": 10047 }, { "epoch": 0.5406801549720189, "grad_norm": 2.9345498085021973, "learning_rate": 2.1817870119850474e-05, "loss": 3.7848, "step": 10048 }, { "epoch": 0.5407339647008179, "grad_norm": 2.136317491531372, "learning_rate": 2.1813678334407385e-05, "loss": 4.4192, "step": 10049 }, { "epoch": 0.5407877744296169, "grad_norm": 2.239426851272583, "learning_rate": 2.1809486640020806e-05, "loss": 4.5803, "step": 10050 }, { "epoch": 0.5408415841584159, "grad_norm": 3.7017972469329834, "learning_rate": 2.1805295036810513e-05, "loss": 4.3397, "step": 10051 }, { "epoch": 0.5408953938872149, "grad_norm": 1.9884752035140991, "learning_rate": 2.1801103524896294e-05, "loss": 4.1997, "step": 10052 }, { "epoch": 0.5409492036160137, "grad_norm": 2.583939790725708, "learning_rate": 2.1796912104397933e-05, "loss": 3.683, "step": 10053 }, { "epoch": 0.5410030133448127, "grad_norm": 2.3638765811920166, "learning_rate": 2.1792720775435218e-05, "loss": 4.478, "step": 10054 }, { "epoch": 0.5410568230736117, "grad_norm": 2.398926019668579, "learning_rate": 2.178852953812791e-05, "loss": 3.9173, "step": 10055 }, { "epoch": 0.5411106328024107, "grad_norm": 1.1603468656539917, "learning_rate": 2.1784338392595795e-05, "loss": 4.3238, "step": 10056 }, { "epoch": 0.5411644425312097, "grad_norm": 3.021012783050537, "learning_rate": 2.178014733895863e-05, "loss": 4.1094, "step": 10057 }, { "epoch": 0.5412182522600086, "grad_norm": 2.7430717945098877, "learning_rate": 2.1775956377336196e-05, "loss": 3.9161, "step": 10058 }, { "epoch": 0.5412720619888076, "grad_norm": 2.0683419704437256, "learning_rate": 2.177176550784826e-05, "loss": 4.3681, "step": 10059 }, { "epoch": 0.5413258717176065, "grad_norm": 1.840035319328308, "learning_rate": 2.1767574730614578e-05, "loss": 4.3289, "step": 10060 }, { "epoch": 0.5413796814464055, "grad_norm": 1.7855075597763062, "learning_rate": 2.176338404575493e-05, "loss": 4.3794, "step": 10061 }, { "epoch": 0.5414334911752045, "grad_norm": 1.7199151515960693, "learning_rate": 2.175919345338905e-05, "loss": 4.3631, "step": 10062 }, { "epoch": 0.5414873009040034, "grad_norm": 2.334747076034546, "learning_rate": 2.1755002953636702e-05, "loss": 4.2313, "step": 10063 }, { "epoch": 0.5415411106328024, "grad_norm": 1.851921558380127, "learning_rate": 2.1750812546617647e-05, "loss": 4.6525, "step": 10064 }, { "epoch": 0.5415949203616014, "grad_norm": 2.023512840270996, "learning_rate": 2.174662223245162e-05, "loss": 4.3298, "step": 10065 }, { "epoch": 0.5416487300904004, "grad_norm": 2.662048578262329, "learning_rate": 2.174243201125839e-05, "loss": 4.4217, "step": 10066 }, { "epoch": 0.5417025398191994, "grad_norm": 2.9063522815704346, "learning_rate": 2.173824188315769e-05, "loss": 4.3904, "step": 10067 }, { "epoch": 0.5417563495479982, "grad_norm": 3.0559823513031006, "learning_rate": 2.1734051848269255e-05, "loss": 3.8022, "step": 10068 }, { "epoch": 0.5418101592767972, "grad_norm": 2.000614881515503, "learning_rate": 2.1729861906712846e-05, "loss": 4.2512, "step": 10069 }, { "epoch": 0.5418639690055962, "grad_norm": 1.4680061340332031, "learning_rate": 2.1725672058608186e-05, "loss": 3.7369, "step": 10070 }, { "epoch": 0.5419177787343952, "grad_norm": 2.8782546520233154, "learning_rate": 2.172148230407501e-05, "loss": 3.39, "step": 10071 }, { "epoch": 0.5419715884631942, "grad_norm": 2.98415470123291, "learning_rate": 2.1717292643233043e-05, "loss": 3.9291, "step": 10072 }, { "epoch": 0.5420253981919931, "grad_norm": 1.9167662858963013, "learning_rate": 2.171310307620203e-05, "loss": 4.7673, "step": 10073 }, { "epoch": 0.5420792079207921, "grad_norm": 3.059257745742798, "learning_rate": 2.1708913603101692e-05, "loss": 3.8228, "step": 10074 }, { "epoch": 0.5421330176495911, "grad_norm": 1.6621025800704956, "learning_rate": 2.170472422405175e-05, "loss": 4.3256, "step": 10075 }, { "epoch": 0.54218682737839, "grad_norm": 1.9070254564285278, "learning_rate": 2.1700534939171917e-05, "loss": 4.046, "step": 10076 }, { "epoch": 0.542240637107189, "grad_norm": 2.5348572731018066, "learning_rate": 2.169634574858194e-05, "loss": 3.6406, "step": 10077 }, { "epoch": 0.5422944468359879, "grad_norm": 2.630448818206787, "learning_rate": 2.1692156652401505e-05, "loss": 4.2912, "step": 10078 }, { "epoch": 0.5423482565647869, "grad_norm": 1.4142812490463257, "learning_rate": 2.1687967650750337e-05, "loss": 4.8415, "step": 10079 }, { "epoch": 0.5424020662935859, "grad_norm": 1.8322253227233887, "learning_rate": 2.168377874374814e-05, "loss": 4.3727, "step": 10080 }, { "epoch": 0.5424558760223849, "grad_norm": 3.151568651199341, "learning_rate": 2.1679589931514633e-05, "loss": 4.0509, "step": 10081 }, { "epoch": 0.5425096857511839, "grad_norm": 2.778995990753174, "learning_rate": 2.1675401214169515e-05, "loss": 3.3314, "step": 10082 }, { "epoch": 0.5425634954799827, "grad_norm": 1.6565265655517578, "learning_rate": 2.167121259183248e-05, "loss": 4.2001, "step": 10083 }, { "epoch": 0.5426173052087817, "grad_norm": 2.26507568359375, "learning_rate": 2.1667024064623254e-05, "loss": 4.1641, "step": 10084 }, { "epoch": 0.5426711149375807, "grad_norm": 2.8265533447265625, "learning_rate": 2.16628356326615e-05, "loss": 4.312, "step": 10085 }, { "epoch": 0.5427249246663797, "grad_norm": 2.3386311531066895, "learning_rate": 2.165864729606693e-05, "loss": 3.9801, "step": 10086 }, { "epoch": 0.5427787343951787, "grad_norm": 2.105797529220581, "learning_rate": 2.1654459054959237e-05, "loss": 4.6396, "step": 10087 }, { "epoch": 0.5428325441239776, "grad_norm": 3.3513331413269043, "learning_rate": 2.16502709094581e-05, "loss": 3.6842, "step": 10088 }, { "epoch": 0.5428863538527766, "grad_norm": 2.8495888710021973, "learning_rate": 2.164608285968321e-05, "loss": 3.7681, "step": 10089 }, { "epoch": 0.5429401635815756, "grad_norm": 3.548553705215454, "learning_rate": 2.1641894905754256e-05, "loss": 3.7322, "step": 10090 }, { "epoch": 0.5429939733103745, "grad_norm": 1.2345855236053467, "learning_rate": 2.163770704779091e-05, "loss": 4.3953, "step": 10091 }, { "epoch": 0.5430477830391734, "grad_norm": 1.5253432989120483, "learning_rate": 2.163351928591287e-05, "loss": 4.1025, "step": 10092 }, { "epoch": 0.5431015927679724, "grad_norm": 2.347581386566162, "learning_rate": 2.1629331620239772e-05, "loss": 4.4706, "step": 10093 }, { "epoch": 0.5431554024967714, "grad_norm": 2.319042921066284, "learning_rate": 2.1625144050891316e-05, "loss": 4.2264, "step": 10094 }, { "epoch": 0.5432092122255704, "grad_norm": 2.294241428375244, "learning_rate": 2.162095657798717e-05, "loss": 4.1695, "step": 10095 }, { "epoch": 0.5432630219543694, "grad_norm": 2.0895321369171143, "learning_rate": 2.161676920164699e-05, "loss": 4.0533, "step": 10096 }, { "epoch": 0.5433168316831684, "grad_norm": 2.1690685749053955, "learning_rate": 2.161258192199045e-05, "loss": 4.0026, "step": 10097 }, { "epoch": 0.5433706414119673, "grad_norm": 1.7984585762023926, "learning_rate": 2.1608394739137208e-05, "loss": 4.2066, "step": 10098 }, { "epoch": 0.5434244511407662, "grad_norm": 2.7309346199035645, "learning_rate": 2.1604207653206918e-05, "loss": 3.8834, "step": 10099 }, { "epoch": 0.5434782608695652, "grad_norm": 2.9719414710998535, "learning_rate": 2.1600020664319248e-05, "loss": 4.3826, "step": 10100 }, { "epoch": 0.5435320705983642, "grad_norm": 3.033933401107788, "learning_rate": 2.159583377259384e-05, "loss": 4.385, "step": 10101 }, { "epoch": 0.5435858803271632, "grad_norm": 2.402770757675171, "learning_rate": 2.1591646978150345e-05, "loss": 4.1098, "step": 10102 }, { "epoch": 0.5436396900559621, "grad_norm": 2.5161325931549072, "learning_rate": 2.1587460281108406e-05, "loss": 4.359, "step": 10103 }, { "epoch": 0.5436934997847611, "grad_norm": 2.2270495891571045, "learning_rate": 2.158327368158768e-05, "loss": 3.8979, "step": 10104 }, { "epoch": 0.5437473095135601, "grad_norm": 1.8637324571609497, "learning_rate": 2.1579087179707804e-05, "loss": 4.6032, "step": 10105 }, { "epoch": 0.543801119242359, "grad_norm": 2.7014222145080566, "learning_rate": 2.1574900775588407e-05, "loss": 3.6958, "step": 10106 }, { "epoch": 0.543854928971158, "grad_norm": 3.2687621116638184, "learning_rate": 2.157071446934915e-05, "loss": 3.4406, "step": 10107 }, { "epoch": 0.5439087386999569, "grad_norm": 2.78188157081604, "learning_rate": 2.1566528261109633e-05, "loss": 3.7941, "step": 10108 }, { "epoch": 0.5439625484287559, "grad_norm": 2.9810614585876465, "learning_rate": 2.156234215098951e-05, "loss": 4.4517, "step": 10109 }, { "epoch": 0.5440163581575549, "grad_norm": 2.5143191814422607, "learning_rate": 2.1558156139108403e-05, "loss": 3.4675, "step": 10110 }, { "epoch": 0.5440701678863539, "grad_norm": 1.4495278596878052, "learning_rate": 2.155397022558593e-05, "loss": 4.3997, "step": 10111 }, { "epoch": 0.5441239776151529, "grad_norm": 1.7431074380874634, "learning_rate": 2.1549784410541722e-05, "loss": 4.48, "step": 10112 }, { "epoch": 0.5441777873439518, "grad_norm": 2.235750198364258, "learning_rate": 2.15455986940954e-05, "loss": 4.1787, "step": 10113 }, { "epoch": 0.5442315970727507, "grad_norm": 1.5508854389190674, "learning_rate": 2.154141307636657e-05, "loss": 4.7956, "step": 10114 }, { "epoch": 0.5442854068015497, "grad_norm": 1.241719365119934, "learning_rate": 2.1537227557474865e-05, "loss": 4.5855, "step": 10115 }, { "epoch": 0.5443392165303487, "grad_norm": 2.50137996673584, "learning_rate": 2.1533042137539865e-05, "loss": 4.2309, "step": 10116 }, { "epoch": 0.5443930262591476, "grad_norm": 3.0824081897735596, "learning_rate": 2.1528856816681205e-05, "loss": 3.795, "step": 10117 }, { "epoch": 0.5444468359879466, "grad_norm": 1.347072720527649, "learning_rate": 2.1524671595018482e-05, "loss": 4.3378, "step": 10118 }, { "epoch": 0.5445006457167456, "grad_norm": 1.486290454864502, "learning_rate": 2.152048647267129e-05, "loss": 4.1147, "step": 10119 }, { "epoch": 0.5445544554455446, "grad_norm": 3.6380743980407715, "learning_rate": 2.151630144975924e-05, "loss": 4.0353, "step": 10120 }, { "epoch": 0.5446082651743436, "grad_norm": 2.260436534881592, "learning_rate": 2.1512116526401928e-05, "loss": 3.4397, "step": 10121 }, { "epoch": 0.5446620749031424, "grad_norm": 2.289409637451172, "learning_rate": 2.1507931702718932e-05, "loss": 4.2959, "step": 10122 }, { "epoch": 0.5447158846319414, "grad_norm": 3.1605637073516846, "learning_rate": 2.150374697882988e-05, "loss": 3.7647, "step": 10123 }, { "epoch": 0.5447696943607404, "grad_norm": 2.447028160095215, "learning_rate": 2.1499562354854312e-05, "loss": 3.9653, "step": 10124 }, { "epoch": 0.5448235040895394, "grad_norm": 2.051074743270874, "learning_rate": 2.1495377830911848e-05, "loss": 3.9055, "step": 10125 }, { "epoch": 0.5448773138183384, "grad_norm": 2.983426094055176, "learning_rate": 2.1491193407122055e-05, "loss": 4.3237, "step": 10126 }, { "epoch": 0.5449311235471374, "grad_norm": 1.5562313795089722, "learning_rate": 2.1487009083604514e-05, "loss": 4.5938, "step": 10127 }, { "epoch": 0.5449849332759363, "grad_norm": 2.4955952167510986, "learning_rate": 2.148282486047881e-05, "loss": 3.8582, "step": 10128 }, { "epoch": 0.5450387430047352, "grad_norm": 2.8319578170776367, "learning_rate": 2.1478640737864513e-05, "loss": 4.0238, "step": 10129 }, { "epoch": 0.5450925527335342, "grad_norm": 2.712791681289673, "learning_rate": 2.147445671588119e-05, "loss": 3.6643, "step": 10130 }, { "epoch": 0.5451463624623332, "grad_norm": 3.6228575706481934, "learning_rate": 2.147027279464841e-05, "loss": 3.5808, "step": 10131 }, { "epoch": 0.5452001721911321, "grad_norm": 3.6787068843841553, "learning_rate": 2.146608897428574e-05, "loss": 3.7163, "step": 10132 }, { "epoch": 0.5452539819199311, "grad_norm": 1.9944628477096558, "learning_rate": 2.146190525491274e-05, "loss": 3.9147, "step": 10133 }, { "epoch": 0.5453077916487301, "grad_norm": 2.447122812271118, "learning_rate": 2.145772163664897e-05, "loss": 4.3006, "step": 10134 }, { "epoch": 0.5453616013775291, "grad_norm": 2.220553398132324, "learning_rate": 2.1453538119613996e-05, "loss": 4.6299, "step": 10135 }, { "epoch": 0.5454154111063281, "grad_norm": 3.5666091442108154, "learning_rate": 2.144935470392736e-05, "loss": 3.9978, "step": 10136 }, { "epoch": 0.5454692208351269, "grad_norm": 1.5764323472976685, "learning_rate": 2.1445171389708614e-05, "loss": 4.6924, "step": 10137 }, { "epoch": 0.5455230305639259, "grad_norm": 1.2822632789611816, "learning_rate": 2.144098817707732e-05, "loss": 4.2008, "step": 10138 }, { "epoch": 0.5455768402927249, "grad_norm": 2.479429006576538, "learning_rate": 2.1436805066152997e-05, "loss": 3.5593, "step": 10139 }, { "epoch": 0.5456306500215239, "grad_norm": 1.2757729291915894, "learning_rate": 2.1432622057055207e-05, "loss": 4.4283, "step": 10140 }, { "epoch": 0.5456844597503229, "grad_norm": 2.6477880477905273, "learning_rate": 2.1428439149903483e-05, "loss": 4.2156, "step": 10141 }, { "epoch": 0.5457382694791219, "grad_norm": 3.082399368286133, "learning_rate": 2.1424256344817355e-05, "loss": 3.3756, "step": 10142 }, { "epoch": 0.5457920792079208, "grad_norm": 1.855579137802124, "learning_rate": 2.142007364191637e-05, "loss": 3.8395, "step": 10143 }, { "epoch": 0.5458458889367198, "grad_norm": 3.1693034172058105, "learning_rate": 2.141589104132005e-05, "loss": 4.3622, "step": 10144 }, { "epoch": 0.5458996986655187, "grad_norm": 2.2391669750213623, "learning_rate": 2.141170854314792e-05, "loss": 3.9511, "step": 10145 }, { "epoch": 0.5459535083943177, "grad_norm": 1.3933104276657104, "learning_rate": 2.1407526147519528e-05, "loss": 4.2469, "step": 10146 }, { "epoch": 0.5460073181231166, "grad_norm": 2.6476032733917236, "learning_rate": 2.1403343854554356e-05, "loss": 4.0804, "step": 10147 }, { "epoch": 0.5460611278519156, "grad_norm": 1.9943927526474, "learning_rate": 2.1399161664371946e-05, "loss": 4.4607, "step": 10148 }, { "epoch": 0.5461149375807146, "grad_norm": 2.049673557281494, "learning_rate": 2.1394979577091814e-05, "loss": 4.1467, "step": 10149 }, { "epoch": 0.5461687473095136, "grad_norm": 1.526222825050354, "learning_rate": 2.1390797592833464e-05, "loss": 4.8896, "step": 10150 }, { "epoch": 0.5462225570383126, "grad_norm": 2.8885574340820312, "learning_rate": 2.1386615711716416e-05, "loss": 3.4958, "step": 10151 }, { "epoch": 0.5462763667671114, "grad_norm": 3.820141315460205, "learning_rate": 2.138243393386017e-05, "loss": 2.9578, "step": 10152 }, { "epoch": 0.5463301764959104, "grad_norm": 2.5694730281829834, "learning_rate": 2.137825225938424e-05, "loss": 4.1709, "step": 10153 }, { "epoch": 0.5463839862247094, "grad_norm": 2.6984431743621826, "learning_rate": 2.1374070688408115e-05, "loss": 4.423, "step": 10154 }, { "epoch": 0.5464377959535084, "grad_norm": 2.792689085006714, "learning_rate": 2.1369889221051286e-05, "loss": 4.0215, "step": 10155 }, { "epoch": 0.5464916056823074, "grad_norm": 3.367173671722412, "learning_rate": 2.136570785743327e-05, "loss": 3.7131, "step": 10156 }, { "epoch": 0.5465454154111064, "grad_norm": 1.569028377532959, "learning_rate": 2.136152659767355e-05, "loss": 4.3994, "step": 10157 }, { "epoch": 0.5465992251399053, "grad_norm": 2.4054477214813232, "learning_rate": 2.1357345441891603e-05, "loss": 3.9711, "step": 10158 }, { "epoch": 0.5466530348687043, "grad_norm": 3.0062942504882812, "learning_rate": 2.1353164390206932e-05, "loss": 4.1023, "step": 10159 }, { "epoch": 0.5467068445975032, "grad_norm": 2.6168558597564697, "learning_rate": 2.1348983442739014e-05, "loss": 3.7183, "step": 10160 }, { "epoch": 0.5467606543263022, "grad_norm": 1.738473892211914, "learning_rate": 2.1344802599607337e-05, "loss": 4.4694, "step": 10161 }, { "epoch": 0.5468144640551011, "grad_norm": 3.5274696350097656, "learning_rate": 2.1340621860931356e-05, "loss": 4.0331, "step": 10162 }, { "epoch": 0.5468682737839001, "grad_norm": 1.0317633152008057, "learning_rate": 2.1336441226830568e-05, "loss": 4.5273, "step": 10163 }, { "epoch": 0.5469220835126991, "grad_norm": 3.0602407455444336, "learning_rate": 2.1332260697424435e-05, "loss": 4.6539, "step": 10164 }, { "epoch": 0.5469758932414981, "grad_norm": 1.6098600625991821, "learning_rate": 2.1328080272832418e-05, "loss": 4.0789, "step": 10165 }, { "epoch": 0.5470297029702971, "grad_norm": 3.0050048828125, "learning_rate": 2.1323899953173997e-05, "loss": 4.1899, "step": 10166 }, { "epoch": 0.5470835126990959, "grad_norm": 2.1896679401397705, "learning_rate": 2.1319719738568634e-05, "loss": 4.0679, "step": 10167 }, { "epoch": 0.5471373224278949, "grad_norm": 3.1215875148773193, "learning_rate": 2.131553962913578e-05, "loss": 3.593, "step": 10168 }, { "epoch": 0.5471911321566939, "grad_norm": 2.2680160999298096, "learning_rate": 2.1311359624994893e-05, "loss": 4.2957, "step": 10169 }, { "epoch": 0.5472449418854929, "grad_norm": 1.9197295904159546, "learning_rate": 2.1307179726265416e-05, "loss": 4.3212, "step": 10170 }, { "epoch": 0.5472987516142919, "grad_norm": 2.6306986808776855, "learning_rate": 2.130299993306682e-05, "loss": 3.6872, "step": 10171 }, { "epoch": 0.5473525613430908, "grad_norm": 2.654542922973633, "learning_rate": 2.1298820245518542e-05, "loss": 3.9109, "step": 10172 }, { "epoch": 0.5474063710718898, "grad_norm": 1.9378464221954346, "learning_rate": 2.129464066374002e-05, "loss": 4.3078, "step": 10173 }, { "epoch": 0.5474601808006888, "grad_norm": 2.624128580093384, "learning_rate": 2.1290461187850704e-05, "loss": 3.5805, "step": 10174 }, { "epoch": 0.5475139905294877, "grad_norm": 3.3534538745880127, "learning_rate": 2.128628181797003e-05, "loss": 3.3857, "step": 10175 }, { "epoch": 0.5475678002582867, "grad_norm": 2.4411873817443848, "learning_rate": 2.128210255421744e-05, "loss": 3.8241, "step": 10176 }, { "epoch": 0.5476216099870856, "grad_norm": 2.3045527935028076, "learning_rate": 2.1277923396712358e-05, "loss": 3.9535, "step": 10177 }, { "epoch": 0.5476754197158846, "grad_norm": 2.0858993530273438, "learning_rate": 2.1273744345574202e-05, "loss": 4.5769, "step": 10178 }, { "epoch": 0.5477292294446836, "grad_norm": 1.4773985147476196, "learning_rate": 2.126956540092242e-05, "loss": 4.2517, "step": 10179 }, { "epoch": 0.5477830391734826, "grad_norm": 3.7641875743865967, "learning_rate": 2.1265386562876422e-05, "loss": 3.5846, "step": 10180 }, { "epoch": 0.5478368489022816, "grad_norm": 2.1890852451324463, "learning_rate": 2.1261207831555627e-05, "loss": 3.9327, "step": 10181 }, { "epoch": 0.5478906586310806, "grad_norm": 1.8169796466827393, "learning_rate": 2.1257029207079463e-05, "loss": 3.8923, "step": 10182 }, { "epoch": 0.5479444683598794, "grad_norm": 2.183380603790283, "learning_rate": 2.1252850689567335e-05, "loss": 4.0051, "step": 10183 }, { "epoch": 0.5479982780886784, "grad_norm": 3.0311241149902344, "learning_rate": 2.124867227913866e-05, "loss": 4.0457, "step": 10184 }, { "epoch": 0.5480520878174774, "grad_norm": 2.468369245529175, "learning_rate": 2.124449397591284e-05, "loss": 3.8965, "step": 10185 }, { "epoch": 0.5481058975462764, "grad_norm": 3.157850980758667, "learning_rate": 2.124031578000927e-05, "loss": 4.2702, "step": 10186 }, { "epoch": 0.5481597072750753, "grad_norm": 2.097052812576294, "learning_rate": 2.1236137691547374e-05, "loss": 4.069, "step": 10187 }, { "epoch": 0.5482135170038743, "grad_norm": 2.318770170211792, "learning_rate": 2.1231959710646535e-05, "loss": 4.8869, "step": 10188 }, { "epoch": 0.5482673267326733, "grad_norm": 1.9857702255249023, "learning_rate": 2.122778183742615e-05, "loss": 4.3712, "step": 10189 }, { "epoch": 0.5483211364614722, "grad_norm": 1.6538524627685547, "learning_rate": 2.1223604072005616e-05, "loss": 4.4318, "step": 10190 }, { "epoch": 0.5483749461902712, "grad_norm": 1.8411301374435425, "learning_rate": 2.1219426414504328e-05, "loss": 3.9915, "step": 10191 }, { "epoch": 0.5484287559190701, "grad_norm": 3.503864288330078, "learning_rate": 2.1215248865041658e-05, "loss": 3.9026, "step": 10192 }, { "epoch": 0.5484825656478691, "grad_norm": 2.368234634399414, "learning_rate": 2.1211071423736992e-05, "loss": 4.0934, "step": 10193 }, { "epoch": 0.5485363753766681, "grad_norm": 1.3969016075134277, "learning_rate": 2.1206894090709716e-05, "loss": 4.1136, "step": 10194 }, { "epoch": 0.5485901851054671, "grad_norm": 2.146282911300659, "learning_rate": 2.1202716866079208e-05, "loss": 4.8326, "step": 10195 }, { "epoch": 0.5486439948342661, "grad_norm": 2.27421236038208, "learning_rate": 2.1198539749964832e-05, "loss": 4.1789, "step": 10196 }, { "epoch": 0.548697804563065, "grad_norm": 1.2963643074035645, "learning_rate": 2.1194362742485972e-05, "loss": 4.4232, "step": 10197 }, { "epoch": 0.5487516142918639, "grad_norm": 2.9679064750671387, "learning_rate": 2.1190185843761985e-05, "loss": 4.092, "step": 10198 }, { "epoch": 0.5488054240206629, "grad_norm": 1.592132568359375, "learning_rate": 2.118600905391225e-05, "loss": 4.6822, "step": 10199 }, { "epoch": 0.5488592337494619, "grad_norm": 2.3060672283172607, "learning_rate": 2.1181832373056107e-05, "loss": 3.5012, "step": 10200 }, { "epoch": 0.5489130434782609, "grad_norm": 2.2945950031280518, "learning_rate": 2.1177655801312923e-05, "loss": 3.9996, "step": 10201 }, { "epoch": 0.5489668532070598, "grad_norm": 1.6116913557052612, "learning_rate": 2.117347933880206e-05, "loss": 4.2136, "step": 10202 }, { "epoch": 0.5490206629358588, "grad_norm": 2.4839234352111816, "learning_rate": 2.1169302985642865e-05, "loss": 4.0638, "step": 10203 }, { "epoch": 0.5490744726646578, "grad_norm": 1.5258166790008545, "learning_rate": 2.1165126741954684e-05, "loss": 4.4814, "step": 10204 }, { "epoch": 0.5491282823934568, "grad_norm": 1.9638187885284424, "learning_rate": 2.1160950607856867e-05, "loss": 4.7061, "step": 10205 }, { "epoch": 0.5491820921222557, "grad_norm": 3.055295705795288, "learning_rate": 2.115677458346876e-05, "loss": 3.8713, "step": 10206 }, { "epoch": 0.5492359018510546, "grad_norm": 2.841479778289795, "learning_rate": 2.11525986689097e-05, "loss": 3.2729, "step": 10207 }, { "epoch": 0.5492897115798536, "grad_norm": 1.9965734481811523, "learning_rate": 2.114842286429902e-05, "loss": 4.4627, "step": 10208 }, { "epoch": 0.5493435213086526, "grad_norm": 1.3844633102416992, "learning_rate": 2.114424716975605e-05, "loss": 4.6423, "step": 10209 }, { "epoch": 0.5493973310374516, "grad_norm": 2.5075130462646484, "learning_rate": 2.1140071585400128e-05, "loss": 3.3134, "step": 10210 }, { "epoch": 0.5494511407662506, "grad_norm": 3.5191245079040527, "learning_rate": 2.113589611135058e-05, "loss": 4.145, "step": 10211 }, { "epoch": 0.5495049504950495, "grad_norm": 3.012216806411743, "learning_rate": 2.1131720747726717e-05, "loss": 4.1739, "step": 10212 }, { "epoch": 0.5495587602238484, "grad_norm": 1.2983531951904297, "learning_rate": 2.1127545494647882e-05, "loss": 4.3599, "step": 10213 }, { "epoch": 0.5496125699526474, "grad_norm": 2.501732587814331, "learning_rate": 2.1123370352233386e-05, "loss": 3.9604, "step": 10214 }, { "epoch": 0.5496663796814464, "grad_norm": 2.2649729251861572, "learning_rate": 2.1119195320602532e-05, "loss": 4.2621, "step": 10215 }, { "epoch": 0.5497201894102454, "grad_norm": 2.594439744949341, "learning_rate": 2.1115020399874634e-05, "loss": 4.2806, "step": 10216 }, { "epoch": 0.5497739991390443, "grad_norm": 3.2976717948913574, "learning_rate": 2.1110845590169004e-05, "loss": 3.3528, "step": 10217 }, { "epoch": 0.5498278088678433, "grad_norm": 1.9369210004806519, "learning_rate": 2.1106670891604953e-05, "loss": 4.2631, "step": 10218 }, { "epoch": 0.5498816185966423, "grad_norm": 1.2874764204025269, "learning_rate": 2.110249630430177e-05, "loss": 4.5979, "step": 10219 }, { "epoch": 0.5499354283254413, "grad_norm": 1.6951711177825928, "learning_rate": 2.1098321828378756e-05, "loss": 4.2702, "step": 10220 }, { "epoch": 0.5499892380542402, "grad_norm": 3.162301778793335, "learning_rate": 2.1094147463955216e-05, "loss": 3.7101, "step": 10221 }, { "epoch": 0.5500430477830391, "grad_norm": 1.9122241735458374, "learning_rate": 2.108997321115044e-05, "loss": 4.2523, "step": 10222 }, { "epoch": 0.5500968575118381, "grad_norm": 2.066695213317871, "learning_rate": 2.108579907008371e-05, "loss": 3.5993, "step": 10223 }, { "epoch": 0.5501506672406371, "grad_norm": 1.7455111742019653, "learning_rate": 2.108162504087431e-05, "loss": 4.092, "step": 10224 }, { "epoch": 0.5502044769694361, "grad_norm": 2.0102477073669434, "learning_rate": 2.107745112364153e-05, "loss": 4.1846, "step": 10225 }, { "epoch": 0.5502582866982351, "grad_norm": 1.9602059125900269, "learning_rate": 2.1073277318504647e-05, "loss": 4.4133, "step": 10226 }, { "epoch": 0.550312096427034, "grad_norm": 2.0231456756591797, "learning_rate": 2.1069103625582932e-05, "loss": 3.8341, "step": 10227 }, { "epoch": 0.550365906155833, "grad_norm": 2.8802342414855957, "learning_rate": 2.1064930044995665e-05, "loss": 4.075, "step": 10228 }, { "epoch": 0.5504197158846319, "grad_norm": 2.2040040493011475, "learning_rate": 2.106075657686212e-05, "loss": 3.8552, "step": 10229 }, { "epoch": 0.5504735256134309, "grad_norm": 2.01601505279541, "learning_rate": 2.1056583221301555e-05, "loss": 4.4563, "step": 10230 }, { "epoch": 0.5505273353422299, "grad_norm": 3.2115073204040527, "learning_rate": 2.105240997843323e-05, "loss": 4.2026, "step": 10231 }, { "epoch": 0.5505811450710288, "grad_norm": 3.264509916305542, "learning_rate": 2.1048236848376407e-05, "loss": 3.6335, "step": 10232 }, { "epoch": 0.5506349547998278, "grad_norm": 1.7655727863311768, "learning_rate": 2.104406383125035e-05, "loss": 4.0105, "step": 10233 }, { "epoch": 0.5506887645286268, "grad_norm": 2.2583463191986084, "learning_rate": 2.103989092717431e-05, "loss": 4.1583, "step": 10234 }, { "epoch": 0.5507425742574258, "grad_norm": 2.1826627254486084, "learning_rate": 2.103571813626753e-05, "loss": 4.0682, "step": 10235 }, { "epoch": 0.5507963839862247, "grad_norm": 2.8601572513580322, "learning_rate": 2.103154545864927e-05, "loss": 4.4239, "step": 10236 }, { "epoch": 0.5508501937150236, "grad_norm": 3.2079834938049316, "learning_rate": 2.1027372894438767e-05, "loss": 3.9099, "step": 10237 }, { "epoch": 0.5509040034438226, "grad_norm": 2.0766258239746094, "learning_rate": 2.1023200443755264e-05, "loss": 4.147, "step": 10238 }, { "epoch": 0.5509578131726216, "grad_norm": 2.717299699783325, "learning_rate": 2.1019028106717993e-05, "loss": 3.1776, "step": 10239 }, { "epoch": 0.5510116229014206, "grad_norm": 2.6869025230407715, "learning_rate": 2.1014855883446183e-05, "loss": 4.3616, "step": 10240 }, { "epoch": 0.5510654326302196, "grad_norm": 1.9498273134231567, "learning_rate": 2.101068377405908e-05, "loss": 4.1735, "step": 10241 }, { "epoch": 0.5511192423590185, "grad_norm": 2.192995071411133, "learning_rate": 2.1006511778675904e-05, "loss": 4.0863, "step": 10242 }, { "epoch": 0.5511730520878175, "grad_norm": 2.30291485786438, "learning_rate": 2.1002339897415877e-05, "loss": 3.9582, "step": 10243 }, { "epoch": 0.5512268618166164, "grad_norm": 2.0752410888671875, "learning_rate": 2.0998168130398226e-05, "loss": 4.4179, "step": 10244 }, { "epoch": 0.5512806715454154, "grad_norm": 1.9383403062820435, "learning_rate": 2.0993996477742173e-05, "loss": 3.6088, "step": 10245 }, { "epoch": 0.5513344812742144, "grad_norm": 1.4557315111160278, "learning_rate": 2.0989824939566922e-05, "loss": 4.2102, "step": 10246 }, { "epoch": 0.5513882910030133, "grad_norm": 3.269031047821045, "learning_rate": 2.0985653515991685e-05, "loss": 3.3896, "step": 10247 }, { "epoch": 0.5514421007318123, "grad_norm": 1.651060700416565, "learning_rate": 2.0981482207135666e-05, "loss": 4.8583, "step": 10248 }, { "epoch": 0.5514959104606113, "grad_norm": 2.2177791595458984, "learning_rate": 2.0977311013118087e-05, "loss": 4.0864, "step": 10249 }, { "epoch": 0.5515497201894103, "grad_norm": 2.0371508598327637, "learning_rate": 2.097313993405814e-05, "loss": 4.0776, "step": 10250 }, { "epoch": 0.5516035299182093, "grad_norm": 1.8931142091751099, "learning_rate": 2.0968968970075014e-05, "loss": 4.0212, "step": 10251 }, { "epoch": 0.5516573396470081, "grad_norm": 2.632690191268921, "learning_rate": 2.096479812128792e-05, "loss": 4.0852, "step": 10252 }, { "epoch": 0.5517111493758071, "grad_norm": 1.2482059001922607, "learning_rate": 2.0960627387816045e-05, "loss": 4.543, "step": 10253 }, { "epoch": 0.5517649591046061, "grad_norm": 2.9890966415405273, "learning_rate": 2.095645676977857e-05, "loss": 4.4018, "step": 10254 }, { "epoch": 0.5518187688334051, "grad_norm": 3.255960464477539, "learning_rate": 2.095228626729468e-05, "loss": 3.9498, "step": 10255 }, { "epoch": 0.5518725785622041, "grad_norm": 1.5240334272384644, "learning_rate": 2.094811588048357e-05, "loss": 4.6183, "step": 10256 }, { "epoch": 0.551926388291003, "grad_norm": 2.033628225326538, "learning_rate": 2.0943945609464408e-05, "loss": 4.0406, "step": 10257 }, { "epoch": 0.551980198019802, "grad_norm": 2.556414842605591, "learning_rate": 2.0939775454356364e-05, "loss": 3.8409, "step": 10258 }, { "epoch": 0.5520340077486009, "grad_norm": 2.111257314682007, "learning_rate": 2.093560541527862e-05, "loss": 4.0326, "step": 10259 }, { "epoch": 0.5520878174773999, "grad_norm": 1.5807156562805176, "learning_rate": 2.0931435492350352e-05, "loss": 4.485, "step": 10260 }, { "epoch": 0.5521416272061989, "grad_norm": 1.846187949180603, "learning_rate": 2.0927265685690704e-05, "loss": 4.4844, "step": 10261 }, { "epoch": 0.5521954369349978, "grad_norm": 2.8189282417297363, "learning_rate": 2.0923095995418855e-05, "loss": 3.6091, "step": 10262 }, { "epoch": 0.5522492466637968, "grad_norm": 3.3012332916259766, "learning_rate": 2.0918926421653945e-05, "loss": 3.8625, "step": 10263 }, { "epoch": 0.5523030563925958, "grad_norm": 2.2773590087890625, "learning_rate": 2.091475696451515e-05, "loss": 4.3018, "step": 10264 }, { "epoch": 0.5523568661213948, "grad_norm": 2.074394464492798, "learning_rate": 2.091058762412161e-05, "loss": 3.8212, "step": 10265 }, { "epoch": 0.5524106758501938, "grad_norm": 1.1148779392242432, "learning_rate": 2.0906418400592475e-05, "loss": 4.4154, "step": 10266 }, { "epoch": 0.5524644855789926, "grad_norm": 1.5538551807403564, "learning_rate": 2.0902249294046893e-05, "loss": 3.8011, "step": 10267 }, { "epoch": 0.5525182953077916, "grad_norm": 2.833465576171875, "learning_rate": 2.0898080304604016e-05, "loss": 3.8332, "step": 10268 }, { "epoch": 0.5525721050365906, "grad_norm": 3.52946138381958, "learning_rate": 2.089391143238296e-05, "loss": 3.967, "step": 10269 }, { "epoch": 0.5526259147653896, "grad_norm": 1.8127468824386597, "learning_rate": 2.0889742677502873e-05, "loss": 4.3144, "step": 10270 }, { "epoch": 0.5526797244941886, "grad_norm": 2.936640501022339, "learning_rate": 2.0885574040082877e-05, "loss": 4.0073, "step": 10271 }, { "epoch": 0.5527335342229875, "grad_norm": 2.813901424407959, "learning_rate": 2.0881405520242117e-05, "loss": 4.0162, "step": 10272 }, { "epoch": 0.5527873439517865, "grad_norm": 2.9009761810302734, "learning_rate": 2.087723711809971e-05, "loss": 3.6487, "step": 10273 }, { "epoch": 0.5528411536805854, "grad_norm": 1.7067992687225342, "learning_rate": 2.087306883377477e-05, "loss": 4.0159, "step": 10274 }, { "epoch": 0.5528949634093844, "grad_norm": 3.352576494216919, "learning_rate": 2.086890066738643e-05, "loss": 3.3744, "step": 10275 }, { "epoch": 0.5529487731381834, "grad_norm": 3.948326587677002, "learning_rate": 2.08647326190538e-05, "loss": 4.2045, "step": 10276 }, { "epoch": 0.5530025828669823, "grad_norm": 2.9969921112060547, "learning_rate": 2.0860564688895985e-05, "loss": 3.7806, "step": 10277 }, { "epoch": 0.5530563925957813, "grad_norm": 1.380385160446167, "learning_rate": 2.085639687703209e-05, "loss": 4.6367, "step": 10278 }, { "epoch": 0.5531102023245803, "grad_norm": 1.1785787343978882, "learning_rate": 2.0852229183581238e-05, "loss": 4.5232, "step": 10279 }, { "epoch": 0.5531640120533793, "grad_norm": 1.5523252487182617, "learning_rate": 2.0848061608662515e-05, "loss": 4.4521, "step": 10280 }, { "epoch": 0.5532178217821783, "grad_norm": 2.0744423866271973, "learning_rate": 2.0843894152395023e-05, "loss": 3.3959, "step": 10281 }, { "epoch": 0.5532716315109771, "grad_norm": 2.341156244277954, "learning_rate": 2.083972681489786e-05, "loss": 4.3035, "step": 10282 }, { "epoch": 0.5533254412397761, "grad_norm": 1.9761360883712769, "learning_rate": 2.0835559596290116e-05, "loss": 3.6417, "step": 10283 }, { "epoch": 0.5533792509685751, "grad_norm": 1.990166425704956, "learning_rate": 2.0831392496690877e-05, "loss": 3.8567, "step": 10284 }, { "epoch": 0.5534330606973741, "grad_norm": 2.7004899978637695, "learning_rate": 2.082722551621923e-05, "loss": 4.401, "step": 10285 }, { "epoch": 0.5534868704261731, "grad_norm": 3.2443268299102783, "learning_rate": 2.0823058654994246e-05, "loss": 4.0655, "step": 10286 }, { "epoch": 0.553540680154972, "grad_norm": 2.632136821746826, "learning_rate": 2.0818891913135016e-05, "loss": 4.2038, "step": 10287 }, { "epoch": 0.553594489883771, "grad_norm": 1.253842830657959, "learning_rate": 2.081472529076061e-05, "loss": 4.5752, "step": 10288 }, { "epoch": 0.55364829961257, "grad_norm": 3.5681803226470947, "learning_rate": 2.0810558787990094e-05, "loss": 4.1639, "step": 10289 }, { "epoch": 0.5537021093413689, "grad_norm": 1.9811466932296753, "learning_rate": 2.080639240494254e-05, "loss": 4.3533, "step": 10290 }, { "epoch": 0.5537559190701679, "grad_norm": 1.8593086004257202, "learning_rate": 2.0802226141737025e-05, "loss": 4.1626, "step": 10291 }, { "epoch": 0.5538097287989668, "grad_norm": 1.7031720876693726, "learning_rate": 2.0798059998492587e-05, "loss": 4.1537, "step": 10292 }, { "epoch": 0.5538635385277658, "grad_norm": 2.532766103744507, "learning_rate": 2.079389397532829e-05, "loss": 3.9905, "step": 10293 }, { "epoch": 0.5539173482565648, "grad_norm": 1.1797945499420166, "learning_rate": 2.078972807236319e-05, "loss": 4.55, "step": 10294 }, { "epoch": 0.5539711579853638, "grad_norm": 1.875166416168213, "learning_rate": 2.0785562289716336e-05, "loss": 4.1388, "step": 10295 }, { "epoch": 0.5540249677141628, "grad_norm": 1.4877654314041138, "learning_rate": 2.0781396627506784e-05, "loss": 4.3935, "step": 10296 }, { "epoch": 0.5540787774429616, "grad_norm": 2.326592445373535, "learning_rate": 2.077723108585356e-05, "loss": 3.9287, "step": 10297 }, { "epoch": 0.5541325871717606, "grad_norm": 2.071564197540283, "learning_rate": 2.077306566487573e-05, "loss": 4.0113, "step": 10298 }, { "epoch": 0.5541863969005596, "grad_norm": 2.3216936588287354, "learning_rate": 2.0768900364692296e-05, "loss": 4.3455, "step": 10299 }, { "epoch": 0.5542402066293586, "grad_norm": 1.891937017440796, "learning_rate": 2.0764735185422316e-05, "loss": 4.3907, "step": 10300 }, { "epoch": 0.5542940163581576, "grad_norm": 2.3707921504974365, "learning_rate": 2.0760570127184813e-05, "loss": 4.1878, "step": 10301 }, { "epoch": 0.5543478260869565, "grad_norm": 2.81528639793396, "learning_rate": 2.075640519009881e-05, "loss": 4.0419, "step": 10302 }, { "epoch": 0.5544016358157555, "grad_norm": 2.384921073913574, "learning_rate": 2.0752240374283334e-05, "loss": 3.7433, "step": 10303 }, { "epoch": 0.5544554455445545, "grad_norm": 2.8318917751312256, "learning_rate": 2.0748075679857406e-05, "loss": 4.1373, "step": 10304 }, { "epoch": 0.5545092552733534, "grad_norm": 2.025588035583496, "learning_rate": 2.0743911106940034e-05, "loss": 4.4915, "step": 10305 }, { "epoch": 0.5545630650021524, "grad_norm": 1.9284439086914062, "learning_rate": 2.0739746655650244e-05, "loss": 4.1198, "step": 10306 }, { "epoch": 0.5546168747309513, "grad_norm": 2.499479055404663, "learning_rate": 2.073558232610703e-05, "loss": 3.6051, "step": 10307 }, { "epoch": 0.5546706844597503, "grad_norm": 1.6846424341201782, "learning_rate": 2.0731418118429404e-05, "loss": 3.5359, "step": 10308 }, { "epoch": 0.5547244941885493, "grad_norm": 1.215059518814087, "learning_rate": 2.072725403273636e-05, "loss": 4.5725, "step": 10309 }, { "epoch": 0.5547783039173483, "grad_norm": 1.1999632120132446, "learning_rate": 2.0723090069146912e-05, "loss": 4.4732, "step": 10310 }, { "epoch": 0.5548321136461473, "grad_norm": 2.241107940673828, "learning_rate": 2.0718926227780045e-05, "loss": 4.519, "step": 10311 }, { "epoch": 0.5548859233749462, "grad_norm": 2.721951961517334, "learning_rate": 2.0714762508754744e-05, "loss": 3.7217, "step": 10312 }, { "epoch": 0.5549397331037451, "grad_norm": 1.9581564664840698, "learning_rate": 2.0710598912190014e-05, "loss": 4.7676, "step": 10313 }, { "epoch": 0.5549935428325441, "grad_norm": 1.5916539430618286, "learning_rate": 2.0706435438204833e-05, "loss": 3.8053, "step": 10314 }, { "epoch": 0.5550473525613431, "grad_norm": 1.3311735391616821, "learning_rate": 2.0702272086918174e-05, "loss": 3.9141, "step": 10315 }, { "epoch": 0.5551011622901421, "grad_norm": 2.5186269283294678, "learning_rate": 2.069810885844902e-05, "loss": 4.0291, "step": 10316 }, { "epoch": 0.555154972018941, "grad_norm": 3.772444486618042, "learning_rate": 2.069394575291634e-05, "loss": 3.3613, "step": 10317 }, { "epoch": 0.55520878174774, "grad_norm": 2.8568191528320312, "learning_rate": 2.068978277043911e-05, "loss": 3.7126, "step": 10318 }, { "epoch": 0.555262591476539, "grad_norm": 1.6583088636398315, "learning_rate": 2.0685619911136295e-05, "loss": 3.8612, "step": 10319 }, { "epoch": 0.5553164012053379, "grad_norm": 2.1111831665039062, "learning_rate": 2.0681457175126854e-05, "loss": 3.5278, "step": 10320 }, { "epoch": 0.5553702109341369, "grad_norm": 2.393594741821289, "learning_rate": 2.067729456252977e-05, "loss": 4.1177, "step": 10321 }, { "epoch": 0.5554240206629358, "grad_norm": 1.645224928855896, "learning_rate": 2.0673132073463965e-05, "loss": 4.0129, "step": 10322 }, { "epoch": 0.5554778303917348, "grad_norm": 2.5315001010894775, "learning_rate": 2.0668969708048407e-05, "loss": 4.3149, "step": 10323 }, { "epoch": 0.5555316401205338, "grad_norm": 3.1167426109313965, "learning_rate": 2.066480746640205e-05, "loss": 4.2374, "step": 10324 }, { "epoch": 0.5555854498493328, "grad_norm": 1.0979623794555664, "learning_rate": 2.066064534864383e-05, "loss": 4.3401, "step": 10325 }, { "epoch": 0.5556392595781318, "grad_norm": 1.8864251375198364, "learning_rate": 2.06564833548927e-05, "loss": 4.5101, "step": 10326 }, { "epoch": 0.5556930693069307, "grad_norm": 2.4184210300445557, "learning_rate": 2.065232148526759e-05, "loss": 4.0475, "step": 10327 }, { "epoch": 0.5557468790357296, "grad_norm": 2.382563829421997, "learning_rate": 2.0648159739887438e-05, "loss": 3.7785, "step": 10328 }, { "epoch": 0.5558006887645286, "grad_norm": 2.178584575653076, "learning_rate": 2.064399811887119e-05, "loss": 3.9388, "step": 10329 }, { "epoch": 0.5558544984933276, "grad_norm": 2.367764949798584, "learning_rate": 2.063983662233774e-05, "loss": 3.8393, "step": 10330 }, { "epoch": 0.5559083082221266, "grad_norm": 2.79965877532959, "learning_rate": 2.063567525040604e-05, "loss": 4.5343, "step": 10331 }, { "epoch": 0.5559621179509255, "grad_norm": 2.1227121353149414, "learning_rate": 2.0631514003195e-05, "loss": 3.9279, "step": 10332 }, { "epoch": 0.5560159276797245, "grad_norm": 1.8645905256271362, "learning_rate": 2.0627352880823538e-05, "loss": 3.8995, "step": 10333 }, { "epoch": 0.5560697374085235, "grad_norm": 1.5282669067382812, "learning_rate": 2.0623191883410574e-05, "loss": 4.1812, "step": 10334 }, { "epoch": 0.5561235471373225, "grad_norm": 2.6663575172424316, "learning_rate": 2.0619031011075012e-05, "loss": 3.4216, "step": 10335 }, { "epoch": 0.5561773568661214, "grad_norm": 1.9406702518463135, "learning_rate": 2.061487026393576e-05, "loss": 3.9078, "step": 10336 }, { "epoch": 0.5562311665949203, "grad_norm": 3.2786755561828613, "learning_rate": 2.0610709642111727e-05, "loss": 3.2603, "step": 10337 }, { "epoch": 0.5562849763237193, "grad_norm": 3.651215076446533, "learning_rate": 2.0606549145721804e-05, "loss": 4.4796, "step": 10338 }, { "epoch": 0.5563387860525183, "grad_norm": 2.4911763668060303, "learning_rate": 2.0602388774884888e-05, "loss": 4.1577, "step": 10339 }, { "epoch": 0.5563925957813173, "grad_norm": 1.0977696180343628, "learning_rate": 2.0598228529719865e-05, "loss": 4.3857, "step": 10340 }, { "epoch": 0.5564464055101163, "grad_norm": 2.143994092941284, "learning_rate": 2.059406841034564e-05, "loss": 4.1354, "step": 10341 }, { "epoch": 0.5565002152389152, "grad_norm": 2.1319775581359863, "learning_rate": 2.0589908416881088e-05, "loss": 4.0017, "step": 10342 }, { "epoch": 0.5565540249677141, "grad_norm": 2.6851892471313477, "learning_rate": 2.0585748549445085e-05, "loss": 3.8564, "step": 10343 }, { "epoch": 0.5566078346965131, "grad_norm": 2.4005258083343506, "learning_rate": 2.0581588808156534e-05, "loss": 3.8725, "step": 10344 }, { "epoch": 0.5566616444253121, "grad_norm": 2.153662919998169, "learning_rate": 2.0577429193134273e-05, "loss": 4.6392, "step": 10345 }, { "epoch": 0.5567154541541111, "grad_norm": 2.1027791500091553, "learning_rate": 2.0573269704497198e-05, "loss": 3.6311, "step": 10346 }, { "epoch": 0.55676926388291, "grad_norm": 3.3531854152679443, "learning_rate": 2.0569110342364168e-05, "loss": 3.2936, "step": 10347 }, { "epoch": 0.556823073611709, "grad_norm": 2.657046318054199, "learning_rate": 2.056495110685404e-05, "loss": 4.2626, "step": 10348 }, { "epoch": 0.556876883340508, "grad_norm": 2.971137046813965, "learning_rate": 2.0560791998085685e-05, "loss": 3.98, "step": 10349 }, { "epoch": 0.556930693069307, "grad_norm": 2.831070899963379, "learning_rate": 2.0556633016177956e-05, "loss": 3.5899, "step": 10350 }, { "epoch": 0.5569845027981059, "grad_norm": 1.6392853260040283, "learning_rate": 2.0552474161249695e-05, "loss": 4.5773, "step": 10351 }, { "epoch": 0.5570383125269048, "grad_norm": 1.10291588306427, "learning_rate": 2.0548315433419782e-05, "loss": 4.2275, "step": 10352 }, { "epoch": 0.5570921222557038, "grad_norm": 1.720934510231018, "learning_rate": 2.054415683280702e-05, "loss": 3.8009, "step": 10353 }, { "epoch": 0.5571459319845028, "grad_norm": 2.3541672229766846, "learning_rate": 2.053999835953028e-05, "loss": 4.0612, "step": 10354 }, { "epoch": 0.5571997417133018, "grad_norm": 1.5906544923782349, "learning_rate": 2.0535840013708388e-05, "loss": 4.1348, "step": 10355 }, { "epoch": 0.5572535514421008, "grad_norm": 2.259059429168701, "learning_rate": 2.0531681795460177e-05, "loss": 4.1147, "step": 10356 }, { "epoch": 0.5573073611708997, "grad_norm": 3.6687231063842773, "learning_rate": 2.0527523704904487e-05, "loss": 2.9552, "step": 10357 }, { "epoch": 0.5573611708996986, "grad_norm": 2.6719560623168945, "learning_rate": 2.052336574216014e-05, "loss": 3.8476, "step": 10358 }, { "epoch": 0.5574149806284976, "grad_norm": 1.9973267316818237, "learning_rate": 2.0519207907345966e-05, "loss": 4.5183, "step": 10359 }, { "epoch": 0.5574687903572966, "grad_norm": 3.9156038761138916, "learning_rate": 2.0515050200580772e-05, "loss": 4.1631, "step": 10360 }, { "epoch": 0.5575226000860956, "grad_norm": 1.7659071683883667, "learning_rate": 2.0510892621983373e-05, "loss": 4.3064, "step": 10361 }, { "epoch": 0.5575764098148945, "grad_norm": 3.154529571533203, "learning_rate": 2.0506735171672596e-05, "loss": 4.6174, "step": 10362 }, { "epoch": 0.5576302195436935, "grad_norm": 2.771432399749756, "learning_rate": 2.050257784976724e-05, "loss": 4.0218, "step": 10363 }, { "epoch": 0.5576840292724925, "grad_norm": 3.020014524459839, "learning_rate": 2.0498420656386107e-05, "loss": 3.6393, "step": 10364 }, { "epoch": 0.5577378390012915, "grad_norm": 1.888234257698059, "learning_rate": 2.049426359164801e-05, "loss": 4.5125, "step": 10365 }, { "epoch": 0.5577916487300904, "grad_norm": 2.7452359199523926, "learning_rate": 2.0490106655671744e-05, "loss": 3.6899, "step": 10366 }, { "epoch": 0.5578454584588893, "grad_norm": 2.2595019340515137, "learning_rate": 2.0485949848576103e-05, "loss": 4.3504, "step": 10367 }, { "epoch": 0.5578992681876883, "grad_norm": 1.4813857078552246, "learning_rate": 2.0481793170479863e-05, "loss": 4.3043, "step": 10368 }, { "epoch": 0.5579530779164873, "grad_norm": 1.4948362112045288, "learning_rate": 2.0477636621501826e-05, "loss": 4.4727, "step": 10369 }, { "epoch": 0.5580068876452863, "grad_norm": 1.4801329374313354, "learning_rate": 2.047348020176077e-05, "loss": 4.3752, "step": 10370 }, { "epoch": 0.5580606973740853, "grad_norm": 1.2161647081375122, "learning_rate": 2.046932391137547e-05, "loss": 4.5858, "step": 10371 }, { "epoch": 0.5581145071028842, "grad_norm": 1.1515370607376099, "learning_rate": 2.0465167750464715e-05, "loss": 4.6634, "step": 10372 }, { "epoch": 0.5581683168316832, "grad_norm": 2.2195558547973633, "learning_rate": 2.0461011719147262e-05, "loss": 3.928, "step": 10373 }, { "epoch": 0.5582221265604821, "grad_norm": 2.2879419326782227, "learning_rate": 2.0456855817541887e-05, "loss": 4.1382, "step": 10374 }, { "epoch": 0.5582759362892811, "grad_norm": 2.2988834381103516, "learning_rate": 2.0452700045767363e-05, "loss": 3.5536, "step": 10375 }, { "epoch": 0.55832974601808, "grad_norm": 1.7709295749664307, "learning_rate": 2.0448544403942433e-05, "loss": 4.3962, "step": 10376 }, { "epoch": 0.558383555746879, "grad_norm": 3.1860835552215576, "learning_rate": 2.0444388892185862e-05, "loss": 3.3722, "step": 10377 }, { "epoch": 0.558437365475678, "grad_norm": 1.9885480403900146, "learning_rate": 2.0440233510616402e-05, "loss": 4.0744, "step": 10378 }, { "epoch": 0.558491175204477, "grad_norm": 1.760817527770996, "learning_rate": 2.04360782593528e-05, "loss": 4.0114, "step": 10379 }, { "epoch": 0.558544984933276, "grad_norm": 2.149857521057129, "learning_rate": 2.043192313851381e-05, "loss": 4.1294, "step": 10380 }, { "epoch": 0.5585987946620748, "grad_norm": 2.7102210521698, "learning_rate": 2.0427768148218172e-05, "loss": 3.7884, "step": 10381 }, { "epoch": 0.5586526043908738, "grad_norm": 1.386157751083374, "learning_rate": 2.042361328858463e-05, "loss": 4.3206, "step": 10382 }, { "epoch": 0.5587064141196728, "grad_norm": 1.8406624794006348, "learning_rate": 2.0419458559731903e-05, "loss": 4.2674, "step": 10383 }, { "epoch": 0.5587602238484718, "grad_norm": 3.8779702186584473, "learning_rate": 2.0415303961778724e-05, "loss": 4.4882, "step": 10384 }, { "epoch": 0.5588140335772708, "grad_norm": 2.5002098083496094, "learning_rate": 2.0411149494843833e-05, "loss": 3.9828, "step": 10385 }, { "epoch": 0.5588678433060698, "grad_norm": 1.378686785697937, "learning_rate": 2.0406995159045946e-05, "loss": 4.4007, "step": 10386 }, { "epoch": 0.5589216530348687, "grad_norm": 2.47172474861145, "learning_rate": 2.040284095450378e-05, "loss": 3.9883, "step": 10387 }, { "epoch": 0.5589754627636677, "grad_norm": 1.7092148065567017, "learning_rate": 2.039868688133606e-05, "loss": 4.11, "step": 10388 }, { "epoch": 0.5590292724924666, "grad_norm": 1.7048710584640503, "learning_rate": 2.0394532939661492e-05, "loss": 3.8175, "step": 10389 }, { "epoch": 0.5590830822212656, "grad_norm": 1.174243688583374, "learning_rate": 2.0390379129598792e-05, "loss": 4.5825, "step": 10390 }, { "epoch": 0.5591368919500646, "grad_norm": 3.1460506916046143, "learning_rate": 2.038622545126665e-05, "loss": 3.9837, "step": 10391 }, { "epoch": 0.5591907016788635, "grad_norm": 3.069141387939453, "learning_rate": 2.038207190478377e-05, "loss": 3.7861, "step": 10392 }, { "epoch": 0.5592445114076625, "grad_norm": 2.527128219604492, "learning_rate": 2.037791849026886e-05, "loss": 4.3192, "step": 10393 }, { "epoch": 0.5592983211364615, "grad_norm": 2.537149667739868, "learning_rate": 2.037376520784061e-05, "loss": 4.2598, "step": 10394 }, { "epoch": 0.5593521308652605, "grad_norm": 3.5069334506988525, "learning_rate": 2.0369612057617697e-05, "loss": 4.2727, "step": 10395 }, { "epoch": 0.5594059405940595, "grad_norm": 1.7128496170043945, "learning_rate": 2.0365459039718826e-05, "loss": 4.7106, "step": 10396 }, { "epoch": 0.5594597503228583, "grad_norm": 1.982854962348938, "learning_rate": 2.0361306154262668e-05, "loss": 3.8748, "step": 10397 }, { "epoch": 0.5595135600516573, "grad_norm": 2.5109543800354004, "learning_rate": 2.035715340136791e-05, "loss": 4.3482, "step": 10398 }, { "epoch": 0.5595673697804563, "grad_norm": 3.1988542079925537, "learning_rate": 2.035300078115321e-05, "loss": 3.8404, "step": 10399 }, { "epoch": 0.5596211795092553, "grad_norm": 2.6246416568756104, "learning_rate": 2.0348848293737255e-05, "loss": 4.3872, "step": 10400 }, { "epoch": 0.5596749892380543, "grad_norm": 1.4530972242355347, "learning_rate": 2.0344695939238706e-05, "loss": 4.6394, "step": 10401 }, { "epoch": 0.5597287989668532, "grad_norm": 2.116849184036255, "learning_rate": 2.0340543717776218e-05, "loss": 4.1917, "step": 10402 }, { "epoch": 0.5597826086956522, "grad_norm": 2.1150717735290527, "learning_rate": 2.0336391629468465e-05, "loss": 3.9931, "step": 10403 }, { "epoch": 0.5598364184244511, "grad_norm": 3.6382856369018555, "learning_rate": 2.0332239674434096e-05, "loss": 3.304, "step": 10404 }, { "epoch": 0.5598902281532501, "grad_norm": 3.65615177154541, "learning_rate": 2.0328087852791762e-05, "loss": 3.4146, "step": 10405 }, { "epoch": 0.559944037882049, "grad_norm": 2.398442029953003, "learning_rate": 2.0323936164660114e-05, "loss": 3.0918, "step": 10406 }, { "epoch": 0.559997847610848, "grad_norm": 2.8339474201202393, "learning_rate": 2.0319784610157782e-05, "loss": 3.3149, "step": 10407 }, { "epoch": 0.560051657339647, "grad_norm": 2.3781120777130127, "learning_rate": 2.0315633189403427e-05, "loss": 3.8861, "step": 10408 }, { "epoch": 0.560105467068446, "grad_norm": 1.3357309103012085, "learning_rate": 2.0311481902515674e-05, "loss": 4.1167, "step": 10409 }, { "epoch": 0.560159276797245, "grad_norm": 3.5319645404815674, "learning_rate": 2.030733074961315e-05, "loss": 4.2599, "step": 10410 }, { "epoch": 0.560213086526044, "grad_norm": 1.6280039548873901, "learning_rate": 2.03031797308145e-05, "loss": 4.0377, "step": 10411 }, { "epoch": 0.5602668962548428, "grad_norm": 1.8313535451889038, "learning_rate": 2.0299028846238342e-05, "loss": 3.9842, "step": 10412 }, { "epoch": 0.5603207059836418, "grad_norm": 2.4223010540008545, "learning_rate": 2.0294878096003295e-05, "loss": 4.3333, "step": 10413 }, { "epoch": 0.5603745157124408, "grad_norm": 5.066783428192139, "learning_rate": 2.0290727480227975e-05, "loss": 4.3121, "step": 10414 }, { "epoch": 0.5604283254412398, "grad_norm": 3.8832638263702393, "learning_rate": 2.028657699903099e-05, "loss": 3.1608, "step": 10415 }, { "epoch": 0.5604821351700388, "grad_norm": 1.9931726455688477, "learning_rate": 2.0282426652530966e-05, "loss": 4.2643, "step": 10416 }, { "epoch": 0.5605359448988377, "grad_norm": 2.5320823192596436, "learning_rate": 2.0278276440846496e-05, "loss": 3.9782, "step": 10417 }, { "epoch": 0.5605897546276367, "grad_norm": 2.5772016048431396, "learning_rate": 2.027412636409618e-05, "loss": 3.2521, "step": 10418 }, { "epoch": 0.5606435643564357, "grad_norm": 2.176128625869751, "learning_rate": 2.026997642239863e-05, "loss": 3.3086, "step": 10419 }, { "epoch": 0.5606973740852346, "grad_norm": 2.645023822784424, "learning_rate": 2.026582661587243e-05, "loss": 3.6263, "step": 10420 }, { "epoch": 0.5607511838140335, "grad_norm": 2.001004457473755, "learning_rate": 2.0261676944636175e-05, "loss": 4.0613, "step": 10421 }, { "epoch": 0.5608049935428325, "grad_norm": 2.180455207824707, "learning_rate": 2.0257527408808445e-05, "loss": 4.0074, "step": 10422 }, { "epoch": 0.5608588032716315, "grad_norm": 1.9691723585128784, "learning_rate": 2.025337800850782e-05, "loss": 3.5219, "step": 10423 }, { "epoch": 0.5609126130004305, "grad_norm": 1.669992208480835, "learning_rate": 2.024922874385289e-05, "loss": 4.2571, "step": 10424 }, { "epoch": 0.5609664227292295, "grad_norm": 3.02949857711792, "learning_rate": 2.0245079614962226e-05, "loss": 3.8074, "step": 10425 }, { "epoch": 0.5610202324580285, "grad_norm": 2.2215306758880615, "learning_rate": 2.024093062195439e-05, "loss": 4.4563, "step": 10426 }, { "epoch": 0.5610740421868273, "grad_norm": 3.050699472427368, "learning_rate": 2.0236781764947964e-05, "loss": 4.0297, "step": 10427 }, { "epoch": 0.5611278519156263, "grad_norm": 2.008338451385498, "learning_rate": 2.0232633044061506e-05, "loss": 4.3984, "step": 10428 }, { "epoch": 0.5611816616444253, "grad_norm": 1.165930986404419, "learning_rate": 2.0228484459413568e-05, "loss": 4.5895, "step": 10429 }, { "epoch": 0.5612354713732243, "grad_norm": 2.3508245944976807, "learning_rate": 2.0224336011122705e-05, "loss": 4.1143, "step": 10430 }, { "epoch": 0.5612892811020233, "grad_norm": 1.7589117288589478, "learning_rate": 2.0220187699307482e-05, "loss": 3.9823, "step": 10431 }, { "epoch": 0.5613430908308222, "grad_norm": 2.360388994216919, "learning_rate": 2.0216039524086435e-05, "loss": 3.5843, "step": 10432 }, { "epoch": 0.5613969005596212, "grad_norm": 3.2700724601745605, "learning_rate": 2.0211891485578104e-05, "loss": 4.0211, "step": 10433 }, { "epoch": 0.5614507102884202, "grad_norm": 3.6545984745025635, "learning_rate": 2.0207743583901045e-05, "loss": 3.419, "step": 10434 }, { "epoch": 0.5615045200172191, "grad_norm": 1.7439613342285156, "learning_rate": 2.0203595819173787e-05, "loss": 3.915, "step": 10435 }, { "epoch": 0.561558329746018, "grad_norm": 1.7952772378921509, "learning_rate": 2.019944819151486e-05, "loss": 4.2697, "step": 10436 }, { "epoch": 0.561612139474817, "grad_norm": 2.42499041557312, "learning_rate": 2.0195300701042786e-05, "loss": 4.2134, "step": 10437 }, { "epoch": 0.561665949203616, "grad_norm": 2.574402332305908, "learning_rate": 2.0191153347876095e-05, "loss": 3.9163, "step": 10438 }, { "epoch": 0.561719758932415, "grad_norm": 3.181046962738037, "learning_rate": 2.0187006132133306e-05, "loss": 4.7218, "step": 10439 }, { "epoch": 0.561773568661214, "grad_norm": 3.36511492729187, "learning_rate": 2.0182859053932943e-05, "loss": 3.7853, "step": 10440 }, { "epoch": 0.561827378390013, "grad_norm": 3.0288586616516113, "learning_rate": 2.0178712113393503e-05, "loss": 3.7769, "step": 10441 }, { "epoch": 0.5618811881188119, "grad_norm": 1.0407156944274902, "learning_rate": 2.0174565310633507e-05, "loss": 4.631, "step": 10442 }, { "epoch": 0.5619349978476108, "grad_norm": 1.815781831741333, "learning_rate": 2.0170418645771456e-05, "loss": 4.5407, "step": 10443 }, { "epoch": 0.5619888075764098, "grad_norm": 2.112072706222534, "learning_rate": 2.0166272118925856e-05, "loss": 4.2752, "step": 10444 }, { "epoch": 0.5620426173052088, "grad_norm": 1.4034086465835571, "learning_rate": 2.016212573021519e-05, "loss": 4.1665, "step": 10445 }, { "epoch": 0.5620964270340078, "grad_norm": 1.4944792985916138, "learning_rate": 2.015797947975796e-05, "loss": 4.447, "step": 10446 }, { "epoch": 0.5621502367628067, "grad_norm": 2.439127206802368, "learning_rate": 2.0153833367672652e-05, "loss": 4.5433, "step": 10447 }, { "epoch": 0.5622040464916057, "grad_norm": 1.6883517503738403, "learning_rate": 2.0149687394077754e-05, "loss": 4.4393, "step": 10448 }, { "epoch": 0.5622578562204047, "grad_norm": 1.354408621788025, "learning_rate": 2.0145541559091738e-05, "loss": 4.6723, "step": 10449 }, { "epoch": 0.5623116659492036, "grad_norm": 3.274852752685547, "learning_rate": 2.0141395862833093e-05, "loss": 3.953, "step": 10450 }, { "epoch": 0.5623654756780025, "grad_norm": 3.3386807441711426, "learning_rate": 2.0137250305420292e-05, "loss": 3.3208, "step": 10451 }, { "epoch": 0.5624192854068015, "grad_norm": 1.2876170873641968, "learning_rate": 2.0133104886971794e-05, "loss": 4.4796, "step": 10452 }, { "epoch": 0.5624730951356005, "grad_norm": 2.058790683746338, "learning_rate": 2.012895960760606e-05, "loss": 4.9606, "step": 10453 }, { "epoch": 0.5625269048643995, "grad_norm": 1.2622443437576294, "learning_rate": 2.0124814467441562e-05, "loss": 4.3764, "step": 10454 }, { "epoch": 0.5625807145931985, "grad_norm": 2.64774751663208, "learning_rate": 2.012066946659676e-05, "loss": 3.9223, "step": 10455 }, { "epoch": 0.5626345243219975, "grad_norm": 2.1947736740112305, "learning_rate": 2.0116524605190094e-05, "loss": 3.9364, "step": 10456 }, { "epoch": 0.5626883340507964, "grad_norm": 1.3538178205490112, "learning_rate": 2.0112379883340022e-05, "loss": 4.5014, "step": 10457 }, { "epoch": 0.5627421437795953, "grad_norm": 1.74586820602417, "learning_rate": 2.0108235301164984e-05, "loss": 4.5514, "step": 10458 }, { "epoch": 0.5627959535083943, "grad_norm": 2.138352155685425, "learning_rate": 2.0104090858783438e-05, "loss": 4.0964, "step": 10459 }, { "epoch": 0.5628497632371933, "grad_norm": 2.9891960620880127, "learning_rate": 2.0099946556313794e-05, "loss": 3.739, "step": 10460 }, { "epoch": 0.5629035729659922, "grad_norm": 1.8364897966384888, "learning_rate": 2.0095802393874495e-05, "loss": 4.1597, "step": 10461 }, { "epoch": 0.5629573826947912, "grad_norm": 2.775522470474243, "learning_rate": 2.0091658371583977e-05, "loss": 3.8364, "step": 10462 }, { "epoch": 0.5630111924235902, "grad_norm": 3.0939106941223145, "learning_rate": 2.0087514489560665e-05, "loss": 4.4352, "step": 10463 }, { "epoch": 0.5630650021523892, "grad_norm": 3.6850457191467285, "learning_rate": 2.0083370747922967e-05, "loss": 3.8523, "step": 10464 }, { "epoch": 0.5631188118811881, "grad_norm": 2.2269186973571777, "learning_rate": 2.0079227146789315e-05, "loss": 4.036, "step": 10465 }, { "epoch": 0.563172621609987, "grad_norm": 2.01037335395813, "learning_rate": 2.0075083686278122e-05, "loss": 4.3881, "step": 10466 }, { "epoch": 0.563226431338786, "grad_norm": 1.9203253984451294, "learning_rate": 2.0070940366507786e-05, "loss": 4.076, "step": 10467 }, { "epoch": 0.563280241067585, "grad_norm": 1.7584033012390137, "learning_rate": 2.006679718759671e-05, "loss": 4.3404, "step": 10468 }, { "epoch": 0.563334050796384, "grad_norm": 3.408581256866455, "learning_rate": 2.0062654149663303e-05, "loss": 3.8682, "step": 10469 }, { "epoch": 0.563387860525183, "grad_norm": 2.022799491882324, "learning_rate": 2.0058511252825966e-05, "loss": 4.0407, "step": 10470 }, { "epoch": 0.563441670253982, "grad_norm": 1.6604862213134766, "learning_rate": 2.0054368497203086e-05, "loss": 3.8628, "step": 10471 }, { "epoch": 0.5634954799827809, "grad_norm": 1.9180450439453125, "learning_rate": 2.0050225882913044e-05, "loss": 4.4516, "step": 10472 }, { "epoch": 0.5635492897115798, "grad_norm": 2.3011186122894287, "learning_rate": 2.004608341007424e-05, "loss": 3.6462, "step": 10473 }, { "epoch": 0.5636030994403788, "grad_norm": 3.164417028427124, "learning_rate": 2.0041941078805053e-05, "loss": 3.9573, "step": 10474 }, { "epoch": 0.5636569091691778, "grad_norm": 2.6206603050231934, "learning_rate": 2.0037798889223846e-05, "loss": 3.3581, "step": 10475 }, { "epoch": 0.5637107188979767, "grad_norm": 2.653606414794922, "learning_rate": 2.0033656841449005e-05, "loss": 4.3995, "step": 10476 }, { "epoch": 0.5637645286267757, "grad_norm": 2.164703130722046, "learning_rate": 2.0029514935598885e-05, "loss": 3.4596, "step": 10477 }, { "epoch": 0.5638183383555747, "grad_norm": 1.5088101625442505, "learning_rate": 2.0025373171791867e-05, "loss": 4.1906, "step": 10478 }, { "epoch": 0.5638721480843737, "grad_norm": 2.999694585800171, "learning_rate": 2.0021231550146302e-05, "loss": 3.5367, "step": 10479 }, { "epoch": 0.5639259578131727, "grad_norm": 2.109323024749756, "learning_rate": 2.001709007078054e-05, "loss": 4.0245, "step": 10480 }, { "epoch": 0.5639797675419715, "grad_norm": 3.003894567489624, "learning_rate": 2.0012948733812954e-05, "loss": 3.9994, "step": 10481 }, { "epoch": 0.5640335772707705, "grad_norm": 3.9200854301452637, "learning_rate": 2.000880753936188e-05, "loss": 4.3018, "step": 10482 }, { "epoch": 0.5640873869995695, "grad_norm": 2.2357301712036133, "learning_rate": 2.0004666487545655e-05, "loss": 3.6653, "step": 10483 }, { "epoch": 0.5641411967283685, "grad_norm": 1.76786208152771, "learning_rate": 2.000052557848262e-05, "loss": 4.0494, "step": 10484 }, { "epoch": 0.5641950064571675, "grad_norm": 1.601942539215088, "learning_rate": 1.999638481229113e-05, "loss": 4.4759, "step": 10485 }, { "epoch": 0.5642488161859665, "grad_norm": 1.4902026653289795, "learning_rate": 1.9992244189089496e-05, "loss": 4.5745, "step": 10486 }, { "epoch": 0.5643026259147654, "grad_norm": 2.1659207344055176, "learning_rate": 1.998810370899605e-05, "loss": 4.2831, "step": 10487 }, { "epoch": 0.5643564356435643, "grad_norm": 2.5267069339752197, "learning_rate": 1.998396337212913e-05, "loss": 3.8918, "step": 10488 }, { "epoch": 0.5644102453723633, "grad_norm": 2.3454837799072266, "learning_rate": 1.9979823178607042e-05, "loss": 4.1941, "step": 10489 }, { "epoch": 0.5644640551011623, "grad_norm": 2.594428300857544, "learning_rate": 1.9975683128548105e-05, "loss": 4.0263, "step": 10490 }, { "epoch": 0.5645178648299612, "grad_norm": 3.772923469543457, "learning_rate": 1.997154322207063e-05, "loss": 3.5978, "step": 10491 }, { "epoch": 0.5645716745587602, "grad_norm": 2.3084352016448975, "learning_rate": 1.996740345929292e-05, "loss": 3.7726, "step": 10492 }, { "epoch": 0.5646254842875592, "grad_norm": 3.1147549152374268, "learning_rate": 1.9963263840333284e-05, "loss": 3.847, "step": 10493 }, { "epoch": 0.5646792940163582, "grad_norm": 1.642268180847168, "learning_rate": 1.9959124365310025e-05, "loss": 4.1969, "step": 10494 }, { "epoch": 0.5647331037451572, "grad_norm": 1.6673057079315186, "learning_rate": 1.9954985034341426e-05, "loss": 4.1476, "step": 10495 }, { "epoch": 0.564786913473956, "grad_norm": 2.830233097076416, "learning_rate": 1.995084584754579e-05, "loss": 4.024, "step": 10496 }, { "epoch": 0.564840723202755, "grad_norm": 2.3131442070007324, "learning_rate": 1.9946706805041407e-05, "loss": 4.2137, "step": 10497 }, { "epoch": 0.564894532931554, "grad_norm": 1.609487533569336, "learning_rate": 1.9942567906946543e-05, "loss": 4.3446, "step": 10498 }, { "epoch": 0.564948342660353, "grad_norm": 2.2180285453796387, "learning_rate": 1.993842915337949e-05, "loss": 4.0005, "step": 10499 }, { "epoch": 0.565002152389152, "grad_norm": 2.8516769409179688, "learning_rate": 1.993429054445851e-05, "loss": 4.2202, "step": 10500 }, { "epoch": 0.565055962117951, "grad_norm": 2.175241231918335, "learning_rate": 1.9930152080301884e-05, "loss": 3.487, "step": 10501 }, { "epoch": 0.5651097718467499, "grad_norm": 2.996901512145996, "learning_rate": 1.992601376102788e-05, "loss": 4.5681, "step": 10502 }, { "epoch": 0.5651635815755489, "grad_norm": 2.390672206878662, "learning_rate": 1.9921875586754747e-05, "loss": 4.1678, "step": 10503 }, { "epoch": 0.5652173913043478, "grad_norm": 2.1460788249969482, "learning_rate": 1.9917737557600754e-05, "loss": 4.1851, "step": 10504 }, { "epoch": 0.5652712010331468, "grad_norm": 1.8656816482543945, "learning_rate": 1.991359967368416e-05, "loss": 4.2891, "step": 10505 }, { "epoch": 0.5653250107619457, "grad_norm": 3.0664267539978027, "learning_rate": 1.99094619351232e-05, "loss": 4.0755, "step": 10506 }, { "epoch": 0.5653788204907447, "grad_norm": 2.1151256561279297, "learning_rate": 1.990532434203613e-05, "loss": 4.0911, "step": 10507 }, { "epoch": 0.5654326302195437, "grad_norm": 1.217012882232666, "learning_rate": 1.9901186894541176e-05, "loss": 4.5622, "step": 10508 }, { "epoch": 0.5654864399483427, "grad_norm": 1.5002821683883667, "learning_rate": 1.9897049592756594e-05, "loss": 4.3262, "step": 10509 }, { "epoch": 0.5655402496771417, "grad_norm": 3.3100671768188477, "learning_rate": 1.9892912436800613e-05, "loss": 2.8878, "step": 10510 }, { "epoch": 0.5655940594059405, "grad_norm": 1.2931267023086548, "learning_rate": 1.988877542679145e-05, "loss": 4.5633, "step": 10511 }, { "epoch": 0.5656478691347395, "grad_norm": 2.1310765743255615, "learning_rate": 1.9884638562847346e-05, "loss": 3.9959, "step": 10512 }, { "epoch": 0.5657016788635385, "grad_norm": 1.8782861232757568, "learning_rate": 1.988050184508651e-05, "loss": 4.4829, "step": 10513 }, { "epoch": 0.5657554885923375, "grad_norm": 1.7689287662506104, "learning_rate": 1.9876365273627162e-05, "loss": 4.2028, "step": 10514 }, { "epoch": 0.5658092983211365, "grad_norm": 2.3251264095306396, "learning_rate": 1.9872228848587506e-05, "loss": 4.019, "step": 10515 }, { "epoch": 0.5658631080499354, "grad_norm": 1.4155986309051514, "learning_rate": 1.9868092570085766e-05, "loss": 4.4434, "step": 10516 }, { "epoch": 0.5659169177787344, "grad_norm": 2.2841956615448, "learning_rate": 1.9863956438240137e-05, "loss": 4.4836, "step": 10517 }, { "epoch": 0.5659707275075334, "grad_norm": 1.4682942628860474, "learning_rate": 1.985982045316881e-05, "loss": 4.2617, "step": 10518 }, { "epoch": 0.5660245372363323, "grad_norm": 2.0245842933654785, "learning_rate": 1.9855684614989996e-05, "loss": 3.8635, "step": 10519 }, { "epoch": 0.5660783469651313, "grad_norm": 2.5559253692626953, "learning_rate": 1.9851548923821884e-05, "loss": 4.3406, "step": 10520 }, { "epoch": 0.5661321566939302, "grad_norm": 2.687357187271118, "learning_rate": 1.9847413379782653e-05, "loss": 4.4488, "step": 10521 }, { "epoch": 0.5661859664227292, "grad_norm": 2.4146409034729004, "learning_rate": 1.9843277982990487e-05, "loss": 4.4004, "step": 10522 }, { "epoch": 0.5662397761515282, "grad_norm": 1.957093358039856, "learning_rate": 1.983914273356356e-05, "loss": 3.7261, "step": 10523 }, { "epoch": 0.5662935858803272, "grad_norm": 1.6695765256881714, "learning_rate": 1.983500763162006e-05, "loss": 4.1302, "step": 10524 }, { "epoch": 0.5663473956091262, "grad_norm": 2.450423240661621, "learning_rate": 1.9830872677278146e-05, "loss": 4.1983, "step": 10525 }, { "epoch": 0.5664012053379252, "grad_norm": 2.5638034343719482, "learning_rate": 1.9826737870655987e-05, "loss": 3.762, "step": 10526 }, { "epoch": 0.566455015066724, "grad_norm": 2.1427054405212402, "learning_rate": 1.982260321187175e-05, "loss": 3.7582, "step": 10527 }, { "epoch": 0.566508824795523, "grad_norm": 2.7831966876983643, "learning_rate": 1.9818468701043592e-05, "loss": 3.8097, "step": 10528 }, { "epoch": 0.566562634524322, "grad_norm": 2.8548214435577393, "learning_rate": 1.9814334338289652e-05, "loss": 3.5681, "step": 10529 }, { "epoch": 0.566616444253121, "grad_norm": 2.439363956451416, "learning_rate": 1.9810200123728097e-05, "loss": 4.2641, "step": 10530 }, { "epoch": 0.56667025398192, "grad_norm": 1.1944348812103271, "learning_rate": 1.980606605747705e-05, "loss": 4.5058, "step": 10531 }, { "epoch": 0.5667240637107189, "grad_norm": 2.1238248348236084, "learning_rate": 1.9801932139654674e-05, "loss": 4.1754, "step": 10532 }, { "epoch": 0.5667778734395179, "grad_norm": 1.2997080087661743, "learning_rate": 1.9797798370379098e-05, "loss": 4.3285, "step": 10533 }, { "epoch": 0.5668316831683168, "grad_norm": 1.6736106872558594, "learning_rate": 1.9793664749768447e-05, "loss": 4.2508, "step": 10534 }, { "epoch": 0.5668854928971158, "grad_norm": 2.0017690658569336, "learning_rate": 1.9789531277940867e-05, "loss": 4.4052, "step": 10535 }, { "epoch": 0.5669393026259147, "grad_norm": 1.6883549690246582, "learning_rate": 1.9785397955014453e-05, "loss": 3.8134, "step": 10536 }, { "epoch": 0.5669931123547137, "grad_norm": 2.166456699371338, "learning_rate": 1.9781264781107348e-05, "loss": 4.2914, "step": 10537 }, { "epoch": 0.5670469220835127, "grad_norm": 2.051093578338623, "learning_rate": 1.977713175633766e-05, "loss": 3.9779, "step": 10538 }, { "epoch": 0.5671007318123117, "grad_norm": 1.960189700126648, "learning_rate": 1.9772998880823487e-05, "loss": 3.8146, "step": 10539 }, { "epoch": 0.5671545415411107, "grad_norm": 3.53609561920166, "learning_rate": 1.9768866154682955e-05, "loss": 3.7891, "step": 10540 }, { "epoch": 0.5672083512699096, "grad_norm": 1.348547101020813, "learning_rate": 1.9764733578034163e-05, "loss": 4.7418, "step": 10541 }, { "epoch": 0.5672621609987085, "grad_norm": 2.1103267669677734, "learning_rate": 1.976060115099519e-05, "loss": 4.078, "step": 10542 }, { "epoch": 0.5673159707275075, "grad_norm": 3.0290780067443848, "learning_rate": 1.975646887368416e-05, "loss": 3.3934, "step": 10543 }, { "epoch": 0.5673697804563065, "grad_norm": 4.1630859375, "learning_rate": 1.9752336746219143e-05, "loss": 4.5408, "step": 10544 }, { "epoch": 0.5674235901851055, "grad_norm": 1.682554006576538, "learning_rate": 1.9748204768718222e-05, "loss": 4.575, "step": 10545 }, { "epoch": 0.5674773999139044, "grad_norm": 2.1804399490356445, "learning_rate": 1.974407294129948e-05, "loss": 4.4177, "step": 10546 }, { "epoch": 0.5675312096427034, "grad_norm": 1.8285300731658936, "learning_rate": 1.9739941264081003e-05, "loss": 4.0727, "step": 10547 }, { "epoch": 0.5675850193715024, "grad_norm": 2.524484634399414, "learning_rate": 1.9735809737180854e-05, "loss": 3.613, "step": 10548 }, { "epoch": 0.5676388291003014, "grad_norm": 2.8819541931152344, "learning_rate": 1.9731678360717098e-05, "loss": 3.9044, "step": 10549 }, { "epoch": 0.5676926388291003, "grad_norm": 2.0388143062591553, "learning_rate": 1.9727547134807813e-05, "loss": 4.21, "step": 10550 }, { "epoch": 0.5677464485578992, "grad_norm": 1.5642802715301514, "learning_rate": 1.9723416059571053e-05, "loss": 4.0959, "step": 10551 }, { "epoch": 0.5678002582866982, "grad_norm": 1.0230352878570557, "learning_rate": 1.9719285135124864e-05, "loss": 4.4283, "step": 10552 }, { "epoch": 0.5678540680154972, "grad_norm": 2.1650376319885254, "learning_rate": 1.9715154361587308e-05, "loss": 3.5143, "step": 10553 }, { "epoch": 0.5679078777442962, "grad_norm": 1.8614771366119385, "learning_rate": 1.971102373907641e-05, "loss": 3.9301, "step": 10554 }, { "epoch": 0.5679616874730952, "grad_norm": 2.702310085296631, "learning_rate": 1.9706893267710242e-05, "loss": 3.3204, "step": 10555 }, { "epoch": 0.5680154972018941, "grad_norm": 2.984011173248291, "learning_rate": 1.9702762947606824e-05, "loss": 3.9702, "step": 10556 }, { "epoch": 0.568069306930693, "grad_norm": 2.98832631111145, "learning_rate": 1.969863277888419e-05, "loss": 3.9633, "step": 10557 }, { "epoch": 0.568123116659492, "grad_norm": 2.4633069038391113, "learning_rate": 1.9694502761660386e-05, "loss": 4.212, "step": 10558 }, { "epoch": 0.568176926388291, "grad_norm": 2.5891125202178955, "learning_rate": 1.9690372896053404e-05, "loss": 4.2351, "step": 10559 }, { "epoch": 0.56823073611709, "grad_norm": 3.3902177810668945, "learning_rate": 1.9686243182181295e-05, "loss": 3.6461, "step": 10560 }, { "epoch": 0.5682845458458889, "grad_norm": 2.635455369949341, "learning_rate": 1.968211362016206e-05, "loss": 4.2348, "step": 10561 }, { "epoch": 0.5683383555746879, "grad_norm": 2.2350754737854004, "learning_rate": 1.967798421011371e-05, "loss": 3.7096, "step": 10562 }, { "epoch": 0.5683921653034869, "grad_norm": 2.938382625579834, "learning_rate": 1.967385495215426e-05, "loss": 4.1961, "step": 10563 }, { "epoch": 0.5684459750322859, "grad_norm": 2.6947386264801025, "learning_rate": 1.9669725846401712e-05, "loss": 4.3563, "step": 10564 }, { "epoch": 0.5684997847610848, "grad_norm": 2.250131607055664, "learning_rate": 1.966559689297406e-05, "loss": 3.932, "step": 10565 }, { "epoch": 0.5685535944898837, "grad_norm": 2.6989493370056152, "learning_rate": 1.966146809198931e-05, "loss": 3.9654, "step": 10566 }, { "epoch": 0.5686074042186827, "grad_norm": 2.6431822776794434, "learning_rate": 1.965733944356543e-05, "loss": 3.9142, "step": 10567 }, { "epoch": 0.5686612139474817, "grad_norm": 2.3684792518615723, "learning_rate": 1.9653210947820426e-05, "loss": 3.7309, "step": 10568 }, { "epoch": 0.5687150236762807, "grad_norm": 3.2293617725372314, "learning_rate": 1.964908260487227e-05, "loss": 4.0151, "step": 10569 }, { "epoch": 0.5687688334050797, "grad_norm": 2.8728177547454834, "learning_rate": 1.9644954414838936e-05, "loss": 3.7502, "step": 10570 }, { "epoch": 0.5688226431338786, "grad_norm": 2.7084765434265137, "learning_rate": 1.964082637783841e-05, "loss": 3.6607, "step": 10571 }, { "epoch": 0.5688764528626775, "grad_norm": 1.9428603649139404, "learning_rate": 1.9636698493988648e-05, "loss": 4.1226, "step": 10572 }, { "epoch": 0.5689302625914765, "grad_norm": 4.002418041229248, "learning_rate": 1.9632570763407624e-05, "loss": 4.74, "step": 10573 }, { "epoch": 0.5689840723202755, "grad_norm": 1.88398277759552, "learning_rate": 1.9628443186213276e-05, "loss": 4.1536, "step": 10574 }, { "epoch": 0.5690378820490745, "grad_norm": 3.2111549377441406, "learning_rate": 1.9624315762523585e-05, "loss": 4.3465, "step": 10575 }, { "epoch": 0.5690916917778734, "grad_norm": 3.4361777305603027, "learning_rate": 1.9620188492456488e-05, "loss": 3.662, "step": 10576 }, { "epoch": 0.5691455015066724, "grad_norm": 2.4157896041870117, "learning_rate": 1.961606137612993e-05, "loss": 4.1015, "step": 10577 }, { "epoch": 0.5691993112354714, "grad_norm": 1.6861109733581543, "learning_rate": 1.961193441366186e-05, "loss": 3.7272, "step": 10578 }, { "epoch": 0.5692531209642704, "grad_norm": 3.3362834453582764, "learning_rate": 1.9607807605170216e-05, "loss": 3.8394, "step": 10579 }, { "epoch": 0.5693069306930693, "grad_norm": 2.37872052192688, "learning_rate": 1.9603680950772916e-05, "loss": 3.9044, "step": 10580 }, { "epoch": 0.5693607404218682, "grad_norm": 2.8217878341674805, "learning_rate": 1.959955445058792e-05, "loss": 4.3112, "step": 10581 }, { "epoch": 0.5694145501506672, "grad_norm": 1.542575716972351, "learning_rate": 1.9595428104733115e-05, "loss": 3.9227, "step": 10582 }, { "epoch": 0.5694683598794662, "grad_norm": 2.1299891471862793, "learning_rate": 1.9591301913326444e-05, "loss": 4.391, "step": 10583 }, { "epoch": 0.5695221696082652, "grad_norm": 2.262244701385498, "learning_rate": 1.958717587648582e-05, "loss": 3.7043, "step": 10584 }, { "epoch": 0.5695759793370642, "grad_norm": 1.6071194410324097, "learning_rate": 1.958304999432914e-05, "loss": 4.1363, "step": 10585 }, { "epoch": 0.5696297890658631, "grad_norm": 3.165792465209961, "learning_rate": 1.957892426697433e-05, "loss": 3.4784, "step": 10586 }, { "epoch": 0.5696835987946621, "grad_norm": 2.3172972202301025, "learning_rate": 1.957479869453928e-05, "loss": 4.3875, "step": 10587 }, { "epoch": 0.569737408523461, "grad_norm": 1.836898922920227, "learning_rate": 1.957067327714189e-05, "loss": 4.1837, "step": 10588 }, { "epoch": 0.56979121825226, "grad_norm": 2.1935667991638184, "learning_rate": 1.956654801490007e-05, "loss": 4.0565, "step": 10589 }, { "epoch": 0.569845027981059, "grad_norm": 2.892117738723755, "learning_rate": 1.9562422907931673e-05, "loss": 3.7719, "step": 10590 }, { "epoch": 0.5698988377098579, "grad_norm": 1.940343976020813, "learning_rate": 1.9558297956354615e-05, "loss": 4.0241, "step": 10591 }, { "epoch": 0.5699526474386569, "grad_norm": 1.9753834009170532, "learning_rate": 1.955417316028676e-05, "loss": 3.8607, "step": 10592 }, { "epoch": 0.5700064571674559, "grad_norm": 2.442382574081421, "learning_rate": 1.9550048519845986e-05, "loss": 4.0884, "step": 10593 }, { "epoch": 0.5700602668962549, "grad_norm": 1.9625262022018433, "learning_rate": 1.9545924035150174e-05, "loss": 4.6142, "step": 10594 }, { "epoch": 0.5701140766250538, "grad_norm": 1.6644604206085205, "learning_rate": 1.954179970631718e-05, "loss": 4.2663, "step": 10595 }, { "epoch": 0.5701678863538527, "grad_norm": 2.3535592555999756, "learning_rate": 1.9537675533464876e-05, "loss": 4.0283, "step": 10596 }, { "epoch": 0.5702216960826517, "grad_norm": 1.5108810663223267, "learning_rate": 1.9533551516711106e-05, "loss": 4.2771, "step": 10597 }, { "epoch": 0.5702755058114507, "grad_norm": 3.4677555561065674, "learning_rate": 1.952942765617373e-05, "loss": 3.4652, "step": 10598 }, { "epoch": 0.5703293155402497, "grad_norm": 1.9428222179412842, "learning_rate": 1.9525303951970598e-05, "loss": 4.346, "step": 10599 }, { "epoch": 0.5703831252690487, "grad_norm": 1.950189232826233, "learning_rate": 1.952118040421956e-05, "loss": 4.6041, "step": 10600 }, { "epoch": 0.5704369349978476, "grad_norm": 3.3255836963653564, "learning_rate": 1.9517057013038438e-05, "loss": 3.3406, "step": 10601 }, { "epoch": 0.5704907447266466, "grad_norm": 2.2864809036254883, "learning_rate": 1.9512933778545083e-05, "loss": 4.3214, "step": 10602 }, { "epoch": 0.5705445544554455, "grad_norm": 5.337821960449219, "learning_rate": 1.9508810700857327e-05, "loss": 3.2672, "step": 10603 }, { "epoch": 0.5705983641842445, "grad_norm": 1.38352370262146, "learning_rate": 1.9504687780092998e-05, "loss": 4.6065, "step": 10604 }, { "epoch": 0.5706521739130435, "grad_norm": 2.0978784561157227, "learning_rate": 1.95005650163699e-05, "loss": 4.815, "step": 10605 }, { "epoch": 0.5707059836418424, "grad_norm": 2.2563393115997314, "learning_rate": 1.9496442409805867e-05, "loss": 3.997, "step": 10606 }, { "epoch": 0.5707597933706414, "grad_norm": 2.204697847366333, "learning_rate": 1.94923199605187e-05, "loss": 4.2078, "step": 10607 }, { "epoch": 0.5708136030994404, "grad_norm": 2.8153293132781982, "learning_rate": 1.948819766862622e-05, "loss": 3.9072, "step": 10608 }, { "epoch": 0.5708674128282394, "grad_norm": 2.7419376373291016, "learning_rate": 1.9484075534246225e-05, "loss": 3.6997, "step": 10609 }, { "epoch": 0.5709212225570384, "grad_norm": 1.9281518459320068, "learning_rate": 1.9479953557496518e-05, "loss": 3.474, "step": 10610 }, { "epoch": 0.5709750322858372, "grad_norm": 2.4869256019592285, "learning_rate": 1.9475831738494883e-05, "loss": 3.7422, "step": 10611 }, { "epoch": 0.5710288420146362, "grad_norm": 1.884521245956421, "learning_rate": 1.9471710077359135e-05, "loss": 4.0539, "step": 10612 }, { "epoch": 0.5710826517434352, "grad_norm": 3.112055778503418, "learning_rate": 1.946758857420703e-05, "loss": 3.8867, "step": 10613 }, { "epoch": 0.5711364614722342, "grad_norm": 2.7486608028411865, "learning_rate": 1.946346722915637e-05, "loss": 4.1917, "step": 10614 }, { "epoch": 0.5711902712010332, "grad_norm": 1.2816721200942993, "learning_rate": 1.945934604232492e-05, "loss": 4.3032, "step": 10615 }, { "epoch": 0.5712440809298321, "grad_norm": 1.579385757446289, "learning_rate": 1.9455225013830454e-05, "loss": 4.5676, "step": 10616 }, { "epoch": 0.5712978906586311, "grad_norm": 1.5033289194107056, "learning_rate": 1.945110414379075e-05, "loss": 4.4822, "step": 10617 }, { "epoch": 0.57135170038743, "grad_norm": 2.196442127227783, "learning_rate": 1.9446983432323562e-05, "loss": 4.8247, "step": 10618 }, { "epoch": 0.571405510116229, "grad_norm": 2.1327507495880127, "learning_rate": 1.944286287954666e-05, "loss": 4.2366, "step": 10619 }, { "epoch": 0.571459319845028, "grad_norm": 2.373624086380005, "learning_rate": 1.9438742485577784e-05, "loss": 3.2042, "step": 10620 }, { "epoch": 0.5715131295738269, "grad_norm": 2.1977415084838867, "learning_rate": 1.9434622250534686e-05, "loss": 4.1852, "step": 10621 }, { "epoch": 0.5715669393026259, "grad_norm": 2.765576124191284, "learning_rate": 1.9430502174535115e-05, "loss": 4.3294, "step": 10622 }, { "epoch": 0.5716207490314249, "grad_norm": 1.300499677658081, "learning_rate": 1.9426382257696816e-05, "loss": 4.5556, "step": 10623 }, { "epoch": 0.5716745587602239, "grad_norm": 2.3241701126098633, "learning_rate": 1.942226250013751e-05, "loss": 4.2132, "step": 10624 }, { "epoch": 0.5717283684890229, "grad_norm": 2.844879150390625, "learning_rate": 1.941814290197495e-05, "loss": 3.5926, "step": 10625 }, { "epoch": 0.5717821782178217, "grad_norm": 1.6039390563964844, "learning_rate": 1.9414023463326853e-05, "loss": 4.2547, "step": 10626 }, { "epoch": 0.5718359879466207, "grad_norm": 1.9247679710388184, "learning_rate": 1.9409904184310947e-05, "loss": 4.3025, "step": 10627 }, { "epoch": 0.5718897976754197, "grad_norm": 1.640099048614502, "learning_rate": 1.9405785065044936e-05, "loss": 4.6405, "step": 10628 }, { "epoch": 0.5719436074042187, "grad_norm": 2.837653398513794, "learning_rate": 1.9401666105646535e-05, "loss": 3.8647, "step": 10629 }, { "epoch": 0.5719974171330177, "grad_norm": 2.5570340156555176, "learning_rate": 1.9397547306233466e-05, "loss": 4.1122, "step": 10630 }, { "epoch": 0.5720512268618166, "grad_norm": 2.4851737022399902, "learning_rate": 1.9393428666923425e-05, "loss": 3.9968, "step": 10631 }, { "epoch": 0.5721050365906156, "grad_norm": 1.1634314060211182, "learning_rate": 1.9389310187834108e-05, "loss": 4.3814, "step": 10632 }, { "epoch": 0.5721588463194146, "grad_norm": 2.033259391784668, "learning_rate": 1.9385191869083218e-05, "loss": 4.6046, "step": 10633 }, { "epoch": 0.5722126560482135, "grad_norm": 3.017656087875366, "learning_rate": 1.9381073710788446e-05, "loss": 3.2659, "step": 10634 }, { "epoch": 0.5722664657770125, "grad_norm": 4.076126575469971, "learning_rate": 1.9376955713067478e-05, "loss": 3.5993, "step": 10635 }, { "epoch": 0.5723202755058114, "grad_norm": 4.101405620574951, "learning_rate": 1.937283787603798e-05, "loss": 3.3276, "step": 10636 }, { "epoch": 0.5723740852346104, "grad_norm": 2.111921787261963, "learning_rate": 1.936872019981765e-05, "loss": 4.4551, "step": 10637 }, { "epoch": 0.5724278949634094, "grad_norm": 1.9910715818405151, "learning_rate": 1.9364602684524143e-05, "loss": 4.1088, "step": 10638 }, { "epoch": 0.5724817046922084, "grad_norm": 1.5848649740219116, "learning_rate": 1.9360485330275132e-05, "loss": 4.4817, "step": 10639 }, { "epoch": 0.5725355144210074, "grad_norm": 2.6153604984283447, "learning_rate": 1.9356368137188288e-05, "loss": 3.9977, "step": 10640 }, { "epoch": 0.5725893241498062, "grad_norm": 2.9451651573181152, "learning_rate": 1.9352251105381263e-05, "loss": 3.9621, "step": 10641 }, { "epoch": 0.5726431338786052, "grad_norm": 4.401656627655029, "learning_rate": 1.9348134234971715e-05, "loss": 3.1982, "step": 10642 }, { "epoch": 0.5726969436074042, "grad_norm": 1.248354196548462, "learning_rate": 1.9344017526077286e-05, "loss": 3.894, "step": 10643 }, { "epoch": 0.5727507533362032, "grad_norm": 1.3712273836135864, "learning_rate": 1.9339900978815615e-05, "loss": 4.4632, "step": 10644 }, { "epoch": 0.5728045630650022, "grad_norm": 2.4909722805023193, "learning_rate": 1.933578459330436e-05, "loss": 4.2707, "step": 10645 }, { "epoch": 0.5728583727938011, "grad_norm": 3.15148663520813, "learning_rate": 1.933166836966114e-05, "loss": 3.7839, "step": 10646 }, { "epoch": 0.5729121825226001, "grad_norm": 2.7156479358673096, "learning_rate": 1.932755230800359e-05, "loss": 3.9372, "step": 10647 }, { "epoch": 0.5729659922513991, "grad_norm": 2.802605152130127, "learning_rate": 1.932343640844934e-05, "loss": 4.0679, "step": 10648 }, { "epoch": 0.573019801980198, "grad_norm": 3.2241997718811035, "learning_rate": 1.9319320671116013e-05, "loss": 3.3566, "step": 10649 }, { "epoch": 0.573073611708997, "grad_norm": 2.767775297164917, "learning_rate": 1.9315205096121226e-05, "loss": 3.6501, "step": 10650 }, { "epoch": 0.5731274214377959, "grad_norm": 3.544809341430664, "learning_rate": 1.931108968358258e-05, "loss": 4.469, "step": 10651 }, { "epoch": 0.5731812311665949, "grad_norm": 2.2839388847351074, "learning_rate": 1.930697443361769e-05, "loss": 3.9886, "step": 10652 }, { "epoch": 0.5732350408953939, "grad_norm": 1.4893136024475098, "learning_rate": 1.9302859346344158e-05, "loss": 4.8429, "step": 10653 }, { "epoch": 0.5732888506241929, "grad_norm": 1.424118161201477, "learning_rate": 1.929874442187958e-05, "loss": 4.2397, "step": 10654 }, { "epoch": 0.5733426603529919, "grad_norm": 2.5037434101104736, "learning_rate": 1.9294629660341555e-05, "loss": 4.5197, "step": 10655 }, { "epoch": 0.5733964700817907, "grad_norm": 2.5720086097717285, "learning_rate": 1.9290515061847668e-05, "loss": 4.615, "step": 10656 }, { "epoch": 0.5734502798105897, "grad_norm": 2.5512454509735107, "learning_rate": 1.928640062651551e-05, "loss": 3.6186, "step": 10657 }, { "epoch": 0.5735040895393887, "grad_norm": 2.297619581222534, "learning_rate": 1.9282286354462653e-05, "loss": 3.9413, "step": 10658 }, { "epoch": 0.5735578992681877, "grad_norm": 2.949336051940918, "learning_rate": 1.9278172245806665e-05, "loss": 3.0872, "step": 10659 }, { "epoch": 0.5736117089969867, "grad_norm": 1.740501046180725, "learning_rate": 1.9274058300665126e-05, "loss": 4.0366, "step": 10660 }, { "epoch": 0.5736655187257856, "grad_norm": 1.7805172204971313, "learning_rate": 1.9269944519155604e-05, "loss": 4.1738, "step": 10661 }, { "epoch": 0.5737193284545846, "grad_norm": 3.3036556243896484, "learning_rate": 1.9265830901395647e-05, "loss": 3.6402, "step": 10662 }, { "epoch": 0.5737731381833836, "grad_norm": 1.5272380113601685, "learning_rate": 1.926171744750283e-05, "loss": 4.3117, "step": 10663 }, { "epoch": 0.5738269479121825, "grad_norm": 2.7404825687408447, "learning_rate": 1.9257604157594692e-05, "loss": 4.0592, "step": 10664 }, { "epoch": 0.5738807576409815, "grad_norm": 2.889913320541382, "learning_rate": 1.9253491031788787e-05, "loss": 3.9712, "step": 10665 }, { "epoch": 0.5739345673697804, "grad_norm": 2.0261662006378174, "learning_rate": 1.9249378070202645e-05, "loss": 4.2941, "step": 10666 }, { "epoch": 0.5739883770985794, "grad_norm": 2.678881883621216, "learning_rate": 1.9245265272953807e-05, "loss": 3.8809, "step": 10667 }, { "epoch": 0.5740421868273784, "grad_norm": 1.1216942071914673, "learning_rate": 1.9241152640159814e-05, "loss": 3.8413, "step": 10668 }, { "epoch": 0.5740959965561774, "grad_norm": 2.284092903137207, "learning_rate": 1.923704017193819e-05, "loss": 4.4195, "step": 10669 }, { "epoch": 0.5741498062849764, "grad_norm": 2.3012077808380127, "learning_rate": 1.923292786840645e-05, "loss": 3.9092, "step": 10670 }, { "epoch": 0.5742036160137753, "grad_norm": 2.2204065322875977, "learning_rate": 1.9228815729682125e-05, "loss": 4.0512, "step": 10671 }, { "epoch": 0.5742574257425742, "grad_norm": 2.49011492729187, "learning_rate": 1.922470375588273e-05, "loss": 4.0744, "step": 10672 }, { "epoch": 0.5743112354713732, "grad_norm": 1.8428014516830444, "learning_rate": 1.9220591947125766e-05, "loss": 4.1075, "step": 10673 }, { "epoch": 0.5743650452001722, "grad_norm": 1.5229566097259521, "learning_rate": 1.9216480303528737e-05, "loss": 4.5608, "step": 10674 }, { "epoch": 0.5744188549289712, "grad_norm": 1.537268042564392, "learning_rate": 1.921236882520914e-05, "loss": 4.26, "step": 10675 }, { "epoch": 0.5744726646577701, "grad_norm": 2.7679224014282227, "learning_rate": 1.920825751228448e-05, "loss": 4.1555, "step": 10676 }, { "epoch": 0.5745264743865691, "grad_norm": 3.132028341293335, "learning_rate": 1.920414636487224e-05, "loss": 3.8064, "step": 10677 }, { "epoch": 0.5745802841153681, "grad_norm": 3.3117167949676514, "learning_rate": 1.9200035383089903e-05, "loss": 3.4506, "step": 10678 }, { "epoch": 0.574634093844167, "grad_norm": 2.972987413406372, "learning_rate": 1.9195924567054964e-05, "loss": 3.899, "step": 10679 }, { "epoch": 0.574687903572966, "grad_norm": 2.8248088359832764, "learning_rate": 1.9191813916884892e-05, "loss": 4.3368, "step": 10680 }, { "epoch": 0.5747417133017649, "grad_norm": 1.4967684745788574, "learning_rate": 1.918770343269715e-05, "loss": 4.2552, "step": 10681 }, { "epoch": 0.5747955230305639, "grad_norm": 2.0496253967285156, "learning_rate": 1.918359311460921e-05, "loss": 4.2519, "step": 10682 }, { "epoch": 0.5748493327593629, "grad_norm": 2.396845817565918, "learning_rate": 1.917948296273853e-05, "loss": 4.5614, "step": 10683 }, { "epoch": 0.5749031424881619, "grad_norm": 1.9413312673568726, "learning_rate": 1.917537297720258e-05, "loss": 3.6517, "step": 10684 }, { "epoch": 0.5749569522169609, "grad_norm": 2.536431312561035, "learning_rate": 1.91712631581188e-05, "loss": 4.2228, "step": 10685 }, { "epoch": 0.5750107619457598, "grad_norm": 1.5866138935089111, "learning_rate": 1.916715350560464e-05, "loss": 4.3082, "step": 10686 }, { "epoch": 0.5750645716745587, "grad_norm": 1.838133454322815, "learning_rate": 1.9163044019777548e-05, "loss": 4.4497, "step": 10687 }, { "epoch": 0.5751183814033577, "grad_norm": 1.1547396183013916, "learning_rate": 1.9158934700754962e-05, "loss": 4.3896, "step": 10688 }, { "epoch": 0.5751721911321567, "grad_norm": 1.2242287397384644, "learning_rate": 1.915482554865431e-05, "loss": 4.635, "step": 10689 }, { "epoch": 0.5752260008609557, "grad_norm": 2.771672487258911, "learning_rate": 1.9150716563593012e-05, "loss": 3.457, "step": 10690 }, { "epoch": 0.5752798105897546, "grad_norm": 2.872645139694214, "learning_rate": 1.914660774568851e-05, "loss": 3.2333, "step": 10691 }, { "epoch": 0.5753336203185536, "grad_norm": 2.889922618865967, "learning_rate": 1.9142499095058214e-05, "loss": 3.4117, "step": 10692 }, { "epoch": 0.5753874300473526, "grad_norm": 1.921927571296692, "learning_rate": 1.9138390611819534e-05, "loss": 4.0705, "step": 10693 }, { "epoch": 0.5754412397761516, "grad_norm": 3.4143266677856445, "learning_rate": 1.9134282296089892e-05, "loss": 3.6259, "step": 10694 }, { "epoch": 0.5754950495049505, "grad_norm": 2.5579745769500732, "learning_rate": 1.9130174147986682e-05, "loss": 3.5367, "step": 10695 }, { "epoch": 0.5755488592337494, "grad_norm": 2.8369388580322266, "learning_rate": 1.9126066167627315e-05, "loss": 4.259, "step": 10696 }, { "epoch": 0.5756026689625484, "grad_norm": 1.201701283454895, "learning_rate": 1.912195835512917e-05, "loss": 4.3155, "step": 10697 }, { "epoch": 0.5756564786913474, "grad_norm": 3.6082770824432373, "learning_rate": 1.9117850710609643e-05, "loss": 4.0654, "step": 10698 }, { "epoch": 0.5757102884201464, "grad_norm": 3.1386966705322266, "learning_rate": 1.911374323418612e-05, "loss": 3.9635, "step": 10699 }, { "epoch": 0.5757640981489454, "grad_norm": 1.9229239225387573, "learning_rate": 1.9109635925975988e-05, "loss": 4.0111, "step": 10700 }, { "epoch": 0.5758179078777443, "grad_norm": 1.778612494468689, "learning_rate": 1.9105528786096613e-05, "loss": 4.0204, "step": 10701 }, { "epoch": 0.5758717176065432, "grad_norm": 1.3251498937606812, "learning_rate": 1.9101421814665376e-05, "loss": 4.5025, "step": 10702 }, { "epoch": 0.5759255273353422, "grad_norm": 1.6415225267410278, "learning_rate": 1.9097315011799642e-05, "loss": 4.1373, "step": 10703 }, { "epoch": 0.5759793370641412, "grad_norm": 3.418349266052246, "learning_rate": 1.909320837761677e-05, "loss": 2.6921, "step": 10704 }, { "epoch": 0.5760331467929402, "grad_norm": 1.9045945405960083, "learning_rate": 1.9089101912234107e-05, "loss": 4.4395, "step": 10705 }, { "epoch": 0.5760869565217391, "grad_norm": 1.7801796197891235, "learning_rate": 1.908499561576901e-05, "loss": 4.4333, "step": 10706 }, { "epoch": 0.5761407662505381, "grad_norm": 1.955538272857666, "learning_rate": 1.9080889488338833e-05, "loss": 3.9506, "step": 10707 }, { "epoch": 0.5761945759793371, "grad_norm": 1.4291232824325562, "learning_rate": 1.9076783530060916e-05, "loss": 4.3924, "step": 10708 }, { "epoch": 0.5762483857081361, "grad_norm": 2.4280295372009277, "learning_rate": 1.907267774105259e-05, "loss": 4.2924, "step": 10709 }, { "epoch": 0.576302195436935, "grad_norm": 2.289285182952881, "learning_rate": 1.9068572121431195e-05, "loss": 4.1481, "step": 10710 }, { "epoch": 0.5763560051657339, "grad_norm": 1.5197511911392212, "learning_rate": 1.906446667131406e-05, "loss": 4.2992, "step": 10711 }, { "epoch": 0.5764098148945329, "grad_norm": 2.3892059326171875, "learning_rate": 1.9060361390818496e-05, "loss": 4.4676, "step": 10712 }, { "epoch": 0.5764636246233319, "grad_norm": 2.3264544010162354, "learning_rate": 1.905625628006183e-05, "loss": 4.371, "step": 10713 }, { "epoch": 0.5765174343521309, "grad_norm": 2.85833477973938, "learning_rate": 1.9052151339161367e-05, "loss": 3.9272, "step": 10714 }, { "epoch": 0.5765712440809299, "grad_norm": 2.353764295578003, "learning_rate": 1.9048046568234425e-05, "loss": 4.6771, "step": 10715 }, { "epoch": 0.5766250538097288, "grad_norm": 1.668194055557251, "learning_rate": 1.9043941967398306e-05, "loss": 3.693, "step": 10716 }, { "epoch": 0.5766788635385278, "grad_norm": 3.2373697757720947, "learning_rate": 1.90398375367703e-05, "loss": 3.3357, "step": 10717 }, { "epoch": 0.5767326732673267, "grad_norm": 1.6844979524612427, "learning_rate": 1.903573327646771e-05, "loss": 4.2188, "step": 10718 }, { "epoch": 0.5767864829961257, "grad_norm": 2.6010823249816895, "learning_rate": 1.9031629186607825e-05, "loss": 3.6631, "step": 10719 }, { "epoch": 0.5768402927249247, "grad_norm": 2.9310524463653564, "learning_rate": 1.9027525267307923e-05, "loss": 2.9799, "step": 10720 }, { "epoch": 0.5768941024537236, "grad_norm": 4.083552360534668, "learning_rate": 1.9023421518685276e-05, "loss": 3.1594, "step": 10721 }, { "epoch": 0.5769479121825226, "grad_norm": 2.2131693363189697, "learning_rate": 1.9019317940857173e-05, "loss": 3.9359, "step": 10722 }, { "epoch": 0.5770017219113216, "grad_norm": 2.077505350112915, "learning_rate": 1.9015214533940878e-05, "loss": 3.9604, "step": 10723 }, { "epoch": 0.5770555316401206, "grad_norm": 2.850402593612671, "learning_rate": 1.901111129805365e-05, "loss": 3.9126, "step": 10724 }, { "epoch": 0.5771093413689194, "grad_norm": 2.633626937866211, "learning_rate": 1.9007008233312757e-05, "loss": 4.4047, "step": 10725 }, { "epoch": 0.5771631510977184, "grad_norm": 2.585186719894409, "learning_rate": 1.9002905339835457e-05, "loss": 4.0448, "step": 10726 }, { "epoch": 0.5772169608265174, "grad_norm": 1.148573875427246, "learning_rate": 1.8998802617738984e-05, "loss": 4.3875, "step": 10727 }, { "epoch": 0.5772707705553164, "grad_norm": 1.5602185726165771, "learning_rate": 1.899470006714059e-05, "loss": 4.2513, "step": 10728 }, { "epoch": 0.5773245802841154, "grad_norm": 2.516611337661743, "learning_rate": 1.8990597688157514e-05, "loss": 4.1614, "step": 10729 }, { "epoch": 0.5773783900129144, "grad_norm": 2.792407274246216, "learning_rate": 1.8986495480906996e-05, "loss": 3.7277, "step": 10730 }, { "epoch": 0.5774321997417133, "grad_norm": 2.4967031478881836, "learning_rate": 1.898239344550626e-05, "loss": 4.6932, "step": 10731 }, { "epoch": 0.5774860094705123, "grad_norm": 1.4221473932266235, "learning_rate": 1.8978291582072533e-05, "loss": 4.5701, "step": 10732 }, { "epoch": 0.5775398191993112, "grad_norm": 1.71885085105896, "learning_rate": 1.897418989072304e-05, "loss": 3.7786, "step": 10733 }, { "epoch": 0.5775936289281102, "grad_norm": 2.6814427375793457, "learning_rate": 1.8970088371574994e-05, "loss": 4.1171, "step": 10734 }, { "epoch": 0.5776474386569092, "grad_norm": 1.6770074367523193, "learning_rate": 1.8965987024745606e-05, "loss": 4.3912, "step": 10735 }, { "epoch": 0.5777012483857081, "grad_norm": 2.574902057647705, "learning_rate": 1.8961885850352074e-05, "loss": 4.2868, "step": 10736 }, { "epoch": 0.5777550581145071, "grad_norm": 1.9535253047943115, "learning_rate": 1.8957784848511602e-05, "loss": 4.2556, "step": 10737 }, { "epoch": 0.5778088678433061, "grad_norm": 1.9834882020950317, "learning_rate": 1.8953684019341388e-05, "loss": 3.9721, "step": 10738 }, { "epoch": 0.5778626775721051, "grad_norm": 1.9182806015014648, "learning_rate": 1.894958336295862e-05, "loss": 4.0885, "step": 10739 }, { "epoch": 0.5779164873009041, "grad_norm": 1.8587887287139893, "learning_rate": 1.894548287948049e-05, "loss": 4.6376, "step": 10740 }, { "epoch": 0.5779702970297029, "grad_norm": 2.0986602306365967, "learning_rate": 1.8941382569024173e-05, "loss": 3.91, "step": 10741 }, { "epoch": 0.5780241067585019, "grad_norm": 2.302023410797119, "learning_rate": 1.8937282431706855e-05, "loss": 4.2891, "step": 10742 }, { "epoch": 0.5780779164873009, "grad_norm": 3.978395700454712, "learning_rate": 1.8933182467645692e-05, "loss": 3.878, "step": 10743 }, { "epoch": 0.5781317262160999, "grad_norm": 1.1359152793884277, "learning_rate": 1.8929082676957855e-05, "loss": 4.5056, "step": 10744 }, { "epoch": 0.5781855359448989, "grad_norm": 2.9739842414855957, "learning_rate": 1.89249830597605e-05, "loss": 4.4292, "step": 10745 }, { "epoch": 0.5782393456736978, "grad_norm": 2.044206380844116, "learning_rate": 1.8920883616170798e-05, "loss": 4.1863, "step": 10746 }, { "epoch": 0.5782931554024968, "grad_norm": 2.5730090141296387, "learning_rate": 1.8916784346305888e-05, "loss": 3.8417, "step": 10747 }, { "epoch": 0.5783469651312957, "grad_norm": 2.589674711227417, "learning_rate": 1.8912685250282916e-05, "loss": 3.9859, "step": 10748 }, { "epoch": 0.5784007748600947, "grad_norm": 2.75052809715271, "learning_rate": 1.8908586328219035e-05, "loss": 3.1702, "step": 10749 }, { "epoch": 0.5784545845888936, "grad_norm": 2.442418336868286, "learning_rate": 1.890448758023137e-05, "loss": 4.0268, "step": 10750 }, { "epoch": 0.5785083943176926, "grad_norm": 2.9793741703033447, "learning_rate": 1.8900389006437057e-05, "loss": 3.7171, "step": 10751 }, { "epoch": 0.5785622040464916, "grad_norm": 2.483912706375122, "learning_rate": 1.889629060695321e-05, "loss": 4.2121, "step": 10752 }, { "epoch": 0.5786160137752906, "grad_norm": 3.0275425910949707, "learning_rate": 1.889219238189697e-05, "loss": 3.7038, "step": 10753 }, { "epoch": 0.5786698235040896, "grad_norm": 2.060143232345581, "learning_rate": 1.8888094331385442e-05, "loss": 4.1631, "step": 10754 }, { "epoch": 0.5787236332328886, "grad_norm": 2.32563853263855, "learning_rate": 1.8883996455535732e-05, "loss": 3.7891, "step": 10755 }, { "epoch": 0.5787774429616874, "grad_norm": 2.584782123565674, "learning_rate": 1.8879898754464958e-05, "loss": 3.6208, "step": 10756 }, { "epoch": 0.5788312526904864, "grad_norm": 2.5556318759918213, "learning_rate": 1.8875801228290225e-05, "loss": 4.0349, "step": 10757 }, { "epoch": 0.5788850624192854, "grad_norm": 2.1756720542907715, "learning_rate": 1.8871703877128613e-05, "loss": 4.1061, "step": 10758 }, { "epoch": 0.5789388721480844, "grad_norm": 2.662085771560669, "learning_rate": 1.8867606701097222e-05, "loss": 4.2128, "step": 10759 }, { "epoch": 0.5789926818768834, "grad_norm": 1.7016255855560303, "learning_rate": 1.886350970031313e-05, "loss": 4.4926, "step": 10760 }, { "epoch": 0.5790464916056823, "grad_norm": 2.6418416500091553, "learning_rate": 1.8859412874893434e-05, "loss": 4.3168, "step": 10761 }, { "epoch": 0.5791003013344813, "grad_norm": 1.251150369644165, "learning_rate": 1.88553162249552e-05, "loss": 4.8528, "step": 10762 }, { "epoch": 0.5791541110632802, "grad_norm": 2.1527092456817627, "learning_rate": 1.8851219750615494e-05, "loss": 4.3066, "step": 10763 }, { "epoch": 0.5792079207920792, "grad_norm": 2.5157220363616943, "learning_rate": 1.884712345199141e-05, "loss": 4.1499, "step": 10764 }, { "epoch": 0.5792617305208781, "grad_norm": 1.9315502643585205, "learning_rate": 1.8843027329199968e-05, "loss": 4.4307, "step": 10765 }, { "epoch": 0.5793155402496771, "grad_norm": 2.6785330772399902, "learning_rate": 1.8838931382358253e-05, "loss": 4.2186, "step": 10766 }, { "epoch": 0.5793693499784761, "grad_norm": 1.3705483675003052, "learning_rate": 1.8834835611583308e-05, "loss": 4.4702, "step": 10767 }, { "epoch": 0.5794231597072751, "grad_norm": 2.845306873321533, "learning_rate": 1.883074001699217e-05, "loss": 3.9426, "step": 10768 }, { "epoch": 0.5794769694360741, "grad_norm": 3.1003899574279785, "learning_rate": 1.88266445987019e-05, "loss": 4.4825, "step": 10769 }, { "epoch": 0.5795307791648731, "grad_norm": 2.8923513889312744, "learning_rate": 1.8822549356829518e-05, "loss": 3.5036, "step": 10770 }, { "epoch": 0.5795845888936719, "grad_norm": 1.9280815124511719, "learning_rate": 1.8818454291492054e-05, "loss": 4.4168, "step": 10771 }, { "epoch": 0.5796383986224709, "grad_norm": 2.337735891342163, "learning_rate": 1.8814359402806557e-05, "loss": 4.097, "step": 10772 }, { "epoch": 0.5796922083512699, "grad_norm": 1.7274608612060547, "learning_rate": 1.8810264690890016e-05, "loss": 4.1571, "step": 10773 }, { "epoch": 0.5797460180800689, "grad_norm": 2.9389705657958984, "learning_rate": 1.880617015585947e-05, "loss": 3.5752, "step": 10774 }, { "epoch": 0.5797998278088679, "grad_norm": 2.4644432067871094, "learning_rate": 1.8802075797831916e-05, "loss": 3.9873, "step": 10775 }, { "epoch": 0.5798536375376668, "grad_norm": 2.2648627758026123, "learning_rate": 1.8797981616924365e-05, "loss": 4.3041, "step": 10776 }, { "epoch": 0.5799074472664658, "grad_norm": 2.199592113494873, "learning_rate": 1.879388761325382e-05, "loss": 4.0896, "step": 10777 }, { "epoch": 0.5799612569952648, "grad_norm": 2.2853331565856934, "learning_rate": 1.8789793786937273e-05, "loss": 3.8308, "step": 10778 }, { "epoch": 0.5800150667240637, "grad_norm": 2.2322309017181396, "learning_rate": 1.8785700138091712e-05, "loss": 4.2779, "step": 10779 }, { "epoch": 0.5800688764528626, "grad_norm": 2.759510040283203, "learning_rate": 1.8781606666834138e-05, "loss": 4.6042, "step": 10780 }, { "epoch": 0.5801226861816616, "grad_norm": 2.887726306915283, "learning_rate": 1.8777513373281518e-05, "loss": 3.6509, "step": 10781 }, { "epoch": 0.5801764959104606, "grad_norm": 1.1215332746505737, "learning_rate": 1.8773420257550824e-05, "loss": 4.3104, "step": 10782 }, { "epoch": 0.5802303056392596, "grad_norm": 2.3653764724731445, "learning_rate": 1.8769327319759028e-05, "loss": 3.9649, "step": 10783 }, { "epoch": 0.5802841153680586, "grad_norm": 2.643479585647583, "learning_rate": 1.8765234560023105e-05, "loss": 3.4609, "step": 10784 }, { "epoch": 0.5803379250968576, "grad_norm": 2.2297351360321045, "learning_rate": 1.8761141978460007e-05, "loss": 4.4029, "step": 10785 }, { "epoch": 0.5803917348256564, "grad_norm": 1.999056339263916, "learning_rate": 1.8757049575186685e-05, "loss": 3.7627, "step": 10786 }, { "epoch": 0.5804455445544554, "grad_norm": 2.854739189147949, "learning_rate": 1.8752957350320112e-05, "loss": 4.456, "step": 10787 }, { "epoch": 0.5804993542832544, "grad_norm": 2.1949119567871094, "learning_rate": 1.87488653039772e-05, "loss": 4.6273, "step": 10788 }, { "epoch": 0.5805531640120534, "grad_norm": 4.445288181304932, "learning_rate": 1.874477343627491e-05, "loss": 3.1763, "step": 10789 }, { "epoch": 0.5806069737408524, "grad_norm": 3.3286633491516113, "learning_rate": 1.874068174733017e-05, "loss": 3.2582, "step": 10790 }, { "epoch": 0.5806607834696513, "grad_norm": 3.502448797225952, "learning_rate": 1.87365902372599e-05, "loss": 3.1619, "step": 10791 }, { "epoch": 0.5807145931984503, "grad_norm": 3.0902299880981445, "learning_rate": 1.8732498906181046e-05, "loss": 3.4183, "step": 10792 }, { "epoch": 0.5807684029272493, "grad_norm": 2.4623160362243652, "learning_rate": 1.8728407754210514e-05, "loss": 4.1394, "step": 10793 }, { "epoch": 0.5808222126560482, "grad_norm": 2.363348960876465, "learning_rate": 1.872431678146521e-05, "loss": 4.4448, "step": 10794 }, { "epoch": 0.5808760223848471, "grad_norm": 2.6681108474731445, "learning_rate": 1.8720225988062072e-05, "loss": 3.6233, "step": 10795 }, { "epoch": 0.5809298321136461, "grad_norm": 2.9609620571136475, "learning_rate": 1.871613537411797e-05, "loss": 3.6577, "step": 10796 }, { "epoch": 0.5809836418424451, "grad_norm": 2.070744514465332, "learning_rate": 1.8712044939749824e-05, "loss": 3.4986, "step": 10797 }, { "epoch": 0.5810374515712441, "grad_norm": 3.223459482192993, "learning_rate": 1.870795468507452e-05, "loss": 3.4628, "step": 10798 }, { "epoch": 0.5810912613000431, "grad_norm": 1.5629454851150513, "learning_rate": 1.870386461020894e-05, "loss": 4.3103, "step": 10799 }, { "epoch": 0.581145071028842, "grad_norm": 1.3822318315505981, "learning_rate": 1.8699774715269978e-05, "loss": 4.4108, "step": 10800 }, { "epoch": 0.581198880757641, "grad_norm": 2.2748117446899414, "learning_rate": 1.8695685000374514e-05, "loss": 4.2882, "step": 10801 }, { "epoch": 0.5812526904864399, "grad_norm": 1.1832756996154785, "learning_rate": 1.869159546563941e-05, "loss": 4.52, "step": 10802 }, { "epoch": 0.5813065002152389, "grad_norm": 2.1669809818267822, "learning_rate": 1.8687506111181555e-05, "loss": 4.4637, "step": 10803 }, { "epoch": 0.5813603099440379, "grad_norm": 2.4321045875549316, "learning_rate": 1.8683416937117783e-05, "loss": 3.8903, "step": 10804 }, { "epoch": 0.5814141196728368, "grad_norm": 1.4225718975067139, "learning_rate": 1.867932794356497e-05, "loss": 4.5524, "step": 10805 }, { "epoch": 0.5814679294016358, "grad_norm": 4.626522541046143, "learning_rate": 1.867523913063996e-05, "loss": 4.4884, "step": 10806 }, { "epoch": 0.5815217391304348, "grad_norm": 2.891205310821533, "learning_rate": 1.86711504984596e-05, "loss": 4.4976, "step": 10807 }, { "epoch": 0.5815755488592338, "grad_norm": 2.5473248958587646, "learning_rate": 1.866706204714074e-05, "loss": 4.1561, "step": 10808 }, { "epoch": 0.5816293585880327, "grad_norm": 1.7471855878829956, "learning_rate": 1.8662973776800215e-05, "loss": 4.1244, "step": 10809 }, { "epoch": 0.5816831683168316, "grad_norm": 3.350208282470703, "learning_rate": 1.8658885687554862e-05, "loss": 3.0607, "step": 10810 }, { "epoch": 0.5817369780456306, "grad_norm": 3.2626311779022217, "learning_rate": 1.865479777952149e-05, "loss": 3.2925, "step": 10811 }, { "epoch": 0.5817907877744296, "grad_norm": 3.0884552001953125, "learning_rate": 1.8650710052816934e-05, "loss": 3.8477, "step": 10812 }, { "epoch": 0.5818445975032286, "grad_norm": 1.898460030555725, "learning_rate": 1.8646622507558007e-05, "loss": 4.1301, "step": 10813 }, { "epoch": 0.5818984072320276, "grad_norm": 2.834165573120117, "learning_rate": 1.8642535143861515e-05, "loss": 4.1715, "step": 10814 }, { "epoch": 0.5819522169608266, "grad_norm": 3.080174684524536, "learning_rate": 1.8638447961844275e-05, "loss": 4.0531, "step": 10815 }, { "epoch": 0.5820060266896255, "grad_norm": 3.6109745502471924, "learning_rate": 1.863436096162308e-05, "loss": 3.192, "step": 10816 }, { "epoch": 0.5820598364184244, "grad_norm": 2.6468088626861572, "learning_rate": 1.8630274143314724e-05, "loss": 4.4136, "step": 10817 }, { "epoch": 0.5821136461472234, "grad_norm": 1.611779808998108, "learning_rate": 1.8626187507036015e-05, "loss": 3.8204, "step": 10818 }, { "epoch": 0.5821674558760224, "grad_norm": 3.3500499725341797, "learning_rate": 1.8622101052903708e-05, "loss": 3.8748, "step": 10819 }, { "epoch": 0.5822212656048213, "grad_norm": 1.7362120151519775, "learning_rate": 1.8618014781034605e-05, "loss": 4.2923, "step": 10820 }, { "epoch": 0.5822750753336203, "grad_norm": 2.7090539932250977, "learning_rate": 1.8613928691545472e-05, "loss": 3.9564, "step": 10821 }, { "epoch": 0.5823288850624193, "grad_norm": 2.199636220932007, "learning_rate": 1.8609842784553077e-05, "loss": 4.1853, "step": 10822 }, { "epoch": 0.5823826947912183, "grad_norm": 1.9640781879425049, "learning_rate": 1.8605757060174193e-05, "loss": 3.9548, "step": 10823 }, { "epoch": 0.5824365045200173, "grad_norm": 2.307429552078247, "learning_rate": 1.860167151852557e-05, "loss": 3.8696, "step": 10824 }, { "epoch": 0.5824903142488161, "grad_norm": 2.3213603496551514, "learning_rate": 1.8597586159723964e-05, "loss": 4.3733, "step": 10825 }, { "epoch": 0.5825441239776151, "grad_norm": 2.7743630409240723, "learning_rate": 1.859350098388614e-05, "loss": 4.2264, "step": 10826 }, { "epoch": 0.5825979337064141, "grad_norm": 1.3152477741241455, "learning_rate": 1.8589415991128813e-05, "loss": 4.2665, "step": 10827 }, { "epoch": 0.5826517434352131, "grad_norm": 2.8877482414245605, "learning_rate": 1.8585331181568737e-05, "loss": 3.7983, "step": 10828 }, { "epoch": 0.5827055531640121, "grad_norm": 1.377157211303711, "learning_rate": 1.858124655532264e-05, "loss": 4.573, "step": 10829 }, { "epoch": 0.582759362892811, "grad_norm": 2.454767942428589, "learning_rate": 1.857716211250725e-05, "loss": 4.3464, "step": 10830 }, { "epoch": 0.58281317262161, "grad_norm": 2.552973747253418, "learning_rate": 1.8573077853239297e-05, "loss": 4.0949, "step": 10831 }, { "epoch": 0.5828669823504089, "grad_norm": 1.9833096265792847, "learning_rate": 1.8568993777635493e-05, "loss": 4.1721, "step": 10832 }, { "epoch": 0.5829207920792079, "grad_norm": 4.18864107131958, "learning_rate": 1.8564909885812552e-05, "loss": 3.2441, "step": 10833 }, { "epoch": 0.5829746018080069, "grad_norm": 2.4449286460876465, "learning_rate": 1.856082617788717e-05, "loss": 4.0423, "step": 10834 }, { "epoch": 0.5830284115368058, "grad_norm": 2.8359594345092773, "learning_rate": 1.8556742653976062e-05, "loss": 3.2354, "step": 10835 }, { "epoch": 0.5830822212656048, "grad_norm": 2.588141441345215, "learning_rate": 1.8552659314195915e-05, "loss": 4.0907, "step": 10836 }, { "epoch": 0.5831360309944038, "grad_norm": 2.125652551651001, "learning_rate": 1.8548576158663428e-05, "loss": 4.1664, "step": 10837 }, { "epoch": 0.5831898407232028, "grad_norm": 4.129744529724121, "learning_rate": 1.8544493187495275e-05, "loss": 3.6355, "step": 10838 }, { "epoch": 0.5832436504520018, "grad_norm": 2.3034486770629883, "learning_rate": 1.854041040080815e-05, "loss": 4.1669, "step": 10839 }, { "epoch": 0.5832974601808006, "grad_norm": 3.131032705307007, "learning_rate": 1.8536327798718718e-05, "loss": 3.6634, "step": 10840 }, { "epoch": 0.5833512699095996, "grad_norm": 4.036374092102051, "learning_rate": 1.853224538134366e-05, "loss": 3.3681, "step": 10841 }, { "epoch": 0.5834050796383986, "grad_norm": 1.7965527772903442, "learning_rate": 1.852816314879962e-05, "loss": 4.5111, "step": 10842 }, { "epoch": 0.5834588893671976, "grad_norm": 3.493955135345459, "learning_rate": 1.852408110120328e-05, "loss": 2.992, "step": 10843 }, { "epoch": 0.5835126990959966, "grad_norm": 4.367419719696045, "learning_rate": 1.8519999238671282e-05, "loss": 3.4691, "step": 10844 }, { "epoch": 0.5835665088247955, "grad_norm": 1.3546966314315796, "learning_rate": 1.8515917561320267e-05, "loss": 4.4993, "step": 10845 }, { "epoch": 0.5836203185535945, "grad_norm": 2.23846435546875, "learning_rate": 1.8511836069266898e-05, "loss": 3.7803, "step": 10846 }, { "epoch": 0.5836741282823935, "grad_norm": 4.47183084487915, "learning_rate": 1.85077547626278e-05, "loss": 3.6048, "step": 10847 }, { "epoch": 0.5837279380111924, "grad_norm": 2.078284502029419, "learning_rate": 1.8503673641519606e-05, "loss": 4.1483, "step": 10848 }, { "epoch": 0.5837817477399914, "grad_norm": 2.3512651920318604, "learning_rate": 1.849959270605896e-05, "loss": 4.1197, "step": 10849 }, { "epoch": 0.5838355574687903, "grad_norm": 2.9361305236816406, "learning_rate": 1.8495511956362457e-05, "loss": 3.308, "step": 10850 }, { "epoch": 0.5838893671975893, "grad_norm": 3.5717477798461914, "learning_rate": 1.8491431392546732e-05, "loss": 3.4832, "step": 10851 }, { "epoch": 0.5839431769263883, "grad_norm": 2.104351043701172, "learning_rate": 1.8487351014728393e-05, "loss": 3.2245, "step": 10852 }, { "epoch": 0.5839969866551873, "grad_norm": 3.013497829437256, "learning_rate": 1.8483270823024033e-05, "loss": 4.5167, "step": 10853 }, { "epoch": 0.5840507963839863, "grad_norm": 1.827932357788086, "learning_rate": 1.847919081755028e-05, "loss": 3.844, "step": 10854 }, { "epoch": 0.5841046061127851, "grad_norm": 2.932816743850708, "learning_rate": 1.8475110998423708e-05, "loss": 3.0192, "step": 10855 }, { "epoch": 0.5841584158415841, "grad_norm": 3.676827907562256, "learning_rate": 1.847103136576092e-05, "loss": 3.4778, "step": 10856 }, { "epoch": 0.5842122255703831, "grad_norm": 3.300175666809082, "learning_rate": 1.846695191967849e-05, "loss": 3.0361, "step": 10857 }, { "epoch": 0.5842660352991821, "grad_norm": 2.4694983959198, "learning_rate": 1.8462872660293e-05, "loss": 4.7085, "step": 10858 }, { "epoch": 0.5843198450279811, "grad_norm": 1.8271821737289429, "learning_rate": 1.8458793587721028e-05, "loss": 4.2406, "step": 10859 }, { "epoch": 0.58437365475678, "grad_norm": 2.9642677307128906, "learning_rate": 1.845471470207914e-05, "loss": 4.1709, "step": 10860 }, { "epoch": 0.584427464485579, "grad_norm": 2.2846407890319824, "learning_rate": 1.8450636003483902e-05, "loss": 4.1743, "step": 10861 }, { "epoch": 0.584481274214378, "grad_norm": 3.4713284969329834, "learning_rate": 1.844655749205187e-05, "loss": 3.3193, "step": 10862 }, { "epoch": 0.5845350839431769, "grad_norm": 1.3944364786148071, "learning_rate": 1.84424791678996e-05, "loss": 3.937, "step": 10863 }, { "epoch": 0.5845888936719759, "grad_norm": 1.9872651100158691, "learning_rate": 1.843840103114365e-05, "loss": 4.4011, "step": 10864 }, { "epoch": 0.5846427034007748, "grad_norm": 1.7558554410934448, "learning_rate": 1.8434323081900527e-05, "loss": 4.5311, "step": 10865 }, { "epoch": 0.5846965131295738, "grad_norm": 2.42291522026062, "learning_rate": 1.8430245320286805e-05, "loss": 3.9814, "step": 10866 }, { "epoch": 0.5847503228583728, "grad_norm": 3.3445568084716797, "learning_rate": 1.8426167746419e-05, "loss": 3.9686, "step": 10867 }, { "epoch": 0.5848041325871718, "grad_norm": 3.1957340240478516, "learning_rate": 1.842209036041363e-05, "loss": 4.0328, "step": 10868 }, { "epoch": 0.5848579423159708, "grad_norm": 2.90742564201355, "learning_rate": 1.8418013162387232e-05, "loss": 3.709, "step": 10869 }, { "epoch": 0.5849117520447696, "grad_norm": 1.6850976943969727, "learning_rate": 1.8413936152456317e-05, "loss": 4.1413, "step": 10870 }, { "epoch": 0.5849655617735686, "grad_norm": 3.22363543510437, "learning_rate": 1.8409859330737393e-05, "loss": 4.0278, "step": 10871 }, { "epoch": 0.5850193715023676, "grad_norm": 3.472398281097412, "learning_rate": 1.8405782697346962e-05, "loss": 3.8083, "step": 10872 }, { "epoch": 0.5850731812311666, "grad_norm": 1.5194019079208374, "learning_rate": 1.8401706252401524e-05, "loss": 3.9761, "step": 10873 }, { "epoch": 0.5851269909599656, "grad_norm": 2.381316661834717, "learning_rate": 1.8397629996017573e-05, "loss": 3.9128, "step": 10874 }, { "epoch": 0.5851808006887645, "grad_norm": 2.6849706172943115, "learning_rate": 1.83935539283116e-05, "loss": 3.5296, "step": 10875 }, { "epoch": 0.5852346104175635, "grad_norm": 3.3687994480133057, "learning_rate": 1.8389478049400083e-05, "loss": 3.8098, "step": 10876 }, { "epoch": 0.5852884201463625, "grad_norm": 2.9961695671081543, "learning_rate": 1.8385402359399506e-05, "loss": 4.4624, "step": 10877 }, { "epoch": 0.5853422298751614, "grad_norm": 2.5515260696411133, "learning_rate": 1.8381326858426337e-05, "loss": 4.2223, "step": 10878 }, { "epoch": 0.5853960396039604, "grad_norm": 2.4262382984161377, "learning_rate": 1.8377251546597053e-05, "loss": 3.6746, "step": 10879 }, { "epoch": 0.5854498493327593, "grad_norm": 3.6726725101470947, "learning_rate": 1.83731764240281e-05, "loss": 3.5181, "step": 10880 }, { "epoch": 0.5855036590615583, "grad_norm": 2.2166945934295654, "learning_rate": 1.836910149083593e-05, "loss": 4.096, "step": 10881 }, { "epoch": 0.5855574687903573, "grad_norm": 2.199582576751709, "learning_rate": 1.836502674713702e-05, "loss": 4.6168, "step": 10882 }, { "epoch": 0.5856112785191563, "grad_norm": 2.115891218185425, "learning_rate": 1.8360952193047795e-05, "loss": 4.2954, "step": 10883 }, { "epoch": 0.5856650882479553, "grad_norm": 2.262962818145752, "learning_rate": 1.8356877828684693e-05, "loss": 3.713, "step": 10884 }, { "epoch": 0.5857188979767542, "grad_norm": 2.5981252193450928, "learning_rate": 1.835280365416416e-05, "loss": 3.6939, "step": 10885 }, { "epoch": 0.5857727077055531, "grad_norm": 2.174666166305542, "learning_rate": 1.834872966960262e-05, "loss": 3.8761, "step": 10886 }, { "epoch": 0.5858265174343521, "grad_norm": 2.9592339992523193, "learning_rate": 1.8344655875116505e-05, "loss": 4.1377, "step": 10887 }, { "epoch": 0.5858803271631511, "grad_norm": 1.3196144104003906, "learning_rate": 1.8340582270822216e-05, "loss": 4.7626, "step": 10888 }, { "epoch": 0.5859341368919501, "grad_norm": 2.1420040130615234, "learning_rate": 1.8336508856836166e-05, "loss": 3.8705, "step": 10889 }, { "epoch": 0.585987946620749, "grad_norm": 2.3172287940979004, "learning_rate": 1.833243563327478e-05, "loss": 4.5335, "step": 10890 }, { "epoch": 0.586041756349548, "grad_norm": 2.951850414276123, "learning_rate": 1.8328362600254447e-05, "loss": 3.6579, "step": 10891 }, { "epoch": 0.586095566078347, "grad_norm": 3.2763075828552246, "learning_rate": 1.8324289757891562e-05, "loss": 3.9979, "step": 10892 }, { "epoch": 0.5861493758071459, "grad_norm": 2.656339168548584, "learning_rate": 1.8320217106302528e-05, "loss": 3.8846, "step": 10893 }, { "epoch": 0.5862031855359449, "grad_norm": 3.153287887573242, "learning_rate": 1.831614464560372e-05, "loss": 3.5616, "step": 10894 }, { "epoch": 0.5862569952647438, "grad_norm": 2.0933523178100586, "learning_rate": 1.8312072375911525e-05, "loss": 4.109, "step": 10895 }, { "epoch": 0.5863108049935428, "grad_norm": 2.062981128692627, "learning_rate": 1.8308000297342305e-05, "loss": 4.299, "step": 10896 }, { "epoch": 0.5863646147223418, "grad_norm": 2.929649591445923, "learning_rate": 1.830392841001244e-05, "loss": 4.3776, "step": 10897 }, { "epoch": 0.5864184244511408, "grad_norm": 1.772565245628357, "learning_rate": 1.8299856714038292e-05, "loss": 3.8315, "step": 10898 }, { "epoch": 0.5864722341799398, "grad_norm": 2.9684202671051025, "learning_rate": 1.8295785209536213e-05, "loss": 3.9726, "step": 10899 }, { "epoch": 0.5865260439087387, "grad_norm": 1.856955885887146, "learning_rate": 1.8291713896622564e-05, "loss": 4.4475, "step": 10900 }, { "epoch": 0.5865798536375376, "grad_norm": 2.8961169719696045, "learning_rate": 1.8287642775413688e-05, "loss": 4.1053, "step": 10901 }, { "epoch": 0.5866336633663366, "grad_norm": 1.7263745069503784, "learning_rate": 1.8283571846025936e-05, "loss": 3.731, "step": 10902 }, { "epoch": 0.5866874730951356, "grad_norm": 1.3814412355422974, "learning_rate": 1.8279501108575627e-05, "loss": 4.2812, "step": 10903 }, { "epoch": 0.5867412828239346, "grad_norm": 2.933621644973755, "learning_rate": 1.8275430563179098e-05, "loss": 3.6214, "step": 10904 }, { "epoch": 0.5867950925527335, "grad_norm": 2.4491231441497803, "learning_rate": 1.827136020995268e-05, "loss": 3.9703, "step": 10905 }, { "epoch": 0.5868489022815325, "grad_norm": 2.1833181381225586, "learning_rate": 1.826729004901269e-05, "loss": 3.7122, "step": 10906 }, { "epoch": 0.5869027120103315, "grad_norm": 3.4206230640411377, "learning_rate": 1.8263220080475434e-05, "loss": 3.6081, "step": 10907 }, { "epoch": 0.5869565217391305, "grad_norm": 3.141455888748169, "learning_rate": 1.825915030445724e-05, "loss": 3.454, "step": 10908 }, { "epoch": 0.5870103314679294, "grad_norm": 2.2522542476654053, "learning_rate": 1.825508072107439e-05, "loss": 4.3625, "step": 10909 }, { "epoch": 0.5870641411967283, "grad_norm": 3.3117947578430176, "learning_rate": 1.8251011330443205e-05, "loss": 3.7055, "step": 10910 }, { "epoch": 0.5871179509255273, "grad_norm": 3.0507242679595947, "learning_rate": 1.8246942132679957e-05, "loss": 3.6426, "step": 10911 }, { "epoch": 0.5871717606543263, "grad_norm": 2.606037139892578, "learning_rate": 1.824287312790093e-05, "loss": 3.4076, "step": 10912 }, { "epoch": 0.5872255703831253, "grad_norm": 2.130016326904297, "learning_rate": 1.823880431622242e-05, "loss": 4.392, "step": 10913 }, { "epoch": 0.5872793801119243, "grad_norm": 2.6359407901763916, "learning_rate": 1.8234735697760703e-05, "loss": 4.1288, "step": 10914 }, { "epoch": 0.5873331898407232, "grad_norm": 1.3342424631118774, "learning_rate": 1.823066727263203e-05, "loss": 4.3587, "step": 10915 }, { "epoch": 0.5873869995695221, "grad_norm": 2.664105176925659, "learning_rate": 1.822659904095269e-05, "loss": 4.1418, "step": 10916 }, { "epoch": 0.5874408092983211, "grad_norm": 2.2121143341064453, "learning_rate": 1.8222531002838935e-05, "loss": 4.0446, "step": 10917 }, { "epoch": 0.5874946190271201, "grad_norm": 1.679284691810608, "learning_rate": 1.8218463158407007e-05, "loss": 4.6026, "step": 10918 }, { "epoch": 0.5875484287559191, "grad_norm": 2.982862949371338, "learning_rate": 1.8214395507773164e-05, "loss": 4.199, "step": 10919 }, { "epoch": 0.587602238484718, "grad_norm": 3.0079338550567627, "learning_rate": 1.8210328051053644e-05, "loss": 3.8041, "step": 10920 }, { "epoch": 0.587656048213517, "grad_norm": 3.5671916007995605, "learning_rate": 1.8206260788364687e-05, "loss": 4.0783, "step": 10921 }, { "epoch": 0.587709857942316, "grad_norm": 2.208683967590332, "learning_rate": 1.8202193719822525e-05, "loss": 4.3938, "step": 10922 }, { "epoch": 0.587763667671115, "grad_norm": 2.7095999717712402, "learning_rate": 1.8198126845543374e-05, "loss": 3.3952, "step": 10923 }, { "epoch": 0.5878174773999139, "grad_norm": 2.6021831035614014, "learning_rate": 1.8194060165643473e-05, "loss": 2.6759, "step": 10924 }, { "epoch": 0.5878712871287128, "grad_norm": 2.987809896469116, "learning_rate": 1.8189993680239032e-05, "loss": 4.0759, "step": 10925 }, { "epoch": 0.5879250968575118, "grad_norm": 3.2321557998657227, "learning_rate": 1.8185927389446246e-05, "loss": 4.1697, "step": 10926 }, { "epoch": 0.5879789065863108, "grad_norm": 2.0793981552124023, "learning_rate": 1.8181861293381326e-05, "loss": 4.2753, "step": 10927 }, { "epoch": 0.5880327163151098, "grad_norm": 1.314822793006897, "learning_rate": 1.8177795392160473e-05, "loss": 4.3143, "step": 10928 }, { "epoch": 0.5880865260439088, "grad_norm": 1.3371411561965942, "learning_rate": 1.817372968589988e-05, "loss": 4.3253, "step": 10929 }, { "epoch": 0.5881403357727077, "grad_norm": 1.8534297943115234, "learning_rate": 1.816966417471573e-05, "loss": 3.8689, "step": 10930 }, { "epoch": 0.5881941455015067, "grad_norm": 1.88290274143219, "learning_rate": 1.8165598858724203e-05, "loss": 4.4019, "step": 10931 }, { "epoch": 0.5882479552303056, "grad_norm": 2.416398763656616, "learning_rate": 1.8161533738041487e-05, "loss": 3.9115, "step": 10932 }, { "epoch": 0.5883017649591046, "grad_norm": 1.528572916984558, "learning_rate": 1.8157468812783745e-05, "loss": 3.8033, "step": 10933 }, { "epoch": 0.5883555746879036, "grad_norm": 1.0989413261413574, "learning_rate": 1.815340408306713e-05, "loss": 4.4066, "step": 10934 }, { "epoch": 0.5884093844167025, "grad_norm": 2.732391357421875, "learning_rate": 1.8149339549007816e-05, "loss": 3.5168, "step": 10935 }, { "epoch": 0.5884631941455015, "grad_norm": 2.9473161697387695, "learning_rate": 1.8145275210721952e-05, "loss": 4.1897, "step": 10936 }, { "epoch": 0.5885170038743005, "grad_norm": 1.6701499223709106, "learning_rate": 1.8141211068325688e-05, "loss": 3.7266, "step": 10937 }, { "epoch": 0.5885708136030995, "grad_norm": 3.7544806003570557, "learning_rate": 1.813714712193515e-05, "loss": 2.7883, "step": 10938 }, { "epoch": 0.5886246233318984, "grad_norm": 2.215759038925171, "learning_rate": 1.8133083371666505e-05, "loss": 4.0214, "step": 10939 }, { "epoch": 0.5886784330606973, "grad_norm": 2.9520387649536133, "learning_rate": 1.8129019817635863e-05, "loss": 3.5315, "step": 10940 }, { "epoch": 0.5887322427894963, "grad_norm": 3.1183223724365234, "learning_rate": 1.812495645995935e-05, "loss": 3.1676, "step": 10941 }, { "epoch": 0.5887860525182953, "grad_norm": 2.0092995166778564, "learning_rate": 1.8120893298753093e-05, "loss": 4.3827, "step": 10942 }, { "epoch": 0.5888398622470943, "grad_norm": 2.570919990539551, "learning_rate": 1.81168303341332e-05, "loss": 4.398, "step": 10943 }, { "epoch": 0.5888936719758933, "grad_norm": 1.958999514579773, "learning_rate": 1.8112767566215786e-05, "loss": 4.1392, "step": 10944 }, { "epoch": 0.5889474817046922, "grad_norm": 2.5636885166168213, "learning_rate": 1.810870499511695e-05, "loss": 4.1981, "step": 10945 }, { "epoch": 0.5890012914334912, "grad_norm": 2.5773065090179443, "learning_rate": 1.8104642620952784e-05, "loss": 4.2773, "step": 10946 }, { "epoch": 0.5890551011622901, "grad_norm": 2.6523594856262207, "learning_rate": 1.810058044383939e-05, "loss": 4.2107, "step": 10947 }, { "epoch": 0.5891089108910891, "grad_norm": 3.1425423622131348, "learning_rate": 1.809651846389285e-05, "loss": 3.2987, "step": 10948 }, { "epoch": 0.5891627206198881, "grad_norm": 1.5713131427764893, "learning_rate": 1.8092456681229246e-05, "loss": 3.7715, "step": 10949 }, { "epoch": 0.589216530348687, "grad_norm": 2.1821017265319824, "learning_rate": 1.808839509596465e-05, "loss": 4.0912, "step": 10950 }, { "epoch": 0.589270340077486, "grad_norm": 2.4613683223724365, "learning_rate": 1.808433370821513e-05, "loss": 3.9326, "step": 10951 }, { "epoch": 0.589324149806285, "grad_norm": 1.4778450727462769, "learning_rate": 1.8080272518096752e-05, "loss": 4.3503, "step": 10952 }, { "epoch": 0.589377959535084, "grad_norm": 3.011157989501953, "learning_rate": 1.8076211525725573e-05, "loss": 3.7906, "step": 10953 }, { "epoch": 0.589431769263883, "grad_norm": 2.287724256515503, "learning_rate": 1.807215073121764e-05, "loss": 3.9746, "step": 10954 }, { "epoch": 0.5894855789926818, "grad_norm": 1.5392169952392578, "learning_rate": 1.8068090134689013e-05, "loss": 3.9938, "step": 10955 }, { "epoch": 0.5895393887214808, "grad_norm": 1.6646528244018555, "learning_rate": 1.8064029736255733e-05, "loss": 4.0683, "step": 10956 }, { "epoch": 0.5895931984502798, "grad_norm": 3.3490543365478516, "learning_rate": 1.805996953603382e-05, "loss": 4.1459, "step": 10957 }, { "epoch": 0.5896470081790788, "grad_norm": 1.1898829936981201, "learning_rate": 1.8055909534139304e-05, "loss": 4.4109, "step": 10958 }, { "epoch": 0.5897008179078778, "grad_norm": 2.1105411052703857, "learning_rate": 1.8051849730688225e-05, "loss": 4.0345, "step": 10959 }, { "epoch": 0.5897546276366767, "grad_norm": 3.4087016582489014, "learning_rate": 1.804779012579659e-05, "loss": 4.0474, "step": 10960 }, { "epoch": 0.5898084373654757, "grad_norm": 2.304628849029541, "learning_rate": 1.8043730719580408e-05, "loss": 4.2161, "step": 10961 }, { "epoch": 0.5898622470942746, "grad_norm": 2.6482043266296387, "learning_rate": 1.8039671512155697e-05, "loss": 3.7522, "step": 10962 }, { "epoch": 0.5899160568230736, "grad_norm": 3.671583414077759, "learning_rate": 1.8035612503638462e-05, "loss": 3.7727, "step": 10963 }, { "epoch": 0.5899698665518726, "grad_norm": 3.1164374351501465, "learning_rate": 1.8031553694144683e-05, "loss": 3.828, "step": 10964 }, { "epoch": 0.5900236762806715, "grad_norm": 2.3354475498199463, "learning_rate": 1.8027495083790352e-05, "loss": 4.1788, "step": 10965 }, { "epoch": 0.5900774860094705, "grad_norm": 2.2050857543945312, "learning_rate": 1.802343667269146e-05, "loss": 3.2192, "step": 10966 }, { "epoch": 0.5901312957382695, "grad_norm": 4.616951942443848, "learning_rate": 1.8019378460963982e-05, "loss": 4.2371, "step": 10967 }, { "epoch": 0.5901851054670685, "grad_norm": 1.5364584922790527, "learning_rate": 1.8015320448723894e-05, "loss": 4.2176, "step": 10968 }, { "epoch": 0.5902389151958675, "grad_norm": 4.031529903411865, "learning_rate": 1.8011262636087155e-05, "loss": 4.1754, "step": 10969 }, { "epoch": 0.5902927249246663, "grad_norm": 2.079106330871582, "learning_rate": 1.800720502316974e-05, "loss": 3.9629, "step": 10970 }, { "epoch": 0.5903465346534653, "grad_norm": 3.084233522415161, "learning_rate": 1.8003147610087602e-05, "loss": 4.479, "step": 10971 }, { "epoch": 0.5904003443822643, "grad_norm": 2.270657777786255, "learning_rate": 1.799909039695668e-05, "loss": 4.3507, "step": 10972 }, { "epoch": 0.5904541541110633, "grad_norm": 2.396044969558716, "learning_rate": 1.7995033383892923e-05, "loss": 4.4972, "step": 10973 }, { "epoch": 0.5905079638398623, "grad_norm": 2.516598701477051, "learning_rate": 1.7990976571012264e-05, "loss": 4.2063, "step": 10974 }, { "epoch": 0.5905617735686612, "grad_norm": 2.309774160385132, "learning_rate": 1.7986919958430652e-05, "loss": 3.9028, "step": 10975 }, { "epoch": 0.5906155832974602, "grad_norm": 3.0288636684417725, "learning_rate": 1.7982863546264e-05, "loss": 4.1746, "step": 10976 }, { "epoch": 0.5906693930262591, "grad_norm": 3.0916993618011475, "learning_rate": 1.7978807334628234e-05, "loss": 3.6552, "step": 10977 }, { "epoch": 0.5907232027550581, "grad_norm": 2.7583649158477783, "learning_rate": 1.7974751323639284e-05, "loss": 4.2312, "step": 10978 }, { "epoch": 0.5907770124838571, "grad_norm": 1.9007848501205444, "learning_rate": 1.7970695513413026e-05, "loss": 4.1436, "step": 10979 }, { "epoch": 0.590830822212656, "grad_norm": 1.9902065992355347, "learning_rate": 1.7966639904065392e-05, "loss": 4.1376, "step": 10980 }, { "epoch": 0.590884631941455, "grad_norm": 3.589531898498535, "learning_rate": 1.796258449571227e-05, "loss": 3.4991, "step": 10981 }, { "epoch": 0.590938441670254, "grad_norm": 1.6149059534072876, "learning_rate": 1.795852928846955e-05, "loss": 4.1439, "step": 10982 }, { "epoch": 0.590992251399053, "grad_norm": 1.8634753227233887, "learning_rate": 1.7954474282453132e-05, "loss": 4.4481, "step": 10983 }, { "epoch": 0.591046061127852, "grad_norm": 2.021193265914917, "learning_rate": 1.7950419477778884e-05, "loss": 3.6846, "step": 10984 }, { "epoch": 0.5910998708566508, "grad_norm": 3.288877248764038, "learning_rate": 1.7946364874562683e-05, "loss": 4.1225, "step": 10985 }, { "epoch": 0.5911536805854498, "grad_norm": 2.44374418258667, "learning_rate": 1.7942310472920416e-05, "loss": 4.2343, "step": 10986 }, { "epoch": 0.5912074903142488, "grad_norm": 2.031728982925415, "learning_rate": 1.7938256272967924e-05, "loss": 3.7163, "step": 10987 }, { "epoch": 0.5912613000430478, "grad_norm": 2.113400459289551, "learning_rate": 1.793420227482107e-05, "loss": 4.4009, "step": 10988 }, { "epoch": 0.5913151097718468, "grad_norm": 1.8751190900802612, "learning_rate": 1.793014847859571e-05, "loss": 4.4602, "step": 10989 }, { "epoch": 0.5913689195006457, "grad_norm": 4.270870208740234, "learning_rate": 1.7926094884407695e-05, "loss": 3.2959, "step": 10990 }, { "epoch": 0.5914227292294447, "grad_norm": 2.0111966133117676, "learning_rate": 1.7922041492372864e-05, "loss": 3.9156, "step": 10991 }, { "epoch": 0.5914765389582437, "grad_norm": 2.5393238067626953, "learning_rate": 1.791798830260704e-05, "loss": 3.5859, "step": 10992 }, { "epoch": 0.5915303486870426, "grad_norm": 3.2532849311828613, "learning_rate": 1.791393531522607e-05, "loss": 4.2727, "step": 10993 }, { "epoch": 0.5915841584158416, "grad_norm": 2.170318603515625, "learning_rate": 1.7909882530345773e-05, "loss": 3.8627, "step": 10994 }, { "epoch": 0.5916379681446405, "grad_norm": 1.870697021484375, "learning_rate": 1.790582994808196e-05, "loss": 4.3876, "step": 10995 }, { "epoch": 0.5916917778734395, "grad_norm": 2.431476593017578, "learning_rate": 1.7901777568550445e-05, "loss": 4.0038, "step": 10996 }, { "epoch": 0.5917455876022385, "grad_norm": 2.4476847648620605, "learning_rate": 1.7897725391867028e-05, "loss": 4.1616, "step": 10997 }, { "epoch": 0.5917993973310375, "grad_norm": 1.3033314943313599, "learning_rate": 1.7893673418147525e-05, "loss": 4.1795, "step": 10998 }, { "epoch": 0.5918532070598365, "grad_norm": 3.5620169639587402, "learning_rate": 1.788962164750772e-05, "loss": 3.6653, "step": 10999 }, { "epoch": 0.5919070167886353, "grad_norm": 2.0335052013397217, "learning_rate": 1.7885570080063396e-05, "loss": 4.2706, "step": 11000 }, { "epoch": 0.5919608265174343, "grad_norm": 2.9406521320343018, "learning_rate": 1.7881518715930364e-05, "loss": 3.9526, "step": 11001 }, { "epoch": 0.5920146362462333, "grad_norm": 2.877809524536133, "learning_rate": 1.7877467555224363e-05, "loss": 4.6055, "step": 11002 }, { "epoch": 0.5920684459750323, "grad_norm": 2.077646255493164, "learning_rate": 1.7873416598061186e-05, "loss": 3.4941, "step": 11003 }, { "epoch": 0.5921222557038313, "grad_norm": 2.161350965499878, "learning_rate": 1.7869365844556595e-05, "loss": 3.9794, "step": 11004 }, { "epoch": 0.5921760654326302, "grad_norm": 3.466215133666992, "learning_rate": 1.7865315294826346e-05, "loss": 4.4668, "step": 11005 }, { "epoch": 0.5922298751614292, "grad_norm": 1.6783099174499512, "learning_rate": 1.78612649489862e-05, "loss": 4.1204, "step": 11006 }, { "epoch": 0.5922836848902282, "grad_norm": 1.5769782066345215, "learning_rate": 1.78572148071519e-05, "loss": 4.4806, "step": 11007 }, { "epoch": 0.5923374946190271, "grad_norm": 2.7480576038360596, "learning_rate": 1.7853164869439183e-05, "loss": 3.7261, "step": 11008 }, { "epoch": 0.592391304347826, "grad_norm": 3.2317211627960205, "learning_rate": 1.7849115135963807e-05, "loss": 3.9242, "step": 11009 }, { "epoch": 0.592445114076625, "grad_norm": 1.9367355108261108, "learning_rate": 1.7845065606841472e-05, "loss": 4.6949, "step": 11010 }, { "epoch": 0.592498923805424, "grad_norm": 4.069579124450684, "learning_rate": 1.7841016282187923e-05, "loss": 2.8666, "step": 11011 }, { "epoch": 0.592552733534223, "grad_norm": 3.0313830375671387, "learning_rate": 1.7836967162118872e-05, "loss": 4.1234, "step": 11012 }, { "epoch": 0.592606543263022, "grad_norm": 2.230285167694092, "learning_rate": 1.783291824675003e-05, "loss": 3.9396, "step": 11013 }, { "epoch": 0.592660352991821, "grad_norm": 2.411578416824341, "learning_rate": 1.782886953619711e-05, "loss": 3.7636, "step": 11014 }, { "epoch": 0.5927141627206199, "grad_norm": 1.3644673824310303, "learning_rate": 1.7824821030575812e-05, "loss": 4.6499, "step": 11015 }, { "epoch": 0.5927679724494188, "grad_norm": 3.0668859481811523, "learning_rate": 1.7820772730001824e-05, "loss": 4.1934, "step": 11016 }, { "epoch": 0.5928217821782178, "grad_norm": 2.1991496086120605, "learning_rate": 1.7816724634590854e-05, "loss": 4.2171, "step": 11017 }, { "epoch": 0.5928755919070168, "grad_norm": 1.611759066581726, "learning_rate": 1.7812676744458566e-05, "loss": 4.3424, "step": 11018 }, { "epoch": 0.5929294016358158, "grad_norm": 2.516334295272827, "learning_rate": 1.7808629059720644e-05, "loss": 4.4326, "step": 11019 }, { "epoch": 0.5929832113646147, "grad_norm": 2.4698431491851807, "learning_rate": 1.7804581580492757e-05, "loss": 4.1651, "step": 11020 }, { "epoch": 0.5930370210934137, "grad_norm": 2.4535441398620605, "learning_rate": 1.780053430689058e-05, "loss": 4.1433, "step": 11021 }, { "epoch": 0.5930908308222127, "grad_norm": 2.474560022354126, "learning_rate": 1.7796487239029773e-05, "loss": 3.9638, "step": 11022 }, { "epoch": 0.5931446405510116, "grad_norm": 2.3567543029785156, "learning_rate": 1.7792440377025975e-05, "loss": 4.5607, "step": 11023 }, { "epoch": 0.5931984502798106, "grad_norm": 1.4155102968215942, "learning_rate": 1.7788393720994863e-05, "loss": 4.5349, "step": 11024 }, { "epoch": 0.5932522600086095, "grad_norm": 2.0721077919006348, "learning_rate": 1.7784347271052044e-05, "loss": 4.3146, "step": 11025 }, { "epoch": 0.5933060697374085, "grad_norm": 1.8049577474594116, "learning_rate": 1.778030102731318e-05, "loss": 4.618, "step": 11026 }, { "epoch": 0.5933598794662075, "grad_norm": 2.5093822479248047, "learning_rate": 1.7776254989893885e-05, "loss": 4.0389, "step": 11027 }, { "epoch": 0.5934136891950065, "grad_norm": 2.971470832824707, "learning_rate": 1.77722091589098e-05, "loss": 3.8549, "step": 11028 }, { "epoch": 0.5934674989238055, "grad_norm": 3.315077781677246, "learning_rate": 1.7768163534476535e-05, "loss": 3.5531, "step": 11029 }, { "epoch": 0.5935213086526044, "grad_norm": 2.84230899810791, "learning_rate": 1.7764118116709706e-05, "loss": 3.8535, "step": 11030 }, { "epoch": 0.5935751183814033, "grad_norm": 3.3227827548980713, "learning_rate": 1.7760072905724914e-05, "loss": 4.0446, "step": 11031 }, { "epoch": 0.5936289281102023, "grad_norm": 1.5328798294067383, "learning_rate": 1.775602790163778e-05, "loss": 4.4268, "step": 11032 }, { "epoch": 0.5936827378390013, "grad_norm": 1.7867481708526611, "learning_rate": 1.775198310456387e-05, "loss": 4.6146, "step": 11033 }, { "epoch": 0.5937365475678003, "grad_norm": 2.8629519939422607, "learning_rate": 1.7747938514618795e-05, "loss": 3.0835, "step": 11034 }, { "epoch": 0.5937903572965992, "grad_norm": 3.390326738357544, "learning_rate": 1.774389413191813e-05, "loss": 3.0701, "step": 11035 }, { "epoch": 0.5938441670253982, "grad_norm": 1.8077088594436646, "learning_rate": 1.7739849956577448e-05, "loss": 4.2797, "step": 11036 }, { "epoch": 0.5938979767541972, "grad_norm": 2.273280382156372, "learning_rate": 1.773580598871233e-05, "loss": 4.0398, "step": 11037 }, { "epoch": 0.5939517864829962, "grad_norm": 2.1922566890716553, "learning_rate": 1.7731762228438343e-05, "loss": 4.1308, "step": 11038 }, { "epoch": 0.594005596211795, "grad_norm": 2.395472288131714, "learning_rate": 1.7727718675871037e-05, "loss": 3.8292, "step": 11039 }, { "epoch": 0.594059405940594, "grad_norm": 1.5783284902572632, "learning_rate": 1.7723675331125978e-05, "loss": 3.9128, "step": 11040 }, { "epoch": 0.594113215669393, "grad_norm": 4.088565349578857, "learning_rate": 1.7719632194318702e-05, "loss": 3.4262, "step": 11041 }, { "epoch": 0.594167025398192, "grad_norm": 1.4290680885314941, "learning_rate": 1.7715589265564758e-05, "loss": 4.6122, "step": 11042 }, { "epoch": 0.594220835126991, "grad_norm": 2.860508441925049, "learning_rate": 1.7711546544979674e-05, "loss": 2.9555, "step": 11043 }, { "epoch": 0.59427464485579, "grad_norm": 2.0564963817596436, "learning_rate": 1.770750403267899e-05, "loss": 4.5509, "step": 11044 }, { "epoch": 0.5943284545845889, "grad_norm": 2.0144741535186768, "learning_rate": 1.7703461728778228e-05, "loss": 4.1491, "step": 11045 }, { "epoch": 0.5943822643133878, "grad_norm": 2.2027037143707275, "learning_rate": 1.7699419633392905e-05, "loss": 3.9084, "step": 11046 }, { "epoch": 0.5944360740421868, "grad_norm": 3.0700671672821045, "learning_rate": 1.7695377746638537e-05, "loss": 4.2748, "step": 11047 }, { "epoch": 0.5944898837709858, "grad_norm": 1.940629482269287, "learning_rate": 1.7691336068630614e-05, "loss": 4.6292, "step": 11048 }, { "epoch": 0.5945436934997848, "grad_norm": 4.132382392883301, "learning_rate": 1.7687294599484654e-05, "loss": 4.0232, "step": 11049 }, { "epoch": 0.5945975032285837, "grad_norm": 2.5073368549346924, "learning_rate": 1.7683253339316146e-05, "loss": 3.831, "step": 11050 }, { "epoch": 0.5946513129573827, "grad_norm": 2.089885950088501, "learning_rate": 1.7679212288240573e-05, "loss": 3.9401, "step": 11051 }, { "epoch": 0.5947051226861817, "grad_norm": 2.2537007331848145, "learning_rate": 1.7675171446373428e-05, "loss": 4.1935, "step": 11052 }, { "epoch": 0.5947589324149807, "grad_norm": 1.3384814262390137, "learning_rate": 1.767113081383018e-05, "loss": 4.309, "step": 11053 }, { "epoch": 0.5948127421437795, "grad_norm": 2.421846389770508, "learning_rate": 1.76670903907263e-05, "loss": 3.6812, "step": 11054 }, { "epoch": 0.5948665518725785, "grad_norm": 1.9065035581588745, "learning_rate": 1.7663050177177267e-05, "loss": 4.3573, "step": 11055 }, { "epoch": 0.5949203616013775, "grad_norm": 3.132453203201294, "learning_rate": 1.7659010173298508e-05, "loss": 4.0058, "step": 11056 }, { "epoch": 0.5949741713301765, "grad_norm": 1.8079150915145874, "learning_rate": 1.7654970379205498e-05, "loss": 4.0172, "step": 11057 }, { "epoch": 0.5950279810589755, "grad_norm": 2.6562483310699463, "learning_rate": 1.765093079501368e-05, "loss": 4.0578, "step": 11058 }, { "epoch": 0.5950817907877745, "grad_norm": 1.3374725580215454, "learning_rate": 1.7646891420838485e-05, "loss": 4.5903, "step": 11059 }, { "epoch": 0.5951356005165734, "grad_norm": 1.9429943561553955, "learning_rate": 1.7642852256795367e-05, "loss": 4.3538, "step": 11060 }, { "epoch": 0.5951894102453723, "grad_norm": 3.717843532562256, "learning_rate": 1.7638813302999742e-05, "loss": 3.7653, "step": 11061 }, { "epoch": 0.5952432199741713, "grad_norm": 1.7749273777008057, "learning_rate": 1.7634774559567032e-05, "loss": 4.2017, "step": 11062 }, { "epoch": 0.5952970297029703, "grad_norm": 2.1699013710021973, "learning_rate": 1.7630736026612653e-05, "loss": 4.3299, "step": 11063 }, { "epoch": 0.5953508394317693, "grad_norm": 2.118914842605591, "learning_rate": 1.7626697704252015e-05, "loss": 4.079, "step": 11064 }, { "epoch": 0.5954046491605682, "grad_norm": 1.0926921367645264, "learning_rate": 1.762265959260053e-05, "loss": 4.6544, "step": 11065 }, { "epoch": 0.5954584588893672, "grad_norm": 2.7190258502960205, "learning_rate": 1.761862169177359e-05, "loss": 3.6932, "step": 11066 }, { "epoch": 0.5955122686181662, "grad_norm": 2.575005531311035, "learning_rate": 1.761458400188658e-05, "loss": 3.5257, "step": 11067 }, { "epoch": 0.5955660783469652, "grad_norm": 3.2695116996765137, "learning_rate": 1.7610546523054906e-05, "loss": 3.7352, "step": 11068 }, { "epoch": 0.595619888075764, "grad_norm": 1.6770881414413452, "learning_rate": 1.760650925539393e-05, "loss": 4.2964, "step": 11069 }, { "epoch": 0.595673697804563, "grad_norm": 1.9976366758346558, "learning_rate": 1.7602472199019047e-05, "loss": 4.2727, "step": 11070 }, { "epoch": 0.595727507533362, "grad_norm": 3.2276997566223145, "learning_rate": 1.7598435354045596e-05, "loss": 3.5657, "step": 11071 }, { "epoch": 0.595781317262161, "grad_norm": 1.57398521900177, "learning_rate": 1.759439872058896e-05, "loss": 4.2128, "step": 11072 }, { "epoch": 0.59583512699096, "grad_norm": 1.6279525756835938, "learning_rate": 1.7590362298764492e-05, "loss": 3.9928, "step": 11073 }, { "epoch": 0.595888936719759, "grad_norm": 1.93950617313385, "learning_rate": 1.7586326088687534e-05, "loss": 3.5446, "step": 11074 }, { "epoch": 0.5959427464485579, "grad_norm": 1.5397862195968628, "learning_rate": 1.758229009047344e-05, "loss": 4.0835, "step": 11075 }, { "epoch": 0.5959965561773569, "grad_norm": 4.244345188140869, "learning_rate": 1.7578254304237546e-05, "loss": 3.2902, "step": 11076 }, { "epoch": 0.5960503659061558, "grad_norm": 2.299541711807251, "learning_rate": 1.757421873009517e-05, "loss": 4.2151, "step": 11077 }, { "epoch": 0.5961041756349548, "grad_norm": 2.261207342147827, "learning_rate": 1.7570183368161675e-05, "loss": 3.152, "step": 11078 }, { "epoch": 0.5961579853637538, "grad_norm": 2.167954444885254, "learning_rate": 1.7566148218552335e-05, "loss": 3.6494, "step": 11079 }, { "epoch": 0.5962117950925527, "grad_norm": 2.815371513366699, "learning_rate": 1.7562113281382486e-05, "loss": 4.3355, "step": 11080 }, { "epoch": 0.5962656048213517, "grad_norm": 1.9156897068023682, "learning_rate": 1.755807855676744e-05, "loss": 4.3378, "step": 11081 }, { "epoch": 0.5963194145501507, "grad_norm": 2.4906959533691406, "learning_rate": 1.7554044044822482e-05, "loss": 4.2652, "step": 11082 }, { "epoch": 0.5963732242789497, "grad_norm": 2.8199799060821533, "learning_rate": 1.7550009745662925e-05, "loss": 4.4289, "step": 11083 }, { "epoch": 0.5964270340077485, "grad_norm": 2.5475518703460693, "learning_rate": 1.7545975659404053e-05, "loss": 3.9876, "step": 11084 }, { "epoch": 0.5964808437365475, "grad_norm": 3.443225383758545, "learning_rate": 1.7541941786161153e-05, "loss": 3.653, "step": 11085 }, { "epoch": 0.5965346534653465, "grad_norm": 2.8127293586730957, "learning_rate": 1.753790812604949e-05, "loss": 4.0646, "step": 11086 }, { "epoch": 0.5965884631941455, "grad_norm": 1.574976921081543, "learning_rate": 1.753387467918434e-05, "loss": 4.4724, "step": 11087 }, { "epoch": 0.5966422729229445, "grad_norm": 2.874431848526001, "learning_rate": 1.7529841445680973e-05, "loss": 4.0649, "step": 11088 }, { "epoch": 0.5966960826517435, "grad_norm": 1.3890900611877441, "learning_rate": 1.7525808425654645e-05, "loss": 4.5739, "step": 11089 }, { "epoch": 0.5967498923805424, "grad_norm": 1.3978596925735474, "learning_rate": 1.7521775619220604e-05, "loss": 4.5349, "step": 11090 }, { "epoch": 0.5968037021093414, "grad_norm": 2.4322409629821777, "learning_rate": 1.7517743026494104e-05, "loss": 4.1681, "step": 11091 }, { "epoch": 0.5968575118381403, "grad_norm": 2.2735190391540527, "learning_rate": 1.7513710647590385e-05, "loss": 3.9436, "step": 11092 }, { "epoch": 0.5969113215669393, "grad_norm": 2.6834895610809326, "learning_rate": 1.750967848262469e-05, "loss": 3.4335, "step": 11093 }, { "epoch": 0.5969651312957382, "grad_norm": 2.608546257019043, "learning_rate": 1.7505646531712227e-05, "loss": 3.7356, "step": 11094 }, { "epoch": 0.5970189410245372, "grad_norm": 2.414368152618408, "learning_rate": 1.7501614794968224e-05, "loss": 4.2016, "step": 11095 }, { "epoch": 0.5970727507533362, "grad_norm": 2.2733166217803955, "learning_rate": 1.749758327250791e-05, "loss": 3.954, "step": 11096 }, { "epoch": 0.5971265604821352, "grad_norm": 3.0974843502044678, "learning_rate": 1.7493551964446487e-05, "loss": 3.8429, "step": 11097 }, { "epoch": 0.5971803702109342, "grad_norm": 3.301244020462036, "learning_rate": 1.748952087089915e-05, "loss": 3.8044, "step": 11098 }, { "epoch": 0.5972341799397332, "grad_norm": 1.2516268491744995, "learning_rate": 1.7485489991981112e-05, "loss": 4.4111, "step": 11099 }, { "epoch": 0.597287989668532, "grad_norm": 1.7081845998764038, "learning_rate": 1.7481459327807558e-05, "loss": 4.1825, "step": 11100 }, { "epoch": 0.597341799397331, "grad_norm": 2.8658132553100586, "learning_rate": 1.747742887849368e-05, "loss": 3.7811, "step": 11101 }, { "epoch": 0.59739560912613, "grad_norm": 2.145287275314331, "learning_rate": 1.7473398644154644e-05, "loss": 3.9017, "step": 11102 }, { "epoch": 0.597449418854929, "grad_norm": 3.0911762714385986, "learning_rate": 1.746936862490563e-05, "loss": 4.3109, "step": 11103 }, { "epoch": 0.597503228583728, "grad_norm": 3.220564842224121, "learning_rate": 1.746533882086181e-05, "loss": 4.1379, "step": 11104 }, { "epoch": 0.5975570383125269, "grad_norm": 2.4298694133758545, "learning_rate": 1.7461309232138334e-05, "loss": 3.9698, "step": 11105 }, { "epoch": 0.5976108480413259, "grad_norm": 2.748310089111328, "learning_rate": 1.7457279858850367e-05, "loss": 3.7435, "step": 11106 }, { "epoch": 0.5976646577701248, "grad_norm": 1.4627784490585327, "learning_rate": 1.7453250701113054e-05, "loss": 4.336, "step": 11107 }, { "epoch": 0.5977184674989238, "grad_norm": 1.8435611724853516, "learning_rate": 1.7449221759041545e-05, "loss": 3.7344, "step": 11108 }, { "epoch": 0.5977722772277227, "grad_norm": 3.380666494369507, "learning_rate": 1.7445193032750964e-05, "loss": 3.2092, "step": 11109 }, { "epoch": 0.5978260869565217, "grad_norm": 2.3768157958984375, "learning_rate": 1.744116452235644e-05, "loss": 4.1043, "step": 11110 }, { "epoch": 0.5978798966853207, "grad_norm": 1.1248669624328613, "learning_rate": 1.743713622797311e-05, "loss": 4.2929, "step": 11111 }, { "epoch": 0.5979337064141197, "grad_norm": 2.250366687774658, "learning_rate": 1.743310814971608e-05, "loss": 4.022, "step": 11112 }, { "epoch": 0.5979875161429187, "grad_norm": 1.873171329498291, "learning_rate": 1.7429080287700467e-05, "loss": 4.5905, "step": 11113 }, { "epoch": 0.5980413258717177, "grad_norm": 2.0744566917419434, "learning_rate": 1.7425052642041378e-05, "loss": 4.3256, "step": 11114 }, { "epoch": 0.5980951356005165, "grad_norm": 3.4751391410827637, "learning_rate": 1.7421025212853908e-05, "loss": 3.3303, "step": 11115 }, { "epoch": 0.5981489453293155, "grad_norm": 1.8750418424606323, "learning_rate": 1.7416998000253165e-05, "loss": 3.6373, "step": 11116 }, { "epoch": 0.5982027550581145, "grad_norm": 1.095599889755249, "learning_rate": 1.741297100435421e-05, "loss": 4.4006, "step": 11117 }, { "epoch": 0.5982565647869135, "grad_norm": 2.833402395248413, "learning_rate": 1.7408944225272138e-05, "loss": 4.0331, "step": 11118 }, { "epoch": 0.5983103745157125, "grad_norm": 2.1462550163269043, "learning_rate": 1.7404917663122023e-05, "loss": 3.755, "step": 11119 }, { "epoch": 0.5983641842445114, "grad_norm": 2.782582998275757, "learning_rate": 1.7400891318018937e-05, "loss": 3.9029, "step": 11120 }, { "epoch": 0.5984179939733104, "grad_norm": 2.2252166271209717, "learning_rate": 1.739686519007793e-05, "loss": 3.9701, "step": 11121 }, { "epoch": 0.5984718037021094, "grad_norm": 1.3415782451629639, "learning_rate": 1.739283927941407e-05, "loss": 4.5106, "step": 11122 }, { "epoch": 0.5985256134309083, "grad_norm": 2.3372793197631836, "learning_rate": 1.7388813586142406e-05, "loss": 4.0498, "step": 11123 }, { "epoch": 0.5985794231597072, "grad_norm": 1.8610535860061646, "learning_rate": 1.7384788110377982e-05, "loss": 3.7118, "step": 11124 }, { "epoch": 0.5986332328885062, "grad_norm": 2.352290391921997, "learning_rate": 1.7380762852235824e-05, "loss": 3.6272, "step": 11125 }, { "epoch": 0.5986870426173052, "grad_norm": 2.168022632598877, "learning_rate": 1.7376737811830966e-05, "loss": 4.2272, "step": 11126 }, { "epoch": 0.5987408523461042, "grad_norm": 2.9661529064178467, "learning_rate": 1.7372712989278446e-05, "loss": 3.9812, "step": 11127 }, { "epoch": 0.5987946620749032, "grad_norm": 2.346524953842163, "learning_rate": 1.736868838469327e-05, "loss": 4.2024, "step": 11128 }, { "epoch": 0.5988484718037022, "grad_norm": 2.477466344833374, "learning_rate": 1.736466399819045e-05, "loss": 4.4987, "step": 11129 }, { "epoch": 0.598902281532501, "grad_norm": 2.9350531101226807, "learning_rate": 1.7360639829885e-05, "loss": 3.7001, "step": 11130 }, { "epoch": 0.5989560912613, "grad_norm": 2.4476704597473145, "learning_rate": 1.7356615879891924e-05, "loss": 4.2482, "step": 11131 }, { "epoch": 0.599009900990099, "grad_norm": 3.16245174407959, "learning_rate": 1.7352592148326198e-05, "loss": 3.6775, "step": 11132 }, { "epoch": 0.599063710718898, "grad_norm": 2.2142369747161865, "learning_rate": 1.734856863530282e-05, "loss": 4.0886, "step": 11133 }, { "epoch": 0.599117520447697, "grad_norm": 2.186211109161377, "learning_rate": 1.734454534093677e-05, "loss": 3.7768, "step": 11134 }, { "epoch": 0.5991713301764959, "grad_norm": 1.7645127773284912, "learning_rate": 1.734052226534303e-05, "loss": 4.3265, "step": 11135 }, { "epoch": 0.5992251399052949, "grad_norm": 2.14224910736084, "learning_rate": 1.7336499408636554e-05, "loss": 4.8087, "step": 11136 }, { "epoch": 0.5992789496340939, "grad_norm": 2.395707845687866, "learning_rate": 1.7332476770932314e-05, "loss": 4.5756, "step": 11137 }, { "epoch": 0.5993327593628928, "grad_norm": 2.4680674076080322, "learning_rate": 1.7328454352345268e-05, "loss": 3.437, "step": 11138 }, { "epoch": 0.5993865690916917, "grad_norm": 3.6657989025115967, "learning_rate": 1.7324432152990366e-05, "loss": 4.0836, "step": 11139 }, { "epoch": 0.5994403788204907, "grad_norm": 1.754369854927063, "learning_rate": 1.7320410172982547e-05, "loss": 4.5051, "step": 11140 }, { "epoch": 0.5994941885492897, "grad_norm": 2.284041166305542, "learning_rate": 1.731638841243674e-05, "loss": 4.1773, "step": 11141 }, { "epoch": 0.5995479982780887, "grad_norm": 1.6925636529922485, "learning_rate": 1.7312366871467894e-05, "loss": 4.6349, "step": 11142 }, { "epoch": 0.5996018080068877, "grad_norm": 2.4573144912719727, "learning_rate": 1.7308345550190923e-05, "loss": 4.254, "step": 11143 }, { "epoch": 0.5996556177356867, "grad_norm": 2.1847498416900635, "learning_rate": 1.7304324448720747e-05, "loss": 4.1506, "step": 11144 }, { "epoch": 0.5997094274644856, "grad_norm": 2.4149420261383057, "learning_rate": 1.7300303567172278e-05, "loss": 3.6882, "step": 11145 }, { "epoch": 0.5997632371932845, "grad_norm": 2.8638880252838135, "learning_rate": 1.729628290566043e-05, "loss": 3.6878, "step": 11146 }, { "epoch": 0.5998170469220835, "grad_norm": 3.2754781246185303, "learning_rate": 1.7292262464300097e-05, "loss": 4.0411, "step": 11147 }, { "epoch": 0.5998708566508825, "grad_norm": 2.986929178237915, "learning_rate": 1.7288242243206168e-05, "loss": 4.168, "step": 11148 }, { "epoch": 0.5999246663796814, "grad_norm": 1.953820824623108, "learning_rate": 1.728422224249353e-05, "loss": 4.3361, "step": 11149 }, { "epoch": 0.5999784761084804, "grad_norm": 2.5676231384277344, "learning_rate": 1.7280202462277067e-05, "loss": 3.7938, "step": 11150 }, { "epoch": 0.6000322858372794, "grad_norm": 2.3354501724243164, "learning_rate": 1.7276182902671655e-05, "loss": 3.9633, "step": 11151 }, { "epoch": 0.6000860955660784, "grad_norm": 1.7115676403045654, "learning_rate": 1.727216356379216e-05, "loss": 4.2664, "step": 11152 }, { "epoch": 0.6001399052948773, "grad_norm": 3.1791112422943115, "learning_rate": 1.726814444575345e-05, "loss": 4.0415, "step": 11153 }, { "epoch": 0.6001937150236762, "grad_norm": 3.9282848834991455, "learning_rate": 1.7264125548670377e-05, "loss": 3.3745, "step": 11154 }, { "epoch": 0.6002475247524752, "grad_norm": 2.8859715461730957, "learning_rate": 1.7260106872657782e-05, "loss": 3.5256, "step": 11155 }, { "epoch": 0.6003013344812742, "grad_norm": 4.641772270202637, "learning_rate": 1.725608841783052e-05, "loss": 2.9118, "step": 11156 }, { "epoch": 0.6003551442100732, "grad_norm": 3.8679630756378174, "learning_rate": 1.7252070184303414e-05, "loss": 3.5044, "step": 11157 }, { "epoch": 0.6004089539388722, "grad_norm": 1.412833333015442, "learning_rate": 1.724805217219131e-05, "loss": 4.4639, "step": 11158 }, { "epoch": 0.6004627636676712, "grad_norm": 2.780029773712158, "learning_rate": 1.7244034381609027e-05, "loss": 4.2528, "step": 11159 }, { "epoch": 0.6005165733964701, "grad_norm": 2.7198874950408936, "learning_rate": 1.7240016812671366e-05, "loss": 4.7372, "step": 11160 }, { "epoch": 0.600570383125269, "grad_norm": 2.8694963455200195, "learning_rate": 1.7235999465493166e-05, "loss": 4.1558, "step": 11161 }, { "epoch": 0.600624192854068, "grad_norm": 3.05135178565979, "learning_rate": 1.723198234018922e-05, "loss": 4.4509, "step": 11162 }, { "epoch": 0.600678002582867, "grad_norm": 2.7089855670928955, "learning_rate": 1.722796543687432e-05, "loss": 3.7425, "step": 11163 }, { "epoch": 0.600731812311666, "grad_norm": 2.1695916652679443, "learning_rate": 1.722394875566326e-05, "loss": 3.6131, "step": 11164 }, { "epoch": 0.6007856220404649, "grad_norm": 2.9326248168945312, "learning_rate": 1.7219932296670835e-05, "loss": 3.4886, "step": 11165 }, { "epoch": 0.6008394317692639, "grad_norm": 3.4081838130950928, "learning_rate": 1.7215916060011816e-05, "loss": 3.6388, "step": 11166 }, { "epoch": 0.6008932414980629, "grad_norm": 1.8179484605789185, "learning_rate": 1.7211900045800976e-05, "loss": 4.0349, "step": 11167 }, { "epoch": 0.6009470512268618, "grad_norm": 2.5149664878845215, "learning_rate": 1.7207884254153094e-05, "loss": 4.143, "step": 11168 }, { "epoch": 0.6010008609556607, "grad_norm": 2.052361249923706, "learning_rate": 1.7203868685182924e-05, "loss": 3.942, "step": 11169 }, { "epoch": 0.6010546706844597, "grad_norm": 3.420175313949585, "learning_rate": 1.719985333900521e-05, "loss": 3.872, "step": 11170 }, { "epoch": 0.6011084804132587, "grad_norm": 2.4429593086242676, "learning_rate": 1.719583821573471e-05, "loss": 3.3299, "step": 11171 }, { "epoch": 0.6011622901420577, "grad_norm": 2.4363608360290527, "learning_rate": 1.719182331548616e-05, "loss": 4.2573, "step": 11172 }, { "epoch": 0.6012160998708567, "grad_norm": 1.9109551906585693, "learning_rate": 1.71878086383743e-05, "loss": 4.2299, "step": 11173 }, { "epoch": 0.6012699095996556, "grad_norm": 2.3163952827453613, "learning_rate": 1.7183794184513856e-05, "loss": 3.1273, "step": 11174 }, { "epoch": 0.6013237193284546, "grad_norm": 3.7210476398468018, "learning_rate": 1.7179779954019548e-05, "loss": 3.6986, "step": 11175 }, { "epoch": 0.6013775290572535, "grad_norm": 1.5555251836776733, "learning_rate": 1.71757659470061e-05, "loss": 4.1055, "step": 11176 }, { "epoch": 0.6014313387860525, "grad_norm": 1.357749104499817, "learning_rate": 1.7171752163588224e-05, "loss": 4.1927, "step": 11177 }, { "epoch": 0.6014851485148515, "grad_norm": 2.716001033782959, "learning_rate": 1.7167738603880605e-05, "loss": 4.6517, "step": 11178 }, { "epoch": 0.6015389582436504, "grad_norm": 3.0361435413360596, "learning_rate": 1.7163725267997953e-05, "loss": 3.4104, "step": 11179 }, { "epoch": 0.6015927679724494, "grad_norm": 1.1367355585098267, "learning_rate": 1.7159712156054952e-05, "loss": 4.4413, "step": 11180 }, { "epoch": 0.6016465777012484, "grad_norm": 3.1253397464752197, "learning_rate": 1.715569926816629e-05, "loss": 3.8609, "step": 11181 }, { "epoch": 0.6017003874300474, "grad_norm": 3.6932871341705322, "learning_rate": 1.7151686604446647e-05, "loss": 3.3799, "step": 11182 }, { "epoch": 0.6017541971588464, "grad_norm": 2.944838047027588, "learning_rate": 1.7147674165010692e-05, "loss": 3.6527, "step": 11183 }, { "epoch": 0.6018080068876452, "grad_norm": 3.433946132659912, "learning_rate": 1.7143661949973088e-05, "loss": 3.037, "step": 11184 }, { "epoch": 0.6018618166164442, "grad_norm": 2.4261014461517334, "learning_rate": 1.7139649959448502e-05, "loss": 3.6464, "step": 11185 }, { "epoch": 0.6019156263452432, "grad_norm": 1.2757673263549805, "learning_rate": 1.713563819355157e-05, "loss": 4.5079, "step": 11186 }, { "epoch": 0.6019694360740422, "grad_norm": 2.543111562728882, "learning_rate": 1.7131626652396948e-05, "loss": 4.2391, "step": 11187 }, { "epoch": 0.6020232458028412, "grad_norm": 3.5342187881469727, "learning_rate": 1.7127615336099268e-05, "loss": 3.5339, "step": 11188 }, { "epoch": 0.6020770555316401, "grad_norm": 3.401064872741699, "learning_rate": 1.7123604244773173e-05, "loss": 3.8034, "step": 11189 }, { "epoch": 0.6021308652604391, "grad_norm": 1.2142597436904907, "learning_rate": 1.7119593378533283e-05, "loss": 4.014, "step": 11190 }, { "epoch": 0.602184674989238, "grad_norm": 3.112452745437622, "learning_rate": 1.7115582737494213e-05, "loss": 3.8564, "step": 11191 }, { "epoch": 0.602238484718037, "grad_norm": 1.9802240133285522, "learning_rate": 1.7111572321770592e-05, "loss": 4.1546, "step": 11192 }, { "epoch": 0.602292294446836, "grad_norm": 2.9942679405212402, "learning_rate": 1.710756213147701e-05, "loss": 4.3588, "step": 11193 }, { "epoch": 0.6023461041756349, "grad_norm": 2.434852123260498, "learning_rate": 1.7103552166728077e-05, "loss": 4.2245, "step": 11194 }, { "epoch": 0.6023999139044339, "grad_norm": 2.7249512672424316, "learning_rate": 1.7099542427638376e-05, "loss": 4.1382, "step": 11195 }, { "epoch": 0.6024537236332329, "grad_norm": 1.326094627380371, "learning_rate": 1.709553291432251e-05, "loss": 4.8945, "step": 11196 }, { "epoch": 0.6025075333620319, "grad_norm": 2.595306158065796, "learning_rate": 1.7091523626895054e-05, "loss": 4.2817, "step": 11197 }, { "epoch": 0.6025613430908309, "grad_norm": 3.573540210723877, "learning_rate": 1.7087514565470576e-05, "loss": 3.4961, "step": 11198 }, { "epoch": 0.6026151528196297, "grad_norm": 1.8755731582641602, "learning_rate": 1.708350573016365e-05, "loss": 3.9845, "step": 11199 }, { "epoch": 0.6026689625484287, "grad_norm": 3.007843494415283, "learning_rate": 1.707949712108885e-05, "loss": 4.2427, "step": 11200 }, { "epoch": 0.6027227722772277, "grad_norm": 2.1539828777313232, "learning_rate": 1.7075488738360707e-05, "loss": 4.571, "step": 11201 }, { "epoch": 0.6027765820060267, "grad_norm": 2.9267971515655518, "learning_rate": 1.7071480582093784e-05, "loss": 3.5073, "step": 11202 }, { "epoch": 0.6028303917348257, "grad_norm": 2.9817168712615967, "learning_rate": 1.7067472652402617e-05, "loss": 4.1599, "step": 11203 }, { "epoch": 0.6028842014636246, "grad_norm": 2.139299154281616, "learning_rate": 1.7063464949401746e-05, "loss": 4.6261, "step": 11204 }, { "epoch": 0.6029380111924236, "grad_norm": 2.411839246749878, "learning_rate": 1.7059457473205707e-05, "loss": 3.7421, "step": 11205 }, { "epoch": 0.6029918209212226, "grad_norm": 3.0777430534362793, "learning_rate": 1.7055450223929005e-05, "loss": 3.7072, "step": 11206 }, { "epoch": 0.6030456306500215, "grad_norm": 2.43747878074646, "learning_rate": 1.7051443201686173e-05, "loss": 3.9876, "step": 11207 }, { "epoch": 0.6030994403788205, "grad_norm": 4.049353122711182, "learning_rate": 1.7047436406591723e-05, "loss": 4.1478, "step": 11208 }, { "epoch": 0.6031532501076194, "grad_norm": 1.073974847793579, "learning_rate": 1.7043429838760145e-05, "loss": 4.538, "step": 11209 }, { "epoch": 0.6032070598364184, "grad_norm": 2.5240941047668457, "learning_rate": 1.703942349830594e-05, "loss": 3.8601, "step": 11210 }, { "epoch": 0.6032608695652174, "grad_norm": 2.6378822326660156, "learning_rate": 1.7035417385343595e-05, "loss": 3.9166, "step": 11211 }, { "epoch": 0.6033146792940164, "grad_norm": 1.974204182624817, "learning_rate": 1.7031411499987605e-05, "loss": 4.3156, "step": 11212 }, { "epoch": 0.6033684890228154, "grad_norm": 1.2638189792633057, "learning_rate": 1.702740584235244e-05, "loss": 4.4502, "step": 11213 }, { "epoch": 0.6034222987516142, "grad_norm": 1.4790918827056885, "learning_rate": 1.702340041255257e-05, "loss": 3.9787, "step": 11214 }, { "epoch": 0.6034761084804132, "grad_norm": 2.4318957328796387, "learning_rate": 1.7019395210702473e-05, "loss": 3.1732, "step": 11215 }, { "epoch": 0.6035299182092122, "grad_norm": 1.583052635192871, "learning_rate": 1.7015390236916585e-05, "loss": 4.3697, "step": 11216 }, { "epoch": 0.6035837279380112, "grad_norm": 2.8949966430664062, "learning_rate": 1.701138549130937e-05, "loss": 3.7006, "step": 11217 }, { "epoch": 0.6036375376668102, "grad_norm": 2.58455228805542, "learning_rate": 1.7007380973995273e-05, "loss": 3.6684, "step": 11218 }, { "epoch": 0.6036913473956091, "grad_norm": 3.9498703479766846, "learning_rate": 1.700337668508872e-05, "loss": 3.8522, "step": 11219 }, { "epoch": 0.6037451571244081, "grad_norm": 2.083169460296631, "learning_rate": 1.699937262470416e-05, "loss": 4.202, "step": 11220 }, { "epoch": 0.6037989668532071, "grad_norm": 1.357391357421875, "learning_rate": 1.6995368792956015e-05, "loss": 4.6447, "step": 11221 }, { "epoch": 0.603852776582006, "grad_norm": 1.8948328495025635, "learning_rate": 1.699136518995869e-05, "loss": 4.4079, "step": 11222 }, { "epoch": 0.603906586310805, "grad_norm": 3.3612914085388184, "learning_rate": 1.6987361815826623e-05, "loss": 3.2485, "step": 11223 }, { "epoch": 0.6039603960396039, "grad_norm": 2.964780330657959, "learning_rate": 1.6983358670674192e-05, "loss": 3.317, "step": 11224 }, { "epoch": 0.6040142057684029, "grad_norm": 3.2415525913238525, "learning_rate": 1.6979355754615814e-05, "loss": 3.9943, "step": 11225 }, { "epoch": 0.6040680154972019, "grad_norm": 2.421872138977051, "learning_rate": 1.6975353067765866e-05, "loss": 3.837, "step": 11226 }, { "epoch": 0.6041218252260009, "grad_norm": 2.5663270950317383, "learning_rate": 1.6971350610238752e-05, "loss": 4.3281, "step": 11227 }, { "epoch": 0.6041756349547999, "grad_norm": 1.6728039979934692, "learning_rate": 1.6967348382148842e-05, "loss": 4.4576, "step": 11228 }, { "epoch": 0.6042294446835988, "grad_norm": 2.0955023765563965, "learning_rate": 1.6963346383610505e-05, "loss": 3.9605, "step": 11229 }, { "epoch": 0.6042832544123977, "grad_norm": 2.613837718963623, "learning_rate": 1.6959344614738115e-05, "loss": 3.6513, "step": 11230 }, { "epoch": 0.6043370641411967, "grad_norm": 1.7179598808288574, "learning_rate": 1.6955343075646037e-05, "loss": 4.3468, "step": 11231 }, { "epoch": 0.6043908738699957, "grad_norm": 2.5966408252716064, "learning_rate": 1.695134176644861e-05, "loss": 4.287, "step": 11232 }, { "epoch": 0.6044446835987947, "grad_norm": 2.319106101989746, "learning_rate": 1.6947340687260188e-05, "loss": 4.2459, "step": 11233 }, { "epoch": 0.6044984933275936, "grad_norm": 3.1386775970458984, "learning_rate": 1.6943339838195105e-05, "loss": 4.8489, "step": 11234 }, { "epoch": 0.6045523030563926, "grad_norm": 1.943850040435791, "learning_rate": 1.6939339219367702e-05, "loss": 4.1866, "step": 11235 }, { "epoch": 0.6046061127851916, "grad_norm": 2.451770782470703, "learning_rate": 1.6935338830892305e-05, "loss": 4.2093, "step": 11236 }, { "epoch": 0.6046599225139905, "grad_norm": 2.598853826522827, "learning_rate": 1.693133867288323e-05, "loss": 4.1537, "step": 11237 }, { "epoch": 0.6047137322427895, "grad_norm": 1.017208456993103, "learning_rate": 1.692733874545481e-05, "loss": 4.323, "step": 11238 }, { "epoch": 0.6047675419715884, "grad_norm": 2.3666491508483887, "learning_rate": 1.6923339048721316e-05, "loss": 3.9677, "step": 11239 }, { "epoch": 0.6048213517003874, "grad_norm": 1.9995601177215576, "learning_rate": 1.691933958279707e-05, "loss": 4.5336, "step": 11240 }, { "epoch": 0.6048751614291864, "grad_norm": 1.2982449531555176, "learning_rate": 1.691534034779637e-05, "loss": 4.4226, "step": 11241 }, { "epoch": 0.6049289711579854, "grad_norm": 2.8581058979034424, "learning_rate": 1.6911341343833493e-05, "loss": 3.3887, "step": 11242 }, { "epoch": 0.6049827808867844, "grad_norm": 1.9951683282852173, "learning_rate": 1.6907342571022726e-05, "loss": 4.4036, "step": 11243 }, { "epoch": 0.6050365906155833, "grad_norm": 1.315321683883667, "learning_rate": 1.6903344029478347e-05, "loss": 4.24, "step": 11244 }, { "epoch": 0.6050904003443822, "grad_norm": 1.8865493535995483, "learning_rate": 1.6899345719314608e-05, "loss": 4.6359, "step": 11245 }, { "epoch": 0.6051442100731812, "grad_norm": 2.5079448223114014, "learning_rate": 1.6895347640645793e-05, "loss": 3.9101, "step": 11246 }, { "epoch": 0.6051980198019802, "grad_norm": 3.3111302852630615, "learning_rate": 1.6891349793586137e-05, "loss": 4.3313, "step": 11247 }, { "epoch": 0.6052518295307792, "grad_norm": 2.0887017250061035, "learning_rate": 1.6887352178249897e-05, "loss": 3.7635, "step": 11248 }, { "epoch": 0.6053056392595781, "grad_norm": 2.9202678203582764, "learning_rate": 1.68833547947513e-05, "loss": 4.0993, "step": 11249 }, { "epoch": 0.6053594489883771, "grad_norm": 3.2479825019836426, "learning_rate": 1.68793576432046e-05, "loss": 3.9284, "step": 11250 }, { "epoch": 0.6054132587171761, "grad_norm": 2.7685108184814453, "learning_rate": 1.687536072372402e-05, "loss": 3.6952, "step": 11251 }, { "epoch": 0.6054670684459751, "grad_norm": 2.9570727348327637, "learning_rate": 1.687136403642377e-05, "loss": 4.6947, "step": 11252 }, { "epoch": 0.605520878174774, "grad_norm": 3.127696990966797, "learning_rate": 1.686736758141808e-05, "loss": 3.7951, "step": 11253 }, { "epoch": 0.6055746879035729, "grad_norm": 2.4860126972198486, "learning_rate": 1.686337135882115e-05, "loss": 3.9467, "step": 11254 }, { "epoch": 0.6056284976323719, "grad_norm": 2.9398386478424072, "learning_rate": 1.6859375368747182e-05, "loss": 4.2519, "step": 11255 }, { "epoch": 0.6056823073611709, "grad_norm": 4.417931079864502, "learning_rate": 1.6855379611310367e-05, "loss": 3.118, "step": 11256 }, { "epoch": 0.6057361170899699, "grad_norm": 2.816816568374634, "learning_rate": 1.6851384086624893e-05, "loss": 3.4543, "step": 11257 }, { "epoch": 0.6057899268187689, "grad_norm": 1.702290654182434, "learning_rate": 1.6847388794804948e-05, "loss": 4.6375, "step": 11258 }, { "epoch": 0.6058437365475678, "grad_norm": 3.5154869556427, "learning_rate": 1.68433937359647e-05, "loss": 3.1676, "step": 11259 }, { "epoch": 0.6058975462763667, "grad_norm": 1.9372665882110596, "learning_rate": 1.6839398910218323e-05, "loss": 4.3654, "step": 11260 }, { "epoch": 0.6059513560051657, "grad_norm": 2.1576623916625977, "learning_rate": 1.6835404317679987e-05, "loss": 4.533, "step": 11261 }, { "epoch": 0.6060051657339647, "grad_norm": 2.7026140689849854, "learning_rate": 1.683140995846382e-05, "loss": 3.3121, "step": 11262 }, { "epoch": 0.6060589754627637, "grad_norm": 1.3643864393234253, "learning_rate": 1.682741583268399e-05, "loss": 4.455, "step": 11263 }, { "epoch": 0.6061127851915626, "grad_norm": 2.1288576126098633, "learning_rate": 1.6823421940454637e-05, "loss": 3.9774, "step": 11264 }, { "epoch": 0.6061665949203616, "grad_norm": 2.3026795387268066, "learning_rate": 1.6819428281889885e-05, "loss": 4.0298, "step": 11265 }, { "epoch": 0.6062204046491606, "grad_norm": 2.4201700687408447, "learning_rate": 1.6815434857103872e-05, "loss": 4.1748, "step": 11266 }, { "epoch": 0.6062742143779596, "grad_norm": 2.7700040340423584, "learning_rate": 1.681144166621072e-05, "loss": 4.0097, "step": 11267 }, { "epoch": 0.6063280241067585, "grad_norm": 2.487410306930542, "learning_rate": 1.6807448709324535e-05, "loss": 3.9967, "step": 11268 }, { "epoch": 0.6063818338355574, "grad_norm": 2.2344706058502197, "learning_rate": 1.6803455986559446e-05, "loss": 3.7608, "step": 11269 }, { "epoch": 0.6064356435643564, "grad_norm": 3.141068935394287, "learning_rate": 1.6799463498029528e-05, "loss": 4.0133, "step": 11270 }, { "epoch": 0.6064894532931554, "grad_norm": 2.196563482284546, "learning_rate": 1.6795471243848886e-05, "loss": 3.7116, "step": 11271 }, { "epoch": 0.6065432630219544, "grad_norm": 1.4357823133468628, "learning_rate": 1.6791479224131605e-05, "loss": 3.9422, "step": 11272 }, { "epoch": 0.6065970727507534, "grad_norm": 2.426595449447632, "learning_rate": 1.678748743899177e-05, "loss": 3.7545, "step": 11273 }, { "epoch": 0.6066508824795523, "grad_norm": 1.1345815658569336, "learning_rate": 1.678349588854346e-05, "loss": 4.4397, "step": 11274 }, { "epoch": 0.6067046922083512, "grad_norm": 1.9991012811660767, "learning_rate": 1.6779504572900734e-05, "loss": 3.6973, "step": 11275 }, { "epoch": 0.6067585019371502, "grad_norm": 2.07598876953125, "learning_rate": 1.6775513492177667e-05, "loss": 4.2598, "step": 11276 }, { "epoch": 0.6068123116659492, "grad_norm": 1.6852281093597412, "learning_rate": 1.677152264648829e-05, "loss": 4.3854, "step": 11277 }, { "epoch": 0.6068661213947482, "grad_norm": 2.862370729446411, "learning_rate": 1.6767532035946668e-05, "loss": 3.8545, "step": 11278 }, { "epoch": 0.6069199311235471, "grad_norm": 1.656050205230713, "learning_rate": 1.6763541660666836e-05, "loss": 4.4555, "step": 11279 }, { "epoch": 0.6069737408523461, "grad_norm": 3.1186180114746094, "learning_rate": 1.675955152076283e-05, "loss": 3.5999, "step": 11280 }, { "epoch": 0.6070275505811451, "grad_norm": 4.083157539367676, "learning_rate": 1.675556161634868e-05, "loss": 4.5668, "step": 11281 }, { "epoch": 0.6070813603099441, "grad_norm": 3.107677459716797, "learning_rate": 1.6751571947538402e-05, "loss": 4.02, "step": 11282 }, { "epoch": 0.607135170038743, "grad_norm": 3.187086582183838, "learning_rate": 1.674758251444601e-05, "loss": 3.1065, "step": 11283 }, { "epoch": 0.6071889797675419, "grad_norm": 3.9825103282928467, "learning_rate": 1.674359331718553e-05, "loss": 3.3401, "step": 11284 }, { "epoch": 0.6072427894963409, "grad_norm": 1.5306254625320435, "learning_rate": 1.6739604355870924e-05, "loss": 4.4563, "step": 11285 }, { "epoch": 0.6072965992251399, "grad_norm": 1.5350919961929321, "learning_rate": 1.673561563061622e-05, "loss": 3.7091, "step": 11286 }, { "epoch": 0.6073504089539389, "grad_norm": 2.6337709426879883, "learning_rate": 1.673162714153539e-05, "loss": 3.8069, "step": 11287 }, { "epoch": 0.6074042186827379, "grad_norm": 2.7510111331939697, "learning_rate": 1.6727638888742408e-05, "loss": 3.2814, "step": 11288 }, { "epoch": 0.6074580284115368, "grad_norm": 2.274981737136841, "learning_rate": 1.6723650872351264e-05, "loss": 3.7708, "step": 11289 }, { "epoch": 0.6075118381403358, "grad_norm": 3.4624581336975098, "learning_rate": 1.671966309247592e-05, "loss": 3.9671, "step": 11290 }, { "epoch": 0.6075656478691347, "grad_norm": 1.954742670059204, "learning_rate": 1.6715675549230324e-05, "loss": 4.1877, "step": 11291 }, { "epoch": 0.6076194575979337, "grad_norm": 2.903358221054077, "learning_rate": 1.671168824272846e-05, "loss": 4.3039, "step": 11292 }, { "epoch": 0.6076732673267327, "grad_norm": 1.9491058588027954, "learning_rate": 1.6707701173084232e-05, "loss": 4.3209, "step": 11293 }, { "epoch": 0.6077270770555316, "grad_norm": 3.4646029472351074, "learning_rate": 1.6703714340411607e-05, "loss": 3.0469, "step": 11294 }, { "epoch": 0.6077808867843306, "grad_norm": 2.026840925216675, "learning_rate": 1.6699727744824517e-05, "loss": 4.3605, "step": 11295 }, { "epoch": 0.6078346965131296, "grad_norm": 1.789017677307129, "learning_rate": 1.6695741386436873e-05, "loss": 3.5438, "step": 11296 }, { "epoch": 0.6078885062419286, "grad_norm": 2.8090579509735107, "learning_rate": 1.6691755265362607e-05, "loss": 3.9275, "step": 11297 }, { "epoch": 0.6079423159707275, "grad_norm": 3.7595808506011963, "learning_rate": 1.6687769381715633e-05, "loss": 3.511, "step": 11298 }, { "epoch": 0.6079961256995264, "grad_norm": 1.9267133474349976, "learning_rate": 1.668378373560986e-05, "loss": 4.0748, "step": 11299 }, { "epoch": 0.6080499354283254, "grad_norm": 1.604974627494812, "learning_rate": 1.6679798327159168e-05, "loss": 4.4093, "step": 11300 }, { "epoch": 0.6081037451571244, "grad_norm": 2.1493022441864014, "learning_rate": 1.667581315647746e-05, "loss": 3.299, "step": 11301 }, { "epoch": 0.6081575548859234, "grad_norm": 2.701486110687256, "learning_rate": 1.6671828223678628e-05, "loss": 4.4212, "step": 11302 }, { "epoch": 0.6082113646147224, "grad_norm": 2.2365405559539795, "learning_rate": 1.6667843528876548e-05, "loss": 3.9284, "step": 11303 }, { "epoch": 0.6082651743435213, "grad_norm": 3.3445653915405273, "learning_rate": 1.666385907218508e-05, "loss": 4.1164, "step": 11304 }, { "epoch": 0.6083189840723203, "grad_norm": 2.5568439960479736, "learning_rate": 1.6659874853718102e-05, "loss": 3.2549, "step": 11305 }, { "epoch": 0.6083727938011192, "grad_norm": 2.586299419403076, "learning_rate": 1.665589087358947e-05, "loss": 3.8833, "step": 11306 }, { "epoch": 0.6084266035299182, "grad_norm": 2.4548442363739014, "learning_rate": 1.665190713191304e-05, "loss": 4.0058, "step": 11307 }, { "epoch": 0.6084804132587172, "grad_norm": 2.2680866718292236, "learning_rate": 1.664792362880264e-05, "loss": 4.3354, "step": 11308 }, { "epoch": 0.6085342229875161, "grad_norm": 2.846754789352417, "learning_rate": 1.6643940364372125e-05, "loss": 4.4381, "step": 11309 }, { "epoch": 0.6085880327163151, "grad_norm": 1.6160271167755127, "learning_rate": 1.6639957338735312e-05, "loss": 4.3554, "step": 11310 }, { "epoch": 0.6086418424451141, "grad_norm": 1.7864347696304321, "learning_rate": 1.6635974552006036e-05, "loss": 4.1246, "step": 11311 }, { "epoch": 0.6086956521739131, "grad_norm": 1.960898518562317, "learning_rate": 1.6631992004298107e-05, "loss": 3.7113, "step": 11312 }, { "epoch": 0.6087494619027121, "grad_norm": 2.199781656265259, "learning_rate": 1.6628009695725346e-05, "loss": 3.8371, "step": 11313 }, { "epoch": 0.6088032716315109, "grad_norm": 3.996677875518799, "learning_rate": 1.6624027626401545e-05, "loss": 2.8735, "step": 11314 }, { "epoch": 0.6088570813603099, "grad_norm": 1.8810538053512573, "learning_rate": 1.662004579644052e-05, "loss": 4.7137, "step": 11315 }, { "epoch": 0.6089108910891089, "grad_norm": 1.3466163873672485, "learning_rate": 1.6616064205956027e-05, "loss": 4.6479, "step": 11316 }, { "epoch": 0.6089647008179079, "grad_norm": 2.98600172996521, "learning_rate": 1.6612082855061878e-05, "loss": 4.0411, "step": 11317 }, { "epoch": 0.6090185105467069, "grad_norm": 3.0050580501556396, "learning_rate": 1.660810174387184e-05, "loss": 4.0576, "step": 11318 }, { "epoch": 0.6090723202755058, "grad_norm": 2.6045620441436768, "learning_rate": 1.6604120872499678e-05, "loss": 3.994, "step": 11319 }, { "epoch": 0.6091261300043048, "grad_norm": 1.8931312561035156, "learning_rate": 1.6600140241059163e-05, "loss": 4.4073, "step": 11320 }, { "epoch": 0.6091799397331037, "grad_norm": 2.1668450832366943, "learning_rate": 1.659615984966405e-05, "loss": 4.4248, "step": 11321 }, { "epoch": 0.6092337494619027, "grad_norm": 3.16841459274292, "learning_rate": 1.6592179698428084e-05, "loss": 4.1282, "step": 11322 }, { "epoch": 0.6092875591907017, "grad_norm": 3.004503011703491, "learning_rate": 1.658819978746501e-05, "loss": 3.9159, "step": 11323 }, { "epoch": 0.6093413689195006, "grad_norm": 2.0511419773101807, "learning_rate": 1.658422011688855e-05, "loss": 4.1277, "step": 11324 }, { "epoch": 0.6093951786482996, "grad_norm": 1.2555173635482788, "learning_rate": 1.6580240686812447e-05, "loss": 4.5403, "step": 11325 }, { "epoch": 0.6094489883770986, "grad_norm": 3.307857036590576, "learning_rate": 1.6576261497350424e-05, "loss": 4.0027, "step": 11326 }, { "epoch": 0.6095027981058976, "grad_norm": 2.3418750762939453, "learning_rate": 1.657228254861618e-05, "loss": 3.6084, "step": 11327 }, { "epoch": 0.6095566078346966, "grad_norm": 2.7886626720428467, "learning_rate": 1.6568303840723443e-05, "loss": 3.534, "step": 11328 }, { "epoch": 0.6096104175634954, "grad_norm": 2.9967472553253174, "learning_rate": 1.6564325373785904e-05, "loss": 3.8932, "step": 11329 }, { "epoch": 0.6096642272922944, "grad_norm": 2.558101177215576, "learning_rate": 1.656034714791726e-05, "loss": 4.2342, "step": 11330 }, { "epoch": 0.6097180370210934, "grad_norm": 2.7926204204559326, "learning_rate": 1.6556369163231185e-05, "loss": 3.8649, "step": 11331 }, { "epoch": 0.6097718467498924, "grad_norm": 1.6744447946548462, "learning_rate": 1.6552391419841367e-05, "loss": 4.5627, "step": 11332 }, { "epoch": 0.6098256564786914, "grad_norm": 1.861596703529358, "learning_rate": 1.6548413917861488e-05, "loss": 4.2026, "step": 11333 }, { "epoch": 0.6098794662074903, "grad_norm": 2.5214405059814453, "learning_rate": 1.6544436657405203e-05, "loss": 3.8781, "step": 11334 }, { "epoch": 0.6099332759362893, "grad_norm": 3.271881580352783, "learning_rate": 1.6540459638586175e-05, "loss": 3.969, "step": 11335 }, { "epoch": 0.6099870856650883, "grad_norm": 2.7626683712005615, "learning_rate": 1.653648286151806e-05, "loss": 4.1664, "step": 11336 }, { "epoch": 0.6100408953938872, "grad_norm": 2.2483954429626465, "learning_rate": 1.65325063263145e-05, "loss": 4.3406, "step": 11337 }, { "epoch": 0.6100947051226862, "grad_norm": 3.3171238899230957, "learning_rate": 1.652853003308914e-05, "loss": 2.7613, "step": 11338 }, { "epoch": 0.6101485148514851, "grad_norm": 3.800422191619873, "learning_rate": 1.652455398195559e-05, "loss": 3.1958, "step": 11339 }, { "epoch": 0.6102023245802841, "grad_norm": 2.5421180725097656, "learning_rate": 1.6520578173027505e-05, "loss": 4.5891, "step": 11340 }, { "epoch": 0.6102561343090831, "grad_norm": 2.785202741622925, "learning_rate": 1.6516602606418486e-05, "loss": 4.1158, "step": 11341 }, { "epoch": 0.6103099440378821, "grad_norm": 2.620576858520508, "learning_rate": 1.6512627282242144e-05, "loss": 4.2281, "step": 11342 }, { "epoch": 0.6103637537666811, "grad_norm": 3.221064567565918, "learning_rate": 1.6508652200612085e-05, "loss": 3.8963, "step": 11343 }, { "epoch": 0.6104175634954799, "grad_norm": 1.360100269317627, "learning_rate": 1.650467736164191e-05, "loss": 4.5088, "step": 11344 }, { "epoch": 0.6104713732242789, "grad_norm": 2.6299309730529785, "learning_rate": 1.6500702765445214e-05, "loss": 3.6708, "step": 11345 }, { "epoch": 0.6105251829530779, "grad_norm": 1.5070559978485107, "learning_rate": 1.6496728412135563e-05, "loss": 4.5591, "step": 11346 }, { "epoch": 0.6105789926818769, "grad_norm": 1.8116923570632935, "learning_rate": 1.649275430182654e-05, "loss": 4.2361, "step": 11347 }, { "epoch": 0.6106328024106759, "grad_norm": 3.622370958328247, "learning_rate": 1.6488780434631723e-05, "loss": 3.571, "step": 11348 }, { "epoch": 0.6106866121394748, "grad_norm": 3.6808483600616455, "learning_rate": 1.648480681066467e-05, "loss": 4.1448, "step": 11349 }, { "epoch": 0.6107404218682738, "grad_norm": 2.3390021324157715, "learning_rate": 1.648083343003893e-05, "loss": 4.2204, "step": 11350 }, { "epoch": 0.6107942315970728, "grad_norm": 1.4388649463653564, "learning_rate": 1.6476860292868057e-05, "loss": 4.3201, "step": 11351 }, { "epoch": 0.6108480413258717, "grad_norm": 3.3317017555236816, "learning_rate": 1.6472887399265596e-05, "loss": 4.5623, "step": 11352 }, { "epoch": 0.6109018510546707, "grad_norm": 3.6762213706970215, "learning_rate": 1.6468914749345084e-05, "loss": 3.517, "step": 11353 }, { "epoch": 0.6109556607834696, "grad_norm": 1.757030725479126, "learning_rate": 1.6464942343220034e-05, "loss": 3.7078, "step": 11354 }, { "epoch": 0.6110094705122686, "grad_norm": 1.8064603805541992, "learning_rate": 1.646097018100397e-05, "loss": 4.5322, "step": 11355 }, { "epoch": 0.6110632802410676, "grad_norm": 2.472526788711548, "learning_rate": 1.645699826281042e-05, "loss": 2.6737, "step": 11356 }, { "epoch": 0.6111170899698666, "grad_norm": 2.235931396484375, "learning_rate": 1.645302658875288e-05, "loss": 3.8861, "step": 11357 }, { "epoch": 0.6111708996986656, "grad_norm": 1.9081710577011108, "learning_rate": 1.6449055158944843e-05, "loss": 3.3376, "step": 11358 }, { "epoch": 0.6112247094274645, "grad_norm": 2.563009738922119, "learning_rate": 1.644508397349982e-05, "loss": 3.925, "step": 11359 }, { "epoch": 0.6112785191562634, "grad_norm": 2.930037260055542, "learning_rate": 1.6441113032531286e-05, "loss": 3.1523, "step": 11360 }, { "epoch": 0.6113323288850624, "grad_norm": 3.541461229324341, "learning_rate": 1.6437142336152723e-05, "loss": 4.1189, "step": 11361 }, { "epoch": 0.6113861386138614, "grad_norm": 1.7004200220108032, "learning_rate": 1.64331718844776e-05, "loss": 3.9956, "step": 11362 }, { "epoch": 0.6114399483426604, "grad_norm": 2.4973526000976562, "learning_rate": 1.6429201677619373e-05, "loss": 4.6652, "step": 11363 }, { "epoch": 0.6114937580714593, "grad_norm": 1.7057665586471558, "learning_rate": 1.6425231715691515e-05, "loss": 4.2848, "step": 11364 }, { "epoch": 0.6115475678002583, "grad_norm": 2.8190674781799316, "learning_rate": 1.6421261998807473e-05, "loss": 3.3577, "step": 11365 }, { "epoch": 0.6116013775290573, "grad_norm": 3.3376097679138184, "learning_rate": 1.6417292527080686e-05, "loss": 3.3731, "step": 11366 }, { "epoch": 0.6116551872578562, "grad_norm": 1.528348684310913, "learning_rate": 1.6413323300624594e-05, "loss": 4.5939, "step": 11367 }, { "epoch": 0.6117089969866552, "grad_norm": 3.022838592529297, "learning_rate": 1.6409354319552632e-05, "loss": 3.2222, "step": 11368 }, { "epoch": 0.6117628067154541, "grad_norm": 3.045203924179077, "learning_rate": 1.6405385583978215e-05, "loss": 2.7915, "step": 11369 }, { "epoch": 0.6118166164442531, "grad_norm": 1.4726516008377075, "learning_rate": 1.6401417094014757e-05, "loss": 4.6313, "step": 11370 }, { "epoch": 0.6118704261730521, "grad_norm": 2.0131072998046875, "learning_rate": 1.6397448849775675e-05, "loss": 4.0694, "step": 11371 }, { "epoch": 0.6119242359018511, "grad_norm": 3.5428659915924072, "learning_rate": 1.6393480851374364e-05, "loss": 3.9609, "step": 11372 }, { "epoch": 0.6119780456306501, "grad_norm": 3.572579860687256, "learning_rate": 1.638951309892422e-05, "loss": 3.7142, "step": 11373 }, { "epoch": 0.612031855359449, "grad_norm": 3.931422472000122, "learning_rate": 1.6385545592538636e-05, "loss": 3.7344, "step": 11374 }, { "epoch": 0.6120856650882479, "grad_norm": 1.5337613821029663, "learning_rate": 1.6381578332330987e-05, "loss": 4.2723, "step": 11375 }, { "epoch": 0.6121394748170469, "grad_norm": 2.3561956882476807, "learning_rate": 1.637761131841466e-05, "loss": 3.9725, "step": 11376 }, { "epoch": 0.6121932845458459, "grad_norm": 2.970942974090576, "learning_rate": 1.6373644550902998e-05, "loss": 3.8235, "step": 11377 }, { "epoch": 0.6122470942746449, "grad_norm": 2.646817922592163, "learning_rate": 1.636967802990937e-05, "loss": 3.8258, "step": 11378 }, { "epoch": 0.6123009040034438, "grad_norm": 2.348710060119629, "learning_rate": 1.6365711755547136e-05, "loss": 3.4389, "step": 11379 }, { "epoch": 0.6123547137322428, "grad_norm": 2.030272960662842, "learning_rate": 1.6361745727929635e-05, "loss": 4.186, "step": 11380 }, { "epoch": 0.6124085234610418, "grad_norm": 2.0373005867004395, "learning_rate": 1.6357779947170206e-05, "loss": 3.7483, "step": 11381 }, { "epoch": 0.6124623331898407, "grad_norm": 2.6565158367156982, "learning_rate": 1.635381441338218e-05, "loss": 4.1234, "step": 11382 }, { "epoch": 0.6125161429186397, "grad_norm": 3.3598203659057617, "learning_rate": 1.634984912667889e-05, "loss": 3.481, "step": 11383 }, { "epoch": 0.6125699526474386, "grad_norm": 3.347541093826294, "learning_rate": 1.6345884087173644e-05, "loss": 2.4957, "step": 11384 }, { "epoch": 0.6126237623762376, "grad_norm": 2.2915351390838623, "learning_rate": 1.634191929497975e-05, "loss": 4.2868, "step": 11385 }, { "epoch": 0.6126775721050366, "grad_norm": 3.354469060897827, "learning_rate": 1.6337954750210514e-05, "loss": 2.522, "step": 11386 }, { "epoch": 0.6127313818338356, "grad_norm": 1.6197130680084229, "learning_rate": 1.6333990452979236e-05, "loss": 3.7459, "step": 11387 }, { "epoch": 0.6127851915626346, "grad_norm": 3.504051446914673, "learning_rate": 1.63300264033992e-05, "loss": 3.1974, "step": 11388 }, { "epoch": 0.6128390012914335, "grad_norm": 4.0875773429870605, "learning_rate": 1.6326062601583686e-05, "loss": 3.6431, "step": 11389 }, { "epoch": 0.6128928110202324, "grad_norm": 2.8017141819000244, "learning_rate": 1.632209904764598e-05, "loss": 3.3855, "step": 11390 }, { "epoch": 0.6129466207490314, "grad_norm": 2.059640884399414, "learning_rate": 1.6318135741699346e-05, "loss": 4.2789, "step": 11391 }, { "epoch": 0.6130004304778304, "grad_norm": 3.3734264373779297, "learning_rate": 1.6314172683857038e-05, "loss": 3.8021, "step": 11392 }, { "epoch": 0.6130542402066294, "grad_norm": 2.0877652168273926, "learning_rate": 1.6310209874232307e-05, "loss": 3.8692, "step": 11393 }, { "epoch": 0.6131080499354283, "grad_norm": 1.9080581665039062, "learning_rate": 1.6306247312938404e-05, "loss": 4.1275, "step": 11394 }, { "epoch": 0.6131618596642273, "grad_norm": 2.17256760597229, "learning_rate": 1.6302285000088573e-05, "loss": 3.4984, "step": 11395 }, { "epoch": 0.6132156693930263, "grad_norm": 1.401142954826355, "learning_rate": 1.6298322935796047e-05, "loss": 4.349, "step": 11396 }, { "epoch": 0.6132694791218253, "grad_norm": 1.6826695203781128, "learning_rate": 1.6294361120174034e-05, "loss": 4.347, "step": 11397 }, { "epoch": 0.6133232888506241, "grad_norm": 1.813464641571045, "learning_rate": 1.629039955333578e-05, "loss": 4.4464, "step": 11398 }, { "epoch": 0.6133770985794231, "grad_norm": 2.634953260421753, "learning_rate": 1.6286438235394475e-05, "loss": 3.4002, "step": 11399 }, { "epoch": 0.6134309083082221, "grad_norm": 2.723470449447632, "learning_rate": 1.628247716646333e-05, "loss": 3.2366, "step": 11400 }, { "epoch": 0.6134847180370211, "grad_norm": 3.26061749458313, "learning_rate": 1.6278516346655532e-05, "loss": 4.224, "step": 11401 }, { "epoch": 0.6135385277658201, "grad_norm": 3.136420726776123, "learning_rate": 1.6274555776084287e-05, "loss": 4.534, "step": 11402 }, { "epoch": 0.6135923374946191, "grad_norm": 2.2726387977600098, "learning_rate": 1.6270595454862764e-05, "loss": 3.8156, "step": 11403 }, { "epoch": 0.613646147223418, "grad_norm": 1.3995438814163208, "learning_rate": 1.6266635383104146e-05, "loss": 4.2684, "step": 11404 }, { "epoch": 0.6136999569522169, "grad_norm": 2.6462230682373047, "learning_rate": 1.6262675560921597e-05, "loss": 4.4342, "step": 11405 }, { "epoch": 0.6137537666810159, "grad_norm": 2.4816646575927734, "learning_rate": 1.6258715988428284e-05, "loss": 4.114, "step": 11406 }, { "epoch": 0.6138075764098149, "grad_norm": 1.4540088176727295, "learning_rate": 1.6254756665737358e-05, "loss": 4.5953, "step": 11407 }, { "epoch": 0.6138613861386139, "grad_norm": 2.089845657348633, "learning_rate": 1.6250797592961964e-05, "loss": 4.1564, "step": 11408 }, { "epoch": 0.6139151958674128, "grad_norm": 3.041084051132202, "learning_rate": 1.6246838770215233e-05, "loss": 4.1338, "step": 11409 }, { "epoch": 0.6139690055962118, "grad_norm": 1.5359599590301514, "learning_rate": 1.6242880197610315e-05, "loss": 4.0056, "step": 11410 }, { "epoch": 0.6140228153250108, "grad_norm": 2.9112842082977295, "learning_rate": 1.6238921875260326e-05, "loss": 4.0637, "step": 11411 }, { "epoch": 0.6140766250538098, "grad_norm": 2.186835527420044, "learning_rate": 1.623496380327838e-05, "loss": 3.708, "step": 11412 }, { "epoch": 0.6141304347826086, "grad_norm": 3.3717331886291504, "learning_rate": 1.6231005981777598e-05, "loss": 4.0986, "step": 11413 }, { "epoch": 0.6141842445114076, "grad_norm": 2.216762065887451, "learning_rate": 1.6227048410871085e-05, "loss": 4.0055, "step": 11414 }, { "epoch": 0.6142380542402066, "grad_norm": 2.389073133468628, "learning_rate": 1.6223091090671925e-05, "loss": 4.1114, "step": 11415 }, { "epoch": 0.6142918639690056, "grad_norm": 2.969372272491455, "learning_rate": 1.6219134021293217e-05, "loss": 3.579, "step": 11416 }, { "epoch": 0.6143456736978046, "grad_norm": 2.6477582454681396, "learning_rate": 1.6215177202848037e-05, "loss": 3.9724, "step": 11417 }, { "epoch": 0.6143994834266036, "grad_norm": 3.3203389644622803, "learning_rate": 1.6211220635449463e-05, "loss": 3.629, "step": 11418 }, { "epoch": 0.6144532931554025, "grad_norm": 1.9081422090530396, "learning_rate": 1.6207264319210568e-05, "loss": 4.2949, "step": 11419 }, { "epoch": 0.6145071028842015, "grad_norm": 2.810734748840332, "learning_rate": 1.6203308254244406e-05, "loss": 3.9275, "step": 11420 }, { "epoch": 0.6145609126130004, "grad_norm": 3.6068122386932373, "learning_rate": 1.619935244066404e-05, "loss": 3.9156, "step": 11421 }, { "epoch": 0.6146147223417994, "grad_norm": 2.8326892852783203, "learning_rate": 1.619539687858251e-05, "loss": 2.8099, "step": 11422 }, { "epoch": 0.6146685320705984, "grad_norm": 3.131823778152466, "learning_rate": 1.6191441568112852e-05, "loss": 3.7124, "step": 11423 }, { "epoch": 0.6147223417993973, "grad_norm": 2.585733652114868, "learning_rate": 1.61874865093681e-05, "loss": 4.6152, "step": 11424 }, { "epoch": 0.6147761515281963, "grad_norm": 2.2356677055358887, "learning_rate": 1.6183531702461282e-05, "loss": 4.7241, "step": 11425 }, { "epoch": 0.6148299612569953, "grad_norm": 2.0049211978912354, "learning_rate": 1.6179577147505415e-05, "loss": 4.2568, "step": 11426 }, { "epoch": 0.6148837709857943, "grad_norm": 2.5215799808502197, "learning_rate": 1.617562284461351e-05, "loss": 3.993, "step": 11427 }, { "epoch": 0.6149375807145931, "grad_norm": 3.628485679626465, "learning_rate": 1.6171668793898566e-05, "loss": 4.0541, "step": 11428 }, { "epoch": 0.6149913904433921, "grad_norm": 2.7778618335723877, "learning_rate": 1.616771499547359e-05, "loss": 3.6918, "step": 11429 }, { "epoch": 0.6150452001721911, "grad_norm": 1.7803031206130981, "learning_rate": 1.6163761449451558e-05, "loss": 3.464, "step": 11430 }, { "epoch": 0.6150990099009901, "grad_norm": 4.213052749633789, "learning_rate": 1.615980815594546e-05, "loss": 4.6191, "step": 11431 }, { "epoch": 0.6151528196297891, "grad_norm": 3.243772268295288, "learning_rate": 1.615585511506826e-05, "loss": 4.1138, "step": 11432 }, { "epoch": 0.615206629358588, "grad_norm": 1.7639644145965576, "learning_rate": 1.6151902326932938e-05, "loss": 4.4103, "step": 11433 }, { "epoch": 0.615260439087387, "grad_norm": 4.986033916473389, "learning_rate": 1.614794979165245e-05, "loss": 4.103, "step": 11434 }, { "epoch": 0.615314248816186, "grad_norm": 2.079861640930176, "learning_rate": 1.614399750933974e-05, "loss": 4.3395, "step": 11435 }, { "epoch": 0.6153680585449849, "grad_norm": 2.740206718444824, "learning_rate": 1.614004548010777e-05, "loss": 3.679, "step": 11436 }, { "epoch": 0.6154218682737839, "grad_norm": 2.0019829273223877, "learning_rate": 1.6136093704069473e-05, "loss": 3.9418, "step": 11437 }, { "epoch": 0.6154756780025828, "grad_norm": 1.5514024496078491, "learning_rate": 1.6132142181337773e-05, "loss": 3.8257, "step": 11438 }, { "epoch": 0.6155294877313818, "grad_norm": 4.019618988037109, "learning_rate": 1.6128190912025597e-05, "loss": 3.6257, "step": 11439 }, { "epoch": 0.6155832974601808, "grad_norm": 3.042898178100586, "learning_rate": 1.6124239896245857e-05, "loss": 3.2005, "step": 11440 }, { "epoch": 0.6156371071889798, "grad_norm": 2.410318374633789, "learning_rate": 1.612028913411147e-05, "loss": 4.3328, "step": 11441 }, { "epoch": 0.6156909169177788, "grad_norm": 4.442768573760986, "learning_rate": 1.611633862573534e-05, "loss": 4.2127, "step": 11442 }, { "epoch": 0.6157447266465778, "grad_norm": 2.1198995113372803, "learning_rate": 1.6112388371230352e-05, "loss": 4.2188, "step": 11443 }, { "epoch": 0.6157985363753766, "grad_norm": 1.0024720430374146, "learning_rate": 1.6108438370709404e-05, "loss": 4.3932, "step": 11444 }, { "epoch": 0.6158523461041756, "grad_norm": 1.8532344102859497, "learning_rate": 1.610448862428538e-05, "loss": 3.6638, "step": 11445 }, { "epoch": 0.6159061558329746, "grad_norm": 2.339305877685547, "learning_rate": 1.6100539132071135e-05, "loss": 4.0387, "step": 11446 }, { "epoch": 0.6159599655617736, "grad_norm": 2.3824357986450195, "learning_rate": 1.6096589894179547e-05, "loss": 4.1582, "step": 11447 }, { "epoch": 0.6160137752905726, "grad_norm": 2.2458720207214355, "learning_rate": 1.6092640910723467e-05, "loss": 4.4562, "step": 11448 }, { "epoch": 0.6160675850193715, "grad_norm": 1.850455641746521, "learning_rate": 1.6088692181815756e-05, "loss": 3.7098, "step": 11449 }, { "epoch": 0.6161213947481705, "grad_norm": 2.560534954071045, "learning_rate": 1.6084743707569257e-05, "loss": 4.1792, "step": 11450 }, { "epoch": 0.6161752044769694, "grad_norm": 1.4328484535217285, "learning_rate": 1.6080795488096796e-05, "loss": 3.4885, "step": 11451 }, { "epoch": 0.6162290142057684, "grad_norm": 3.630192756652832, "learning_rate": 1.607684752351122e-05, "loss": 3.6358, "step": 11452 }, { "epoch": 0.6162828239345673, "grad_norm": 2.7015252113342285, "learning_rate": 1.6072899813925337e-05, "loss": 4.4496, "step": 11453 }, { "epoch": 0.6163366336633663, "grad_norm": 2.043520212173462, "learning_rate": 1.6068952359451967e-05, "loss": 4.0603, "step": 11454 }, { "epoch": 0.6163904433921653, "grad_norm": 2.5280070304870605, "learning_rate": 1.6065005160203912e-05, "loss": 3.7063, "step": 11455 }, { "epoch": 0.6164442531209643, "grad_norm": 1.9929237365722656, "learning_rate": 1.6061058216293983e-05, "loss": 4.5489, "step": 11456 }, { "epoch": 0.6164980628497633, "grad_norm": 2.287374258041382, "learning_rate": 1.605711152783496e-05, "loss": 4.1598, "step": 11457 }, { "epoch": 0.6165518725785623, "grad_norm": 2.652935266494751, "learning_rate": 1.605316509493964e-05, "loss": 3.9572, "step": 11458 }, { "epoch": 0.6166056823073611, "grad_norm": 3.502772092819214, "learning_rate": 1.60492189177208e-05, "loss": 3.6064, "step": 11459 }, { "epoch": 0.6166594920361601, "grad_norm": 2.777358055114746, "learning_rate": 1.6045272996291212e-05, "loss": 4.1392, "step": 11460 }, { "epoch": 0.6167133017649591, "grad_norm": 3.157076835632324, "learning_rate": 1.604132733076363e-05, "loss": 4.3152, "step": 11461 }, { "epoch": 0.6167671114937581, "grad_norm": 2.288831949234009, "learning_rate": 1.6037381921250822e-05, "loss": 3.9631, "step": 11462 }, { "epoch": 0.616820921222557, "grad_norm": 2.703660249710083, "learning_rate": 1.6033436767865524e-05, "loss": 4.0177, "step": 11463 }, { "epoch": 0.616874730951356, "grad_norm": 3.0076916217803955, "learning_rate": 1.602949187072049e-05, "loss": 3.859, "step": 11464 }, { "epoch": 0.616928540680155, "grad_norm": 3.173874855041504, "learning_rate": 1.6025547229928452e-05, "loss": 3.7915, "step": 11465 }, { "epoch": 0.6169823504089539, "grad_norm": 3.2700672149658203, "learning_rate": 1.602160284560213e-05, "loss": 3.2398, "step": 11466 }, { "epoch": 0.6170361601377529, "grad_norm": 3.3292462825775146, "learning_rate": 1.6017658717854262e-05, "loss": 3.8813, "step": 11467 }, { "epoch": 0.6170899698665518, "grad_norm": 2.2576496601104736, "learning_rate": 1.6013714846797537e-05, "loss": 3.9152, "step": 11468 }, { "epoch": 0.6171437795953508, "grad_norm": 2.280290126800537, "learning_rate": 1.6009771232544674e-05, "loss": 4.039, "step": 11469 }, { "epoch": 0.6171975893241498, "grad_norm": 1.9022406339645386, "learning_rate": 1.6005827875208372e-05, "loss": 4.0078, "step": 11470 }, { "epoch": 0.6172513990529488, "grad_norm": 3.1548831462860107, "learning_rate": 1.6001884774901312e-05, "loss": 3.9405, "step": 11471 }, { "epoch": 0.6173052087817478, "grad_norm": 3.466829776763916, "learning_rate": 1.599794193173618e-05, "loss": 3.6209, "step": 11472 }, { "epoch": 0.6173590185105468, "grad_norm": 1.8626575469970703, "learning_rate": 1.5993999345825667e-05, "loss": 3.9476, "step": 11473 }, { "epoch": 0.6174128282393456, "grad_norm": 3.6123528480529785, "learning_rate": 1.5990057017282417e-05, "loss": 3.8455, "step": 11474 }, { "epoch": 0.6174666379681446, "grad_norm": 2.8070566654205322, "learning_rate": 1.598611494621912e-05, "loss": 3.6079, "step": 11475 }, { "epoch": 0.6175204476969436, "grad_norm": 2.5927510261535645, "learning_rate": 1.59821731327484e-05, "loss": 3.6517, "step": 11476 }, { "epoch": 0.6175742574257426, "grad_norm": 2.1972811222076416, "learning_rate": 1.5978231576982923e-05, "loss": 4.0348, "step": 11477 }, { "epoch": 0.6176280671545415, "grad_norm": 3.1918561458587646, "learning_rate": 1.5974290279035316e-05, "loss": 3.805, "step": 11478 }, { "epoch": 0.6176818768833405, "grad_norm": 3.164985418319702, "learning_rate": 1.5970349239018216e-05, "loss": 3.8933, "step": 11479 }, { "epoch": 0.6177356866121395, "grad_norm": 2.1731672286987305, "learning_rate": 1.5966408457044252e-05, "loss": 3.5871, "step": 11480 }, { "epoch": 0.6177894963409385, "grad_norm": 1.9281738996505737, "learning_rate": 1.5962467933226032e-05, "loss": 3.8942, "step": 11481 }, { "epoch": 0.6178433060697374, "grad_norm": 2.522622585296631, "learning_rate": 1.595852766767617e-05, "loss": 3.707, "step": 11482 }, { "epoch": 0.6178971157985363, "grad_norm": 1.2294689416885376, "learning_rate": 1.5954587660507282e-05, "loss": 4.4888, "step": 11483 }, { "epoch": 0.6179509255273353, "grad_norm": 2.934643268585205, "learning_rate": 1.5950647911831938e-05, "loss": 3.8934, "step": 11484 }, { "epoch": 0.6180047352561343, "grad_norm": 1.4089754819869995, "learning_rate": 1.594670842176274e-05, "loss": 4.6359, "step": 11485 }, { "epoch": 0.6180585449849333, "grad_norm": 1.960703730583191, "learning_rate": 1.594276919041226e-05, "loss": 4.3444, "step": 11486 }, { "epoch": 0.6181123547137323, "grad_norm": 2.2674272060394287, "learning_rate": 1.593883021789308e-05, "loss": 3.3867, "step": 11487 }, { "epoch": 0.6181661644425313, "grad_norm": 1.9203249216079712, "learning_rate": 1.5934891504317763e-05, "loss": 4.1182, "step": 11488 }, { "epoch": 0.6182199741713301, "grad_norm": 1.755987524986267, "learning_rate": 1.593095304979885e-05, "loss": 4.1492, "step": 11489 }, { "epoch": 0.6182737839001291, "grad_norm": 2.196953535079956, "learning_rate": 1.592701485444893e-05, "loss": 3.9122, "step": 11490 }, { "epoch": 0.6183275936289281, "grad_norm": 1.9932805299758911, "learning_rate": 1.592307691838051e-05, "loss": 4.1452, "step": 11491 }, { "epoch": 0.6183814033577271, "grad_norm": 2.1324005126953125, "learning_rate": 1.5919139241706135e-05, "loss": 4.2158, "step": 11492 }, { "epoch": 0.618435213086526, "grad_norm": 2.1729273796081543, "learning_rate": 1.591520182453834e-05, "loss": 4.3874, "step": 11493 }, { "epoch": 0.618489022815325, "grad_norm": 4.793673515319824, "learning_rate": 1.5911264666989633e-05, "loss": 3.844, "step": 11494 }, { "epoch": 0.618542832544124, "grad_norm": 2.4591054916381836, "learning_rate": 1.5907327769172544e-05, "loss": 4.0935, "step": 11495 }, { "epoch": 0.618596642272923, "grad_norm": 2.8117287158966064, "learning_rate": 1.590339113119957e-05, "loss": 4.1065, "step": 11496 }, { "epoch": 0.6186504520017219, "grad_norm": 2.0249483585357666, "learning_rate": 1.5899454753183204e-05, "loss": 4.6163, "step": 11497 }, { "epoch": 0.6187042617305208, "grad_norm": 2.38784122467041, "learning_rate": 1.5895518635235964e-05, "loss": 4.1006, "step": 11498 }, { "epoch": 0.6187580714593198, "grad_norm": 1.572960615158081, "learning_rate": 1.589158277747029e-05, "loss": 4.0235, "step": 11499 }, { "epoch": 0.6188118811881188, "grad_norm": 2.980562448501587, "learning_rate": 1.588764717999869e-05, "loss": 3.0002, "step": 11500 }, { "epoch": 0.6188656909169178, "grad_norm": 2.023634672164917, "learning_rate": 1.5883711842933625e-05, "loss": 4.0944, "step": 11501 }, { "epoch": 0.6189195006457168, "grad_norm": 2.193681001663208, "learning_rate": 1.587977676638755e-05, "loss": 4.2335, "step": 11502 }, { "epoch": 0.6189733103745158, "grad_norm": 2.5873351097106934, "learning_rate": 1.587584195047293e-05, "loss": 4.2554, "step": 11503 }, { "epoch": 0.6190271201033147, "grad_norm": 1.7191712856292725, "learning_rate": 1.5871907395302208e-05, "loss": 4.0394, "step": 11504 }, { "epoch": 0.6190809298321136, "grad_norm": 3.7009129524230957, "learning_rate": 1.5867973100987812e-05, "loss": 4.3709, "step": 11505 }, { "epoch": 0.6191347395609126, "grad_norm": 2.876328706741333, "learning_rate": 1.58640390676422e-05, "loss": 4.2935, "step": 11506 }, { "epoch": 0.6191885492897116, "grad_norm": 2.848144054412842, "learning_rate": 1.5860105295377764e-05, "loss": 3.9884, "step": 11507 }, { "epoch": 0.6192423590185105, "grad_norm": 2.3157153129577637, "learning_rate": 1.585617178430694e-05, "loss": 3.4591, "step": 11508 }, { "epoch": 0.6192961687473095, "grad_norm": 1.6681658029556274, "learning_rate": 1.585223853454213e-05, "loss": 4.2012, "step": 11509 }, { "epoch": 0.6193499784761085, "grad_norm": 1.4040952920913696, "learning_rate": 1.5848305546195734e-05, "loss": 4.7938, "step": 11510 }, { "epoch": 0.6194037882049075, "grad_norm": 1.5351701974868774, "learning_rate": 1.5844372819380158e-05, "loss": 3.908, "step": 11511 }, { "epoch": 0.6194575979337064, "grad_norm": 2.642155408859253, "learning_rate": 1.5840440354207777e-05, "loss": 3.9219, "step": 11512 }, { "epoch": 0.6195114076625053, "grad_norm": 2.278151750564575, "learning_rate": 1.5836508150790982e-05, "loss": 3.8914, "step": 11513 }, { "epoch": 0.6195652173913043, "grad_norm": 2.3327770233154297, "learning_rate": 1.5832576209242128e-05, "loss": 4.2085, "step": 11514 }, { "epoch": 0.6196190271201033, "grad_norm": 1.7627222537994385, "learning_rate": 1.582864452967359e-05, "loss": 4.014, "step": 11515 }, { "epoch": 0.6196728368489023, "grad_norm": 2.603635311126709, "learning_rate": 1.5824713112197727e-05, "loss": 3.2177, "step": 11516 }, { "epoch": 0.6197266465777013, "grad_norm": 2.6684305667877197, "learning_rate": 1.5820781956926877e-05, "loss": 3.359, "step": 11517 }, { "epoch": 0.6197804563065002, "grad_norm": 1.3213411569595337, "learning_rate": 1.5816851063973397e-05, "loss": 4.6027, "step": 11518 }, { "epoch": 0.6198342660352992, "grad_norm": 3.031362533569336, "learning_rate": 1.581292043344961e-05, "loss": 4.39, "step": 11519 }, { "epoch": 0.6198880757640981, "grad_norm": 2.5111989974975586, "learning_rate": 1.5808990065467844e-05, "loss": 3.5512, "step": 11520 }, { "epoch": 0.6199418854928971, "grad_norm": 2.1962008476257324, "learning_rate": 1.5805059960140435e-05, "loss": 3.7522, "step": 11521 }, { "epoch": 0.6199956952216961, "grad_norm": 2.8119285106658936, "learning_rate": 1.5801130117579668e-05, "loss": 3.9327, "step": 11522 }, { "epoch": 0.620049504950495, "grad_norm": 2.0617835521698, "learning_rate": 1.5797200537897867e-05, "loss": 4.2613, "step": 11523 }, { "epoch": 0.620103314679294, "grad_norm": 2.781672716140747, "learning_rate": 1.5793271221207317e-05, "loss": 4.3087, "step": 11524 }, { "epoch": 0.620157124408093, "grad_norm": 2.9307916164398193, "learning_rate": 1.578934216762031e-05, "loss": 3.5363, "step": 11525 }, { "epoch": 0.620210934136892, "grad_norm": 2.3894453048706055, "learning_rate": 1.5785413377249134e-05, "loss": 3.9118, "step": 11526 }, { "epoch": 0.620264743865691, "grad_norm": 3.111419439315796, "learning_rate": 1.578148485020606e-05, "loss": 3.3056, "step": 11527 }, { "epoch": 0.6203185535944898, "grad_norm": 2.730725049972534, "learning_rate": 1.577755658660335e-05, "loss": 3.1097, "step": 11528 }, { "epoch": 0.6203723633232888, "grad_norm": 3.9094481468200684, "learning_rate": 1.5773628586553278e-05, "loss": 3.1705, "step": 11529 }, { "epoch": 0.6204261730520878, "grad_norm": 1.9238598346710205, "learning_rate": 1.5769700850168073e-05, "loss": 4.4984, "step": 11530 }, { "epoch": 0.6204799827808868, "grad_norm": 1.5936437845230103, "learning_rate": 1.5765773377559997e-05, "loss": 4.4439, "step": 11531 }, { "epoch": 0.6205337925096858, "grad_norm": 2.2826266288757324, "learning_rate": 1.576184616884128e-05, "loss": 3.7902, "step": 11532 }, { "epoch": 0.6205876022384847, "grad_norm": 3.3654558658599854, "learning_rate": 1.5757919224124144e-05, "loss": 4.0184, "step": 11533 }, { "epoch": 0.6206414119672837, "grad_norm": 2.3102004528045654, "learning_rate": 1.575399254352083e-05, "loss": 4.286, "step": 11534 }, { "epoch": 0.6206952216960826, "grad_norm": 3.358276128768921, "learning_rate": 1.5750066127143535e-05, "loss": 4.1872, "step": 11535 }, { "epoch": 0.6207490314248816, "grad_norm": 2.842193603515625, "learning_rate": 1.574613997510448e-05, "loss": 3.9174, "step": 11536 }, { "epoch": 0.6208028411536806, "grad_norm": 2.6670660972595215, "learning_rate": 1.5742214087515845e-05, "loss": 4.366, "step": 11537 }, { "epoch": 0.6208566508824795, "grad_norm": 2.7475106716156006, "learning_rate": 1.5738288464489824e-05, "loss": 3.5649, "step": 11538 }, { "epoch": 0.6209104606112785, "grad_norm": 2.621335983276367, "learning_rate": 1.5734363106138617e-05, "loss": 3.2054, "step": 11539 }, { "epoch": 0.6209642703400775, "grad_norm": 3.5897130966186523, "learning_rate": 1.573043801257439e-05, "loss": 3.7783, "step": 11540 }, { "epoch": 0.6210180800688765, "grad_norm": 2.9131791591644287, "learning_rate": 1.572651318390931e-05, "loss": 3.5383, "step": 11541 }, { "epoch": 0.6210718897976755, "grad_norm": 3.105074167251587, "learning_rate": 1.572258862025554e-05, "loss": 3.752, "step": 11542 }, { "epoch": 0.6211256995264743, "grad_norm": 2.2166080474853516, "learning_rate": 1.571866432172524e-05, "loss": 3.5312, "step": 11543 }, { "epoch": 0.6211795092552733, "grad_norm": 2.832233428955078, "learning_rate": 1.5714740288430548e-05, "loss": 4.1696, "step": 11544 }, { "epoch": 0.6212333189840723, "grad_norm": 2.03495454788208, "learning_rate": 1.57108165204836e-05, "loss": 2.9151, "step": 11545 }, { "epoch": 0.6212871287128713, "grad_norm": 2.4818668365478516, "learning_rate": 1.570689301799653e-05, "loss": 3.1838, "step": 11546 }, { "epoch": 0.6213409384416703, "grad_norm": 3.7056379318237305, "learning_rate": 1.5702969781081468e-05, "loss": 4.1684, "step": 11547 }, { "epoch": 0.6213947481704692, "grad_norm": 2.0929641723632812, "learning_rate": 1.5699046809850514e-05, "loss": 3.6412, "step": 11548 }, { "epoch": 0.6214485578992682, "grad_norm": 3.042623996734619, "learning_rate": 1.569512410441579e-05, "loss": 4.282, "step": 11549 }, { "epoch": 0.6215023676280672, "grad_norm": 3.3376212120056152, "learning_rate": 1.56912016648894e-05, "loss": 3.5731, "step": 11550 }, { "epoch": 0.6215561773568661, "grad_norm": 2.72965669631958, "learning_rate": 1.5687279491383417e-05, "loss": 3.9263, "step": 11551 }, { "epoch": 0.6216099870856651, "grad_norm": 3.297431707382202, "learning_rate": 1.5683357584009954e-05, "loss": 3.7648, "step": 11552 }, { "epoch": 0.621663796814464, "grad_norm": 1.975050687789917, "learning_rate": 1.5679435942881058e-05, "loss": 4.6466, "step": 11553 }, { "epoch": 0.621717606543263, "grad_norm": 2.459602117538452, "learning_rate": 1.5675514568108817e-05, "loss": 3.4558, "step": 11554 }, { "epoch": 0.621771416272062, "grad_norm": 1.830108404159546, "learning_rate": 1.5671593459805288e-05, "loss": 4.0239, "step": 11555 }, { "epoch": 0.621825226000861, "grad_norm": 1.6619396209716797, "learning_rate": 1.5667672618082526e-05, "loss": 3.8108, "step": 11556 }, { "epoch": 0.62187903572966, "grad_norm": 1.9522204399108887, "learning_rate": 1.5663752043052583e-05, "loss": 4.2768, "step": 11557 }, { "epoch": 0.6219328454584588, "grad_norm": 2.0833492279052734, "learning_rate": 1.5659831734827496e-05, "loss": 4.4937, "step": 11558 }, { "epoch": 0.6219866551872578, "grad_norm": 3.2973921298980713, "learning_rate": 1.5655911693519302e-05, "loss": 3.7248, "step": 11559 }, { "epoch": 0.6220404649160568, "grad_norm": 2.502122640609741, "learning_rate": 1.565199191924001e-05, "loss": 3.8462, "step": 11560 }, { "epoch": 0.6220942746448558, "grad_norm": 3.9214911460876465, "learning_rate": 1.5648072412101644e-05, "loss": 4.295, "step": 11561 }, { "epoch": 0.6221480843736548, "grad_norm": 1.9429959058761597, "learning_rate": 1.5644153172216218e-05, "loss": 4.1211, "step": 11562 }, { "epoch": 0.6222018941024537, "grad_norm": 3.230447292327881, "learning_rate": 1.5640234199695735e-05, "loss": 3.8757, "step": 11563 }, { "epoch": 0.6222557038312527, "grad_norm": 3.280597686767578, "learning_rate": 1.5636315494652177e-05, "loss": 3.0796, "step": 11564 }, { "epoch": 0.6223095135600517, "grad_norm": 3.140244722366333, "learning_rate": 1.5632397057197538e-05, "loss": 4.4278, "step": 11565 }, { "epoch": 0.6223633232888506, "grad_norm": 1.550352692604065, "learning_rate": 1.5628478887443796e-05, "loss": 4.6475, "step": 11566 }, { "epoch": 0.6224171330176496, "grad_norm": 2.53507924079895, "learning_rate": 1.562456098550293e-05, "loss": 3.7373, "step": 11567 }, { "epoch": 0.6224709427464485, "grad_norm": 2.571638345718384, "learning_rate": 1.5620643351486884e-05, "loss": 4.1685, "step": 11568 }, { "epoch": 0.6225247524752475, "grad_norm": 1.5267338752746582, "learning_rate": 1.561672598550762e-05, "loss": 3.8998, "step": 11569 }, { "epoch": 0.6225785622040465, "grad_norm": 2.674964427947998, "learning_rate": 1.5612808887677094e-05, "loss": 2.4388, "step": 11570 }, { "epoch": 0.6226323719328455, "grad_norm": 2.0986859798431396, "learning_rate": 1.5608892058107243e-05, "loss": 4.0416, "step": 11571 }, { "epoch": 0.6226861816616445, "grad_norm": 3.487159013748169, "learning_rate": 1.560497549690999e-05, "loss": 3.9321, "step": 11572 }, { "epoch": 0.6227399913904433, "grad_norm": 1.8381627798080444, "learning_rate": 1.560105920419728e-05, "loss": 3.8072, "step": 11573 }, { "epoch": 0.6227938011192423, "grad_norm": 4.857780933380127, "learning_rate": 1.5597143180081015e-05, "loss": 3.3966, "step": 11574 }, { "epoch": 0.6228476108480413, "grad_norm": 3.3309476375579834, "learning_rate": 1.5593227424673103e-05, "loss": 4.0008, "step": 11575 }, { "epoch": 0.6229014205768403, "grad_norm": 3.270564079284668, "learning_rate": 1.558931193808545e-05, "loss": 3.9787, "step": 11576 }, { "epoch": 0.6229552303056393, "grad_norm": 3.0262367725372314, "learning_rate": 1.5585396720429952e-05, "loss": 3.3707, "step": 11577 }, { "epoch": 0.6230090400344382, "grad_norm": 2.6005325317382812, "learning_rate": 1.558148177181849e-05, "loss": 3.7765, "step": 11578 }, { "epoch": 0.6230628497632372, "grad_norm": 2.5873053073883057, "learning_rate": 1.5577567092362944e-05, "loss": 4.2913, "step": 11579 }, { "epoch": 0.6231166594920362, "grad_norm": 2.4504408836364746, "learning_rate": 1.5573652682175194e-05, "loss": 4.1299, "step": 11580 }, { "epoch": 0.6231704692208351, "grad_norm": 4.4715681076049805, "learning_rate": 1.5569738541367097e-05, "loss": 3.2843, "step": 11581 }, { "epoch": 0.6232242789496341, "grad_norm": 3.365968942642212, "learning_rate": 1.5565824670050507e-05, "loss": 3.1064, "step": 11582 }, { "epoch": 0.623278088678433, "grad_norm": 1.9965307712554932, "learning_rate": 1.5561911068337274e-05, "loss": 4.0934, "step": 11583 }, { "epoch": 0.623331898407232, "grad_norm": 2.8845441341400146, "learning_rate": 1.555799773633923e-05, "loss": 2.9117, "step": 11584 }, { "epoch": 0.623385708136031, "grad_norm": 2.1227924823760986, "learning_rate": 1.5554084674168217e-05, "loss": 3.943, "step": 11585 }, { "epoch": 0.62343951786483, "grad_norm": 2.520808219909668, "learning_rate": 1.555017188193606e-05, "loss": 4.3009, "step": 11586 }, { "epoch": 0.623493327593629, "grad_norm": 1.6813126802444458, "learning_rate": 1.5546259359754573e-05, "loss": 4.2753, "step": 11587 }, { "epoch": 0.623547137322428, "grad_norm": 3.0918900966644287, "learning_rate": 1.5542347107735568e-05, "loss": 3.7878, "step": 11588 }, { "epoch": 0.6236009470512268, "grad_norm": 1.7440261840820312, "learning_rate": 1.553843512599084e-05, "loss": 4.4001, "step": 11589 }, { "epoch": 0.6236547567800258, "grad_norm": 2.231375217437744, "learning_rate": 1.5534523414632197e-05, "loss": 4.1365, "step": 11590 }, { "epoch": 0.6237085665088248, "grad_norm": 4.430942535400391, "learning_rate": 1.5530611973771407e-05, "loss": 3.3934, "step": 11591 }, { "epoch": 0.6237623762376238, "grad_norm": 1.6711536645889282, "learning_rate": 1.5526700803520257e-05, "loss": 4.3855, "step": 11592 }, { "epoch": 0.6238161859664227, "grad_norm": 1.8452253341674805, "learning_rate": 1.552278990399052e-05, "loss": 4.4923, "step": 11593 }, { "epoch": 0.6238699956952217, "grad_norm": 1.7517759799957275, "learning_rate": 1.551887927529396e-05, "loss": 3.7378, "step": 11594 }, { "epoch": 0.6239238054240207, "grad_norm": 2.7876715660095215, "learning_rate": 1.5514968917542317e-05, "loss": 4.2831, "step": 11595 }, { "epoch": 0.6239776151528196, "grad_norm": 1.2006992101669312, "learning_rate": 1.551105883084736e-05, "loss": 4.5341, "step": 11596 }, { "epoch": 0.6240314248816186, "grad_norm": 1.735511064529419, "learning_rate": 1.5507149015320827e-05, "loss": 4.4536, "step": 11597 }, { "epoch": 0.6240852346104175, "grad_norm": 2.9619266986846924, "learning_rate": 1.5503239471074434e-05, "loss": 3.6953, "step": 11598 }, { "epoch": 0.6241390443392165, "grad_norm": 3.4498555660247803, "learning_rate": 1.5499330198219914e-05, "loss": 3.5631, "step": 11599 }, { "epoch": 0.6241928540680155, "grad_norm": 1.9428720474243164, "learning_rate": 1.5495421196868978e-05, "loss": 4.1709, "step": 11600 }, { "epoch": 0.6242466637968145, "grad_norm": 2.042391777038574, "learning_rate": 1.5491512467133346e-05, "loss": 3.4928, "step": 11601 }, { "epoch": 0.6243004735256135, "grad_norm": 2.6202690601348877, "learning_rate": 1.548760400912471e-05, "loss": 3.8525, "step": 11602 }, { "epoch": 0.6243542832544124, "grad_norm": 2.1844024658203125, "learning_rate": 1.5483695822954764e-05, "loss": 4.0814, "step": 11603 }, { "epoch": 0.6244080929832113, "grad_norm": 2.601989984512329, "learning_rate": 1.54797879087352e-05, "loss": 4.0368, "step": 11604 }, { "epoch": 0.6244619027120103, "grad_norm": 3.1142449378967285, "learning_rate": 1.5475880266577698e-05, "loss": 3.5073, "step": 11605 }, { "epoch": 0.6245157124408093, "grad_norm": 2.9960567951202393, "learning_rate": 1.5471972896593913e-05, "loss": 3.3316, "step": 11606 }, { "epoch": 0.6245695221696083, "grad_norm": 3.23647141456604, "learning_rate": 1.546806579889551e-05, "loss": 4.0254, "step": 11607 }, { "epoch": 0.6246233318984072, "grad_norm": 1.808793544769287, "learning_rate": 1.5464158973594156e-05, "loss": 4.1942, "step": 11608 }, { "epoch": 0.6246771416272062, "grad_norm": 2.796828508377075, "learning_rate": 1.546025242080149e-05, "loss": 3.316, "step": 11609 }, { "epoch": 0.6247309513560052, "grad_norm": 1.4560922384262085, "learning_rate": 1.5456346140629145e-05, "loss": 4.3553, "step": 11610 }, { "epoch": 0.6247847610848042, "grad_norm": 1.1782562732696533, "learning_rate": 1.5452440133188762e-05, "loss": 4.2639, "step": 11611 }, { "epoch": 0.6248385708136031, "grad_norm": 6.280483722686768, "learning_rate": 1.5448534398591963e-05, "loss": 2.5092, "step": 11612 }, { "epoch": 0.624892380542402, "grad_norm": 2.7019765377044678, "learning_rate": 1.544462893695036e-05, "loss": 3.9429, "step": 11613 }, { "epoch": 0.624946190271201, "grad_norm": 3.275869607925415, "learning_rate": 1.5440723748375563e-05, "loss": 3.5979, "step": 11614 }, { "epoch": 0.625, "grad_norm": 2.4409823417663574, "learning_rate": 1.543681883297916e-05, "loss": 4.3946, "step": 11615 }, { "epoch": 0.625053809728799, "grad_norm": 2.4124138355255127, "learning_rate": 1.5432914190872757e-05, "loss": 3.6733, "step": 11616 }, { "epoch": 0.625107619457598, "grad_norm": 1.871977686882019, "learning_rate": 1.5429009822167938e-05, "loss": 4.4485, "step": 11617 }, { "epoch": 0.6251614291863969, "grad_norm": 1.5721765756607056, "learning_rate": 1.542510572697627e-05, "loss": 4.358, "step": 11618 }, { "epoch": 0.6252152389151958, "grad_norm": 2.5793583393096924, "learning_rate": 1.5421201905409326e-05, "loss": 4.0884, "step": 11619 }, { "epoch": 0.6252690486439948, "grad_norm": 3.2451581954956055, "learning_rate": 1.541729835757868e-05, "loss": 3.6212, "step": 11620 }, { "epoch": 0.6253228583727938, "grad_norm": 1.6206623315811157, "learning_rate": 1.5413395083595864e-05, "loss": 4.1101, "step": 11621 }, { "epoch": 0.6253766681015928, "grad_norm": 2.663067579269409, "learning_rate": 1.540949208357243e-05, "loss": 3.5742, "step": 11622 }, { "epoch": 0.6254304778303917, "grad_norm": 2.924802541732788, "learning_rate": 1.5405589357619916e-05, "loss": 3.2403, "step": 11623 }, { "epoch": 0.6254842875591907, "grad_norm": 2.437710762023926, "learning_rate": 1.5401686905849855e-05, "loss": 4.2753, "step": 11624 }, { "epoch": 0.6255380972879897, "grad_norm": 2.121305465698242, "learning_rate": 1.5397784728373765e-05, "loss": 3.6715, "step": 11625 }, { "epoch": 0.6255919070167887, "grad_norm": 2.7592289447784424, "learning_rate": 1.5393882825303156e-05, "loss": 3.2484, "step": 11626 }, { "epoch": 0.6256457167455876, "grad_norm": 2.48762583732605, "learning_rate": 1.5389981196749546e-05, "loss": 4.0394, "step": 11627 }, { "epoch": 0.6256995264743865, "grad_norm": 3.718886137008667, "learning_rate": 1.5386079842824428e-05, "loss": 3.5379, "step": 11628 }, { "epoch": 0.6257533362031855, "grad_norm": 1.9288084506988525, "learning_rate": 1.5382178763639284e-05, "loss": 3.6181, "step": 11629 }, { "epoch": 0.6258071459319845, "grad_norm": 3.3742105960845947, "learning_rate": 1.5378277959305598e-05, "loss": 3.0999, "step": 11630 }, { "epoch": 0.6258609556607835, "grad_norm": 2.182671308517456, "learning_rate": 1.5374377429934852e-05, "loss": 4.1505, "step": 11631 }, { "epoch": 0.6259147653895825, "grad_norm": 1.7536239624023438, "learning_rate": 1.537047717563851e-05, "loss": 4.3262, "step": 11632 }, { "epoch": 0.6259685751183814, "grad_norm": 2.534238576889038, "learning_rate": 1.5366577196528025e-05, "loss": 3.4728, "step": 11633 }, { "epoch": 0.6260223848471804, "grad_norm": 2.810776472091675, "learning_rate": 1.5362677492714862e-05, "loss": 4.5667, "step": 11634 }, { "epoch": 0.6260761945759793, "grad_norm": 3.8247079849243164, "learning_rate": 1.535877806431045e-05, "loss": 3.5437, "step": 11635 }, { "epoch": 0.6261300043047783, "grad_norm": 2.1064188480377197, "learning_rate": 1.5354878911426236e-05, "loss": 4.3827, "step": 11636 }, { "epoch": 0.6261838140335773, "grad_norm": 2.213395595550537, "learning_rate": 1.5350980034173634e-05, "loss": 4.0612, "step": 11637 }, { "epoch": 0.6262376237623762, "grad_norm": 2.3115108013153076, "learning_rate": 1.534708143266407e-05, "loss": 3.7674, "step": 11638 }, { "epoch": 0.6262914334911752, "grad_norm": 2.2429192066192627, "learning_rate": 1.534318310700895e-05, "loss": 3.9906, "step": 11639 }, { "epoch": 0.6263452432199742, "grad_norm": 2.896775722503662, "learning_rate": 1.533928505731969e-05, "loss": 4.0986, "step": 11640 }, { "epoch": 0.6263990529487732, "grad_norm": 3.035938024520874, "learning_rate": 1.5335387283707675e-05, "loss": 4.1695, "step": 11641 }, { "epoch": 0.626452862677572, "grad_norm": 1.3354575634002686, "learning_rate": 1.5331489786284297e-05, "loss": 4.3081, "step": 11642 }, { "epoch": 0.626506672406371, "grad_norm": 1.8092131614685059, "learning_rate": 1.5327592565160945e-05, "loss": 4.419, "step": 11643 }, { "epoch": 0.62656048213517, "grad_norm": 2.2540671825408936, "learning_rate": 1.5323695620448974e-05, "loss": 3.795, "step": 11644 }, { "epoch": 0.626614291863969, "grad_norm": 1.6712456941604614, "learning_rate": 1.5319798952259755e-05, "loss": 4.3986, "step": 11645 }, { "epoch": 0.626668101592768, "grad_norm": 1.3739686012268066, "learning_rate": 1.5315902560704646e-05, "loss": 4.4201, "step": 11646 }, { "epoch": 0.626721911321567, "grad_norm": 3.5636861324310303, "learning_rate": 1.5312006445894994e-05, "loss": 3.4862, "step": 11647 }, { "epoch": 0.6267757210503659, "grad_norm": 3.231781244277954, "learning_rate": 1.5308110607942144e-05, "loss": 3.5224, "step": 11648 }, { "epoch": 0.6268295307791649, "grad_norm": 1.5197911262512207, "learning_rate": 1.5304215046957415e-05, "loss": 4.182, "step": 11649 }, { "epoch": 0.6268833405079638, "grad_norm": 2.3051962852478027, "learning_rate": 1.530031976305215e-05, "loss": 4.0284, "step": 11650 }, { "epoch": 0.6269371502367628, "grad_norm": 2.01615834236145, "learning_rate": 1.5296424756337664e-05, "loss": 3.9715, "step": 11651 }, { "epoch": 0.6269909599655618, "grad_norm": 3.434352159500122, "learning_rate": 1.529253002692525e-05, "loss": 3.9, "step": 11652 }, { "epoch": 0.6270447696943607, "grad_norm": 1.7702585458755493, "learning_rate": 1.528863557492622e-05, "loss": 3.8618, "step": 11653 }, { "epoch": 0.6270985794231597, "grad_norm": 1.935503363609314, "learning_rate": 1.5284741400451856e-05, "loss": 3.7205, "step": 11654 }, { "epoch": 0.6271523891519587, "grad_norm": 3.3828325271606445, "learning_rate": 1.528084750361346e-05, "loss": 3.511, "step": 11655 }, { "epoch": 0.6272061988807577, "grad_norm": 2.637406587600708, "learning_rate": 1.5276953884522298e-05, "loss": 4.0049, "step": 11656 }, { "epoch": 0.6272600086095567, "grad_norm": 2.6466197967529297, "learning_rate": 1.527306054328964e-05, "loss": 4.4259, "step": 11657 }, { "epoch": 0.6273138183383555, "grad_norm": 2.5818440914154053, "learning_rate": 1.5269167480026757e-05, "loss": 3.9101, "step": 11658 }, { "epoch": 0.6273676280671545, "grad_norm": 2.821171283721924, "learning_rate": 1.5265274694844894e-05, "loss": 4.279, "step": 11659 }, { "epoch": 0.6274214377959535, "grad_norm": 1.4898380041122437, "learning_rate": 1.5261382187855296e-05, "loss": 4.425, "step": 11660 }, { "epoch": 0.6274752475247525, "grad_norm": 3.898689031600952, "learning_rate": 1.525748995916919e-05, "loss": 3.5834, "step": 11661 }, { "epoch": 0.6275290572535515, "grad_norm": 1.7397257089614868, "learning_rate": 1.5253598008897829e-05, "loss": 3.7397, "step": 11662 }, { "epoch": 0.6275828669823504, "grad_norm": 2.319122076034546, "learning_rate": 1.5249706337152419e-05, "loss": 4.7461, "step": 11663 }, { "epoch": 0.6276366767111494, "grad_norm": 1.5891231298446655, "learning_rate": 1.5245814944044173e-05, "loss": 4.0193, "step": 11664 }, { "epoch": 0.6276904864399483, "grad_norm": 1.8414113521575928, "learning_rate": 1.5241923829684301e-05, "loss": 4.3406, "step": 11665 }, { "epoch": 0.6277442961687473, "grad_norm": 2.4787704944610596, "learning_rate": 1.523803299418401e-05, "loss": 3.86, "step": 11666 }, { "epoch": 0.6277981058975463, "grad_norm": 2.3130366802215576, "learning_rate": 1.5234142437654472e-05, "loss": 4.2065, "step": 11667 }, { "epoch": 0.6278519156263452, "grad_norm": 2.8495521545410156, "learning_rate": 1.5230252160206876e-05, "loss": 2.8645, "step": 11668 }, { "epoch": 0.6279057253551442, "grad_norm": 2.267228841781616, "learning_rate": 1.5226362161952393e-05, "loss": 4.3327, "step": 11669 }, { "epoch": 0.6279595350839432, "grad_norm": 2.915107250213623, "learning_rate": 1.5222472443002194e-05, "loss": 4.2545, "step": 11670 }, { "epoch": 0.6280133448127422, "grad_norm": 1.591381549835205, "learning_rate": 1.5218583003467435e-05, "loss": 3.754, "step": 11671 }, { "epoch": 0.6280671545415412, "grad_norm": 2.0900461673736572, "learning_rate": 1.521469384345926e-05, "loss": 4.2528, "step": 11672 }, { "epoch": 0.62812096427034, "grad_norm": 1.9446614980697632, "learning_rate": 1.521080496308882e-05, "loss": 3.5437, "step": 11673 }, { "epoch": 0.628174773999139, "grad_norm": 2.572421073913574, "learning_rate": 1.5206916362467249e-05, "loss": 4.2918, "step": 11674 }, { "epoch": 0.628228583727938, "grad_norm": 2.294651508331299, "learning_rate": 1.5203028041705664e-05, "loss": 4.1304, "step": 11675 }, { "epoch": 0.628282393456737, "grad_norm": 2.9499638080596924, "learning_rate": 1.5199140000915185e-05, "loss": 3.0888, "step": 11676 }, { "epoch": 0.628336203185536, "grad_norm": 1.8157970905303955, "learning_rate": 1.519525224020692e-05, "loss": 4.0495, "step": 11677 }, { "epoch": 0.6283900129143349, "grad_norm": 1.7783030271530151, "learning_rate": 1.5191364759691978e-05, "loss": 4.0009, "step": 11678 }, { "epoch": 0.6284438226431339, "grad_norm": 4.078184604644775, "learning_rate": 1.518747755948145e-05, "loss": 3.6659, "step": 11679 }, { "epoch": 0.6284976323719328, "grad_norm": 3.301907777786255, "learning_rate": 1.5183590639686418e-05, "loss": 4.1202, "step": 11680 }, { "epoch": 0.6285514421007318, "grad_norm": 2.8909575939178467, "learning_rate": 1.5179704000417974e-05, "loss": 4.03, "step": 11681 }, { "epoch": 0.6286052518295308, "grad_norm": 2.795974016189575, "learning_rate": 1.5175817641787163e-05, "loss": 4.0909, "step": 11682 }, { "epoch": 0.6286590615583297, "grad_norm": 1.867891550064087, "learning_rate": 1.5171931563905064e-05, "loss": 4.0982, "step": 11683 }, { "epoch": 0.6287128712871287, "grad_norm": 2.5214951038360596, "learning_rate": 1.5168045766882727e-05, "loss": 3.9288, "step": 11684 }, { "epoch": 0.6287666810159277, "grad_norm": 2.3100526332855225, "learning_rate": 1.5164160250831194e-05, "loss": 4.8179, "step": 11685 }, { "epoch": 0.6288204907447267, "grad_norm": 2.468886375427246, "learning_rate": 1.5160275015861508e-05, "loss": 4.0151, "step": 11686 }, { "epoch": 0.6288743004735257, "grad_norm": 2.2234716415405273, "learning_rate": 1.5156390062084697e-05, "loss": 3.6662, "step": 11687 }, { "epoch": 0.6289281102023245, "grad_norm": 2.4499599933624268, "learning_rate": 1.5152505389611776e-05, "loss": 4.0536, "step": 11688 }, { "epoch": 0.6289819199311235, "grad_norm": 2.5250391960144043, "learning_rate": 1.5148620998553776e-05, "loss": 4.2939, "step": 11689 }, { "epoch": 0.6290357296599225, "grad_norm": 3.1452929973602295, "learning_rate": 1.5144736889021684e-05, "loss": 3.7616, "step": 11690 }, { "epoch": 0.6290895393887215, "grad_norm": 1.9175313711166382, "learning_rate": 1.5140853061126506e-05, "loss": 4.5508, "step": 11691 }, { "epoch": 0.6291433491175205, "grad_norm": 2.3146731853485107, "learning_rate": 1.5136969514979221e-05, "loss": 4.2315, "step": 11692 }, { "epoch": 0.6291971588463194, "grad_norm": 2.34454083442688, "learning_rate": 1.5133086250690828e-05, "loss": 3.6053, "step": 11693 }, { "epoch": 0.6292509685751184, "grad_norm": 2.3472981452941895, "learning_rate": 1.5129203268372288e-05, "loss": 3.844, "step": 11694 }, { "epoch": 0.6293047783039174, "grad_norm": 2.5833241939544678, "learning_rate": 1.5125320568134568e-05, "loss": 4.2426, "step": 11695 }, { "epoch": 0.6293585880327163, "grad_norm": 2.1116673946380615, "learning_rate": 1.5121438150088629e-05, "loss": 3.9682, "step": 11696 }, { "epoch": 0.6294123977615153, "grad_norm": 2.3031108379364014, "learning_rate": 1.5117556014345425e-05, "loss": 3.3945, "step": 11697 }, { "epoch": 0.6294662074903142, "grad_norm": 1.4750590324401855, "learning_rate": 1.5113674161015879e-05, "loss": 4.2022, "step": 11698 }, { "epoch": 0.6295200172191132, "grad_norm": 3.170139789581299, "learning_rate": 1.5109792590210938e-05, "loss": 3.5994, "step": 11699 }, { "epoch": 0.6295738269479122, "grad_norm": 2.8605313301086426, "learning_rate": 1.510591130204152e-05, "loss": 3.6358, "step": 11700 }, { "epoch": 0.6296276366767112, "grad_norm": 1.7054940462112427, "learning_rate": 1.5102030296618547e-05, "loss": 3.8835, "step": 11701 }, { "epoch": 0.6296814464055102, "grad_norm": 2.9526145458221436, "learning_rate": 1.5098149574052929e-05, "loss": 3.7081, "step": 11702 }, { "epoch": 0.629735256134309, "grad_norm": 2.133772850036621, "learning_rate": 1.5094269134455553e-05, "loss": 4.1833, "step": 11703 }, { "epoch": 0.629789065863108, "grad_norm": 2.2493906021118164, "learning_rate": 1.509038897793734e-05, "loss": 4.4569, "step": 11704 }, { "epoch": 0.629842875591907, "grad_norm": 3.6652019023895264, "learning_rate": 1.5086509104609142e-05, "loss": 3.5184, "step": 11705 }, { "epoch": 0.629896685320706, "grad_norm": 3.136362075805664, "learning_rate": 1.5082629514581853e-05, "loss": 3.0482, "step": 11706 }, { "epoch": 0.629950495049505, "grad_norm": 2.6054277420043945, "learning_rate": 1.5078750207966335e-05, "loss": 3.7249, "step": 11707 }, { "epoch": 0.6300043047783039, "grad_norm": 2.2678871154785156, "learning_rate": 1.5074871184873451e-05, "loss": 3.7915, "step": 11708 }, { "epoch": 0.6300581145071029, "grad_norm": 2.661724328994751, "learning_rate": 1.5070992445414056e-05, "loss": 3.8145, "step": 11709 }, { "epoch": 0.6301119242359019, "grad_norm": 3.8181676864624023, "learning_rate": 1.5067113989698994e-05, "loss": 3.0788, "step": 11710 }, { "epoch": 0.6301657339647008, "grad_norm": 1.36454439163208, "learning_rate": 1.5063235817839088e-05, "loss": 3.9204, "step": 11711 }, { "epoch": 0.6302195436934998, "grad_norm": 1.922419548034668, "learning_rate": 1.5059357929945195e-05, "loss": 4.1324, "step": 11712 }, { "epoch": 0.6302733534222987, "grad_norm": 2.0798394680023193, "learning_rate": 1.5055480326128097e-05, "loss": 3.9293, "step": 11713 }, { "epoch": 0.6303271631510977, "grad_norm": 2.432520866394043, "learning_rate": 1.5051603006498633e-05, "loss": 3.9596, "step": 11714 }, { "epoch": 0.6303809728798967, "grad_norm": 3.183326482772827, "learning_rate": 1.5047725971167592e-05, "loss": 4.752, "step": 11715 }, { "epoch": 0.6304347826086957, "grad_norm": 2.841168165206909, "learning_rate": 1.504384922024577e-05, "loss": 3.3716, "step": 11716 }, { "epoch": 0.6304885923374947, "grad_norm": 2.222168445587158, "learning_rate": 1.5039972753843965e-05, "loss": 4.0134, "step": 11717 }, { "epoch": 0.6305424020662936, "grad_norm": 1.8669300079345703, "learning_rate": 1.503609657207295e-05, "loss": 4.1089, "step": 11718 }, { "epoch": 0.6305962117950925, "grad_norm": 2.8985445499420166, "learning_rate": 1.5032220675043488e-05, "loss": 4.3072, "step": 11719 }, { "epoch": 0.6306500215238915, "grad_norm": 2.891615629196167, "learning_rate": 1.5028345062866361e-05, "loss": 3.6663, "step": 11720 }, { "epoch": 0.6307038312526905, "grad_norm": 4.067286491394043, "learning_rate": 1.5024469735652306e-05, "loss": 3.4366, "step": 11721 }, { "epoch": 0.6307576409814895, "grad_norm": 2.494006395339966, "learning_rate": 1.5020594693512075e-05, "loss": 4.3947, "step": 11722 }, { "epoch": 0.6308114507102884, "grad_norm": 1.227382779121399, "learning_rate": 1.50167199365564e-05, "loss": 4.4287, "step": 11723 }, { "epoch": 0.6308652604390874, "grad_norm": 3.365882635116577, "learning_rate": 1.5012845464896021e-05, "loss": 2.9439, "step": 11724 }, { "epoch": 0.6309190701678864, "grad_norm": 2.0908827781677246, "learning_rate": 1.500897127864166e-05, "loss": 4.2524, "step": 11725 }, { "epoch": 0.6309728798966853, "grad_norm": 2.468212366104126, "learning_rate": 1.500509737790402e-05, "loss": 3.7199, "step": 11726 }, { "epoch": 0.6310266896254842, "grad_norm": 1.7705506086349487, "learning_rate": 1.500122376279383e-05, "loss": 4.1442, "step": 11727 }, { "epoch": 0.6310804993542832, "grad_norm": 2.057105302810669, "learning_rate": 1.4997350433421753e-05, "loss": 4.0571, "step": 11728 }, { "epoch": 0.6311343090830822, "grad_norm": 3.1313774585723877, "learning_rate": 1.4993477389898505e-05, "loss": 3.5882, "step": 11729 }, { "epoch": 0.6311881188118812, "grad_norm": 2.5453429222106934, "learning_rate": 1.4989604632334758e-05, "loss": 4.5048, "step": 11730 }, { "epoch": 0.6312419285406802, "grad_norm": 3.146411657333374, "learning_rate": 1.4985732160841181e-05, "loss": 4.3317, "step": 11731 }, { "epoch": 0.6312957382694792, "grad_norm": 2.2564587593078613, "learning_rate": 1.4981859975528451e-05, "loss": 3.9948, "step": 11732 }, { "epoch": 0.6313495479982781, "grad_norm": 1.817409634590149, "learning_rate": 1.4977988076507213e-05, "loss": 3.8627, "step": 11733 }, { "epoch": 0.631403357727077, "grad_norm": 2.9353907108306885, "learning_rate": 1.4974116463888115e-05, "loss": 3.8318, "step": 11734 }, { "epoch": 0.631457167455876, "grad_norm": 1.6812900304794312, "learning_rate": 1.4970245137781819e-05, "loss": 4.2484, "step": 11735 }, { "epoch": 0.631510977184675, "grad_norm": 1.2079284191131592, "learning_rate": 1.4966374098298924e-05, "loss": 4.6687, "step": 11736 }, { "epoch": 0.631564786913474, "grad_norm": 3.4264237880706787, "learning_rate": 1.4962503345550077e-05, "loss": 3.8083, "step": 11737 }, { "epoch": 0.6316185966422729, "grad_norm": 2.487766981124878, "learning_rate": 1.4958632879645884e-05, "loss": 3.8827, "step": 11738 }, { "epoch": 0.6316724063710719, "grad_norm": 3.1906797885894775, "learning_rate": 1.4954762700696952e-05, "loss": 2.4913, "step": 11739 }, { "epoch": 0.6317262160998709, "grad_norm": 2.084320545196533, "learning_rate": 1.4950892808813888e-05, "loss": 4.091, "step": 11740 }, { "epoch": 0.6317800258286699, "grad_norm": 2.745469331741333, "learning_rate": 1.494702320410728e-05, "loss": 4.4832, "step": 11741 }, { "epoch": 0.6318338355574687, "grad_norm": 2.7453737258911133, "learning_rate": 1.4943153886687702e-05, "loss": 3.8425, "step": 11742 }, { "epoch": 0.6318876452862677, "grad_norm": 1.9936907291412354, "learning_rate": 1.4939284856665752e-05, "loss": 3.4306, "step": 11743 }, { "epoch": 0.6319414550150667, "grad_norm": 2.401642084121704, "learning_rate": 1.4935416114151967e-05, "loss": 4.1813, "step": 11744 }, { "epoch": 0.6319952647438657, "grad_norm": 3.224071502685547, "learning_rate": 1.4931547659256923e-05, "loss": 3.9324, "step": 11745 }, { "epoch": 0.6320490744726647, "grad_norm": 1.9977673292160034, "learning_rate": 1.4927679492091165e-05, "loss": 4.2713, "step": 11746 }, { "epoch": 0.6321028842014637, "grad_norm": 3.0884084701538086, "learning_rate": 1.4923811612765231e-05, "loss": 3.7941, "step": 11747 }, { "epoch": 0.6321566939302626, "grad_norm": 2.182213306427002, "learning_rate": 1.4919944021389665e-05, "loss": 4.3571, "step": 11748 }, { "epoch": 0.6322105036590615, "grad_norm": 2.9672679901123047, "learning_rate": 1.4916076718074987e-05, "loss": 3.9053, "step": 11749 }, { "epoch": 0.6322643133878605, "grad_norm": 3.78338360786438, "learning_rate": 1.4912209702931718e-05, "loss": 3.9098, "step": 11750 }, { "epoch": 0.6323181231166595, "grad_norm": 4.897398948669434, "learning_rate": 1.4908342976070355e-05, "loss": 2.9264, "step": 11751 }, { "epoch": 0.6323719328454585, "grad_norm": 3.666922092437744, "learning_rate": 1.4904476537601409e-05, "loss": 3.7685, "step": 11752 }, { "epoch": 0.6324257425742574, "grad_norm": 1.8519892692565918, "learning_rate": 1.4900610387635369e-05, "loss": 4.1514, "step": 11753 }, { "epoch": 0.6324795523030564, "grad_norm": 3.5093765258789062, "learning_rate": 1.4896744526282717e-05, "loss": 2.8995, "step": 11754 }, { "epoch": 0.6325333620318554, "grad_norm": 1.5755836963653564, "learning_rate": 1.4892878953653935e-05, "loss": 4.4109, "step": 11755 }, { "epoch": 0.6325871717606544, "grad_norm": 2.602280855178833, "learning_rate": 1.4889013669859489e-05, "loss": 4.2464, "step": 11756 }, { "epoch": 0.6326409814894532, "grad_norm": 3.4055087566375732, "learning_rate": 1.488514867500983e-05, "loss": 4.23, "step": 11757 }, { "epoch": 0.6326947912182522, "grad_norm": 2.613220691680908, "learning_rate": 1.4881283969215435e-05, "loss": 3.9394, "step": 11758 }, { "epoch": 0.6327486009470512, "grad_norm": 3.8161659240722656, "learning_rate": 1.487741955258671e-05, "loss": 3.8164, "step": 11759 }, { "epoch": 0.6328024106758502, "grad_norm": 1.7810133695602417, "learning_rate": 1.4873555425234115e-05, "loss": 4.0068, "step": 11760 }, { "epoch": 0.6328562204046492, "grad_norm": 2.5916547775268555, "learning_rate": 1.4869691587268064e-05, "loss": 3.3526, "step": 11761 }, { "epoch": 0.6329100301334482, "grad_norm": 2.9086480140686035, "learning_rate": 1.4865828038798979e-05, "loss": 4.405, "step": 11762 }, { "epoch": 0.6329638398622471, "grad_norm": 3.0477123260498047, "learning_rate": 1.4861964779937276e-05, "loss": 3.5507, "step": 11763 }, { "epoch": 0.6330176495910461, "grad_norm": 2.5641260147094727, "learning_rate": 1.4858101810793351e-05, "loss": 4.0573, "step": 11764 }, { "epoch": 0.633071459319845, "grad_norm": 3.779555559158325, "learning_rate": 1.4854239131477593e-05, "loss": 3.227, "step": 11765 }, { "epoch": 0.633125269048644, "grad_norm": 1.3270665407180786, "learning_rate": 1.4850376742100409e-05, "loss": 4.7636, "step": 11766 }, { "epoch": 0.633179078777443, "grad_norm": 3.4810421466827393, "learning_rate": 1.4846514642772139e-05, "loss": 3.1982, "step": 11767 }, { "epoch": 0.6332328885062419, "grad_norm": 2.06535267829895, "learning_rate": 1.4842652833603177e-05, "loss": 4.1656, "step": 11768 }, { "epoch": 0.6332866982350409, "grad_norm": 1.7674715518951416, "learning_rate": 1.4838791314703877e-05, "loss": 3.6888, "step": 11769 }, { "epoch": 0.6333405079638399, "grad_norm": 1.9286926984786987, "learning_rate": 1.4834930086184587e-05, "loss": 4.5004, "step": 11770 }, { "epoch": 0.6333943176926389, "grad_norm": 2.886878728866577, "learning_rate": 1.4831069148155657e-05, "loss": 4.2428, "step": 11771 }, { "epoch": 0.6334481274214377, "grad_norm": 3.1223056316375732, "learning_rate": 1.4827208500727424e-05, "loss": 4.0165, "step": 11772 }, { "epoch": 0.6335019371502367, "grad_norm": 2.7622182369232178, "learning_rate": 1.4823348144010213e-05, "loss": 4.1312, "step": 11773 }, { "epoch": 0.6335557468790357, "grad_norm": 2.52294921875, "learning_rate": 1.4819488078114335e-05, "loss": 4.7096, "step": 11774 }, { "epoch": 0.6336095566078347, "grad_norm": 2.993365526199341, "learning_rate": 1.4815628303150098e-05, "loss": 4.1849, "step": 11775 }, { "epoch": 0.6336633663366337, "grad_norm": 1.6574747562408447, "learning_rate": 1.4811768819227817e-05, "loss": 4.289, "step": 11776 }, { "epoch": 0.6337171760654327, "grad_norm": 2.8570010662078857, "learning_rate": 1.4807909626457782e-05, "loss": 3.432, "step": 11777 }, { "epoch": 0.6337709857942316, "grad_norm": 2.2638328075408936, "learning_rate": 1.4804050724950273e-05, "loss": 3.9288, "step": 11778 }, { "epoch": 0.6338247955230306, "grad_norm": 2.231642246246338, "learning_rate": 1.4800192114815573e-05, "loss": 3.9994, "step": 11779 }, { "epoch": 0.6338786052518295, "grad_norm": 3.2278027534484863, "learning_rate": 1.4796333796163948e-05, "loss": 3.656, "step": 11780 }, { "epoch": 0.6339324149806285, "grad_norm": 2.2157211303710938, "learning_rate": 1.4792475769105663e-05, "loss": 3.9236, "step": 11781 }, { "epoch": 0.6339862247094274, "grad_norm": 2.2687127590179443, "learning_rate": 1.4788618033750956e-05, "loss": 3.8838, "step": 11782 }, { "epoch": 0.6340400344382264, "grad_norm": 1.5403697490692139, "learning_rate": 1.4784760590210086e-05, "loss": 3.7018, "step": 11783 }, { "epoch": 0.6340938441670254, "grad_norm": 2.2308688163757324, "learning_rate": 1.4780903438593283e-05, "loss": 3.8732, "step": 11784 }, { "epoch": 0.6341476538958244, "grad_norm": 2.5194132328033447, "learning_rate": 1.4777046579010767e-05, "loss": 3.9471, "step": 11785 }, { "epoch": 0.6342014636246234, "grad_norm": 3.059516668319702, "learning_rate": 1.4773190011572768e-05, "loss": 3.6402, "step": 11786 }, { "epoch": 0.6342552733534222, "grad_norm": 3.2980027198791504, "learning_rate": 1.4769333736389495e-05, "loss": 4.0518, "step": 11787 }, { "epoch": 0.6343090830822212, "grad_norm": 1.5004531145095825, "learning_rate": 1.476547775357115e-05, "loss": 3.5775, "step": 11788 }, { "epoch": 0.6343628928110202, "grad_norm": 2.8603672981262207, "learning_rate": 1.4761622063227914e-05, "loss": 4.5626, "step": 11789 }, { "epoch": 0.6344167025398192, "grad_norm": 4.176789283752441, "learning_rate": 1.475776666546998e-05, "loss": 4.1245, "step": 11790 }, { "epoch": 0.6344705122686182, "grad_norm": 3.2568323612213135, "learning_rate": 1.4753911560407533e-05, "loss": 3.5964, "step": 11791 }, { "epoch": 0.6345243219974172, "grad_norm": 4.334575176239014, "learning_rate": 1.4750056748150732e-05, "loss": 2.7255, "step": 11792 }, { "epoch": 0.6345781317262161, "grad_norm": 3.9116172790527344, "learning_rate": 1.4746202228809735e-05, "loss": 3.3097, "step": 11793 }, { "epoch": 0.6346319414550151, "grad_norm": 2.941427707672119, "learning_rate": 1.4742348002494704e-05, "loss": 3.8835, "step": 11794 }, { "epoch": 0.634685751183814, "grad_norm": 2.7288243770599365, "learning_rate": 1.4738494069315777e-05, "loss": 3.9174, "step": 11795 }, { "epoch": 0.634739560912613, "grad_norm": 1.4224754571914673, "learning_rate": 1.4734640429383097e-05, "loss": 3.915, "step": 11796 }, { "epoch": 0.634793370641412, "grad_norm": 1.3203659057617188, "learning_rate": 1.4730787082806777e-05, "loss": 4.5694, "step": 11797 }, { "epoch": 0.6348471803702109, "grad_norm": 1.3962030410766602, "learning_rate": 1.4726934029696934e-05, "loss": 3.5373, "step": 11798 }, { "epoch": 0.6349009900990099, "grad_norm": 3.946469306945801, "learning_rate": 1.472308127016369e-05, "loss": 4.0585, "step": 11799 }, { "epoch": 0.6349547998278089, "grad_norm": 1.669028639793396, "learning_rate": 1.4719228804317148e-05, "loss": 4.2705, "step": 11800 }, { "epoch": 0.6350086095566079, "grad_norm": 3.1387526988983154, "learning_rate": 1.4715376632267383e-05, "loss": 3.547, "step": 11801 }, { "epoch": 0.6350624192854069, "grad_norm": 3.7590413093566895, "learning_rate": 1.4711524754124497e-05, "loss": 3.7683, "step": 11802 }, { "epoch": 0.6351162290142057, "grad_norm": 2.7487399578094482, "learning_rate": 1.4707673169998565e-05, "loss": 3.3813, "step": 11803 }, { "epoch": 0.6351700387430047, "grad_norm": 4.219085693359375, "learning_rate": 1.4703821879999651e-05, "loss": 4.488, "step": 11804 }, { "epoch": 0.6352238484718037, "grad_norm": 3.2786829471588135, "learning_rate": 1.4699970884237807e-05, "loss": 3.5036, "step": 11805 }, { "epoch": 0.6352776582006027, "grad_norm": 3.5106894969940186, "learning_rate": 1.4696120182823094e-05, "loss": 3.5155, "step": 11806 }, { "epoch": 0.6353314679294016, "grad_norm": 2.3283791542053223, "learning_rate": 1.4692269775865553e-05, "loss": 3.4422, "step": 11807 }, { "epoch": 0.6353852776582006, "grad_norm": 2.531036376953125, "learning_rate": 1.4688419663475217e-05, "loss": 4.3722, "step": 11808 }, { "epoch": 0.6354390873869996, "grad_norm": 2.2057747840881348, "learning_rate": 1.4684569845762108e-05, "loss": 4.4964, "step": 11809 }, { "epoch": 0.6354928971157985, "grad_norm": 2.0254201889038086, "learning_rate": 1.4680720322836255e-05, "loss": 4.5098, "step": 11810 }, { "epoch": 0.6355467068445975, "grad_norm": 3.381192684173584, "learning_rate": 1.467687109480766e-05, "loss": 3.8675, "step": 11811 }, { "epoch": 0.6356005165733964, "grad_norm": 3.3727195262908936, "learning_rate": 1.467302216178632e-05, "loss": 3.8185, "step": 11812 }, { "epoch": 0.6356543263021954, "grad_norm": 3.0129549503326416, "learning_rate": 1.4669173523882227e-05, "loss": 3.9905, "step": 11813 }, { "epoch": 0.6357081360309944, "grad_norm": 2.248872995376587, "learning_rate": 1.4665325181205369e-05, "loss": 4.2555, "step": 11814 }, { "epoch": 0.6357619457597934, "grad_norm": 1.9772478342056274, "learning_rate": 1.4661477133865725e-05, "loss": 4.3346, "step": 11815 }, { "epoch": 0.6358157554885924, "grad_norm": 3.4369635581970215, "learning_rate": 1.4657629381973247e-05, "loss": 3.1067, "step": 11816 }, { "epoch": 0.6358695652173914, "grad_norm": 2.1390695571899414, "learning_rate": 1.4653781925637913e-05, "loss": 4.1192, "step": 11817 }, { "epoch": 0.6359233749461902, "grad_norm": 2.9520347118377686, "learning_rate": 1.4649934764969664e-05, "loss": 4.4223, "step": 11818 }, { "epoch": 0.6359771846749892, "grad_norm": 2.9653193950653076, "learning_rate": 1.4646087900078443e-05, "loss": 3.9684, "step": 11819 }, { "epoch": 0.6360309944037882, "grad_norm": 2.2168452739715576, "learning_rate": 1.4642241331074175e-05, "loss": 3.8839, "step": 11820 }, { "epoch": 0.6360848041325872, "grad_norm": 3.2560501098632812, "learning_rate": 1.463839505806679e-05, "loss": 4.319, "step": 11821 }, { "epoch": 0.6361386138613861, "grad_norm": 2.1573100090026855, "learning_rate": 1.4634549081166205e-05, "loss": 4.0013, "step": 11822 }, { "epoch": 0.6361924235901851, "grad_norm": 3.8266382217407227, "learning_rate": 1.4630703400482331e-05, "loss": 3.6716, "step": 11823 }, { "epoch": 0.6362462333189841, "grad_norm": 1.3358885049819946, "learning_rate": 1.4626858016125058e-05, "loss": 4.3014, "step": 11824 }, { "epoch": 0.6363000430477831, "grad_norm": 2.188429832458496, "learning_rate": 1.4623012928204289e-05, "loss": 4.2053, "step": 11825 }, { "epoch": 0.636353852776582, "grad_norm": 1.1638823747634888, "learning_rate": 1.4619168136829897e-05, "loss": 4.2934, "step": 11826 }, { "epoch": 0.6364076625053809, "grad_norm": 3.1087470054626465, "learning_rate": 1.461532364211176e-05, "loss": 3.9274, "step": 11827 }, { "epoch": 0.6364614722341799, "grad_norm": 1.6943601369857788, "learning_rate": 1.4611479444159742e-05, "loss": 4.4609, "step": 11828 }, { "epoch": 0.6365152819629789, "grad_norm": 1.6546138525009155, "learning_rate": 1.4607635543083698e-05, "loss": 4.0084, "step": 11829 }, { "epoch": 0.6365690916917779, "grad_norm": 4.716789245605469, "learning_rate": 1.4603791938993477e-05, "loss": 3.4966, "step": 11830 }, { "epoch": 0.6366229014205769, "grad_norm": 1.918755292892456, "learning_rate": 1.4599948631998923e-05, "loss": 4.1352, "step": 11831 }, { "epoch": 0.6366767111493759, "grad_norm": 2.5258963108062744, "learning_rate": 1.4596105622209855e-05, "loss": 3.2552, "step": 11832 }, { "epoch": 0.6367305208781747, "grad_norm": 3.042695999145508, "learning_rate": 1.4592262909736115e-05, "loss": 3.7446, "step": 11833 }, { "epoch": 0.6367843306069737, "grad_norm": 1.7257604598999023, "learning_rate": 1.4588420494687516e-05, "loss": 3.6909, "step": 11834 }, { "epoch": 0.6368381403357727, "grad_norm": 1.783400535583496, "learning_rate": 1.4584578377173833e-05, "loss": 3.9434, "step": 11835 }, { "epoch": 0.6368919500645717, "grad_norm": 2.514930009841919, "learning_rate": 1.4580736557304897e-05, "loss": 3.8466, "step": 11836 }, { "epoch": 0.6369457597933706, "grad_norm": 1.4443305730819702, "learning_rate": 1.4576895035190486e-05, "loss": 4.3951, "step": 11837 }, { "epoch": 0.6369995695221696, "grad_norm": 3.1504647731781006, "learning_rate": 1.457305381094038e-05, "loss": 3.1383, "step": 11838 }, { "epoch": 0.6370533792509686, "grad_norm": 2.691903591156006, "learning_rate": 1.4569212884664352e-05, "loss": 4.1333, "step": 11839 }, { "epoch": 0.6371071889797676, "grad_norm": 2.8676862716674805, "learning_rate": 1.4565372256472165e-05, "loss": 3.7368, "step": 11840 }, { "epoch": 0.6371609987085665, "grad_norm": 3.017483711242676, "learning_rate": 1.456153192647356e-05, "loss": 3.9003, "step": 11841 }, { "epoch": 0.6372148084373654, "grad_norm": 2.0163204669952393, "learning_rate": 1.4557691894778319e-05, "loss": 4.2191, "step": 11842 }, { "epoch": 0.6372686181661644, "grad_norm": 2.074075698852539, "learning_rate": 1.4553852161496145e-05, "loss": 4.2146, "step": 11843 }, { "epoch": 0.6373224278949634, "grad_norm": 1.2346099615097046, "learning_rate": 1.4550012726736782e-05, "loss": 4.4445, "step": 11844 }, { "epoch": 0.6373762376237624, "grad_norm": 3.751983880996704, "learning_rate": 1.4546173590609946e-05, "loss": 3.8962, "step": 11845 }, { "epoch": 0.6374300473525614, "grad_norm": 2.3104240894317627, "learning_rate": 1.454233475322534e-05, "loss": 4.1843, "step": 11846 }, { "epoch": 0.6374838570813603, "grad_norm": 1.2124049663543701, "learning_rate": 1.4538496214692693e-05, "loss": 4.2754, "step": 11847 }, { "epoch": 0.6375376668101593, "grad_norm": 2.1054420471191406, "learning_rate": 1.4534657975121682e-05, "loss": 2.4496, "step": 11848 }, { "epoch": 0.6375914765389582, "grad_norm": 3.2571053504943848, "learning_rate": 1.4530820034622e-05, "loss": 3.748, "step": 11849 }, { "epoch": 0.6376452862677572, "grad_norm": 2.151669979095459, "learning_rate": 1.452698239330332e-05, "loss": 4.1969, "step": 11850 }, { "epoch": 0.6376990959965562, "grad_norm": 3.053480863571167, "learning_rate": 1.4523145051275317e-05, "loss": 4.3384, "step": 11851 }, { "epoch": 0.6377529057253551, "grad_norm": 1.74319326877594, "learning_rate": 1.4519308008647648e-05, "loss": 4.0245, "step": 11852 }, { "epoch": 0.6378067154541541, "grad_norm": 2.6764984130859375, "learning_rate": 1.4515471265529968e-05, "loss": 4.3485, "step": 11853 }, { "epoch": 0.6378605251829531, "grad_norm": 3.7120368480682373, "learning_rate": 1.4511634822031916e-05, "loss": 4.2564, "step": 11854 }, { "epoch": 0.6379143349117521, "grad_norm": 2.230691432952881, "learning_rate": 1.4507798678263132e-05, "loss": 3.7113, "step": 11855 }, { "epoch": 0.637968144640551, "grad_norm": 4.942363739013672, "learning_rate": 1.4503962834333231e-05, "loss": 3.5898, "step": 11856 }, { "epoch": 0.6380219543693499, "grad_norm": 3.2938883304595947, "learning_rate": 1.4500127290351862e-05, "loss": 3.4223, "step": 11857 }, { "epoch": 0.6380757640981489, "grad_norm": 1.4780898094177246, "learning_rate": 1.4496292046428604e-05, "loss": 4.3485, "step": 11858 }, { "epoch": 0.6381295738269479, "grad_norm": 1.78480064868927, "learning_rate": 1.4492457102673066e-05, "loss": 4.4681, "step": 11859 }, { "epoch": 0.6381833835557469, "grad_norm": 2.3355393409729004, "learning_rate": 1.4488622459194842e-05, "loss": 4.3823, "step": 11860 }, { "epoch": 0.6382371932845459, "grad_norm": 3.41264271736145, "learning_rate": 1.4484788116103507e-05, "loss": 3.8878, "step": 11861 }, { "epoch": 0.6382910030133448, "grad_norm": 2.791741132736206, "learning_rate": 1.4480954073508655e-05, "loss": 4.4716, "step": 11862 }, { "epoch": 0.6383448127421438, "grad_norm": 3.933551788330078, "learning_rate": 1.4477120331519841e-05, "loss": 4.0009, "step": 11863 }, { "epoch": 0.6383986224709427, "grad_norm": 1.3500359058380127, "learning_rate": 1.4473286890246626e-05, "loss": 4.6128, "step": 11864 }, { "epoch": 0.6384524321997417, "grad_norm": 2.8769571781158447, "learning_rate": 1.4469453749798567e-05, "loss": 4.0936, "step": 11865 }, { "epoch": 0.6385062419285407, "grad_norm": 2.1947267055511475, "learning_rate": 1.4465620910285177e-05, "loss": 4.3153, "step": 11866 }, { "epoch": 0.6385600516573396, "grad_norm": 2.7559564113616943, "learning_rate": 1.4461788371816018e-05, "loss": 3.5207, "step": 11867 }, { "epoch": 0.6386138613861386, "grad_norm": 3.630851984024048, "learning_rate": 1.4457956134500603e-05, "loss": 3.6363, "step": 11868 }, { "epoch": 0.6386676711149376, "grad_norm": 1.8352560997009277, "learning_rate": 1.4454124198448446e-05, "loss": 4.593, "step": 11869 }, { "epoch": 0.6387214808437366, "grad_norm": 1.9409598112106323, "learning_rate": 1.4450292563769052e-05, "loss": 4.0743, "step": 11870 }, { "epoch": 0.6387752905725355, "grad_norm": 3.184311628341675, "learning_rate": 1.4446461230571926e-05, "loss": 3.6294, "step": 11871 }, { "epoch": 0.6388291003013344, "grad_norm": 1.940516710281372, "learning_rate": 1.444263019896655e-05, "loss": 4.1059, "step": 11872 }, { "epoch": 0.6388829100301334, "grad_norm": 3.018627405166626, "learning_rate": 1.4438799469062406e-05, "loss": 4.2369, "step": 11873 }, { "epoch": 0.6389367197589324, "grad_norm": 1.2790417671203613, "learning_rate": 1.4434969040968968e-05, "loss": 4.4421, "step": 11874 }, { "epoch": 0.6389905294877314, "grad_norm": 2.072626829147339, "learning_rate": 1.4431138914795697e-05, "loss": 3.9784, "step": 11875 }, { "epoch": 0.6390443392165304, "grad_norm": 1.6273859739303589, "learning_rate": 1.4427309090652049e-05, "loss": 4.6297, "step": 11876 }, { "epoch": 0.6390981489453293, "grad_norm": 2.5192272663116455, "learning_rate": 1.4423479568647464e-05, "loss": 3.5367, "step": 11877 }, { "epoch": 0.6391519586741283, "grad_norm": 2.4593820571899414, "learning_rate": 1.4419650348891389e-05, "loss": 4.1142, "step": 11878 }, { "epoch": 0.6392057684029272, "grad_norm": 2.221386671066284, "learning_rate": 1.4415821431493253e-05, "loss": 3.4492, "step": 11879 }, { "epoch": 0.6392595781317262, "grad_norm": 2.4911651611328125, "learning_rate": 1.441199281656248e-05, "loss": 4.3579, "step": 11880 }, { "epoch": 0.6393133878605252, "grad_norm": 2.6727540493011475, "learning_rate": 1.440816450420846e-05, "loss": 3.8291, "step": 11881 }, { "epoch": 0.6393671975893241, "grad_norm": 1.386530876159668, "learning_rate": 1.4404336494540615e-05, "loss": 4.1716, "step": 11882 }, { "epoch": 0.6394210073181231, "grad_norm": 2.1587905883789062, "learning_rate": 1.4400508787668332e-05, "loss": 4.2558, "step": 11883 }, { "epoch": 0.6394748170469221, "grad_norm": 2.6321611404418945, "learning_rate": 1.4396681383701002e-05, "loss": 3.5211, "step": 11884 }, { "epoch": 0.6395286267757211, "grad_norm": 2.5725317001342773, "learning_rate": 1.4392854282747997e-05, "loss": 4.5632, "step": 11885 }, { "epoch": 0.6395824365045201, "grad_norm": 1.6359119415283203, "learning_rate": 1.4389027484918688e-05, "loss": 4.5997, "step": 11886 }, { "epoch": 0.6396362462333189, "grad_norm": 2.2759687900543213, "learning_rate": 1.4385200990322423e-05, "loss": 3.6883, "step": 11887 }, { "epoch": 0.6396900559621179, "grad_norm": 2.212069511413574, "learning_rate": 1.4381374799068582e-05, "loss": 3.887, "step": 11888 }, { "epoch": 0.6397438656909169, "grad_norm": 3.328731060028076, "learning_rate": 1.437754891126648e-05, "loss": 3.8289, "step": 11889 }, { "epoch": 0.6397976754197159, "grad_norm": 2.556183099746704, "learning_rate": 1.4373723327025457e-05, "loss": 4.1205, "step": 11890 }, { "epoch": 0.6398514851485149, "grad_norm": 1.9105299711227417, "learning_rate": 1.4369898046454843e-05, "loss": 4.1153, "step": 11891 }, { "epoch": 0.6399052948773138, "grad_norm": 2.289234161376953, "learning_rate": 1.4366073069663937e-05, "loss": 4.5089, "step": 11892 }, { "epoch": 0.6399591046061128, "grad_norm": 1.1069802045822144, "learning_rate": 1.4362248396762077e-05, "loss": 4.2175, "step": 11893 }, { "epoch": 0.6400129143349117, "grad_norm": 3.408055305480957, "learning_rate": 1.4358424027858541e-05, "loss": 4.2423, "step": 11894 }, { "epoch": 0.6400667240637107, "grad_norm": 1.9768531322479248, "learning_rate": 1.4354599963062634e-05, "loss": 4.4972, "step": 11895 }, { "epoch": 0.6401205337925097, "grad_norm": 1.7634069919586182, "learning_rate": 1.4350776202483618e-05, "loss": 3.81, "step": 11896 }, { "epoch": 0.6401743435213086, "grad_norm": 4.003584384918213, "learning_rate": 1.4346952746230765e-05, "loss": 4.5218, "step": 11897 }, { "epoch": 0.6402281532501076, "grad_norm": 2.6753807067871094, "learning_rate": 1.434312959441336e-05, "loss": 3.8788, "step": 11898 }, { "epoch": 0.6402819629789066, "grad_norm": 1.4031805992126465, "learning_rate": 1.4339306747140646e-05, "loss": 4.5231, "step": 11899 }, { "epoch": 0.6403357727077056, "grad_norm": 1.81740403175354, "learning_rate": 1.4335484204521873e-05, "loss": 4.1206, "step": 11900 }, { "epoch": 0.6403895824365046, "grad_norm": 1.3507364988327026, "learning_rate": 1.4331661966666277e-05, "loss": 4.2661, "step": 11901 }, { "epoch": 0.6404433921653034, "grad_norm": 2.3050637245178223, "learning_rate": 1.4327840033683088e-05, "loss": 4.2459, "step": 11902 }, { "epoch": 0.6404972018941024, "grad_norm": 1.6454508304595947, "learning_rate": 1.4324018405681525e-05, "loss": 4.2004, "step": 11903 }, { "epoch": 0.6405510116229014, "grad_norm": 2.296919107437134, "learning_rate": 1.43201970827708e-05, "loss": 4.3987, "step": 11904 }, { "epoch": 0.6406048213517004, "grad_norm": 1.2058759927749634, "learning_rate": 1.4316376065060116e-05, "loss": 4.3601, "step": 11905 }, { "epoch": 0.6406586310804994, "grad_norm": 2.9819703102111816, "learning_rate": 1.4312555352658674e-05, "loss": 3.2612, "step": 11906 }, { "epoch": 0.6407124408092983, "grad_norm": 1.5403817892074585, "learning_rate": 1.430873494567565e-05, "loss": 4.2799, "step": 11907 }, { "epoch": 0.6407662505380973, "grad_norm": 1.2389663457870483, "learning_rate": 1.4304914844220216e-05, "loss": 4.7702, "step": 11908 }, { "epoch": 0.6408200602668963, "grad_norm": 3.4359028339385986, "learning_rate": 1.4301095048401559e-05, "loss": 4.0093, "step": 11909 }, { "epoch": 0.6408738699956952, "grad_norm": 1.425763726234436, "learning_rate": 1.429727555832883e-05, "loss": 4.4433, "step": 11910 }, { "epoch": 0.6409276797244942, "grad_norm": 3.236549139022827, "learning_rate": 1.4293456374111186e-05, "loss": 3.6087, "step": 11911 }, { "epoch": 0.6409814894532931, "grad_norm": 2.4878952503204346, "learning_rate": 1.4289637495857743e-05, "loss": 4.3105, "step": 11912 }, { "epoch": 0.6410352991820921, "grad_norm": 2.4790256023406982, "learning_rate": 1.4285818923677663e-05, "loss": 4.4769, "step": 11913 }, { "epoch": 0.6410891089108911, "grad_norm": 2.033668279647827, "learning_rate": 1.4282000657680062e-05, "loss": 4.226, "step": 11914 }, { "epoch": 0.6411429186396901, "grad_norm": 3.712228775024414, "learning_rate": 1.4278182697974052e-05, "loss": 4.3005, "step": 11915 }, { "epoch": 0.6411967283684891, "grad_norm": 1.935973048210144, "learning_rate": 1.4274365044668744e-05, "loss": 4.2671, "step": 11916 }, { "epoch": 0.6412505380972879, "grad_norm": 3.1029186248779297, "learning_rate": 1.4270547697873232e-05, "loss": 3.4722, "step": 11917 }, { "epoch": 0.6413043478260869, "grad_norm": 3.448331594467163, "learning_rate": 1.4266730657696608e-05, "loss": 3.3317, "step": 11918 }, { "epoch": 0.6413581575548859, "grad_norm": 1.159292221069336, "learning_rate": 1.4262913924247957e-05, "loss": 4.1997, "step": 11919 }, { "epoch": 0.6414119672836849, "grad_norm": 1.8612867593765259, "learning_rate": 1.4259097497636343e-05, "loss": 3.1962, "step": 11920 }, { "epoch": 0.6414657770124839, "grad_norm": 3.6822640895843506, "learning_rate": 1.4255281377970836e-05, "loss": 4.0888, "step": 11921 }, { "epoch": 0.6415195867412828, "grad_norm": 2.4622554779052734, "learning_rate": 1.4251465565360484e-05, "loss": 4.0941, "step": 11922 }, { "epoch": 0.6415733964700818, "grad_norm": 3.530536651611328, "learning_rate": 1.4247650059914324e-05, "loss": 3.5562, "step": 11923 }, { "epoch": 0.6416272061988808, "grad_norm": 2.7880780696868896, "learning_rate": 1.424383486174142e-05, "loss": 3.8813, "step": 11924 }, { "epoch": 0.6416810159276797, "grad_norm": 3.202646017074585, "learning_rate": 1.4240019970950782e-05, "loss": 3.4516, "step": 11925 }, { "epoch": 0.6417348256564787, "grad_norm": 2.2126598358154297, "learning_rate": 1.4236205387651443e-05, "loss": 3.771, "step": 11926 }, { "epoch": 0.6417886353852776, "grad_norm": 2.719007968902588, "learning_rate": 1.4232391111952392e-05, "loss": 3.3988, "step": 11927 }, { "epoch": 0.6418424451140766, "grad_norm": 2.7356960773468018, "learning_rate": 1.4228577143962635e-05, "loss": 3.6032, "step": 11928 }, { "epoch": 0.6418962548428756, "grad_norm": 2.595052480697632, "learning_rate": 1.4224763483791176e-05, "loss": 4.2712, "step": 11929 }, { "epoch": 0.6419500645716746, "grad_norm": 2.4609110355377197, "learning_rate": 1.4220950131547e-05, "loss": 4.4, "step": 11930 }, { "epoch": 0.6420038743004736, "grad_norm": 3.4429733753204346, "learning_rate": 1.4217137087339073e-05, "loss": 3.8403, "step": 11931 }, { "epoch": 0.6420576840292725, "grad_norm": 1.6058762073516846, "learning_rate": 1.421332435127637e-05, "loss": 4.3561, "step": 11932 }, { "epoch": 0.6421114937580714, "grad_norm": 2.2591066360473633, "learning_rate": 1.4209511923467839e-05, "loss": 3.9761, "step": 11933 }, { "epoch": 0.6421653034868704, "grad_norm": 3.794245719909668, "learning_rate": 1.4205699804022438e-05, "loss": 4.2454, "step": 11934 }, { "epoch": 0.6422191132156694, "grad_norm": 3.3326609134674072, "learning_rate": 1.4201887993049101e-05, "loss": 3.1185, "step": 11935 }, { "epoch": 0.6422729229444684, "grad_norm": 2.644704818725586, "learning_rate": 1.4198076490656764e-05, "loss": 3.5841, "step": 11936 }, { "epoch": 0.6423267326732673, "grad_norm": 2.1970584392547607, "learning_rate": 1.4194265296954345e-05, "loss": 4.0416, "step": 11937 }, { "epoch": 0.6423805424020663, "grad_norm": 2.88008189201355, "learning_rate": 1.4190454412050761e-05, "loss": 4.2262, "step": 11938 }, { "epoch": 0.6424343521308653, "grad_norm": 3.0798826217651367, "learning_rate": 1.4186643836054902e-05, "loss": 3.827, "step": 11939 }, { "epoch": 0.6424881618596642, "grad_norm": 1.544351577758789, "learning_rate": 1.4182833569075693e-05, "loss": 4.5421, "step": 11940 }, { "epoch": 0.6425419715884632, "grad_norm": 2.0691819190979004, "learning_rate": 1.4179023611222014e-05, "loss": 4.007, "step": 11941 }, { "epoch": 0.6425957813172621, "grad_norm": 2.6451759338378906, "learning_rate": 1.4175213962602724e-05, "loss": 3.4372, "step": 11942 }, { "epoch": 0.6426495910460611, "grad_norm": 2.3884172439575195, "learning_rate": 1.4171404623326695e-05, "loss": 3.8188, "step": 11943 }, { "epoch": 0.6427034007748601, "grad_norm": 2.60937237739563, "learning_rate": 1.4167595593502806e-05, "loss": 4.0565, "step": 11944 }, { "epoch": 0.6427572105036591, "grad_norm": 2.2342143058776855, "learning_rate": 1.4163786873239897e-05, "loss": 4.5738, "step": 11945 }, { "epoch": 0.6428110202324581, "grad_norm": 2.016042709350586, "learning_rate": 1.4159978462646817e-05, "loss": 4.4998, "step": 11946 }, { "epoch": 0.642864829961257, "grad_norm": 1.9193296432495117, "learning_rate": 1.4156170361832393e-05, "loss": 4.2907, "step": 11947 }, { "epoch": 0.6429186396900559, "grad_norm": 1.9080073833465576, "learning_rate": 1.415236257090546e-05, "loss": 4.1968, "step": 11948 }, { "epoch": 0.6429724494188549, "grad_norm": 2.6843063831329346, "learning_rate": 1.4148555089974818e-05, "loss": 3.5619, "step": 11949 }, { "epoch": 0.6430262591476539, "grad_norm": 1.24260675907135, "learning_rate": 1.4144747919149292e-05, "loss": 4.3984, "step": 11950 }, { "epoch": 0.6430800688764529, "grad_norm": 2.5373687744140625, "learning_rate": 1.414094105853767e-05, "loss": 3.467, "step": 11951 }, { "epoch": 0.6431338786052518, "grad_norm": 1.7991153001785278, "learning_rate": 1.4137134508248747e-05, "loss": 3.9812, "step": 11952 }, { "epoch": 0.6431876883340508, "grad_norm": 2.2855284214019775, "learning_rate": 1.4133328268391302e-05, "loss": 4.2056, "step": 11953 }, { "epoch": 0.6432414980628498, "grad_norm": 2.54828143119812, "learning_rate": 1.4129522339074097e-05, "loss": 3.849, "step": 11954 }, { "epoch": 0.6432953077916488, "grad_norm": 2.843445301055908, "learning_rate": 1.4125716720405912e-05, "loss": 4.0291, "step": 11955 }, { "epoch": 0.6433491175204477, "grad_norm": 1.3620554208755493, "learning_rate": 1.4121911412495497e-05, "loss": 4.5222, "step": 11956 }, { "epoch": 0.6434029272492466, "grad_norm": 2.7530465126037598, "learning_rate": 1.411810641545161e-05, "loss": 3.2424, "step": 11957 }, { "epoch": 0.6434567369780456, "grad_norm": 2.812915086746216, "learning_rate": 1.4114301729382957e-05, "loss": 4.2, "step": 11958 }, { "epoch": 0.6435105467068446, "grad_norm": 2.153282642364502, "learning_rate": 1.4110497354398272e-05, "loss": 4.6747, "step": 11959 }, { "epoch": 0.6435643564356436, "grad_norm": 2.72912859916687, "learning_rate": 1.4106693290606293e-05, "loss": 3.1739, "step": 11960 }, { "epoch": 0.6436181661644426, "grad_norm": 2.8370327949523926, "learning_rate": 1.4102889538115723e-05, "loss": 4.1673, "step": 11961 }, { "epoch": 0.6436719758932415, "grad_norm": 2.961210250854492, "learning_rate": 1.4099086097035258e-05, "loss": 3.8686, "step": 11962 }, { "epoch": 0.6437257856220404, "grad_norm": 2.626224994659424, "learning_rate": 1.4095282967473595e-05, "loss": 3.9652, "step": 11963 }, { "epoch": 0.6437795953508394, "grad_norm": 1.6205626726150513, "learning_rate": 1.409148014953941e-05, "loss": 4.4291, "step": 11964 }, { "epoch": 0.6438334050796384, "grad_norm": 3.0948641300201416, "learning_rate": 1.4087677643341384e-05, "loss": 3.0653, "step": 11965 }, { "epoch": 0.6438872148084374, "grad_norm": 2.061729907989502, "learning_rate": 1.4083875448988181e-05, "loss": 4.5344, "step": 11966 }, { "epoch": 0.6439410245372363, "grad_norm": 3.3007609844207764, "learning_rate": 1.4080073566588458e-05, "loss": 3.9461, "step": 11967 }, { "epoch": 0.6439948342660353, "grad_norm": 1.9159903526306152, "learning_rate": 1.4076271996250862e-05, "loss": 3.2923, "step": 11968 }, { "epoch": 0.6440486439948343, "grad_norm": 1.3325814008712769, "learning_rate": 1.4072470738084026e-05, "loss": 4.6667, "step": 11969 }, { "epoch": 0.6441024537236333, "grad_norm": 3.1383588314056396, "learning_rate": 1.406866979219658e-05, "loss": 3.6712, "step": 11970 }, { "epoch": 0.6441562634524322, "grad_norm": 1.2335721254348755, "learning_rate": 1.4064869158697155e-05, "loss": 4.4142, "step": 11971 }, { "epoch": 0.6442100731812311, "grad_norm": 2.2934768199920654, "learning_rate": 1.4061068837694369e-05, "loss": 3.3817, "step": 11972 }, { "epoch": 0.6442638829100301, "grad_norm": 1.9395743608474731, "learning_rate": 1.4057268829296805e-05, "loss": 4.1824, "step": 11973 }, { "epoch": 0.6443176926388291, "grad_norm": 2.6206271648406982, "learning_rate": 1.4053469133613054e-05, "loss": 4.526, "step": 11974 }, { "epoch": 0.6443715023676281, "grad_norm": 2.962804079055786, "learning_rate": 1.404966975075172e-05, "loss": 4.1299, "step": 11975 }, { "epoch": 0.6444253120964271, "grad_norm": 1.6045469045639038, "learning_rate": 1.4045870680821376e-05, "loss": 3.9338, "step": 11976 }, { "epoch": 0.644479121825226, "grad_norm": 2.09808611869812, "learning_rate": 1.4042071923930584e-05, "loss": 4.0094, "step": 11977 }, { "epoch": 0.6445329315540249, "grad_norm": 2.9031224250793457, "learning_rate": 1.4038273480187903e-05, "loss": 2.7783, "step": 11978 }, { "epoch": 0.6445867412828239, "grad_norm": 2.429288625717163, "learning_rate": 1.4034475349701881e-05, "loss": 4.2675, "step": 11979 }, { "epoch": 0.6446405510116229, "grad_norm": 2.816180944442749, "learning_rate": 1.403067753258106e-05, "loss": 3.63, "step": 11980 }, { "epoch": 0.6446943607404219, "grad_norm": 2.3640291690826416, "learning_rate": 1.402688002893397e-05, "loss": 4.2103, "step": 11981 }, { "epoch": 0.6447481704692208, "grad_norm": 3.3814358711242676, "learning_rate": 1.4023082838869134e-05, "loss": 3.4516, "step": 11982 }, { "epoch": 0.6448019801980198, "grad_norm": 2.8488471508026123, "learning_rate": 1.4019285962495068e-05, "loss": 3.9284, "step": 11983 }, { "epoch": 0.6448557899268188, "grad_norm": 2.6144020557403564, "learning_rate": 1.4015489399920273e-05, "loss": 4.1316, "step": 11984 }, { "epoch": 0.6449095996556178, "grad_norm": 3.4401772022247314, "learning_rate": 1.4011693151253241e-05, "loss": 3.6513, "step": 11985 }, { "epoch": 0.6449634093844167, "grad_norm": 2.427960157394409, "learning_rate": 1.4007897216602468e-05, "loss": 3.7894, "step": 11986 }, { "epoch": 0.6450172191132156, "grad_norm": 1.6357371807098389, "learning_rate": 1.4004101596076441e-05, "loss": 4.6987, "step": 11987 }, { "epoch": 0.6450710288420146, "grad_norm": 2.8942835330963135, "learning_rate": 1.4000306289783602e-05, "loss": 4.0091, "step": 11988 }, { "epoch": 0.6451248385708136, "grad_norm": 2.6189322471618652, "learning_rate": 1.3996511297832423e-05, "loss": 3.5917, "step": 11989 }, { "epoch": 0.6451786482996126, "grad_norm": 2.397223711013794, "learning_rate": 1.3992716620331348e-05, "loss": 3.8152, "step": 11990 }, { "epoch": 0.6452324580284116, "grad_norm": 2.3630599975585938, "learning_rate": 1.3988922257388836e-05, "loss": 3.9486, "step": 11991 }, { "epoch": 0.6452862677572105, "grad_norm": 1.9599552154541016, "learning_rate": 1.3985128209113308e-05, "loss": 3.8765, "step": 11992 }, { "epoch": 0.6453400774860095, "grad_norm": 2.643160343170166, "learning_rate": 1.3981334475613188e-05, "loss": 3.8452, "step": 11993 }, { "epoch": 0.6453938872148084, "grad_norm": 2.142578125, "learning_rate": 1.3977541056996896e-05, "loss": 4.4981, "step": 11994 }, { "epoch": 0.6454476969436074, "grad_norm": 2.327326536178589, "learning_rate": 1.397374795337283e-05, "loss": 4.3076, "step": 11995 }, { "epoch": 0.6455015066724064, "grad_norm": 2.8257646560668945, "learning_rate": 1.3969955164849392e-05, "loss": 3.9901, "step": 11996 }, { "epoch": 0.6455553164012053, "grad_norm": 2.254164218902588, "learning_rate": 1.3966162691534967e-05, "loss": 3.4757, "step": 11997 }, { "epoch": 0.6456091261300043, "grad_norm": 1.7265617847442627, "learning_rate": 1.3962370533537935e-05, "loss": 4.6799, "step": 11998 }, { "epoch": 0.6456629358588033, "grad_norm": 3.8391499519348145, "learning_rate": 1.3958578690966668e-05, "loss": 3.5988, "step": 11999 }, { "epoch": 0.6457167455876023, "grad_norm": 3.236694097518921, "learning_rate": 1.395478716392952e-05, "loss": 4.0851, "step": 12000 }, { "epoch": 0.6457705553164012, "grad_norm": 3.1540451049804688, "learning_rate": 1.395099595253484e-05, "loss": 4.2183, "step": 12001 }, { "epoch": 0.6458243650452001, "grad_norm": 3.0961456298828125, "learning_rate": 1.3947205056890995e-05, "loss": 4.0243, "step": 12002 }, { "epoch": 0.6458781747739991, "grad_norm": 2.3392791748046875, "learning_rate": 1.3943414477106293e-05, "loss": 4.3142, "step": 12003 }, { "epoch": 0.6459319845027981, "grad_norm": 2.6029791831970215, "learning_rate": 1.3939624213289066e-05, "loss": 3.9326, "step": 12004 }, { "epoch": 0.6459857942315971, "grad_norm": 1.971543312072754, "learning_rate": 1.3935834265547618e-05, "loss": 3.8782, "step": 12005 }, { "epoch": 0.6460396039603961, "grad_norm": 3.62662935256958, "learning_rate": 1.3932044633990277e-05, "loss": 3.3006, "step": 12006 }, { "epoch": 0.646093413689195, "grad_norm": 2.2286429405212402, "learning_rate": 1.3928255318725334e-05, "loss": 4.3069, "step": 12007 }, { "epoch": 0.646147223417994, "grad_norm": 1.4110593795776367, "learning_rate": 1.3924466319861073e-05, "loss": 4.1581, "step": 12008 }, { "epoch": 0.6462010331467929, "grad_norm": 1.2438091039657593, "learning_rate": 1.3920677637505774e-05, "loss": 4.2825, "step": 12009 }, { "epoch": 0.6462548428755919, "grad_norm": 2.7527782917022705, "learning_rate": 1.3916889271767713e-05, "loss": 3.8045, "step": 12010 }, { "epoch": 0.6463086526043909, "grad_norm": 3.744412422180176, "learning_rate": 1.3913101222755142e-05, "loss": 3.2089, "step": 12011 }, { "epoch": 0.6463624623331898, "grad_norm": 2.144829750061035, "learning_rate": 1.390931349057632e-05, "loss": 4.2112, "step": 12012 }, { "epoch": 0.6464162720619888, "grad_norm": 1.6271246671676636, "learning_rate": 1.3905526075339486e-05, "loss": 4.3044, "step": 12013 }, { "epoch": 0.6464700817907878, "grad_norm": 2.9350242614746094, "learning_rate": 1.3901738977152878e-05, "loss": 4.1381, "step": 12014 }, { "epoch": 0.6465238915195868, "grad_norm": 1.9359134435653687, "learning_rate": 1.389795219612472e-05, "loss": 4.1903, "step": 12015 }, { "epoch": 0.6465777012483858, "grad_norm": 2.630949020385742, "learning_rate": 1.3894165732363212e-05, "loss": 3.9945, "step": 12016 }, { "epoch": 0.6466315109771846, "grad_norm": 2.3359878063201904, "learning_rate": 1.3890379585976593e-05, "loss": 4.1346, "step": 12017 }, { "epoch": 0.6466853207059836, "grad_norm": 2.722564935684204, "learning_rate": 1.3886593757073048e-05, "loss": 4.4175, "step": 12018 }, { "epoch": 0.6467391304347826, "grad_norm": 3.521310329437256, "learning_rate": 1.3882808245760755e-05, "loss": 4.0462, "step": 12019 }, { "epoch": 0.6467929401635816, "grad_norm": 3.427588939666748, "learning_rate": 1.3879023052147899e-05, "loss": 3.5238, "step": 12020 }, { "epoch": 0.6468467498923806, "grad_norm": 2.538081169128418, "learning_rate": 1.3875238176342647e-05, "loss": 3.9634, "step": 12021 }, { "epoch": 0.6469005596211795, "grad_norm": 2.652172327041626, "learning_rate": 1.3871453618453172e-05, "loss": 4.0531, "step": 12022 }, { "epoch": 0.6469543693499785, "grad_norm": 3.7221860885620117, "learning_rate": 1.386766937858762e-05, "loss": 4.8211, "step": 12023 }, { "epoch": 0.6470081790787774, "grad_norm": 1.5808340311050415, "learning_rate": 1.3863885456854137e-05, "loss": 4.4047, "step": 12024 }, { "epoch": 0.6470619888075764, "grad_norm": 3.121046304702759, "learning_rate": 1.3860101853360852e-05, "loss": 3.7339, "step": 12025 }, { "epoch": 0.6471157985363754, "grad_norm": 2.7339274883270264, "learning_rate": 1.3856318568215895e-05, "loss": 4.4457, "step": 12026 }, { "epoch": 0.6471696082651743, "grad_norm": 3.4740800857543945, "learning_rate": 1.3852535601527377e-05, "loss": 3.8905, "step": 12027 }, { "epoch": 0.6472234179939733, "grad_norm": 1.4639564752578735, "learning_rate": 1.3848752953403415e-05, "loss": 4.6496, "step": 12028 }, { "epoch": 0.6472772277227723, "grad_norm": 2.4672532081604004, "learning_rate": 1.3844970623952097e-05, "loss": 4.0426, "step": 12029 }, { "epoch": 0.6473310374515713, "grad_norm": 1.889282464981079, "learning_rate": 1.3841188613281515e-05, "loss": 4.3576, "step": 12030 }, { "epoch": 0.6473848471803703, "grad_norm": 2.5114998817443848, "learning_rate": 1.3837406921499737e-05, "loss": 3.7186, "step": 12031 }, { "epoch": 0.6474386569091691, "grad_norm": 2.22452974319458, "learning_rate": 1.3833625548714858e-05, "loss": 3.8402, "step": 12032 }, { "epoch": 0.6474924666379681, "grad_norm": 3.9351491928100586, "learning_rate": 1.3829844495034933e-05, "loss": 3.23, "step": 12033 }, { "epoch": 0.6475462763667671, "grad_norm": 2.977102279663086, "learning_rate": 1.3826063760568004e-05, "loss": 3.8952, "step": 12034 }, { "epoch": 0.6476000860955661, "grad_norm": 3.6479666233062744, "learning_rate": 1.3822283345422113e-05, "loss": 3.5463, "step": 12035 }, { "epoch": 0.6476538958243651, "grad_norm": 2.597752571105957, "learning_rate": 1.3818503249705292e-05, "loss": 4.5165, "step": 12036 }, { "epoch": 0.647707705553164, "grad_norm": 2.442188262939453, "learning_rate": 1.3814723473525581e-05, "loss": 3.5997, "step": 12037 }, { "epoch": 0.647761515281963, "grad_norm": 3.768578290939331, "learning_rate": 1.3810944016990992e-05, "loss": 3.3092, "step": 12038 }, { "epoch": 0.647815325010762, "grad_norm": 3.2448689937591553, "learning_rate": 1.3807164880209527e-05, "loss": 4.1401, "step": 12039 }, { "epoch": 0.6478691347395609, "grad_norm": 2.028618812561035, "learning_rate": 1.3803386063289181e-05, "loss": 4.0162, "step": 12040 }, { "epoch": 0.6479229444683599, "grad_norm": 2.5767247676849365, "learning_rate": 1.3799607566337951e-05, "loss": 4.1602, "step": 12041 }, { "epoch": 0.6479767541971588, "grad_norm": 3.099792242050171, "learning_rate": 1.379582938946381e-05, "loss": 4.0494, "step": 12042 }, { "epoch": 0.6480305639259578, "grad_norm": 2.0940606594085693, "learning_rate": 1.3792051532774727e-05, "loss": 4.3173, "step": 12043 }, { "epoch": 0.6480843736547568, "grad_norm": 2.4739010334014893, "learning_rate": 1.3788273996378667e-05, "loss": 4.1246, "step": 12044 }, { "epoch": 0.6481381833835558, "grad_norm": 1.874122977256775, "learning_rate": 1.378449678038358e-05, "loss": 3.8436, "step": 12045 }, { "epoch": 0.6481919931123548, "grad_norm": 2.772679090499878, "learning_rate": 1.3780719884897409e-05, "loss": 4.1506, "step": 12046 }, { "epoch": 0.6482458028411536, "grad_norm": 2.5244500637054443, "learning_rate": 1.3776943310028077e-05, "loss": 3.9032, "step": 12047 }, { "epoch": 0.6482996125699526, "grad_norm": 2.677192211151123, "learning_rate": 1.3773167055883538e-05, "loss": 3.0126, "step": 12048 }, { "epoch": 0.6483534222987516, "grad_norm": 1.5497760772705078, "learning_rate": 1.3769391122571679e-05, "loss": 3.9591, "step": 12049 }, { "epoch": 0.6484072320275506, "grad_norm": 4.102537631988525, "learning_rate": 1.3765615510200414e-05, "loss": 4.185, "step": 12050 }, { "epoch": 0.6484610417563496, "grad_norm": 3.509803056716919, "learning_rate": 1.3761840218877642e-05, "loss": 3.0832, "step": 12051 }, { "epoch": 0.6485148514851485, "grad_norm": 2.0565025806427, "learning_rate": 1.3758065248711239e-05, "loss": 4.4344, "step": 12052 }, { "epoch": 0.6485686612139475, "grad_norm": 1.8945904970169067, "learning_rate": 1.3754290599809105e-05, "loss": 3.9692, "step": 12053 }, { "epoch": 0.6486224709427465, "grad_norm": 1.6091245412826538, "learning_rate": 1.3750516272279095e-05, "loss": 4.5458, "step": 12054 }, { "epoch": 0.6486762806715454, "grad_norm": 2.769089460372925, "learning_rate": 1.3746742266229074e-05, "loss": 3.5958, "step": 12055 }, { "epoch": 0.6487300904003444, "grad_norm": 2.4865589141845703, "learning_rate": 1.3742968581766893e-05, "loss": 4.4752, "step": 12056 }, { "epoch": 0.6487839001291433, "grad_norm": 2.6633005142211914, "learning_rate": 1.3739195219000389e-05, "loss": 3.9816, "step": 12057 }, { "epoch": 0.6488377098579423, "grad_norm": 3.1549620628356934, "learning_rate": 1.3735422178037399e-05, "loss": 3.555, "step": 12058 }, { "epoch": 0.6488915195867413, "grad_norm": 1.9165759086608887, "learning_rate": 1.3731649458985746e-05, "loss": 4.1369, "step": 12059 }, { "epoch": 0.6489453293155403, "grad_norm": 1.821844458580017, "learning_rate": 1.3727877061953243e-05, "loss": 4.5745, "step": 12060 }, { "epoch": 0.6489991390443393, "grad_norm": 2.6463234424591064, "learning_rate": 1.3724104987047697e-05, "loss": 3.9008, "step": 12061 }, { "epoch": 0.6490529487731382, "grad_norm": 1.5567817687988281, "learning_rate": 1.372033323437689e-05, "loss": 4.1581, "step": 12062 }, { "epoch": 0.6491067585019371, "grad_norm": 1.9696627855300903, "learning_rate": 1.3716561804048627e-05, "loss": 4.3365, "step": 12063 }, { "epoch": 0.6491605682307361, "grad_norm": 3.046706199645996, "learning_rate": 1.3712790696170694e-05, "loss": 3.1829, "step": 12064 }, { "epoch": 0.6492143779595351, "grad_norm": 3.051203727722168, "learning_rate": 1.3709019910850831e-05, "loss": 3.5484, "step": 12065 }, { "epoch": 0.649268187688334, "grad_norm": 1.30814528465271, "learning_rate": 1.3705249448196811e-05, "loss": 4.2065, "step": 12066 }, { "epoch": 0.649321997417133, "grad_norm": 2.0667190551757812, "learning_rate": 1.3701479308316373e-05, "loss": 3.9413, "step": 12067 }, { "epoch": 0.649375807145932, "grad_norm": 2.1418569087982178, "learning_rate": 1.3697709491317274e-05, "loss": 3.7306, "step": 12068 }, { "epoch": 0.649429616874731, "grad_norm": 3.867241144180298, "learning_rate": 1.369393999730724e-05, "loss": 4.0541, "step": 12069 }, { "epoch": 0.6494834266035299, "grad_norm": 1.3392422199249268, "learning_rate": 1.3690170826393991e-05, "loss": 4.061, "step": 12070 }, { "epoch": 0.6495372363323288, "grad_norm": 3.209087610244751, "learning_rate": 1.3686401978685248e-05, "loss": 4.0309, "step": 12071 }, { "epoch": 0.6495910460611278, "grad_norm": 1.55671226978302, "learning_rate": 1.368263345428869e-05, "loss": 4.3897, "step": 12072 }, { "epoch": 0.6496448557899268, "grad_norm": 3.9238693714141846, "learning_rate": 1.3678865253312036e-05, "loss": 3.5098, "step": 12073 }, { "epoch": 0.6496986655187258, "grad_norm": 2.9192416667938232, "learning_rate": 1.3675097375862963e-05, "loss": 3.6526, "step": 12074 }, { "epoch": 0.6497524752475248, "grad_norm": 2.591149091720581, "learning_rate": 1.3671329822049148e-05, "loss": 3.991, "step": 12075 }, { "epoch": 0.6498062849763238, "grad_norm": 1.095375895500183, "learning_rate": 1.3667562591978256e-05, "loss": 4.5933, "step": 12076 }, { "epoch": 0.6498600947051227, "grad_norm": 3.1055233478546143, "learning_rate": 1.3663795685757941e-05, "loss": 4.0002, "step": 12077 }, { "epoch": 0.6499139044339216, "grad_norm": 3.311951160430908, "learning_rate": 1.3660029103495848e-05, "loss": 4.0618, "step": 12078 }, { "epoch": 0.6499677141627206, "grad_norm": 2.3667309284210205, "learning_rate": 1.365626284529964e-05, "loss": 4.0368, "step": 12079 }, { "epoch": 0.6500215238915196, "grad_norm": 2.3929786682128906, "learning_rate": 1.365249691127692e-05, "loss": 3.956, "step": 12080 }, { "epoch": 0.6500753336203186, "grad_norm": 2.7111763954162598, "learning_rate": 1.3648731301535317e-05, "loss": 3.6709, "step": 12081 }, { "epoch": 0.6501291433491175, "grad_norm": 1.9224276542663574, "learning_rate": 1.3644966016182442e-05, "loss": 4.3279, "step": 12082 }, { "epoch": 0.6501829530779165, "grad_norm": 2.9185264110565186, "learning_rate": 1.3641201055325887e-05, "loss": 3.2032, "step": 12083 }, { "epoch": 0.6502367628067155, "grad_norm": 2.316272497177124, "learning_rate": 1.3637436419073263e-05, "loss": 4.3348, "step": 12084 }, { "epoch": 0.6502905725355144, "grad_norm": 2.407640218734741, "learning_rate": 1.3633672107532147e-05, "loss": 3.2106, "step": 12085 }, { "epoch": 0.6503443822643133, "grad_norm": 2.58539080619812, "learning_rate": 1.3629908120810117e-05, "loss": 3.8889, "step": 12086 }, { "epoch": 0.6503981919931123, "grad_norm": 2.609360456466675, "learning_rate": 1.3626144459014712e-05, "loss": 3.771, "step": 12087 }, { "epoch": 0.6504520017219113, "grad_norm": 2.3377797603607178, "learning_rate": 1.3622381122253519e-05, "loss": 3.7097, "step": 12088 }, { "epoch": 0.6505058114507103, "grad_norm": 3.625523805618286, "learning_rate": 1.3618618110634068e-05, "loss": 3.5787, "step": 12089 }, { "epoch": 0.6505596211795093, "grad_norm": 2.4610280990600586, "learning_rate": 1.36148554242639e-05, "loss": 3.0621, "step": 12090 }, { "epoch": 0.6506134309083083, "grad_norm": 3.0063700675964355, "learning_rate": 1.3611093063250544e-05, "loss": 3.7668, "step": 12091 }, { "epoch": 0.6506672406371072, "grad_norm": 1.328576683998108, "learning_rate": 1.3607331027701514e-05, "loss": 4.2048, "step": 12092 }, { "epoch": 0.6507210503659061, "grad_norm": 2.449198007583618, "learning_rate": 1.3603569317724308e-05, "loss": 3.8995, "step": 12093 }, { "epoch": 0.6507748600947051, "grad_norm": 1.894415020942688, "learning_rate": 1.3599807933426461e-05, "loss": 4.1874, "step": 12094 }, { "epoch": 0.6508286698235041, "grad_norm": 1.7215410470962524, "learning_rate": 1.359604687491543e-05, "loss": 4.5635, "step": 12095 }, { "epoch": 0.650882479552303, "grad_norm": 3.9669830799102783, "learning_rate": 1.3592286142298705e-05, "loss": 4.4259, "step": 12096 }, { "epoch": 0.650936289281102, "grad_norm": 4.4372968673706055, "learning_rate": 1.358852573568376e-05, "loss": 2.9996, "step": 12097 }, { "epoch": 0.650990099009901, "grad_norm": 1.4846473932266235, "learning_rate": 1.3584765655178045e-05, "loss": 4.7304, "step": 12098 }, { "epoch": 0.6510439087387, "grad_norm": 4.840884208679199, "learning_rate": 1.3581005900889038e-05, "loss": 3.8544, "step": 12099 }, { "epoch": 0.651097718467499, "grad_norm": 1.6819010972976685, "learning_rate": 1.3577246472924165e-05, "loss": 4.3965, "step": 12100 }, { "epoch": 0.6511515281962978, "grad_norm": 1.8541172742843628, "learning_rate": 1.3573487371390863e-05, "loss": 3.8204, "step": 12101 }, { "epoch": 0.6512053379250968, "grad_norm": 2.3359737396240234, "learning_rate": 1.3569728596396572e-05, "loss": 3.8813, "step": 12102 }, { "epoch": 0.6512591476538958, "grad_norm": 1.2487648725509644, "learning_rate": 1.3565970148048674e-05, "loss": 4.612, "step": 12103 }, { "epoch": 0.6513129573826948, "grad_norm": 1.591565728187561, "learning_rate": 1.3562212026454602e-05, "loss": 4.1683, "step": 12104 }, { "epoch": 0.6513667671114938, "grad_norm": 2.833430528640747, "learning_rate": 1.3558454231721748e-05, "loss": 4.2608, "step": 12105 }, { "epoch": 0.6514205768402928, "grad_norm": 2.0392274856567383, "learning_rate": 1.3554696763957497e-05, "loss": 4.0012, "step": 12106 }, { "epoch": 0.6514743865690917, "grad_norm": 2.9546959400177, "learning_rate": 1.3550939623269229e-05, "loss": 3.7714, "step": 12107 }, { "epoch": 0.6515281962978906, "grad_norm": 3.1590511798858643, "learning_rate": 1.3547182809764315e-05, "loss": 3.4804, "step": 12108 }, { "epoch": 0.6515820060266896, "grad_norm": 2.0786283016204834, "learning_rate": 1.3543426323550107e-05, "loss": 3.9513, "step": 12109 }, { "epoch": 0.6516358157554886, "grad_norm": 3.3403615951538086, "learning_rate": 1.3539670164733964e-05, "loss": 3.9342, "step": 12110 }, { "epoch": 0.6516896254842875, "grad_norm": 2.0635793209075928, "learning_rate": 1.3535914333423219e-05, "loss": 3.5893, "step": 12111 }, { "epoch": 0.6517434352130865, "grad_norm": 1.909657597541809, "learning_rate": 1.353215882972521e-05, "loss": 4.3002, "step": 12112 }, { "epoch": 0.6517972449418855, "grad_norm": 2.9840707778930664, "learning_rate": 1.3528403653747256e-05, "loss": 4.1991, "step": 12113 }, { "epoch": 0.6518510546706845, "grad_norm": 1.906402826309204, "learning_rate": 1.3524648805596662e-05, "loss": 3.8606, "step": 12114 }, { "epoch": 0.6519048643994835, "grad_norm": 2.8890926837921143, "learning_rate": 1.3520894285380748e-05, "loss": 3.9405, "step": 12115 }, { "epoch": 0.6519586741282823, "grad_norm": 2.3905975818634033, "learning_rate": 1.3517140093206803e-05, "loss": 3.92, "step": 12116 }, { "epoch": 0.6520124838570813, "grad_norm": 2.9800608158111572, "learning_rate": 1.3513386229182118e-05, "loss": 3.1964, "step": 12117 }, { "epoch": 0.6520662935858803, "grad_norm": 2.81241512298584, "learning_rate": 1.3509632693413937e-05, "loss": 3.8453, "step": 12118 }, { "epoch": 0.6521201033146793, "grad_norm": 1.0890541076660156, "learning_rate": 1.350587948600956e-05, "loss": 4.0774, "step": 12119 }, { "epoch": 0.6521739130434783, "grad_norm": 1.6827356815338135, "learning_rate": 1.3502126607076232e-05, "loss": 4.3473, "step": 12120 }, { "epoch": 0.6522277227722773, "grad_norm": 3.3569324016571045, "learning_rate": 1.3498374056721197e-05, "loss": 3.3511, "step": 12121 }, { "epoch": 0.6522815325010762, "grad_norm": 3.172830581665039, "learning_rate": 1.3494621835051702e-05, "loss": 3.7216, "step": 12122 }, { "epoch": 0.6523353422298752, "grad_norm": 2.2624588012695312, "learning_rate": 1.3490869942174964e-05, "loss": 4.0809, "step": 12123 }, { "epoch": 0.6523891519586741, "grad_norm": 2.6453893184661865, "learning_rate": 1.34871183781982e-05, "loss": 4.2498, "step": 12124 }, { "epoch": 0.6524429616874731, "grad_norm": 2.9409782886505127, "learning_rate": 1.3483367143228642e-05, "loss": 3.3396, "step": 12125 }, { "epoch": 0.652496771416272, "grad_norm": 1.1930898427963257, "learning_rate": 1.3479616237373468e-05, "loss": 4.3381, "step": 12126 }, { "epoch": 0.652550581145071, "grad_norm": 2.2753775119781494, "learning_rate": 1.3475865660739875e-05, "loss": 4.2205, "step": 12127 }, { "epoch": 0.65260439087387, "grad_norm": 2.5127463340759277, "learning_rate": 1.3472115413435047e-05, "loss": 4.3815, "step": 12128 }, { "epoch": 0.652658200602669, "grad_norm": 2.3137857913970947, "learning_rate": 1.3468365495566144e-05, "loss": 4.2619, "step": 12129 }, { "epoch": 0.652712010331468, "grad_norm": 2.948324680328369, "learning_rate": 1.3464615907240346e-05, "loss": 4.2508, "step": 12130 }, { "epoch": 0.6527658200602668, "grad_norm": 2.174872636795044, "learning_rate": 1.3460866648564802e-05, "loss": 3.7266, "step": 12131 }, { "epoch": 0.6528196297890658, "grad_norm": 3.1742262840270996, "learning_rate": 1.3457117719646661e-05, "loss": 3.5692, "step": 12132 }, { "epoch": 0.6528734395178648, "grad_norm": 2.402594566345215, "learning_rate": 1.3453369120593037e-05, "loss": 4.0203, "step": 12133 }, { "epoch": 0.6529272492466638, "grad_norm": 3.129045009613037, "learning_rate": 1.3449620851511058e-05, "loss": 3.672, "step": 12134 }, { "epoch": 0.6529810589754628, "grad_norm": 2.7093122005462646, "learning_rate": 1.3445872912507862e-05, "loss": 3.9111, "step": 12135 }, { "epoch": 0.6530348687042618, "grad_norm": 1.434696912765503, "learning_rate": 1.3442125303690537e-05, "loss": 4.2766, "step": 12136 }, { "epoch": 0.6530886784330607, "grad_norm": 1.2996582984924316, "learning_rate": 1.3438378025166184e-05, "loss": 4.6309, "step": 12137 }, { "epoch": 0.6531424881618597, "grad_norm": 3.1199560165405273, "learning_rate": 1.3434631077041892e-05, "loss": 2.8033, "step": 12138 }, { "epoch": 0.6531962978906586, "grad_norm": 2.3795456886291504, "learning_rate": 1.3430884459424733e-05, "loss": 3.5584, "step": 12139 }, { "epoch": 0.6532501076194576, "grad_norm": 2.9678456783294678, "learning_rate": 1.3427138172421782e-05, "loss": 3.7796, "step": 12140 }, { "epoch": 0.6533039173482565, "grad_norm": 1.3411946296691895, "learning_rate": 1.3423392216140097e-05, "loss": 4.2796, "step": 12141 }, { "epoch": 0.6533577270770555, "grad_norm": 1.2546652555465698, "learning_rate": 1.3419646590686718e-05, "loss": 3.6471, "step": 12142 }, { "epoch": 0.6534115368058545, "grad_norm": 2.17002010345459, "learning_rate": 1.3415901296168698e-05, "loss": 4.329, "step": 12143 }, { "epoch": 0.6534653465346535, "grad_norm": 2.0336077213287354, "learning_rate": 1.341215633269306e-05, "loss": 4.325, "step": 12144 }, { "epoch": 0.6535191562634525, "grad_norm": 1.4296424388885498, "learning_rate": 1.3408411700366813e-05, "loss": 4.0174, "step": 12145 }, { "epoch": 0.6535729659922515, "grad_norm": 3.108802080154419, "learning_rate": 1.3404667399296993e-05, "loss": 4.0113, "step": 12146 }, { "epoch": 0.6536267757210503, "grad_norm": 2.613614320755005, "learning_rate": 1.3400923429590595e-05, "loss": 4.6694, "step": 12147 }, { "epoch": 0.6536805854498493, "grad_norm": 1.9657305479049683, "learning_rate": 1.3397179791354614e-05, "loss": 4.3001, "step": 12148 }, { "epoch": 0.6537343951786483, "grad_norm": 2.690406084060669, "learning_rate": 1.339343648469601e-05, "loss": 3.2438, "step": 12149 }, { "epoch": 0.6537882049074473, "grad_norm": 2.1805684566497803, "learning_rate": 1.3389693509721779e-05, "loss": 3.9361, "step": 12150 }, { "epoch": 0.6538420146362462, "grad_norm": 2.032041549682617, "learning_rate": 1.3385950866538883e-05, "loss": 3.8498, "step": 12151 }, { "epoch": 0.6538958243650452, "grad_norm": 3.7779455184936523, "learning_rate": 1.3382208555254272e-05, "loss": 2.9598, "step": 12152 }, { "epoch": 0.6539496340938442, "grad_norm": 2.6020779609680176, "learning_rate": 1.337846657597489e-05, "loss": 3.9876, "step": 12153 }, { "epoch": 0.6540034438226431, "grad_norm": 2.067530632019043, "learning_rate": 1.3374724928807678e-05, "loss": 3.9328, "step": 12154 }, { "epoch": 0.6540572535514421, "grad_norm": 3.479320526123047, "learning_rate": 1.3370983613859559e-05, "loss": 3.8165, "step": 12155 }, { "epoch": 0.654111063280241, "grad_norm": 3.4194540977478027, "learning_rate": 1.3367242631237448e-05, "loss": 3.7522, "step": 12156 }, { "epoch": 0.65416487300904, "grad_norm": 2.8207850456237793, "learning_rate": 1.3363501981048255e-05, "loss": 3.5532, "step": 12157 }, { "epoch": 0.654218682737839, "grad_norm": 1.84343683719635, "learning_rate": 1.3359761663398878e-05, "loss": 4.0855, "step": 12158 }, { "epoch": 0.654272492466638, "grad_norm": 1.53766667842865, "learning_rate": 1.3356021678396202e-05, "loss": 4.5521, "step": 12159 }, { "epoch": 0.654326302195437, "grad_norm": 3.089226484298706, "learning_rate": 1.33522820261471e-05, "loss": 4.1666, "step": 12160 }, { "epoch": 0.654380111924236, "grad_norm": 2.531020164489746, "learning_rate": 1.3348542706758458e-05, "loss": 4.1853, "step": 12161 }, { "epoch": 0.6544339216530348, "grad_norm": 2.107150077819824, "learning_rate": 1.3344803720337126e-05, "loss": 3.7813, "step": 12162 }, { "epoch": 0.6544877313818338, "grad_norm": 2.466064929962158, "learning_rate": 1.3341065066989967e-05, "loss": 3.489, "step": 12163 }, { "epoch": 0.6545415411106328, "grad_norm": 1.865760087966919, "learning_rate": 1.3337326746823798e-05, "loss": 4.7977, "step": 12164 }, { "epoch": 0.6545953508394318, "grad_norm": 1.4878826141357422, "learning_rate": 1.333358875994545e-05, "loss": 4.5723, "step": 12165 }, { "epoch": 0.6546491605682307, "grad_norm": 2.051923990249634, "learning_rate": 1.3329851106461769e-05, "loss": 4.4737, "step": 12166 }, { "epoch": 0.6547029702970297, "grad_norm": 2.7257816791534424, "learning_rate": 1.3326113786479553e-05, "loss": 3.5854, "step": 12167 }, { "epoch": 0.6547567800258287, "grad_norm": 2.214982509613037, "learning_rate": 1.3322376800105607e-05, "loss": 4.1388, "step": 12168 }, { "epoch": 0.6548105897546277, "grad_norm": 2.5399694442749023, "learning_rate": 1.331864014744672e-05, "loss": 4.158, "step": 12169 }, { "epoch": 0.6548643994834266, "grad_norm": 2.665266990661621, "learning_rate": 1.3314903828609681e-05, "loss": 3.7399, "step": 12170 }, { "epoch": 0.6549182092122255, "grad_norm": 3.5849955081939697, "learning_rate": 1.331116784370126e-05, "loss": 3.0231, "step": 12171 }, { "epoch": 0.6549720189410245, "grad_norm": 3.30786395072937, "learning_rate": 1.3307432192828226e-05, "loss": 3.9481, "step": 12172 }, { "epoch": 0.6550258286698235, "grad_norm": 3.394947052001953, "learning_rate": 1.3303696876097326e-05, "loss": 2.761, "step": 12173 }, { "epoch": 0.6550796383986225, "grad_norm": 3.037461996078491, "learning_rate": 1.3299961893615316e-05, "loss": 3.2333, "step": 12174 }, { "epoch": 0.6551334481274215, "grad_norm": 1.536272406578064, "learning_rate": 1.329622724548892e-05, "loss": 3.8676, "step": 12175 }, { "epoch": 0.6551872578562205, "grad_norm": 3.5433545112609863, "learning_rate": 1.3292492931824862e-05, "loss": 3.378, "step": 12176 }, { "epoch": 0.6552410675850193, "grad_norm": 3.5049047470092773, "learning_rate": 1.3288758952729876e-05, "loss": 3.5091, "step": 12177 }, { "epoch": 0.6552948773138183, "grad_norm": 2.6169252395629883, "learning_rate": 1.3285025308310673e-05, "loss": 3.7292, "step": 12178 }, { "epoch": 0.6553486870426173, "grad_norm": 1.664245367050171, "learning_rate": 1.3281291998673923e-05, "loss": 4.3338, "step": 12179 }, { "epoch": 0.6554024967714163, "grad_norm": 3.4246184825897217, "learning_rate": 1.3277559023926317e-05, "loss": 3.5277, "step": 12180 }, { "epoch": 0.6554563065002152, "grad_norm": 2.831611156463623, "learning_rate": 1.3273826384174559e-05, "loss": 4.0002, "step": 12181 }, { "epoch": 0.6555101162290142, "grad_norm": 2.850193738937378, "learning_rate": 1.3270094079525296e-05, "loss": 3.8853, "step": 12182 }, { "epoch": 0.6555639259578132, "grad_norm": 3.7429144382476807, "learning_rate": 1.3266362110085201e-05, "loss": 3.4403, "step": 12183 }, { "epoch": 0.6556177356866122, "grad_norm": 2.452676296234131, "learning_rate": 1.3262630475960916e-05, "loss": 3.8528, "step": 12184 }, { "epoch": 0.6556715454154111, "grad_norm": 1.8057290315628052, "learning_rate": 1.3258899177259081e-05, "loss": 4.0562, "step": 12185 }, { "epoch": 0.65572535514421, "grad_norm": 3.7549965381622314, "learning_rate": 1.3255168214086328e-05, "loss": 3.4879, "step": 12186 }, { "epoch": 0.655779164873009, "grad_norm": 2.9505014419555664, "learning_rate": 1.3251437586549278e-05, "loss": 4.3822, "step": 12187 }, { "epoch": 0.655832974601808, "grad_norm": 4.463243007659912, "learning_rate": 1.3247707294754541e-05, "loss": 2.7686, "step": 12188 }, { "epoch": 0.655886784330607, "grad_norm": 2.5953593254089355, "learning_rate": 1.3243977338808721e-05, "loss": 4.2108, "step": 12189 }, { "epoch": 0.655940594059406, "grad_norm": 1.7848570346832275, "learning_rate": 1.3240247718818411e-05, "loss": 4.3538, "step": 12190 }, { "epoch": 0.655994403788205, "grad_norm": 1.5978889465332031, "learning_rate": 1.3236518434890177e-05, "loss": 4.5292, "step": 12191 }, { "epoch": 0.6560482135170038, "grad_norm": 4.056630611419678, "learning_rate": 1.3232789487130614e-05, "loss": 3.3659, "step": 12192 }, { "epoch": 0.6561020232458028, "grad_norm": 2.41686749458313, "learning_rate": 1.3229060875646294e-05, "loss": 3.3387, "step": 12193 }, { "epoch": 0.6561558329746018, "grad_norm": 2.598799228668213, "learning_rate": 1.3225332600543738e-05, "loss": 4.3252, "step": 12194 }, { "epoch": 0.6562096427034008, "grad_norm": 2.3887546062469482, "learning_rate": 1.3221604661929509e-05, "loss": 4.2905, "step": 12195 }, { "epoch": 0.6562634524321997, "grad_norm": 1.9604336023330688, "learning_rate": 1.3217877059910127e-05, "loss": 4.2423, "step": 12196 }, { "epoch": 0.6563172621609987, "grad_norm": 2.5578062534332275, "learning_rate": 1.321414979459214e-05, "loss": 4.2488, "step": 12197 }, { "epoch": 0.6563710718897977, "grad_norm": 1.9877225160598755, "learning_rate": 1.3210422866082054e-05, "loss": 4.0345, "step": 12198 }, { "epoch": 0.6564248816185967, "grad_norm": 1.0966880321502686, "learning_rate": 1.3206696274486369e-05, "loss": 4.3204, "step": 12199 }, { "epoch": 0.6564786913473956, "grad_norm": 1.9504247903823853, "learning_rate": 1.3202970019911585e-05, "loss": 4.1137, "step": 12200 }, { "epoch": 0.6565325010761945, "grad_norm": 2.945669651031494, "learning_rate": 1.3199244102464187e-05, "loss": 3.2356, "step": 12201 }, { "epoch": 0.6565863108049935, "grad_norm": 1.5814999341964722, "learning_rate": 1.3195518522250652e-05, "loss": 4.1261, "step": 12202 }, { "epoch": 0.6566401205337925, "grad_norm": 1.9016051292419434, "learning_rate": 1.3191793279377448e-05, "loss": 4.5694, "step": 12203 }, { "epoch": 0.6566939302625915, "grad_norm": 2.83828067779541, "learning_rate": 1.3188068373951032e-05, "loss": 3.9632, "step": 12204 }, { "epoch": 0.6567477399913905, "grad_norm": 4.142434120178223, "learning_rate": 1.3184343806077853e-05, "loss": 3.4865, "step": 12205 }, { "epoch": 0.6568015497201894, "grad_norm": 2.7956132888793945, "learning_rate": 1.3180619575864334e-05, "loss": 3.8644, "step": 12206 }, { "epoch": 0.6568553594489884, "grad_norm": 2.686105966567993, "learning_rate": 1.317689568341693e-05, "loss": 3.2368, "step": 12207 }, { "epoch": 0.6569091691777873, "grad_norm": 2.4175446033477783, "learning_rate": 1.3173172128842046e-05, "loss": 3.857, "step": 12208 }, { "epoch": 0.6569629789065863, "grad_norm": 3.5108776092529297, "learning_rate": 1.3169448912246101e-05, "loss": 3.9485, "step": 12209 }, { "epoch": 0.6570167886353853, "grad_norm": 3.956627607345581, "learning_rate": 1.3165726033735475e-05, "loss": 3.2567, "step": 12210 }, { "epoch": 0.6570705983641842, "grad_norm": 2.286386489868164, "learning_rate": 1.3162003493416563e-05, "loss": 4.3163, "step": 12211 }, { "epoch": 0.6571244080929832, "grad_norm": 2.7730133533477783, "learning_rate": 1.3158281291395758e-05, "loss": 4.0954, "step": 12212 }, { "epoch": 0.6571782178217822, "grad_norm": 2.0123865604400635, "learning_rate": 1.3154559427779423e-05, "loss": 3.588, "step": 12213 }, { "epoch": 0.6572320275505812, "grad_norm": 2.8671927452087402, "learning_rate": 1.3150837902673919e-05, "loss": 3.5587, "step": 12214 }, { "epoch": 0.6572858372793801, "grad_norm": 2.260343551635742, "learning_rate": 1.3147116716185598e-05, "loss": 4.3779, "step": 12215 }, { "epoch": 0.657339647008179, "grad_norm": 2.640298366546631, "learning_rate": 1.3143395868420798e-05, "loss": 4.2369, "step": 12216 }, { "epoch": 0.657393456736978, "grad_norm": 3.0626659393310547, "learning_rate": 1.3139675359485857e-05, "loss": 3.6405, "step": 12217 }, { "epoch": 0.657447266465777, "grad_norm": 2.3816723823547363, "learning_rate": 1.3135955189487092e-05, "loss": 4.4191, "step": 12218 }, { "epoch": 0.657501076194576, "grad_norm": 2.3250839710235596, "learning_rate": 1.3132235358530817e-05, "loss": 4.1322, "step": 12219 }, { "epoch": 0.657554885923375, "grad_norm": 1.2213664054870605, "learning_rate": 1.3128515866723335e-05, "loss": 3.8288, "step": 12220 }, { "epoch": 0.657608695652174, "grad_norm": 1.7602730989456177, "learning_rate": 1.312479671417094e-05, "loss": 3.9195, "step": 12221 }, { "epoch": 0.6576625053809729, "grad_norm": 3.2610349655151367, "learning_rate": 1.3121077900979906e-05, "loss": 3.6984, "step": 12222 }, { "epoch": 0.6577163151097718, "grad_norm": 2.08846378326416, "learning_rate": 1.311735942725652e-05, "loss": 4.2731, "step": 12223 }, { "epoch": 0.6577701248385708, "grad_norm": 3.1882174015045166, "learning_rate": 1.3113641293107054e-05, "loss": 3.8029, "step": 12224 }, { "epoch": 0.6578239345673698, "grad_norm": 2.64906907081604, "learning_rate": 1.3109923498637738e-05, "loss": 3.7152, "step": 12225 }, { "epoch": 0.6578777442961687, "grad_norm": 2.641408681869507, "learning_rate": 1.3106206043954833e-05, "loss": 3.0318, "step": 12226 }, { "epoch": 0.6579315540249677, "grad_norm": 2.4647417068481445, "learning_rate": 1.3102488929164553e-05, "loss": 3.3193, "step": 12227 }, { "epoch": 0.6579853637537667, "grad_norm": 1.817285180091858, "learning_rate": 1.3098772154373151e-05, "loss": 4.0472, "step": 12228 }, { "epoch": 0.6580391734825657, "grad_norm": 1.4071193933486938, "learning_rate": 1.3095055719686827e-05, "loss": 4.0204, "step": 12229 }, { "epoch": 0.6580929832113647, "grad_norm": 1.1863867044448853, "learning_rate": 1.3091339625211796e-05, "loss": 4.1497, "step": 12230 }, { "epoch": 0.6581467929401635, "grad_norm": 3.0244405269622803, "learning_rate": 1.3087623871054244e-05, "loss": 4.2413, "step": 12231 }, { "epoch": 0.6582006026689625, "grad_norm": 2.8458330631256104, "learning_rate": 1.3083908457320363e-05, "loss": 4.0557, "step": 12232 }, { "epoch": 0.6582544123977615, "grad_norm": 2.1898152828216553, "learning_rate": 1.3080193384116324e-05, "loss": 4.4744, "step": 12233 }, { "epoch": 0.6583082221265605, "grad_norm": 2.4700889587402344, "learning_rate": 1.3076478651548301e-05, "loss": 3.7137, "step": 12234 }, { "epoch": 0.6583620318553595, "grad_norm": 3.213918685913086, "learning_rate": 1.3072764259722448e-05, "loss": 4.7546, "step": 12235 }, { "epoch": 0.6584158415841584, "grad_norm": 2.193389415740967, "learning_rate": 1.306905020874491e-05, "loss": 3.3108, "step": 12236 }, { "epoch": 0.6584696513129574, "grad_norm": 2.48356294631958, "learning_rate": 1.306533649872182e-05, "loss": 3.429, "step": 12237 }, { "epoch": 0.6585234610417563, "grad_norm": 1.426794171333313, "learning_rate": 1.306162312975932e-05, "loss": 4.2678, "step": 12238 }, { "epoch": 0.6585772707705553, "grad_norm": 3.22631573677063, "learning_rate": 1.3057910101963527e-05, "loss": 3.4492, "step": 12239 }, { "epoch": 0.6586310804993543, "grad_norm": 3.2547531127929688, "learning_rate": 1.305419741544054e-05, "loss": 3.8275, "step": 12240 }, { "epoch": 0.6586848902281532, "grad_norm": 1.6725767850875854, "learning_rate": 1.3050485070296454e-05, "loss": 4.7542, "step": 12241 }, { "epoch": 0.6587386999569522, "grad_norm": 2.9745869636535645, "learning_rate": 1.3046773066637357e-05, "loss": 3.4514, "step": 12242 }, { "epoch": 0.6587925096857512, "grad_norm": 3.5538036823272705, "learning_rate": 1.3043061404569345e-05, "loss": 3.4659, "step": 12243 }, { "epoch": 0.6588463194145502, "grad_norm": 3.503727674484253, "learning_rate": 1.3039350084198483e-05, "loss": 4.018, "step": 12244 }, { "epoch": 0.6589001291433492, "grad_norm": 1.6640478372573853, "learning_rate": 1.3035639105630817e-05, "loss": 4.3586, "step": 12245 }, { "epoch": 0.658953938872148, "grad_norm": 1.8491406440734863, "learning_rate": 1.303192846897241e-05, "loss": 4.0991, "step": 12246 }, { "epoch": 0.659007748600947, "grad_norm": 2.9717540740966797, "learning_rate": 1.3028218174329293e-05, "loss": 3.4499, "step": 12247 }, { "epoch": 0.659061558329746, "grad_norm": 1.6892527341842651, "learning_rate": 1.3024508221807502e-05, "loss": 4.0489, "step": 12248 }, { "epoch": 0.659115368058545, "grad_norm": 1.8106186389923096, "learning_rate": 1.3020798611513058e-05, "loss": 3.9432, "step": 12249 }, { "epoch": 0.659169177787344, "grad_norm": 3.1216394901275635, "learning_rate": 1.3017089343551967e-05, "loss": 4.0595, "step": 12250 }, { "epoch": 0.6592229875161429, "grad_norm": 2.2003939151763916, "learning_rate": 1.3013380418030233e-05, "loss": 3.5917, "step": 12251 }, { "epoch": 0.6592767972449419, "grad_norm": 3.3247952461242676, "learning_rate": 1.3009671835053847e-05, "loss": 4.2486, "step": 12252 }, { "epoch": 0.6593306069737409, "grad_norm": 2.5263710021972656, "learning_rate": 1.3005963594728779e-05, "loss": 3.6918, "step": 12253 }, { "epoch": 0.6593844167025398, "grad_norm": 2.063507318496704, "learning_rate": 1.300225569716102e-05, "loss": 4.1271, "step": 12254 }, { "epoch": 0.6594382264313388, "grad_norm": 2.8892571926116943, "learning_rate": 1.2998548142456534e-05, "loss": 4.1756, "step": 12255 }, { "epoch": 0.6594920361601377, "grad_norm": 3.032144069671631, "learning_rate": 1.2994840930721253e-05, "loss": 3.5308, "step": 12256 }, { "epoch": 0.6595458458889367, "grad_norm": 2.172492265701294, "learning_rate": 1.2991134062061128e-05, "loss": 4.2701, "step": 12257 }, { "epoch": 0.6595996556177357, "grad_norm": 2.6331374645233154, "learning_rate": 1.2987427536582081e-05, "loss": 3.9417, "step": 12258 }, { "epoch": 0.6596534653465347, "grad_norm": 2.7221481800079346, "learning_rate": 1.2983721354390055e-05, "loss": 4.4921, "step": 12259 }, { "epoch": 0.6597072750753337, "grad_norm": 1.9642468690872192, "learning_rate": 1.2980015515590954e-05, "loss": 3.8418, "step": 12260 }, { "epoch": 0.6597610848041325, "grad_norm": 2.0638961791992188, "learning_rate": 1.2976310020290678e-05, "loss": 4.4405, "step": 12261 }, { "epoch": 0.6598148945329315, "grad_norm": 4.082123756408691, "learning_rate": 1.2972604868595122e-05, "loss": 3.4945, "step": 12262 }, { "epoch": 0.6598687042617305, "grad_norm": 1.4867141246795654, "learning_rate": 1.2968900060610168e-05, "loss": 4.1555, "step": 12263 }, { "epoch": 0.6599225139905295, "grad_norm": 3.156217575073242, "learning_rate": 1.2965195596441693e-05, "loss": 3.7462, "step": 12264 }, { "epoch": 0.6599763237193285, "grad_norm": 3.3143539428710938, "learning_rate": 1.2961491476195557e-05, "loss": 3.9957, "step": 12265 }, { "epoch": 0.6600301334481274, "grad_norm": 3.2397396564483643, "learning_rate": 1.2957787699977613e-05, "loss": 3.7034, "step": 12266 }, { "epoch": 0.6600839431769264, "grad_norm": 4.130260467529297, "learning_rate": 1.2954084267893707e-05, "loss": 3.5269, "step": 12267 }, { "epoch": 0.6601377529057254, "grad_norm": 3.1908955574035645, "learning_rate": 1.2950381180049664e-05, "loss": 3.2629, "step": 12268 }, { "epoch": 0.6601915626345243, "grad_norm": 2.6687262058258057, "learning_rate": 1.2946678436551329e-05, "loss": 3.8643, "step": 12269 }, { "epoch": 0.6602453723633233, "grad_norm": 2.2902517318725586, "learning_rate": 1.2942976037504512e-05, "loss": 3.9726, "step": 12270 }, { "epoch": 0.6602991820921222, "grad_norm": 1.9449875354766846, "learning_rate": 1.2939273983015e-05, "loss": 4.1297, "step": 12271 }, { "epoch": 0.6603529918209212, "grad_norm": 2.6280534267425537, "learning_rate": 1.29355722731886e-05, "loss": 3.7931, "step": 12272 }, { "epoch": 0.6604068015497202, "grad_norm": 3.3840651512145996, "learning_rate": 1.2931870908131082e-05, "loss": 3.6831, "step": 12273 }, { "epoch": 0.6604606112785192, "grad_norm": 1.9639503955841064, "learning_rate": 1.292816988794825e-05, "loss": 4.6118, "step": 12274 }, { "epoch": 0.6605144210073182, "grad_norm": 1.7912657260894775, "learning_rate": 1.2924469212745848e-05, "loss": 4.4083, "step": 12275 }, { "epoch": 0.660568230736117, "grad_norm": 2.4616622924804688, "learning_rate": 1.2920768882629636e-05, "loss": 3.6959, "step": 12276 }, { "epoch": 0.660622040464916, "grad_norm": 2.665985584259033, "learning_rate": 1.2917068897705373e-05, "loss": 3.8845, "step": 12277 }, { "epoch": 0.660675850193715, "grad_norm": 4.336305141448975, "learning_rate": 1.2913369258078761e-05, "loss": 2.7048, "step": 12278 }, { "epoch": 0.660729659922514, "grad_norm": 3.883298397064209, "learning_rate": 1.2909669963855553e-05, "loss": 3.4953, "step": 12279 }, { "epoch": 0.660783469651313, "grad_norm": 1.3857688903808594, "learning_rate": 1.2905971015141463e-05, "loss": 4.6425, "step": 12280 }, { "epoch": 0.6608372793801119, "grad_norm": 1.9104915857315063, "learning_rate": 1.2902272412042191e-05, "loss": 4.775, "step": 12281 }, { "epoch": 0.6608910891089109, "grad_norm": 3.16697096824646, "learning_rate": 1.2898574154663435e-05, "loss": 3.6977, "step": 12282 }, { "epoch": 0.6609448988377099, "grad_norm": 2.42067813873291, "learning_rate": 1.2894876243110875e-05, "loss": 3.6271, "step": 12283 }, { "epoch": 0.6609987085665088, "grad_norm": 2.746826171875, "learning_rate": 1.289117867749019e-05, "loss": 3.1514, "step": 12284 }, { "epoch": 0.6610525182953078, "grad_norm": 3.0876777172088623, "learning_rate": 1.2887481457907066e-05, "loss": 3.4986, "step": 12285 }, { "epoch": 0.6611063280241067, "grad_norm": 2.8551478385925293, "learning_rate": 1.2883784584467135e-05, "loss": 4.1554, "step": 12286 }, { "epoch": 0.6611601377529057, "grad_norm": 2.1893012523651123, "learning_rate": 1.2880088057276052e-05, "loss": 3.7511, "step": 12287 }, { "epoch": 0.6612139474817047, "grad_norm": 2.1504273414611816, "learning_rate": 1.287639187643945e-05, "loss": 3.6769, "step": 12288 }, { "epoch": 0.6612677572105037, "grad_norm": 2.008423089981079, "learning_rate": 1.2872696042062953e-05, "loss": 4.3558, "step": 12289 }, { "epoch": 0.6613215669393027, "grad_norm": 2.234161138534546, "learning_rate": 1.2869000554252192e-05, "loss": 4.1195, "step": 12290 }, { "epoch": 0.6613753766681016, "grad_norm": 3.2220370769500732, "learning_rate": 1.2865305413112768e-05, "loss": 3.5097, "step": 12291 }, { "epoch": 0.6614291863969005, "grad_norm": 1.822831630706787, "learning_rate": 1.2861610618750278e-05, "loss": 4.1733, "step": 12292 }, { "epoch": 0.6614829961256995, "grad_norm": 1.7245843410491943, "learning_rate": 1.2857916171270307e-05, "loss": 4.5443, "step": 12293 }, { "epoch": 0.6615368058544985, "grad_norm": 3.801142692565918, "learning_rate": 1.2854222070778432e-05, "loss": 4.1967, "step": 12294 }, { "epoch": 0.6615906155832975, "grad_norm": 2.31396222114563, "learning_rate": 1.2850528317380223e-05, "loss": 4.1393, "step": 12295 }, { "epoch": 0.6616444253120964, "grad_norm": 1.2184840440750122, "learning_rate": 1.2846834911181238e-05, "loss": 4.4549, "step": 12296 }, { "epoch": 0.6616982350408954, "grad_norm": 3.1907143592834473, "learning_rate": 1.2843141852287021e-05, "loss": 3.9774, "step": 12297 }, { "epoch": 0.6617520447696944, "grad_norm": 2.314479112625122, "learning_rate": 1.2839449140803112e-05, "loss": 4.1539, "step": 12298 }, { "epoch": 0.6618058544984933, "grad_norm": 2.1787142753601074, "learning_rate": 1.2835756776835029e-05, "loss": 3.7982, "step": 12299 }, { "epoch": 0.6618596642272923, "grad_norm": 1.3089576959609985, "learning_rate": 1.2832064760488322e-05, "loss": 4.4247, "step": 12300 }, { "epoch": 0.6619134739560912, "grad_norm": 2.426955223083496, "learning_rate": 1.2828373091868462e-05, "loss": 3.6577, "step": 12301 }, { "epoch": 0.6619672836848902, "grad_norm": 2.0998072624206543, "learning_rate": 1.2824681771080962e-05, "loss": 4.3285, "step": 12302 }, { "epoch": 0.6620210934136892, "grad_norm": 3.115309953689575, "learning_rate": 1.2820990798231309e-05, "loss": 3.7787, "step": 12303 }, { "epoch": 0.6620749031424882, "grad_norm": 3.276045560836792, "learning_rate": 1.2817300173424973e-05, "loss": 3.7684, "step": 12304 }, { "epoch": 0.6621287128712872, "grad_norm": 2.2376277446746826, "learning_rate": 1.2813609896767442e-05, "loss": 3.8005, "step": 12305 }, { "epoch": 0.6621825226000861, "grad_norm": 2.6195685863494873, "learning_rate": 1.2809919968364158e-05, "loss": 3.9847, "step": 12306 }, { "epoch": 0.662236332328885, "grad_norm": 2.415574073791504, "learning_rate": 1.2806230388320577e-05, "loss": 4.1395, "step": 12307 }, { "epoch": 0.662290142057684, "grad_norm": 2.041968584060669, "learning_rate": 1.2802541156742143e-05, "loss": 4.4782, "step": 12308 }, { "epoch": 0.662343951786483, "grad_norm": 2.9655210971832275, "learning_rate": 1.2798852273734258e-05, "loss": 3.3057, "step": 12309 }, { "epoch": 0.662397761515282, "grad_norm": 3.270806074142456, "learning_rate": 1.2795163739402362e-05, "loss": 3.6773, "step": 12310 }, { "epoch": 0.6624515712440809, "grad_norm": 2.987283945083618, "learning_rate": 1.2791475553851864e-05, "loss": 3.6532, "step": 12311 }, { "epoch": 0.6625053809728799, "grad_norm": 2.754774808883667, "learning_rate": 1.2787787717188154e-05, "loss": 3.2091, "step": 12312 }, { "epoch": 0.6625591907016789, "grad_norm": 2.3048408031463623, "learning_rate": 1.2784100229516627e-05, "loss": 4.3647, "step": 12313 }, { "epoch": 0.6626130004304779, "grad_norm": 2.669694423675537, "learning_rate": 1.278041309094266e-05, "loss": 3.7268, "step": 12314 }, { "epoch": 0.6626668101592768, "grad_norm": 3.458911180496216, "learning_rate": 1.2776726301571607e-05, "loss": 3.0072, "step": 12315 }, { "epoch": 0.6627206198880757, "grad_norm": 2.819103479385376, "learning_rate": 1.2773039861508862e-05, "loss": 3.932, "step": 12316 }, { "epoch": 0.6627744296168747, "grad_norm": 2.318096399307251, "learning_rate": 1.2769353770859738e-05, "loss": 4.0395, "step": 12317 }, { "epoch": 0.6628282393456737, "grad_norm": 1.3762857913970947, "learning_rate": 1.2765668029729589e-05, "loss": 3.7588, "step": 12318 }, { "epoch": 0.6628820490744727, "grad_norm": 2.3405063152313232, "learning_rate": 1.276198263822374e-05, "loss": 3.3872, "step": 12319 }, { "epoch": 0.6629358588032717, "grad_norm": 1.840250849723816, "learning_rate": 1.2758297596447499e-05, "loss": 4.5132, "step": 12320 }, { "epoch": 0.6629896685320706, "grad_norm": 3.343066930770874, "learning_rate": 1.2754612904506202e-05, "loss": 3.3754, "step": 12321 }, { "epoch": 0.6630434782608695, "grad_norm": 2.4410204887390137, "learning_rate": 1.2750928562505127e-05, "loss": 3.547, "step": 12322 }, { "epoch": 0.6630972879896685, "grad_norm": 1.2542535066604614, "learning_rate": 1.2747244570549576e-05, "loss": 4.1791, "step": 12323 }, { "epoch": 0.6631510977184675, "grad_norm": 1.7187341451644897, "learning_rate": 1.2743560928744805e-05, "loss": 3.8727, "step": 12324 }, { "epoch": 0.6632049074472665, "grad_norm": 3.364539384841919, "learning_rate": 1.2739877637196105e-05, "loss": 4.3628, "step": 12325 }, { "epoch": 0.6632587171760654, "grad_norm": 3.575822591781616, "learning_rate": 1.2736194696008725e-05, "loss": 3.3456, "step": 12326 }, { "epoch": 0.6633125269048644, "grad_norm": 1.2608351707458496, "learning_rate": 1.2732512105287913e-05, "loss": 4.3605, "step": 12327 }, { "epoch": 0.6633663366336634, "grad_norm": 1.3093243837356567, "learning_rate": 1.2728829865138914e-05, "loss": 4.4052, "step": 12328 }, { "epoch": 0.6634201463624624, "grad_norm": 2.3636691570281982, "learning_rate": 1.2725147975666948e-05, "loss": 3.7173, "step": 12329 }, { "epoch": 0.6634739560912613, "grad_norm": 3.7390167713165283, "learning_rate": 1.272146643697723e-05, "loss": 4.0172, "step": 12330 }, { "epoch": 0.6635277658200602, "grad_norm": 3.1673858165740967, "learning_rate": 1.2717785249174993e-05, "loss": 4.013, "step": 12331 }, { "epoch": 0.6635815755488592, "grad_norm": 3.5560295581817627, "learning_rate": 1.271410441236541e-05, "loss": 4.4829, "step": 12332 }, { "epoch": 0.6636353852776582, "grad_norm": 1.8803225755691528, "learning_rate": 1.2710423926653677e-05, "loss": 4.1794, "step": 12333 }, { "epoch": 0.6636891950064572, "grad_norm": 2.456195592880249, "learning_rate": 1.2706743792144976e-05, "loss": 3.9636, "step": 12334 }, { "epoch": 0.6637430047352562, "grad_norm": 2.8614535331726074, "learning_rate": 1.270306400894446e-05, "loss": 3.1982, "step": 12335 }, { "epoch": 0.6637968144640551, "grad_norm": 2.9472525119781494, "learning_rate": 1.2699384577157309e-05, "loss": 4.08, "step": 12336 }, { "epoch": 0.6638506241928541, "grad_norm": 2.859590768814087, "learning_rate": 1.2695705496888663e-05, "loss": 3.8483, "step": 12337 }, { "epoch": 0.663904433921653, "grad_norm": 2.080650568008423, "learning_rate": 1.269202676824366e-05, "loss": 4.0365, "step": 12338 }, { "epoch": 0.663958243650452, "grad_norm": 2.3971104621887207, "learning_rate": 1.2688348391327434e-05, "loss": 4.0291, "step": 12339 }, { "epoch": 0.664012053379251, "grad_norm": 2.2328264713287354, "learning_rate": 1.268467036624508e-05, "loss": 4.3069, "step": 12340 }, { "epoch": 0.6640658631080499, "grad_norm": 1.9098261594772339, "learning_rate": 1.2680992693101732e-05, "loss": 3.8284, "step": 12341 }, { "epoch": 0.6641196728368489, "grad_norm": 1.6863149404525757, "learning_rate": 1.267731537200248e-05, "loss": 3.7467, "step": 12342 }, { "epoch": 0.6641734825656479, "grad_norm": 1.7347241640090942, "learning_rate": 1.2673638403052407e-05, "loss": 3.8782, "step": 12343 }, { "epoch": 0.6642272922944469, "grad_norm": 2.9111948013305664, "learning_rate": 1.2669961786356597e-05, "loss": 3.6771, "step": 12344 }, { "epoch": 0.6642811020232458, "grad_norm": 2.339738130569458, "learning_rate": 1.2666285522020114e-05, "loss": 3.017, "step": 12345 }, { "epoch": 0.6643349117520447, "grad_norm": 2.1176986694335938, "learning_rate": 1.2662609610148016e-05, "loss": 4.185, "step": 12346 }, { "epoch": 0.6643887214808437, "grad_norm": 2.68782377243042, "learning_rate": 1.2658934050845353e-05, "loss": 3.4134, "step": 12347 }, { "epoch": 0.6644425312096427, "grad_norm": 3.469831943511963, "learning_rate": 1.265525884421716e-05, "loss": 3.8704, "step": 12348 }, { "epoch": 0.6644963409384417, "grad_norm": 3.1987736225128174, "learning_rate": 1.2651583990368469e-05, "loss": 3.428, "step": 12349 }, { "epoch": 0.6645501506672407, "grad_norm": 2.09320068359375, "learning_rate": 1.2647909489404291e-05, "loss": 4.4243, "step": 12350 }, { "epoch": 0.6646039603960396, "grad_norm": 2.251471757888794, "learning_rate": 1.2644235341429627e-05, "loss": 3.8188, "step": 12351 }, { "epoch": 0.6646577701248386, "grad_norm": 1.9856971502304077, "learning_rate": 1.2640561546549495e-05, "loss": 4.2092, "step": 12352 }, { "epoch": 0.6647115798536375, "grad_norm": 2.2584686279296875, "learning_rate": 1.2636888104868872e-05, "loss": 4.2603, "step": 12353 }, { "epoch": 0.6647653895824365, "grad_norm": 3.6938867568969727, "learning_rate": 1.2633215016492743e-05, "loss": 3.7109, "step": 12354 }, { "epoch": 0.6648191993112355, "grad_norm": 2.8858871459960938, "learning_rate": 1.2629542281526047e-05, "loss": 3.2154, "step": 12355 }, { "epoch": 0.6648730090400344, "grad_norm": 1.734044075012207, "learning_rate": 1.2625869900073767e-05, "loss": 4.3822, "step": 12356 }, { "epoch": 0.6649268187688334, "grad_norm": 3.292292356491089, "learning_rate": 1.2622197872240845e-05, "loss": 4.3944, "step": 12357 }, { "epoch": 0.6649806284976324, "grad_norm": 3.400789260864258, "learning_rate": 1.2618526198132217e-05, "loss": 3.9184, "step": 12358 }, { "epoch": 0.6650344382264314, "grad_norm": 3.6102685928344727, "learning_rate": 1.2614854877852804e-05, "loss": 3.5639, "step": 12359 }, { "epoch": 0.6650882479552304, "grad_norm": 2.2550370693206787, "learning_rate": 1.2611183911507529e-05, "loss": 3.0145, "step": 12360 }, { "epoch": 0.6651420576840292, "grad_norm": 1.6025941371917725, "learning_rate": 1.2607513299201285e-05, "loss": 3.8348, "step": 12361 }, { "epoch": 0.6651958674128282, "grad_norm": 2.639310359954834, "learning_rate": 1.2603843041039e-05, "loss": 3.2994, "step": 12362 }, { "epoch": 0.6652496771416272, "grad_norm": 2.5512187480926514, "learning_rate": 1.2600173137125528e-05, "loss": 4.3867, "step": 12363 }, { "epoch": 0.6653034868704262, "grad_norm": 3.162238121032715, "learning_rate": 1.2596503587565756e-05, "loss": 3.4591, "step": 12364 }, { "epoch": 0.6653572965992252, "grad_norm": 1.8659089803695679, "learning_rate": 1.2592834392464553e-05, "loss": 4.6259, "step": 12365 }, { "epoch": 0.6654111063280241, "grad_norm": 1.489788293838501, "learning_rate": 1.2589165551926757e-05, "loss": 4.0367, "step": 12366 }, { "epoch": 0.6654649160568231, "grad_norm": 2.3529365062713623, "learning_rate": 1.2585497066057242e-05, "loss": 3.6232, "step": 12367 }, { "epoch": 0.665518725785622, "grad_norm": 2.8311691284179688, "learning_rate": 1.2581828934960827e-05, "loss": 3.9939, "step": 12368 }, { "epoch": 0.665572535514421, "grad_norm": 1.5905994176864624, "learning_rate": 1.2578161158742352e-05, "loss": 4.2275, "step": 12369 }, { "epoch": 0.66562634524322, "grad_norm": 1.4465981721878052, "learning_rate": 1.2574493737506609e-05, "loss": 4.7901, "step": 12370 }, { "epoch": 0.6656801549720189, "grad_norm": 3.032902479171753, "learning_rate": 1.2570826671358405e-05, "loss": 3.3194, "step": 12371 }, { "epoch": 0.6657339647008179, "grad_norm": 3.318711280822754, "learning_rate": 1.2567159960402556e-05, "loss": 3.0984, "step": 12372 }, { "epoch": 0.6657877744296169, "grad_norm": 3.283729076385498, "learning_rate": 1.2563493604743831e-05, "loss": 3.8678, "step": 12373 }, { "epoch": 0.6658415841584159, "grad_norm": 3.8955633640289307, "learning_rate": 1.2559827604487013e-05, "loss": 3.9891, "step": 12374 }, { "epoch": 0.6658953938872149, "grad_norm": 3.5261311531066895, "learning_rate": 1.255616195973686e-05, "loss": 3.2384, "step": 12375 }, { "epoch": 0.6659492036160137, "grad_norm": 1.6612977981567383, "learning_rate": 1.2552496670598127e-05, "loss": 4.5172, "step": 12376 }, { "epoch": 0.6660030133448127, "grad_norm": 3.9136366844177246, "learning_rate": 1.254883173717556e-05, "loss": 3.8557, "step": 12377 }, { "epoch": 0.6660568230736117, "grad_norm": 1.5407204627990723, "learning_rate": 1.2545167159573892e-05, "loss": 4.1005, "step": 12378 }, { "epoch": 0.6661106328024107, "grad_norm": 3.745713233947754, "learning_rate": 1.2541502937897848e-05, "loss": 3.8263, "step": 12379 }, { "epoch": 0.6661644425312097, "grad_norm": 3.446183204650879, "learning_rate": 1.253783907225214e-05, "loss": 3.2807, "step": 12380 }, { "epoch": 0.6662182522600086, "grad_norm": 3.3743338584899902, "learning_rate": 1.2534175562741471e-05, "loss": 2.9336, "step": 12381 }, { "epoch": 0.6662720619888076, "grad_norm": 2.0291569232940674, "learning_rate": 1.2530512409470527e-05, "loss": 4.0455, "step": 12382 }, { "epoch": 0.6663258717176065, "grad_norm": 2.480874538421631, "learning_rate": 1.252684961254401e-05, "loss": 4.0699, "step": 12383 }, { "epoch": 0.6663796814464055, "grad_norm": 3.2142882347106934, "learning_rate": 1.2523187172066588e-05, "loss": 3.6205, "step": 12384 }, { "epoch": 0.6664334911752045, "grad_norm": 1.0396519899368286, "learning_rate": 1.251952508814291e-05, "loss": 4.4183, "step": 12385 }, { "epoch": 0.6664873009040034, "grad_norm": 2.8706612586975098, "learning_rate": 1.2515863360877627e-05, "loss": 3.7589, "step": 12386 }, { "epoch": 0.6665411106328024, "grad_norm": 1.7504756450653076, "learning_rate": 1.2512201990375406e-05, "loss": 4.0966, "step": 12387 }, { "epoch": 0.6665949203616014, "grad_norm": 2.793138265609741, "learning_rate": 1.2508540976740858e-05, "loss": 4.0874, "step": 12388 }, { "epoch": 0.6666487300904004, "grad_norm": 2.3806426525115967, "learning_rate": 1.250488032007861e-05, "loss": 4.1504, "step": 12389 }, { "epoch": 0.6667025398191994, "grad_norm": 3.2522435188293457, "learning_rate": 1.2501220020493276e-05, "loss": 3.5347, "step": 12390 }, { "epoch": 0.6667563495479982, "grad_norm": 1.7520008087158203, "learning_rate": 1.2497560078089457e-05, "loss": 3.7402, "step": 12391 }, { "epoch": 0.6668101592767972, "grad_norm": 2.4144701957702637, "learning_rate": 1.2493900492971741e-05, "loss": 3.993, "step": 12392 }, { "epoch": 0.6668639690055962, "grad_norm": 1.7396886348724365, "learning_rate": 1.2490241265244715e-05, "loss": 4.0061, "step": 12393 }, { "epoch": 0.6669177787343952, "grad_norm": 1.7663768529891968, "learning_rate": 1.2486582395012943e-05, "loss": 3.5682, "step": 12394 }, { "epoch": 0.6669715884631942, "grad_norm": 3.6204206943511963, "learning_rate": 1.2482923882380989e-05, "loss": 3.2335, "step": 12395 }, { "epoch": 0.6670253981919931, "grad_norm": 2.806426763534546, "learning_rate": 1.2479265727453407e-05, "loss": 4.629, "step": 12396 }, { "epoch": 0.6670792079207921, "grad_norm": 1.958825945854187, "learning_rate": 1.2475607930334721e-05, "loss": 4.3067, "step": 12397 }, { "epoch": 0.6671330176495911, "grad_norm": 2.841392755508423, "learning_rate": 1.2471950491129483e-05, "loss": 4.2184, "step": 12398 }, { "epoch": 0.66718682737839, "grad_norm": 2.6322951316833496, "learning_rate": 1.2468293409942206e-05, "loss": 4.1469, "step": 12399 }, { "epoch": 0.667240637107189, "grad_norm": 1.7724521160125732, "learning_rate": 1.2464636686877407e-05, "loss": 4.4142, "step": 12400 }, { "epoch": 0.6672944468359879, "grad_norm": 2.6203017234802246, "learning_rate": 1.2460980322039562e-05, "loss": 3.325, "step": 12401 }, { "epoch": 0.6673482565647869, "grad_norm": 2.146210193634033, "learning_rate": 1.2457324315533167e-05, "loss": 3.2394, "step": 12402 }, { "epoch": 0.6674020662935859, "grad_norm": 2.4126412868499756, "learning_rate": 1.2453668667462714e-05, "loss": 3.4138, "step": 12403 }, { "epoch": 0.6674558760223849, "grad_norm": 1.9943957328796387, "learning_rate": 1.2450013377932667e-05, "loss": 3.938, "step": 12404 }, { "epoch": 0.6675096857511839, "grad_norm": 2.436997413635254, "learning_rate": 1.2446358447047483e-05, "loss": 3.8438, "step": 12405 }, { "epoch": 0.6675634954799827, "grad_norm": 2.666412591934204, "learning_rate": 1.2442703874911607e-05, "loss": 4.0257, "step": 12406 }, { "epoch": 0.6676173052087817, "grad_norm": 2.295020818710327, "learning_rate": 1.243904966162948e-05, "loss": 3.9779, "step": 12407 }, { "epoch": 0.6676711149375807, "grad_norm": 1.836544394493103, "learning_rate": 1.2435395807305527e-05, "loss": 4.2413, "step": 12408 }, { "epoch": 0.6677249246663797, "grad_norm": 2.9630179405212402, "learning_rate": 1.243174231204417e-05, "loss": 3.4057, "step": 12409 }, { "epoch": 0.6677787343951787, "grad_norm": 3.7802627086639404, "learning_rate": 1.2428089175949811e-05, "loss": 3.6795, "step": 12410 }, { "epoch": 0.6678325441239776, "grad_norm": 1.8006125688552856, "learning_rate": 1.2424436399126852e-05, "loss": 4.3927, "step": 12411 }, { "epoch": 0.6678863538527766, "grad_norm": 3.021615982055664, "learning_rate": 1.2420783981679663e-05, "loss": 3.5391, "step": 12412 }, { "epoch": 0.6679401635815756, "grad_norm": 2.24809193611145, "learning_rate": 1.2417131923712644e-05, "loss": 3.6135, "step": 12413 }, { "epoch": 0.6679939733103745, "grad_norm": 1.2026827335357666, "learning_rate": 1.2413480225330152e-05, "loss": 4.6394, "step": 12414 }, { "epoch": 0.6680477830391734, "grad_norm": 2.5287046432495117, "learning_rate": 1.2409828886636551e-05, "loss": 3.5911, "step": 12415 }, { "epoch": 0.6681015927679724, "grad_norm": 3.108055353164673, "learning_rate": 1.2406177907736167e-05, "loss": 3.8822, "step": 12416 }, { "epoch": 0.6681554024967714, "grad_norm": 3.509652614593506, "learning_rate": 1.2402527288733334e-05, "loss": 3.8835, "step": 12417 }, { "epoch": 0.6682092122255704, "grad_norm": 2.3336308002471924, "learning_rate": 1.2398877029732401e-05, "loss": 3.6575, "step": 12418 }, { "epoch": 0.6682630219543694, "grad_norm": 3.4326515197753906, "learning_rate": 1.2395227130837664e-05, "loss": 4.3132, "step": 12419 }, { "epoch": 0.6683168316831684, "grad_norm": 3.4230165481567383, "learning_rate": 1.2391577592153436e-05, "loss": 3.5458, "step": 12420 }, { "epoch": 0.6683706414119673, "grad_norm": 4.09432315826416, "learning_rate": 1.2387928413784008e-05, "loss": 3.9088, "step": 12421 }, { "epoch": 0.6684244511407662, "grad_norm": 2.0553648471832275, "learning_rate": 1.2384279595833665e-05, "loss": 4.2318, "step": 12422 }, { "epoch": 0.6684782608695652, "grad_norm": 1.7812473773956299, "learning_rate": 1.2380631138406676e-05, "loss": 2.7825, "step": 12423 }, { "epoch": 0.6685320705983642, "grad_norm": 2.2311325073242188, "learning_rate": 1.2376983041607307e-05, "loss": 4.2419, "step": 12424 }, { "epoch": 0.6685858803271632, "grad_norm": 2.8834002017974854, "learning_rate": 1.237333530553981e-05, "loss": 4.5855, "step": 12425 }, { "epoch": 0.6686396900559621, "grad_norm": 3.562481641769409, "learning_rate": 1.236968793030843e-05, "loss": 3.6977, "step": 12426 }, { "epoch": 0.6686934997847611, "grad_norm": 2.9126527309417725, "learning_rate": 1.2366040916017399e-05, "loss": 4.2551, "step": 12427 }, { "epoch": 0.6687473095135601, "grad_norm": 1.4684010744094849, "learning_rate": 1.2362394262770924e-05, "loss": 4.6658, "step": 12428 }, { "epoch": 0.668801119242359, "grad_norm": 2.6774916648864746, "learning_rate": 1.2358747970673243e-05, "loss": 3.2425, "step": 12429 }, { "epoch": 0.668854928971158, "grad_norm": 2.321786880493164, "learning_rate": 1.235510203982855e-05, "loss": 3.8041, "step": 12430 }, { "epoch": 0.6689087386999569, "grad_norm": 3.8857367038726807, "learning_rate": 1.2351456470341022e-05, "loss": 3.6065, "step": 12431 }, { "epoch": 0.6689625484287559, "grad_norm": 1.9913195371627808, "learning_rate": 1.2347811262314849e-05, "loss": 4.0616, "step": 12432 }, { "epoch": 0.6690163581575549, "grad_norm": 3.5838141441345215, "learning_rate": 1.2344166415854188e-05, "loss": 3.8884, "step": 12433 }, { "epoch": 0.6690701678863539, "grad_norm": 1.7323697805404663, "learning_rate": 1.234052193106322e-05, "loss": 4.4095, "step": 12434 }, { "epoch": 0.6691239776151529, "grad_norm": 3.5901520252227783, "learning_rate": 1.2336877808046088e-05, "loss": 3.0945, "step": 12435 }, { "epoch": 0.6691777873439518, "grad_norm": 2.3656396865844727, "learning_rate": 1.2333234046906925e-05, "loss": 4.0614, "step": 12436 }, { "epoch": 0.6692315970727507, "grad_norm": 2.392108678817749, "learning_rate": 1.2329590647749867e-05, "loss": 3.7932, "step": 12437 }, { "epoch": 0.6692854068015497, "grad_norm": 1.9188600778579712, "learning_rate": 1.2325947610679025e-05, "loss": 3.9898, "step": 12438 }, { "epoch": 0.6693392165303487, "grad_norm": 3.423513650894165, "learning_rate": 1.2322304935798512e-05, "loss": 4.0856, "step": 12439 }, { "epoch": 0.6693930262591476, "grad_norm": 3.509065866470337, "learning_rate": 1.2318662623212426e-05, "loss": 3.7115, "step": 12440 }, { "epoch": 0.6694468359879466, "grad_norm": 3.073862075805664, "learning_rate": 1.2315020673024854e-05, "loss": 3.4928, "step": 12441 }, { "epoch": 0.6695006457167456, "grad_norm": 2.769416093826294, "learning_rate": 1.2311379085339872e-05, "loss": 3.9554, "step": 12442 }, { "epoch": 0.6695544554455446, "grad_norm": 1.9185339212417603, "learning_rate": 1.2307737860261537e-05, "loss": 4.1858, "step": 12443 }, { "epoch": 0.6696082651743436, "grad_norm": 2.4998703002929688, "learning_rate": 1.2304096997893927e-05, "loss": 3.4005, "step": 12444 }, { "epoch": 0.6696620749031424, "grad_norm": 3.5841259956359863, "learning_rate": 1.2300456498341075e-05, "loss": 4.0178, "step": 12445 }, { "epoch": 0.6697158846319414, "grad_norm": 2.92189359664917, "learning_rate": 1.229681636170703e-05, "loss": 4.2532, "step": 12446 }, { "epoch": 0.6697696943607404, "grad_norm": 2.516937255859375, "learning_rate": 1.2293176588095796e-05, "loss": 4.2383, "step": 12447 }, { "epoch": 0.6698235040895394, "grad_norm": 2.079028367996216, "learning_rate": 1.2289537177611387e-05, "loss": 3.5722, "step": 12448 }, { "epoch": 0.6698773138183384, "grad_norm": 2.5113580226898193, "learning_rate": 1.2285898130357828e-05, "loss": 4.0315, "step": 12449 }, { "epoch": 0.6699311235471374, "grad_norm": 2.401315212249756, "learning_rate": 1.2282259446439103e-05, "loss": 4.8115, "step": 12450 }, { "epoch": 0.6699849332759363, "grad_norm": 2.5485336780548096, "learning_rate": 1.2278621125959197e-05, "loss": 4.5656, "step": 12451 }, { "epoch": 0.6700387430047352, "grad_norm": 3.0327725410461426, "learning_rate": 1.2274983169022083e-05, "loss": 3.6099, "step": 12452 }, { "epoch": 0.6700925527335342, "grad_norm": 2.378566265106201, "learning_rate": 1.2271345575731723e-05, "loss": 3.9212, "step": 12453 }, { "epoch": 0.6701463624623332, "grad_norm": 2.72912859916687, "learning_rate": 1.2267708346192072e-05, "loss": 4.2229, "step": 12454 }, { "epoch": 0.6702001721911321, "grad_norm": 1.802124261856079, "learning_rate": 1.226407148050707e-05, "loss": 4.2548, "step": 12455 }, { "epoch": 0.6702539819199311, "grad_norm": 4.1633620262146, "learning_rate": 1.226043497878065e-05, "loss": 4.2425, "step": 12456 }, { "epoch": 0.6703077916487301, "grad_norm": 1.4467235803604126, "learning_rate": 1.2256798841116731e-05, "loss": 4.4238, "step": 12457 }, { "epoch": 0.6703616013775291, "grad_norm": 2.8134825229644775, "learning_rate": 1.2253163067619228e-05, "loss": 3.3779, "step": 12458 }, { "epoch": 0.6704154111063281, "grad_norm": 2.676481008529663, "learning_rate": 1.2249527658392026e-05, "loss": 4.0832, "step": 12459 }, { "epoch": 0.6704692208351269, "grad_norm": 2.526498317718506, "learning_rate": 1.2245892613539043e-05, "loss": 3.9969, "step": 12460 }, { "epoch": 0.6705230305639259, "grad_norm": 3.7005462646484375, "learning_rate": 1.2242257933164154e-05, "loss": 3.5949, "step": 12461 }, { "epoch": 0.6705768402927249, "grad_norm": 2.146357536315918, "learning_rate": 1.2238623617371207e-05, "loss": 4.2274, "step": 12462 }, { "epoch": 0.6706306500215239, "grad_norm": 1.982625126838684, "learning_rate": 1.2234989666264074e-05, "loss": 3.7944, "step": 12463 }, { "epoch": 0.6706844597503229, "grad_norm": 3.91787052154541, "learning_rate": 1.2231356079946594e-05, "loss": 3.5722, "step": 12464 }, { "epoch": 0.6707382694791219, "grad_norm": 2.7829272747039795, "learning_rate": 1.2227722858522619e-05, "loss": 3.6472, "step": 12465 }, { "epoch": 0.6707920792079208, "grad_norm": 1.9487024545669556, "learning_rate": 1.2224090002095976e-05, "loss": 3.828, "step": 12466 }, { "epoch": 0.6708458889367198, "grad_norm": 2.2685437202453613, "learning_rate": 1.2220457510770474e-05, "loss": 4.3683, "step": 12467 }, { "epoch": 0.6708996986655187, "grad_norm": 2.66029691696167, "learning_rate": 1.2216825384649928e-05, "loss": 3.7632, "step": 12468 }, { "epoch": 0.6709535083943177, "grad_norm": 1.9283483028411865, "learning_rate": 1.2213193623838127e-05, "loss": 4.5634, "step": 12469 }, { "epoch": 0.6710073181231166, "grad_norm": 2.3038885593414307, "learning_rate": 1.2209562228438859e-05, "loss": 3.7567, "step": 12470 }, { "epoch": 0.6710611278519156, "grad_norm": 1.618175983428955, "learning_rate": 1.2205931198555901e-05, "loss": 4.3628, "step": 12471 }, { "epoch": 0.6711149375807146, "grad_norm": 1.4542831182479858, "learning_rate": 1.2202300534293015e-05, "loss": 3.9931, "step": 12472 }, { "epoch": 0.6711687473095136, "grad_norm": 2.544055223464966, "learning_rate": 1.2198670235753962e-05, "loss": 4.0836, "step": 12473 }, { "epoch": 0.6712225570383126, "grad_norm": 2.4973304271698, "learning_rate": 1.2195040303042471e-05, "loss": 3.3895, "step": 12474 }, { "epoch": 0.6712763667671114, "grad_norm": 2.375450611114502, "learning_rate": 1.2191410736262295e-05, "loss": 3.6389, "step": 12475 }, { "epoch": 0.6713301764959104, "grad_norm": 2.097475051879883, "learning_rate": 1.2187781535517159e-05, "loss": 4.778, "step": 12476 }, { "epoch": 0.6713839862247094, "grad_norm": 2.659003257751465, "learning_rate": 1.2184152700910758e-05, "loss": 3.817, "step": 12477 }, { "epoch": 0.6714377959535084, "grad_norm": 2.9972383975982666, "learning_rate": 1.2180524232546802e-05, "loss": 3.8471, "step": 12478 }, { "epoch": 0.6714916056823074, "grad_norm": 2.2937068939208984, "learning_rate": 1.2176896130528972e-05, "loss": 4.0347, "step": 12479 }, { "epoch": 0.6715454154111064, "grad_norm": 1.8419479131698608, "learning_rate": 1.2173268394960974e-05, "loss": 3.9179, "step": 12480 }, { "epoch": 0.6715992251399053, "grad_norm": 3.8129727840423584, "learning_rate": 1.216964102594646e-05, "loss": 3.1124, "step": 12481 }, { "epoch": 0.6716530348687043, "grad_norm": 2.3004562854766846, "learning_rate": 1.21660140235891e-05, "loss": 3.8953, "step": 12482 }, { "epoch": 0.6717068445975032, "grad_norm": 1.3083035945892334, "learning_rate": 1.2162387387992539e-05, "loss": 4.4672, "step": 12483 }, { "epoch": 0.6717606543263022, "grad_norm": 2.9727046489715576, "learning_rate": 1.2158761119260414e-05, "loss": 4.1332, "step": 12484 }, { "epoch": 0.6718144640551011, "grad_norm": 1.7260338068008423, "learning_rate": 1.215513521749636e-05, "loss": 4.3303, "step": 12485 }, { "epoch": 0.6718682737839001, "grad_norm": 2.436095952987671, "learning_rate": 1.2151509682803994e-05, "loss": 4.3452, "step": 12486 }, { "epoch": 0.6719220835126991, "grad_norm": 2.4265940189361572, "learning_rate": 1.2147884515286922e-05, "loss": 4.2638, "step": 12487 }, { "epoch": 0.6719758932414981, "grad_norm": 1.1955108642578125, "learning_rate": 1.2144259715048742e-05, "loss": 4.4998, "step": 12488 }, { "epoch": 0.6720297029702971, "grad_norm": 2.8503503799438477, "learning_rate": 1.214063528219304e-05, "loss": 3.927, "step": 12489 }, { "epoch": 0.6720835126990959, "grad_norm": 2.3357841968536377, "learning_rate": 1.2137011216823388e-05, "loss": 3.5453, "step": 12490 }, { "epoch": 0.6721373224278949, "grad_norm": 2.519815683364868, "learning_rate": 1.2133387519043373e-05, "loss": 4.185, "step": 12491 }, { "epoch": 0.6721911321566939, "grad_norm": 2.236647367477417, "learning_rate": 1.212976418895653e-05, "loss": 4.1215, "step": 12492 }, { "epoch": 0.6722449418854929, "grad_norm": 2.0394272804260254, "learning_rate": 1.2126141226666407e-05, "loss": 3.4891, "step": 12493 }, { "epoch": 0.6722987516142919, "grad_norm": 1.6289883852005005, "learning_rate": 1.2122518632276541e-05, "loss": 4.273, "step": 12494 }, { "epoch": 0.6723525613430908, "grad_norm": 1.826629638671875, "learning_rate": 1.2118896405890447e-05, "loss": 4.0457, "step": 12495 }, { "epoch": 0.6724063710718898, "grad_norm": 2.6526060104370117, "learning_rate": 1.211527454761166e-05, "loss": 3.7427, "step": 12496 }, { "epoch": 0.6724601808006888, "grad_norm": 1.910940170288086, "learning_rate": 1.2111653057543667e-05, "loss": 4.155, "step": 12497 }, { "epoch": 0.6725139905294877, "grad_norm": 2.778979778289795, "learning_rate": 1.2108031935789965e-05, "loss": 3.5355, "step": 12498 }, { "epoch": 0.6725678002582867, "grad_norm": 1.1976128816604614, "learning_rate": 1.2104411182454037e-05, "loss": 4.3041, "step": 12499 }, { "epoch": 0.6726216099870856, "grad_norm": 3.800281047821045, "learning_rate": 1.210079079763935e-05, "loss": 4.0789, "step": 12500 }, { "epoch": 0.6726754197158846, "grad_norm": 2.4200081825256348, "learning_rate": 1.2097170781449368e-05, "loss": 3.6297, "step": 12501 }, { "epoch": 0.6727292294446836, "grad_norm": 3.119293689727783, "learning_rate": 1.209355113398754e-05, "loss": 3.6321, "step": 12502 }, { "epoch": 0.6727830391734826, "grad_norm": 3.6993355751037598, "learning_rate": 1.2089931855357307e-05, "loss": 3.6724, "step": 12503 }, { "epoch": 0.6728368489022816, "grad_norm": 1.6303901672363281, "learning_rate": 1.2086312945662095e-05, "loss": 3.6358, "step": 12504 }, { "epoch": 0.6728906586310806, "grad_norm": 2.728778123855591, "learning_rate": 1.2082694405005321e-05, "loss": 4.0023, "step": 12505 }, { "epoch": 0.6729444683598794, "grad_norm": 2.385286331176758, "learning_rate": 1.2079076233490402e-05, "loss": 4.0166, "step": 12506 }, { "epoch": 0.6729982780886784, "grad_norm": 2.6729800701141357, "learning_rate": 1.2075458431220743e-05, "loss": 4.1845, "step": 12507 }, { "epoch": 0.6730520878174774, "grad_norm": 3.4753494262695312, "learning_rate": 1.207184099829971e-05, "loss": 3.148, "step": 12508 }, { "epoch": 0.6731058975462764, "grad_norm": 2.426541566848755, "learning_rate": 1.2068223934830686e-05, "loss": 4.36, "step": 12509 }, { "epoch": 0.6731597072750753, "grad_norm": 2.8898496627807617, "learning_rate": 1.2064607240917033e-05, "loss": 3.2666, "step": 12510 }, { "epoch": 0.6732135170038743, "grad_norm": 2.660404682159424, "learning_rate": 1.2060990916662121e-05, "loss": 3.9473, "step": 12511 }, { "epoch": 0.6732673267326733, "grad_norm": 2.8123459815979004, "learning_rate": 1.2057374962169288e-05, "loss": 4.2191, "step": 12512 }, { "epoch": 0.6733211364614722, "grad_norm": 2.151576280593872, "learning_rate": 1.2053759377541866e-05, "loss": 4.1579, "step": 12513 }, { "epoch": 0.6733749461902712, "grad_norm": 1.9328933954238892, "learning_rate": 1.2050144162883188e-05, "loss": 4.6003, "step": 12514 }, { "epoch": 0.6734287559190701, "grad_norm": 2.867183208465576, "learning_rate": 1.204652931829654e-05, "loss": 4.0375, "step": 12515 }, { "epoch": 0.6734825656478691, "grad_norm": 2.7136387825012207, "learning_rate": 1.2042914843885254e-05, "loss": 4.7185, "step": 12516 }, { "epoch": 0.6735363753766681, "grad_norm": 2.7519357204437256, "learning_rate": 1.2039300739752613e-05, "loss": 3.0735, "step": 12517 }, { "epoch": 0.6735901851054671, "grad_norm": 4.577487945556641, "learning_rate": 1.2035687006001891e-05, "loss": 3.4504, "step": 12518 }, { "epoch": 0.6736439948342661, "grad_norm": 4.048870086669922, "learning_rate": 1.2032073642736368e-05, "loss": 3.3377, "step": 12519 }, { "epoch": 0.673697804563065, "grad_norm": 2.013158082962036, "learning_rate": 1.2028460650059304e-05, "loss": 3.4189, "step": 12520 }, { "epoch": 0.6737516142918639, "grad_norm": 3.7229621410369873, "learning_rate": 1.2024848028073931e-05, "loss": 2.44, "step": 12521 }, { "epoch": 0.6738054240206629, "grad_norm": 1.894272804260254, "learning_rate": 1.2021235776883524e-05, "loss": 3.906, "step": 12522 }, { "epoch": 0.6738592337494619, "grad_norm": 3.9112277030944824, "learning_rate": 1.201762389659128e-05, "loss": 3.5001, "step": 12523 }, { "epoch": 0.6739130434782609, "grad_norm": 2.9560420513153076, "learning_rate": 1.2014012387300425e-05, "loss": 4.063, "step": 12524 }, { "epoch": 0.6739668532070598, "grad_norm": 2.025334358215332, "learning_rate": 1.2010401249114167e-05, "loss": 4.2713, "step": 12525 }, { "epoch": 0.6740206629358588, "grad_norm": 3.2100250720977783, "learning_rate": 1.2006790482135696e-05, "loss": 4.2112, "step": 12526 }, { "epoch": 0.6740744726646578, "grad_norm": 2.090317487716675, "learning_rate": 1.2003180086468212e-05, "loss": 4.1749, "step": 12527 }, { "epoch": 0.6741282823934568, "grad_norm": 3.5523483753204346, "learning_rate": 1.1999570062214887e-05, "loss": 3.2156, "step": 12528 }, { "epoch": 0.6741820921222557, "grad_norm": 4.580742835998535, "learning_rate": 1.1995960409478882e-05, "loss": 3.698, "step": 12529 }, { "epoch": 0.6742359018510546, "grad_norm": 2.3890249729156494, "learning_rate": 1.1992351128363352e-05, "loss": 4.7763, "step": 12530 }, { "epoch": 0.6742897115798536, "grad_norm": 2.8211753368377686, "learning_rate": 1.1988742218971441e-05, "loss": 4.1541, "step": 12531 }, { "epoch": 0.6743435213086526, "grad_norm": 3.216249465942383, "learning_rate": 1.198513368140628e-05, "loss": 4.2117, "step": 12532 }, { "epoch": 0.6743973310374516, "grad_norm": 2.3109259605407715, "learning_rate": 1.1981525515770991e-05, "loss": 3.9152, "step": 12533 }, { "epoch": 0.6744511407662506, "grad_norm": 4.802571773529053, "learning_rate": 1.1977917722168689e-05, "loss": 3.7193, "step": 12534 }, { "epoch": 0.6745049504950495, "grad_norm": 1.6845155954360962, "learning_rate": 1.197431030070247e-05, "loss": 4.5558, "step": 12535 }, { "epoch": 0.6745587602238484, "grad_norm": 2.52166485786438, "learning_rate": 1.1970703251475424e-05, "loss": 3.534, "step": 12536 }, { "epoch": 0.6746125699526474, "grad_norm": 3.135852575302124, "learning_rate": 1.196709657459065e-05, "loss": 4.0412, "step": 12537 }, { "epoch": 0.6746663796814464, "grad_norm": 2.661236047744751, "learning_rate": 1.1963490270151193e-05, "loss": 3.8574, "step": 12538 }, { "epoch": 0.6747201894102454, "grad_norm": 4.21409797668457, "learning_rate": 1.1959884338260119e-05, "loss": 3.5389, "step": 12539 }, { "epoch": 0.6747739991390443, "grad_norm": 1.6575039625167847, "learning_rate": 1.1956278779020475e-05, "loss": 4.7112, "step": 12540 }, { "epoch": 0.6748278088678433, "grad_norm": 1.715539574623108, "learning_rate": 1.1952673592535294e-05, "loss": 4.6839, "step": 12541 }, { "epoch": 0.6748816185966423, "grad_norm": 2.55111026763916, "learning_rate": 1.1949068778907615e-05, "loss": 3.5848, "step": 12542 }, { "epoch": 0.6749354283254413, "grad_norm": 1.9105232954025269, "learning_rate": 1.194546433824045e-05, "loss": 4.3978, "step": 12543 }, { "epoch": 0.6749892380542402, "grad_norm": 2.6551434993743896, "learning_rate": 1.19418602706368e-05, "loss": 3.6185, "step": 12544 }, { "epoch": 0.6750430477830391, "grad_norm": 3.0781633853912354, "learning_rate": 1.1938256576199672e-05, "loss": 4.4553, "step": 12545 }, { "epoch": 0.6750968575118381, "grad_norm": 3.0467817783355713, "learning_rate": 1.193465325503202e-05, "loss": 3.2975, "step": 12546 }, { "epoch": 0.6751506672406371, "grad_norm": 1.6738542318344116, "learning_rate": 1.1931050307236844e-05, "loss": 4.245, "step": 12547 }, { "epoch": 0.6752044769694361, "grad_norm": 2.289665937423706, "learning_rate": 1.1927447732917101e-05, "loss": 3.8663, "step": 12548 }, { "epoch": 0.6752582866982351, "grad_norm": 1.051954984664917, "learning_rate": 1.192384553217574e-05, "loss": 4.2136, "step": 12549 }, { "epoch": 0.675312096427034, "grad_norm": 3.7541677951812744, "learning_rate": 1.1920243705115702e-05, "loss": 4.134, "step": 12550 }, { "epoch": 0.675365906155833, "grad_norm": 2.3149490356445312, "learning_rate": 1.191664225183992e-05, "loss": 4.1124, "step": 12551 }, { "epoch": 0.6754197158846319, "grad_norm": 3.805583953857422, "learning_rate": 1.1913041172451303e-05, "loss": 4.0941, "step": 12552 }, { "epoch": 0.6754735256134309, "grad_norm": 1.627967357635498, "learning_rate": 1.1909440467052787e-05, "loss": 4.6416, "step": 12553 }, { "epoch": 0.6755273353422299, "grad_norm": 2.9541287422180176, "learning_rate": 1.1905840135747243e-05, "loss": 3.3702, "step": 12554 }, { "epoch": 0.6755811450710288, "grad_norm": 1.4262492656707764, "learning_rate": 1.1902240178637568e-05, "loss": 4.9099, "step": 12555 }, { "epoch": 0.6756349547998278, "grad_norm": 2.8031160831451416, "learning_rate": 1.1898640595826644e-05, "loss": 4.1791, "step": 12556 }, { "epoch": 0.6756887645286268, "grad_norm": 2.0923519134521484, "learning_rate": 1.1895041387417321e-05, "loss": 3.8439, "step": 12557 }, { "epoch": 0.6757425742574258, "grad_norm": 2.0762526988983154, "learning_rate": 1.1891442553512478e-05, "loss": 4.0173, "step": 12558 }, { "epoch": 0.6757963839862247, "grad_norm": 2.8995113372802734, "learning_rate": 1.1887844094214948e-05, "loss": 3.8256, "step": 12559 }, { "epoch": 0.6758501937150236, "grad_norm": 2.3554694652557373, "learning_rate": 1.1884246009627576e-05, "loss": 3.9188, "step": 12560 }, { "epoch": 0.6759040034438226, "grad_norm": 1.6322221755981445, "learning_rate": 1.1880648299853156e-05, "loss": 4.6338, "step": 12561 }, { "epoch": 0.6759578131726216, "grad_norm": 2.4001052379608154, "learning_rate": 1.187705096499453e-05, "loss": 4.0854, "step": 12562 }, { "epoch": 0.6760116229014206, "grad_norm": 3.570540428161621, "learning_rate": 1.1873454005154492e-05, "loss": 3.7685, "step": 12563 }, { "epoch": 0.6760654326302196, "grad_norm": 3.1704859733581543, "learning_rate": 1.1869857420435832e-05, "loss": 4.0224, "step": 12564 }, { "epoch": 0.6761192423590185, "grad_norm": 1.9952143430709839, "learning_rate": 1.186626121094133e-05, "loss": 3.5452, "step": 12565 }, { "epoch": 0.6761730520878175, "grad_norm": 1.9566909074783325, "learning_rate": 1.1862665376773757e-05, "loss": 3.6865, "step": 12566 }, { "epoch": 0.6762268618166164, "grad_norm": 2.763836145401001, "learning_rate": 1.1859069918035865e-05, "loss": 3.5949, "step": 12567 }, { "epoch": 0.6762806715454154, "grad_norm": 1.1470750570297241, "learning_rate": 1.1855474834830427e-05, "loss": 4.3902, "step": 12568 }, { "epoch": 0.6763344812742144, "grad_norm": 2.2551183700561523, "learning_rate": 1.1851880127260154e-05, "loss": 4.4689, "step": 12569 }, { "epoch": 0.6763882910030133, "grad_norm": 2.77022123336792, "learning_rate": 1.1848285795427782e-05, "loss": 3.7782, "step": 12570 }, { "epoch": 0.6764421007318123, "grad_norm": 3.3833956718444824, "learning_rate": 1.1844691839436031e-05, "loss": 4.381, "step": 12571 }, { "epoch": 0.6764959104606113, "grad_norm": 2.832461357116699, "learning_rate": 1.1841098259387593e-05, "loss": 3.9991, "step": 12572 }, { "epoch": 0.6765497201894103, "grad_norm": 2.312607526779175, "learning_rate": 1.183750505538518e-05, "loss": 3.7984, "step": 12573 }, { "epoch": 0.6766035299182093, "grad_norm": 2.611367702484131, "learning_rate": 1.183391222753147e-05, "loss": 4.0999, "step": 12574 }, { "epoch": 0.6766573396470081, "grad_norm": 3.4041292667388916, "learning_rate": 1.1830319775929139e-05, "loss": 3.1753, "step": 12575 }, { "epoch": 0.6767111493758071, "grad_norm": 2.5746209621429443, "learning_rate": 1.1826727700680857e-05, "loss": 4.0565, "step": 12576 }, { "epoch": 0.6767649591046061, "grad_norm": 3.277296781539917, "learning_rate": 1.1823136001889243e-05, "loss": 4.82, "step": 12577 }, { "epoch": 0.6768187688334051, "grad_norm": 3.7760398387908936, "learning_rate": 1.1819544679656972e-05, "loss": 3.4223, "step": 12578 }, { "epoch": 0.6768725785622041, "grad_norm": 4.149322032928467, "learning_rate": 1.181595373408666e-05, "loss": 3.0686, "step": 12579 }, { "epoch": 0.676926388291003, "grad_norm": 3.11523175239563, "learning_rate": 1.1812363165280932e-05, "loss": 3.5027, "step": 12580 }, { "epoch": 0.676980198019802, "grad_norm": 3.388974189758301, "learning_rate": 1.1808772973342391e-05, "loss": 3.9019, "step": 12581 }, { "epoch": 0.6770340077486009, "grad_norm": 2.05704402923584, "learning_rate": 1.1805183158373642e-05, "loss": 3.5157, "step": 12582 }, { "epoch": 0.6770878174773999, "grad_norm": 1.4638127088546753, "learning_rate": 1.1801593720477267e-05, "loss": 4.4918, "step": 12583 }, { "epoch": 0.6771416272061989, "grad_norm": 3.1487512588500977, "learning_rate": 1.1798004659755844e-05, "loss": 3.2664, "step": 12584 }, { "epoch": 0.6771954369349978, "grad_norm": 1.9137837886810303, "learning_rate": 1.1794415976311936e-05, "loss": 4.025, "step": 12585 }, { "epoch": 0.6772492466637968, "grad_norm": 2.6389994621276855, "learning_rate": 1.1790827670248106e-05, "loss": 4.2904, "step": 12586 }, { "epoch": 0.6773030563925958, "grad_norm": 2.738276481628418, "learning_rate": 1.1787239741666878e-05, "loss": 3.8659, "step": 12587 }, { "epoch": 0.6773568661213948, "grad_norm": 2.643052101135254, "learning_rate": 1.1783652190670814e-05, "loss": 4.214, "step": 12588 }, { "epoch": 0.6774106758501938, "grad_norm": 1.193372130393982, "learning_rate": 1.1780065017362419e-05, "loss": 3.9494, "step": 12589 }, { "epoch": 0.6774644855789926, "grad_norm": 3.665172576904297, "learning_rate": 1.1776478221844208e-05, "loss": 3.7594, "step": 12590 }, { "epoch": 0.6775182953077916, "grad_norm": 2.662766695022583, "learning_rate": 1.1772891804218694e-05, "loss": 4.076, "step": 12591 }, { "epoch": 0.6775721050365906, "grad_norm": 2.9860358238220215, "learning_rate": 1.1769305764588337e-05, "loss": 3.9621, "step": 12592 }, { "epoch": 0.6776259147653896, "grad_norm": 2.48319411277771, "learning_rate": 1.1765720103055644e-05, "loss": 4.2795, "step": 12593 }, { "epoch": 0.6776797244941886, "grad_norm": 3.6313159465789795, "learning_rate": 1.1762134819723072e-05, "loss": 3.9348, "step": 12594 }, { "epoch": 0.6777335342229875, "grad_norm": 1.2670818567276, "learning_rate": 1.1758549914693084e-05, "loss": 4.0768, "step": 12595 }, { "epoch": 0.6777873439517865, "grad_norm": 2.743102550506592, "learning_rate": 1.1754965388068124e-05, "loss": 4.3005, "step": 12596 }, { "epoch": 0.6778411536805854, "grad_norm": 2.5941693782806396, "learning_rate": 1.1751381239950626e-05, "loss": 3.2093, "step": 12597 }, { "epoch": 0.6778949634093844, "grad_norm": 4.832396030426025, "learning_rate": 1.174779747044302e-05, "loss": 3.6599, "step": 12598 }, { "epoch": 0.6779487731381834, "grad_norm": 3.412937879562378, "learning_rate": 1.1744214079647716e-05, "loss": 4.0986, "step": 12599 }, { "epoch": 0.6780025828669823, "grad_norm": 3.0014705657958984, "learning_rate": 1.1740631067667121e-05, "loss": 3.9331, "step": 12600 }, { "epoch": 0.6780563925957813, "grad_norm": 4.431029319763184, "learning_rate": 1.1737048434603626e-05, "loss": 2.953, "step": 12601 }, { "epoch": 0.6781102023245803, "grad_norm": 3.5726583003997803, "learning_rate": 1.1733466180559614e-05, "loss": 2.9643, "step": 12602 }, { "epoch": 0.6781640120533793, "grad_norm": 2.962045907974243, "learning_rate": 1.1729884305637445e-05, "loss": 3.6981, "step": 12603 }, { "epoch": 0.6782178217821783, "grad_norm": 1.8917076587677002, "learning_rate": 1.1726302809939501e-05, "loss": 3.7573, "step": 12604 }, { "epoch": 0.6782716315109771, "grad_norm": 4.162419319152832, "learning_rate": 1.1722721693568122e-05, "loss": 3.3282, "step": 12605 }, { "epoch": 0.6783254412397761, "grad_norm": 3.3862271308898926, "learning_rate": 1.1719140956625652e-05, "loss": 3.4968, "step": 12606 }, { "epoch": 0.6783792509685751, "grad_norm": 2.366119623184204, "learning_rate": 1.1715560599214403e-05, "loss": 3.9332, "step": 12607 }, { "epoch": 0.6784330606973741, "grad_norm": 3.1535115242004395, "learning_rate": 1.1711980621436694e-05, "loss": 3.5396, "step": 12608 }, { "epoch": 0.6784868704261731, "grad_norm": 3.117797613143921, "learning_rate": 1.1708401023394847e-05, "loss": 4.4825, "step": 12609 }, { "epoch": 0.678540680154972, "grad_norm": 1.1525564193725586, "learning_rate": 1.1704821805191147e-05, "loss": 4.3445, "step": 12610 }, { "epoch": 0.678594489883771, "grad_norm": 2.3742151260375977, "learning_rate": 1.170124296692788e-05, "loss": 3.8519, "step": 12611 }, { "epoch": 0.67864829961257, "grad_norm": 2.5426084995269775, "learning_rate": 1.169766450870732e-05, "loss": 3.7157, "step": 12612 }, { "epoch": 0.6787021093413689, "grad_norm": 1.4921711683273315, "learning_rate": 1.1694086430631732e-05, "loss": 4.6008, "step": 12613 }, { "epoch": 0.6787559190701679, "grad_norm": 2.3676068782806396, "learning_rate": 1.1690508732803359e-05, "loss": 3.8799, "step": 12614 }, { "epoch": 0.6788097287989668, "grad_norm": 3.01947021484375, "learning_rate": 1.1686931415324453e-05, "loss": 3.6739, "step": 12615 }, { "epoch": 0.6788635385277658, "grad_norm": 2.208740711212158, "learning_rate": 1.168335447829724e-05, "loss": 3.9444, "step": 12616 }, { "epoch": 0.6789173482565648, "grad_norm": 1.9409574270248413, "learning_rate": 1.1679777921823934e-05, "loss": 3.758, "step": 12617 }, { "epoch": 0.6789711579853638, "grad_norm": 1.797238826751709, "learning_rate": 1.1676201746006743e-05, "loss": 4.1438, "step": 12618 }, { "epoch": 0.6790249677141628, "grad_norm": 2.651120901107788, "learning_rate": 1.1672625950947875e-05, "loss": 3.7358, "step": 12619 }, { "epoch": 0.6790787774429616, "grad_norm": 2.4076223373413086, "learning_rate": 1.1669050536749513e-05, "loss": 4.1096, "step": 12620 }, { "epoch": 0.6791325871717606, "grad_norm": 4.062073230743408, "learning_rate": 1.166547550351384e-05, "loss": 4.7102, "step": 12621 }, { "epoch": 0.6791863969005596, "grad_norm": 4.2549285888671875, "learning_rate": 1.1661900851342999e-05, "loss": 3.7808, "step": 12622 }, { "epoch": 0.6792402066293586, "grad_norm": 2.282393455505371, "learning_rate": 1.1658326580339151e-05, "loss": 4.3332, "step": 12623 }, { "epoch": 0.6792940163581576, "grad_norm": 3.15665340423584, "learning_rate": 1.1654752690604454e-05, "loss": 3.5884, "step": 12624 }, { "epoch": 0.6793478260869565, "grad_norm": 2.3390681743621826, "learning_rate": 1.1651179182241026e-05, "loss": 3.4661, "step": 12625 }, { "epoch": 0.6794016358157555, "grad_norm": 1.5919681787490845, "learning_rate": 1.1647606055350996e-05, "loss": 4.5259, "step": 12626 }, { "epoch": 0.6794554455445545, "grad_norm": 4.336354732513428, "learning_rate": 1.1644033310036472e-05, "loss": 3.3731, "step": 12627 }, { "epoch": 0.6795092552733534, "grad_norm": 3.615255832672119, "learning_rate": 1.164046094639955e-05, "loss": 3.149, "step": 12628 }, { "epoch": 0.6795630650021524, "grad_norm": 4.82649564743042, "learning_rate": 1.1636888964542325e-05, "loss": 3.6423, "step": 12629 }, { "epoch": 0.6796168747309513, "grad_norm": 3.6076276302337646, "learning_rate": 1.1633317364566867e-05, "loss": 4.1736, "step": 12630 }, { "epoch": 0.6796706844597503, "grad_norm": 4.214066028594971, "learning_rate": 1.1629746146575249e-05, "loss": 3.5248, "step": 12631 }, { "epoch": 0.6797244941885493, "grad_norm": 3.2939860820770264, "learning_rate": 1.1626175310669524e-05, "loss": 3.2364, "step": 12632 }, { "epoch": 0.6797783039173483, "grad_norm": 1.7911168336868286, "learning_rate": 1.1622604856951736e-05, "loss": 4.5116, "step": 12633 }, { "epoch": 0.6798321136461473, "grad_norm": 2.46622633934021, "learning_rate": 1.1619034785523913e-05, "loss": 3.957, "step": 12634 }, { "epoch": 0.6798859233749462, "grad_norm": 5.322498798370361, "learning_rate": 1.1615465096488093e-05, "loss": 3.4209, "step": 12635 }, { "epoch": 0.6799397331037451, "grad_norm": 2.6186578273773193, "learning_rate": 1.161189578994628e-05, "loss": 3.9436, "step": 12636 }, { "epoch": 0.6799935428325441, "grad_norm": 2.7276358604431152, "learning_rate": 1.1608326866000485e-05, "loss": 3.7143, "step": 12637 }, { "epoch": 0.6800473525613431, "grad_norm": 1.8997026681900024, "learning_rate": 1.1604758324752682e-05, "loss": 3.6614, "step": 12638 }, { "epoch": 0.6801011622901421, "grad_norm": 2.280879497528076, "learning_rate": 1.1601190166304846e-05, "loss": 4.0112, "step": 12639 }, { "epoch": 0.680154972018941, "grad_norm": 3.1435298919677734, "learning_rate": 1.1597622390758964e-05, "loss": 4.1669, "step": 12640 }, { "epoch": 0.68020878174774, "grad_norm": 2.8257956504821777, "learning_rate": 1.1594054998216989e-05, "loss": 3.5075, "step": 12641 }, { "epoch": 0.680262591476539, "grad_norm": 2.076916456222534, "learning_rate": 1.1590487988780863e-05, "loss": 4.0707, "step": 12642 }, { "epoch": 0.6803164012053379, "grad_norm": 2.857835292816162, "learning_rate": 1.1586921362552522e-05, "loss": 3.1233, "step": 12643 }, { "epoch": 0.6803702109341369, "grad_norm": 1.7373136281967163, "learning_rate": 1.1583355119633893e-05, "loss": 4.2965, "step": 12644 }, { "epoch": 0.6804240206629358, "grad_norm": 2.9442219734191895, "learning_rate": 1.1579789260126888e-05, "loss": 3.5641, "step": 12645 }, { "epoch": 0.6804778303917348, "grad_norm": 2.209763526916504, "learning_rate": 1.1576223784133408e-05, "loss": 4.2841, "step": 12646 }, { "epoch": 0.6805316401205338, "grad_norm": 3.0946760177612305, "learning_rate": 1.1572658691755347e-05, "loss": 3.9434, "step": 12647 }, { "epoch": 0.6805854498493328, "grad_norm": 2.0917465686798096, "learning_rate": 1.1569093983094587e-05, "loss": 3.76, "step": 12648 }, { "epoch": 0.6806392595781318, "grad_norm": 4.196552753448486, "learning_rate": 1.1565529658252989e-05, "loss": 4.5303, "step": 12649 }, { "epoch": 0.6806930693069307, "grad_norm": 2.0505943298339844, "learning_rate": 1.1561965717332423e-05, "loss": 3.9029, "step": 12650 }, { "epoch": 0.6807468790357296, "grad_norm": 2.084444522857666, "learning_rate": 1.1558402160434733e-05, "loss": 3.88, "step": 12651 }, { "epoch": 0.6808006887645286, "grad_norm": 1.987679123878479, "learning_rate": 1.155483898766177e-05, "loss": 3.7839, "step": 12652 }, { "epoch": 0.6808544984933276, "grad_norm": 4.762546539306641, "learning_rate": 1.1551276199115332e-05, "loss": 3.1899, "step": 12653 }, { "epoch": 0.6809083082221266, "grad_norm": 2.829465866088867, "learning_rate": 1.154771379489724e-05, "loss": 3.5393, "step": 12654 }, { "epoch": 0.6809621179509255, "grad_norm": 1.7467560768127441, "learning_rate": 1.1544151775109313e-05, "loss": 4.2238, "step": 12655 }, { "epoch": 0.6810159276797245, "grad_norm": 1.380997657775879, "learning_rate": 1.1540590139853336e-05, "loss": 4.3141, "step": 12656 }, { "epoch": 0.6810697374085235, "grad_norm": 2.199206829071045, "learning_rate": 1.1537028889231093e-05, "loss": 4.0765, "step": 12657 }, { "epoch": 0.6811235471373225, "grad_norm": 2.658555030822754, "learning_rate": 1.1533468023344351e-05, "loss": 3.9054, "step": 12658 }, { "epoch": 0.6811773568661214, "grad_norm": 2.1876044273376465, "learning_rate": 1.1529907542294874e-05, "loss": 4.3369, "step": 12659 }, { "epoch": 0.6812311665949203, "grad_norm": 3.008617639541626, "learning_rate": 1.152634744618441e-05, "loss": 3.3563, "step": 12660 }, { "epoch": 0.6812849763237193, "grad_norm": 1.4606800079345703, "learning_rate": 1.1522787735114696e-05, "loss": 4.0323, "step": 12661 }, { "epoch": 0.6813387860525183, "grad_norm": 2.103541851043701, "learning_rate": 1.1519228409187457e-05, "loss": 3.5021, "step": 12662 }, { "epoch": 0.6813925957813173, "grad_norm": 2.6860508918762207, "learning_rate": 1.1515669468504412e-05, "loss": 3.8572, "step": 12663 }, { "epoch": 0.6814464055101163, "grad_norm": 2.671982765197754, "learning_rate": 1.1512110913167266e-05, "loss": 3.6399, "step": 12664 }, { "epoch": 0.6815002152389152, "grad_norm": 1.4421520233154297, "learning_rate": 1.15085527432777e-05, "loss": 3.8932, "step": 12665 }, { "epoch": 0.6815540249677141, "grad_norm": 2.211249589920044, "learning_rate": 1.150499495893742e-05, "loss": 4.126, "step": 12666 }, { "epoch": 0.6816078346965131, "grad_norm": 2.789198398590088, "learning_rate": 1.1501437560248096e-05, "loss": 4.0051, "step": 12667 }, { "epoch": 0.6816616444253121, "grad_norm": 3.944115161895752, "learning_rate": 1.1497880547311371e-05, "loss": 2.7791, "step": 12668 }, { "epoch": 0.6817154541541111, "grad_norm": 3.4869868755340576, "learning_rate": 1.1494323920228902e-05, "loss": 3.5523, "step": 12669 }, { "epoch": 0.68176926388291, "grad_norm": 1.9413795471191406, "learning_rate": 1.1490767679102321e-05, "loss": 4.2248, "step": 12670 }, { "epoch": 0.681823073611709, "grad_norm": 1.1725126504898071, "learning_rate": 1.1487211824033273e-05, "loss": 4.226, "step": 12671 }, { "epoch": 0.681876883340508, "grad_norm": 1.3597326278686523, "learning_rate": 1.1483656355123367e-05, "loss": 4.4594, "step": 12672 }, { "epoch": 0.681930693069307, "grad_norm": 1.8371163606643677, "learning_rate": 1.1480101272474205e-05, "loss": 3.4811, "step": 12673 }, { "epoch": 0.6819845027981059, "grad_norm": 2.593229055404663, "learning_rate": 1.1476546576187388e-05, "loss": 3.2966, "step": 12674 }, { "epoch": 0.6820383125269048, "grad_norm": 3.138662576675415, "learning_rate": 1.1472992266364494e-05, "loss": 3.3069, "step": 12675 }, { "epoch": 0.6820921222557038, "grad_norm": 4.486226558685303, "learning_rate": 1.14694383431071e-05, "loss": 3.9587, "step": 12676 }, { "epoch": 0.6821459319845028, "grad_norm": 2.6981191635131836, "learning_rate": 1.146588480651676e-05, "loss": 3.6632, "step": 12677 }, { "epoch": 0.6821997417133018, "grad_norm": 2.041839599609375, "learning_rate": 1.1462331656695035e-05, "loss": 4.6356, "step": 12678 }, { "epoch": 0.6822535514421008, "grad_norm": 2.7579588890075684, "learning_rate": 1.1458778893743458e-05, "loss": 3.8359, "step": 12679 }, { "epoch": 0.6823073611708997, "grad_norm": 3.235034227371216, "learning_rate": 1.1455226517763549e-05, "loss": 3.5717, "step": 12680 }, { "epoch": 0.6823611708996986, "grad_norm": 3.0834059715270996, "learning_rate": 1.1451674528856843e-05, "loss": 3.7589, "step": 12681 }, { "epoch": 0.6824149806284976, "grad_norm": 1.8600313663482666, "learning_rate": 1.1448122927124849e-05, "loss": 4.3668, "step": 12682 }, { "epoch": 0.6824687903572966, "grad_norm": 2.3245480060577393, "learning_rate": 1.1444571712669039e-05, "loss": 4.365, "step": 12683 }, { "epoch": 0.6825226000860956, "grad_norm": 3.499452590942383, "learning_rate": 1.1441020885590914e-05, "loss": 3.7234, "step": 12684 }, { "epoch": 0.6825764098148945, "grad_norm": 1.9210617542266846, "learning_rate": 1.143747044599193e-05, "loss": 3.8218, "step": 12685 }, { "epoch": 0.6826302195436935, "grad_norm": 2.8309686183929443, "learning_rate": 1.1433920393973574e-05, "loss": 3.3262, "step": 12686 }, { "epoch": 0.6826840292724925, "grad_norm": 2.275707244873047, "learning_rate": 1.1430370729637282e-05, "loss": 4.6418, "step": 12687 }, { "epoch": 0.6827378390012915, "grad_norm": 1.9852032661437988, "learning_rate": 1.14268214530845e-05, "loss": 4.1574, "step": 12688 }, { "epoch": 0.6827916487300904, "grad_norm": 3.146827220916748, "learning_rate": 1.1423272564416648e-05, "loss": 3.5678, "step": 12689 }, { "epoch": 0.6828454584588893, "grad_norm": 2.5538339614868164, "learning_rate": 1.1419724063735154e-05, "loss": 3.0889, "step": 12690 }, { "epoch": 0.6828992681876883, "grad_norm": 4.15013313293457, "learning_rate": 1.1416175951141417e-05, "loss": 3.6948, "step": 12691 }, { "epoch": 0.6829530779164873, "grad_norm": 2.7216572761535645, "learning_rate": 1.1412628226736835e-05, "loss": 4.0085, "step": 12692 }, { "epoch": 0.6830068876452863, "grad_norm": 3.23750901222229, "learning_rate": 1.1409080890622795e-05, "loss": 3.0676, "step": 12693 }, { "epoch": 0.6830606973740853, "grad_norm": 2.840724229812622, "learning_rate": 1.1405533942900665e-05, "loss": 3.4482, "step": 12694 }, { "epoch": 0.6831145071028842, "grad_norm": 2.0794339179992676, "learning_rate": 1.1401987383671811e-05, "loss": 4.4816, "step": 12695 }, { "epoch": 0.6831683168316832, "grad_norm": 3.7218832969665527, "learning_rate": 1.1398441213037575e-05, "loss": 3.2336, "step": 12696 }, { "epoch": 0.6832221265604821, "grad_norm": 3.60707688331604, "learning_rate": 1.1394895431099314e-05, "loss": 3.0103, "step": 12697 }, { "epoch": 0.6832759362892811, "grad_norm": 3.1072440147399902, "learning_rate": 1.1391350037958356e-05, "loss": 4.0197, "step": 12698 }, { "epoch": 0.68332974601808, "grad_norm": 1.688431978225708, "learning_rate": 1.1387805033716004e-05, "loss": 3.3711, "step": 12699 }, { "epoch": 0.683383555746879, "grad_norm": 3.2544519901275635, "learning_rate": 1.1384260418473569e-05, "loss": 3.7988, "step": 12700 }, { "epoch": 0.683437365475678, "grad_norm": 2.410008668899536, "learning_rate": 1.138071619233234e-05, "loss": 3.6003, "step": 12701 }, { "epoch": 0.683491175204477, "grad_norm": 2.254572868347168, "learning_rate": 1.1377172355393622e-05, "loss": 4.03, "step": 12702 }, { "epoch": 0.683544984933276, "grad_norm": 2.4371492862701416, "learning_rate": 1.137362890775868e-05, "loss": 3.5311, "step": 12703 }, { "epoch": 0.6835987946620748, "grad_norm": 3.1741199493408203, "learning_rate": 1.1370085849528766e-05, "loss": 4.2103, "step": 12704 }, { "epoch": 0.6836526043908738, "grad_norm": 1.9022310972213745, "learning_rate": 1.1366543180805145e-05, "loss": 3.636, "step": 12705 }, { "epoch": 0.6837064141196728, "grad_norm": 2.095449924468994, "learning_rate": 1.1363000901689044e-05, "loss": 3.8702, "step": 12706 }, { "epoch": 0.6837602238484718, "grad_norm": 2.6423373222351074, "learning_rate": 1.1359459012281703e-05, "loss": 3.8495, "step": 12707 }, { "epoch": 0.6838140335772708, "grad_norm": 3.8523459434509277, "learning_rate": 1.1355917512684332e-05, "loss": 2.3637, "step": 12708 }, { "epoch": 0.6838678433060698, "grad_norm": 2.2278146743774414, "learning_rate": 1.1352376402998142e-05, "loss": 4.4768, "step": 12709 }, { "epoch": 0.6839216530348687, "grad_norm": 2.013423442840576, "learning_rate": 1.1348835683324324e-05, "loss": 4.2192, "step": 12710 }, { "epoch": 0.6839754627636677, "grad_norm": 1.335625410079956, "learning_rate": 1.1345295353764057e-05, "loss": 4.3448, "step": 12711 }, { "epoch": 0.6840292724924666, "grad_norm": 2.6148769855499268, "learning_rate": 1.134175541441853e-05, "loss": 4.3178, "step": 12712 }, { "epoch": 0.6840830822212656, "grad_norm": 2.0330581665039062, "learning_rate": 1.133821586538891e-05, "loss": 4.2394, "step": 12713 }, { "epoch": 0.6841368919500646, "grad_norm": 4.062112808227539, "learning_rate": 1.1334676706776324e-05, "loss": 3.6007, "step": 12714 }, { "epoch": 0.6841907016788635, "grad_norm": 1.9022243022918701, "learning_rate": 1.1331137938681919e-05, "loss": 4.7792, "step": 12715 }, { "epoch": 0.6842445114076625, "grad_norm": 2.7258188724517822, "learning_rate": 1.132759956120682e-05, "loss": 3.4967, "step": 12716 }, { "epoch": 0.6842983211364615, "grad_norm": 2.979179620742798, "learning_rate": 1.132406157445216e-05, "loss": 3.1555, "step": 12717 }, { "epoch": 0.6843521308652605, "grad_norm": 2.656055212020874, "learning_rate": 1.1320523978519034e-05, "loss": 3.7315, "step": 12718 }, { "epoch": 0.6844059405940595, "grad_norm": 2.1563706398010254, "learning_rate": 1.1316986773508545e-05, "loss": 4.2515, "step": 12719 }, { "epoch": 0.6844597503228583, "grad_norm": 3.0635573863983154, "learning_rate": 1.1313449959521765e-05, "loss": 3.7638, "step": 12720 }, { "epoch": 0.6845135600516573, "grad_norm": 3.995983362197876, "learning_rate": 1.1309913536659778e-05, "loss": 3.3342, "step": 12721 }, { "epoch": 0.6845673697804563, "grad_norm": 2.8152554035186768, "learning_rate": 1.1306377505023635e-05, "loss": 3.8302, "step": 12722 }, { "epoch": 0.6846211795092553, "grad_norm": 2.0140469074249268, "learning_rate": 1.1302841864714394e-05, "loss": 4.1309, "step": 12723 }, { "epoch": 0.6846749892380543, "grad_norm": 2.5392825603485107, "learning_rate": 1.1299306615833092e-05, "loss": 3.8914, "step": 12724 }, { "epoch": 0.6847287989668532, "grad_norm": 3.492994546890259, "learning_rate": 1.1295771758480755e-05, "loss": 3.9031, "step": 12725 }, { "epoch": 0.6847826086956522, "grad_norm": 2.411205291748047, "learning_rate": 1.1292237292758401e-05, "loss": 3.3897, "step": 12726 }, { "epoch": 0.6848364184244511, "grad_norm": 2.0289831161499023, "learning_rate": 1.1288703218767027e-05, "loss": 4.1466, "step": 12727 }, { "epoch": 0.6848902281532501, "grad_norm": 2.4011378288269043, "learning_rate": 1.1285169536607656e-05, "loss": 4.2954, "step": 12728 }, { "epoch": 0.684944037882049, "grad_norm": 2.0762205123901367, "learning_rate": 1.1281636246381238e-05, "loss": 3.9359, "step": 12729 }, { "epoch": 0.684997847610848, "grad_norm": 2.9228646755218506, "learning_rate": 1.1278103348188762e-05, "loss": 3.8173, "step": 12730 }, { "epoch": 0.685051657339647, "grad_norm": 2.1351332664489746, "learning_rate": 1.1274570842131183e-05, "loss": 3.8891, "step": 12731 }, { "epoch": 0.685105467068446, "grad_norm": 2.644791603088379, "learning_rate": 1.1271038728309443e-05, "loss": 4.7829, "step": 12732 }, { "epoch": 0.685159276797245, "grad_norm": 2.947695732116699, "learning_rate": 1.1267507006824498e-05, "loss": 3.5713, "step": 12733 }, { "epoch": 0.685213086526044, "grad_norm": 3.6414647102355957, "learning_rate": 1.126397567777727e-05, "loss": 3.7562, "step": 12734 }, { "epoch": 0.6852668962548428, "grad_norm": 1.1817048788070679, "learning_rate": 1.126044474126867e-05, "loss": 4.3253, "step": 12735 }, { "epoch": 0.6853207059836418, "grad_norm": 2.3589324951171875, "learning_rate": 1.12569141973996e-05, "loss": 3.8627, "step": 12736 }, { "epoch": 0.6853745157124408, "grad_norm": 1.5113532543182373, "learning_rate": 1.1253384046270963e-05, "loss": 4.4148, "step": 12737 }, { "epoch": 0.6854283254412398, "grad_norm": 4.035470962524414, "learning_rate": 1.1249854287983633e-05, "loss": 2.681, "step": 12738 }, { "epoch": 0.6854821351700388, "grad_norm": 1.6686344146728516, "learning_rate": 1.1246324922638485e-05, "loss": 4.3973, "step": 12739 }, { "epoch": 0.6855359448988377, "grad_norm": 1.6701607704162598, "learning_rate": 1.1242795950336377e-05, "loss": 3.5345, "step": 12740 }, { "epoch": 0.6855897546276367, "grad_norm": 2.8426406383514404, "learning_rate": 1.1239267371178161e-05, "loss": 3.8534, "step": 12741 }, { "epoch": 0.6856435643564357, "grad_norm": 2.0511438846588135, "learning_rate": 1.123573918526466e-05, "loss": 4.0008, "step": 12742 }, { "epoch": 0.6856973740852346, "grad_norm": 2.8666069507598877, "learning_rate": 1.123221139269672e-05, "loss": 4.211, "step": 12743 }, { "epoch": 0.6857511838140335, "grad_norm": 1.420729398727417, "learning_rate": 1.1228683993575156e-05, "loss": 4.4367, "step": 12744 }, { "epoch": 0.6858049935428325, "grad_norm": 3.1145339012145996, "learning_rate": 1.1225156988000756e-05, "loss": 3.9625, "step": 12745 }, { "epoch": 0.6858588032716315, "grad_norm": 1.3959828615188599, "learning_rate": 1.1221630376074319e-05, "loss": 4.1701, "step": 12746 }, { "epoch": 0.6859126130004305, "grad_norm": 1.2779220342636108, "learning_rate": 1.1218104157896617e-05, "loss": 4.4513, "step": 12747 }, { "epoch": 0.6859664227292295, "grad_norm": 2.4491078853607178, "learning_rate": 1.1214578333568438e-05, "loss": 3.8624, "step": 12748 }, { "epoch": 0.6860202324580285, "grad_norm": 4.818097114562988, "learning_rate": 1.121105290319053e-05, "loss": 3.4733, "step": 12749 }, { "epoch": 0.6860740421868273, "grad_norm": 3.7397704124450684, "learning_rate": 1.1207527866863647e-05, "loss": 3.8105, "step": 12750 }, { "epoch": 0.6861278519156263, "grad_norm": 2.442359685897827, "learning_rate": 1.1204003224688525e-05, "loss": 4.5556, "step": 12751 }, { "epoch": 0.6861816616444253, "grad_norm": 3.609215259552002, "learning_rate": 1.1200478976765866e-05, "loss": 4.2163, "step": 12752 }, { "epoch": 0.6862354713732243, "grad_norm": 2.812563180923462, "learning_rate": 1.1196955123196412e-05, "loss": 3.6275, "step": 12753 }, { "epoch": 0.6862892811020233, "grad_norm": 1.7789326906204224, "learning_rate": 1.1193431664080856e-05, "loss": 4.245, "step": 12754 }, { "epoch": 0.6863430908308222, "grad_norm": 1.8190516233444214, "learning_rate": 1.1189908599519886e-05, "loss": 4.1095, "step": 12755 }, { "epoch": 0.6863969005596212, "grad_norm": 1.1315253973007202, "learning_rate": 1.1186385929614181e-05, "loss": 4.1684, "step": 12756 }, { "epoch": 0.6864507102884202, "grad_norm": 2.072253942489624, "learning_rate": 1.1182863654464414e-05, "loss": 3.9723, "step": 12757 }, { "epoch": 0.6865045200172191, "grad_norm": 2.175384283065796, "learning_rate": 1.1179341774171234e-05, "loss": 3.6451, "step": 12758 }, { "epoch": 0.686558329746018, "grad_norm": 2.637230157852173, "learning_rate": 1.117582028883531e-05, "loss": 4.5582, "step": 12759 }, { "epoch": 0.686612139474817, "grad_norm": 3.0176095962524414, "learning_rate": 1.1172299198557246e-05, "loss": 4.4425, "step": 12760 }, { "epoch": 0.686665949203616, "grad_norm": 2.3149948120117188, "learning_rate": 1.1168778503437682e-05, "loss": 3.7972, "step": 12761 }, { "epoch": 0.686719758932415, "grad_norm": 4.25671911239624, "learning_rate": 1.1165258203577228e-05, "loss": 2.5288, "step": 12762 }, { "epoch": 0.686773568661214, "grad_norm": 1.9702640771865845, "learning_rate": 1.116173829907647e-05, "loss": 4.2219, "step": 12763 }, { "epoch": 0.686827378390013, "grad_norm": 3.523716449737549, "learning_rate": 1.1158218790036024e-05, "loss": 2.6208, "step": 12764 }, { "epoch": 0.6868811881188119, "grad_norm": 2.588747262954712, "learning_rate": 1.1154699676556454e-05, "loss": 3.8769, "step": 12765 }, { "epoch": 0.6869349978476108, "grad_norm": 3.397952079772949, "learning_rate": 1.1151180958738327e-05, "loss": 3.3347, "step": 12766 }, { "epoch": 0.6869888075764098, "grad_norm": 2.270310401916504, "learning_rate": 1.1147662636682199e-05, "loss": 4.253, "step": 12767 }, { "epoch": 0.6870426173052088, "grad_norm": 2.2625832557678223, "learning_rate": 1.1144144710488616e-05, "loss": 4.354, "step": 12768 }, { "epoch": 0.6870964270340078, "grad_norm": 1.7639633417129517, "learning_rate": 1.1140627180258108e-05, "loss": 4.5538, "step": 12769 }, { "epoch": 0.6871502367628067, "grad_norm": 1.6719350814819336, "learning_rate": 1.1137110046091197e-05, "loss": 4.0614, "step": 12770 }, { "epoch": 0.6872040464916057, "grad_norm": 4.279195308685303, "learning_rate": 1.1133593308088398e-05, "loss": 3.2334, "step": 12771 }, { "epoch": 0.6872578562204047, "grad_norm": 3.019543170928955, "learning_rate": 1.1130076966350202e-05, "loss": 3.5081, "step": 12772 }, { "epoch": 0.6873116659492036, "grad_norm": 2.433443546295166, "learning_rate": 1.1126561020977094e-05, "loss": 3.3892, "step": 12773 }, { "epoch": 0.6873654756780025, "grad_norm": 3.5090818405151367, "learning_rate": 1.1123045472069574e-05, "loss": 3.1388, "step": 12774 }, { "epoch": 0.6874192854068015, "grad_norm": 4.013245582580566, "learning_rate": 1.1119530319728081e-05, "loss": 3.1082, "step": 12775 }, { "epoch": 0.6874730951356005, "grad_norm": 2.460435152053833, "learning_rate": 1.1116015564053076e-05, "loss": 3.9052, "step": 12776 }, { "epoch": 0.6875269048643995, "grad_norm": 2.1485936641693115, "learning_rate": 1.1112501205145004e-05, "loss": 3.7815, "step": 12777 }, { "epoch": 0.6875807145931985, "grad_norm": 2.7188313007354736, "learning_rate": 1.1108987243104284e-05, "loss": 3.7043, "step": 12778 }, { "epoch": 0.6876345243219975, "grad_norm": 2.1415982246398926, "learning_rate": 1.1105473678031355e-05, "loss": 3.8516, "step": 12779 }, { "epoch": 0.6876883340507964, "grad_norm": 2.4796416759490967, "learning_rate": 1.1101960510026619e-05, "loss": 3.607, "step": 12780 }, { "epoch": 0.6877421437795953, "grad_norm": 2.2089056968688965, "learning_rate": 1.1098447739190468e-05, "loss": 3.8656, "step": 12781 }, { "epoch": 0.6877959535083943, "grad_norm": 2.302347421646118, "learning_rate": 1.1094935365623302e-05, "loss": 4.3027, "step": 12782 }, { "epoch": 0.6878497632371933, "grad_norm": 2.609344005584717, "learning_rate": 1.1091423389425462e-05, "loss": 4.0774, "step": 12783 }, { "epoch": 0.6879035729659922, "grad_norm": 3.725802421569824, "learning_rate": 1.108791181069734e-05, "loss": 2.8699, "step": 12784 }, { "epoch": 0.6879573826947912, "grad_norm": 1.5217275619506836, "learning_rate": 1.1084400629539283e-05, "loss": 4.2846, "step": 12785 }, { "epoch": 0.6880111924235902, "grad_norm": 2.85223126411438, "learning_rate": 1.1080889846051627e-05, "loss": 3.4881, "step": 12786 }, { "epoch": 0.6880650021523892, "grad_norm": 2.6674880981445312, "learning_rate": 1.1077379460334696e-05, "loss": 3.0667, "step": 12787 }, { "epoch": 0.6881188118811881, "grad_norm": 3.4293389320373535, "learning_rate": 1.1073869472488818e-05, "loss": 4.1576, "step": 12788 }, { "epoch": 0.688172621609987, "grad_norm": 2.559248924255371, "learning_rate": 1.1070359882614292e-05, "loss": 4.1197, "step": 12789 }, { "epoch": 0.688226431338786, "grad_norm": 2.3505332469940186, "learning_rate": 1.1066850690811414e-05, "loss": 4.1681, "step": 12790 }, { "epoch": 0.688280241067585, "grad_norm": 2.7597031593322754, "learning_rate": 1.1063341897180467e-05, "loss": 4.2918, "step": 12791 }, { "epoch": 0.688334050796384, "grad_norm": 2.185884475708008, "learning_rate": 1.1059833501821723e-05, "loss": 4.1381, "step": 12792 }, { "epoch": 0.688387860525183, "grad_norm": 2.2816295623779297, "learning_rate": 1.1056325504835436e-05, "loss": 3.6726, "step": 12793 }, { "epoch": 0.688441670253982, "grad_norm": 3.010464906692505, "learning_rate": 1.1052817906321869e-05, "loss": 3.3184, "step": 12794 }, { "epoch": 0.6884954799827809, "grad_norm": 3.5707967281341553, "learning_rate": 1.1049310706381255e-05, "loss": 3.9854, "step": 12795 }, { "epoch": 0.6885492897115798, "grad_norm": 2.5575337409973145, "learning_rate": 1.1045803905113817e-05, "loss": 4.1303, "step": 12796 }, { "epoch": 0.6886030994403788, "grad_norm": 3.6568920612335205, "learning_rate": 1.1042297502619777e-05, "loss": 2.8735, "step": 12797 }, { "epoch": 0.6886569091691778, "grad_norm": 3.499197483062744, "learning_rate": 1.1038791498999317e-05, "loss": 2.9119, "step": 12798 }, { "epoch": 0.6887107188979767, "grad_norm": 4.121502876281738, "learning_rate": 1.1035285894352654e-05, "loss": 3.5604, "step": 12799 }, { "epoch": 0.6887645286267757, "grad_norm": 2.3367385864257812, "learning_rate": 1.1031780688779961e-05, "loss": 3.435, "step": 12800 }, { "epoch": 0.6888183383555747, "grad_norm": 1.795222520828247, "learning_rate": 1.1028275882381403e-05, "loss": 4.3223, "step": 12801 }, { "epoch": 0.6888721480843737, "grad_norm": 2.1238574981689453, "learning_rate": 1.1024771475257143e-05, "loss": 3.7807, "step": 12802 }, { "epoch": 0.6889259578131727, "grad_norm": 3.3590688705444336, "learning_rate": 1.1021267467507323e-05, "loss": 3.8467, "step": 12803 }, { "epoch": 0.6889797675419715, "grad_norm": 2.224652051925659, "learning_rate": 1.1017763859232072e-05, "loss": 3.6008, "step": 12804 }, { "epoch": 0.6890335772707705, "grad_norm": 2.4890520572662354, "learning_rate": 1.101426065053154e-05, "loss": 3.8392, "step": 12805 }, { "epoch": 0.6890873869995695, "grad_norm": 3.2298521995544434, "learning_rate": 1.1010757841505814e-05, "loss": 3.8734, "step": 12806 }, { "epoch": 0.6891411967283685, "grad_norm": 1.3773452043533325, "learning_rate": 1.1007255432255002e-05, "loss": 4.6118, "step": 12807 }, { "epoch": 0.6891950064571675, "grad_norm": 3.6770408153533936, "learning_rate": 1.1003753422879192e-05, "loss": 3.3196, "step": 12808 }, { "epoch": 0.6892488161859665, "grad_norm": 2.7393958568573, "learning_rate": 1.1000251813478457e-05, "loss": 3.3425, "step": 12809 }, { "epoch": 0.6893026259147654, "grad_norm": 4.087616920471191, "learning_rate": 1.0996750604152878e-05, "loss": 3.0456, "step": 12810 }, { "epoch": 0.6893564356435643, "grad_norm": 2.849494457244873, "learning_rate": 1.0993249795002503e-05, "loss": 4.2051, "step": 12811 }, { "epoch": 0.6894102453723633, "grad_norm": 3.6244616508483887, "learning_rate": 1.0989749386127382e-05, "loss": 4.3017, "step": 12812 }, { "epoch": 0.6894640551011623, "grad_norm": 2.3579020500183105, "learning_rate": 1.0986249377627533e-05, "loss": 3.4787, "step": 12813 }, { "epoch": 0.6895178648299612, "grad_norm": 2.3526523113250732, "learning_rate": 1.0982749769602977e-05, "loss": 3.6341, "step": 12814 }, { "epoch": 0.6895716745587602, "grad_norm": 2.7285895347595215, "learning_rate": 1.0979250562153737e-05, "loss": 4.2609, "step": 12815 }, { "epoch": 0.6896254842875592, "grad_norm": 3.3992226123809814, "learning_rate": 1.0975751755379803e-05, "loss": 4.009, "step": 12816 }, { "epoch": 0.6896792940163582, "grad_norm": 2.864267349243164, "learning_rate": 1.0972253349381168e-05, "loss": 4.0424, "step": 12817 }, { "epoch": 0.6897331037451572, "grad_norm": 2.423112154006958, "learning_rate": 1.0968755344257798e-05, "loss": 4.0831, "step": 12818 }, { "epoch": 0.689786913473956, "grad_norm": 3.059227466583252, "learning_rate": 1.0965257740109663e-05, "loss": 3.9131, "step": 12819 }, { "epoch": 0.689840723202755, "grad_norm": 2.4358575344085693, "learning_rate": 1.0961760537036711e-05, "loss": 4.7049, "step": 12820 }, { "epoch": 0.689894532931554, "grad_norm": 3.4288809299468994, "learning_rate": 1.0958263735138885e-05, "loss": 3.5247, "step": 12821 }, { "epoch": 0.689948342660353, "grad_norm": 1.99238121509552, "learning_rate": 1.0954767334516113e-05, "loss": 3.6973, "step": 12822 }, { "epoch": 0.690002152389152, "grad_norm": 1.8371944427490234, "learning_rate": 1.0951271335268314e-05, "loss": 4.1994, "step": 12823 }, { "epoch": 0.690055962117951, "grad_norm": 2.9038076400756836, "learning_rate": 1.0947775737495386e-05, "loss": 4.1226, "step": 12824 }, { "epoch": 0.6901097718467499, "grad_norm": 3.6534359455108643, "learning_rate": 1.0944280541297238e-05, "loss": 4.2506, "step": 12825 }, { "epoch": 0.6901635815755489, "grad_norm": 2.633740186691284, "learning_rate": 1.094078574677375e-05, "loss": 3.4261, "step": 12826 }, { "epoch": 0.6902173913043478, "grad_norm": 2.6038243770599365, "learning_rate": 1.0937291354024786e-05, "loss": 4.1976, "step": 12827 }, { "epoch": 0.6902712010331468, "grad_norm": 2.4174182415008545, "learning_rate": 1.0933797363150225e-05, "loss": 3.7086, "step": 12828 }, { "epoch": 0.6903250107619457, "grad_norm": 2.8560891151428223, "learning_rate": 1.093030377424988e-05, "loss": 3.823, "step": 12829 }, { "epoch": 0.6903788204907447, "grad_norm": 3.365135669708252, "learning_rate": 1.092681058742362e-05, "loss": 3.5818, "step": 12830 }, { "epoch": 0.6904326302195437, "grad_norm": 2.191696882247925, "learning_rate": 1.092331780277126e-05, "loss": 3.3707, "step": 12831 }, { "epoch": 0.6904864399483427, "grad_norm": 3.236494541168213, "learning_rate": 1.0919825420392618e-05, "loss": 3.6761, "step": 12832 }, { "epoch": 0.6905402496771417, "grad_norm": 3.2713372707366943, "learning_rate": 1.091633344038749e-05, "loss": 3.9117, "step": 12833 }, { "epoch": 0.6905940594059405, "grad_norm": 2.8420662879943848, "learning_rate": 1.0912841862855677e-05, "loss": 3.7709, "step": 12834 }, { "epoch": 0.6906478691347395, "grad_norm": 1.8203001022338867, "learning_rate": 1.090935068789695e-05, "loss": 4.1243, "step": 12835 }, { "epoch": 0.6907016788635385, "grad_norm": 3.095454216003418, "learning_rate": 1.090585991561108e-05, "loss": 3.3567, "step": 12836 }, { "epoch": 0.6907554885923375, "grad_norm": 2.9511702060699463, "learning_rate": 1.090236954609783e-05, "loss": 3.9138, "step": 12837 }, { "epoch": 0.6908092983211365, "grad_norm": 2.313356399536133, "learning_rate": 1.0898879579456936e-05, "loss": 4.0291, "step": 12838 }, { "epoch": 0.6908631080499354, "grad_norm": 1.8720074892044067, "learning_rate": 1.0895390015788137e-05, "loss": 3.3253, "step": 12839 }, { "epoch": 0.6909169177787344, "grad_norm": 3.330076217651367, "learning_rate": 1.0891900855191145e-05, "loss": 4.1311, "step": 12840 }, { "epoch": 0.6909707275075334, "grad_norm": 1.3242921829223633, "learning_rate": 1.0888412097765688e-05, "loss": 3.753, "step": 12841 }, { "epoch": 0.6910245372363323, "grad_norm": 3.1745381355285645, "learning_rate": 1.088492374361146e-05, "loss": 2.9689, "step": 12842 }, { "epoch": 0.6910783469651313, "grad_norm": 2.124070405960083, "learning_rate": 1.0881435792828154e-05, "loss": 3.0935, "step": 12843 }, { "epoch": 0.6911321566939302, "grad_norm": 3.043487787246704, "learning_rate": 1.087794824551543e-05, "loss": 4.1345, "step": 12844 }, { "epoch": 0.6911859664227292, "grad_norm": 1.427167534828186, "learning_rate": 1.087446110177295e-05, "loss": 3.6688, "step": 12845 }, { "epoch": 0.6912397761515282, "grad_norm": 2.5657238960266113, "learning_rate": 1.0870974361700392e-05, "loss": 4.0733, "step": 12846 }, { "epoch": 0.6912935858803272, "grad_norm": 2.9303455352783203, "learning_rate": 1.0867488025397383e-05, "loss": 3.4465, "step": 12847 }, { "epoch": 0.6913473956091262, "grad_norm": 1.7881921529769897, "learning_rate": 1.0864002092963552e-05, "loss": 4.2552, "step": 12848 }, { "epoch": 0.6914012053379252, "grad_norm": 2.5957858562469482, "learning_rate": 1.0860516564498522e-05, "loss": 2.6496, "step": 12849 }, { "epoch": 0.691455015066724, "grad_norm": 1.6080056428909302, "learning_rate": 1.0857031440101895e-05, "loss": 4.2203, "step": 12850 }, { "epoch": 0.691508824795523, "grad_norm": 2.5887341499328613, "learning_rate": 1.0853546719873272e-05, "loss": 3.9422, "step": 12851 }, { "epoch": 0.691562634524322, "grad_norm": 2.688396692276001, "learning_rate": 1.0850062403912234e-05, "loss": 4.0527, "step": 12852 }, { "epoch": 0.691616444253121, "grad_norm": 2.476104497909546, "learning_rate": 1.0846578492318351e-05, "loss": 3.7296, "step": 12853 }, { "epoch": 0.69167025398192, "grad_norm": 1.520220398902893, "learning_rate": 1.0843094985191188e-05, "loss": 4.1896, "step": 12854 }, { "epoch": 0.6917240637107189, "grad_norm": 1.443255066871643, "learning_rate": 1.0839611882630285e-05, "loss": 4.0092, "step": 12855 }, { "epoch": 0.6917778734395179, "grad_norm": 2.672781229019165, "learning_rate": 1.0836129184735194e-05, "loss": 4.0768, "step": 12856 }, { "epoch": 0.6918316831683168, "grad_norm": 3.0427796840667725, "learning_rate": 1.0832646891605438e-05, "loss": 3.6728, "step": 12857 }, { "epoch": 0.6918854928971158, "grad_norm": 3.887106418609619, "learning_rate": 1.0829165003340536e-05, "loss": 2.2767, "step": 12858 }, { "epoch": 0.6919393026259147, "grad_norm": 1.9960726499557495, "learning_rate": 1.0825683520039973e-05, "loss": 3.9084, "step": 12859 }, { "epoch": 0.6919931123547137, "grad_norm": 2.465474843978882, "learning_rate": 1.0822202441803242e-05, "loss": 3.9012, "step": 12860 }, { "epoch": 0.6920469220835127, "grad_norm": 3.303598403930664, "learning_rate": 1.081872176872984e-05, "loss": 3.3312, "step": 12861 }, { "epoch": 0.6921007318123117, "grad_norm": 2.549734592437744, "learning_rate": 1.0815241500919227e-05, "loss": 4.4926, "step": 12862 }, { "epoch": 0.6921545415411107, "grad_norm": 2.3612356185913086, "learning_rate": 1.0811761638470858e-05, "loss": 3.9474, "step": 12863 }, { "epoch": 0.6922083512699096, "grad_norm": 3.232661247253418, "learning_rate": 1.080828218148418e-05, "loss": 4.0221, "step": 12864 }, { "epoch": 0.6922621609987085, "grad_norm": 2.5001845359802246, "learning_rate": 1.0804803130058628e-05, "loss": 3.5445, "step": 12865 }, { "epoch": 0.6923159707275075, "grad_norm": 2.4003195762634277, "learning_rate": 1.080132448429362e-05, "loss": 4.0537, "step": 12866 }, { "epoch": 0.6923697804563065, "grad_norm": 3.3612003326416016, "learning_rate": 1.079784624428857e-05, "loss": 3.7203, "step": 12867 }, { "epoch": 0.6924235901851055, "grad_norm": 3.3755691051483154, "learning_rate": 1.0794368410142874e-05, "loss": 3.6227, "step": 12868 }, { "epoch": 0.6924773999139044, "grad_norm": 2.3044469356536865, "learning_rate": 1.079089098195592e-05, "loss": 3.7728, "step": 12869 }, { "epoch": 0.6925312096427034, "grad_norm": 1.6856170892715454, "learning_rate": 1.0787413959827087e-05, "loss": 3.8603, "step": 12870 }, { "epoch": 0.6925850193715024, "grad_norm": 1.8420695066452026, "learning_rate": 1.0783937343855722e-05, "loss": 4.0149, "step": 12871 }, { "epoch": 0.6926388291003014, "grad_norm": 3.8714301586151123, "learning_rate": 1.07804611341412e-05, "loss": 3.8137, "step": 12872 }, { "epoch": 0.6926926388291003, "grad_norm": 3.1764888763427734, "learning_rate": 1.0776985330782857e-05, "loss": 3.464, "step": 12873 }, { "epoch": 0.6927464485578992, "grad_norm": 3.0006351470947266, "learning_rate": 1.0773509933880024e-05, "loss": 4.1487, "step": 12874 }, { "epoch": 0.6928002582866982, "grad_norm": 1.334808349609375, "learning_rate": 1.0770034943532004e-05, "loss": 4.4989, "step": 12875 }, { "epoch": 0.6928540680154972, "grad_norm": 1.9235111474990845, "learning_rate": 1.0766560359838102e-05, "loss": 4.2736, "step": 12876 }, { "epoch": 0.6929078777442962, "grad_norm": 2.8925838470458984, "learning_rate": 1.0763086182897631e-05, "loss": 3.9484, "step": 12877 }, { "epoch": 0.6929616874730952, "grad_norm": 1.7642271518707275, "learning_rate": 1.0759612412809861e-05, "loss": 4.3419, "step": 12878 }, { "epoch": 0.6930154972018941, "grad_norm": 1.9285204410552979, "learning_rate": 1.075613904967407e-05, "loss": 4.019, "step": 12879 }, { "epoch": 0.693069306930693, "grad_norm": 1.323193907737732, "learning_rate": 1.075266609358951e-05, "loss": 4.1809, "step": 12880 }, { "epoch": 0.693123116659492, "grad_norm": 1.7918636798858643, "learning_rate": 1.0749193544655434e-05, "loss": 4.2231, "step": 12881 }, { "epoch": 0.693176926388291, "grad_norm": 2.226912021636963, "learning_rate": 1.0745721402971076e-05, "loss": 4.1349, "step": 12882 }, { "epoch": 0.69323073611709, "grad_norm": 2.4005250930786133, "learning_rate": 1.0742249668635661e-05, "loss": 4.0561, "step": 12883 }, { "epoch": 0.6932845458458889, "grad_norm": 2.225308656692505, "learning_rate": 1.0738778341748403e-05, "loss": 4.4468, "step": 12884 }, { "epoch": 0.6933383555746879, "grad_norm": 3.4176108837127686, "learning_rate": 1.0735307422408503e-05, "loss": 2.5904, "step": 12885 }, { "epoch": 0.6933921653034869, "grad_norm": 2.1189944744110107, "learning_rate": 1.0731836910715137e-05, "loss": 3.9405, "step": 12886 }, { "epoch": 0.6934459750322859, "grad_norm": 3.2612690925598145, "learning_rate": 1.0728366806767504e-05, "loss": 4.2211, "step": 12887 }, { "epoch": 0.6934997847610848, "grad_norm": 3.0777628421783447, "learning_rate": 1.0724897110664764e-05, "loss": 3.6009, "step": 12888 }, { "epoch": 0.6935535944898837, "grad_norm": 3.5539186000823975, "learning_rate": 1.0721427822506077e-05, "loss": 4.1385, "step": 12889 }, { "epoch": 0.6936074042186827, "grad_norm": 2.8322579860687256, "learning_rate": 1.0717958942390568e-05, "loss": 3.9205, "step": 12890 }, { "epoch": 0.6936612139474817, "grad_norm": 2.397402286529541, "learning_rate": 1.071449047041737e-05, "loss": 3.9663, "step": 12891 }, { "epoch": 0.6937150236762807, "grad_norm": 1.9261443614959717, "learning_rate": 1.071102240668562e-05, "loss": 3.4268, "step": 12892 }, { "epoch": 0.6937688334050797, "grad_norm": 2.561509370803833, "learning_rate": 1.0707554751294416e-05, "loss": 3.8358, "step": 12893 }, { "epoch": 0.6938226431338786, "grad_norm": 2.6900219917297363, "learning_rate": 1.0704087504342859e-05, "loss": 3.9538, "step": 12894 }, { "epoch": 0.6938764528626775, "grad_norm": 2.59297513961792, "learning_rate": 1.0700620665930026e-05, "loss": 3.9464, "step": 12895 }, { "epoch": 0.6939302625914765, "grad_norm": 3.123823881149292, "learning_rate": 1.069715423615499e-05, "loss": 3.6266, "step": 12896 }, { "epoch": 0.6939840723202755, "grad_norm": 2.7799017429351807, "learning_rate": 1.069368821511682e-05, "loss": 2.8879, "step": 12897 }, { "epoch": 0.6940378820490745, "grad_norm": 1.3955234289169312, "learning_rate": 1.0690222602914562e-05, "loss": 4.4387, "step": 12898 }, { "epoch": 0.6940916917778734, "grad_norm": 1.5967175960540771, "learning_rate": 1.0686757399647254e-05, "loss": 4.1124, "step": 12899 }, { "epoch": 0.6941455015066724, "grad_norm": 2.3477065563201904, "learning_rate": 1.0683292605413919e-05, "loss": 3.6859, "step": 12900 }, { "epoch": 0.6941993112354714, "grad_norm": 2.6115100383758545, "learning_rate": 1.0679828220313575e-05, "loss": 4.198, "step": 12901 }, { "epoch": 0.6942531209642704, "grad_norm": 1.819053292274475, "learning_rate": 1.0676364244445214e-05, "loss": 4.6239, "step": 12902 }, { "epoch": 0.6943069306930693, "grad_norm": 2.9675912857055664, "learning_rate": 1.0672900677907846e-05, "loss": 4.1177, "step": 12903 }, { "epoch": 0.6943607404218682, "grad_norm": 4.5844621658325195, "learning_rate": 1.0669437520800452e-05, "loss": 3.6466, "step": 12904 }, { "epoch": 0.6944145501506672, "grad_norm": 2.599259853363037, "learning_rate": 1.0665974773221976e-05, "loss": 3.7765, "step": 12905 }, { "epoch": 0.6944683598794662, "grad_norm": 3.102797508239746, "learning_rate": 1.0662512435271391e-05, "loss": 4.053, "step": 12906 }, { "epoch": 0.6945221696082652, "grad_norm": 3.5505735874176025, "learning_rate": 1.0659050507047626e-05, "loss": 3.4253, "step": 12907 }, { "epoch": 0.6945759793370642, "grad_norm": 3.7200303077697754, "learning_rate": 1.0655588988649635e-05, "loss": 3.8119, "step": 12908 }, { "epoch": 0.6946297890658631, "grad_norm": 1.9121986627578735, "learning_rate": 1.0652127880176326e-05, "loss": 4.0519, "step": 12909 }, { "epoch": 0.6946835987946621, "grad_norm": 1.9647146463394165, "learning_rate": 1.0648667181726616e-05, "loss": 4.2657, "step": 12910 }, { "epoch": 0.694737408523461, "grad_norm": 4.789642810821533, "learning_rate": 1.0645206893399396e-05, "loss": 4.0017, "step": 12911 }, { "epoch": 0.69479121825226, "grad_norm": 3.0917294025421143, "learning_rate": 1.064174701529355e-05, "loss": 3.967, "step": 12912 }, { "epoch": 0.694845027981059, "grad_norm": 2.7413034439086914, "learning_rate": 1.0638287547507957e-05, "loss": 4.134, "step": 12913 }, { "epoch": 0.6948988377098579, "grad_norm": 2.264810085296631, "learning_rate": 1.0634828490141477e-05, "loss": 4.0966, "step": 12914 }, { "epoch": 0.6949526474386569, "grad_norm": 1.8865408897399902, "learning_rate": 1.0631369843292963e-05, "loss": 4.1254, "step": 12915 }, { "epoch": 0.6950064571674559, "grad_norm": 2.0004725456237793, "learning_rate": 1.062791160706125e-05, "loss": 3.0602, "step": 12916 }, { "epoch": 0.6950602668962549, "grad_norm": 3.674511432647705, "learning_rate": 1.0624453781545157e-05, "loss": 3.6292, "step": 12917 }, { "epoch": 0.6951140766250538, "grad_norm": 1.670279622077942, "learning_rate": 1.062099636684352e-05, "loss": 4.0058, "step": 12918 }, { "epoch": 0.6951678863538527, "grad_norm": 3.316035032272339, "learning_rate": 1.061753936305514e-05, "loss": 3.5159, "step": 12919 }, { "epoch": 0.6952216960826517, "grad_norm": 2.545020580291748, "learning_rate": 1.061408277027879e-05, "loss": 4.0998, "step": 12920 }, { "epoch": 0.6952755058114507, "grad_norm": 1.7165160179138184, "learning_rate": 1.0610626588613265e-05, "loss": 4.2158, "step": 12921 }, { "epoch": 0.6953293155402497, "grad_norm": 3.0556294918060303, "learning_rate": 1.0607170818157317e-05, "loss": 3.5264, "step": 12922 }, { "epoch": 0.6953831252690487, "grad_norm": 1.2106499671936035, "learning_rate": 1.0603715459009725e-05, "loss": 3.9357, "step": 12923 }, { "epoch": 0.6954369349978476, "grad_norm": 2.7646780014038086, "learning_rate": 1.0600260511269222e-05, "loss": 3.4815, "step": 12924 }, { "epoch": 0.6954907447266466, "grad_norm": 3.498335123062134, "learning_rate": 1.0596805975034545e-05, "loss": 2.8113, "step": 12925 }, { "epoch": 0.6955445544554455, "grad_norm": 3.2939462661743164, "learning_rate": 1.0593351850404411e-05, "loss": 3.5627, "step": 12926 }, { "epoch": 0.6955983641842445, "grad_norm": 2.2938971519470215, "learning_rate": 1.0589898137477536e-05, "loss": 4.0484, "step": 12927 }, { "epoch": 0.6956521739130435, "grad_norm": 1.8942124843597412, "learning_rate": 1.058644483635261e-05, "loss": 4.0571, "step": 12928 }, { "epoch": 0.6957059836418424, "grad_norm": 2.5017495155334473, "learning_rate": 1.0582991947128324e-05, "loss": 3.7084, "step": 12929 }, { "epoch": 0.6957597933706414, "grad_norm": 2.5131070613861084, "learning_rate": 1.0579539469903351e-05, "loss": 3.642, "step": 12930 }, { "epoch": 0.6958136030994404, "grad_norm": 2.4196815490722656, "learning_rate": 1.0576087404776352e-05, "loss": 3.4472, "step": 12931 }, { "epoch": 0.6958674128282394, "grad_norm": 3.5964293479919434, "learning_rate": 1.057263575184598e-05, "loss": 3.6583, "step": 12932 }, { "epoch": 0.6959212225570384, "grad_norm": 2.3397669792175293, "learning_rate": 1.0569184511210867e-05, "loss": 3.9544, "step": 12933 }, { "epoch": 0.6959750322858372, "grad_norm": 1.250380516052246, "learning_rate": 1.0565733682969653e-05, "loss": 4.3947, "step": 12934 }, { "epoch": 0.6960288420146362, "grad_norm": 1.7983806133270264, "learning_rate": 1.0562283267220954e-05, "loss": 4.5452, "step": 12935 }, { "epoch": 0.6960826517434352, "grad_norm": 2.997258186340332, "learning_rate": 1.0558833264063358e-05, "loss": 3.9845, "step": 12936 }, { "epoch": 0.6961364614722342, "grad_norm": 3.2096915245056152, "learning_rate": 1.0555383673595468e-05, "loss": 4.3229, "step": 12937 }, { "epoch": 0.6961902712010332, "grad_norm": 3.313998222351074, "learning_rate": 1.055193449591585e-05, "loss": 3.4383, "step": 12938 }, { "epoch": 0.6962440809298321, "grad_norm": 2.181276798248291, "learning_rate": 1.0548485731123092e-05, "loss": 3.949, "step": 12939 }, { "epoch": 0.6962978906586311, "grad_norm": 2.344539165496826, "learning_rate": 1.0545037379315743e-05, "loss": 3.9501, "step": 12940 }, { "epoch": 0.69635170038743, "grad_norm": 2.3832333087921143, "learning_rate": 1.0541589440592345e-05, "loss": 3.6896, "step": 12941 }, { "epoch": 0.696405510116229, "grad_norm": 2.1759064197540283, "learning_rate": 1.0538141915051433e-05, "loss": 3.4584, "step": 12942 }, { "epoch": 0.696459319845028, "grad_norm": 2.9820950031280518, "learning_rate": 1.0534694802791525e-05, "loss": 4.1968, "step": 12943 }, { "epoch": 0.6965131295738269, "grad_norm": 3.103386878967285, "learning_rate": 1.0531248103911137e-05, "loss": 3.6768, "step": 12944 }, { "epoch": 0.6965669393026259, "grad_norm": 3.6908676624298096, "learning_rate": 1.052780181850876e-05, "loss": 3.5979, "step": 12945 }, { "epoch": 0.6966207490314249, "grad_norm": 3.366703987121582, "learning_rate": 1.052435594668288e-05, "loss": 3.8105, "step": 12946 }, { "epoch": 0.6966745587602239, "grad_norm": 1.5255171060562134, "learning_rate": 1.0520910488531973e-05, "loss": 4.5311, "step": 12947 }, { "epoch": 0.6967283684890229, "grad_norm": 2.7009201049804688, "learning_rate": 1.0517465444154489e-05, "loss": 3.541, "step": 12948 }, { "epoch": 0.6967821782178217, "grad_norm": 1.815969705581665, "learning_rate": 1.05140208136489e-05, "loss": 3.9645, "step": 12949 }, { "epoch": 0.6968359879466207, "grad_norm": 2.723191022872925, "learning_rate": 1.0510576597113645e-05, "loss": 3.5145, "step": 12950 }, { "epoch": 0.6968897976754197, "grad_norm": 2.3221073150634766, "learning_rate": 1.0507132794647126e-05, "loss": 4.1649, "step": 12951 }, { "epoch": 0.6969436074042187, "grad_norm": 3.194114923477173, "learning_rate": 1.0503689406347772e-05, "loss": 3.3888, "step": 12952 }, { "epoch": 0.6969974171330177, "grad_norm": 3.7714414596557617, "learning_rate": 1.0500246432313975e-05, "loss": 3.5763, "step": 12953 }, { "epoch": 0.6970512268618166, "grad_norm": 3.3050875663757324, "learning_rate": 1.0496803872644145e-05, "loss": 4.0437, "step": 12954 }, { "epoch": 0.6971050365906156, "grad_norm": 2.5587353706359863, "learning_rate": 1.049336172743665e-05, "loss": 3.0095, "step": 12955 }, { "epoch": 0.6971588463194146, "grad_norm": 2.9117581844329834, "learning_rate": 1.048991999678986e-05, "loss": 3.2175, "step": 12956 }, { "epoch": 0.6972126560482135, "grad_norm": 3.4861481189727783, "learning_rate": 1.0486478680802128e-05, "loss": 3.1867, "step": 12957 }, { "epoch": 0.6972664657770125, "grad_norm": 2.2065954208374023, "learning_rate": 1.04830377795718e-05, "loss": 3.7007, "step": 12958 }, { "epoch": 0.6973202755058114, "grad_norm": 4.330014705657959, "learning_rate": 1.0479597293197204e-05, "loss": 3.8285, "step": 12959 }, { "epoch": 0.6973740852346104, "grad_norm": 1.4029737710952759, "learning_rate": 1.0476157221776663e-05, "loss": 4.4129, "step": 12960 }, { "epoch": 0.6974278949634094, "grad_norm": 1.3222265243530273, "learning_rate": 1.0472717565408486e-05, "loss": 4.4555, "step": 12961 }, { "epoch": 0.6974817046922084, "grad_norm": 2.0578739643096924, "learning_rate": 1.0469278324190964e-05, "loss": 4.3114, "step": 12962 }, { "epoch": 0.6975355144210074, "grad_norm": 2.6043622493743896, "learning_rate": 1.0465839498222385e-05, "loss": 3.7777, "step": 12963 }, { "epoch": 0.6975893241498062, "grad_norm": 2.199033260345459, "learning_rate": 1.0462401087601012e-05, "loss": 4.0347, "step": 12964 }, { "epoch": 0.6976431338786052, "grad_norm": 1.9794775247573853, "learning_rate": 1.0458963092425133e-05, "loss": 4.4771, "step": 12965 }, { "epoch": 0.6976969436074042, "grad_norm": 2.2128725051879883, "learning_rate": 1.045552551279297e-05, "loss": 3.9865, "step": 12966 }, { "epoch": 0.6977507533362032, "grad_norm": 2.7383861541748047, "learning_rate": 1.0452088348802765e-05, "loss": 3.803, "step": 12967 }, { "epoch": 0.6978045630650022, "grad_norm": 3.1195595264434814, "learning_rate": 1.044865160055275e-05, "loss": 4.0499, "step": 12968 }, { "epoch": 0.6978583727938011, "grad_norm": 3.027843475341797, "learning_rate": 1.0445215268141123e-05, "loss": 4.5661, "step": 12969 }, { "epoch": 0.6979121825226001, "grad_norm": 2.670696973800659, "learning_rate": 1.0441779351666104e-05, "loss": 4.1561, "step": 12970 }, { "epoch": 0.6979659922513991, "grad_norm": 2.5518603324890137, "learning_rate": 1.0438343851225873e-05, "loss": 3.9533, "step": 12971 }, { "epoch": 0.698019801980198, "grad_norm": 2.595986843109131, "learning_rate": 1.043490876691861e-05, "loss": 3.7146, "step": 12972 }, { "epoch": 0.698073611708997, "grad_norm": 3.1048505306243896, "learning_rate": 1.0431474098842477e-05, "loss": 3.214, "step": 12973 }, { "epoch": 0.6981274214377959, "grad_norm": 1.3366791009902954, "learning_rate": 1.0428039847095634e-05, "loss": 4.1352, "step": 12974 }, { "epoch": 0.6981812311665949, "grad_norm": 1.6497132778167725, "learning_rate": 1.0424606011776214e-05, "loss": 3.9843, "step": 12975 }, { "epoch": 0.6982350408953939, "grad_norm": 2.530747890472412, "learning_rate": 1.0421172592982353e-05, "loss": 4.0209, "step": 12976 }, { "epoch": 0.6982888506241929, "grad_norm": 2.0820446014404297, "learning_rate": 1.0417739590812164e-05, "loss": 4.3414, "step": 12977 }, { "epoch": 0.6983426603529919, "grad_norm": 2.029710292816162, "learning_rate": 1.041430700536376e-05, "loss": 4.4954, "step": 12978 }, { "epoch": 0.6983964700817907, "grad_norm": 2.983321189880371, "learning_rate": 1.0410874836735218e-05, "loss": 3.4904, "step": 12979 }, { "epoch": 0.6984502798105897, "grad_norm": 2.711256980895996, "learning_rate": 1.0407443085024655e-05, "loss": 3.5695, "step": 12980 }, { "epoch": 0.6985040895393887, "grad_norm": 3.903215169906616, "learning_rate": 1.0404011750330107e-05, "loss": 4.0635, "step": 12981 }, { "epoch": 0.6985578992681877, "grad_norm": 1.1070010662078857, "learning_rate": 1.0400580832749646e-05, "loss": 4.4329, "step": 12982 }, { "epoch": 0.6986117089969867, "grad_norm": 1.5962902307510376, "learning_rate": 1.0397150332381316e-05, "loss": 4.3104, "step": 12983 }, { "epoch": 0.6986655187257856, "grad_norm": 2.433176040649414, "learning_rate": 1.0393720249323143e-05, "loss": 4.0566, "step": 12984 }, { "epoch": 0.6987193284545846, "grad_norm": 4.66526460647583, "learning_rate": 1.039029058367317e-05, "loss": 3.8385, "step": 12985 }, { "epoch": 0.6987731381833836, "grad_norm": 2.8614983558654785, "learning_rate": 1.0386861335529397e-05, "loss": 3.686, "step": 12986 }, { "epoch": 0.6988269479121825, "grad_norm": 3.6380202770233154, "learning_rate": 1.038343250498982e-05, "loss": 3.8154, "step": 12987 }, { "epoch": 0.6988807576409815, "grad_norm": 2.1872668266296387, "learning_rate": 1.038000409215244e-05, "loss": 4.0378, "step": 12988 }, { "epoch": 0.6989345673697804, "grad_norm": 3.9331300258636475, "learning_rate": 1.0376576097115198e-05, "loss": 2.7571, "step": 12989 }, { "epoch": 0.6989883770985794, "grad_norm": 2.530386209487915, "learning_rate": 1.0373148519976091e-05, "loss": 3.8427, "step": 12990 }, { "epoch": 0.6990421868273784, "grad_norm": 2.5283069610595703, "learning_rate": 1.0369721360833056e-05, "loss": 4.1602, "step": 12991 }, { "epoch": 0.6990959965561774, "grad_norm": 2.044602870941162, "learning_rate": 1.0366294619784034e-05, "loss": 4.0274, "step": 12992 }, { "epoch": 0.6991498062849764, "grad_norm": 2.556960344314575, "learning_rate": 1.0362868296926954e-05, "loss": 3.6617, "step": 12993 }, { "epoch": 0.6992036160137753, "grad_norm": 1.6891995668411255, "learning_rate": 1.0359442392359725e-05, "loss": 4.2233, "step": 12994 }, { "epoch": 0.6992574257425742, "grad_norm": 4.466245174407959, "learning_rate": 1.0356016906180246e-05, "loss": 4.2401, "step": 12995 }, { "epoch": 0.6993112354713732, "grad_norm": 2.832794666290283, "learning_rate": 1.0352591838486436e-05, "loss": 4.0086, "step": 12996 }, { "epoch": 0.6993650452001722, "grad_norm": 3.2643423080444336, "learning_rate": 1.0349167189376144e-05, "loss": 3.0536, "step": 12997 }, { "epoch": 0.6994188549289712, "grad_norm": 2.8686652183532715, "learning_rate": 1.0345742958947246e-05, "loss": 3.0773, "step": 12998 }, { "epoch": 0.6994726646577701, "grad_norm": 2.395233392715454, "learning_rate": 1.0342319147297594e-05, "loss": 3.3664, "step": 12999 }, { "epoch": 0.6995264743865691, "grad_norm": 2.832918167114258, "learning_rate": 1.0338895754525042e-05, "loss": 4.2391, "step": 13000 }, { "epoch": 0.6995802841153681, "grad_norm": 2.1830499172210693, "learning_rate": 1.0335472780727414e-05, "loss": 4.3802, "step": 13001 }, { "epoch": 0.699634093844167, "grad_norm": 2.9094128608703613, "learning_rate": 1.0332050226002535e-05, "loss": 4.0769, "step": 13002 }, { "epoch": 0.699687903572966, "grad_norm": 2.8926780223846436, "learning_rate": 1.0328628090448217e-05, "loss": 4.0886, "step": 13003 }, { "epoch": 0.6997417133017649, "grad_norm": 2.186208724975586, "learning_rate": 1.0325206374162227e-05, "loss": 4.1218, "step": 13004 }, { "epoch": 0.6997955230305639, "grad_norm": 2.954747438430786, "learning_rate": 1.0321785077242377e-05, "loss": 4.1756, "step": 13005 }, { "epoch": 0.6998493327593629, "grad_norm": 1.3205766677856445, "learning_rate": 1.0318364199786432e-05, "loss": 4.536, "step": 13006 }, { "epoch": 0.6999031424881619, "grad_norm": 2.8177177906036377, "learning_rate": 1.0314943741892146e-05, "loss": 2.8727, "step": 13007 }, { "epoch": 0.6999569522169609, "grad_norm": 3.79465913772583, "learning_rate": 1.0311523703657272e-05, "loss": 3.0611, "step": 13008 }, { "epoch": 0.7000107619457598, "grad_norm": 3.3403992652893066, "learning_rate": 1.0308104085179542e-05, "loss": 4.429, "step": 13009 }, { "epoch": 0.7000645716745587, "grad_norm": 2.73044753074646, "learning_rate": 1.0304684886556676e-05, "loss": 3.6213, "step": 13010 }, { "epoch": 0.7001183814033577, "grad_norm": 2.248805522918701, "learning_rate": 1.0301266107886403e-05, "loss": 3.5319, "step": 13011 }, { "epoch": 0.7001721911321567, "grad_norm": 2.2776482105255127, "learning_rate": 1.0297847749266404e-05, "loss": 3.9765, "step": 13012 }, { "epoch": 0.7002260008609557, "grad_norm": 3.9197442531585693, "learning_rate": 1.0294429810794367e-05, "loss": 4.0368, "step": 13013 }, { "epoch": 0.7002798105897546, "grad_norm": 2.2579522132873535, "learning_rate": 1.0291012292567978e-05, "loss": 3.9465, "step": 13014 }, { "epoch": 0.7003336203185536, "grad_norm": 3.3803634643554688, "learning_rate": 1.0287595194684884e-05, "loss": 3.4788, "step": 13015 }, { "epoch": 0.7003874300473526, "grad_norm": 2.655658483505249, "learning_rate": 1.0284178517242757e-05, "loss": 4.5648, "step": 13016 }, { "epoch": 0.7004412397761516, "grad_norm": 1.7573087215423584, "learning_rate": 1.0280762260339228e-05, "loss": 4.2798, "step": 13017 }, { "epoch": 0.7004950495049505, "grad_norm": 1.7047749757766724, "learning_rate": 1.027734642407192e-05, "loss": 3.8178, "step": 13018 }, { "epoch": 0.7005488592337494, "grad_norm": 1.5482890605926514, "learning_rate": 1.0273931008538465e-05, "loss": 4.2881, "step": 13019 }, { "epoch": 0.7006026689625484, "grad_norm": 3.005265474319458, "learning_rate": 1.0270516013836434e-05, "loss": 3.5183, "step": 13020 }, { "epoch": 0.7006564786913474, "grad_norm": 2.7134578227996826, "learning_rate": 1.0267101440063445e-05, "loss": 4.0863, "step": 13021 }, { "epoch": 0.7007102884201464, "grad_norm": 3.1137149333953857, "learning_rate": 1.0263687287317073e-05, "loss": 2.5907, "step": 13022 }, { "epoch": 0.7007640981489454, "grad_norm": 3.5923705101013184, "learning_rate": 1.026027355569488e-05, "loss": 3.4477, "step": 13023 }, { "epoch": 0.7008179078777443, "grad_norm": 4.28713846206665, "learning_rate": 1.0256860245294425e-05, "loss": 4.0228, "step": 13024 }, { "epoch": 0.7008717176065432, "grad_norm": 1.484831690788269, "learning_rate": 1.025344735621325e-05, "loss": 4.0612, "step": 13025 }, { "epoch": 0.7009255273353422, "grad_norm": 3.724726676940918, "learning_rate": 1.0250034888548885e-05, "loss": 3.6121, "step": 13026 }, { "epoch": 0.7009793370641412, "grad_norm": 3.3908488750457764, "learning_rate": 1.0246622842398848e-05, "loss": 3.8936, "step": 13027 }, { "epoch": 0.7010331467929402, "grad_norm": 1.8094462156295776, "learning_rate": 1.0243211217860652e-05, "loss": 4.1403, "step": 13028 }, { "epoch": 0.7010869565217391, "grad_norm": 1.4406663179397583, "learning_rate": 1.0239800015031787e-05, "loss": 4.6463, "step": 13029 }, { "epoch": 0.7011407662505381, "grad_norm": 3.4783623218536377, "learning_rate": 1.0236389234009727e-05, "loss": 3.5281, "step": 13030 }, { "epoch": 0.7011945759793371, "grad_norm": 2.0724704265594482, "learning_rate": 1.0232978874891962e-05, "loss": 4.3113, "step": 13031 }, { "epoch": 0.7012483857081361, "grad_norm": 1.9798309803009033, "learning_rate": 1.0229568937775943e-05, "loss": 3.7803, "step": 13032 }, { "epoch": 0.701302195436935, "grad_norm": 2.3977620601654053, "learning_rate": 1.0226159422759118e-05, "loss": 3.7558, "step": 13033 }, { "epoch": 0.7013560051657339, "grad_norm": 1.9677238464355469, "learning_rate": 1.0222750329938926e-05, "loss": 3.8463, "step": 13034 }, { "epoch": 0.7014098148945329, "grad_norm": 2.10561203956604, "learning_rate": 1.0219341659412767e-05, "loss": 3.7374, "step": 13035 }, { "epoch": 0.7014636246233319, "grad_norm": 2.6861979961395264, "learning_rate": 1.0215933411278078e-05, "loss": 4.2754, "step": 13036 }, { "epoch": 0.7015174343521309, "grad_norm": 2.4554636478424072, "learning_rate": 1.0212525585632247e-05, "loss": 4.7333, "step": 13037 }, { "epoch": 0.7015712440809299, "grad_norm": 2.7991223335266113, "learning_rate": 1.0209118182572657e-05, "loss": 3.1685, "step": 13038 }, { "epoch": 0.7016250538097288, "grad_norm": 3.0423247814178467, "learning_rate": 1.0205711202196691e-05, "loss": 3.9537, "step": 13039 }, { "epoch": 0.7016788635385278, "grad_norm": 2.101637840270996, "learning_rate": 1.0202304644601707e-05, "loss": 4.133, "step": 13040 }, { "epoch": 0.7017326732673267, "grad_norm": 2.484022855758667, "learning_rate": 1.0198898509885043e-05, "loss": 3.8182, "step": 13041 }, { "epoch": 0.7017864829961257, "grad_norm": 2.8209826946258545, "learning_rate": 1.0195492798144071e-05, "loss": 3.7765, "step": 13042 }, { "epoch": 0.7018402927249247, "grad_norm": 3.2964959144592285, "learning_rate": 1.0192087509476084e-05, "loss": 3.4019, "step": 13043 }, { "epoch": 0.7018941024537236, "grad_norm": 1.5876957178115845, "learning_rate": 1.018868264397841e-05, "loss": 4.1282, "step": 13044 }, { "epoch": 0.7019479121825226, "grad_norm": 3.6866188049316406, "learning_rate": 1.0185278201748344e-05, "loss": 3.4413, "step": 13045 }, { "epoch": 0.7020017219113216, "grad_norm": 2.4356634616851807, "learning_rate": 1.0181874182883175e-05, "loss": 3.9371, "step": 13046 }, { "epoch": 0.7020555316401206, "grad_norm": 2.7917845249176025, "learning_rate": 1.0178470587480194e-05, "loss": 3.195, "step": 13047 }, { "epoch": 0.7021093413689194, "grad_norm": 2.200244903564453, "learning_rate": 1.0175067415636655e-05, "loss": 3.6128, "step": 13048 }, { "epoch": 0.7021631510977184, "grad_norm": 3.986180543899536, "learning_rate": 1.0171664667449826e-05, "loss": 3.5289, "step": 13049 }, { "epoch": 0.7022169608265174, "grad_norm": 3.7342073917388916, "learning_rate": 1.0168262343016929e-05, "loss": 3.5959, "step": 13050 }, { "epoch": 0.7022707705553164, "grad_norm": 1.3713301420211792, "learning_rate": 1.0164860442435192e-05, "loss": 3.978, "step": 13051 }, { "epoch": 0.7023245802841154, "grad_norm": 3.6845109462738037, "learning_rate": 1.0161458965801852e-05, "loss": 3.6423, "step": 13052 }, { "epoch": 0.7023783900129144, "grad_norm": 2.550431251525879, "learning_rate": 1.0158057913214102e-05, "loss": 4.2497, "step": 13053 }, { "epoch": 0.7024321997417133, "grad_norm": 3.78364634513855, "learning_rate": 1.0154657284769136e-05, "loss": 3.8069, "step": 13054 }, { "epoch": 0.7024860094705123, "grad_norm": 1.9244108200073242, "learning_rate": 1.0151257080564139e-05, "loss": 3.7659, "step": 13055 }, { "epoch": 0.7025398191993112, "grad_norm": 2.6939783096313477, "learning_rate": 1.0147857300696273e-05, "loss": 3.9004, "step": 13056 }, { "epoch": 0.7025936289281102, "grad_norm": 1.985716700553894, "learning_rate": 1.01444579452627e-05, "loss": 4.3693, "step": 13057 }, { "epoch": 0.7026474386569092, "grad_norm": 2.326883316040039, "learning_rate": 1.014105901436056e-05, "loss": 4.3544, "step": 13058 }, { "epoch": 0.7027012483857081, "grad_norm": 3.260319948196411, "learning_rate": 1.0137660508086988e-05, "loss": 2.7258, "step": 13059 }, { "epoch": 0.7027550581145071, "grad_norm": 1.2334574460983276, "learning_rate": 1.0134262426539104e-05, "loss": 4.0074, "step": 13060 }, { "epoch": 0.7028088678433061, "grad_norm": 2.0053303241729736, "learning_rate": 1.0130864769814008e-05, "loss": 3.7753, "step": 13061 }, { "epoch": 0.7028626775721051, "grad_norm": 3.607362985610962, "learning_rate": 1.0127467538008811e-05, "loss": 3.3622, "step": 13062 }, { "epoch": 0.7029164873009041, "grad_norm": 3.5191173553466797, "learning_rate": 1.0124070731220592e-05, "loss": 3.3269, "step": 13063 }, { "epoch": 0.7029702970297029, "grad_norm": 1.947341799736023, "learning_rate": 1.0120674349546416e-05, "loss": 3.8228, "step": 13064 }, { "epoch": 0.7030241067585019, "grad_norm": 2.7276110649108887, "learning_rate": 1.0117278393083358e-05, "loss": 3.8091, "step": 13065 }, { "epoch": 0.7030779164873009, "grad_norm": 2.981726884841919, "learning_rate": 1.0113882861928434e-05, "loss": 3.9893, "step": 13066 }, { "epoch": 0.7031317262160999, "grad_norm": 4.557164669036865, "learning_rate": 1.011048775617871e-05, "loss": 3.8526, "step": 13067 }, { "epoch": 0.7031855359448989, "grad_norm": 2.417658567428589, "learning_rate": 1.0107093075931196e-05, "loss": 4.4303, "step": 13068 }, { "epoch": 0.7032393456736978, "grad_norm": 4.071791648864746, "learning_rate": 1.0103698821282906e-05, "loss": 3.94, "step": 13069 }, { "epoch": 0.7032931554024968, "grad_norm": 1.7562084197998047, "learning_rate": 1.0100304992330836e-05, "loss": 4.4174, "step": 13070 }, { "epoch": 0.7033469651312957, "grad_norm": 5.266785621643066, "learning_rate": 1.0096911589171976e-05, "loss": 3.2143, "step": 13071 }, { "epoch": 0.7034007748600947, "grad_norm": 2.7504539489746094, "learning_rate": 1.0093518611903296e-05, "loss": 3.7789, "step": 13072 }, { "epoch": 0.7034545845888936, "grad_norm": 1.615095615386963, "learning_rate": 1.009012606062176e-05, "loss": 3.9899, "step": 13073 }, { "epoch": 0.7035083943176926, "grad_norm": 3.5290074348449707, "learning_rate": 1.008673393542432e-05, "loss": 3.8719, "step": 13074 }, { "epoch": 0.7035622040464916, "grad_norm": 1.3845601081848145, "learning_rate": 1.008334223640791e-05, "loss": 3.7676, "step": 13075 }, { "epoch": 0.7036160137752906, "grad_norm": 3.077327013015747, "learning_rate": 1.007995096366946e-05, "loss": 3.6489, "step": 13076 }, { "epoch": 0.7036698235040896, "grad_norm": 3.125614643096924, "learning_rate": 1.0076560117305872e-05, "loss": 3.3773, "step": 13077 }, { "epoch": 0.7037236332328886, "grad_norm": 2.7582292556762695, "learning_rate": 1.0073169697414068e-05, "loss": 4.2635, "step": 13078 }, { "epoch": 0.7037774429616874, "grad_norm": 1.8456919193267822, "learning_rate": 1.006977970409092e-05, "loss": 4.2774, "step": 13079 }, { "epoch": 0.7038312526904864, "grad_norm": 3.375483274459839, "learning_rate": 1.0066390137433323e-05, "loss": 4.003, "step": 13080 }, { "epoch": 0.7038850624192854, "grad_norm": 3.8155791759490967, "learning_rate": 1.0063000997538119e-05, "loss": 3.3518, "step": 13081 }, { "epoch": 0.7039388721480844, "grad_norm": 1.9939956665039062, "learning_rate": 1.0059612284502162e-05, "loss": 4.1865, "step": 13082 }, { "epoch": 0.7039926818768834, "grad_norm": 3.5477426052093506, "learning_rate": 1.0056223998422309e-05, "loss": 4.0804, "step": 13083 }, { "epoch": 0.7040464916056823, "grad_norm": 2.7110164165496826, "learning_rate": 1.0052836139395384e-05, "loss": 3.393, "step": 13084 }, { "epoch": 0.7041003013344813, "grad_norm": 2.8255367279052734, "learning_rate": 1.0049448707518195e-05, "loss": 4.0252, "step": 13085 }, { "epoch": 0.7041541110632802, "grad_norm": 2.6876015663146973, "learning_rate": 1.0046061702887549e-05, "loss": 3.6629, "step": 13086 }, { "epoch": 0.7042079207920792, "grad_norm": 3.5163655281066895, "learning_rate": 1.004267512560024e-05, "loss": 3.8228, "step": 13087 }, { "epoch": 0.7042617305208781, "grad_norm": 4.0198588371276855, "learning_rate": 1.0039288975753047e-05, "loss": 3.8725, "step": 13088 }, { "epoch": 0.7043155402496771, "grad_norm": 1.5495811700820923, "learning_rate": 1.0035903253442732e-05, "loss": 3.7145, "step": 13089 }, { "epoch": 0.7043693499784761, "grad_norm": 1.5030367374420166, "learning_rate": 1.0032517958766059e-05, "loss": 3.9008, "step": 13090 }, { "epoch": 0.7044231597072751, "grad_norm": 1.772649884223938, "learning_rate": 1.002913309181976e-05, "loss": 4.2351, "step": 13091 }, { "epoch": 0.7044769694360741, "grad_norm": 2.3073418140411377, "learning_rate": 1.0025748652700561e-05, "loss": 3.6807, "step": 13092 }, { "epoch": 0.7045307791648731, "grad_norm": 2.0675086975097656, "learning_rate": 1.00223646415052e-05, "loss": 3.9666, "step": 13093 }, { "epoch": 0.7045845888936719, "grad_norm": 2.2173473834991455, "learning_rate": 1.0018981058330373e-05, "loss": 4.125, "step": 13094 }, { "epoch": 0.7046383986224709, "grad_norm": 2.325315475463867, "learning_rate": 1.001559790327278e-05, "loss": 3.618, "step": 13095 }, { "epoch": 0.7046922083512699, "grad_norm": 2.9874391555786133, "learning_rate": 1.0012215176429087e-05, "loss": 4.0854, "step": 13096 }, { "epoch": 0.7047460180800689, "grad_norm": 4.087647438049316, "learning_rate": 1.0008832877895966e-05, "loss": 3.0211, "step": 13097 }, { "epoch": 0.7047998278088679, "grad_norm": 1.4882874488830566, "learning_rate": 1.0005451007770086e-05, "loss": 3.9552, "step": 13098 }, { "epoch": 0.7048536375376668, "grad_norm": 2.356179714202881, "learning_rate": 1.0002069566148086e-05, "loss": 4.1313, "step": 13099 }, { "epoch": 0.7049074472664658, "grad_norm": 1.9792742729187012, "learning_rate": 9.998688553126601e-06, "loss": 3.8593, "step": 13100 }, { "epoch": 0.7049612569952648, "grad_norm": 1.9893498420715332, "learning_rate": 9.995307968802244e-06, "loss": 4.3328, "step": 13101 }, { "epoch": 0.7050150667240637, "grad_norm": 1.9310637712478638, "learning_rate": 9.991927813271629e-06, "loss": 4.4553, "step": 13102 }, { "epoch": 0.7050688764528626, "grad_norm": 2.0540597438812256, "learning_rate": 9.988548086631352e-06, "loss": 4.0334, "step": 13103 }, { "epoch": 0.7051226861816616, "grad_norm": 2.5966341495513916, "learning_rate": 9.985168788977991e-06, "loss": 4.2271, "step": 13104 }, { "epoch": 0.7051764959104606, "grad_norm": 4.5171613693237305, "learning_rate": 9.981789920408125e-06, "loss": 2.7021, "step": 13105 }, { "epoch": 0.7052303056392596, "grad_norm": 3.903005838394165, "learning_rate": 9.978411481018307e-06, "loss": 4.2008, "step": 13106 }, { "epoch": 0.7052841153680586, "grad_norm": 4.387098789215088, "learning_rate": 9.975033470905084e-06, "loss": 3.2032, "step": 13107 }, { "epoch": 0.7053379250968576, "grad_norm": 3.8141541481018066, "learning_rate": 9.971655890164985e-06, "loss": 3.3145, "step": 13108 }, { "epoch": 0.7053917348256564, "grad_norm": 2.307124614715576, "learning_rate": 9.968278738894545e-06, "loss": 4.5528, "step": 13109 }, { "epoch": 0.7054455445544554, "grad_norm": 2.8286020755767822, "learning_rate": 9.96490201719028e-06, "loss": 4.3176, "step": 13110 }, { "epoch": 0.7054993542832544, "grad_norm": 1.6513276100158691, "learning_rate": 9.961525725148668e-06, "loss": 3.7994, "step": 13111 }, { "epoch": 0.7055531640120534, "grad_norm": 2.4438085556030273, "learning_rate": 9.9581498628662e-06, "loss": 4.0584, "step": 13112 }, { "epoch": 0.7056069737408524, "grad_norm": 2.4015731811523438, "learning_rate": 9.954774430439342e-06, "loss": 4.4059, "step": 13113 }, { "epoch": 0.7056607834696513, "grad_norm": 2.8591010570526123, "learning_rate": 9.951399427964572e-06, "loss": 3.811, "step": 13114 }, { "epoch": 0.7057145931984503, "grad_norm": 3.249574661254883, "learning_rate": 9.948024855538331e-06, "loss": 4.1242, "step": 13115 }, { "epoch": 0.7057684029272493, "grad_norm": 3.928438186645508, "learning_rate": 9.944650713257056e-06, "loss": 3.9631, "step": 13116 }, { "epoch": 0.7058222126560482, "grad_norm": 1.9518463611602783, "learning_rate": 9.941277001217169e-06, "loss": 3.852, "step": 13117 }, { "epoch": 0.7058760223848471, "grad_norm": 2.237504005432129, "learning_rate": 9.937903719515081e-06, "loss": 4.4876, "step": 13118 }, { "epoch": 0.7059298321136461, "grad_norm": 1.7784314155578613, "learning_rate": 9.934530868247194e-06, "loss": 4.7143, "step": 13119 }, { "epoch": 0.7059836418424451, "grad_norm": 1.298946738243103, "learning_rate": 9.931158447509892e-06, "loss": 4.3201, "step": 13120 }, { "epoch": 0.7060374515712441, "grad_norm": 2.5111658573150635, "learning_rate": 9.927786457399552e-06, "loss": 3.8649, "step": 13121 }, { "epoch": 0.7060912613000431, "grad_norm": 2.97868013381958, "learning_rate": 9.924414898012536e-06, "loss": 3.8978, "step": 13122 }, { "epoch": 0.706145071028842, "grad_norm": 2.8072714805603027, "learning_rate": 9.921043769445185e-06, "loss": 3.9089, "step": 13123 }, { "epoch": 0.706198880757641, "grad_norm": 3.1595911979675293, "learning_rate": 9.917673071793851e-06, "loss": 3.0634, "step": 13124 }, { "epoch": 0.7062526904864399, "grad_norm": 1.747989535331726, "learning_rate": 9.914302805154857e-06, "loss": 4.4577, "step": 13125 }, { "epoch": 0.7063065002152389, "grad_norm": 3.399629592895508, "learning_rate": 9.91093296962452e-06, "loss": 3.7186, "step": 13126 }, { "epoch": 0.7063603099440379, "grad_norm": 1.9451053142547607, "learning_rate": 9.907563565299127e-06, "loss": 3.8628, "step": 13127 }, { "epoch": 0.7064141196728368, "grad_norm": 2.2693066596984863, "learning_rate": 9.904194592274965e-06, "loss": 4.1548, "step": 13128 }, { "epoch": 0.7064679294016358, "grad_norm": 2.0237197875976562, "learning_rate": 9.900826050648326e-06, "loss": 4.1523, "step": 13129 }, { "epoch": 0.7065217391304348, "grad_norm": 3.2755510807037354, "learning_rate": 9.897457940515468e-06, "loss": 3.3193, "step": 13130 }, { "epoch": 0.7065755488592338, "grad_norm": 1.6233080625534058, "learning_rate": 9.894090261972639e-06, "loss": 3.8333, "step": 13131 }, { "epoch": 0.7066293585880327, "grad_norm": 1.8236538171768188, "learning_rate": 9.89072301511608e-06, "loss": 3.8554, "step": 13132 }, { "epoch": 0.7066831683168316, "grad_norm": 2.474644422531128, "learning_rate": 9.887356200042019e-06, "loss": 3.8588, "step": 13133 }, { "epoch": 0.7067369780456306, "grad_norm": 2.8308537006378174, "learning_rate": 9.88398981684667e-06, "loss": 3.4874, "step": 13134 }, { "epoch": 0.7067907877744296, "grad_norm": 4.006601810455322, "learning_rate": 9.880623865626235e-06, "loss": 3.2853, "step": 13135 }, { "epoch": 0.7068445975032286, "grad_norm": 2.059865713119507, "learning_rate": 9.8772583464769e-06, "loss": 4.1362, "step": 13136 }, { "epoch": 0.7068984072320276, "grad_norm": 2.9256210327148438, "learning_rate": 9.873893259494852e-06, "loss": 3.5948, "step": 13137 }, { "epoch": 0.7069522169608266, "grad_norm": 3.9378368854522705, "learning_rate": 9.870528604776244e-06, "loss": 3.8138, "step": 13138 }, { "epoch": 0.7070060266896255, "grad_norm": 1.6365283727645874, "learning_rate": 9.86716438241723e-06, "loss": 4.0134, "step": 13139 }, { "epoch": 0.7070598364184244, "grad_norm": 2.7723946571350098, "learning_rate": 9.863800592513963e-06, "loss": 4.4828, "step": 13140 }, { "epoch": 0.7071136461472234, "grad_norm": 3.3498387336730957, "learning_rate": 9.860437235162573e-06, "loss": 3.0998, "step": 13141 }, { "epoch": 0.7071674558760224, "grad_norm": 3.3609700202941895, "learning_rate": 9.857074310459157e-06, "loss": 3.1312, "step": 13142 }, { "epoch": 0.7072212656048213, "grad_norm": 3.8172824382781982, "learning_rate": 9.853711818499828e-06, "loss": 3.3527, "step": 13143 }, { "epoch": 0.7072750753336203, "grad_norm": 1.962438941001892, "learning_rate": 9.850349759380667e-06, "loss": 4.5396, "step": 13144 }, { "epoch": 0.7073288850624193, "grad_norm": 3.728472948074341, "learning_rate": 9.84698813319777e-06, "loss": 3.0237, "step": 13145 }, { "epoch": 0.7073826947912183, "grad_norm": 2.888885736465454, "learning_rate": 9.843626940047198e-06, "loss": 3.7911, "step": 13146 }, { "epoch": 0.7074365045200173, "grad_norm": 1.9945499897003174, "learning_rate": 9.840266180025001e-06, "loss": 4.0256, "step": 13147 }, { "epoch": 0.7074903142488161, "grad_norm": 1.330883502960205, "learning_rate": 9.83690585322722e-06, "loss": 4.3532, "step": 13148 }, { "epoch": 0.7075441239776151, "grad_norm": 1.8304455280303955, "learning_rate": 9.833545959749888e-06, "loss": 3.4672, "step": 13149 }, { "epoch": 0.7075979337064141, "grad_norm": 2.1096460819244385, "learning_rate": 9.83018649968902e-06, "loss": 4.5142, "step": 13150 }, { "epoch": 0.7076517434352131, "grad_norm": 2.3585612773895264, "learning_rate": 9.826827473140618e-06, "loss": 4.2838, "step": 13151 }, { "epoch": 0.7077055531640121, "grad_norm": 1.5953377485275269, "learning_rate": 9.823468880200676e-06, "loss": 3.7789, "step": 13152 }, { "epoch": 0.707759362892811, "grad_norm": 2.5913681983947754, "learning_rate": 9.820110720965173e-06, "loss": 4.0617, "step": 13153 }, { "epoch": 0.70781317262161, "grad_norm": 2.686213254928589, "learning_rate": 9.816752995530069e-06, "loss": 3.9815, "step": 13154 }, { "epoch": 0.7078669823504089, "grad_norm": 2.8130526542663574, "learning_rate": 9.813395703991335e-06, "loss": 3.9725, "step": 13155 }, { "epoch": 0.7079207920792079, "grad_norm": 2.307903528213501, "learning_rate": 9.810038846444913e-06, "loss": 4.7608, "step": 13156 }, { "epoch": 0.7079746018080069, "grad_norm": 2.754028797149658, "learning_rate": 9.806682422986715e-06, "loss": 3.6299, "step": 13157 }, { "epoch": 0.7080284115368058, "grad_norm": 2.07273268699646, "learning_rate": 9.803326433712668e-06, "loss": 4.0928, "step": 13158 }, { "epoch": 0.7080822212656048, "grad_norm": 2.918470621109009, "learning_rate": 9.79997087871867e-06, "loss": 3.4307, "step": 13159 }, { "epoch": 0.7081360309944038, "grad_norm": 2.6846187114715576, "learning_rate": 9.796615758100627e-06, "loss": 3.9379, "step": 13160 }, { "epoch": 0.7081898407232028, "grad_norm": 4.331860542297363, "learning_rate": 9.793261071954419e-06, "loss": 3.5113, "step": 13161 }, { "epoch": 0.7082436504520018, "grad_norm": 1.7523515224456787, "learning_rate": 9.789906820375901e-06, "loss": 4.1962, "step": 13162 }, { "epoch": 0.7082974601808006, "grad_norm": 2.53238844871521, "learning_rate": 9.786553003460941e-06, "loss": 3.5128, "step": 13163 }, { "epoch": 0.7083512699095996, "grad_norm": 2.2697157859802246, "learning_rate": 9.783199621305376e-06, "loss": 3.9758, "step": 13164 }, { "epoch": 0.7084050796383986, "grad_norm": 2.6562395095825195, "learning_rate": 9.779846674005036e-06, "loss": 3.5195, "step": 13165 }, { "epoch": 0.7084588893671976, "grad_norm": 2.041191816329956, "learning_rate": 9.776494161655742e-06, "loss": 4.063, "step": 13166 }, { "epoch": 0.7085126990959966, "grad_norm": 2.0387964248657227, "learning_rate": 9.773142084353295e-06, "loss": 4.5, "step": 13167 }, { "epoch": 0.7085665088247955, "grad_norm": 2.6036815643310547, "learning_rate": 9.769790442193496e-06, "loss": 4.0807, "step": 13168 }, { "epoch": 0.7086203185535945, "grad_norm": 2.6425721645355225, "learning_rate": 9.76643923527212e-06, "loss": 3.9454, "step": 13169 }, { "epoch": 0.7086741282823935, "grad_norm": 3.0341999530792236, "learning_rate": 9.763088463684928e-06, "loss": 3.9117, "step": 13170 }, { "epoch": 0.7087279380111924, "grad_norm": 4.269764423370361, "learning_rate": 9.759738127527696e-06, "loss": 3.6947, "step": 13171 }, { "epoch": 0.7087817477399914, "grad_norm": 2.750385284423828, "learning_rate": 9.756388226896163e-06, "loss": 3.4637, "step": 13172 }, { "epoch": 0.7088355574687903, "grad_norm": 2.3681230545043945, "learning_rate": 9.753038761886046e-06, "loss": 3.6196, "step": 13173 }, { "epoch": 0.7088893671975893, "grad_norm": 4.05420446395874, "learning_rate": 9.749689732593062e-06, "loss": 3.455, "step": 13174 }, { "epoch": 0.7089431769263883, "grad_norm": 2.3049957752227783, "learning_rate": 9.746341139112938e-06, "loss": 3.5706, "step": 13175 }, { "epoch": 0.7089969866551873, "grad_norm": 3.8049986362457275, "learning_rate": 9.742992981541355e-06, "loss": 2.4821, "step": 13176 }, { "epoch": 0.7090507963839863, "grad_norm": 2.59187650680542, "learning_rate": 9.739645259973997e-06, "loss": 4.2301, "step": 13177 }, { "epoch": 0.7091046061127851, "grad_norm": 2.311785936355591, "learning_rate": 9.73629797450653e-06, "loss": 4.2587, "step": 13178 }, { "epoch": 0.7091584158415841, "grad_norm": 4.510940074920654, "learning_rate": 9.732951125234615e-06, "loss": 3.7272, "step": 13179 }, { "epoch": 0.7092122255703831, "grad_norm": 1.9469177722930908, "learning_rate": 9.729604712253893e-06, "loss": 3.9809, "step": 13180 }, { "epoch": 0.7092660352991821, "grad_norm": 4.376801490783691, "learning_rate": 9.726258735659996e-06, "loss": 3.8121, "step": 13181 }, { "epoch": 0.7093198450279811, "grad_norm": 2.774918794631958, "learning_rate": 9.722913195548542e-06, "loss": 3.4844, "step": 13182 }, { "epoch": 0.70937365475678, "grad_norm": 3.6159844398498535, "learning_rate": 9.719568092015139e-06, "loss": 3.4091, "step": 13183 }, { "epoch": 0.709427464485579, "grad_norm": 4.391286849975586, "learning_rate": 9.716223425155377e-06, "loss": 3.6904, "step": 13184 }, { "epoch": 0.709481274214378, "grad_norm": 1.4024434089660645, "learning_rate": 9.712879195064836e-06, "loss": 4.4108, "step": 13185 }, { "epoch": 0.7095350839431769, "grad_norm": 2.210111141204834, "learning_rate": 9.709535401839098e-06, "loss": 4.1737, "step": 13186 }, { "epoch": 0.7095888936719759, "grad_norm": 4.445632457733154, "learning_rate": 9.70619204557372e-06, "loss": 4.1736, "step": 13187 }, { "epoch": 0.7096427034007748, "grad_norm": 3.414705991744995, "learning_rate": 9.70284912636423e-06, "loss": 3.3098, "step": 13188 }, { "epoch": 0.7096965131295738, "grad_norm": 2.6915180683135986, "learning_rate": 9.699506644306166e-06, "loss": 4.1917, "step": 13189 }, { "epoch": 0.7097503228583728, "grad_norm": 4.029757499694824, "learning_rate": 9.69616459949504e-06, "loss": 3.6567, "step": 13190 }, { "epoch": 0.7098041325871718, "grad_norm": 3.1294009685516357, "learning_rate": 9.692822992026377e-06, "loss": 4.4069, "step": 13191 }, { "epoch": 0.7098579423159708, "grad_norm": 1.803241491317749, "learning_rate": 9.68948182199566e-06, "loss": 3.7029, "step": 13192 }, { "epoch": 0.7099117520447696, "grad_norm": 3.981949806213379, "learning_rate": 9.686141089498374e-06, "loss": 3.2818, "step": 13193 }, { "epoch": 0.7099655617735686, "grad_norm": 3.7140743732452393, "learning_rate": 9.682800794629992e-06, "loss": 4.1105, "step": 13194 }, { "epoch": 0.7100193715023676, "grad_norm": 1.745180606842041, "learning_rate": 9.67946093748595e-06, "loss": 3.9121, "step": 13195 }, { "epoch": 0.7100731812311666, "grad_norm": 2.6432714462280273, "learning_rate": 9.676121518161715e-06, "loss": 4.2602, "step": 13196 }, { "epoch": 0.7101269909599656, "grad_norm": 1.972818374633789, "learning_rate": 9.672782536752711e-06, "loss": 3.9627, "step": 13197 }, { "epoch": 0.7101808006887645, "grad_norm": 1.734511375427246, "learning_rate": 9.669443993354357e-06, "loss": 4.0856, "step": 13198 }, { "epoch": 0.7102346104175635, "grad_norm": 3.9935836791992188, "learning_rate": 9.666105888062057e-06, "loss": 4.1645, "step": 13199 }, { "epoch": 0.7102884201463625, "grad_norm": 3.3564422130584717, "learning_rate": 9.66276822097121e-06, "loss": 3.5133, "step": 13200 }, { "epoch": 0.7103422298751614, "grad_norm": 2.387239694595337, "learning_rate": 9.659430992177187e-06, "loss": 3.5584, "step": 13201 }, { "epoch": 0.7103960396039604, "grad_norm": 1.4405697584152222, "learning_rate": 9.656094201775382e-06, "loss": 4.076, "step": 13202 }, { "epoch": 0.7104498493327593, "grad_norm": 2.577322006225586, "learning_rate": 9.652757849861122e-06, "loss": 3.7641, "step": 13203 }, { "epoch": 0.7105036590615583, "grad_norm": 2.985623359680176, "learning_rate": 9.649421936529768e-06, "loss": 3.2086, "step": 13204 }, { "epoch": 0.7105574687903573, "grad_norm": 3.0843429565429688, "learning_rate": 9.646086461876635e-06, "loss": 3.7945, "step": 13205 }, { "epoch": 0.7106112785191563, "grad_norm": 4.722280025482178, "learning_rate": 9.642751425997062e-06, "loss": 3.2346, "step": 13206 }, { "epoch": 0.7106650882479553, "grad_norm": 2.151064157485962, "learning_rate": 9.63941682898635e-06, "loss": 4.6187, "step": 13207 }, { "epoch": 0.7107188979767542, "grad_norm": 2.5022082328796387, "learning_rate": 9.636082670939788e-06, "loss": 3.8351, "step": 13208 }, { "epoch": 0.7107727077055531, "grad_norm": 2.178640842437744, "learning_rate": 9.632748951952662e-06, "loss": 3.8464, "step": 13209 }, { "epoch": 0.7108265174343521, "grad_norm": 2.4136064052581787, "learning_rate": 9.629415672120234e-06, "loss": 4.3463, "step": 13210 }, { "epoch": 0.7108803271631511, "grad_norm": 1.355884313583374, "learning_rate": 9.626082831537764e-06, "loss": 4.269, "step": 13211 }, { "epoch": 0.7109341368919501, "grad_norm": 2.997194528579712, "learning_rate": 9.622750430300498e-06, "loss": 3.3993, "step": 13212 }, { "epoch": 0.710987946620749, "grad_norm": 2.572930097579956, "learning_rate": 9.619418468503663e-06, "loss": 2.5278, "step": 13213 }, { "epoch": 0.711041756349548, "grad_norm": 1.937819242477417, "learning_rate": 9.61608694624248e-06, "loss": 3.3254, "step": 13214 }, { "epoch": 0.711095566078347, "grad_norm": 1.7238554954528809, "learning_rate": 9.612755863612154e-06, "loss": 4.0727, "step": 13215 }, { "epoch": 0.7111493758071459, "grad_norm": 3.4857211112976074, "learning_rate": 9.609425220707873e-06, "loss": 3.2703, "step": 13216 }, { "epoch": 0.7112031855359449, "grad_norm": 3.104264974594116, "learning_rate": 9.606095017624839e-06, "loss": 3.4148, "step": 13217 }, { "epoch": 0.7112569952647438, "grad_norm": 1.8137611150741577, "learning_rate": 9.602765254458192e-06, "loss": 4.6644, "step": 13218 }, { "epoch": 0.7113108049935428, "grad_norm": 3.4134371280670166, "learning_rate": 9.599435931303106e-06, "loss": 2.9388, "step": 13219 }, { "epoch": 0.7113646147223418, "grad_norm": 1.9227997064590454, "learning_rate": 9.596107048254715e-06, "loss": 4.4149, "step": 13220 }, { "epoch": 0.7114184244511408, "grad_norm": 2.343022108078003, "learning_rate": 9.592778605408145e-06, "loss": 3.7295, "step": 13221 }, { "epoch": 0.7114722341799398, "grad_norm": 1.711969017982483, "learning_rate": 9.589450602858533e-06, "loss": 4.0983, "step": 13222 }, { "epoch": 0.7115260439087387, "grad_norm": 3.9966952800750732, "learning_rate": 9.58612304070097e-06, "loss": 3.9211, "step": 13223 }, { "epoch": 0.7115798536375376, "grad_norm": 2.3274385929107666, "learning_rate": 9.582795919030555e-06, "loss": 4.069, "step": 13224 }, { "epoch": 0.7116336633663366, "grad_norm": 2.9737234115600586, "learning_rate": 9.57946923794237e-06, "loss": 3.939, "step": 13225 }, { "epoch": 0.7116874730951356, "grad_norm": 1.9738410711288452, "learning_rate": 9.576142997531462e-06, "loss": 3.9191, "step": 13226 }, { "epoch": 0.7117412828239346, "grad_norm": 1.998218059539795, "learning_rate": 9.572817197892911e-06, "loss": 3.5912, "step": 13227 }, { "epoch": 0.7117950925527335, "grad_norm": 1.7982507944107056, "learning_rate": 9.569491839121752e-06, "loss": 4.3375, "step": 13228 }, { "epoch": 0.7118489022815325, "grad_norm": 1.3137704133987427, "learning_rate": 9.56616692131301e-06, "loss": 4.0519, "step": 13229 }, { "epoch": 0.7119027120103315, "grad_norm": 2.1391680240631104, "learning_rate": 9.562842444561706e-06, "loss": 4.5015, "step": 13230 }, { "epoch": 0.7119565217391305, "grad_norm": 1.8809667825698853, "learning_rate": 9.559518408962845e-06, "loss": 4.2467, "step": 13231 }, { "epoch": 0.7120103314679294, "grad_norm": 3.2916698455810547, "learning_rate": 9.556194814611411e-06, "loss": 3.5123, "step": 13232 }, { "epoch": 0.7120641411967283, "grad_norm": 2.787828207015991, "learning_rate": 9.552871661602402e-06, "loss": 4.2205, "step": 13233 }, { "epoch": 0.7121179509255273, "grad_norm": 1.9642393589019775, "learning_rate": 9.549548950030768e-06, "loss": 3.9764, "step": 13234 }, { "epoch": 0.7121717606543263, "grad_norm": 1.8715693950653076, "learning_rate": 9.546226679991468e-06, "loss": 2.9961, "step": 13235 }, { "epoch": 0.7122255703831253, "grad_norm": 2.2978174686431885, "learning_rate": 9.542904851579435e-06, "loss": 3.7201, "step": 13236 }, { "epoch": 0.7122793801119243, "grad_norm": 1.220065712928772, "learning_rate": 9.539583464889614e-06, "loss": 4.2673, "step": 13237 }, { "epoch": 0.7123331898407232, "grad_norm": 2.096907377243042, "learning_rate": 9.536262520016916e-06, "loss": 3.3981, "step": 13238 }, { "epoch": 0.7123869995695221, "grad_norm": 3.0912749767303467, "learning_rate": 9.532942017056243e-06, "loss": 3.8803, "step": 13239 }, { "epoch": 0.7124408092983211, "grad_norm": 3.4688196182250977, "learning_rate": 9.529621956102492e-06, "loss": 3.8414, "step": 13240 }, { "epoch": 0.7124946190271201, "grad_norm": 2.640401840209961, "learning_rate": 9.52630233725052e-06, "loss": 3.592, "step": 13241 }, { "epoch": 0.7125484287559191, "grad_norm": 3.643918037414551, "learning_rate": 9.522983160595214e-06, "loss": 3.3767, "step": 13242 }, { "epoch": 0.712602238484718, "grad_norm": 2.275738000869751, "learning_rate": 9.519664426231422e-06, "loss": 4.4068, "step": 13243 }, { "epoch": 0.712656048213517, "grad_norm": 2.121087074279785, "learning_rate": 9.516346134253983e-06, "loss": 4.215, "step": 13244 }, { "epoch": 0.712709857942316, "grad_norm": 3.744180917739868, "learning_rate": 9.513028284757727e-06, "loss": 3.5973, "step": 13245 }, { "epoch": 0.712763667671115, "grad_norm": 2.686170816421509, "learning_rate": 9.509710877837466e-06, "loss": 4.0555, "step": 13246 }, { "epoch": 0.7128174773999139, "grad_norm": 2.2109971046447754, "learning_rate": 9.506393913587997e-06, "loss": 3.7725, "step": 13247 }, { "epoch": 0.7128712871287128, "grad_norm": 2.44307541847229, "learning_rate": 9.503077392104132e-06, "loss": 3.7471, "step": 13248 }, { "epoch": 0.7129250968575118, "grad_norm": 3.258866548538208, "learning_rate": 9.499761313480626e-06, "loss": 3.8504, "step": 13249 }, { "epoch": 0.7129789065863108, "grad_norm": 3.315565824508667, "learning_rate": 9.496445677812252e-06, "loss": 4.5108, "step": 13250 }, { "epoch": 0.7130327163151098, "grad_norm": 2.2337214946746826, "learning_rate": 9.49313048519376e-06, "loss": 4.2471, "step": 13251 }, { "epoch": 0.7130865260439088, "grad_norm": 2.8998754024505615, "learning_rate": 9.489815735719882e-06, "loss": 3.9161, "step": 13252 }, { "epoch": 0.7131403357727077, "grad_norm": 2.511190176010132, "learning_rate": 9.486501429485358e-06, "loss": 4.5457, "step": 13253 }, { "epoch": 0.7131941455015067, "grad_norm": 2.9940390586853027, "learning_rate": 9.483187566584901e-06, "loss": 3.3574, "step": 13254 }, { "epoch": 0.7132479552303056, "grad_norm": 3.068845510482788, "learning_rate": 9.479874147113207e-06, "loss": 3.3766, "step": 13255 }, { "epoch": 0.7133017649591046, "grad_norm": 2.7907826900482178, "learning_rate": 9.476561171164974e-06, "loss": 3.5741, "step": 13256 }, { "epoch": 0.7133555746879036, "grad_norm": 1.9256166219711304, "learning_rate": 9.47324863883485e-06, "loss": 3.9292, "step": 13257 }, { "epoch": 0.7134093844167025, "grad_norm": 2.2898943424224854, "learning_rate": 9.469936550217528e-06, "loss": 4.2663, "step": 13258 }, { "epoch": 0.7134631941455015, "grad_norm": 2.775681495666504, "learning_rate": 9.46662490540765e-06, "loss": 3.4584, "step": 13259 }, { "epoch": 0.7135170038743005, "grad_norm": 2.051687240600586, "learning_rate": 9.463313704499852e-06, "loss": 4.4888, "step": 13260 }, { "epoch": 0.7135708136030995, "grad_norm": 3.3206100463867188, "learning_rate": 9.460002947588758e-06, "loss": 4.3561, "step": 13261 }, { "epoch": 0.7136246233318984, "grad_norm": 2.5658814907073975, "learning_rate": 9.456692634768985e-06, "loss": 4.2588, "step": 13262 }, { "epoch": 0.7136784330606973, "grad_norm": 2.437476634979248, "learning_rate": 9.453382766135127e-06, "loss": 3.7592, "step": 13263 }, { "epoch": 0.7137322427894963, "grad_norm": 3.339312791824341, "learning_rate": 9.450073341781776e-06, "loss": 3.7224, "step": 13264 }, { "epoch": 0.7137860525182953, "grad_norm": 2.8664934635162354, "learning_rate": 9.446764361803504e-06, "loss": 3.6907, "step": 13265 }, { "epoch": 0.7138398622470943, "grad_norm": 3.5151865482330322, "learning_rate": 9.443455826294869e-06, "loss": 4.3314, "step": 13266 }, { "epoch": 0.7138936719758933, "grad_norm": 3.1207196712493896, "learning_rate": 9.440147735350421e-06, "loss": 3.3181, "step": 13267 }, { "epoch": 0.7139474817046922, "grad_norm": 2.072254180908203, "learning_rate": 9.436840089064708e-06, "loss": 3.8774, "step": 13268 }, { "epoch": 0.7140012914334912, "grad_norm": 3.178173303604126, "learning_rate": 9.433532887532243e-06, "loss": 3.4241, "step": 13269 }, { "epoch": 0.7140551011622901, "grad_norm": 1.914904236793518, "learning_rate": 9.430226130847538e-06, "loss": 4.001, "step": 13270 }, { "epoch": 0.7141089108910891, "grad_norm": 3.0860273838043213, "learning_rate": 9.426919819105104e-06, "loss": 3.4105, "step": 13271 }, { "epoch": 0.7141627206198881, "grad_norm": 2.036452054977417, "learning_rate": 9.423613952399399e-06, "loss": 4.5354, "step": 13272 }, { "epoch": 0.714216530348687, "grad_norm": 2.466822385787964, "learning_rate": 9.420308530824917e-06, "loss": 4.0825, "step": 13273 }, { "epoch": 0.714270340077486, "grad_norm": 1.8830746412277222, "learning_rate": 9.417003554476114e-06, "loss": 3.6763, "step": 13274 }, { "epoch": 0.714324149806285, "grad_norm": 3.8022854328155518, "learning_rate": 9.413699023447437e-06, "loss": 3.9784, "step": 13275 }, { "epoch": 0.714377959535084, "grad_norm": 3.4566428661346436, "learning_rate": 9.410394937833316e-06, "loss": 3.2263, "step": 13276 }, { "epoch": 0.714431769263883, "grad_norm": 2.124910354614258, "learning_rate": 9.40709129772818e-06, "loss": 4.0612, "step": 13277 }, { "epoch": 0.7144855789926818, "grad_norm": 3.639315366744995, "learning_rate": 9.403788103226425e-06, "loss": 3.1704, "step": 13278 }, { "epoch": 0.7145393887214808, "grad_norm": 2.329911231994629, "learning_rate": 9.400485354422475e-06, "loss": 3.6248, "step": 13279 }, { "epoch": 0.7145931984502798, "grad_norm": 2.4853057861328125, "learning_rate": 9.397183051410687e-06, "loss": 4.4234, "step": 13280 }, { "epoch": 0.7146470081790788, "grad_norm": 2.584660530090332, "learning_rate": 9.39388119428544e-06, "loss": 4.049, "step": 13281 }, { "epoch": 0.7147008179078778, "grad_norm": 3.1106579303741455, "learning_rate": 9.390579783141093e-06, "loss": 2.8917, "step": 13282 }, { "epoch": 0.7147546276366767, "grad_norm": 1.9189212322235107, "learning_rate": 9.387278818071985e-06, "loss": 4.3725, "step": 13283 }, { "epoch": 0.7148084373654757, "grad_norm": 3.571455478668213, "learning_rate": 9.38397829917246e-06, "loss": 3.1613, "step": 13284 }, { "epoch": 0.7148622470942746, "grad_norm": 3.4202880859375, "learning_rate": 9.380678226536835e-06, "loss": 2.8845, "step": 13285 }, { "epoch": 0.7149160568230736, "grad_norm": 1.9689418077468872, "learning_rate": 9.377378600259423e-06, "loss": 4.0292, "step": 13286 }, { "epoch": 0.7149698665518726, "grad_norm": 4.02193546295166, "learning_rate": 9.374079420434503e-06, "loss": 3.7665, "step": 13287 }, { "epoch": 0.7150236762806715, "grad_norm": 3.0818912982940674, "learning_rate": 9.370780687156358e-06, "loss": 3.7494, "step": 13288 }, { "epoch": 0.7150774860094705, "grad_norm": 2.150728225708008, "learning_rate": 9.367482400519267e-06, "loss": 4.4082, "step": 13289 }, { "epoch": 0.7151312957382695, "grad_norm": 4.121857166290283, "learning_rate": 9.364184560617486e-06, "loss": 3.7696, "step": 13290 }, { "epoch": 0.7151851054670685, "grad_norm": 2.5606484413146973, "learning_rate": 9.360887167545255e-06, "loss": 4.2831, "step": 13291 }, { "epoch": 0.7152389151958675, "grad_norm": 3.8494040966033936, "learning_rate": 9.357590221396804e-06, "loss": 3.1379, "step": 13292 }, { "epoch": 0.7152927249246663, "grad_norm": 2.911667823791504, "learning_rate": 9.35429372226635e-06, "loss": 3.2469, "step": 13293 }, { "epoch": 0.7153465346534653, "grad_norm": 2.5786001682281494, "learning_rate": 9.350997670248099e-06, "loss": 2.9123, "step": 13294 }, { "epoch": 0.7154003443822643, "grad_norm": 3.5642826557159424, "learning_rate": 9.347702065436245e-06, "loss": 3.2071, "step": 13295 }, { "epoch": 0.7154541541110633, "grad_norm": 3.0836308002471924, "learning_rate": 9.344406907924966e-06, "loss": 3.813, "step": 13296 }, { "epoch": 0.7155079638398623, "grad_norm": 3.182121753692627, "learning_rate": 9.34111219780843e-06, "loss": 3.9442, "step": 13297 }, { "epoch": 0.7155617735686612, "grad_norm": 3.075117826461792, "learning_rate": 9.337817935180778e-06, "loss": 3.4665, "step": 13298 }, { "epoch": 0.7156155832974602, "grad_norm": 2.385911226272583, "learning_rate": 9.334524120136176e-06, "loss": 3.2775, "step": 13299 }, { "epoch": 0.7156693930262591, "grad_norm": 3.3735554218292236, "learning_rate": 9.331230752768738e-06, "loss": 3.2472, "step": 13300 }, { "epoch": 0.7157232027550581, "grad_norm": 4.685428142547607, "learning_rate": 9.32793783317259e-06, "loss": 3.8308, "step": 13301 }, { "epoch": 0.7157770124838571, "grad_norm": 2.2969021797180176, "learning_rate": 9.324645361441813e-06, "loss": 4.2795, "step": 13302 }, { "epoch": 0.715830822212656, "grad_norm": 3.6182029247283936, "learning_rate": 9.321353337670508e-06, "loss": 3.7372, "step": 13303 }, { "epoch": 0.715884631941455, "grad_norm": 2.209789514541626, "learning_rate": 9.318061761952757e-06, "loss": 3.6704, "step": 13304 }, { "epoch": 0.715938441670254, "grad_norm": 2.821716547012329, "learning_rate": 9.314770634382624e-06, "loss": 3.7981, "step": 13305 }, { "epoch": 0.715992251399053, "grad_norm": 2.9309113025665283, "learning_rate": 9.31147995505416e-06, "loss": 4.016, "step": 13306 }, { "epoch": 0.716046061127852, "grad_norm": 3.4149999618530273, "learning_rate": 9.308189724061397e-06, "loss": 3.4773, "step": 13307 }, { "epoch": 0.7160998708566508, "grad_norm": 2.149341344833374, "learning_rate": 9.304899941498368e-06, "loss": 4.3017, "step": 13308 }, { "epoch": 0.7161536805854498, "grad_norm": 2.5366742610931396, "learning_rate": 9.301610607459085e-06, "loss": 3.2099, "step": 13309 }, { "epoch": 0.7162074903142488, "grad_norm": 2.5936028957366943, "learning_rate": 9.298321722037545e-06, "loss": 3.4353, "step": 13310 }, { "epoch": 0.7162613000430478, "grad_norm": 2.168257713317871, "learning_rate": 9.29503328532774e-06, "loss": 3.7484, "step": 13311 }, { "epoch": 0.7163151097718468, "grad_norm": 2.9406113624572754, "learning_rate": 9.29174529742364e-06, "loss": 3.5511, "step": 13312 }, { "epoch": 0.7163689195006457, "grad_norm": 3.0805070400238037, "learning_rate": 9.288457758419208e-06, "loss": 3.5432, "step": 13313 }, { "epoch": 0.7164227292294447, "grad_norm": 2.2181923389434814, "learning_rate": 9.285170668408388e-06, "loss": 4.0203, "step": 13314 }, { "epoch": 0.7164765389582437, "grad_norm": 3.886068820953369, "learning_rate": 9.281884027485133e-06, "loss": 3.8336, "step": 13315 }, { "epoch": 0.7165303486870426, "grad_norm": 1.9120333194732666, "learning_rate": 9.278597835743353e-06, "loss": 3.6069, "step": 13316 }, { "epoch": 0.7165841584158416, "grad_norm": 1.736727237701416, "learning_rate": 9.27531209327697e-06, "loss": 4.3084, "step": 13317 }, { "epoch": 0.7166379681446405, "grad_norm": 2.024343967437744, "learning_rate": 9.272026800179865e-06, "loss": 4.375, "step": 13318 }, { "epoch": 0.7166917778734395, "grad_norm": 2.4040489196777344, "learning_rate": 9.26874195654592e-06, "loss": 4.165, "step": 13319 }, { "epoch": 0.7167455876022385, "grad_norm": 2.6407113075256348, "learning_rate": 9.265457562469027e-06, "loss": 3.41, "step": 13320 }, { "epoch": 0.7167993973310375, "grad_norm": 2.771589756011963, "learning_rate": 9.262173618043038e-06, "loss": 3.5236, "step": 13321 }, { "epoch": 0.7168532070598365, "grad_norm": 2.6946959495544434, "learning_rate": 9.258890123361797e-06, "loss": 3.0107, "step": 13322 }, { "epoch": 0.7169070167886353, "grad_norm": 2.778688430786133, "learning_rate": 9.255607078519135e-06, "loss": 4.0912, "step": 13323 }, { "epoch": 0.7169608265174343, "grad_norm": 3.119375467300415, "learning_rate": 9.252324483608876e-06, "loss": 3.3932, "step": 13324 }, { "epoch": 0.7170146362462333, "grad_norm": 2.9615061283111572, "learning_rate": 9.24904233872483e-06, "loss": 4.1114, "step": 13325 }, { "epoch": 0.7170684459750323, "grad_norm": 3.3019399642944336, "learning_rate": 9.245760643960785e-06, "loss": 2.9347, "step": 13326 }, { "epoch": 0.7171222557038313, "grad_norm": 3.293597459793091, "learning_rate": 9.24247939941053e-06, "loss": 3.245, "step": 13327 }, { "epoch": 0.7171760654326302, "grad_norm": 4.355595588684082, "learning_rate": 9.239198605167828e-06, "loss": 3.3714, "step": 13328 }, { "epoch": 0.7172298751614292, "grad_norm": 2.348212718963623, "learning_rate": 9.235918261326434e-06, "loss": 4.2967, "step": 13329 }, { "epoch": 0.7172836848902282, "grad_norm": 1.5299159288406372, "learning_rate": 9.2326383679801e-06, "loss": 4.3112, "step": 13330 }, { "epoch": 0.7173374946190271, "grad_norm": 2.4902756214141846, "learning_rate": 9.229358925222555e-06, "loss": 3.8223, "step": 13331 }, { "epoch": 0.717391304347826, "grad_norm": 2.5000874996185303, "learning_rate": 9.226079933147521e-06, "loss": 3.7641, "step": 13332 }, { "epoch": 0.717445114076625, "grad_norm": 3.0526602268218994, "learning_rate": 9.222801391848687e-06, "loss": 3.3705, "step": 13333 }, { "epoch": 0.717498923805424, "grad_norm": 0.984521210193634, "learning_rate": 9.219523301419747e-06, "loss": 4.2661, "step": 13334 }, { "epoch": 0.717552733534223, "grad_norm": 2.6453473567962646, "learning_rate": 9.216245661954393e-06, "loss": 3.8492, "step": 13335 }, { "epoch": 0.717606543263022, "grad_norm": 3.063183307647705, "learning_rate": 9.212968473546285e-06, "loss": 3.2152, "step": 13336 }, { "epoch": 0.717660352991821, "grad_norm": 3.0083727836608887, "learning_rate": 9.209691736289074e-06, "loss": 4.1304, "step": 13337 }, { "epoch": 0.7177141627206199, "grad_norm": 2.1842823028564453, "learning_rate": 9.206415450276406e-06, "loss": 4.2551, "step": 13338 }, { "epoch": 0.7177679724494188, "grad_norm": 3.3579254150390625, "learning_rate": 9.203139615601904e-06, "loss": 3.257, "step": 13339 }, { "epoch": 0.7178217821782178, "grad_norm": 1.7759283781051636, "learning_rate": 9.199864232359182e-06, "loss": 3.3496, "step": 13340 }, { "epoch": 0.7178755919070168, "grad_norm": 3.394615888595581, "learning_rate": 9.196589300641842e-06, "loss": 3.2928, "step": 13341 }, { "epoch": 0.7179294016358158, "grad_norm": 6.861231803894043, "learning_rate": 9.193314820543475e-06, "loss": 3.5596, "step": 13342 }, { "epoch": 0.7179832113646147, "grad_norm": 3.6826930046081543, "learning_rate": 9.190040792157656e-06, "loss": 4.3644, "step": 13343 }, { "epoch": 0.7180370210934137, "grad_norm": 3.7308273315429688, "learning_rate": 9.186767215577947e-06, "loss": 3.6817, "step": 13344 }, { "epoch": 0.7180908308222127, "grad_norm": 2.569465398788452, "learning_rate": 9.18349409089789e-06, "loss": 3.3812, "step": 13345 }, { "epoch": 0.7181446405510116, "grad_norm": 3.007167339324951, "learning_rate": 9.180221418211038e-06, "loss": 2.6367, "step": 13346 }, { "epoch": 0.7181984502798106, "grad_norm": 1.895581841468811, "learning_rate": 9.176949197610916e-06, "loss": 3.9996, "step": 13347 }, { "epoch": 0.7182522600086095, "grad_norm": 4.352056980133057, "learning_rate": 9.173677429191019e-06, "loss": 4.0793, "step": 13348 }, { "epoch": 0.7183060697374085, "grad_norm": 3.965914487838745, "learning_rate": 9.170406113044852e-06, "loss": 3.3141, "step": 13349 }, { "epoch": 0.7183598794662075, "grad_norm": 1.9871553182601929, "learning_rate": 9.167135249265896e-06, "loss": 4.5785, "step": 13350 }, { "epoch": 0.7184136891950065, "grad_norm": 3.3055849075317383, "learning_rate": 9.163864837947637e-06, "loss": 3.7333, "step": 13351 }, { "epoch": 0.7184674989238055, "grad_norm": 2.4472439289093018, "learning_rate": 9.160594879183523e-06, "loss": 3.3565, "step": 13352 }, { "epoch": 0.7185213086526044, "grad_norm": 4.162193775177002, "learning_rate": 9.157325373067008e-06, "loss": 3.5517, "step": 13353 }, { "epoch": 0.7185751183814033, "grad_norm": 2.6575398445129395, "learning_rate": 9.154056319691523e-06, "loss": 3.4952, "step": 13354 }, { "epoch": 0.7186289281102023, "grad_norm": 1.3248659372329712, "learning_rate": 9.150787719150486e-06, "loss": 4.388, "step": 13355 }, { "epoch": 0.7186827378390013, "grad_norm": 2.2803573608398438, "learning_rate": 9.147519571537304e-06, "loss": 4.5216, "step": 13356 }, { "epoch": 0.7187365475678003, "grad_norm": 1.6027358770370483, "learning_rate": 9.144251876945378e-06, "loss": 4.0723, "step": 13357 }, { "epoch": 0.7187903572965992, "grad_norm": 4.280777454376221, "learning_rate": 9.140984635468085e-06, "loss": 3.6698, "step": 13358 }, { "epoch": 0.7188441670253982, "grad_norm": 2.008939027786255, "learning_rate": 9.137717847198798e-06, "loss": 3.9565, "step": 13359 }, { "epoch": 0.7188979767541972, "grad_norm": 3.158308744430542, "learning_rate": 9.13445151223086e-06, "loss": 3.7318, "step": 13360 }, { "epoch": 0.7189517864829962, "grad_norm": 2.055326223373413, "learning_rate": 9.131185630657633e-06, "loss": 4.4255, "step": 13361 }, { "epoch": 0.719005596211795, "grad_norm": 2.501269817352295, "learning_rate": 9.127920202572438e-06, "loss": 3.726, "step": 13362 }, { "epoch": 0.719059405940594, "grad_norm": 2.770653247833252, "learning_rate": 9.124655228068601e-06, "loss": 3.636, "step": 13363 }, { "epoch": 0.719113215669393, "grad_norm": 3.2043986320495605, "learning_rate": 9.12139070723941e-06, "loss": 4.1726, "step": 13364 }, { "epoch": 0.719167025398192, "grad_norm": 3.408872604370117, "learning_rate": 9.118126640178157e-06, "loss": 2.616, "step": 13365 }, { "epoch": 0.719220835126991, "grad_norm": 3.218606948852539, "learning_rate": 9.114863026978132e-06, "loss": 3.6046, "step": 13366 }, { "epoch": 0.71927464485579, "grad_norm": 3.651895761489868, "learning_rate": 9.111599867732598e-06, "loss": 3.5317, "step": 13367 }, { "epoch": 0.7193284545845889, "grad_norm": 1.808233380317688, "learning_rate": 9.108337162534804e-06, "loss": 4.6563, "step": 13368 }, { "epoch": 0.7193822643133878, "grad_norm": 2.644381046295166, "learning_rate": 9.105074911477995e-06, "loss": 3.96, "step": 13369 }, { "epoch": 0.7194360740421868, "grad_norm": 2.883998155593872, "learning_rate": 9.101813114655388e-06, "loss": 3.7091, "step": 13370 }, { "epoch": 0.7194898837709858, "grad_norm": 3.0104496479034424, "learning_rate": 9.098551772160202e-06, "loss": 2.9104, "step": 13371 }, { "epoch": 0.7195436934997848, "grad_norm": 1.394295573234558, "learning_rate": 9.09529088408564e-06, "loss": 4.3575, "step": 13372 }, { "epoch": 0.7195975032285837, "grad_norm": 3.1998252868652344, "learning_rate": 9.09203045052488e-06, "loss": 3.9995, "step": 13373 }, { "epoch": 0.7196513129573827, "grad_norm": 3.1066431999206543, "learning_rate": 9.088770471571107e-06, "loss": 3.9769, "step": 13374 }, { "epoch": 0.7197051226861817, "grad_norm": 3.381150722503662, "learning_rate": 9.085510947317474e-06, "loss": 4.191, "step": 13375 }, { "epoch": 0.7197589324149807, "grad_norm": 2.6955413818359375, "learning_rate": 9.082251877857125e-06, "loss": 3.828, "step": 13376 }, { "epoch": 0.7198127421437795, "grad_norm": 3.2696948051452637, "learning_rate": 9.078993263283214e-06, "loss": 4.0507, "step": 13377 }, { "epoch": 0.7198665518725785, "grad_norm": 2.5439164638519287, "learning_rate": 9.075735103688862e-06, "loss": 4.1402, "step": 13378 }, { "epoch": 0.7199203616013775, "grad_norm": 2.427612781524658, "learning_rate": 9.072477399167162e-06, "loss": 4.2449, "step": 13379 }, { "epoch": 0.7199741713301765, "grad_norm": 2.33389949798584, "learning_rate": 9.069220149811205e-06, "loss": 3.98, "step": 13380 }, { "epoch": 0.7200279810589755, "grad_norm": 3.0540964603424072, "learning_rate": 9.0659633557141e-06, "loss": 4.0156, "step": 13381 }, { "epoch": 0.7200817907877745, "grad_norm": 2.8403818607330322, "learning_rate": 9.062707016968902e-06, "loss": 4.0498, "step": 13382 }, { "epoch": 0.7201356005165734, "grad_norm": 3.6821963787078857, "learning_rate": 9.059451133668673e-06, "loss": 4.2845, "step": 13383 }, { "epoch": 0.7201894102453723, "grad_norm": 3.30181622505188, "learning_rate": 9.056195705906456e-06, "loss": 3.9328, "step": 13384 }, { "epoch": 0.7202432199741713, "grad_norm": 1.6946969032287598, "learning_rate": 9.052940733775281e-06, "loss": 4.3156, "step": 13385 }, { "epoch": 0.7202970297029703, "grad_norm": 2.6714487075805664, "learning_rate": 9.049686217368167e-06, "loss": 3.1371, "step": 13386 }, { "epoch": 0.7203508394317693, "grad_norm": 3.170461654663086, "learning_rate": 9.046432156778117e-06, "loss": 3.5081, "step": 13387 }, { "epoch": 0.7204046491605682, "grad_norm": 1.3293917179107666, "learning_rate": 9.04317855209813e-06, "loss": 4.2637, "step": 13388 }, { "epoch": 0.7204584588893672, "grad_norm": 1.5543485879898071, "learning_rate": 9.039925403421179e-06, "loss": 4.3592, "step": 13389 }, { "epoch": 0.7205122686181662, "grad_norm": 3.453977346420288, "learning_rate": 9.036672710840235e-06, "loss": 3.7673, "step": 13390 }, { "epoch": 0.7205660783469652, "grad_norm": 2.8045907020568848, "learning_rate": 9.033420474448236e-06, "loss": 3.3621, "step": 13391 }, { "epoch": 0.720619888075764, "grad_norm": 1.5427088737487793, "learning_rate": 9.030168694338148e-06, "loss": 4.3854, "step": 13392 }, { "epoch": 0.720673697804563, "grad_norm": 3.1689717769622803, "learning_rate": 9.026917370602891e-06, "loss": 3.1436, "step": 13393 }, { "epoch": 0.720727507533362, "grad_norm": 2.056720018386841, "learning_rate": 9.023666503335365e-06, "loss": 4.0888, "step": 13394 }, { "epoch": 0.720781317262161, "grad_norm": 2.257518768310547, "learning_rate": 9.020416092628479e-06, "loss": 4.0009, "step": 13395 }, { "epoch": 0.72083512699096, "grad_norm": 2.0881431102752686, "learning_rate": 9.017166138575111e-06, "loss": 3.8466, "step": 13396 }, { "epoch": 0.720888936719759, "grad_norm": 3.062697649002075, "learning_rate": 9.013916641268155e-06, "loss": 3.6284, "step": 13397 }, { "epoch": 0.7209427464485579, "grad_norm": 2.3868227005004883, "learning_rate": 9.010667600800466e-06, "loss": 4.4652, "step": 13398 }, { "epoch": 0.7209965561773569, "grad_norm": 2.6364552974700928, "learning_rate": 9.007419017264888e-06, "loss": 4.0529, "step": 13399 }, { "epoch": 0.7210503659061558, "grad_norm": 1.9177064895629883, "learning_rate": 9.00417089075426e-06, "loss": 4.0499, "step": 13400 }, { "epoch": 0.7211041756349548, "grad_norm": 2.0987040996551514, "learning_rate": 9.000923221361403e-06, "loss": 3.965, "step": 13401 }, { "epoch": 0.7211579853637538, "grad_norm": 2.2659478187561035, "learning_rate": 8.997676009179131e-06, "loss": 3.8478, "step": 13402 }, { "epoch": 0.7212117950925527, "grad_norm": 2.0043182373046875, "learning_rate": 8.994429254300237e-06, "loss": 3.63, "step": 13403 }, { "epoch": 0.7212656048213517, "grad_norm": 3.3695409297943115, "learning_rate": 8.991182956817505e-06, "loss": 3.2391, "step": 13404 }, { "epoch": 0.7213194145501507, "grad_norm": 3.891709327697754, "learning_rate": 8.987937116823706e-06, "loss": 4.1462, "step": 13405 }, { "epoch": 0.7213732242789497, "grad_norm": 3.0218067169189453, "learning_rate": 8.984691734411593e-06, "loss": 4.1125, "step": 13406 }, { "epoch": 0.7214270340077485, "grad_norm": 1.7730365991592407, "learning_rate": 8.98144680967391e-06, "loss": 4.3701, "step": 13407 }, { "epoch": 0.7214808437365475, "grad_norm": 2.3024230003356934, "learning_rate": 8.978202342703407e-06, "loss": 3.5156, "step": 13408 }, { "epoch": 0.7215346534653465, "grad_norm": 2.388272523880005, "learning_rate": 8.974958333592779e-06, "loss": 4.1247, "step": 13409 }, { "epoch": 0.7215884631941455, "grad_norm": 2.431943416595459, "learning_rate": 8.97171478243474e-06, "loss": 3.7976, "step": 13410 }, { "epoch": 0.7216422729229445, "grad_norm": 2.9547367095947266, "learning_rate": 8.968471689321972e-06, "loss": 4.0843, "step": 13411 }, { "epoch": 0.7216960826517435, "grad_norm": 2.9581868648529053, "learning_rate": 8.965229054347173e-06, "loss": 3.4358, "step": 13412 }, { "epoch": 0.7217498923805424, "grad_norm": 2.454967975616455, "learning_rate": 8.961986877602998e-06, "loss": 3.452, "step": 13413 }, { "epoch": 0.7218037021093414, "grad_norm": 2.713789463043213, "learning_rate": 8.958745159182103e-06, "loss": 3.9183, "step": 13414 }, { "epoch": 0.7218575118381403, "grad_norm": 1.9018279314041138, "learning_rate": 8.955503899177123e-06, "loss": 3.5413, "step": 13415 }, { "epoch": 0.7219113215669393, "grad_norm": 1.6142767667770386, "learning_rate": 8.952263097680688e-06, "loss": 3.8064, "step": 13416 }, { "epoch": 0.7219651312957382, "grad_norm": 3.7490131855010986, "learning_rate": 8.94902275478541e-06, "loss": 3.3524, "step": 13417 }, { "epoch": 0.7220189410245372, "grad_norm": 1.7917619943618774, "learning_rate": 8.945782870583891e-06, "loss": 4.274, "step": 13418 }, { "epoch": 0.7220727507533362, "grad_norm": 4.022303581237793, "learning_rate": 8.942543445168717e-06, "loss": 3.8676, "step": 13419 }, { "epoch": 0.7221265604821352, "grad_norm": 2.160456418991089, "learning_rate": 8.93930447863246e-06, "loss": 3.0574, "step": 13420 }, { "epoch": 0.7221803702109342, "grad_norm": 1.831155776977539, "learning_rate": 8.936065971067683e-06, "loss": 4.4157, "step": 13421 }, { "epoch": 0.7222341799397332, "grad_norm": 2.7585577964782715, "learning_rate": 8.932827922566928e-06, "loss": 4.0599, "step": 13422 }, { "epoch": 0.722287989668532, "grad_norm": 4.564176082611084, "learning_rate": 8.92959033322274e-06, "loss": 4.0219, "step": 13423 }, { "epoch": 0.722341799397331, "grad_norm": 2.00028133392334, "learning_rate": 8.926353203127647e-06, "loss": 4.2042, "step": 13424 }, { "epoch": 0.72239560912613, "grad_norm": 1.8109270334243774, "learning_rate": 8.923116532374137e-06, "loss": 3.9984, "step": 13425 }, { "epoch": 0.722449418854929, "grad_norm": 2.04807186126709, "learning_rate": 8.919880321054714e-06, "loss": 3.7634, "step": 13426 }, { "epoch": 0.722503228583728, "grad_norm": 2.0244317054748535, "learning_rate": 8.916644569261854e-06, "loss": 4.0912, "step": 13427 }, { "epoch": 0.7225570383125269, "grad_norm": 2.9243602752685547, "learning_rate": 8.91340927708804e-06, "loss": 4.0679, "step": 13428 }, { "epoch": 0.7226108480413259, "grad_norm": 2.109750270843506, "learning_rate": 8.910174444625721e-06, "loss": 4.0468, "step": 13429 }, { "epoch": 0.7226646577701248, "grad_norm": 1.9398839473724365, "learning_rate": 8.90694007196734e-06, "loss": 3.9658, "step": 13430 }, { "epoch": 0.7227184674989238, "grad_norm": 3.097515821456909, "learning_rate": 8.903706159205335e-06, "loss": 4.0807, "step": 13431 }, { "epoch": 0.7227722772277227, "grad_norm": 2.148200273513794, "learning_rate": 8.9004727064321e-06, "loss": 4.5702, "step": 13432 }, { "epoch": 0.7228260869565217, "grad_norm": 2.5055155754089355, "learning_rate": 8.897239713740058e-06, "loss": 3.8115, "step": 13433 }, { "epoch": 0.7228798966853207, "grad_norm": 1.8594353199005127, "learning_rate": 8.894007181221595e-06, "loss": 3.7098, "step": 13434 }, { "epoch": 0.7229337064141197, "grad_norm": 2.421212673187256, "learning_rate": 8.890775108969086e-06, "loss": 4.4735, "step": 13435 }, { "epoch": 0.7229875161429187, "grad_norm": 3.242743968963623, "learning_rate": 8.887543497074894e-06, "loss": 3.988, "step": 13436 }, { "epoch": 0.7230413258717177, "grad_norm": 2.0715553760528564, "learning_rate": 8.884312345631374e-06, "loss": 3.5709, "step": 13437 }, { "epoch": 0.7230951356005165, "grad_norm": 4.428123474121094, "learning_rate": 8.881081654730849e-06, "loss": 3.6886, "step": 13438 }, { "epoch": 0.7231489453293155, "grad_norm": 2.5357444286346436, "learning_rate": 8.877851424465677e-06, "loss": 4.043, "step": 13439 }, { "epoch": 0.7232027550581145, "grad_norm": 3.4133074283599854, "learning_rate": 8.874621654928137e-06, "loss": 3.1226, "step": 13440 }, { "epoch": 0.7232565647869135, "grad_norm": 2.890082597732544, "learning_rate": 8.871392346210539e-06, "loss": 4.2889, "step": 13441 }, { "epoch": 0.7233103745157125, "grad_norm": 3.5484936237335205, "learning_rate": 8.868163498405158e-06, "loss": 3.5749, "step": 13442 }, { "epoch": 0.7233641842445114, "grad_norm": 2.6071064472198486, "learning_rate": 8.864935111604281e-06, "loss": 3.1856, "step": 13443 }, { "epoch": 0.7234179939733104, "grad_norm": 3.3742167949676514, "learning_rate": 8.861707185900162e-06, "loss": 3.9112, "step": 13444 }, { "epoch": 0.7234718037021094, "grad_norm": 2.2119381427764893, "learning_rate": 8.858479721385046e-06, "loss": 4.2821, "step": 13445 }, { "epoch": 0.7235256134309083, "grad_norm": 3.55831241607666, "learning_rate": 8.855252718151164e-06, "loss": 3.4347, "step": 13446 }, { "epoch": 0.7235794231597072, "grad_norm": 2.1140456199645996, "learning_rate": 8.852026176290732e-06, "loss": 4.2084, "step": 13447 }, { "epoch": 0.7236332328885062, "grad_norm": 2.211561441421509, "learning_rate": 8.848800095895962e-06, "loss": 4.0577, "step": 13448 }, { "epoch": 0.7236870426173052, "grad_norm": 3.7013797760009766, "learning_rate": 8.84557447705904e-06, "loss": 3.7283, "step": 13449 }, { "epoch": 0.7237408523461042, "grad_norm": 1.9872187376022339, "learning_rate": 8.842349319872154e-06, "loss": 3.3996, "step": 13450 }, { "epoch": 0.7237946620749032, "grad_norm": 2.9428913593292236, "learning_rate": 8.839124624427461e-06, "loss": 4.1896, "step": 13451 }, { "epoch": 0.7238484718037022, "grad_norm": 3.9634807109832764, "learning_rate": 8.835900390817122e-06, "loss": 4.2466, "step": 13452 }, { "epoch": 0.723902281532501, "grad_norm": 1.5941826105117798, "learning_rate": 8.832676619133263e-06, "loss": 4.5041, "step": 13453 }, { "epoch": 0.7239560912613, "grad_norm": 2.7899351119995117, "learning_rate": 8.829453309468038e-06, "loss": 3.2128, "step": 13454 }, { "epoch": 0.724009900990099, "grad_norm": 2.362487554550171, "learning_rate": 8.826230461913537e-06, "loss": 4.0758, "step": 13455 }, { "epoch": 0.724063710718898, "grad_norm": 1.3814761638641357, "learning_rate": 8.823008076561867e-06, "loss": 4.5731, "step": 13456 }, { "epoch": 0.724117520447697, "grad_norm": 2.3115017414093018, "learning_rate": 8.819786153505113e-06, "loss": 3.994, "step": 13457 }, { "epoch": 0.7241713301764959, "grad_norm": 1.5318657159805298, "learning_rate": 8.816564692835344e-06, "loss": 4.4242, "step": 13458 }, { "epoch": 0.7242251399052949, "grad_norm": 2.9732589721679688, "learning_rate": 8.813343694644637e-06, "loss": 3.7422, "step": 13459 }, { "epoch": 0.7242789496340939, "grad_norm": 1.3886237144470215, "learning_rate": 8.81012315902503e-06, "loss": 3.9021, "step": 13460 }, { "epoch": 0.7243327593628928, "grad_norm": 3.5799851417541504, "learning_rate": 8.806903086068554e-06, "loss": 3.6051, "step": 13461 }, { "epoch": 0.7243865690916917, "grad_norm": 2.7552711963653564, "learning_rate": 8.803683475867247e-06, "loss": 4.1658, "step": 13462 }, { "epoch": 0.7244403788204907, "grad_norm": 2.6454150676727295, "learning_rate": 8.800464328513083e-06, "loss": 4.4132, "step": 13463 }, { "epoch": 0.7244941885492897, "grad_norm": 3.7677886486053467, "learning_rate": 8.797245644098087e-06, "loss": 4.1659, "step": 13464 }, { "epoch": 0.7245479982780887, "grad_norm": 4.118010997772217, "learning_rate": 8.79402742271423e-06, "loss": 3.9444, "step": 13465 }, { "epoch": 0.7246018080068877, "grad_norm": 2.2155685424804688, "learning_rate": 8.790809664453481e-06, "loss": 3.4461, "step": 13466 }, { "epoch": 0.7246556177356867, "grad_norm": 2.9365413188934326, "learning_rate": 8.787592369407794e-06, "loss": 3.8335, "step": 13467 }, { "epoch": 0.7247094274644856, "grad_norm": 2.319316864013672, "learning_rate": 8.784375537669107e-06, "loss": 4.3881, "step": 13468 }, { "epoch": 0.7247632371932845, "grad_norm": 2.5398311614990234, "learning_rate": 8.781159169329348e-06, "loss": 3.6258, "step": 13469 }, { "epoch": 0.7248170469220835, "grad_norm": 1.9618427753448486, "learning_rate": 8.777943264480451e-06, "loss": 3.9262, "step": 13470 }, { "epoch": 0.7248708566508825, "grad_norm": 3.3179919719696045, "learning_rate": 8.774727823214296e-06, "loss": 3.7023, "step": 13471 }, { "epoch": 0.7249246663796814, "grad_norm": 2.443721055984497, "learning_rate": 8.771512845622778e-06, "loss": 3.7502, "step": 13472 }, { "epoch": 0.7249784761084804, "grad_norm": 2.6197478771209717, "learning_rate": 8.768298331797767e-06, "loss": 3.7974, "step": 13473 }, { "epoch": 0.7250322858372794, "grad_norm": 2.6189749240875244, "learning_rate": 8.76508428183114e-06, "loss": 3.9501, "step": 13474 }, { "epoch": 0.7250860955660784, "grad_norm": 3.456376314163208, "learning_rate": 8.761870695814736e-06, "loss": 3.7158, "step": 13475 }, { "epoch": 0.7251399052948773, "grad_norm": 3.2141761779785156, "learning_rate": 8.758657573840392e-06, "loss": 3.2785, "step": 13476 }, { "epoch": 0.7251937150236762, "grad_norm": 3.074709415435791, "learning_rate": 8.755444915999938e-06, "loss": 3.6887, "step": 13477 }, { "epoch": 0.7252475247524752, "grad_norm": 3.0552704334259033, "learning_rate": 8.75223272238516e-06, "loss": 3.9764, "step": 13478 }, { "epoch": 0.7253013344812742, "grad_norm": 4.292605400085449, "learning_rate": 8.749020993087879e-06, "loss": 4.2871, "step": 13479 }, { "epoch": 0.7253551442100732, "grad_norm": 2.20839786529541, "learning_rate": 8.745809728199866e-06, "loss": 4.1683, "step": 13480 }, { "epoch": 0.7254089539388722, "grad_norm": 2.4507763385772705, "learning_rate": 8.742598927812892e-06, "loss": 3.8256, "step": 13481 }, { "epoch": 0.7254627636676712, "grad_norm": 2.715064764022827, "learning_rate": 8.739388592018715e-06, "loss": 3.0898, "step": 13482 }, { "epoch": 0.7255165733964701, "grad_norm": 4.108097553253174, "learning_rate": 8.736178720909075e-06, "loss": 3.1886, "step": 13483 }, { "epoch": 0.725570383125269, "grad_norm": 3.1740427017211914, "learning_rate": 8.732969314575695e-06, "loss": 3.985, "step": 13484 }, { "epoch": 0.725624192854068, "grad_norm": 1.9217405319213867, "learning_rate": 8.729760373110315e-06, "loss": 3.736, "step": 13485 }, { "epoch": 0.725678002582867, "grad_norm": 2.7648203372955322, "learning_rate": 8.726551896604615e-06, "loss": 4.2704, "step": 13486 }, { "epoch": 0.725731812311666, "grad_norm": 3.014111280441284, "learning_rate": 8.72334388515029e-06, "loss": 3.8585, "step": 13487 }, { "epoch": 0.7257856220404649, "grad_norm": 2.975739002227783, "learning_rate": 8.720136338839017e-06, "loss": 3.6992, "step": 13488 }, { "epoch": 0.7258394317692639, "grad_norm": 1.1170928478240967, "learning_rate": 8.716929257762452e-06, "loss": 4.6777, "step": 13489 }, { "epoch": 0.7258932414980629, "grad_norm": 3.121880531311035, "learning_rate": 8.713722642012262e-06, "loss": 3.4554, "step": 13490 }, { "epoch": 0.7259470512268618, "grad_norm": 2.433324098587036, "learning_rate": 8.710516491680074e-06, "loss": 4.7062, "step": 13491 }, { "epoch": 0.7260008609556607, "grad_norm": 3.11425518989563, "learning_rate": 8.707310806857517e-06, "loss": 4.0919, "step": 13492 }, { "epoch": 0.7260546706844597, "grad_norm": 3.520075559616089, "learning_rate": 8.704105587636189e-06, "loss": 3.7565, "step": 13493 }, { "epoch": 0.7261084804132587, "grad_norm": 3.412686347961426, "learning_rate": 8.70090083410768e-06, "loss": 3.3346, "step": 13494 }, { "epoch": 0.7261622901420577, "grad_norm": 2.5754175186157227, "learning_rate": 8.697696546363599e-06, "loss": 4.1888, "step": 13495 }, { "epoch": 0.7262160998708567, "grad_norm": 3.132514238357544, "learning_rate": 8.6944927244955e-06, "loss": 3.2569, "step": 13496 }, { "epoch": 0.7262699095996556, "grad_norm": 2.5388975143432617, "learning_rate": 8.691289368594946e-06, "loss": 4.1735, "step": 13497 }, { "epoch": 0.7263237193284546, "grad_norm": 2.4987058639526367, "learning_rate": 8.688086478753472e-06, "loss": 4.2313, "step": 13498 }, { "epoch": 0.7263775290572535, "grad_norm": 2.3346073627471924, "learning_rate": 8.684884055062613e-06, "loss": 3.8013, "step": 13499 }, { "epoch": 0.7264313387860525, "grad_norm": 2.2118079662323, "learning_rate": 8.681682097613889e-06, "loss": 3.6382, "step": 13500 }, { "epoch": 0.7264851485148515, "grad_norm": 3.3867928981781006, "learning_rate": 8.678480606498796e-06, "loss": 3.3048, "step": 13501 }, { "epoch": 0.7265389582436504, "grad_norm": 2.6452603340148926, "learning_rate": 8.67527958180883e-06, "loss": 2.9891, "step": 13502 }, { "epoch": 0.7265927679724494, "grad_norm": 2.8971433639526367, "learning_rate": 8.672079023635462e-06, "loss": 2.9392, "step": 13503 }, { "epoch": 0.7266465777012484, "grad_norm": 1.957604169845581, "learning_rate": 8.668878932070152e-06, "loss": 3.8465, "step": 13504 }, { "epoch": 0.7267003874300474, "grad_norm": 2.172508716583252, "learning_rate": 8.665679307204366e-06, "loss": 3.54, "step": 13505 }, { "epoch": 0.7267541971588464, "grad_norm": 1.7159255743026733, "learning_rate": 8.66248014912953e-06, "loss": 4.3412, "step": 13506 }, { "epoch": 0.7268080068876452, "grad_norm": 2.309908151626587, "learning_rate": 8.659281457937069e-06, "loss": 4.2276, "step": 13507 }, { "epoch": 0.7268618166164442, "grad_norm": 4.200987339019775, "learning_rate": 8.656083233718401e-06, "loss": 4.0835, "step": 13508 }, { "epoch": 0.7269156263452432, "grad_norm": 2.0436768531799316, "learning_rate": 8.652885476564896e-06, "loss": 4.1091, "step": 13509 }, { "epoch": 0.7269694360740422, "grad_norm": 1.977569341659546, "learning_rate": 8.649688186567965e-06, "loss": 4.4597, "step": 13510 }, { "epoch": 0.7270232458028412, "grad_norm": 3.562208890914917, "learning_rate": 8.646491363818968e-06, "loss": 3.8373, "step": 13511 }, { "epoch": 0.7270770555316401, "grad_norm": 3.321582317352295, "learning_rate": 8.643295008409264e-06, "loss": 3.6151, "step": 13512 }, { "epoch": 0.7271308652604391, "grad_norm": 1.6910871267318726, "learning_rate": 8.640099120430192e-06, "loss": 4.2181, "step": 13513 }, { "epoch": 0.727184674989238, "grad_norm": 1.9835907220840454, "learning_rate": 8.636903699973084e-06, "loss": 3.6781, "step": 13514 }, { "epoch": 0.727238484718037, "grad_norm": 1.9410886764526367, "learning_rate": 8.633708747129257e-06, "loss": 4.041, "step": 13515 }, { "epoch": 0.727292294446836, "grad_norm": 3.860377550125122, "learning_rate": 8.630514261990016e-06, "loss": 4.1004, "step": 13516 }, { "epoch": 0.7273461041756349, "grad_norm": 2.785665988922119, "learning_rate": 8.627320244646647e-06, "loss": 4.1509, "step": 13517 }, { "epoch": 0.7273999139044339, "grad_norm": 1.8678327798843384, "learning_rate": 8.62412669519043e-06, "loss": 4.2344, "step": 13518 }, { "epoch": 0.7274537236332329, "grad_norm": 2.9574053287506104, "learning_rate": 8.620933613712622e-06, "loss": 2.8541, "step": 13519 }, { "epoch": 0.7275075333620319, "grad_norm": 3.3794755935668945, "learning_rate": 8.617741000304472e-06, "loss": 4.2675, "step": 13520 }, { "epoch": 0.7275613430908309, "grad_norm": 1.8943418264389038, "learning_rate": 8.614548855057227e-06, "loss": 4.3459, "step": 13521 }, { "epoch": 0.7276151528196297, "grad_norm": 2.9171066284179688, "learning_rate": 8.611357178062105e-06, "loss": 3.1556, "step": 13522 }, { "epoch": 0.7276689625484287, "grad_norm": 2.6453449726104736, "learning_rate": 8.608165969410324e-06, "loss": 3.8045, "step": 13523 }, { "epoch": 0.7277227722772277, "grad_norm": 1.4893110990524292, "learning_rate": 8.60497522919306e-06, "loss": 4.2141, "step": 13524 }, { "epoch": 0.7277765820060267, "grad_norm": 3.7448840141296387, "learning_rate": 8.601784957501503e-06, "loss": 3.6158, "step": 13525 }, { "epoch": 0.7278303917348257, "grad_norm": 2.494849920272827, "learning_rate": 8.598595154426831e-06, "loss": 3.5154, "step": 13526 }, { "epoch": 0.7278842014636246, "grad_norm": 2.590533494949341, "learning_rate": 8.595405820060192e-06, "loss": 4.0836, "step": 13527 }, { "epoch": 0.7279380111924236, "grad_norm": 1.7511405944824219, "learning_rate": 8.592216954492735e-06, "loss": 4.4244, "step": 13528 }, { "epoch": 0.7279918209212226, "grad_norm": 2.245624303817749, "learning_rate": 8.589028557815584e-06, "loss": 4.1459, "step": 13529 }, { "epoch": 0.7280456306500215, "grad_norm": 2.9178643226623535, "learning_rate": 8.585840630119859e-06, "loss": 3.7704, "step": 13530 }, { "epoch": 0.7280994403788205, "grad_norm": 3.0244388580322266, "learning_rate": 8.582653171496657e-06, "loss": 3.8964, "step": 13531 }, { "epoch": 0.7281532501076194, "grad_norm": 1.298769235610962, "learning_rate": 8.579466182037074e-06, "loss": 4.3386, "step": 13532 }, { "epoch": 0.7282070598364184, "grad_norm": 2.320974111557007, "learning_rate": 8.576279661832179e-06, "loss": 3.6308, "step": 13533 }, { "epoch": 0.7282608695652174, "grad_norm": 2.2939956188201904, "learning_rate": 8.573093610973035e-06, "loss": 3.6312, "step": 13534 }, { "epoch": 0.7283146792940164, "grad_norm": 3.2634878158569336, "learning_rate": 8.569908029550685e-06, "loss": 4.0333, "step": 13535 }, { "epoch": 0.7283684890228154, "grad_norm": 2.373157501220703, "learning_rate": 8.566722917656182e-06, "loss": 4.3056, "step": 13536 }, { "epoch": 0.7284222987516142, "grad_norm": 2.5921218395233154, "learning_rate": 8.563538275380536e-06, "loss": 2.9218, "step": 13537 }, { "epoch": 0.7284761084804132, "grad_norm": 1.5574891567230225, "learning_rate": 8.560354102814766e-06, "loss": 4.2024, "step": 13538 }, { "epoch": 0.7285299182092122, "grad_norm": 3.3604776859283447, "learning_rate": 8.557170400049849e-06, "loss": 4.2458, "step": 13539 }, { "epoch": 0.7285837279380112, "grad_norm": 2.5334017276763916, "learning_rate": 8.55398716717677e-06, "loss": 4.1702, "step": 13540 }, { "epoch": 0.7286375376668102, "grad_norm": 3.3031740188598633, "learning_rate": 8.550804404286509e-06, "loss": 3.5618, "step": 13541 }, { "epoch": 0.7286913473956091, "grad_norm": 3.895531177520752, "learning_rate": 8.547622111470016e-06, "loss": 3.4736, "step": 13542 }, { "epoch": 0.7287451571244081, "grad_norm": 3.7478644847869873, "learning_rate": 8.544440288818232e-06, "loss": 3.1247, "step": 13543 }, { "epoch": 0.7287989668532071, "grad_norm": 2.150205373764038, "learning_rate": 8.541258936422083e-06, "loss": 4.137, "step": 13544 }, { "epoch": 0.728852776582006, "grad_norm": 3.753051996231079, "learning_rate": 8.538078054372483e-06, "loss": 3.9095, "step": 13545 }, { "epoch": 0.728906586310805, "grad_norm": 1.9002193212509155, "learning_rate": 8.534897642760339e-06, "loss": 4.0494, "step": 13546 }, { "epoch": 0.7289603960396039, "grad_norm": 3.5060064792633057, "learning_rate": 8.531717701676533e-06, "loss": 3.4983, "step": 13547 }, { "epoch": 0.7290142057684029, "grad_norm": 2.3726072311401367, "learning_rate": 8.528538231211941e-06, "loss": 4.0271, "step": 13548 }, { "epoch": 0.7290680154972019, "grad_norm": 3.6927731037139893, "learning_rate": 8.525359231457422e-06, "loss": 4.2955, "step": 13549 }, { "epoch": 0.7291218252260009, "grad_norm": 3.483139991760254, "learning_rate": 8.522180702503824e-06, "loss": 4.0761, "step": 13550 }, { "epoch": 0.7291756349547999, "grad_norm": 2.801462173461914, "learning_rate": 8.519002644441975e-06, "loss": 3.6217, "step": 13551 }, { "epoch": 0.7292294446835988, "grad_norm": 1.5007743835449219, "learning_rate": 8.515825057362708e-06, "loss": 4.3535, "step": 13552 }, { "epoch": 0.7292832544123977, "grad_norm": 2.2901394367218018, "learning_rate": 8.512647941356828e-06, "loss": 4.4998, "step": 13553 }, { "epoch": 0.7293370641411967, "grad_norm": 1.9646122455596924, "learning_rate": 8.509471296515128e-06, "loss": 3.7943, "step": 13554 }, { "epoch": 0.7293908738699957, "grad_norm": 1.366400957107544, "learning_rate": 8.506295122928369e-06, "loss": 3.7465, "step": 13555 }, { "epoch": 0.7294446835987947, "grad_norm": 2.6471128463745117, "learning_rate": 8.503119420687338e-06, "loss": 3.8161, "step": 13556 }, { "epoch": 0.7294984933275936, "grad_norm": 2.8240864276885986, "learning_rate": 8.499944189882786e-06, "loss": 4.1006, "step": 13557 }, { "epoch": 0.7295523030563926, "grad_norm": 3.3538880348205566, "learning_rate": 8.49676943060545e-06, "loss": 4.2827, "step": 13558 }, { "epoch": 0.7296061127851916, "grad_norm": 2.7555527687072754, "learning_rate": 8.493595142946053e-06, "loss": 3.2538, "step": 13559 }, { "epoch": 0.7296599225139905, "grad_norm": 2.004957437515259, "learning_rate": 8.49042132699531e-06, "loss": 4.108, "step": 13560 }, { "epoch": 0.7297137322427895, "grad_norm": 2.941053867340088, "learning_rate": 8.48724798284392e-06, "loss": 4.0179, "step": 13561 }, { "epoch": 0.7297675419715884, "grad_norm": 2.8799099922180176, "learning_rate": 8.484075110582568e-06, "loss": 3.6255, "step": 13562 }, { "epoch": 0.7298213517003874, "grad_norm": 3.3193132877349854, "learning_rate": 8.480902710301927e-06, "loss": 4.0083, "step": 13563 }, { "epoch": 0.7298751614291864, "grad_norm": 2.2772884368896484, "learning_rate": 8.477730782092658e-06, "loss": 3.826, "step": 13564 }, { "epoch": 0.7299289711579854, "grad_norm": 2.360393524169922, "learning_rate": 8.4745593260454e-06, "loss": 4.0146, "step": 13565 }, { "epoch": 0.7299827808867844, "grad_norm": 2.330256938934326, "learning_rate": 8.47138834225078e-06, "loss": 3.8843, "step": 13566 }, { "epoch": 0.7300365906155833, "grad_norm": 1.4816442728042603, "learning_rate": 8.468217830799435e-06, "loss": 4.5046, "step": 13567 }, { "epoch": 0.7300904003443822, "grad_norm": 1.4988816976547241, "learning_rate": 8.465047791781957e-06, "loss": 4.1323, "step": 13568 }, { "epoch": 0.7301442100731812, "grad_norm": 2.8271803855895996, "learning_rate": 8.461878225288949e-06, "loss": 3.271, "step": 13569 }, { "epoch": 0.7301980198019802, "grad_norm": 1.9442580938339233, "learning_rate": 8.458709131410972e-06, "loss": 4.2289, "step": 13570 }, { "epoch": 0.7302518295307792, "grad_norm": 5.070646286010742, "learning_rate": 8.455540510238588e-06, "loss": 3.2857, "step": 13571 }, { "epoch": 0.7303056392595781, "grad_norm": 4.949620723724365, "learning_rate": 8.452372361862366e-06, "loss": 3.6573, "step": 13572 }, { "epoch": 0.7303594489883771, "grad_norm": 3.671846866607666, "learning_rate": 8.44920468637283e-06, "loss": 2.5808, "step": 13573 }, { "epoch": 0.7304132587171761, "grad_norm": 2.9608395099639893, "learning_rate": 8.446037483860512e-06, "loss": 3.3523, "step": 13574 }, { "epoch": 0.7304670684459751, "grad_norm": 1.581248164176941, "learning_rate": 8.442870754415917e-06, "loss": 4.3485, "step": 13575 }, { "epoch": 0.730520878174774, "grad_norm": 1.8362147808074951, "learning_rate": 8.439704498129538e-06, "loss": 4.037, "step": 13576 }, { "epoch": 0.7305746879035729, "grad_norm": 3.373004198074341, "learning_rate": 8.436538715091865e-06, "loss": 4.1528, "step": 13577 }, { "epoch": 0.7306284976323719, "grad_norm": 2.286632537841797, "learning_rate": 8.43337340539337e-06, "loss": 4.2735, "step": 13578 }, { "epoch": 0.7306823073611709, "grad_norm": 1.4967162609100342, "learning_rate": 8.430208569124498e-06, "loss": 4.8404, "step": 13579 }, { "epoch": 0.7307361170899699, "grad_norm": 1.730178952217102, "learning_rate": 8.427044206375701e-06, "loss": 4.4244, "step": 13580 }, { "epoch": 0.7307899268187689, "grad_norm": 2.0083582401275635, "learning_rate": 8.423880317237401e-06, "loss": 3.5864, "step": 13581 }, { "epoch": 0.7308437365475678, "grad_norm": 2.990293502807617, "learning_rate": 8.42071690180001e-06, "loss": 3.6113, "step": 13582 }, { "epoch": 0.7308975462763667, "grad_norm": 1.706446886062622, "learning_rate": 8.417553960153949e-06, "loss": 4.8278, "step": 13583 }, { "epoch": 0.7309513560051657, "grad_norm": 2.773912191390991, "learning_rate": 8.414391492389597e-06, "loss": 4.2552, "step": 13584 }, { "epoch": 0.7310051657339647, "grad_norm": 3.390218734741211, "learning_rate": 8.41122949859732e-06, "loss": 3.2901, "step": 13585 }, { "epoch": 0.7310589754627637, "grad_norm": 2.6280429363250732, "learning_rate": 8.40806797886748e-06, "loss": 3.8945, "step": 13586 }, { "epoch": 0.7311127851915626, "grad_norm": 2.5166757106781006, "learning_rate": 8.404906933290435e-06, "loss": 4.2767, "step": 13587 }, { "epoch": 0.7311665949203616, "grad_norm": 2.5901896953582764, "learning_rate": 8.401746361956515e-06, "loss": 3.5782, "step": 13588 }, { "epoch": 0.7312204046491606, "grad_norm": 3.211367607116699, "learning_rate": 8.39858626495604e-06, "loss": 3.2856, "step": 13589 }, { "epoch": 0.7312742143779596, "grad_norm": 2.7451162338256836, "learning_rate": 8.395426642379317e-06, "loss": 3.8846, "step": 13590 }, { "epoch": 0.7313280241067585, "grad_norm": 2.262037754058838, "learning_rate": 8.392267494316638e-06, "loss": 3.8308, "step": 13591 }, { "epoch": 0.7313818338355574, "grad_norm": 1.9799277782440186, "learning_rate": 8.389108820858288e-06, "loss": 3.8177, "step": 13592 }, { "epoch": 0.7314356435643564, "grad_norm": 2.897873878479004, "learning_rate": 8.385950622094526e-06, "loss": 3.0752, "step": 13593 }, { "epoch": 0.7314894532931554, "grad_norm": 2.5278894901275635, "learning_rate": 8.382792898115612e-06, "loss": 3.7568, "step": 13594 }, { "epoch": 0.7315432630219544, "grad_norm": 1.6023770570755005, "learning_rate": 8.37963564901178e-06, "loss": 4.463, "step": 13595 }, { "epoch": 0.7315970727507534, "grad_norm": 3.2139298915863037, "learning_rate": 8.376478874873258e-06, "loss": 3.1975, "step": 13596 }, { "epoch": 0.7316508824795523, "grad_norm": 2.5077638626098633, "learning_rate": 8.373322575790251e-06, "loss": 4.1138, "step": 13597 }, { "epoch": 0.7317046922083512, "grad_norm": 3.2992496490478516, "learning_rate": 8.37016675185297e-06, "loss": 3.025, "step": 13598 }, { "epoch": 0.7317585019371502, "grad_norm": 2.5381901264190674, "learning_rate": 8.367011403151604e-06, "loss": 3.0685, "step": 13599 }, { "epoch": 0.7318123116659492, "grad_norm": 2.682588577270508, "learning_rate": 8.363856529776307e-06, "loss": 4.5834, "step": 13600 }, { "epoch": 0.7318661213947482, "grad_norm": 2.851457118988037, "learning_rate": 8.36070213181724e-06, "loss": 4.0297, "step": 13601 }, { "epoch": 0.7319199311235471, "grad_norm": 1.3567163944244385, "learning_rate": 8.35754820936455e-06, "loss": 4.0134, "step": 13602 }, { "epoch": 0.7319737408523461, "grad_norm": 2.644519090652466, "learning_rate": 8.354394762508374e-06, "loss": 4.0831, "step": 13603 }, { "epoch": 0.7320275505811451, "grad_norm": 2.103055715560913, "learning_rate": 8.351241791338823e-06, "loss": 4.2359, "step": 13604 }, { "epoch": 0.7320813603099441, "grad_norm": 4.840423583984375, "learning_rate": 8.348089295946004e-06, "loss": 3.5543, "step": 13605 }, { "epoch": 0.732135170038743, "grad_norm": 2.6490464210510254, "learning_rate": 8.344937276420003e-06, "loss": 4.133, "step": 13606 }, { "epoch": 0.7321889797675419, "grad_norm": 1.9555820226669312, "learning_rate": 8.341785732850898e-06, "loss": 4.1391, "step": 13607 }, { "epoch": 0.7322427894963409, "grad_norm": 1.7269089221954346, "learning_rate": 8.338634665328754e-06, "loss": 3.7608, "step": 13608 }, { "epoch": 0.7322965992251399, "grad_norm": 1.5270451307296753, "learning_rate": 8.335484073943614e-06, "loss": 4.4513, "step": 13609 }, { "epoch": 0.7323504089539389, "grad_norm": 4.253779888153076, "learning_rate": 8.332333958785518e-06, "loss": 4.1566, "step": 13610 }, { "epoch": 0.7324042186827379, "grad_norm": 2.50805926322937, "learning_rate": 8.32918431994449e-06, "loss": 3.9393, "step": 13611 }, { "epoch": 0.7324580284115368, "grad_norm": 3.8548216819763184, "learning_rate": 8.32603515751053e-06, "loss": 3.6018, "step": 13612 }, { "epoch": 0.7325118381403358, "grad_norm": 1.3534212112426758, "learning_rate": 8.322886471573633e-06, "loss": 4.1877, "step": 13613 }, { "epoch": 0.7325656478691347, "grad_norm": 2.8494420051574707, "learning_rate": 8.319738262223789e-06, "loss": 3.1121, "step": 13614 }, { "epoch": 0.7326194575979337, "grad_norm": 1.737712025642395, "learning_rate": 8.316590529550972e-06, "loss": 4.3402, "step": 13615 }, { "epoch": 0.7326732673267327, "grad_norm": 2.645698070526123, "learning_rate": 8.313443273645113e-06, "loss": 4.2875, "step": 13616 }, { "epoch": 0.7327270770555316, "grad_norm": 1.4310153722763062, "learning_rate": 8.31029649459616e-06, "loss": 4.6482, "step": 13617 }, { "epoch": 0.7327808867843306, "grad_norm": 2.6036245822906494, "learning_rate": 8.307150192494048e-06, "loss": 3.6284, "step": 13618 }, { "epoch": 0.7328346965131296, "grad_norm": 2.5107626914978027, "learning_rate": 8.304004367428686e-06, "loss": 4.5577, "step": 13619 }, { "epoch": 0.7328885062419286, "grad_norm": 4.089131832122803, "learning_rate": 8.300859019489974e-06, "loss": 3.241, "step": 13620 }, { "epoch": 0.7329423159707275, "grad_norm": 1.4926429986953735, "learning_rate": 8.297714148767793e-06, "loss": 4.4185, "step": 13621 }, { "epoch": 0.7329961256995264, "grad_norm": 1.4860947132110596, "learning_rate": 8.294569755352019e-06, "loss": 4.0558, "step": 13622 }, { "epoch": 0.7330499354283254, "grad_norm": 3.42824387550354, "learning_rate": 8.29142583933251e-06, "loss": 4.8323, "step": 13623 }, { "epoch": 0.7331037451571244, "grad_norm": 2.62058162689209, "learning_rate": 8.288282400799108e-06, "loss": 3.9302, "step": 13624 }, { "epoch": 0.7331575548859234, "grad_norm": 2.828191041946411, "learning_rate": 8.285139439841646e-06, "loss": 3.3565, "step": 13625 }, { "epoch": 0.7332113646147224, "grad_norm": 3.3823771476745605, "learning_rate": 8.281996956549942e-06, "loss": 4.3718, "step": 13626 }, { "epoch": 0.7332651743435213, "grad_norm": 3.049722671508789, "learning_rate": 8.278854951013798e-06, "loss": 4.1548, "step": 13627 }, { "epoch": 0.7333189840723203, "grad_norm": 2.9901039600372314, "learning_rate": 8.275713423322998e-06, "loss": 3.3787, "step": 13628 }, { "epoch": 0.7333727938011192, "grad_norm": 3.304784059524536, "learning_rate": 8.272572373567333e-06, "loss": 3.7374, "step": 13629 }, { "epoch": 0.7334266035299182, "grad_norm": 2.287358283996582, "learning_rate": 8.269431801836566e-06, "loss": 3.4968, "step": 13630 }, { "epoch": 0.7334804132587172, "grad_norm": 3.941211462020874, "learning_rate": 8.266291708220428e-06, "loss": 2.9332, "step": 13631 }, { "epoch": 0.7335342229875161, "grad_norm": 3.627769708633423, "learning_rate": 8.263152092808668e-06, "loss": 3.3208, "step": 13632 }, { "epoch": 0.7335880327163151, "grad_norm": 3.1697487831115723, "learning_rate": 8.260012955690993e-06, "loss": 3.7356, "step": 13633 }, { "epoch": 0.7336418424451141, "grad_norm": 2.2727928161621094, "learning_rate": 8.256874296957135e-06, "loss": 3.8572, "step": 13634 }, { "epoch": 0.7336956521739131, "grad_norm": 3.0894317626953125, "learning_rate": 8.253736116696773e-06, "loss": 3.9928, "step": 13635 }, { "epoch": 0.7337494619027121, "grad_norm": 2.2730674743652344, "learning_rate": 8.25059841499959e-06, "loss": 3.9815, "step": 13636 }, { "epoch": 0.7338032716315109, "grad_norm": 3.7031972408294678, "learning_rate": 8.247461191955252e-06, "loss": 3.4927, "step": 13637 }, { "epoch": 0.7338570813603099, "grad_norm": 3.3354969024658203, "learning_rate": 8.244324447653418e-06, "loss": 3.813, "step": 13638 }, { "epoch": 0.7339108910891089, "grad_norm": 2.073113441467285, "learning_rate": 8.241188182183723e-06, "loss": 4.3148, "step": 13639 }, { "epoch": 0.7339647008179079, "grad_norm": 2.004286527633667, "learning_rate": 8.238052395635793e-06, "loss": 3.95, "step": 13640 }, { "epoch": 0.7340185105467069, "grad_norm": 3.5445656776428223, "learning_rate": 8.234917088099242e-06, "loss": 3.5714, "step": 13641 }, { "epoch": 0.7340723202755058, "grad_norm": 3.1264240741729736, "learning_rate": 8.231782259663668e-06, "loss": 4.2219, "step": 13642 }, { "epoch": 0.7341261300043048, "grad_norm": 2.7590043544769287, "learning_rate": 8.228647910418652e-06, "loss": 4.0919, "step": 13643 }, { "epoch": 0.7341799397331037, "grad_norm": 3.4709372520446777, "learning_rate": 8.225514040453766e-06, "loss": 3.6734, "step": 13644 }, { "epoch": 0.7342337494619027, "grad_norm": 2.935220718383789, "learning_rate": 8.222380649858585e-06, "loss": 3.8617, "step": 13645 }, { "epoch": 0.7342875591907017, "grad_norm": 3.053117275238037, "learning_rate": 8.21924773872263e-06, "loss": 3.0569, "step": 13646 }, { "epoch": 0.7343413689195006, "grad_norm": 2.0889954566955566, "learning_rate": 8.216115307135438e-06, "loss": 4.1989, "step": 13647 }, { "epoch": 0.7343951786482996, "grad_norm": 2.4918487071990967, "learning_rate": 8.212983355186523e-06, "loss": 3.9246, "step": 13648 }, { "epoch": 0.7344489883770986, "grad_norm": 1.2659854888916016, "learning_rate": 8.209851882965396e-06, "loss": 4.3577, "step": 13649 }, { "epoch": 0.7345027981058976, "grad_norm": 2.8220479488372803, "learning_rate": 8.206720890561545e-06, "loss": 3.0367, "step": 13650 }, { "epoch": 0.7345566078346966, "grad_norm": 1.4661990404129028, "learning_rate": 8.203590378064443e-06, "loss": 3.6584, "step": 13651 }, { "epoch": 0.7346104175634954, "grad_norm": 1.840973973274231, "learning_rate": 8.200460345563548e-06, "loss": 4.6324, "step": 13652 }, { "epoch": 0.7346642272922944, "grad_norm": 2.3917009830474854, "learning_rate": 8.197330793148313e-06, "loss": 3.233, "step": 13653 }, { "epoch": 0.7347180370210934, "grad_norm": 3.3048715591430664, "learning_rate": 8.194201720908167e-06, "loss": 3.5031, "step": 13654 }, { "epoch": 0.7347718467498924, "grad_norm": 2.309846878051758, "learning_rate": 8.19107312893254e-06, "loss": 4.0908, "step": 13655 }, { "epoch": 0.7348256564786914, "grad_norm": 2.093418836593628, "learning_rate": 8.187945017310827e-06, "loss": 3.9439, "step": 13656 }, { "epoch": 0.7348794662074903, "grad_norm": 3.7372868061065674, "learning_rate": 8.184817386132427e-06, "loss": 2.887, "step": 13657 }, { "epoch": 0.7349332759362893, "grad_norm": 3.7000911235809326, "learning_rate": 8.181690235486719e-06, "loss": 3.5047, "step": 13658 }, { "epoch": 0.7349870856650883, "grad_norm": 2.7527363300323486, "learning_rate": 8.17856356546306e-06, "loss": 3.6671, "step": 13659 }, { "epoch": 0.7350408953938872, "grad_norm": 2.359504222869873, "learning_rate": 8.175437376150819e-06, "loss": 3.6352, "step": 13660 }, { "epoch": 0.7350947051226862, "grad_norm": 2.070805788040161, "learning_rate": 8.172311667639333e-06, "loss": 3.1163, "step": 13661 }, { "epoch": 0.7351485148514851, "grad_norm": 1.6183828115463257, "learning_rate": 8.169186440017907e-06, "loss": 4.1811, "step": 13662 }, { "epoch": 0.7352023245802841, "grad_norm": 1.7393842935562134, "learning_rate": 8.166061693375864e-06, "loss": 4.3641, "step": 13663 }, { "epoch": 0.7352561343090831, "grad_norm": 3.4536943435668945, "learning_rate": 8.162937427802495e-06, "loss": 4.0869, "step": 13664 }, { "epoch": 0.7353099440378821, "grad_norm": 1.5154420137405396, "learning_rate": 8.159813643387094e-06, "loss": 4.6139, "step": 13665 }, { "epoch": 0.7353637537666811, "grad_norm": 2.8662819862365723, "learning_rate": 8.156690340218925e-06, "loss": 3.5355, "step": 13666 }, { "epoch": 0.7354175634954799, "grad_norm": 1.6815366744995117, "learning_rate": 8.153567518387243e-06, "loss": 3.7747, "step": 13667 }, { "epoch": 0.7354713732242789, "grad_norm": 2.833526849746704, "learning_rate": 8.150445177981298e-06, "loss": 3.8516, "step": 13668 }, { "epoch": 0.7355251829530779, "grad_norm": 3.644307851791382, "learning_rate": 8.147323319090291e-06, "loss": 3.4064, "step": 13669 }, { "epoch": 0.7355789926818769, "grad_norm": 2.534862995147705, "learning_rate": 8.144201941803464e-06, "loss": 3.7478, "step": 13670 }, { "epoch": 0.7356328024106759, "grad_norm": 1.8478132486343384, "learning_rate": 8.141081046210012e-06, "loss": 4.2684, "step": 13671 }, { "epoch": 0.7356866121394748, "grad_norm": 2.074195146560669, "learning_rate": 8.137960632399116e-06, "loss": 3.5195, "step": 13672 }, { "epoch": 0.7357404218682738, "grad_norm": 1.5174099206924438, "learning_rate": 8.134840700459954e-06, "loss": 4.0968, "step": 13673 }, { "epoch": 0.7357942315970728, "grad_norm": 1.465917944908142, "learning_rate": 8.131721250481677e-06, "loss": 4.3274, "step": 13674 }, { "epoch": 0.7358480413258717, "grad_norm": 1.4571398496627808, "learning_rate": 8.128602282553433e-06, "loss": 4.1715, "step": 13675 }, { "epoch": 0.7359018510546707, "grad_norm": 2.846497058868408, "learning_rate": 8.125483796764371e-06, "loss": 3.5591, "step": 13676 }, { "epoch": 0.7359556607834696, "grad_norm": 1.3673666715621948, "learning_rate": 8.12236579320359e-06, "loss": 4.7204, "step": 13677 }, { "epoch": 0.7360094705122686, "grad_norm": 4.456234931945801, "learning_rate": 8.119248271960197e-06, "loss": 3.1882, "step": 13678 }, { "epoch": 0.7360632802410676, "grad_norm": 4.084557056427002, "learning_rate": 8.116131233123277e-06, "loss": 3.6219, "step": 13679 }, { "epoch": 0.7361170899698666, "grad_norm": 3.468367099761963, "learning_rate": 8.113014676781922e-06, "loss": 2.9242, "step": 13680 }, { "epoch": 0.7361708996986656, "grad_norm": 3.585068464279175, "learning_rate": 8.109898603025188e-06, "loss": 4.0787, "step": 13681 }, { "epoch": 0.7362247094274645, "grad_norm": 2.5175609588623047, "learning_rate": 8.106783011942121e-06, "loss": 4.1321, "step": 13682 }, { "epoch": 0.7362785191562634, "grad_norm": 2.0069987773895264, "learning_rate": 8.10366790362176e-06, "loss": 3.9866, "step": 13683 }, { "epoch": 0.7363323288850624, "grad_norm": 1.6618940830230713, "learning_rate": 8.100553278153119e-06, "loss": 4.6453, "step": 13684 }, { "epoch": 0.7363861386138614, "grad_norm": 1.7505075931549072, "learning_rate": 8.097439135625218e-06, "loss": 4.5152, "step": 13685 }, { "epoch": 0.7364399483426604, "grad_norm": 3.692487955093384, "learning_rate": 8.09432547612704e-06, "loss": 3.5276, "step": 13686 }, { "epoch": 0.7364937580714593, "grad_norm": 1.369100570678711, "learning_rate": 8.091212299747571e-06, "loss": 3.7608, "step": 13687 }, { "epoch": 0.7365475678002583, "grad_norm": 2.2318882942199707, "learning_rate": 8.088099606575774e-06, "loss": 4.537, "step": 13688 }, { "epoch": 0.7366013775290573, "grad_norm": 3.3939805030822754, "learning_rate": 8.084987396700602e-06, "loss": 3.4288, "step": 13689 }, { "epoch": 0.7366551872578562, "grad_norm": 2.5317368507385254, "learning_rate": 8.081875670210989e-06, "loss": 4.4539, "step": 13690 }, { "epoch": 0.7367089969866552, "grad_norm": 3.877938747406006, "learning_rate": 8.07876442719588e-06, "loss": 3.6558, "step": 13691 }, { "epoch": 0.7367628067154541, "grad_norm": 2.852834701538086, "learning_rate": 8.07565366774416e-06, "loss": 3.9361, "step": 13692 }, { "epoch": 0.7368166164442531, "grad_norm": 2.2383015155792236, "learning_rate": 8.072543391944739e-06, "loss": 3.5305, "step": 13693 }, { "epoch": 0.7368704261730521, "grad_norm": 4.333268642425537, "learning_rate": 8.0694335998865e-06, "loss": 3.2263, "step": 13694 }, { "epoch": 0.7369242359018511, "grad_norm": 2.285858631134033, "learning_rate": 8.0663242916583e-06, "loss": 3.4858, "step": 13695 }, { "epoch": 0.7369780456306501, "grad_norm": 1.5547711849212646, "learning_rate": 8.063215467349014e-06, "loss": 4.4929, "step": 13696 }, { "epoch": 0.737031855359449, "grad_norm": 1.1875698566436768, "learning_rate": 8.060107127047478e-06, "loss": 4.2282, "step": 13697 }, { "epoch": 0.7370856650882479, "grad_norm": 3.2128334045410156, "learning_rate": 8.056999270842513e-06, "loss": 3.3264, "step": 13698 }, { "epoch": 0.7371394748170469, "grad_norm": 2.77917218208313, "learning_rate": 8.053891898822949e-06, "loss": 4.3633, "step": 13699 }, { "epoch": 0.7371932845458459, "grad_norm": 2.6391053199768066, "learning_rate": 8.050785011077558e-06, "loss": 3.926, "step": 13700 }, { "epoch": 0.7372470942746449, "grad_norm": 1.229755163192749, "learning_rate": 8.047678607695152e-06, "loss": 4.4657, "step": 13701 }, { "epoch": 0.7373009040034438, "grad_norm": 4.421268939971924, "learning_rate": 8.044572688764493e-06, "loss": 3.1613, "step": 13702 }, { "epoch": 0.7373547137322428, "grad_norm": 2.278701066970825, "learning_rate": 8.041467254374344e-06, "loss": 3.947, "step": 13703 }, { "epoch": 0.7374085234610418, "grad_norm": 1.9966423511505127, "learning_rate": 8.038362304613448e-06, "loss": 4.1715, "step": 13704 }, { "epoch": 0.7374623331898407, "grad_norm": 2.1772139072418213, "learning_rate": 8.035257839570534e-06, "loss": 4.1707, "step": 13705 }, { "epoch": 0.7375161429186397, "grad_norm": 3.4709036350250244, "learning_rate": 8.032153859334321e-06, "loss": 3.0566, "step": 13706 }, { "epoch": 0.7375699526474386, "grad_norm": 1.4142638444900513, "learning_rate": 8.029050363993512e-06, "loss": 4.6144, "step": 13707 }, { "epoch": 0.7376237623762376, "grad_norm": 3.4766457080841064, "learning_rate": 8.0259473536368e-06, "loss": 3.4757, "step": 13708 }, { "epoch": 0.7376775721050366, "grad_norm": 3.1326847076416016, "learning_rate": 8.022844828352858e-06, "loss": 3.8217, "step": 13709 }, { "epoch": 0.7377313818338356, "grad_norm": 1.820715069770813, "learning_rate": 8.019742788230336e-06, "loss": 3.9762, "step": 13710 }, { "epoch": 0.7377851915626346, "grad_norm": 3.5731356143951416, "learning_rate": 8.016641233357901e-06, "loss": 3.8178, "step": 13711 }, { "epoch": 0.7378390012914335, "grad_norm": 3.0939390659332275, "learning_rate": 8.013540163824185e-06, "loss": 3.3105, "step": 13712 }, { "epoch": 0.7378928110202324, "grad_norm": 2.704159736633301, "learning_rate": 8.0104395797178e-06, "loss": 4.3079, "step": 13713 }, { "epoch": 0.7379466207490314, "grad_norm": 3.2599375247955322, "learning_rate": 8.007339481127362e-06, "loss": 3.6068, "step": 13714 }, { "epoch": 0.7380004304778304, "grad_norm": 3.237863779067993, "learning_rate": 8.004239868141442e-06, "loss": 3.4662, "step": 13715 }, { "epoch": 0.7380542402066294, "grad_norm": 3.417570114135742, "learning_rate": 8.001140740848643e-06, "loss": 3.7435, "step": 13716 }, { "epoch": 0.7381080499354283, "grad_norm": 1.7813564538955688, "learning_rate": 7.998042099337519e-06, "loss": 4.4019, "step": 13717 }, { "epoch": 0.7381618596642273, "grad_norm": 2.22330904006958, "learning_rate": 7.99494394369662e-06, "loss": 3.6915, "step": 13718 }, { "epoch": 0.7382156693930263, "grad_norm": 2.840322494506836, "learning_rate": 7.991846274014485e-06, "loss": 4.1152, "step": 13719 }, { "epoch": 0.7382694791218253, "grad_norm": 3.119473934173584, "learning_rate": 7.988749090379641e-06, "loss": 3.8044, "step": 13720 }, { "epoch": 0.7383232888506241, "grad_norm": 3.587977647781372, "learning_rate": 7.98565239288058e-06, "loss": 3.1153, "step": 13721 }, { "epoch": 0.7383770985794231, "grad_norm": 2.0944669246673584, "learning_rate": 7.982556181605829e-06, "loss": 3.9395, "step": 13722 }, { "epoch": 0.7384309083082221, "grad_norm": 3.021225929260254, "learning_rate": 7.979460456643842e-06, "loss": 3.6693, "step": 13723 }, { "epoch": 0.7384847180370211, "grad_norm": 2.314279794692993, "learning_rate": 7.976365218083096e-06, "loss": 2.7624, "step": 13724 }, { "epoch": 0.7385385277658201, "grad_norm": 2.8243749141693115, "learning_rate": 7.973270466012045e-06, "loss": 4.0431, "step": 13725 }, { "epoch": 0.7385923374946191, "grad_norm": 1.9882123470306396, "learning_rate": 7.970176200519117e-06, "loss": 3.9624, "step": 13726 }, { "epoch": 0.738646147223418, "grad_norm": 3.7195491790771484, "learning_rate": 7.967082421692757e-06, "loss": 3.3523, "step": 13727 }, { "epoch": 0.7386999569522169, "grad_norm": 3.741400957107544, "learning_rate": 7.963989129621369e-06, "loss": 3.6944, "step": 13728 }, { "epoch": 0.7387537666810159, "grad_norm": 2.3001022338867188, "learning_rate": 7.960896324393357e-06, "loss": 3.9763, "step": 13729 }, { "epoch": 0.7388075764098149, "grad_norm": 2.0874924659729004, "learning_rate": 7.957804006097092e-06, "loss": 4.1411, "step": 13730 }, { "epoch": 0.7388613861386139, "grad_norm": 2.069697380065918, "learning_rate": 7.95471217482094e-06, "loss": 4.0962, "step": 13731 }, { "epoch": 0.7389151958674128, "grad_norm": 1.8877836465835571, "learning_rate": 7.951620830653278e-06, "loss": 3.8517, "step": 13732 }, { "epoch": 0.7389690055962118, "grad_norm": 1.5085874795913696, "learning_rate": 7.94852997368244e-06, "loss": 4.1377, "step": 13733 }, { "epoch": 0.7390228153250108, "grad_norm": 2.6240365505218506, "learning_rate": 7.945439603996747e-06, "loss": 3.3526, "step": 13734 }, { "epoch": 0.7390766250538098, "grad_norm": 2.1497271060943604, "learning_rate": 7.942349721684522e-06, "loss": 4.263, "step": 13735 }, { "epoch": 0.7391304347826086, "grad_norm": 3.738821268081665, "learning_rate": 7.93926032683406e-06, "loss": 3.4746, "step": 13736 }, { "epoch": 0.7391842445114076, "grad_norm": 1.9250396490097046, "learning_rate": 7.936171419533653e-06, "loss": 4.0648, "step": 13737 }, { "epoch": 0.7392380542402066, "grad_norm": 2.8206818103790283, "learning_rate": 7.933082999871567e-06, "loss": 3.9202, "step": 13738 }, { "epoch": 0.7392918639690056, "grad_norm": 2.206732749938965, "learning_rate": 7.929995067936066e-06, "loss": 3.9776, "step": 13739 }, { "epoch": 0.7393456736978046, "grad_norm": 2.6796047687530518, "learning_rate": 7.926907623815394e-06, "loss": 4.3273, "step": 13740 }, { "epoch": 0.7393994834266036, "grad_norm": 3.1483893394470215, "learning_rate": 7.92382066759777e-06, "loss": 3.5835, "step": 13741 }, { "epoch": 0.7394532931554025, "grad_norm": 2.654472827911377, "learning_rate": 7.920734199371432e-06, "loss": 3.652, "step": 13742 }, { "epoch": 0.7395071028842015, "grad_norm": 3.9741077423095703, "learning_rate": 7.917648219224575e-06, "loss": 3.6316, "step": 13743 }, { "epoch": 0.7395609126130004, "grad_norm": 3.2497377395629883, "learning_rate": 7.914562727245382e-06, "loss": 3.6672, "step": 13744 }, { "epoch": 0.7396147223417994, "grad_norm": 2.0705363750457764, "learning_rate": 7.91147772352204e-06, "loss": 4.2112, "step": 13745 }, { "epoch": 0.7396685320705984, "grad_norm": 1.600695013999939, "learning_rate": 7.908393208142686e-06, "loss": 3.9049, "step": 13746 }, { "epoch": 0.7397223417993973, "grad_norm": 2.155132532119751, "learning_rate": 7.905309181195494e-06, "loss": 3.7337, "step": 13747 }, { "epoch": 0.7397761515281963, "grad_norm": 2.1386427879333496, "learning_rate": 7.902225642768584e-06, "loss": 4.1847, "step": 13748 }, { "epoch": 0.7398299612569953, "grad_norm": 2.2489287853240967, "learning_rate": 7.899142592950077e-06, "loss": 3.6468, "step": 13749 }, { "epoch": 0.7398837709857943, "grad_norm": 3.4994993209838867, "learning_rate": 7.896060031828079e-06, "loss": 3.143, "step": 13750 }, { "epoch": 0.7399375807145931, "grad_norm": 2.7141506671905518, "learning_rate": 7.892977959490683e-06, "loss": 2.6389, "step": 13751 }, { "epoch": 0.7399913904433921, "grad_norm": 1.624431848526001, "learning_rate": 7.889896376025963e-06, "loss": 4.2854, "step": 13752 }, { "epoch": 0.7400452001721911, "grad_norm": 1.543875813484192, "learning_rate": 7.886815281521984e-06, "loss": 4.4858, "step": 13753 }, { "epoch": 0.7400990099009901, "grad_norm": 1.8886337280273438, "learning_rate": 7.883734676066796e-06, "loss": 4.1924, "step": 13754 }, { "epoch": 0.7401528196297891, "grad_norm": 2.137193202972412, "learning_rate": 7.880654559748431e-06, "loss": 4.2008, "step": 13755 }, { "epoch": 0.740206629358588, "grad_norm": 2.3894174098968506, "learning_rate": 7.877574932654916e-06, "loss": 3.383, "step": 13756 }, { "epoch": 0.740260439087387, "grad_norm": 2.722691059112549, "learning_rate": 7.874495794874246e-06, "loss": 4.0404, "step": 13757 }, { "epoch": 0.740314248816186, "grad_norm": 2.89452862739563, "learning_rate": 7.871417146494432e-06, "loss": 3.1111, "step": 13758 }, { "epoch": 0.7403680585449849, "grad_norm": 3.0999889373779297, "learning_rate": 7.868338987603446e-06, "loss": 3.6956, "step": 13759 }, { "epoch": 0.7404218682737839, "grad_norm": 3.531421422958374, "learning_rate": 7.86526131828926e-06, "loss": 3.4511, "step": 13760 }, { "epoch": 0.7404756780025828, "grad_norm": 1.4942705631256104, "learning_rate": 7.862184138639802e-06, "loss": 4.4271, "step": 13761 }, { "epoch": 0.7405294877313818, "grad_norm": 3.5757553577423096, "learning_rate": 7.859107448743036e-06, "loss": 3.5111, "step": 13762 }, { "epoch": 0.7405832974601808, "grad_norm": 4.293615341186523, "learning_rate": 7.856031248686876e-06, "loss": 2.825, "step": 13763 }, { "epoch": 0.7406371071889798, "grad_norm": 3.3971192836761475, "learning_rate": 7.85295553855923e-06, "loss": 3.3783, "step": 13764 }, { "epoch": 0.7406909169177788, "grad_norm": 2.2840168476104736, "learning_rate": 7.849880318447994e-06, "loss": 3.8071, "step": 13765 }, { "epoch": 0.7407447266465778, "grad_norm": 2.939232587814331, "learning_rate": 7.84680558844105e-06, "loss": 3.6873, "step": 13766 }, { "epoch": 0.7407985363753766, "grad_norm": 2.3115711212158203, "learning_rate": 7.843731348626258e-06, "loss": 4.1911, "step": 13767 }, { "epoch": 0.7408523461041756, "grad_norm": 2.0237085819244385, "learning_rate": 7.840657599091494e-06, "loss": 4.3269, "step": 13768 }, { "epoch": 0.7409061558329746, "grad_norm": 2.7916860580444336, "learning_rate": 7.837584339924578e-06, "loss": 4.053, "step": 13769 }, { "epoch": 0.7409599655617736, "grad_norm": 3.435321807861328, "learning_rate": 7.834511571213337e-06, "loss": 4.4921, "step": 13770 }, { "epoch": 0.7410137752905726, "grad_norm": 2.9300825595855713, "learning_rate": 7.831439293045586e-06, "loss": 3.9102, "step": 13771 }, { "epoch": 0.7410675850193715, "grad_norm": 1.3440157175064087, "learning_rate": 7.828367505509115e-06, "loss": 4.2673, "step": 13772 }, { "epoch": 0.7411213947481705, "grad_norm": 4.094241142272949, "learning_rate": 7.82529620869172e-06, "loss": 3.4139, "step": 13773 }, { "epoch": 0.7411752044769694, "grad_norm": 2.684866189956665, "learning_rate": 7.822225402681169e-06, "loss": 4.1838, "step": 13774 }, { "epoch": 0.7412290142057684, "grad_norm": 3.0784595012664795, "learning_rate": 7.819155087565219e-06, "loss": 3.748, "step": 13775 }, { "epoch": 0.7412828239345673, "grad_norm": 1.3163976669311523, "learning_rate": 7.816085263431597e-06, "loss": 4.3846, "step": 13776 }, { "epoch": 0.7413366336633663, "grad_norm": 3.1674063205718994, "learning_rate": 7.813015930368032e-06, "loss": 4.4565, "step": 13777 }, { "epoch": 0.7413904433921653, "grad_norm": 2.0446269512176514, "learning_rate": 7.809947088462252e-06, "loss": 4.1859, "step": 13778 }, { "epoch": 0.7414442531209643, "grad_norm": 1.8725401163101196, "learning_rate": 7.806878737801948e-06, "loss": 4.261, "step": 13779 }, { "epoch": 0.7414980628497633, "grad_norm": 4.135664939880371, "learning_rate": 7.803810878474804e-06, "loss": 4.1253, "step": 13780 }, { "epoch": 0.7415518725785623, "grad_norm": 1.929401159286499, "learning_rate": 7.800743510568495e-06, "loss": 4.1955, "step": 13781 }, { "epoch": 0.7416056823073611, "grad_norm": 2.2561984062194824, "learning_rate": 7.797676634170675e-06, "loss": 3.7004, "step": 13782 }, { "epoch": 0.7416594920361601, "grad_norm": 2.842820644378662, "learning_rate": 7.794610249368989e-06, "loss": 3.6247, "step": 13783 }, { "epoch": 0.7417133017649591, "grad_norm": 2.430020570755005, "learning_rate": 7.791544356251063e-06, "loss": 4.2255, "step": 13784 }, { "epoch": 0.7417671114937581, "grad_norm": 2.1689982414245605, "learning_rate": 7.788478954904516e-06, "loss": 3.5339, "step": 13785 }, { "epoch": 0.741820921222557, "grad_norm": 3.0569958686828613, "learning_rate": 7.785414045416944e-06, "loss": 3.761, "step": 13786 }, { "epoch": 0.741874730951356, "grad_norm": 2.2297775745391846, "learning_rate": 7.78234962787594e-06, "loss": 3.3497, "step": 13787 }, { "epoch": 0.741928540680155, "grad_norm": 3.5744662284851074, "learning_rate": 7.779285702369065e-06, "loss": 4.224, "step": 13788 }, { "epoch": 0.7419823504089539, "grad_norm": 2.093815565109253, "learning_rate": 7.776222268983893e-06, "loss": 4.1943, "step": 13789 }, { "epoch": 0.7420361601377529, "grad_norm": 1.7221354246139526, "learning_rate": 7.773159327807971e-06, "loss": 4.4089, "step": 13790 }, { "epoch": 0.7420899698665518, "grad_norm": 2.333192825317383, "learning_rate": 7.770096878928813e-06, "loss": 3.9866, "step": 13791 }, { "epoch": 0.7421437795953508, "grad_norm": 3.76558518409729, "learning_rate": 7.767034922433936e-06, "loss": 3.3872, "step": 13792 }, { "epoch": 0.7421975893241498, "grad_norm": 4.32319974899292, "learning_rate": 7.763973458410856e-06, "loss": 2.7709, "step": 13793 }, { "epoch": 0.7422513990529488, "grad_norm": 3.5317318439483643, "learning_rate": 7.760912486947056e-06, "loss": 2.7644, "step": 13794 }, { "epoch": 0.7423052087817478, "grad_norm": 1.7488203048706055, "learning_rate": 7.757852008130006e-06, "loss": 3.7111, "step": 13795 }, { "epoch": 0.7423590185105468, "grad_norm": 2.504683256149292, "learning_rate": 7.754792022047175e-06, "loss": 4.2498, "step": 13796 }, { "epoch": 0.7424128282393456, "grad_norm": 4.169610023498535, "learning_rate": 7.751732528786001e-06, "loss": 4.0571, "step": 13797 }, { "epoch": 0.7424666379681446, "grad_norm": 1.8641890287399292, "learning_rate": 7.74867352843392e-06, "loss": 3.781, "step": 13798 }, { "epoch": 0.7425204476969436, "grad_norm": 2.8540873527526855, "learning_rate": 7.745615021078347e-06, "loss": 3.2631, "step": 13799 }, { "epoch": 0.7425742574257426, "grad_norm": 2.629620313644409, "learning_rate": 7.742557006806689e-06, "loss": 3.5003, "step": 13800 }, { "epoch": 0.7426280671545415, "grad_norm": 3.624171733856201, "learning_rate": 7.739499485706334e-06, "loss": 3.0714, "step": 13801 }, { "epoch": 0.7426818768833405, "grad_norm": 1.429987907409668, "learning_rate": 7.73644245786466e-06, "loss": 4.1445, "step": 13802 }, { "epoch": 0.7427356866121395, "grad_norm": 2.728538990020752, "learning_rate": 7.733385923369019e-06, "loss": 3.2166, "step": 13803 }, { "epoch": 0.7427894963409385, "grad_norm": 2.5052273273468018, "learning_rate": 7.730329882306773e-06, "loss": 3.9206, "step": 13804 }, { "epoch": 0.7428433060697374, "grad_norm": 2.4581756591796875, "learning_rate": 7.72727433476525e-06, "loss": 3.7165, "step": 13805 }, { "epoch": 0.7428971157985363, "grad_norm": 2.2888998985290527, "learning_rate": 7.724219280831776e-06, "loss": 4.0109, "step": 13806 }, { "epoch": 0.7429509255273353, "grad_norm": 2.26828932762146, "learning_rate": 7.72116472059364e-06, "loss": 3.735, "step": 13807 }, { "epoch": 0.7430047352561343, "grad_norm": 3.8615882396698, "learning_rate": 7.718110654138136e-06, "loss": 2.8432, "step": 13808 }, { "epoch": 0.7430585449849333, "grad_norm": 2.364936590194702, "learning_rate": 7.715057081552551e-06, "loss": 4.7303, "step": 13809 }, { "epoch": 0.7431123547137323, "grad_norm": 2.6888623237609863, "learning_rate": 7.712004002924147e-06, "loss": 3.9469, "step": 13810 }, { "epoch": 0.7431661644425313, "grad_norm": 1.106850266456604, "learning_rate": 7.708951418340168e-06, "loss": 4.1725, "step": 13811 }, { "epoch": 0.7432199741713301, "grad_norm": 2.932037353515625, "learning_rate": 7.70589932788785e-06, "loss": 3.7015, "step": 13812 }, { "epoch": 0.7432737839001291, "grad_norm": 2.925739288330078, "learning_rate": 7.702847731654414e-06, "loss": 3.8838, "step": 13813 }, { "epoch": 0.7433275936289281, "grad_norm": 2.091825485229492, "learning_rate": 7.699796629727066e-06, "loss": 4.5819, "step": 13814 }, { "epoch": 0.7433814033577271, "grad_norm": 3.592434883117676, "learning_rate": 7.696746022192996e-06, "loss": 4.1902, "step": 13815 }, { "epoch": 0.743435213086526, "grad_norm": 2.396495819091797, "learning_rate": 7.693695909139387e-06, "loss": 3.9386, "step": 13816 }, { "epoch": 0.743489022815325, "grad_norm": 3.6791510581970215, "learning_rate": 7.6906462906534e-06, "loss": 3.9943, "step": 13817 }, { "epoch": 0.743542832544124, "grad_norm": 2.8190977573394775, "learning_rate": 7.687597166822186e-06, "loss": 3.3407, "step": 13818 }, { "epoch": 0.743596642272923, "grad_norm": 1.699340581893921, "learning_rate": 7.68454853773287e-06, "loss": 4.4997, "step": 13819 }, { "epoch": 0.7436504520017219, "grad_norm": 3.0855393409729004, "learning_rate": 7.681500403472592e-06, "loss": 3.4407, "step": 13820 }, { "epoch": 0.7437042617305208, "grad_norm": 4.258136749267578, "learning_rate": 7.67845276412846e-06, "loss": 3.7607, "step": 13821 }, { "epoch": 0.7437580714593198, "grad_norm": 1.9388113021850586, "learning_rate": 7.675405619787551e-06, "loss": 3.7423, "step": 13822 }, { "epoch": 0.7438118811881188, "grad_norm": 2.130706787109375, "learning_rate": 7.67235897053694e-06, "loss": 4.3431, "step": 13823 }, { "epoch": 0.7438656909169178, "grad_norm": 3.7602732181549072, "learning_rate": 7.669312816463717e-06, "loss": 3.3826, "step": 13824 }, { "epoch": 0.7439195006457168, "grad_norm": 4.244169235229492, "learning_rate": 7.666267157654918e-06, "loss": 4.3509, "step": 13825 }, { "epoch": 0.7439733103745158, "grad_norm": 2.5304207801818848, "learning_rate": 7.66322199419758e-06, "loss": 3.7842, "step": 13826 }, { "epoch": 0.7440271201033147, "grad_norm": 1.775307059288025, "learning_rate": 7.660177326178727e-06, "loss": 4.2695, "step": 13827 }, { "epoch": 0.7440809298321136, "grad_norm": 2.1155362129211426, "learning_rate": 7.65713315368537e-06, "loss": 3.5682, "step": 13828 }, { "epoch": 0.7441347395609126, "grad_norm": 2.193648099899292, "learning_rate": 7.654089476804499e-06, "loss": 3.3621, "step": 13829 }, { "epoch": 0.7441885492897116, "grad_norm": 3.9101428985595703, "learning_rate": 7.651046295623095e-06, "loss": 3.6411, "step": 13830 }, { "epoch": 0.7442423590185105, "grad_norm": 3.4540586471557617, "learning_rate": 7.648003610228124e-06, "loss": 2.7772, "step": 13831 }, { "epoch": 0.7442961687473095, "grad_norm": 2.2368602752685547, "learning_rate": 7.644961420706539e-06, "loss": 3.3268, "step": 13832 }, { "epoch": 0.7443499784761085, "grad_norm": 1.6704388856887817, "learning_rate": 7.64191972714528e-06, "loss": 3.7391, "step": 13833 }, { "epoch": 0.7444037882049075, "grad_norm": 1.7516642808914185, "learning_rate": 7.638878529631257e-06, "loss": 4.515, "step": 13834 }, { "epoch": 0.7444575979337064, "grad_norm": 3.599407434463501, "learning_rate": 7.635837828251396e-06, "loss": 3.7648, "step": 13835 }, { "epoch": 0.7445114076625053, "grad_norm": 3.512773275375366, "learning_rate": 7.632797623092597e-06, "loss": 2.9931, "step": 13836 }, { "epoch": 0.7445652173913043, "grad_norm": 2.8041563034057617, "learning_rate": 7.62975791424172e-06, "loss": 2.9815, "step": 13837 }, { "epoch": 0.7446190271201033, "grad_norm": 2.846473217010498, "learning_rate": 7.62671870178564e-06, "loss": 2.9375, "step": 13838 }, { "epoch": 0.7446728368489023, "grad_norm": 3.4264752864837646, "learning_rate": 7.623679985811205e-06, "loss": 4.1157, "step": 13839 }, { "epoch": 0.7447266465777013, "grad_norm": 2.9698879718780518, "learning_rate": 7.620641766405268e-06, "loss": 3.9962, "step": 13840 }, { "epoch": 0.7447804563065002, "grad_norm": 2.8678629398345947, "learning_rate": 7.617604043654641e-06, "loss": 3.2556, "step": 13841 }, { "epoch": 0.7448342660352992, "grad_norm": 3.262434482574463, "learning_rate": 7.614566817646141e-06, "loss": 3.2517, "step": 13842 }, { "epoch": 0.7448880757640981, "grad_norm": 3.0835354328155518, "learning_rate": 7.6115300884665565e-06, "loss": 3.6939, "step": 13843 }, { "epoch": 0.7449418854928971, "grad_norm": 3.400969982147217, "learning_rate": 7.608493856202675e-06, "loss": 3.8783, "step": 13844 }, { "epoch": 0.7449956952216961, "grad_norm": 2.9069602489471436, "learning_rate": 7.605458120941261e-06, "loss": 3.7934, "step": 13845 }, { "epoch": 0.745049504950495, "grad_norm": 1.8570523262023926, "learning_rate": 7.602422882769067e-06, "loss": 4.3718, "step": 13846 }, { "epoch": 0.745103314679294, "grad_norm": 2.2640912532806396, "learning_rate": 7.599388141772834e-06, "loss": 3.6045, "step": 13847 }, { "epoch": 0.745157124408093, "grad_norm": 2.162571668624878, "learning_rate": 7.5963538980392855e-06, "loss": 3.1316, "step": 13848 }, { "epoch": 0.745210934136892, "grad_norm": 2.7025485038757324, "learning_rate": 7.593320151655134e-06, "loss": 3.7662, "step": 13849 }, { "epoch": 0.745264743865691, "grad_norm": 2.8798398971557617, "learning_rate": 7.590286902707064e-06, "loss": 3.8842, "step": 13850 }, { "epoch": 0.7453185535944898, "grad_norm": 3.5159316062927246, "learning_rate": 7.587254151281775e-06, "loss": 3.9179, "step": 13851 }, { "epoch": 0.7453723633232888, "grad_norm": 2.3091037273406982, "learning_rate": 7.584221897465937e-06, "loss": 3.8752, "step": 13852 }, { "epoch": 0.7454261730520878, "grad_norm": 1.9248653650283813, "learning_rate": 7.581190141346187e-06, "loss": 4.4603, "step": 13853 }, { "epoch": 0.7454799827808868, "grad_norm": 2.9909932613372803, "learning_rate": 7.578158883009162e-06, "loss": 3.1216, "step": 13854 }, { "epoch": 0.7455337925096858, "grad_norm": 2.4213900566101074, "learning_rate": 7.5751281225415055e-06, "loss": 3.744, "step": 13855 }, { "epoch": 0.7455876022384847, "grad_norm": 3.5734920501708984, "learning_rate": 7.57209786002982e-06, "loss": 3.367, "step": 13856 }, { "epoch": 0.7456414119672837, "grad_norm": 2.2926130294799805, "learning_rate": 7.569068095560702e-06, "loss": 4.0101, "step": 13857 }, { "epoch": 0.7456952216960826, "grad_norm": 3.2605979442596436, "learning_rate": 7.5660388292207344e-06, "loss": 4.0777, "step": 13858 }, { "epoch": 0.7457490314248816, "grad_norm": 1.526830792427063, "learning_rate": 7.563010061096484e-06, "loss": 4.5596, "step": 13859 }, { "epoch": 0.7458028411536806, "grad_norm": 3.849775791168213, "learning_rate": 7.559981791274507e-06, "loss": 2.7369, "step": 13860 }, { "epoch": 0.7458566508824795, "grad_norm": 3.3364109992980957, "learning_rate": 7.556954019841342e-06, "loss": 3.3074, "step": 13861 }, { "epoch": 0.7459104606112785, "grad_norm": 3.4922142028808594, "learning_rate": 7.553926746883516e-06, "loss": 3.6703, "step": 13862 }, { "epoch": 0.7459642703400775, "grad_norm": 2.6894869804382324, "learning_rate": 7.550899972487538e-06, "loss": 4.0287, "step": 13863 }, { "epoch": 0.7460180800688765, "grad_norm": 3.204237461090088, "learning_rate": 7.5478736967399075e-06, "loss": 3.3641, "step": 13864 }, { "epoch": 0.7460718897976755, "grad_norm": 2.071561098098755, "learning_rate": 7.5448479197270965e-06, "loss": 4.6154, "step": 13865 }, { "epoch": 0.7461256995264743, "grad_norm": 2.921992063522339, "learning_rate": 7.54182264153559e-06, "loss": 3.6657, "step": 13866 }, { "epoch": 0.7461795092552733, "grad_norm": 2.4977047443389893, "learning_rate": 7.5387978622518456e-06, "loss": 3.1894, "step": 13867 }, { "epoch": 0.7462333189840723, "grad_norm": 3.167829751968384, "learning_rate": 7.535773581962285e-06, "loss": 3.3626, "step": 13868 }, { "epoch": 0.7462871287128713, "grad_norm": 3.895805597305298, "learning_rate": 7.532749800753341e-06, "loss": 3.0952, "step": 13869 }, { "epoch": 0.7463409384416703, "grad_norm": 2.672020196914673, "learning_rate": 7.5297265187114195e-06, "loss": 4.1452, "step": 13870 }, { "epoch": 0.7463947481704692, "grad_norm": 2.20845627784729, "learning_rate": 7.526703735922932e-06, "loss": 4.2965, "step": 13871 }, { "epoch": 0.7464485578992682, "grad_norm": 2.139539957046509, "learning_rate": 7.523681452474254e-06, "loss": 3.8499, "step": 13872 }, { "epoch": 0.7465023676280672, "grad_norm": 4.0191216468811035, "learning_rate": 7.5206596684517545e-06, "loss": 3.988, "step": 13873 }, { "epoch": 0.7465561773568661, "grad_norm": 2.016080141067505, "learning_rate": 7.517638383941789e-06, "loss": 3.9831, "step": 13874 }, { "epoch": 0.7466099870856651, "grad_norm": 2.530212879180908, "learning_rate": 7.5146175990306965e-06, "loss": 3.2793, "step": 13875 }, { "epoch": 0.746663796814464, "grad_norm": 2.2648229598999023, "learning_rate": 7.5115973138048e-06, "loss": 3.6549, "step": 13876 }, { "epoch": 0.746717606543263, "grad_norm": 3.842620849609375, "learning_rate": 7.508577528350416e-06, "loss": 3.0849, "step": 13877 }, { "epoch": 0.746771416272062, "grad_norm": 4.242770671844482, "learning_rate": 7.505558242753838e-06, "loss": 2.3752, "step": 13878 }, { "epoch": 0.746825226000861, "grad_norm": 2.835465669631958, "learning_rate": 7.502539457101354e-06, "loss": 3.4907, "step": 13879 }, { "epoch": 0.74687903572966, "grad_norm": 5.239651203155518, "learning_rate": 7.4995211714792264e-06, "loss": 3.6989, "step": 13880 }, { "epoch": 0.7469328454584588, "grad_norm": 2.1871461868286133, "learning_rate": 7.496503385973708e-06, "loss": 4.3482, "step": 13881 }, { "epoch": 0.7469866551872578, "grad_norm": 2.4710745811462402, "learning_rate": 7.493486100671057e-06, "loss": 3.9767, "step": 13882 }, { "epoch": 0.7470404649160568, "grad_norm": 2.042421817779541, "learning_rate": 7.490469315657481e-06, "loss": 3.584, "step": 13883 }, { "epoch": 0.7470942746448558, "grad_norm": 3.6200008392333984, "learning_rate": 7.487453031019196e-06, "loss": 4.1692, "step": 13884 }, { "epoch": 0.7471480843736548, "grad_norm": 2.0624775886535645, "learning_rate": 7.484437246842391e-06, "loss": 3.7979, "step": 13885 }, { "epoch": 0.7472018941024537, "grad_norm": 5.238998889923096, "learning_rate": 7.481421963213267e-06, "loss": 2.657, "step": 13886 }, { "epoch": 0.7472557038312527, "grad_norm": 2.2380640506744385, "learning_rate": 7.4784071802179836e-06, "loss": 3.901, "step": 13887 }, { "epoch": 0.7473095135600517, "grad_norm": 2.5854291915893555, "learning_rate": 7.4753928979426956e-06, "loss": 4.0866, "step": 13888 }, { "epoch": 0.7473633232888506, "grad_norm": 3.663081645965576, "learning_rate": 7.472379116473544e-06, "loss": 2.517, "step": 13889 }, { "epoch": 0.7474171330176496, "grad_norm": 2.8391520977020264, "learning_rate": 7.469365835896652e-06, "loss": 4.0487, "step": 13890 }, { "epoch": 0.7474709427464485, "grad_norm": 2.431089162826538, "learning_rate": 7.466353056298134e-06, "loss": 3.9185, "step": 13891 }, { "epoch": 0.7475247524752475, "grad_norm": 1.8171707391738892, "learning_rate": 7.463340777764083e-06, "loss": 4.1517, "step": 13892 }, { "epoch": 0.7475785622040465, "grad_norm": 1.5923057794570923, "learning_rate": 7.460329000380587e-06, "loss": 4.4305, "step": 13893 }, { "epoch": 0.7476323719328455, "grad_norm": 1.8610007762908936, "learning_rate": 7.457317724233712e-06, "loss": 4.262, "step": 13894 }, { "epoch": 0.7476861816616445, "grad_norm": 3.6232545375823975, "learning_rate": 7.454306949409512e-06, "loss": 3.1244, "step": 13895 }, { "epoch": 0.7477399913904433, "grad_norm": 3.089350461959839, "learning_rate": 7.451296675994019e-06, "loss": 3.193, "step": 13896 }, { "epoch": 0.7477938011192423, "grad_norm": 3.3637850284576416, "learning_rate": 7.448286904073279e-06, "loss": 2.9985, "step": 13897 }, { "epoch": 0.7478476108480413, "grad_norm": 2.6116228103637695, "learning_rate": 7.445277633733286e-06, "loss": 4.0942, "step": 13898 }, { "epoch": 0.7479014205768403, "grad_norm": 4.891239166259766, "learning_rate": 7.442268865060043e-06, "loss": 3.5941, "step": 13899 }, { "epoch": 0.7479552303056393, "grad_norm": 1.051110029220581, "learning_rate": 7.439260598139527e-06, "loss": 4.1145, "step": 13900 }, { "epoch": 0.7480090400344382, "grad_norm": 4.388917922973633, "learning_rate": 7.4362528330577056e-06, "loss": 4.0402, "step": 13901 }, { "epoch": 0.7480628497632372, "grad_norm": 2.1387341022491455, "learning_rate": 7.433245569900543e-06, "loss": 3.8113, "step": 13902 }, { "epoch": 0.7481166594920362, "grad_norm": 2.189326047897339, "learning_rate": 7.430238808753975e-06, "loss": 3.769, "step": 13903 }, { "epoch": 0.7481704692208351, "grad_norm": 2.196810483932495, "learning_rate": 7.427232549703925e-06, "loss": 4.0689, "step": 13904 }, { "epoch": 0.7482242789496341, "grad_norm": 2.039396286010742, "learning_rate": 7.4242267928363084e-06, "loss": 3.214, "step": 13905 }, { "epoch": 0.748278088678433, "grad_norm": 2.5970656871795654, "learning_rate": 7.421221538237005e-06, "loss": 4.1904, "step": 13906 }, { "epoch": 0.748331898407232, "grad_norm": 2.163888692855835, "learning_rate": 7.4182167859919135e-06, "loss": 4.1727, "step": 13907 }, { "epoch": 0.748385708136031, "grad_norm": 1.714469075202942, "learning_rate": 7.4152125361869e-06, "loss": 3.902, "step": 13908 }, { "epoch": 0.74843951786483, "grad_norm": 2.6555471420288086, "learning_rate": 7.412208788907809e-06, "loss": 3.3182, "step": 13909 }, { "epoch": 0.748493327593629, "grad_norm": 4.442901134490967, "learning_rate": 7.409205544240491e-06, "loss": 4.1931, "step": 13910 }, { "epoch": 0.748547137322428, "grad_norm": 1.6038330793380737, "learning_rate": 7.406202802270762e-06, "loss": 3.9548, "step": 13911 }, { "epoch": 0.7486009470512268, "grad_norm": 2.8131768703460693, "learning_rate": 7.403200563084428e-06, "loss": 2.8725, "step": 13912 }, { "epoch": 0.7486547567800258, "grad_norm": 4.739546298980713, "learning_rate": 7.400198826767307e-06, "loss": 2.7244, "step": 13913 }, { "epoch": 0.7487085665088248, "grad_norm": 2.6476683616638184, "learning_rate": 7.397197593405159e-06, "loss": 4.2635, "step": 13914 }, { "epoch": 0.7487623762376238, "grad_norm": 2.4639837741851807, "learning_rate": 7.394196863083758e-06, "loss": 4.0293, "step": 13915 }, { "epoch": 0.7488161859664227, "grad_norm": 1.781435489654541, "learning_rate": 7.391196635888847e-06, "loss": 3.1859, "step": 13916 }, { "epoch": 0.7488699956952217, "grad_norm": 2.4497454166412354, "learning_rate": 7.388196911906184e-06, "loss": 4.3639, "step": 13917 }, { "epoch": 0.7489238054240207, "grad_norm": 2.621232748031616, "learning_rate": 7.385197691221482e-06, "loss": 3.7592, "step": 13918 }, { "epoch": 0.7489776151528196, "grad_norm": 2.2662272453308105, "learning_rate": 7.382198973920451e-06, "loss": 4.4084, "step": 13919 }, { "epoch": 0.7490314248816186, "grad_norm": 1.8704800605773926, "learning_rate": 7.379200760088794e-06, "loss": 4.3211, "step": 13920 }, { "epoch": 0.7490852346104175, "grad_norm": 1.7009440660476685, "learning_rate": 7.376203049812172e-06, "loss": 4.3655, "step": 13921 }, { "epoch": 0.7491390443392165, "grad_norm": 2.8131847381591797, "learning_rate": 7.373205843176273e-06, "loss": 3.1822, "step": 13922 }, { "epoch": 0.7491928540680155, "grad_norm": 2.2922680377960205, "learning_rate": 7.370209140266737e-06, "loss": 4.2039, "step": 13923 }, { "epoch": 0.7492466637968145, "grad_norm": 2.6927478313446045, "learning_rate": 7.367212941169207e-06, "loss": 4.1901, "step": 13924 }, { "epoch": 0.7493004735256135, "grad_norm": 4.107272148132324, "learning_rate": 7.364217245969304e-06, "loss": 3.0665, "step": 13925 }, { "epoch": 0.7493542832544124, "grad_norm": 2.9581823348999023, "learning_rate": 7.361222054752637e-06, "loss": 4.1349, "step": 13926 }, { "epoch": 0.7494080929832113, "grad_norm": 2.1294028759002686, "learning_rate": 7.358227367604795e-06, "loss": 3.8662, "step": 13927 }, { "epoch": 0.7494619027120103, "grad_norm": 1.4535094499588013, "learning_rate": 7.3552331846113795e-06, "loss": 3.3963, "step": 13928 }, { "epoch": 0.7495157124408093, "grad_norm": 2.6397595405578613, "learning_rate": 7.35223950585793e-06, "loss": 3.3559, "step": 13929 }, { "epoch": 0.7495695221696083, "grad_norm": 2.887669086456299, "learning_rate": 7.349246331430009e-06, "loss": 3.4382, "step": 13930 }, { "epoch": 0.7496233318984072, "grad_norm": 1.5435806512832642, "learning_rate": 7.346253661413155e-06, "loss": 4.4594, "step": 13931 }, { "epoch": 0.7496771416272062, "grad_norm": 2.2698283195495605, "learning_rate": 7.3432614958928806e-06, "loss": 3.888, "step": 13932 }, { "epoch": 0.7497309513560052, "grad_norm": 1.7420169115066528, "learning_rate": 7.340269834954708e-06, "loss": 3.9493, "step": 13933 }, { "epoch": 0.7497847610848042, "grad_norm": 3.4385197162628174, "learning_rate": 7.337278678684126e-06, "loss": 3.6604, "step": 13934 }, { "epoch": 0.7498385708136031, "grad_norm": 1.5545549392700195, "learning_rate": 7.334288027166611e-06, "loss": 3.9252, "step": 13935 }, { "epoch": 0.749892380542402, "grad_norm": 2.9113171100616455, "learning_rate": 7.331297880487631e-06, "loss": 3.5945, "step": 13936 }, { "epoch": 0.749946190271201, "grad_norm": 2.7114853858947754, "learning_rate": 7.328308238732631e-06, "loss": 3.4212, "step": 13937 }, { "epoch": 0.75, "grad_norm": 2.330904960632324, "learning_rate": 7.325319101987052e-06, "loss": 4.1323, "step": 13938 }, { "epoch": 0.750053809728799, "grad_norm": 2.1377859115600586, "learning_rate": 7.3223304703363135e-06, "loss": 4.2971, "step": 13939 }, { "epoch": 0.750107619457598, "grad_norm": 1.946418285369873, "learning_rate": 7.319342343865823e-06, "loss": 3.7272, "step": 13940 }, { "epoch": 0.7501614291863969, "grad_norm": 2.021286964416504, "learning_rate": 7.316354722660973e-06, "loss": 4.4586, "step": 13941 }, { "epoch": 0.7502152389151958, "grad_norm": 2.727827310562134, "learning_rate": 7.3133676068071425e-06, "loss": 4.5806, "step": 13942 }, { "epoch": 0.7502690486439948, "grad_norm": 3.1048216819763184, "learning_rate": 7.310380996389693e-06, "loss": 3.8579, "step": 13943 }, { "epoch": 0.7503228583727938, "grad_norm": 2.362701654434204, "learning_rate": 7.3073948914939734e-06, "loss": 4.1222, "step": 13944 }, { "epoch": 0.7503766681015928, "grad_norm": 2.9928386211395264, "learning_rate": 7.304409292205325e-06, "loss": 4.073, "step": 13945 }, { "epoch": 0.7504304778303917, "grad_norm": 3.2628204822540283, "learning_rate": 7.301424198609061e-06, "loss": 4.044, "step": 13946 }, { "epoch": 0.7504842875591907, "grad_norm": 2.4569039344787598, "learning_rate": 7.2984396107904806e-06, "loss": 3.1549, "step": 13947 }, { "epoch": 0.7505380972879897, "grad_norm": 4.02005672454834, "learning_rate": 7.295455528834894e-06, "loss": 2.9767, "step": 13948 }, { "epoch": 0.7505919070167887, "grad_norm": 3.0097033977508545, "learning_rate": 7.292471952827567e-06, "loss": 3.6235, "step": 13949 }, { "epoch": 0.7506457167455876, "grad_norm": 1.126442790031433, "learning_rate": 7.289488882853768e-06, "loss": 4.6763, "step": 13950 }, { "epoch": 0.7506995264743865, "grad_norm": 2.378838300704956, "learning_rate": 7.286506318998746e-06, "loss": 3.3353, "step": 13951 }, { "epoch": 0.7507533362031855, "grad_norm": 2.491267681121826, "learning_rate": 7.2835242613477126e-06, "loss": 3.2779, "step": 13952 }, { "epoch": 0.7508071459319845, "grad_norm": 2.872814893722534, "learning_rate": 7.280542709985913e-06, "loss": 3.8015, "step": 13953 }, { "epoch": 0.7508609556607835, "grad_norm": 3.3684470653533936, "learning_rate": 7.2775616649985445e-06, "loss": 3.9018, "step": 13954 }, { "epoch": 0.7509147653895825, "grad_norm": 1.695577621459961, "learning_rate": 7.274581126470795e-06, "loss": 3.887, "step": 13955 }, { "epoch": 0.7509685751183814, "grad_norm": 2.1560075283050537, "learning_rate": 7.27160109448784e-06, "loss": 4.1707, "step": 13956 }, { "epoch": 0.7510223848471804, "grad_norm": 5.751495361328125, "learning_rate": 7.2686215691348425e-06, "loss": 3.8299, "step": 13957 }, { "epoch": 0.7510761945759793, "grad_norm": 5.462421894073486, "learning_rate": 7.265642550496943e-06, "loss": 4.2899, "step": 13958 }, { "epoch": 0.7511300043047783, "grad_norm": 1.2712681293487549, "learning_rate": 7.262664038659292e-06, "loss": 4.1855, "step": 13959 }, { "epoch": 0.7511838140335773, "grad_norm": 3.9137563705444336, "learning_rate": 7.2596860337069885e-06, "loss": 3.734, "step": 13960 }, { "epoch": 0.7512376237623762, "grad_norm": 3.45129656791687, "learning_rate": 7.256708535725143e-06, "loss": 3.7837, "step": 13961 }, { "epoch": 0.7512914334911752, "grad_norm": 2.408600091934204, "learning_rate": 7.253731544798845e-06, "loss": 3.8359, "step": 13962 }, { "epoch": 0.7513452432199742, "grad_norm": 2.109041690826416, "learning_rate": 7.2507550610131566e-06, "loss": 4.1868, "step": 13963 }, { "epoch": 0.7513990529487732, "grad_norm": 2.7443363666534424, "learning_rate": 7.247779084453157e-06, "loss": 3.1453, "step": 13964 }, { "epoch": 0.751452862677572, "grad_norm": 2.438856840133667, "learning_rate": 7.244803615203885e-06, "loss": 3.5094, "step": 13965 }, { "epoch": 0.751506672406371, "grad_norm": 2.65744948387146, "learning_rate": 7.241828653350377e-06, "loss": 3.4737, "step": 13966 }, { "epoch": 0.75156048213517, "grad_norm": 1.854645848274231, "learning_rate": 7.238854198977626e-06, "loss": 3.9812, "step": 13967 }, { "epoch": 0.751614291863969, "grad_norm": 3.957089900970459, "learning_rate": 7.23588025217066e-06, "loss": 4.6523, "step": 13968 }, { "epoch": 0.751668101592768, "grad_norm": 3.823403835296631, "learning_rate": 7.232906813014454e-06, "loss": 3.4191, "step": 13969 }, { "epoch": 0.751721911321567, "grad_norm": 4.685352325439453, "learning_rate": 7.229933881593984e-06, "loss": 3.2544, "step": 13970 }, { "epoch": 0.7517757210503659, "grad_norm": 3.2522683143615723, "learning_rate": 7.226961457994208e-06, "loss": 4.0306, "step": 13971 }, { "epoch": 0.7518295307791649, "grad_norm": 2.4356486797332764, "learning_rate": 7.223989542300069e-06, "loss": 4.0481, "step": 13972 }, { "epoch": 0.7518833405079638, "grad_norm": 1.2401268482208252, "learning_rate": 7.2210181345964915e-06, "loss": 4.1058, "step": 13973 }, { "epoch": 0.7519371502367628, "grad_norm": 3.2379512786865234, "learning_rate": 7.218047234968409e-06, "loss": 3.4764, "step": 13974 }, { "epoch": 0.7519909599655618, "grad_norm": 2.0784871578216553, "learning_rate": 7.215076843500704e-06, "loss": 4.276, "step": 13975 }, { "epoch": 0.7520447696943607, "grad_norm": 3.705195903778076, "learning_rate": 7.2121069602782645e-06, "loss": 3.6493, "step": 13976 }, { "epoch": 0.7520985794231597, "grad_norm": 4.0253095626831055, "learning_rate": 7.209137585385964e-06, "loss": 3.7065, "step": 13977 }, { "epoch": 0.7521523891519587, "grad_norm": 2.720999240875244, "learning_rate": 7.206168718908651e-06, "loss": 3.5658, "step": 13978 }, { "epoch": 0.7522061988807577, "grad_norm": 2.0984203815460205, "learning_rate": 7.203200360931187e-06, "loss": 4.2549, "step": 13979 }, { "epoch": 0.7522600086095567, "grad_norm": 3.372253179550171, "learning_rate": 7.200232511538388e-06, "loss": 3.621, "step": 13980 }, { "epoch": 0.7523138183383555, "grad_norm": 1.9716763496398926, "learning_rate": 7.197265170815065e-06, "loss": 3.9238, "step": 13981 }, { "epoch": 0.7523676280671545, "grad_norm": 2.1268508434295654, "learning_rate": 7.194298338846031e-06, "loss": 3.6419, "step": 13982 }, { "epoch": 0.7524214377959535, "grad_norm": 2.781744956970215, "learning_rate": 7.191332015716043e-06, "loss": 4.6012, "step": 13983 }, { "epoch": 0.7524752475247525, "grad_norm": 2.168250322341919, "learning_rate": 7.188366201509891e-06, "loss": 3.9273, "step": 13984 }, { "epoch": 0.7525290572535515, "grad_norm": 2.720491409301758, "learning_rate": 7.185400896312328e-06, "loss": 3.9422, "step": 13985 }, { "epoch": 0.7525828669823504, "grad_norm": 2.877476930618286, "learning_rate": 7.182436100208092e-06, "loss": 3.8912, "step": 13986 }, { "epoch": 0.7526366767111494, "grad_norm": 3.4932785034179688, "learning_rate": 7.1794718132819076e-06, "loss": 3.9988, "step": 13987 }, { "epoch": 0.7526904864399483, "grad_norm": 1.8093446493148804, "learning_rate": 7.176508035618487e-06, "loss": 3.9394, "step": 13988 }, { "epoch": 0.7527442961687473, "grad_norm": 2.425398588180542, "learning_rate": 7.173544767302528e-06, "loss": 3.6721, "step": 13989 }, { "epoch": 0.7527981058975463, "grad_norm": 3.7149295806884766, "learning_rate": 7.170582008418711e-06, "loss": 3.6015, "step": 13990 }, { "epoch": 0.7528519156263452, "grad_norm": 3.0898613929748535, "learning_rate": 7.167619759051705e-06, "loss": 4.7432, "step": 13991 }, { "epoch": 0.7529057253551442, "grad_norm": 2.209399938583374, "learning_rate": 7.164658019286164e-06, "loss": 2.5597, "step": 13992 }, { "epoch": 0.7529595350839432, "grad_norm": 1.3477157354354858, "learning_rate": 7.161696789206723e-06, "loss": 4.4104, "step": 13993 }, { "epoch": 0.7530133448127422, "grad_norm": 4.3418288230896, "learning_rate": 7.158736068898003e-06, "loss": 4.1805, "step": 13994 }, { "epoch": 0.7530671545415412, "grad_norm": 2.0160467624664307, "learning_rate": 7.155775858444624e-06, "loss": 4.2711, "step": 13995 }, { "epoch": 0.75312096427034, "grad_norm": 3.0969135761260986, "learning_rate": 7.152816157931178e-06, "loss": 3.927, "step": 13996 }, { "epoch": 0.753174773999139, "grad_norm": 3.3427274227142334, "learning_rate": 7.1498569674422505e-06, "loss": 3.0331, "step": 13997 }, { "epoch": 0.753228583727938, "grad_norm": 2.413121223449707, "learning_rate": 7.146898287062384e-06, "loss": 3.4916, "step": 13998 }, { "epoch": 0.753282393456737, "grad_norm": 3.35923171043396, "learning_rate": 7.143940116876152e-06, "loss": 4.2683, "step": 13999 }, { "epoch": 0.753336203185536, "grad_norm": 1.6006742715835571, "learning_rate": 7.140982456968085e-06, "loss": 4.2851, "step": 14000 }, { "epoch": 0.7533900129143349, "grad_norm": 3.222952365875244, "learning_rate": 7.138025307422705e-06, "loss": 3.5509, "step": 14001 }, { "epoch": 0.7534438226431339, "grad_norm": 2.36966609954834, "learning_rate": 7.135068668324515e-06, "loss": 3.4594, "step": 14002 }, { "epoch": 0.7534976323719328, "grad_norm": 3.3498170375823975, "learning_rate": 7.1321125397580154e-06, "loss": 3.1695, "step": 14003 }, { "epoch": 0.7535514421007318, "grad_norm": 4.048851013183594, "learning_rate": 7.129156921807678e-06, "loss": 4.1532, "step": 14004 }, { "epoch": 0.7536052518295308, "grad_norm": 4.27923059463501, "learning_rate": 7.12620181455797e-06, "loss": 3.5072, "step": 14005 }, { "epoch": 0.7536590615583297, "grad_norm": 3.142310619354248, "learning_rate": 7.12324721809334e-06, "loss": 3.8026, "step": 14006 }, { "epoch": 0.7537128712871287, "grad_norm": 1.9909030199050903, "learning_rate": 7.120293132498221e-06, "loss": 3.9097, "step": 14007 }, { "epoch": 0.7537666810159277, "grad_norm": 2.5760912895202637, "learning_rate": 7.117339557857034e-06, "loss": 3.7647, "step": 14008 }, { "epoch": 0.7538204907447267, "grad_norm": 2.897031784057617, "learning_rate": 7.114386494254175e-06, "loss": 3.4765, "step": 14009 }, { "epoch": 0.7538743004735257, "grad_norm": 3.0510241985321045, "learning_rate": 7.111433941774051e-06, "loss": 4.2366, "step": 14010 }, { "epoch": 0.7539281102023245, "grad_norm": 2.244687795639038, "learning_rate": 7.1084819005010325e-06, "loss": 4.3519, "step": 14011 }, { "epoch": 0.7539819199311235, "grad_norm": 4.037869930267334, "learning_rate": 7.1055303705194834e-06, "loss": 2.7116, "step": 14012 }, { "epoch": 0.7540357296599225, "grad_norm": 2.8907382488250732, "learning_rate": 7.102579351913741e-06, "loss": 3.865, "step": 14013 }, { "epoch": 0.7540895393887215, "grad_norm": 2.0533323287963867, "learning_rate": 7.099628844768133e-06, "loss": 4.1117, "step": 14014 }, { "epoch": 0.7541433491175205, "grad_norm": 3.2123308181762695, "learning_rate": 7.096678849166993e-06, "loss": 3.7342, "step": 14015 }, { "epoch": 0.7541971588463194, "grad_norm": 3.0296132564544678, "learning_rate": 7.093729365194621e-06, "loss": 3.9232, "step": 14016 }, { "epoch": 0.7542509685751184, "grad_norm": 2.6646206378936768, "learning_rate": 7.090780392935298e-06, "loss": 3.3648, "step": 14017 }, { "epoch": 0.7543047783039174, "grad_norm": 2.699880361557007, "learning_rate": 7.087831932473302e-06, "loss": 3.2742, "step": 14018 }, { "epoch": 0.7543585880327163, "grad_norm": 2.6142656803131104, "learning_rate": 7.084883983892893e-06, "loss": 3.9143, "step": 14019 }, { "epoch": 0.7544123977615153, "grad_norm": 3.168518304824829, "learning_rate": 7.081936547278312e-06, "loss": 3.4983, "step": 14020 }, { "epoch": 0.7544662074903142, "grad_norm": 3.3282949924468994, "learning_rate": 7.078989622713789e-06, "loss": 2.9202, "step": 14021 }, { "epoch": 0.7545200172191132, "grad_norm": 3.287510633468628, "learning_rate": 7.076043210283542e-06, "loss": 3.717, "step": 14022 }, { "epoch": 0.7545738269479122, "grad_norm": 3.558650255203247, "learning_rate": 7.0730973100717715e-06, "loss": 4.0392, "step": 14023 }, { "epoch": 0.7546276366767112, "grad_norm": 2.4206302165985107, "learning_rate": 7.070151922162663e-06, "loss": 3.6405, "step": 14024 }, { "epoch": 0.7546814464055102, "grad_norm": 3.829425096511841, "learning_rate": 7.067207046640376e-06, "loss": 4.2581, "step": 14025 }, { "epoch": 0.754735256134309, "grad_norm": 2.4784858226776123, "learning_rate": 7.064262683589087e-06, "loss": 4.2612, "step": 14026 }, { "epoch": 0.754789065863108, "grad_norm": 2.2302002906799316, "learning_rate": 7.0613188330929395e-06, "loss": 4.059, "step": 14027 }, { "epoch": 0.754842875591907, "grad_norm": 4.785262584686279, "learning_rate": 7.058375495236039e-06, "loss": 3.4739, "step": 14028 }, { "epoch": 0.754896685320706, "grad_norm": 5.070221900939941, "learning_rate": 7.055432670102502e-06, "loss": 4.6355, "step": 14029 }, { "epoch": 0.754950495049505, "grad_norm": 2.1839466094970703, "learning_rate": 7.052490357776445e-06, "loss": 4.347, "step": 14030 }, { "epoch": 0.7550043047783039, "grad_norm": 2.2789418697357178, "learning_rate": 7.049548558341937e-06, "loss": 4.2695, "step": 14031 }, { "epoch": 0.7550581145071029, "grad_norm": 3.34601092338562, "learning_rate": 7.0466072718830516e-06, "loss": 3.2551, "step": 14032 }, { "epoch": 0.7551119242359019, "grad_norm": 2.376447916030884, "learning_rate": 7.0436664984838415e-06, "loss": 4.1084, "step": 14033 }, { "epoch": 0.7551657339647008, "grad_norm": 2.5459649562835693, "learning_rate": 7.0407262382283456e-06, "loss": 3.2616, "step": 14034 }, { "epoch": 0.7552195436934998, "grad_norm": 2.039482593536377, "learning_rate": 7.03778649120059e-06, "loss": 3.3549, "step": 14035 }, { "epoch": 0.7552733534222987, "grad_norm": 1.8611472845077515, "learning_rate": 7.034847257484584e-06, "loss": 3.2367, "step": 14036 }, { "epoch": 0.7553271631510977, "grad_norm": 2.0768706798553467, "learning_rate": 7.031908537164322e-06, "loss": 3.9771, "step": 14037 }, { "epoch": 0.7553809728798967, "grad_norm": 3.820030450820923, "learning_rate": 7.028970330323784e-06, "loss": 3.1322, "step": 14038 }, { "epoch": 0.7554347826086957, "grad_norm": 3.9705111980438232, "learning_rate": 7.026032637046939e-06, "loss": 3.3412, "step": 14039 }, { "epoch": 0.7554885923374947, "grad_norm": 2.5492208003997803, "learning_rate": 7.02309545741773e-06, "loss": 2.9917, "step": 14040 }, { "epoch": 0.7555424020662936, "grad_norm": 3.1209897994995117, "learning_rate": 7.0201587915201064e-06, "loss": 3.7281, "step": 14041 }, { "epoch": 0.7555962117950925, "grad_norm": 2.41009259223938, "learning_rate": 7.017222639437987e-06, "loss": 3.7701, "step": 14042 }, { "epoch": 0.7556500215238915, "grad_norm": 2.461498260498047, "learning_rate": 7.014287001255282e-06, "loss": 3.6204, "step": 14043 }, { "epoch": 0.7557038312526905, "grad_norm": 2.563859462738037, "learning_rate": 7.011351877055872e-06, "loss": 3.8557, "step": 14044 }, { "epoch": 0.7557576409814895, "grad_norm": 1.388156771659851, "learning_rate": 7.008417266923634e-06, "loss": 4.52, "step": 14045 }, { "epoch": 0.7558114507102884, "grad_norm": 2.0121021270751953, "learning_rate": 7.005483170942445e-06, "loss": 3.8121, "step": 14046 }, { "epoch": 0.7558652604390874, "grad_norm": 2.4350576400756836, "learning_rate": 7.0025495891961505e-06, "loss": 3.7652, "step": 14047 }, { "epoch": 0.7559190701678864, "grad_norm": 3.7687346935272217, "learning_rate": 6.999616521768579e-06, "loss": 3.0545, "step": 14048 }, { "epoch": 0.7559728798966853, "grad_norm": 3.6498606204986572, "learning_rate": 6.996683968743553e-06, "loss": 4.0788, "step": 14049 }, { "epoch": 0.7560266896254842, "grad_norm": 3.112921953201294, "learning_rate": 6.993751930204875e-06, "loss": 3.7192, "step": 14050 }, { "epoch": 0.7560804993542832, "grad_norm": 2.845076084136963, "learning_rate": 6.990820406236334e-06, "loss": 3.8556, "step": 14051 }, { "epoch": 0.7561343090830822, "grad_norm": 2.047020435333252, "learning_rate": 6.98788939692171e-06, "loss": 4.6717, "step": 14052 }, { "epoch": 0.7561881188118812, "grad_norm": 3.736285924911499, "learning_rate": 6.98495890234476e-06, "loss": 2.447, "step": 14053 }, { "epoch": 0.7562419285406802, "grad_norm": 2.780707359313965, "learning_rate": 6.982028922589229e-06, "loss": 3.7056, "step": 14054 }, { "epoch": 0.7562957382694792, "grad_norm": 4.739199638366699, "learning_rate": 6.979099457738847e-06, "loss": 3.8528, "step": 14055 }, { "epoch": 0.7563495479982781, "grad_norm": 3.218043565750122, "learning_rate": 6.976170507877328e-06, "loss": 3.4875, "step": 14056 }, { "epoch": 0.756403357727077, "grad_norm": 3.049222469329834, "learning_rate": 6.973242073088382e-06, "loss": 4.0925, "step": 14057 }, { "epoch": 0.756457167455876, "grad_norm": 3.4857096672058105, "learning_rate": 6.970314153455698e-06, "loss": 3.2141, "step": 14058 }, { "epoch": 0.756510977184675, "grad_norm": 1.5998218059539795, "learning_rate": 6.967386749062938e-06, "loss": 4.1969, "step": 14059 }, { "epoch": 0.756564786913474, "grad_norm": 2.9932971000671387, "learning_rate": 6.964459859993752e-06, "loss": 4.1344, "step": 14060 }, { "epoch": 0.7566185966422729, "grad_norm": 2.892836809158325, "learning_rate": 6.9615334863318005e-06, "loss": 4.041, "step": 14061 }, { "epoch": 0.7566724063710719, "grad_norm": 2.9039549827575684, "learning_rate": 6.958607628160704e-06, "loss": 2.9081, "step": 14062 }, { "epoch": 0.7567262160998709, "grad_norm": 1.172588586807251, "learning_rate": 6.9556822855640775e-06, "loss": 4.4835, "step": 14063 }, { "epoch": 0.7567800258286699, "grad_norm": 2.9340779781341553, "learning_rate": 6.95275745862552e-06, "loss": 3.8953, "step": 14064 }, { "epoch": 0.7568338355574687, "grad_norm": 1.7093162536621094, "learning_rate": 6.949833147428608e-06, "loss": 4.2361, "step": 14065 }, { "epoch": 0.7568876452862677, "grad_norm": 1.6616485118865967, "learning_rate": 6.9469093520569185e-06, "loss": 4.3224, "step": 14066 }, { "epoch": 0.7569414550150667, "grad_norm": 1.212877869606018, "learning_rate": 6.943986072594002e-06, "loss": 4.4186, "step": 14067 }, { "epoch": 0.7569952647438657, "grad_norm": 2.0619852542877197, "learning_rate": 6.941063309123399e-06, "loss": 2.9225, "step": 14068 }, { "epoch": 0.7570490744726647, "grad_norm": 3.9222636222839355, "learning_rate": 6.938141061728632e-06, "loss": 3.051, "step": 14069 }, { "epoch": 0.7571028842014637, "grad_norm": 2.3728935718536377, "learning_rate": 6.935219330493214e-06, "loss": 4.0006, "step": 14070 }, { "epoch": 0.7571566939302626, "grad_norm": 3.694581985473633, "learning_rate": 6.932298115500633e-06, "loss": 3.8762, "step": 14071 }, { "epoch": 0.7572105036590615, "grad_norm": 2.840766191482544, "learning_rate": 6.929377416834379e-06, "loss": 3.5437, "step": 14072 }, { "epoch": 0.7572643133878605, "grad_norm": 2.1552116870880127, "learning_rate": 6.926457234577924e-06, "loss": 4.0036, "step": 14073 }, { "epoch": 0.7573181231166595, "grad_norm": 3.630634069442749, "learning_rate": 6.923537568814703e-06, "loss": 4.3846, "step": 14074 }, { "epoch": 0.7573719328454585, "grad_norm": 2.109001874923706, "learning_rate": 6.920618419628156e-06, "loss": 4.3568, "step": 14075 }, { "epoch": 0.7574257425742574, "grad_norm": 5.028304100036621, "learning_rate": 6.9176997871017e-06, "loss": 2.4989, "step": 14076 }, { "epoch": 0.7574795523030564, "grad_norm": 2.7554686069488525, "learning_rate": 6.914781671318757e-06, "loss": 3.9336, "step": 14077 }, { "epoch": 0.7575333620318554, "grad_norm": 2.4732041358947754, "learning_rate": 6.911864072362709e-06, "loss": 3.854, "step": 14078 }, { "epoch": 0.7575871717606544, "grad_norm": 3.1821770668029785, "learning_rate": 6.9089469903169365e-06, "loss": 3.5154, "step": 14079 }, { "epoch": 0.7576409814894532, "grad_norm": 3.048210382461548, "learning_rate": 6.906030425264798e-06, "loss": 4.1089, "step": 14080 }, { "epoch": 0.7576947912182522, "grad_norm": 1.346266269683838, "learning_rate": 6.90311437728964e-06, "loss": 4.1912, "step": 14081 }, { "epoch": 0.7577486009470512, "grad_norm": 1.9543993473052979, "learning_rate": 6.900198846474803e-06, "loss": 3.9624, "step": 14082 }, { "epoch": 0.7578024106758502, "grad_norm": 4.4532694816589355, "learning_rate": 6.897283832903598e-06, "loss": 3.6194, "step": 14083 }, { "epoch": 0.7578562204046492, "grad_norm": 2.9561760425567627, "learning_rate": 6.8943693366593315e-06, "loss": 3.1175, "step": 14084 }, { "epoch": 0.7579100301334482, "grad_norm": 2.511143445968628, "learning_rate": 6.891455357825291e-06, "loss": 3.8631, "step": 14085 }, { "epoch": 0.7579638398622471, "grad_norm": 2.1124749183654785, "learning_rate": 6.888541896484749e-06, "loss": 4.1611, "step": 14086 }, { "epoch": 0.7580176495910461, "grad_norm": 1.9985575675964355, "learning_rate": 6.885628952720957e-06, "loss": 4.1446, "step": 14087 }, { "epoch": 0.758071459319845, "grad_norm": 3.4766852855682373, "learning_rate": 6.882716526617178e-06, "loss": 4.2278, "step": 14088 }, { "epoch": 0.758125269048644, "grad_norm": 2.7195231914520264, "learning_rate": 6.879804618256636e-06, "loss": 4.163, "step": 14089 }, { "epoch": 0.758179078777443, "grad_norm": 1.8398357629776, "learning_rate": 6.876893227722534e-06, "loss": 4.7078, "step": 14090 }, { "epoch": 0.7582328885062419, "grad_norm": 3.854475259780884, "learning_rate": 6.873982355098071e-06, "loss": 3.8916, "step": 14091 }, { "epoch": 0.7582866982350409, "grad_norm": 1.4066914319992065, "learning_rate": 6.871072000466444e-06, "loss": 4.2766, "step": 14092 }, { "epoch": 0.7583405079638399, "grad_norm": 2.18574857711792, "learning_rate": 6.868162163910821e-06, "loss": 3.0382, "step": 14093 }, { "epoch": 0.7583943176926389, "grad_norm": 1.7384488582611084, "learning_rate": 6.865252845514352e-06, "loss": 4.3638, "step": 14094 }, { "epoch": 0.7584481274214377, "grad_norm": 3.4135758876800537, "learning_rate": 6.862344045360184e-06, "loss": 3.4613, "step": 14095 }, { "epoch": 0.7585019371502367, "grad_norm": 3.443875789642334, "learning_rate": 6.859435763531435e-06, "loss": 4.473, "step": 14096 }, { "epoch": 0.7585557468790357, "grad_norm": 4.052205562591553, "learning_rate": 6.85652800011122e-06, "loss": 3.2774, "step": 14097 }, { "epoch": 0.7586095566078347, "grad_norm": 3.739412784576416, "learning_rate": 6.8536207551826355e-06, "loss": 3.1773, "step": 14098 }, { "epoch": 0.7586633663366337, "grad_norm": 1.4242674112319946, "learning_rate": 6.8507140288287616e-06, "loss": 3.7374, "step": 14099 }, { "epoch": 0.7587171760654327, "grad_norm": 3.620802402496338, "learning_rate": 6.847807821132665e-06, "loss": 3.5248, "step": 14100 }, { "epoch": 0.7587709857942316, "grad_norm": 1.9415028095245361, "learning_rate": 6.844902132177397e-06, "loss": 3.7476, "step": 14101 }, { "epoch": 0.7588247955230306, "grad_norm": 2.16902494430542, "learning_rate": 6.841996962045988e-06, "loss": 3.6482, "step": 14102 }, { "epoch": 0.7588786052518295, "grad_norm": 5.5236921310424805, "learning_rate": 6.8390923108214734e-06, "loss": 3.7924, "step": 14103 }, { "epoch": 0.7589324149806285, "grad_norm": 2.7815706729888916, "learning_rate": 6.836188178586861e-06, "loss": 3.7665, "step": 14104 }, { "epoch": 0.7589862247094274, "grad_norm": 4.452915668487549, "learning_rate": 6.833284565425127e-06, "loss": 4.2931, "step": 14105 }, { "epoch": 0.7590400344382264, "grad_norm": 2.539294719696045, "learning_rate": 6.8303814714192585e-06, "loss": 4.1854, "step": 14106 }, { "epoch": 0.7590938441670254, "grad_norm": 2.2489593029022217, "learning_rate": 6.827478896652209e-06, "loss": 4.0362, "step": 14107 }, { "epoch": 0.7591476538958244, "grad_norm": 4.419032573699951, "learning_rate": 6.824576841206942e-06, "loss": 3.6028, "step": 14108 }, { "epoch": 0.7592014636246234, "grad_norm": 2.657759189605713, "learning_rate": 6.821675305166381e-06, "loss": 3.3411, "step": 14109 }, { "epoch": 0.7592552733534222, "grad_norm": 4.170888423919678, "learning_rate": 6.818774288613447e-06, "loss": 2.6909, "step": 14110 }, { "epoch": 0.7593090830822212, "grad_norm": 4.121516227722168, "learning_rate": 6.81587379163105e-06, "loss": 3.391, "step": 14111 }, { "epoch": 0.7593628928110202, "grad_norm": 3.1750500202178955, "learning_rate": 6.812973814302057e-06, "loss": 4.4092, "step": 14112 }, { "epoch": 0.7594167025398192, "grad_norm": 2.08428955078125, "learning_rate": 6.810074356709361e-06, "loss": 3.2342, "step": 14113 }, { "epoch": 0.7594705122686182, "grad_norm": 3.012164831161499, "learning_rate": 6.807175418935816e-06, "loss": 4.0352, "step": 14114 }, { "epoch": 0.7595243219974172, "grad_norm": 3.737541675567627, "learning_rate": 6.804277001064263e-06, "loss": 3.0399, "step": 14115 }, { "epoch": 0.7595781317262161, "grad_norm": 2.2322068214416504, "learning_rate": 6.801379103177533e-06, "loss": 4.4099, "step": 14116 }, { "epoch": 0.7596319414550151, "grad_norm": 1.7738821506500244, "learning_rate": 6.798481725358438e-06, "loss": 3.792, "step": 14117 }, { "epoch": 0.759685751183814, "grad_norm": 2.550678253173828, "learning_rate": 6.795584867689772e-06, "loss": 3.5273, "step": 14118 }, { "epoch": 0.759739560912613, "grad_norm": 2.1661412715911865, "learning_rate": 6.792688530254343e-06, "loss": 4.273, "step": 14119 }, { "epoch": 0.759793370641412, "grad_norm": 2.4281747341156006, "learning_rate": 6.789792713134896e-06, "loss": 3.7936, "step": 14120 }, { "epoch": 0.7598471803702109, "grad_norm": 4.127760887145996, "learning_rate": 6.786897416414195e-06, "loss": 2.9026, "step": 14121 }, { "epoch": 0.7599009900990099, "grad_norm": 3.7011094093322754, "learning_rate": 6.784002640174969e-06, "loss": 3.114, "step": 14122 }, { "epoch": 0.7599547998278089, "grad_norm": 3.067655324935913, "learning_rate": 6.78110838449996e-06, "loss": 3.7826, "step": 14123 }, { "epoch": 0.7600086095566079, "grad_norm": 2.9045190811157227, "learning_rate": 6.77821464947187e-06, "loss": 3.2461, "step": 14124 }, { "epoch": 0.7600624192854069, "grad_norm": 3.2478394508361816, "learning_rate": 6.775321435173393e-06, "loss": 4.0637, "step": 14125 }, { "epoch": 0.7601162290142057, "grad_norm": 1.2255371809005737, "learning_rate": 6.7724287416872145e-06, "loss": 4.4403, "step": 14126 }, { "epoch": 0.7601700387430047, "grad_norm": 1.887765884399414, "learning_rate": 6.7695365690959935e-06, "loss": 4.1944, "step": 14127 }, { "epoch": 0.7602238484718037, "grad_norm": 3.3657898902893066, "learning_rate": 6.766644917482384e-06, "loss": 3.5224, "step": 14128 }, { "epoch": 0.7602776582006027, "grad_norm": 2.1901373863220215, "learning_rate": 6.76375378692902e-06, "loss": 3.8641, "step": 14129 }, { "epoch": 0.7603314679294016, "grad_norm": 2.21201491355896, "learning_rate": 6.760863177518523e-06, "loss": 3.7327, "step": 14130 }, { "epoch": 0.7603852776582006, "grad_norm": 2.493072748184204, "learning_rate": 6.757973089333499e-06, "loss": 3.4595, "step": 14131 }, { "epoch": 0.7604390873869996, "grad_norm": 2.838931083679199, "learning_rate": 6.75508352245654e-06, "loss": 3.9303, "step": 14132 }, { "epoch": 0.7604928971157985, "grad_norm": 1.764204978942871, "learning_rate": 6.752194476970214e-06, "loss": 3.8606, "step": 14133 }, { "epoch": 0.7605467068445975, "grad_norm": 2.300071954727173, "learning_rate": 6.749305952957103e-06, "loss": 4.0314, "step": 14134 }, { "epoch": 0.7606005165733964, "grad_norm": 3.2830309867858887, "learning_rate": 6.746417950499731e-06, "loss": 2.6636, "step": 14135 }, { "epoch": 0.7606543263021954, "grad_norm": 2.7547333240509033, "learning_rate": 6.743530469680637e-06, "loss": 3.6196, "step": 14136 }, { "epoch": 0.7607081360309944, "grad_norm": 1.4573054313659668, "learning_rate": 6.740643510582339e-06, "loss": 3.5967, "step": 14137 }, { "epoch": 0.7607619457597934, "grad_norm": 1.9421195983886719, "learning_rate": 6.737757073287332e-06, "loss": 4.0534, "step": 14138 }, { "epoch": 0.7608157554885924, "grad_norm": 3.132725238800049, "learning_rate": 6.734871157878111e-06, "loss": 3.6439, "step": 14139 }, { "epoch": 0.7608695652173914, "grad_norm": 1.2108569145202637, "learning_rate": 6.731985764437148e-06, "loss": 4.6175, "step": 14140 }, { "epoch": 0.7609233749461902, "grad_norm": 4.655367374420166, "learning_rate": 6.729100893046897e-06, "loss": 3.2638, "step": 14141 }, { "epoch": 0.7609771846749892, "grad_norm": 2.6316118240356445, "learning_rate": 6.7262165437897986e-06, "loss": 3.7354, "step": 14142 }, { "epoch": 0.7610309944037882, "grad_norm": 3.132115125656128, "learning_rate": 6.723332716748282e-06, "loss": 3.9056, "step": 14143 }, { "epoch": 0.7610848041325872, "grad_norm": 2.2236876487731934, "learning_rate": 6.720449412004756e-06, "loss": 3.2662, "step": 14144 }, { "epoch": 0.7611386138613861, "grad_norm": 3.950784206390381, "learning_rate": 6.717566629641622e-06, "loss": 3.9741, "step": 14145 }, { "epoch": 0.7611924235901851, "grad_norm": 2.431129217147827, "learning_rate": 6.714684369741259e-06, "loss": 3.3726, "step": 14146 }, { "epoch": 0.7612462333189841, "grad_norm": 2.6445095539093018, "learning_rate": 6.711802632386033e-06, "loss": 3.6556, "step": 14147 }, { "epoch": 0.7613000430477831, "grad_norm": 3.8905556201934814, "learning_rate": 6.708921417658292e-06, "loss": 4.4003, "step": 14148 }, { "epoch": 0.761353852776582, "grad_norm": 3.011080265045166, "learning_rate": 6.706040725640387e-06, "loss": 4.2055, "step": 14149 }, { "epoch": 0.7614076625053809, "grad_norm": 2.056577205657959, "learning_rate": 6.703160556414642e-06, "loss": 3.7557, "step": 14150 }, { "epoch": 0.7614614722341799, "grad_norm": 3.9792189598083496, "learning_rate": 6.700280910063345e-06, "loss": 2.5824, "step": 14151 }, { "epoch": 0.7615152819629789, "grad_norm": 2.7183570861816406, "learning_rate": 6.697401786668803e-06, "loss": 3.3832, "step": 14152 }, { "epoch": 0.7615690916917779, "grad_norm": 2.8799047470092773, "learning_rate": 6.694523186313279e-06, "loss": 3.7516, "step": 14153 }, { "epoch": 0.7616229014205769, "grad_norm": 1.182767629623413, "learning_rate": 6.691645109079056e-06, "loss": 3.6211, "step": 14154 }, { "epoch": 0.7616767111493759, "grad_norm": 2.081181049346924, "learning_rate": 6.688767555048369e-06, "loss": 4.4146, "step": 14155 }, { "epoch": 0.7617305208781747, "grad_norm": 2.425058364868164, "learning_rate": 6.685890524303456e-06, "loss": 3.8804, "step": 14156 }, { "epoch": 0.7617843306069737, "grad_norm": 3.4874417781829834, "learning_rate": 6.6830140169265425e-06, "loss": 3.4991, "step": 14157 }, { "epoch": 0.7618381403357727, "grad_norm": 4.243896007537842, "learning_rate": 6.680138032999803e-06, "loss": 3.0521, "step": 14158 }, { "epoch": 0.7618919500645717, "grad_norm": 2.4794347286224365, "learning_rate": 6.677262572605453e-06, "loss": 4.0838, "step": 14159 }, { "epoch": 0.7619457597933706, "grad_norm": 2.2739555835723877, "learning_rate": 6.674387635825655e-06, "loss": 3.6282, "step": 14160 }, { "epoch": 0.7619995695221696, "grad_norm": 1.283685326576233, "learning_rate": 6.67151322274257e-06, "loss": 4.2889, "step": 14161 }, { "epoch": 0.7620533792509686, "grad_norm": 2.535799741744995, "learning_rate": 6.668639333438336e-06, "loss": 4.499, "step": 14162 }, { "epoch": 0.7621071889797676, "grad_norm": 1.201095461845398, "learning_rate": 6.665765967995088e-06, "loss": 4.2847, "step": 14163 }, { "epoch": 0.7621609987085665, "grad_norm": 1.8950258493423462, "learning_rate": 6.6628931264949265e-06, "loss": 3.9707, "step": 14164 }, { "epoch": 0.7622148084373654, "grad_norm": 3.8708298206329346, "learning_rate": 6.660020809019973e-06, "loss": 3.5844, "step": 14165 }, { "epoch": 0.7622686181661644, "grad_norm": 1.6726027727127075, "learning_rate": 6.657149015652289e-06, "loss": 4.0978, "step": 14166 }, { "epoch": 0.7623224278949634, "grad_norm": 3.3350000381469727, "learning_rate": 6.65427774647395e-06, "loss": 3.6213, "step": 14167 }, { "epoch": 0.7623762376237624, "grad_norm": 2.707233190536499, "learning_rate": 6.651407001567009e-06, "loss": 2.9584, "step": 14168 }, { "epoch": 0.7624300473525614, "grad_norm": 2.231668710708618, "learning_rate": 6.648536781013495e-06, "loss": 3.6124, "step": 14169 }, { "epoch": 0.7624838570813603, "grad_norm": 3.993258476257324, "learning_rate": 6.645667084895449e-06, "loss": 3.9162, "step": 14170 }, { "epoch": 0.7625376668101593, "grad_norm": 2.2783451080322266, "learning_rate": 6.6427979132948705e-06, "loss": 4.6095, "step": 14171 }, { "epoch": 0.7625914765389582, "grad_norm": 2.9322683811187744, "learning_rate": 6.639929266293751e-06, "loss": 3.8502, "step": 14172 }, { "epoch": 0.7626452862677572, "grad_norm": 2.946993112564087, "learning_rate": 6.6370611439740715e-06, "loss": 3.4873, "step": 14173 }, { "epoch": 0.7626990959965562, "grad_norm": 2.2071146965026855, "learning_rate": 6.634193546417794e-06, "loss": 4.0905, "step": 14174 }, { "epoch": 0.7627529057253551, "grad_norm": 1.9704902172088623, "learning_rate": 6.631326473706867e-06, "loss": 4.392, "step": 14175 }, { "epoch": 0.7628067154541541, "grad_norm": 2.991237163543701, "learning_rate": 6.628459925923222e-06, "loss": 2.9637, "step": 14176 }, { "epoch": 0.7628605251829531, "grad_norm": 2.2312872409820557, "learning_rate": 6.62559390314878e-06, "loss": 3.7765, "step": 14177 }, { "epoch": 0.7629143349117521, "grad_norm": 1.6856147050857544, "learning_rate": 6.622728405465442e-06, "loss": 4.4997, "step": 14178 }, { "epoch": 0.762968144640551, "grad_norm": 4.301580905914307, "learning_rate": 6.619863432955093e-06, "loss": 2.0876, "step": 14179 }, { "epoch": 0.7630219543693499, "grad_norm": 3.7480454444885254, "learning_rate": 6.616998985699621e-06, "loss": 2.7704, "step": 14180 }, { "epoch": 0.7630757640981489, "grad_norm": 2.7741546630859375, "learning_rate": 6.614135063780866e-06, "loss": 3.9494, "step": 14181 }, { "epoch": 0.7631295738269479, "grad_norm": 3.7358250617980957, "learning_rate": 6.61127166728068e-06, "loss": 3.1594, "step": 14182 }, { "epoch": 0.7631833835557469, "grad_norm": 3.4885172843933105, "learning_rate": 6.608408796280891e-06, "loss": 3.7946, "step": 14183 }, { "epoch": 0.7632371932845459, "grad_norm": 3.1855554580688477, "learning_rate": 6.605546450863304e-06, "loss": 3.5468, "step": 14184 }, { "epoch": 0.7632910030133448, "grad_norm": 1.690807580947876, "learning_rate": 6.602684631109729e-06, "loss": 3.8088, "step": 14185 }, { "epoch": 0.7633448127421438, "grad_norm": 2.825187921524048, "learning_rate": 6.599823337101946e-06, "loss": 3.7925, "step": 14186 }, { "epoch": 0.7633986224709427, "grad_norm": 3.671830654144287, "learning_rate": 6.596962568921719e-06, "loss": 4.0958, "step": 14187 }, { "epoch": 0.7634524321997417, "grad_norm": 3.3582592010498047, "learning_rate": 6.594102326650814e-06, "loss": 2.199, "step": 14188 }, { "epoch": 0.7635062419285407, "grad_norm": 1.8524702787399292, "learning_rate": 6.591242610370943e-06, "loss": 3.9506, "step": 14189 }, { "epoch": 0.7635600516573396, "grad_norm": 2.2516560554504395, "learning_rate": 6.588383420163852e-06, "loss": 3.9344, "step": 14190 }, { "epoch": 0.7636138613861386, "grad_norm": 2.9628329277038574, "learning_rate": 6.585524756111239e-06, "loss": 3.9916, "step": 14191 }, { "epoch": 0.7636676711149376, "grad_norm": 3.6068761348724365, "learning_rate": 6.5826666182948025e-06, "loss": 3.4067, "step": 14192 }, { "epoch": 0.7637214808437366, "grad_norm": 1.9717683792114258, "learning_rate": 6.579809006796214e-06, "loss": 3.7889, "step": 14193 }, { "epoch": 0.7637752905725355, "grad_norm": 1.2366833686828613, "learning_rate": 6.5769519216971414e-06, "loss": 4.7285, "step": 14194 }, { "epoch": 0.7638291003013344, "grad_norm": 4.367438316345215, "learning_rate": 6.57409536307923e-06, "loss": 2.7852, "step": 14195 }, { "epoch": 0.7638829100301334, "grad_norm": 2.622938632965088, "learning_rate": 6.5712393310241145e-06, "loss": 4.1599, "step": 14196 }, { "epoch": 0.7639367197589324, "grad_norm": 2.151182174682617, "learning_rate": 6.568383825613411e-06, "loss": 4.088, "step": 14197 }, { "epoch": 0.7639905294877314, "grad_norm": 3.1767165660858154, "learning_rate": 6.565528846928723e-06, "loss": 3.8815, "step": 14198 }, { "epoch": 0.7640443392165304, "grad_norm": 3.344062328338623, "learning_rate": 6.562674395051638e-06, "loss": 4.3604, "step": 14199 }, { "epoch": 0.7640981489453293, "grad_norm": 2.85825252532959, "learning_rate": 6.559820470063718e-06, "loss": 3.7231, "step": 14200 }, { "epoch": 0.7641519586741283, "grad_norm": 3.0089876651763916, "learning_rate": 6.556967072046541e-06, "loss": 4.078, "step": 14201 }, { "epoch": 0.7642057684029272, "grad_norm": 2.952425003051758, "learning_rate": 6.554114201081638e-06, "loss": 2.9548, "step": 14202 }, { "epoch": 0.7642595781317262, "grad_norm": 1.7179549932479858, "learning_rate": 6.551261857250543e-06, "loss": 3.7519, "step": 14203 }, { "epoch": 0.7643133878605252, "grad_norm": 3.7553744316101074, "learning_rate": 6.54841004063475e-06, "loss": 3.6969, "step": 14204 }, { "epoch": 0.7643671975893241, "grad_norm": 2.6656839847564697, "learning_rate": 6.545558751315778e-06, "loss": 3.5224, "step": 14205 }, { "epoch": 0.7644210073181231, "grad_norm": 2.101457357406616, "learning_rate": 6.542707989375099e-06, "loss": 3.9188, "step": 14206 }, { "epoch": 0.7644748170469221, "grad_norm": 2.76759934425354, "learning_rate": 6.539857754894179e-06, "loss": 3.9482, "step": 14207 }, { "epoch": 0.7645286267757211, "grad_norm": 1.887323260307312, "learning_rate": 6.537008047954477e-06, "loss": 4.1564, "step": 14208 }, { "epoch": 0.7645824365045201, "grad_norm": 1.4055662155151367, "learning_rate": 6.5341588686374214e-06, "loss": 4.199, "step": 14209 }, { "epoch": 0.7646362462333189, "grad_norm": 3.518059015274048, "learning_rate": 6.531310217024433e-06, "loss": 3.5435, "step": 14210 }, { "epoch": 0.7646900559621179, "grad_norm": 3.378403425216675, "learning_rate": 6.528462093196938e-06, "loss": 3.3818, "step": 14211 }, { "epoch": 0.7647438656909169, "grad_norm": 3.618806838989258, "learning_rate": 6.525614497236305e-06, "loss": 3.6659, "step": 14212 }, { "epoch": 0.7647976754197159, "grad_norm": 1.7896246910095215, "learning_rate": 6.522767429223919e-06, "loss": 4.1971, "step": 14213 }, { "epoch": 0.7648514851485149, "grad_norm": 3.2927443981170654, "learning_rate": 6.519920889241146e-06, "loss": 3.8844, "step": 14214 }, { "epoch": 0.7649052948773138, "grad_norm": 4.288501739501953, "learning_rate": 6.517074877369317e-06, "loss": 3.6538, "step": 14215 }, { "epoch": 0.7649591046061128, "grad_norm": 1.9753940105438232, "learning_rate": 6.5142293936897834e-06, "loss": 3.9649, "step": 14216 }, { "epoch": 0.7650129143349117, "grad_norm": 2.135430335998535, "learning_rate": 6.511384438283855e-06, "loss": 3.1626, "step": 14217 }, { "epoch": 0.7650667240637107, "grad_norm": 4.497433662414551, "learning_rate": 6.508540011232836e-06, "loss": 3.4115, "step": 14218 }, { "epoch": 0.7651205337925097, "grad_norm": 3.8651187419891357, "learning_rate": 6.505696112617998e-06, "loss": 4.2214, "step": 14219 }, { "epoch": 0.7651743435213086, "grad_norm": 1.5250900983810425, "learning_rate": 6.502852742520615e-06, "loss": 4.7214, "step": 14220 }, { "epoch": 0.7652281532501076, "grad_norm": 3.423250436782837, "learning_rate": 6.500009901021958e-06, "loss": 4.1107, "step": 14221 }, { "epoch": 0.7652819629789066, "grad_norm": 4.103623390197754, "learning_rate": 6.49716758820326e-06, "loss": 3.3428, "step": 14222 }, { "epoch": 0.7653357727077056, "grad_norm": 2.3550894260406494, "learning_rate": 6.494325804145743e-06, "loss": 3.7789, "step": 14223 }, { "epoch": 0.7653895824365046, "grad_norm": 3.74229097366333, "learning_rate": 6.4914845489306206e-06, "loss": 4.2167, "step": 14224 }, { "epoch": 0.7654433921653034, "grad_norm": 2.729006052017212, "learning_rate": 6.48864382263909e-06, "loss": 3.9575, "step": 14225 }, { "epoch": 0.7654972018941024, "grad_norm": 4.882545471191406, "learning_rate": 6.4858036253523265e-06, "loss": 3.6772, "step": 14226 }, { "epoch": 0.7655510116229014, "grad_norm": 2.077711582183838, "learning_rate": 6.4829639571515e-06, "loss": 3.5973, "step": 14227 }, { "epoch": 0.7656048213517004, "grad_norm": 3.7583205699920654, "learning_rate": 6.480124818117755e-06, "loss": 3.7884, "step": 14228 }, { "epoch": 0.7656586310804994, "grad_norm": 3.3605411052703857, "learning_rate": 6.477286208332234e-06, "loss": 3.9938, "step": 14229 }, { "epoch": 0.7657124408092983, "grad_norm": 3.1949377059936523, "learning_rate": 6.4744481278760514e-06, "loss": 3.3666, "step": 14230 }, { "epoch": 0.7657662505380973, "grad_norm": 2.4436612129211426, "learning_rate": 6.471610576830306e-06, "loss": 3.9134, "step": 14231 }, { "epoch": 0.7658200602668963, "grad_norm": 3.04276704788208, "learning_rate": 6.468773555276103e-06, "loss": 3.839, "step": 14232 }, { "epoch": 0.7658738699956952, "grad_norm": 1.866072654724121, "learning_rate": 6.465937063294508e-06, "loss": 3.5393, "step": 14233 }, { "epoch": 0.7659276797244942, "grad_norm": 2.9915213584899902, "learning_rate": 6.46310110096659e-06, "loss": 3.3395, "step": 14234 }, { "epoch": 0.7659814894532931, "grad_norm": 3.4155569076538086, "learning_rate": 6.460265668373366e-06, "loss": 3.7942, "step": 14235 }, { "epoch": 0.7660352991820921, "grad_norm": 2.6597650051116943, "learning_rate": 6.457430765595893e-06, "loss": 4.4575, "step": 14236 }, { "epoch": 0.7660891089108911, "grad_norm": 2.4491984844207764, "learning_rate": 6.454596392715173e-06, "loss": 3.9179, "step": 14237 }, { "epoch": 0.7661429186396901, "grad_norm": 3.601857900619507, "learning_rate": 6.45176254981221e-06, "loss": 3.2672, "step": 14238 }, { "epoch": 0.7661967283684891, "grad_norm": 2.2051215171813965, "learning_rate": 6.4489292369679824e-06, "loss": 3.8529, "step": 14239 }, { "epoch": 0.7662505380972879, "grad_norm": 2.654208183288574, "learning_rate": 6.446096454263462e-06, "loss": 3.6691, "step": 14240 }, { "epoch": 0.7663043478260869, "grad_norm": 2.657139301300049, "learning_rate": 6.443264201779597e-06, "loss": 2.8996, "step": 14241 }, { "epoch": 0.7663581575548859, "grad_norm": 2.638012647628784, "learning_rate": 6.440432479597333e-06, "loss": 4.2713, "step": 14242 }, { "epoch": 0.7664119672836849, "grad_norm": 3.440204620361328, "learning_rate": 6.43760128779759e-06, "loss": 4.4104, "step": 14243 }, { "epoch": 0.7664657770124839, "grad_norm": 3.9438743591308594, "learning_rate": 6.434770626461273e-06, "loss": 3.886, "step": 14244 }, { "epoch": 0.7665195867412828, "grad_norm": 2.242443084716797, "learning_rate": 6.431940495669278e-06, "loss": 4.5528, "step": 14245 }, { "epoch": 0.7665733964700818, "grad_norm": 3.8790032863616943, "learning_rate": 6.429110895502471e-06, "loss": 3.5935, "step": 14246 }, { "epoch": 0.7666272061988808, "grad_norm": 2.612246036529541, "learning_rate": 6.4262818260417356e-06, "loss": 4.1478, "step": 14247 }, { "epoch": 0.7666810159276797, "grad_norm": 2.1837353706359863, "learning_rate": 6.423453287367909e-06, "loss": 4.0338, "step": 14248 }, { "epoch": 0.7667348256564787, "grad_norm": 1.747641921043396, "learning_rate": 6.420625279561829e-06, "loss": 3.9282, "step": 14249 }, { "epoch": 0.7667886353852776, "grad_norm": 4.504411697387695, "learning_rate": 6.417797802704295e-06, "loss": 2.5581, "step": 14250 }, { "epoch": 0.7668424451140766, "grad_norm": 3.143362283706665, "learning_rate": 6.4149708568761155e-06, "loss": 3.9539, "step": 14251 }, { "epoch": 0.7668962548428756, "grad_norm": 2.4451804161071777, "learning_rate": 6.412144442158089e-06, "loss": 4.122, "step": 14252 }, { "epoch": 0.7669500645716746, "grad_norm": 2.7886269092559814, "learning_rate": 6.409318558630978e-06, "loss": 4.3883, "step": 14253 }, { "epoch": 0.7670038743004736, "grad_norm": 4.03074312210083, "learning_rate": 6.4064932063755385e-06, "loss": 3.2037, "step": 14254 }, { "epoch": 0.7670576840292725, "grad_norm": 2.5685133934020996, "learning_rate": 6.403668385472511e-06, "loss": 4.0051, "step": 14255 }, { "epoch": 0.7671114937580714, "grad_norm": 3.6134109497070312, "learning_rate": 6.4008440960026254e-06, "loss": 4.0542, "step": 14256 }, { "epoch": 0.7671653034868704, "grad_norm": 3.0989291667938232, "learning_rate": 6.39802033804659e-06, "loss": 4.0031, "step": 14257 }, { "epoch": 0.7672191132156694, "grad_norm": 3.5752742290496826, "learning_rate": 6.3951971116851e-06, "loss": 4.5529, "step": 14258 }, { "epoch": 0.7672729229444684, "grad_norm": 2.112185478210449, "learning_rate": 6.3923744169988335e-06, "loss": 4.2736, "step": 14259 }, { "epoch": 0.7673267326732673, "grad_norm": 1.5034583806991577, "learning_rate": 6.389552254068459e-06, "loss": 4.386, "step": 14260 }, { "epoch": 0.7673805424020663, "grad_norm": 3.9093055725097656, "learning_rate": 6.386730622974624e-06, "loss": 2.3251, "step": 14261 }, { "epoch": 0.7674343521308653, "grad_norm": 3.2099828720092773, "learning_rate": 6.383909523797957e-06, "loss": 3.1674, "step": 14262 }, { "epoch": 0.7674881618596642, "grad_norm": 3.6751136779785156, "learning_rate": 6.381088956619091e-06, "loss": 3.4441, "step": 14263 }, { "epoch": 0.7675419715884632, "grad_norm": 1.9729608297348022, "learning_rate": 6.378268921518632e-06, "loss": 4.113, "step": 14264 }, { "epoch": 0.7675957813172621, "grad_norm": 5.239009380340576, "learning_rate": 6.375449418577153e-06, "loss": 2.9697, "step": 14265 }, { "epoch": 0.7676495910460611, "grad_norm": 1.8464452028274536, "learning_rate": 6.3726304478752305e-06, "loss": 4.3332, "step": 14266 }, { "epoch": 0.7677034007748601, "grad_norm": 3.11069393157959, "learning_rate": 6.369812009493431e-06, "loss": 3.2224, "step": 14267 }, { "epoch": 0.7677572105036591, "grad_norm": 2.025432825088501, "learning_rate": 6.366994103512297e-06, "loss": 4.2815, "step": 14268 }, { "epoch": 0.7678110202324581, "grad_norm": 2.7094714641571045, "learning_rate": 6.364176730012356e-06, "loss": 2.8575, "step": 14269 }, { "epoch": 0.767864829961257, "grad_norm": 3.0379457473754883, "learning_rate": 6.361359889074117e-06, "loss": 3.1763, "step": 14270 }, { "epoch": 0.7679186396900559, "grad_norm": 2.278785228729248, "learning_rate": 6.358543580778084e-06, "loss": 4.5501, "step": 14271 }, { "epoch": 0.7679724494188549, "grad_norm": 3.9148647785186768, "learning_rate": 6.355727805204731e-06, "loss": 2.909, "step": 14272 }, { "epoch": 0.7680262591476539, "grad_norm": 3.276334285736084, "learning_rate": 6.352912562434535e-06, "loss": 3.5597, "step": 14273 }, { "epoch": 0.7680800688764529, "grad_norm": 4.527059555053711, "learning_rate": 6.3500978525479395e-06, "loss": 3.1493, "step": 14274 }, { "epoch": 0.7681338786052518, "grad_norm": 1.4237111806869507, "learning_rate": 6.347283675625388e-06, "loss": 4.0645, "step": 14275 }, { "epoch": 0.7681876883340508, "grad_norm": 2.0414364337921143, "learning_rate": 6.344470031747296e-06, "loss": 3.7843, "step": 14276 }, { "epoch": 0.7682414980628498, "grad_norm": 3.53265643119812, "learning_rate": 6.341656920994065e-06, "loss": 4.1638, "step": 14277 }, { "epoch": 0.7682953077916488, "grad_norm": 3.2190914154052734, "learning_rate": 6.338844343446104e-06, "loss": 3.5859, "step": 14278 }, { "epoch": 0.7683491175204477, "grad_norm": 2.2472288608551025, "learning_rate": 6.33603229918378e-06, "loss": 3.9285, "step": 14279 }, { "epoch": 0.7684029272492466, "grad_norm": 2.692284345626831, "learning_rate": 6.333220788287459e-06, "loss": 4.1307, "step": 14280 }, { "epoch": 0.7684567369780456, "grad_norm": 1.6908645629882812, "learning_rate": 6.3304098108374735e-06, "loss": 4.3991, "step": 14281 }, { "epoch": 0.7685105467068446, "grad_norm": 1.8119032382965088, "learning_rate": 6.32759936691415e-06, "loss": 4.4085, "step": 14282 }, { "epoch": 0.7685643564356436, "grad_norm": 3.1657049655914307, "learning_rate": 6.324789456597824e-06, "loss": 3.1102, "step": 14283 }, { "epoch": 0.7686181661644426, "grad_norm": 3.4832217693328857, "learning_rate": 6.321980079968784e-06, "loss": 3.1646, "step": 14284 }, { "epoch": 0.7686719758932415, "grad_norm": 4.142110824584961, "learning_rate": 6.319171237107316e-06, "loss": 3.4928, "step": 14285 }, { "epoch": 0.7687257856220404, "grad_norm": 2.8729465007781982, "learning_rate": 6.316362928093686e-06, "loss": 3.1539, "step": 14286 }, { "epoch": 0.7687795953508394, "grad_norm": 2.276944398880005, "learning_rate": 6.313555153008152e-06, "loss": 4.0148, "step": 14287 }, { "epoch": 0.7688334050796384, "grad_norm": 2.3418784141540527, "learning_rate": 6.310747911930953e-06, "loss": 3.7375, "step": 14288 }, { "epoch": 0.7688872148084374, "grad_norm": 4.047316551208496, "learning_rate": 6.307941204942308e-06, "loss": 3.4406, "step": 14289 }, { "epoch": 0.7689410245372363, "grad_norm": 2.438556671142578, "learning_rate": 6.305135032122428e-06, "loss": 3.5748, "step": 14290 }, { "epoch": 0.7689948342660353, "grad_norm": 4.4551239013671875, "learning_rate": 6.3023293935515065e-06, "loss": 3.4411, "step": 14291 }, { "epoch": 0.7690486439948343, "grad_norm": 2.4545645713806152, "learning_rate": 6.299524289309719e-06, "loss": 4.1544, "step": 14292 }, { "epoch": 0.7691024537236333, "grad_norm": 2.354327440261841, "learning_rate": 6.296719719477223e-06, "loss": 3.4777, "step": 14293 }, { "epoch": 0.7691562634524322, "grad_norm": 2.7864162921905518, "learning_rate": 6.293915684134177e-06, "loss": 3.9187, "step": 14294 }, { "epoch": 0.7692100731812311, "grad_norm": 4.329212188720703, "learning_rate": 6.291112183360717e-06, "loss": 4.3506, "step": 14295 }, { "epoch": 0.7692638829100301, "grad_norm": 3.181764841079712, "learning_rate": 6.28830921723694e-06, "loss": 3.0461, "step": 14296 }, { "epoch": 0.7693176926388291, "grad_norm": 2.9242427349090576, "learning_rate": 6.285506785842951e-06, "loss": 4.1915, "step": 14297 }, { "epoch": 0.7693715023676281, "grad_norm": 1.9632816314697266, "learning_rate": 6.28270488925885e-06, "loss": 4.0312, "step": 14298 }, { "epoch": 0.7694253120964271, "grad_norm": 3.936556577682495, "learning_rate": 6.279903527564699e-06, "loss": 3.5964, "step": 14299 }, { "epoch": 0.769479121825226, "grad_norm": 3.3733434677124023, "learning_rate": 6.277102700840554e-06, "loss": 3.8589, "step": 14300 }, { "epoch": 0.7695329315540249, "grad_norm": 2.9710469245910645, "learning_rate": 6.274302409166455e-06, "loss": 3.547, "step": 14301 }, { "epoch": 0.7695867412828239, "grad_norm": 2.7699553966522217, "learning_rate": 6.271502652622427e-06, "loss": 4.1714, "step": 14302 }, { "epoch": 0.7696405510116229, "grad_norm": 1.6231040954589844, "learning_rate": 6.268703431288478e-06, "loss": 4.5836, "step": 14303 }, { "epoch": 0.7696943607404219, "grad_norm": 1.9895317554473877, "learning_rate": 6.2659047452446055e-06, "loss": 3.7548, "step": 14304 }, { "epoch": 0.7697481704692208, "grad_norm": 2.169299602508545, "learning_rate": 6.263106594570786e-06, "loss": 4.4577, "step": 14305 }, { "epoch": 0.7698019801980198, "grad_norm": 3.4445271492004395, "learning_rate": 6.2603089793469825e-06, "loss": 3.9074, "step": 14306 }, { "epoch": 0.7698557899268188, "grad_norm": 2.2593417167663574, "learning_rate": 6.257511899653145e-06, "loss": 3.7495, "step": 14307 }, { "epoch": 0.7699095996556178, "grad_norm": 2.146303653717041, "learning_rate": 6.254715355569201e-06, "loss": 4.019, "step": 14308 }, { "epoch": 0.7699634093844167, "grad_norm": 3.0487916469573975, "learning_rate": 6.251919347175078e-06, "loss": 3.5532, "step": 14309 }, { "epoch": 0.7700172191132156, "grad_norm": 1.879445195198059, "learning_rate": 6.249123874550683e-06, "loss": 4.1803, "step": 14310 }, { "epoch": 0.7700710288420146, "grad_norm": 2.6384406089782715, "learning_rate": 6.246328937775886e-06, "loss": 3.9561, "step": 14311 }, { "epoch": 0.7701248385708136, "grad_norm": 1.7322299480438232, "learning_rate": 6.243534536930565e-06, "loss": 3.9229, "step": 14312 }, { "epoch": 0.7701786482996126, "grad_norm": 1.7792553901672363, "learning_rate": 6.2407406720945725e-06, "loss": 4.3822, "step": 14313 }, { "epoch": 0.7702324580284116, "grad_norm": 1.7340890169143677, "learning_rate": 6.237947343347761e-06, "loss": 4.4625, "step": 14314 }, { "epoch": 0.7702862677572105, "grad_norm": 2.5533909797668457, "learning_rate": 6.23515455076995e-06, "loss": 3.9172, "step": 14315 }, { "epoch": 0.7703400774860095, "grad_norm": 1.8263312578201294, "learning_rate": 6.232362294440952e-06, "loss": 3.156, "step": 14316 }, { "epoch": 0.7703938872148084, "grad_norm": 2.6610679626464844, "learning_rate": 6.22957057444056e-06, "loss": 3.3789, "step": 14317 }, { "epoch": 0.7704476969436074, "grad_norm": 1.2064753770828247, "learning_rate": 6.226779390848555e-06, "loss": 4.58, "step": 14318 }, { "epoch": 0.7705015066724064, "grad_norm": 2.5770301818847656, "learning_rate": 6.223988743744699e-06, "loss": 4.3319, "step": 14319 }, { "epoch": 0.7705553164012053, "grad_norm": 1.4520556926727295, "learning_rate": 6.2211986332087465e-06, "loss": 4.4159, "step": 14320 }, { "epoch": 0.7706091261300043, "grad_norm": 2.078923463821411, "learning_rate": 6.218409059320426e-06, "loss": 3.9069, "step": 14321 }, { "epoch": 0.7706629358588033, "grad_norm": 3.1557552814483643, "learning_rate": 6.215620022159458e-06, "loss": 4.3311, "step": 14322 }, { "epoch": 0.7707167455876023, "grad_norm": 2.094090461730957, "learning_rate": 6.212831521805546e-06, "loss": 3.8033, "step": 14323 }, { "epoch": 0.7707705553164012, "grad_norm": 2.233379364013672, "learning_rate": 6.210043558338369e-06, "loss": 4.2759, "step": 14324 }, { "epoch": 0.7708243650452001, "grad_norm": 2.9410979747772217, "learning_rate": 6.207256131837624e-06, "loss": 3.1982, "step": 14325 }, { "epoch": 0.7708781747739991, "grad_norm": 3.591472864151001, "learning_rate": 6.204469242382946e-06, "loss": 3.9474, "step": 14326 }, { "epoch": 0.7709319845027981, "grad_norm": 3.056119918823242, "learning_rate": 6.201682890053981e-06, "loss": 3.8456, "step": 14327 }, { "epoch": 0.7709857942315971, "grad_norm": 1.6449118852615356, "learning_rate": 6.198897074930352e-06, "loss": 3.8359, "step": 14328 }, { "epoch": 0.7710396039603961, "grad_norm": 1.4168680906295776, "learning_rate": 6.1961117970916805e-06, "loss": 4.2242, "step": 14329 }, { "epoch": 0.771093413689195, "grad_norm": 2.968806266784668, "learning_rate": 6.193327056617559e-06, "loss": 4.1002, "step": 14330 }, { "epoch": 0.771147223417994, "grad_norm": 1.8718966245651245, "learning_rate": 6.190542853587566e-06, "loss": 3.538, "step": 14331 }, { "epoch": 0.7712010331467929, "grad_norm": 2.086970329284668, "learning_rate": 6.187759188081266e-06, "loss": 3.4594, "step": 14332 }, { "epoch": 0.7712548428755919, "grad_norm": 3.7736783027648926, "learning_rate": 6.184976060178211e-06, "loss": 3.0436, "step": 14333 }, { "epoch": 0.7713086526043909, "grad_norm": 3.3947503566741943, "learning_rate": 6.1821934699579305e-06, "loss": 4.0174, "step": 14334 }, { "epoch": 0.7713624623331898, "grad_norm": 2.199819326400757, "learning_rate": 6.17941141749995e-06, "loss": 3.3454, "step": 14335 }, { "epoch": 0.7714162720619888, "grad_norm": 2.1958606243133545, "learning_rate": 6.1766299028837685e-06, "loss": 4.4662, "step": 14336 }, { "epoch": 0.7714700817907878, "grad_norm": 4.198714733123779, "learning_rate": 6.173848926188877e-06, "loss": 2.9928, "step": 14337 }, { "epoch": 0.7715238915195868, "grad_norm": 1.9316107034683228, "learning_rate": 6.171068487494744e-06, "loss": 3.9759, "step": 14338 }, { "epoch": 0.7715777012483858, "grad_norm": 2.8511624336242676, "learning_rate": 6.168288586880824e-06, "loss": 2.8269, "step": 14339 }, { "epoch": 0.7716315109771846, "grad_norm": 4.8460307121276855, "learning_rate": 6.165509224426572e-06, "loss": 3.8409, "step": 14340 }, { "epoch": 0.7716853207059836, "grad_norm": 3.1150662899017334, "learning_rate": 6.162730400211414e-06, "loss": 3.8771, "step": 14341 }, { "epoch": 0.7717391304347826, "grad_norm": 2.3266499042510986, "learning_rate": 6.159952114314749e-06, "loss": 4.0176, "step": 14342 }, { "epoch": 0.7717929401635816, "grad_norm": 2.78517484664917, "learning_rate": 6.1571743668159795e-06, "loss": 2.9586, "step": 14343 }, { "epoch": 0.7718467498923806, "grad_norm": 3.605860710144043, "learning_rate": 6.154397157794475e-06, "loss": 3.3406, "step": 14344 }, { "epoch": 0.7719005596211795, "grad_norm": 3.9532151222229004, "learning_rate": 6.15162048732962e-06, "loss": 3.9789, "step": 14345 }, { "epoch": 0.7719543693499785, "grad_norm": 2.9275171756744385, "learning_rate": 6.148844355500754e-06, "loss": 3.3116, "step": 14346 }, { "epoch": 0.7720081790787774, "grad_norm": 2.4877610206604004, "learning_rate": 6.146068762387216e-06, "loss": 4.2302, "step": 14347 }, { "epoch": 0.7720619888075764, "grad_norm": 1.5138068199157715, "learning_rate": 6.143293708068318e-06, "loss": 3.9097, "step": 14348 }, { "epoch": 0.7721157985363754, "grad_norm": 3.8041226863861084, "learning_rate": 6.140519192623371e-06, "loss": 4.304, "step": 14349 }, { "epoch": 0.7721696082651743, "grad_norm": 3.4742369651794434, "learning_rate": 6.137745216131657e-06, "loss": 3.4421, "step": 14350 }, { "epoch": 0.7722234179939733, "grad_norm": 2.2122316360473633, "learning_rate": 6.134971778672452e-06, "loss": 3.4728, "step": 14351 }, { "epoch": 0.7722772277227723, "grad_norm": 2.1718759536743164, "learning_rate": 6.1321988803250104e-06, "loss": 3.5576, "step": 14352 }, { "epoch": 0.7723310374515713, "grad_norm": 2.27632999420166, "learning_rate": 6.12942652116858e-06, "loss": 3.9237, "step": 14353 }, { "epoch": 0.7723848471803703, "grad_norm": 4.389102458953857, "learning_rate": 6.126654701282372e-06, "loss": 3.8585, "step": 14354 }, { "epoch": 0.7724386569091691, "grad_norm": 2.779862880706787, "learning_rate": 6.123883420745619e-06, "loss": 4.1028, "step": 14355 }, { "epoch": 0.7724924666379681, "grad_norm": 2.5821824073791504, "learning_rate": 6.121112679637514e-06, "loss": 4.0005, "step": 14356 }, { "epoch": 0.7725462763667671, "grad_norm": 2.208820104598999, "learning_rate": 6.118342478037226e-06, "loss": 3.9598, "step": 14357 }, { "epoch": 0.7726000860955661, "grad_norm": 3.658099412918091, "learning_rate": 6.11557281602392e-06, "loss": 3.3764, "step": 14358 }, { "epoch": 0.7726538958243651, "grad_norm": 2.720592498779297, "learning_rate": 6.1128036936767445e-06, "loss": 4.4014, "step": 14359 }, { "epoch": 0.772707705553164, "grad_norm": 2.929109573364258, "learning_rate": 6.110035111074846e-06, "loss": 3.1365, "step": 14360 }, { "epoch": 0.772761515281963, "grad_norm": 4.344139099121094, "learning_rate": 6.107267068297337e-06, "loss": 3.6016, "step": 14361 }, { "epoch": 0.772815325010762, "grad_norm": 3.3692286014556885, "learning_rate": 6.104499565423319e-06, "loss": 3.6031, "step": 14362 }, { "epoch": 0.7728691347395609, "grad_norm": 1.447282314300537, "learning_rate": 6.101732602531879e-06, "loss": 3.8143, "step": 14363 }, { "epoch": 0.7729229444683599, "grad_norm": 2.0281765460968018, "learning_rate": 6.098966179702093e-06, "loss": 4.2654, "step": 14364 }, { "epoch": 0.7729767541971588, "grad_norm": 2.1793107986450195, "learning_rate": 6.096200297013014e-06, "loss": 4.4496, "step": 14365 }, { "epoch": 0.7730305639259578, "grad_norm": 2.0738067626953125, "learning_rate": 6.093434954543686e-06, "loss": 3.995, "step": 14366 }, { "epoch": 0.7730843736547568, "grad_norm": 2.069748878479004, "learning_rate": 6.090670152373134e-06, "loss": 3.5299, "step": 14367 }, { "epoch": 0.7731381833835558, "grad_norm": 1.7590993642807007, "learning_rate": 6.08790589058037e-06, "loss": 3.9476, "step": 14368 }, { "epoch": 0.7731919931123548, "grad_norm": 2.624385356903076, "learning_rate": 6.085142169244387e-06, "loss": 2.9232, "step": 14369 }, { "epoch": 0.7732458028411536, "grad_norm": 3.2677247524261475, "learning_rate": 6.0823789884441595e-06, "loss": 3.8678, "step": 14370 }, { "epoch": 0.7732996125699526, "grad_norm": 2.916278839111328, "learning_rate": 6.079616348258671e-06, "loss": 3.5771, "step": 14371 }, { "epoch": 0.7733534222987516, "grad_norm": 3.0097732543945312, "learning_rate": 6.07685424876685e-06, "loss": 3.2498, "step": 14372 }, { "epoch": 0.7734072320275506, "grad_norm": 3.5531322956085205, "learning_rate": 6.074092690047639e-06, "loss": 3.401, "step": 14373 }, { "epoch": 0.7734610417563496, "grad_norm": 2.7344424724578857, "learning_rate": 6.071331672179953e-06, "loss": 3.7475, "step": 14374 }, { "epoch": 0.7735148514851485, "grad_norm": 2.405118227005005, "learning_rate": 6.068571195242689e-06, "loss": 2.9462, "step": 14375 }, { "epoch": 0.7735686612139475, "grad_norm": 1.8099647760391235, "learning_rate": 6.065811259314749e-06, "loss": 3.9868, "step": 14376 }, { "epoch": 0.7736224709427465, "grad_norm": 1.72319757938385, "learning_rate": 6.063051864474994e-06, "loss": 3.8511, "step": 14377 }, { "epoch": 0.7736762806715454, "grad_norm": 3.316584587097168, "learning_rate": 6.060293010802284e-06, "loss": 1.9795, "step": 14378 }, { "epoch": 0.7737300904003444, "grad_norm": 1.3412175178527832, "learning_rate": 6.057534698375459e-06, "loss": 4.3583, "step": 14379 }, { "epoch": 0.7737839001291433, "grad_norm": 2.0259392261505127, "learning_rate": 6.05477692727334e-06, "loss": 3.7461, "step": 14380 }, { "epoch": 0.7738377098579423, "grad_norm": 2.8908286094665527, "learning_rate": 6.052019697574743e-06, "loss": 4.3241, "step": 14381 }, { "epoch": 0.7738915195867413, "grad_norm": 2.5235161781311035, "learning_rate": 6.049263009358455e-06, "loss": 3.7967, "step": 14382 }, { "epoch": 0.7739453293155403, "grad_norm": 3.0935750007629395, "learning_rate": 6.04650686270326e-06, "loss": 3.7212, "step": 14383 }, { "epoch": 0.7739991390443393, "grad_norm": 2.2655911445617676, "learning_rate": 6.043751257687924e-06, "loss": 3.9696, "step": 14384 }, { "epoch": 0.7740529487731382, "grad_norm": 2.66990327835083, "learning_rate": 6.04099619439118e-06, "loss": 3.9986, "step": 14385 }, { "epoch": 0.7741067585019371, "grad_norm": 1.8296267986297607, "learning_rate": 6.038241672891779e-06, "loss": 4.0445, "step": 14386 }, { "epoch": 0.7741605682307361, "grad_norm": 2.038525342941284, "learning_rate": 6.035487693268435e-06, "loss": 4.6396, "step": 14387 }, { "epoch": 0.7742143779595351, "grad_norm": 2.3400471210479736, "learning_rate": 6.032734255599839e-06, "loss": 3.8725, "step": 14388 }, { "epoch": 0.774268187688334, "grad_norm": 2.584033966064453, "learning_rate": 6.029981359964681e-06, "loss": 3.7622, "step": 14389 }, { "epoch": 0.774321997417133, "grad_norm": 1.9709159135818481, "learning_rate": 6.027229006441626e-06, "loss": 3.8205, "step": 14390 }, { "epoch": 0.774375807145932, "grad_norm": 2.7579379081726074, "learning_rate": 6.0244771951093435e-06, "loss": 4.1775, "step": 14391 }, { "epoch": 0.774429616874731, "grad_norm": 2.808159589767456, "learning_rate": 6.021725926046462e-06, "loss": 2.9765, "step": 14392 }, { "epoch": 0.7744834266035299, "grad_norm": 3.7904484272003174, "learning_rate": 6.0189751993316115e-06, "loss": 3.5812, "step": 14393 }, { "epoch": 0.7745372363323288, "grad_norm": 2.58577299118042, "learning_rate": 6.0162250150434e-06, "loss": 3.9745, "step": 14394 }, { "epoch": 0.7745910460611278, "grad_norm": 2.7107222080230713, "learning_rate": 6.013475373260405e-06, "loss": 3.7395, "step": 14395 }, { "epoch": 0.7746448557899268, "grad_norm": 2.021516799926758, "learning_rate": 6.010726274061224e-06, "loss": 3.3656, "step": 14396 }, { "epoch": 0.7746986655187258, "grad_norm": 4.197298526763916, "learning_rate": 6.00797771752441e-06, "loss": 3.8005, "step": 14397 }, { "epoch": 0.7747524752475248, "grad_norm": 4.228654861450195, "learning_rate": 6.00522970372851e-06, "loss": 2.6793, "step": 14398 }, { "epoch": 0.7748062849763238, "grad_norm": 2.717226028442383, "learning_rate": 6.002482232752055e-06, "loss": 4.093, "step": 14399 }, { "epoch": 0.7748600947051227, "grad_norm": 3.384622097015381, "learning_rate": 5.999735304673559e-06, "loss": 3.7674, "step": 14400 }, { "epoch": 0.7749139044339216, "grad_norm": 2.483978033065796, "learning_rate": 5.99698891957152e-06, "loss": 3.7958, "step": 14401 }, { "epoch": 0.7749677141627206, "grad_norm": 2.415696144104004, "learning_rate": 5.994243077524437e-06, "loss": 2.9496, "step": 14402 }, { "epoch": 0.7750215238915196, "grad_norm": 1.380421757698059, "learning_rate": 5.991497778610761e-06, "loss": 4.4946, "step": 14403 }, { "epoch": 0.7750753336203186, "grad_norm": 5.926521301269531, "learning_rate": 5.988753022908952e-06, "loss": 3.5268, "step": 14404 }, { "epoch": 0.7751291433491175, "grad_norm": 4.195176124572754, "learning_rate": 5.986008810497448e-06, "loss": 4.2014, "step": 14405 }, { "epoch": 0.7751829530779165, "grad_norm": 3.5372719764709473, "learning_rate": 5.983265141454661e-06, "loss": 4.027, "step": 14406 }, { "epoch": 0.7752367628067155, "grad_norm": 3.247539520263672, "learning_rate": 5.9805220158590164e-06, "loss": 4.1572, "step": 14407 }, { "epoch": 0.7752905725355144, "grad_norm": 3.9000093936920166, "learning_rate": 5.977779433788897e-06, "loss": 4.0196, "step": 14408 }, { "epoch": 0.7753443822643133, "grad_norm": 3.5087969303131104, "learning_rate": 5.975037395322683e-06, "loss": 3.4982, "step": 14409 }, { "epoch": 0.7753981919931123, "grad_norm": 3.771395683288574, "learning_rate": 5.972295900538713e-06, "loss": 3.6421, "step": 14410 }, { "epoch": 0.7754520017219113, "grad_norm": 3.200270652770996, "learning_rate": 5.969554949515357e-06, "loss": 3.6641, "step": 14411 }, { "epoch": 0.7755058114507103, "grad_norm": 3.2331252098083496, "learning_rate": 5.966814542330936e-06, "loss": 3.1275, "step": 14412 }, { "epoch": 0.7755596211795093, "grad_norm": 2.7042624950408936, "learning_rate": 5.964074679063761e-06, "loss": 3.9119, "step": 14413 }, { "epoch": 0.7756134309083083, "grad_norm": 6.314384937286377, "learning_rate": 5.961335359792131e-06, "loss": 3.3234, "step": 14414 }, { "epoch": 0.7756672406371072, "grad_norm": 2.001267671585083, "learning_rate": 5.958596584594328e-06, "loss": 3.8882, "step": 14415 }, { "epoch": 0.7757210503659061, "grad_norm": 3.192410945892334, "learning_rate": 5.955858353548613e-06, "loss": 3.9615, "step": 14416 }, { "epoch": 0.7757748600947051, "grad_norm": 2.697807788848877, "learning_rate": 5.953120666733255e-06, "loss": 4.1129, "step": 14417 }, { "epoch": 0.7758286698235041, "grad_norm": 3.5136959552764893, "learning_rate": 5.950383524226474e-06, "loss": 3.9606, "step": 14418 }, { "epoch": 0.775882479552303, "grad_norm": 2.8876895904541016, "learning_rate": 5.9476469261064955e-06, "loss": 4.0753, "step": 14419 }, { "epoch": 0.775936289281102, "grad_norm": 1.997849941253662, "learning_rate": 5.94491087245152e-06, "loss": 4.3155, "step": 14420 }, { "epoch": 0.775990099009901, "grad_norm": 3.0025746822357178, "learning_rate": 5.942175363339733e-06, "loss": 3.727, "step": 14421 }, { "epoch": 0.7760439087387, "grad_norm": 3.1425278186798096, "learning_rate": 5.939440398849322e-06, "loss": 2.8308, "step": 14422 }, { "epoch": 0.776097718467499, "grad_norm": 2.8983206748962402, "learning_rate": 5.936705979058438e-06, "loss": 3.6398, "step": 14423 }, { "epoch": 0.7761515281962978, "grad_norm": 2.9214816093444824, "learning_rate": 5.933972104045224e-06, "loss": 4.123, "step": 14424 }, { "epoch": 0.7762053379250968, "grad_norm": 3.855651617050171, "learning_rate": 5.9312387738878125e-06, "loss": 3.9146, "step": 14425 }, { "epoch": 0.7762591476538958, "grad_norm": 3.3673899173736572, "learning_rate": 5.9285059886642926e-06, "loss": 2.9472, "step": 14426 }, { "epoch": 0.7763129573826948, "grad_norm": 3.2282378673553467, "learning_rate": 5.925773748452782e-06, "loss": 3.7271, "step": 14427 }, { "epoch": 0.7763667671114938, "grad_norm": 2.9291794300079346, "learning_rate": 5.923042053331354e-06, "loss": 3.4987, "step": 14428 }, { "epoch": 0.7764205768402928, "grad_norm": 3.2600269317626953, "learning_rate": 5.920310903378073e-06, "loss": 3.604, "step": 14429 }, { "epoch": 0.7764743865690917, "grad_norm": 1.6777204275131226, "learning_rate": 5.917580298670991e-06, "loss": 3.7483, "step": 14430 }, { "epoch": 0.7765281962978906, "grad_norm": 2.5962424278259277, "learning_rate": 5.914850239288136e-06, "loss": 3.3227, "step": 14431 }, { "epoch": 0.7765820060266896, "grad_norm": 2.4991495609283447, "learning_rate": 5.9121207253075265e-06, "loss": 4.6017, "step": 14432 }, { "epoch": 0.7766358157554886, "grad_norm": 1.5267870426177979, "learning_rate": 5.90939175680717e-06, "loss": 4.5893, "step": 14433 }, { "epoch": 0.7766896254842875, "grad_norm": 2.3753015995025635, "learning_rate": 5.9066633338650455e-06, "loss": 3.2889, "step": 14434 }, { "epoch": 0.7767434352130865, "grad_norm": 2.7176623344421387, "learning_rate": 5.903935456559132e-06, "loss": 2.8748, "step": 14435 }, { "epoch": 0.7767972449418855, "grad_norm": 2.5082385540008545, "learning_rate": 5.9012081249673774e-06, "loss": 3.4787, "step": 14436 }, { "epoch": 0.7768510546706845, "grad_norm": 2.123809576034546, "learning_rate": 5.898481339167719e-06, "loss": 4.5013, "step": 14437 }, { "epoch": 0.7769048643994835, "grad_norm": 2.170029878616333, "learning_rate": 5.895755099238093e-06, "loss": 3.5277, "step": 14438 }, { "epoch": 0.7769586741282823, "grad_norm": 2.3321645259857178, "learning_rate": 5.893029405256404e-06, "loss": 3.5254, "step": 14439 }, { "epoch": 0.7770124838570813, "grad_norm": 1.7917248010635376, "learning_rate": 5.89030425730055e-06, "loss": 4.0963, "step": 14440 }, { "epoch": 0.7770662935858803, "grad_norm": 2.670940399169922, "learning_rate": 5.887579655448386e-06, "loss": 3.5065, "step": 14441 }, { "epoch": 0.7771201033146793, "grad_norm": 2.7201874256134033, "learning_rate": 5.8848555997777945e-06, "loss": 3.4889, "step": 14442 }, { "epoch": 0.7771739130434783, "grad_norm": 2.22357439994812, "learning_rate": 5.882132090366618e-06, "loss": 3.8554, "step": 14443 }, { "epoch": 0.7772277227722773, "grad_norm": 1.7097779512405396, "learning_rate": 5.879409127292684e-06, "loss": 4.0909, "step": 14444 }, { "epoch": 0.7772815325010762, "grad_norm": 2.6035850048065186, "learning_rate": 5.8766867106338105e-06, "loss": 4.2791, "step": 14445 }, { "epoch": 0.7773353422298752, "grad_norm": 1.4026340246200562, "learning_rate": 5.873964840467796e-06, "loss": 4.2517, "step": 14446 }, { "epoch": 0.7773891519586741, "grad_norm": 2.3997132778167725, "learning_rate": 5.871243516872413e-06, "loss": 4.1206, "step": 14447 }, { "epoch": 0.7774429616874731, "grad_norm": 2.7750139236450195, "learning_rate": 5.868522739925458e-06, "loss": 3.8073, "step": 14448 }, { "epoch": 0.777496771416272, "grad_norm": 3.057542324066162, "learning_rate": 5.865802509704655e-06, "loss": 3.5023, "step": 14449 }, { "epoch": 0.777550581145071, "grad_norm": 2.604186773300171, "learning_rate": 5.863082826287752e-06, "loss": 3.6664, "step": 14450 }, { "epoch": 0.77760439087387, "grad_norm": 3.2884109020233154, "learning_rate": 5.860363689752471e-06, "loss": 3.561, "step": 14451 }, { "epoch": 0.777658200602669, "grad_norm": 3.030233383178711, "learning_rate": 5.857645100176509e-06, "loss": 4.2391, "step": 14452 }, { "epoch": 0.777712010331468, "grad_norm": 2.9167120456695557, "learning_rate": 5.854927057637568e-06, "loss": 3.3642, "step": 14453 }, { "epoch": 0.7777658200602668, "grad_norm": 3.1163556575775146, "learning_rate": 5.85220956221332e-06, "loss": 4.2852, "step": 14454 }, { "epoch": 0.7778196297890658, "grad_norm": 2.9326541423797607, "learning_rate": 5.849492613981427e-06, "loss": 3.8153, "step": 14455 }, { "epoch": 0.7778734395178648, "grad_norm": 2.0879428386688232, "learning_rate": 5.8467762130195195e-06, "loss": 3.9879, "step": 14456 }, { "epoch": 0.7779272492466638, "grad_norm": 3.746502637863159, "learning_rate": 5.844060359405226e-06, "loss": 4.002, "step": 14457 }, { "epoch": 0.7779810589754628, "grad_norm": 3.175790786743164, "learning_rate": 5.8413450532161714e-06, "loss": 3.7631, "step": 14458 }, { "epoch": 0.7780348687042618, "grad_norm": 2.359548330307007, "learning_rate": 5.838630294529942e-06, "loss": 4.0222, "step": 14459 }, { "epoch": 0.7780886784330607, "grad_norm": 2.9228968620300293, "learning_rate": 5.83591608342412e-06, "loss": 3.3028, "step": 14460 }, { "epoch": 0.7781424881618597, "grad_norm": 1.9079262018203735, "learning_rate": 5.833202419976275e-06, "loss": 4.6915, "step": 14461 }, { "epoch": 0.7781962978906586, "grad_norm": 2.7763733863830566, "learning_rate": 5.830489304263948e-06, "loss": 4.0516, "step": 14462 }, { "epoch": 0.7782501076194576, "grad_norm": 2.401153326034546, "learning_rate": 5.827776736364679e-06, "loss": 4.3799, "step": 14463 }, { "epoch": 0.7783039173482565, "grad_norm": 2.4393229484558105, "learning_rate": 5.825064716355982e-06, "loss": 3.7147, "step": 14464 }, { "epoch": 0.7783577270770555, "grad_norm": 1.731927752494812, "learning_rate": 5.822353244315362e-06, "loss": 4.1938, "step": 14465 }, { "epoch": 0.7784115368058545, "grad_norm": 2.603724718093872, "learning_rate": 5.819642320320307e-06, "loss": 3.8402, "step": 14466 }, { "epoch": 0.7784653465346535, "grad_norm": 1.8372724056243896, "learning_rate": 5.816931944448281e-06, "loss": 4.3877, "step": 14467 }, { "epoch": 0.7785191562634525, "grad_norm": 2.262788772583008, "learning_rate": 5.8142221167767406e-06, "loss": 4.245, "step": 14468 }, { "epoch": 0.7785729659922515, "grad_norm": 4.124642372131348, "learning_rate": 5.811512837383132e-06, "loss": 4.1684, "step": 14469 }, { "epoch": 0.7786267757210503, "grad_norm": 1.6153817176818848, "learning_rate": 5.808804106344878e-06, "loss": 4.4947, "step": 14470 }, { "epoch": 0.7786805854498493, "grad_norm": 3.3338894844055176, "learning_rate": 5.806095923739391e-06, "loss": 4.0257, "step": 14471 }, { "epoch": 0.7787343951786483, "grad_norm": 1.39949631690979, "learning_rate": 5.80338828964404e-06, "loss": 4.5784, "step": 14472 }, { "epoch": 0.7787882049074473, "grad_norm": 2.830897808074951, "learning_rate": 5.800681204136229e-06, "loss": 3.2814, "step": 14473 }, { "epoch": 0.7788420146362462, "grad_norm": 3.7864670753479004, "learning_rate": 5.797974667293307e-06, "loss": 3.5932, "step": 14474 }, { "epoch": 0.7788958243650452, "grad_norm": 1.7518216371536255, "learning_rate": 5.795268679192625e-06, "loss": 3.7302, "step": 14475 }, { "epoch": 0.7789496340938442, "grad_norm": 5.958035469055176, "learning_rate": 5.792563239911505e-06, "loss": 3.6964, "step": 14476 }, { "epoch": 0.7790034438226431, "grad_norm": 3.354708194732666, "learning_rate": 5.789858349527269e-06, "loss": 3.4397, "step": 14477 }, { "epoch": 0.7790572535514421, "grad_norm": 3.852766513824463, "learning_rate": 5.787154008117213e-06, "loss": 3.7208, "step": 14478 }, { "epoch": 0.779111063280241, "grad_norm": 2.2524218559265137, "learning_rate": 5.784450215758616e-06, "loss": 3.3378, "step": 14479 }, { "epoch": 0.77916487300904, "grad_norm": 4.496728897094727, "learning_rate": 5.781746972528748e-06, "loss": 3.0477, "step": 14480 }, { "epoch": 0.779218682737839, "grad_norm": 1.8870307207107544, "learning_rate": 5.779044278504864e-06, "loss": 3.7633, "step": 14481 }, { "epoch": 0.779272492466638, "grad_norm": 2.4771530628204346, "learning_rate": 5.776342133764193e-06, "loss": 3.6061, "step": 14482 }, { "epoch": 0.779326302195437, "grad_norm": 2.903867483139038, "learning_rate": 5.773640538383951e-06, "loss": 3.9487, "step": 14483 }, { "epoch": 0.779380111924236, "grad_norm": 5.166652679443359, "learning_rate": 5.77093949244136e-06, "loss": 4.1162, "step": 14484 }, { "epoch": 0.7794339216530348, "grad_norm": 1.6465613842010498, "learning_rate": 5.7682389960135946e-06, "loss": 2.8835, "step": 14485 }, { "epoch": 0.7794877313818338, "grad_norm": 3.7139647006988525, "learning_rate": 5.76553904917784e-06, "loss": 2.5942, "step": 14486 }, { "epoch": 0.7795415411106328, "grad_norm": 2.195619583129883, "learning_rate": 5.762839652011237e-06, "loss": 3.5705, "step": 14487 }, { "epoch": 0.7795953508394318, "grad_norm": 2.900308132171631, "learning_rate": 5.76014080459093e-06, "loss": 3.9138, "step": 14488 }, { "epoch": 0.7796491605682307, "grad_norm": 2.0338644981384277, "learning_rate": 5.757442506994054e-06, "loss": 3.7806, "step": 14489 }, { "epoch": 0.7797029702970297, "grad_norm": 3.746814489364624, "learning_rate": 5.754744759297715e-06, "loss": 3.1376, "step": 14490 }, { "epoch": 0.7797567800258287, "grad_norm": 2.2858128547668457, "learning_rate": 5.752047561579007e-06, "loss": 3.9761, "step": 14491 }, { "epoch": 0.7798105897546277, "grad_norm": 3.06730580329895, "learning_rate": 5.749350913915011e-06, "loss": 2.1985, "step": 14492 }, { "epoch": 0.7798643994834266, "grad_norm": 2.930527687072754, "learning_rate": 5.746654816382788e-06, "loss": 3.3289, "step": 14493 }, { "epoch": 0.7799182092122255, "grad_norm": 4.328799724578857, "learning_rate": 5.743959269059382e-06, "loss": 3.4605, "step": 14494 }, { "epoch": 0.7799720189410245, "grad_norm": 2.9057717323303223, "learning_rate": 5.741264272021829e-06, "loss": 3.2959, "step": 14495 }, { "epoch": 0.7800258286698235, "grad_norm": 2.12884259223938, "learning_rate": 5.738569825347143e-06, "loss": 4.1533, "step": 14496 }, { "epoch": 0.7800796383986225, "grad_norm": 2.7643933296203613, "learning_rate": 5.735875929112325e-06, "loss": 4.0013, "step": 14497 }, { "epoch": 0.7801334481274215, "grad_norm": 3.177692174911499, "learning_rate": 5.733182583394356e-06, "loss": 4.0151, "step": 14498 }, { "epoch": 0.7801872578562205, "grad_norm": 3.3922696113586426, "learning_rate": 5.730489788270202e-06, "loss": 3.4392, "step": 14499 }, { "epoch": 0.7802410675850193, "grad_norm": 1.6544232368469238, "learning_rate": 5.727797543816829e-06, "loss": 4.5392, "step": 14500 }, { "epoch": 0.7802948773138183, "grad_norm": 1.7755370140075684, "learning_rate": 5.72510585011117e-06, "loss": 4.422, "step": 14501 }, { "epoch": 0.7803486870426173, "grad_norm": 2.8916079998016357, "learning_rate": 5.722414707230139e-06, "loss": 3.7351, "step": 14502 }, { "epoch": 0.7804024967714163, "grad_norm": 2.3776025772094727, "learning_rate": 5.719724115250635e-06, "loss": 4.1512, "step": 14503 }, { "epoch": 0.7804563065002152, "grad_norm": 1.7470957040786743, "learning_rate": 5.717034074249567e-06, "loss": 3.8132, "step": 14504 }, { "epoch": 0.7805101162290142, "grad_norm": 4.026572227478027, "learning_rate": 5.714344584303799e-06, "loss": 2.6562, "step": 14505 }, { "epoch": 0.7805639259578132, "grad_norm": 2.9125936031341553, "learning_rate": 5.711655645490191e-06, "loss": 3.7204, "step": 14506 }, { "epoch": 0.7806177356866122, "grad_norm": 2.95945143699646, "learning_rate": 5.708967257885583e-06, "loss": 3.8079, "step": 14507 }, { "epoch": 0.7806715454154111, "grad_norm": 2.4467103481292725, "learning_rate": 5.706279421566807e-06, "loss": 3.6979, "step": 14508 }, { "epoch": 0.78072535514421, "grad_norm": 2.16975474357605, "learning_rate": 5.7035921366106694e-06, "loss": 4.4693, "step": 14509 }, { "epoch": 0.780779164873009, "grad_norm": 2.0033271312713623, "learning_rate": 5.7009054030939674e-06, "loss": 4.3877, "step": 14510 }, { "epoch": 0.780832974601808, "grad_norm": 3.0166120529174805, "learning_rate": 5.698219221093481e-06, "loss": 3.5538, "step": 14511 }, { "epoch": 0.780886784330607, "grad_norm": 4.100663661956787, "learning_rate": 5.695533590685976e-06, "loss": 4.1508, "step": 14512 }, { "epoch": 0.780940594059406, "grad_norm": 2.5554587841033936, "learning_rate": 5.692848511948195e-06, "loss": 3.8148, "step": 14513 }, { "epoch": 0.780994403788205, "grad_norm": 1.9377870559692383, "learning_rate": 5.690163984956867e-06, "loss": 4.0748, "step": 14514 }, { "epoch": 0.7810482135170038, "grad_norm": 2.930546522140503, "learning_rate": 5.687480009788721e-06, "loss": 3.417, "step": 14515 }, { "epoch": 0.7811020232458028, "grad_norm": 2.8304097652435303, "learning_rate": 5.6847965865204605e-06, "loss": 3.6108, "step": 14516 }, { "epoch": 0.7811558329746018, "grad_norm": 3.083073616027832, "learning_rate": 5.682113715228754e-06, "loss": 4.149, "step": 14517 }, { "epoch": 0.7812096427034008, "grad_norm": 2.9826931953430176, "learning_rate": 5.679431395990279e-06, "loss": 4.0253, "step": 14518 }, { "epoch": 0.7812634524321997, "grad_norm": 2.9698500633239746, "learning_rate": 5.676749628881681e-06, "loss": 3.6186, "step": 14519 }, { "epoch": 0.7813172621609987, "grad_norm": 2.961907148361206, "learning_rate": 5.674068413979611e-06, "loss": 4.0966, "step": 14520 }, { "epoch": 0.7813710718897977, "grad_norm": 3.8518455028533936, "learning_rate": 5.671387751360685e-06, "loss": 3.9254, "step": 14521 }, { "epoch": 0.7814248816185967, "grad_norm": 1.4290708303451538, "learning_rate": 5.6687076411015115e-06, "loss": 4.3157, "step": 14522 }, { "epoch": 0.7814786913473956, "grad_norm": 1.8854297399520874, "learning_rate": 5.666028083278676e-06, "loss": 3.9185, "step": 14523 }, { "epoch": 0.7815325010761945, "grad_norm": 1.8932420015335083, "learning_rate": 5.663349077968757e-06, "loss": 4.6725, "step": 14524 }, { "epoch": 0.7815863108049935, "grad_norm": 2.9347329139709473, "learning_rate": 5.660670625248312e-06, "loss": 3.0859, "step": 14525 }, { "epoch": 0.7816401205337925, "grad_norm": 2.106114625930786, "learning_rate": 5.657992725193884e-06, "loss": 4.3286, "step": 14526 }, { "epoch": 0.7816939302625915, "grad_norm": 2.968116044998169, "learning_rate": 5.655315377882e-06, "loss": 4.3313, "step": 14527 }, { "epoch": 0.7817477399913905, "grad_norm": 2.1994690895080566, "learning_rate": 5.6526385833891724e-06, "loss": 3.7415, "step": 14528 }, { "epoch": 0.7818015497201894, "grad_norm": 3.2584424018859863, "learning_rate": 5.649962341791887e-06, "loss": 4.1972, "step": 14529 }, { "epoch": 0.7818553594489884, "grad_norm": 2.8342294692993164, "learning_rate": 5.647286653166639e-06, "loss": 3.8595, "step": 14530 }, { "epoch": 0.7819091691777873, "grad_norm": 2.940072536468506, "learning_rate": 5.644611517589888e-06, "loss": 3.005, "step": 14531 }, { "epoch": 0.7819629789065863, "grad_norm": 2.5277979373931885, "learning_rate": 5.641936935138084e-06, "loss": 4.1518, "step": 14532 }, { "epoch": 0.7820167886353853, "grad_norm": 1.6443560123443604, "learning_rate": 5.6392629058876515e-06, "loss": 4.225, "step": 14533 }, { "epoch": 0.7820705983641842, "grad_norm": 2.966541051864624, "learning_rate": 5.6365894299150015e-06, "loss": 3.3594, "step": 14534 }, { "epoch": 0.7821244080929832, "grad_norm": 2.6462321281433105, "learning_rate": 5.633916507296552e-06, "loss": 4.3078, "step": 14535 }, { "epoch": 0.7821782178217822, "grad_norm": 3.3568644523620605, "learning_rate": 5.631244138108682e-06, "loss": 3.2742, "step": 14536 }, { "epoch": 0.7822320275505812, "grad_norm": 3.108081579208374, "learning_rate": 5.628572322427755e-06, "loss": 3.9905, "step": 14537 }, { "epoch": 0.7822858372793801, "grad_norm": 3.231721878051758, "learning_rate": 5.62590106033013e-06, "loss": 3.5692, "step": 14538 }, { "epoch": 0.782339647008179, "grad_norm": 4.872914791107178, "learning_rate": 5.623230351892142e-06, "loss": 3.8986, "step": 14539 }, { "epoch": 0.782393456736978, "grad_norm": 2.498497247695923, "learning_rate": 5.6205601971901135e-06, "loss": 3.5989, "step": 14540 }, { "epoch": 0.782447266465777, "grad_norm": 3.2574846744537354, "learning_rate": 5.617890596300351e-06, "loss": 3.3758, "step": 14541 }, { "epoch": 0.782501076194576, "grad_norm": 2.1716911792755127, "learning_rate": 5.615221549299143e-06, "loss": 3.6435, "step": 14542 }, { "epoch": 0.782554885923375, "grad_norm": 2.782320022583008, "learning_rate": 5.612553056262762e-06, "loss": 3.5524, "step": 14543 }, { "epoch": 0.782608695652174, "grad_norm": 3.3838515281677246, "learning_rate": 5.609885117267471e-06, "loss": 3.4714, "step": 14544 }, { "epoch": 0.7826625053809729, "grad_norm": 2.2252352237701416, "learning_rate": 5.607217732389503e-06, "loss": 3.2678, "step": 14545 }, { "epoch": 0.7827163151097718, "grad_norm": 4.567487716674805, "learning_rate": 5.604550901705097e-06, "loss": 3.8266, "step": 14546 }, { "epoch": 0.7827701248385708, "grad_norm": 2.902981996536255, "learning_rate": 5.6018846252904655e-06, "loss": 3.5866, "step": 14547 }, { "epoch": 0.7828239345673698, "grad_norm": 3.808129072189331, "learning_rate": 5.599218903221792e-06, "loss": 3.1732, "step": 14548 }, { "epoch": 0.7828777442961687, "grad_norm": 2.97741436958313, "learning_rate": 5.596553735575258e-06, "loss": 3.6404, "step": 14549 }, { "epoch": 0.7829315540249677, "grad_norm": 3.5563249588012695, "learning_rate": 5.593889122427023e-06, "loss": 3.4442, "step": 14550 }, { "epoch": 0.7829853637537667, "grad_norm": 3.6208603382110596, "learning_rate": 5.5912250638532475e-06, "loss": 3.7401, "step": 14551 }, { "epoch": 0.7830391734825657, "grad_norm": 3.164759397506714, "learning_rate": 5.5885615599300584e-06, "loss": 3.4752, "step": 14552 }, { "epoch": 0.7830929832113647, "grad_norm": 2.4278554916381836, "learning_rate": 5.585898610733567e-06, "loss": 3.3894, "step": 14553 }, { "epoch": 0.7831467929401635, "grad_norm": 3.0025904178619385, "learning_rate": 5.583236216339874e-06, "loss": 3.5992, "step": 14554 }, { "epoch": 0.7832006026689625, "grad_norm": 2.9164130687713623, "learning_rate": 5.580574376825068e-06, "loss": 3.6952, "step": 14555 }, { "epoch": 0.7832544123977615, "grad_norm": 1.6451635360717773, "learning_rate": 5.577913092265214e-06, "loss": 4.5301, "step": 14556 }, { "epoch": 0.7833082221265605, "grad_norm": 4.591335296630859, "learning_rate": 5.575252362736361e-06, "loss": 3.8956, "step": 14557 }, { "epoch": 0.7833620318553595, "grad_norm": 3.139817714691162, "learning_rate": 5.5725921883145515e-06, "loss": 3.4463, "step": 14558 }, { "epoch": 0.7834158415841584, "grad_norm": 3.457817792892456, "learning_rate": 5.569932569075803e-06, "loss": 3.6748, "step": 14559 }, { "epoch": 0.7834696513129574, "grad_norm": 3.280900239944458, "learning_rate": 5.567273505096115e-06, "loss": 3.7944, "step": 14560 }, { "epoch": 0.7835234610417563, "grad_norm": 1.8383265733718872, "learning_rate": 5.5646149964514896e-06, "loss": 4.0367, "step": 14561 }, { "epoch": 0.7835772707705553, "grad_norm": 4.207467079162598, "learning_rate": 5.5619570432179e-06, "loss": 3.1342, "step": 14562 }, { "epoch": 0.7836310804993543, "grad_norm": 3.0564651489257812, "learning_rate": 5.5592996454712855e-06, "loss": 3.2058, "step": 14563 }, { "epoch": 0.7836848902281532, "grad_norm": 2.7776951789855957, "learning_rate": 5.556642803287601e-06, "loss": 3.3947, "step": 14564 }, { "epoch": 0.7837386999569522, "grad_norm": 2.6561217308044434, "learning_rate": 5.553986516742763e-06, "loss": 3.0609, "step": 14565 }, { "epoch": 0.7837925096857512, "grad_norm": 1.866828203201294, "learning_rate": 5.55133078591269e-06, "loss": 3.4779, "step": 14566 }, { "epoch": 0.7838463194145502, "grad_norm": 3.7798011302948, "learning_rate": 5.548675610873274e-06, "loss": 3.3886, "step": 14567 }, { "epoch": 0.7839001291433492, "grad_norm": 3.221778631210327, "learning_rate": 5.54602099170039e-06, "loss": 4.0718, "step": 14568 }, { "epoch": 0.783953938872148, "grad_norm": 3.729203939437866, "learning_rate": 5.543366928469904e-06, "loss": 4.3311, "step": 14569 }, { "epoch": 0.784007748600947, "grad_norm": 3.920051097869873, "learning_rate": 5.540713421257657e-06, "loss": 3.1928, "step": 14570 }, { "epoch": 0.784061558329746, "grad_norm": 2.4133706092834473, "learning_rate": 5.5380604701394804e-06, "loss": 4.3439, "step": 14571 }, { "epoch": 0.784115368058545, "grad_norm": 3.6386799812316895, "learning_rate": 5.53540807519119e-06, "loss": 3.8704, "step": 14572 }, { "epoch": 0.784169177787344, "grad_norm": 2.4417333602905273, "learning_rate": 5.532756236488581e-06, "loss": 3.3451, "step": 14573 }, { "epoch": 0.7842229875161429, "grad_norm": 2.408038854598999, "learning_rate": 5.53010495410744e-06, "loss": 3.7926, "step": 14574 }, { "epoch": 0.7842767972449419, "grad_norm": 3.090031147003174, "learning_rate": 5.5274542281235326e-06, "loss": 4.0845, "step": 14575 }, { "epoch": 0.7843306069737409, "grad_norm": 3.53556752204895, "learning_rate": 5.524804058612601e-06, "loss": 3.7869, "step": 14576 }, { "epoch": 0.7843844167025398, "grad_norm": 3.548861026763916, "learning_rate": 5.5221544456503935e-06, "loss": 3.8057, "step": 14577 }, { "epoch": 0.7844382264313388, "grad_norm": 1.409756064414978, "learning_rate": 5.519505389312629e-06, "loss": 4.6923, "step": 14578 }, { "epoch": 0.7844920361601377, "grad_norm": 4.6629228591918945, "learning_rate": 5.516856889674998e-06, "loss": 3.2171, "step": 14579 }, { "epoch": 0.7845458458889367, "grad_norm": 4.342918395996094, "learning_rate": 5.514208946813193e-06, "loss": 4.4833, "step": 14580 }, { "epoch": 0.7845996556177357, "grad_norm": 3.0240814685821533, "learning_rate": 5.511561560802881e-06, "loss": 3.7058, "step": 14581 }, { "epoch": 0.7846534653465347, "grad_norm": 2.9611856937408447, "learning_rate": 5.508914731719725e-06, "loss": 4.1803, "step": 14582 }, { "epoch": 0.7847072750753337, "grad_norm": 1.4836106300354004, "learning_rate": 5.5062684596393635e-06, "loss": 3.8356, "step": 14583 }, { "epoch": 0.7847610848041325, "grad_norm": 2.842485189437866, "learning_rate": 5.503622744637416e-06, "loss": 4.09, "step": 14584 }, { "epoch": 0.7848148945329315, "grad_norm": 2.636681318283081, "learning_rate": 5.500977586789493e-06, "loss": 3.6596, "step": 14585 }, { "epoch": 0.7848687042617305, "grad_norm": 2.41375732421875, "learning_rate": 5.498332986171184e-06, "loss": 3.3947, "step": 14586 }, { "epoch": 0.7849225139905295, "grad_norm": 1.9859484434127808, "learning_rate": 5.495688942858065e-06, "loss": 3.71, "step": 14587 }, { "epoch": 0.7849763237193285, "grad_norm": 2.9328486919403076, "learning_rate": 5.493045456925694e-06, "loss": 2.7268, "step": 14588 }, { "epoch": 0.7850301334481274, "grad_norm": 5.402872085571289, "learning_rate": 5.490402528449618e-06, "loss": 2.8809, "step": 14589 }, { "epoch": 0.7850839431769264, "grad_norm": 2.0050864219665527, "learning_rate": 5.4877601575053614e-06, "loss": 3.2413, "step": 14590 }, { "epoch": 0.7851377529057254, "grad_norm": 3.9113781452178955, "learning_rate": 5.485118344168433e-06, "loss": 3.6558, "step": 14591 }, { "epoch": 0.7851915626345243, "grad_norm": 2.96370267868042, "learning_rate": 5.48247708851434e-06, "loss": 3.4831, "step": 14592 }, { "epoch": 0.7852453723633233, "grad_norm": 3.341207265853882, "learning_rate": 5.479836390618562e-06, "loss": 3.5676, "step": 14593 }, { "epoch": 0.7852991820921222, "grad_norm": 3.4494690895080566, "learning_rate": 5.4771962505565485e-06, "loss": 3.9833, "step": 14594 }, { "epoch": 0.7853529918209212, "grad_norm": 2.6195228099823, "learning_rate": 5.47455666840376e-06, "loss": 3.7579, "step": 14595 }, { "epoch": 0.7854068015497202, "grad_norm": 3.214531183242798, "learning_rate": 5.471917644235613e-06, "loss": 3.7273, "step": 14596 }, { "epoch": 0.7854606112785192, "grad_norm": 3.4679977893829346, "learning_rate": 5.469279178127545e-06, "loss": 4.3307, "step": 14597 }, { "epoch": 0.7855144210073182, "grad_norm": 2.669670343399048, "learning_rate": 5.466641270154949e-06, "loss": 3.6303, "step": 14598 }, { "epoch": 0.785568230736117, "grad_norm": 1.9722601175308228, "learning_rate": 5.4640039203932015e-06, "loss": 4.201, "step": 14599 }, { "epoch": 0.785622040464916, "grad_norm": 2.173015594482422, "learning_rate": 5.461367128917688e-06, "loss": 4.557, "step": 14600 }, { "epoch": 0.785675850193715, "grad_norm": 3.474046230316162, "learning_rate": 5.458730895803732e-06, "loss": 3.1335, "step": 14601 }, { "epoch": 0.785729659922514, "grad_norm": 2.7033345699310303, "learning_rate": 5.456095221126695e-06, "loss": 3.8938, "step": 14602 }, { "epoch": 0.785783469651313, "grad_norm": 3.099618673324585, "learning_rate": 5.453460104961891e-06, "loss": 3.738, "step": 14603 }, { "epoch": 0.7858372793801119, "grad_norm": 2.9257495403289795, "learning_rate": 5.450825547384622e-06, "loss": 3.8293, "step": 14604 }, { "epoch": 0.7858910891089109, "grad_norm": 1.762359857559204, "learning_rate": 5.448191548470177e-06, "loss": 4.2805, "step": 14605 }, { "epoch": 0.7859448988377099, "grad_norm": 2.250760555267334, "learning_rate": 5.44555810829383e-06, "loss": 3.5741, "step": 14606 }, { "epoch": 0.7859987085665088, "grad_norm": 2.1547653675079346, "learning_rate": 5.4429252269308314e-06, "loss": 3.8875, "step": 14607 }, { "epoch": 0.7860525182953078, "grad_norm": 2.5508217811584473, "learning_rate": 5.44029290445644e-06, "loss": 3.6535, "step": 14608 }, { "epoch": 0.7861063280241067, "grad_norm": 2.6513612270355225, "learning_rate": 5.43766114094586e-06, "loss": 3.6722, "step": 14609 }, { "epoch": 0.7861601377529057, "grad_norm": 3.327821731567383, "learning_rate": 5.435029936474312e-06, "loss": 4.2996, "step": 14610 }, { "epoch": 0.7862139474817047, "grad_norm": 2.8407607078552246, "learning_rate": 5.432399291116979e-06, "loss": 3.8443, "step": 14611 }, { "epoch": 0.7862677572105037, "grad_norm": 2.7701289653778076, "learning_rate": 5.429769204949043e-06, "loss": 3.7267, "step": 14612 }, { "epoch": 0.7863215669393027, "grad_norm": 2.7000439167022705, "learning_rate": 5.427139678045667e-06, "loss": 4.4648, "step": 14613 }, { "epoch": 0.7863753766681016, "grad_norm": 2.251121997833252, "learning_rate": 5.424510710481998e-06, "loss": 4.2556, "step": 14614 }, { "epoch": 0.7864291863969005, "grad_norm": 3.4346704483032227, "learning_rate": 5.4218823023331585e-06, "loss": 3.7184, "step": 14615 }, { "epoch": 0.7864829961256995, "grad_norm": 2.3872251510620117, "learning_rate": 5.419254453674263e-06, "loss": 4.1964, "step": 14616 }, { "epoch": 0.7865368058544985, "grad_norm": 3.917778968811035, "learning_rate": 5.416627164580412e-06, "loss": 4.2491, "step": 14617 }, { "epoch": 0.7865906155832975, "grad_norm": 2.834864616394043, "learning_rate": 5.414000435126684e-06, "loss": 4.7742, "step": 14618 }, { "epoch": 0.7866444253120964, "grad_norm": 2.321138620376587, "learning_rate": 5.4113742653881415e-06, "loss": 4.1599, "step": 14619 }, { "epoch": 0.7866982350408954, "grad_norm": 3.831073760986328, "learning_rate": 5.408748655439835e-06, "loss": 3.4052, "step": 14620 }, { "epoch": 0.7867520447696944, "grad_norm": 2.4509525299072266, "learning_rate": 5.4061236053568e-06, "loss": 4.1322, "step": 14621 }, { "epoch": 0.7868058544984933, "grad_norm": 2.897557020187378, "learning_rate": 5.403499115214042e-06, "loss": 3.6448, "step": 14622 }, { "epoch": 0.7868596642272923, "grad_norm": 3.023500919342041, "learning_rate": 5.400875185086585e-06, "loss": 3.7792, "step": 14623 }, { "epoch": 0.7869134739560912, "grad_norm": 3.7281036376953125, "learning_rate": 5.398251815049393e-06, "loss": 3.9273, "step": 14624 }, { "epoch": 0.7869672836848902, "grad_norm": 3.0911943912506104, "learning_rate": 5.395629005177441e-06, "loss": 3.5317, "step": 14625 }, { "epoch": 0.7870210934136892, "grad_norm": 3.0655767917633057, "learning_rate": 5.393006755545682e-06, "loss": 4.3396, "step": 14626 }, { "epoch": 0.7870749031424882, "grad_norm": 2.594926595687866, "learning_rate": 5.390385066229048e-06, "loss": 4.2718, "step": 14627 }, { "epoch": 0.7871287128712872, "grad_norm": 2.0774106979370117, "learning_rate": 5.387763937302473e-06, "loss": 4.0447, "step": 14628 }, { "epoch": 0.7871825226000861, "grad_norm": 2.3470609188079834, "learning_rate": 5.3851433688408506e-06, "loss": 3.6517, "step": 14629 }, { "epoch": 0.787236332328885, "grad_norm": 3.3174774646759033, "learning_rate": 5.382523360919075e-06, "loss": 3.9053, "step": 14630 }, { "epoch": 0.787290142057684, "grad_norm": 2.5764222145080566, "learning_rate": 5.3799039136120246e-06, "loss": 3.8049, "step": 14631 }, { "epoch": 0.787343951786483, "grad_norm": 2.33160662651062, "learning_rate": 5.3772850269945326e-06, "loss": 3.7293, "step": 14632 }, { "epoch": 0.787397761515282, "grad_norm": 3.240055799484253, "learning_rate": 5.3746667011414644e-06, "loss": 3.5126, "step": 14633 }, { "epoch": 0.7874515712440809, "grad_norm": 3.4225993156433105, "learning_rate": 5.372048936127635e-06, "loss": 4.4713, "step": 14634 }, { "epoch": 0.7875053809728799, "grad_norm": 3.635047674179077, "learning_rate": 5.369431732027855e-06, "loss": 3.8546, "step": 14635 }, { "epoch": 0.7875591907016789, "grad_norm": 3.6343250274658203, "learning_rate": 5.366815088916915e-06, "loss": 3.7218, "step": 14636 }, { "epoch": 0.7876130004304779, "grad_norm": 3.359804153442383, "learning_rate": 5.364199006869591e-06, "loss": 3.4383, "step": 14637 }, { "epoch": 0.7876668101592768, "grad_norm": 2.5169522762298584, "learning_rate": 5.361583485960642e-06, "loss": 4.531, "step": 14638 }, { "epoch": 0.7877206198880757, "grad_norm": 1.9410598278045654, "learning_rate": 5.358968526264827e-06, "loss": 4.6194, "step": 14639 }, { "epoch": 0.7877744296168747, "grad_norm": 1.818179965019226, "learning_rate": 5.356354127856858e-06, "loss": 4.4369, "step": 14640 }, { "epoch": 0.7878282393456737, "grad_norm": 3.273207902908325, "learning_rate": 5.353740290811451e-06, "loss": 3.4927, "step": 14641 }, { "epoch": 0.7878820490744727, "grad_norm": 2.3459510803222656, "learning_rate": 5.351127015203308e-06, "loss": 4.064, "step": 14642 }, { "epoch": 0.7879358588032717, "grad_norm": 4.802536487579346, "learning_rate": 5.348514301107096e-06, "loss": 4.1925, "step": 14643 }, { "epoch": 0.7879896685320706, "grad_norm": 2.924870014190674, "learning_rate": 5.345902148597495e-06, "loss": 3.1348, "step": 14644 }, { "epoch": 0.7880434782608695, "grad_norm": 1.9605505466461182, "learning_rate": 5.343290557749148e-06, "loss": 3.5581, "step": 14645 }, { "epoch": 0.7880972879896685, "grad_norm": 3.2268998622894287, "learning_rate": 5.340679528636694e-06, "loss": 3.4102, "step": 14646 }, { "epoch": 0.7881510977184675, "grad_norm": 2.956050395965576, "learning_rate": 5.338069061334727e-06, "loss": 3.5972, "step": 14647 }, { "epoch": 0.7882049074472665, "grad_norm": 3.6991405487060547, "learning_rate": 5.335459155917871e-06, "loss": 3.8883, "step": 14648 }, { "epoch": 0.7882587171760654, "grad_norm": 3.34446120262146, "learning_rate": 5.332849812460699e-06, "loss": 3.6975, "step": 14649 }, { "epoch": 0.7883125269048644, "grad_norm": 2.5091984272003174, "learning_rate": 5.330241031037781e-06, "loss": 3.5854, "step": 14650 }, { "epoch": 0.7883663366336634, "grad_norm": 2.299030065536499, "learning_rate": 5.32763281172367e-06, "loss": 2.7013, "step": 14651 }, { "epoch": 0.7884201463624624, "grad_norm": 3.485592842102051, "learning_rate": 5.3250251545929e-06, "loss": 3.2174, "step": 14652 }, { "epoch": 0.7884739560912613, "grad_norm": 3.7830920219421387, "learning_rate": 5.322418059719986e-06, "loss": 3.8412, "step": 14653 }, { "epoch": 0.7885277658200602, "grad_norm": 3.152381658554077, "learning_rate": 5.319811527179449e-06, "loss": 3.6801, "step": 14654 }, { "epoch": 0.7885815755488592, "grad_norm": 1.3856247663497925, "learning_rate": 5.3172055570457595e-06, "loss": 4.3151, "step": 14655 }, { "epoch": 0.7886353852776582, "grad_norm": 2.6311209201812744, "learning_rate": 5.314600149393392e-06, "loss": 3.2426, "step": 14656 }, { "epoch": 0.7886891950064572, "grad_norm": 2.005033254623413, "learning_rate": 5.311995304296807e-06, "loss": 3.401, "step": 14657 }, { "epoch": 0.7887430047352562, "grad_norm": 2.67919659614563, "learning_rate": 5.309391021830437e-06, "loss": 4.1823, "step": 14658 }, { "epoch": 0.7887968144640551, "grad_norm": 2.8297197818756104, "learning_rate": 5.3067873020687135e-06, "loss": 3.6009, "step": 14659 }, { "epoch": 0.7888506241928541, "grad_norm": 2.275010824203491, "learning_rate": 5.304184145086041e-06, "loss": 3.9174, "step": 14660 }, { "epoch": 0.788904433921653, "grad_norm": 1.7654387950897217, "learning_rate": 5.301581550956813e-06, "loss": 4.345, "step": 14661 }, { "epoch": 0.788958243650452, "grad_norm": 2.1307010650634766, "learning_rate": 5.298979519755406e-06, "loss": 4.2357, "step": 14662 }, { "epoch": 0.789012053379251, "grad_norm": 2.023214101791382, "learning_rate": 5.296378051556161e-06, "loss": 4.5131, "step": 14663 }, { "epoch": 0.7890658631080499, "grad_norm": 2.5776007175445557, "learning_rate": 5.293777146433443e-06, "loss": 3.3381, "step": 14664 }, { "epoch": 0.7891196728368489, "grad_norm": 3.152987480163574, "learning_rate": 5.29117680446157e-06, "loss": 4.105, "step": 14665 }, { "epoch": 0.7891734825656479, "grad_norm": 2.538296699523926, "learning_rate": 5.288577025714852e-06, "loss": 3.501, "step": 14666 }, { "epoch": 0.7892272922944469, "grad_norm": 3.114377737045288, "learning_rate": 5.285977810267587e-06, "loss": 4.1429, "step": 14667 }, { "epoch": 0.7892811020232458, "grad_norm": 2.0433640480041504, "learning_rate": 5.2833791581940486e-06, "loss": 4.3466, "step": 14668 }, { "epoch": 0.7893349117520447, "grad_norm": 3.576035976409912, "learning_rate": 5.280781069568505e-06, "loss": 3.471, "step": 14669 }, { "epoch": 0.7893887214808437, "grad_norm": 1.8990213871002197, "learning_rate": 5.278183544465201e-06, "loss": 4.0833, "step": 14670 }, { "epoch": 0.7894425312096427, "grad_norm": 3.0279698371887207, "learning_rate": 5.275586582958364e-06, "loss": 3.2805, "step": 14671 }, { "epoch": 0.7894963409384417, "grad_norm": 3.157630443572998, "learning_rate": 5.272990185122212e-06, "loss": 3.9753, "step": 14672 }, { "epoch": 0.7895501506672407, "grad_norm": 3.4347283840179443, "learning_rate": 5.270394351030939e-06, "loss": 4.0164, "step": 14673 }, { "epoch": 0.7896039603960396, "grad_norm": 3.841939926147461, "learning_rate": 5.267799080758723e-06, "loss": 3.1549, "step": 14674 }, { "epoch": 0.7896577701248386, "grad_norm": 2.1696012020111084, "learning_rate": 5.265204374379743e-06, "loss": 3.6114, "step": 14675 }, { "epoch": 0.7897115798536375, "grad_norm": 3.67522931098938, "learning_rate": 5.262610231968141e-06, "loss": 3.1051, "step": 14676 }, { "epoch": 0.7897653895824365, "grad_norm": 3.3104429244995117, "learning_rate": 5.2600166535980576e-06, "loss": 3.75, "step": 14677 }, { "epoch": 0.7898191993112355, "grad_norm": 2.86309814453125, "learning_rate": 5.257423639343589e-06, "loss": 4.3955, "step": 14678 }, { "epoch": 0.7898730090400344, "grad_norm": 2.394838333129883, "learning_rate": 5.254831189278861e-06, "loss": 3.4279, "step": 14679 }, { "epoch": 0.7899268187688334, "grad_norm": 2.384747266769409, "learning_rate": 5.252239303477949e-06, "loss": 4.2093, "step": 14680 }, { "epoch": 0.7899806284976324, "grad_norm": 3.1031246185302734, "learning_rate": 5.249647982014922e-06, "loss": 3.9609, "step": 14681 }, { "epoch": 0.7900344382264314, "grad_norm": 1.3520079851150513, "learning_rate": 5.247057224963834e-06, "loss": 3.719, "step": 14682 }, { "epoch": 0.7900882479552304, "grad_norm": 2.4636518955230713, "learning_rate": 5.24446703239872e-06, "loss": 4.2656, "step": 14683 }, { "epoch": 0.7901420576840292, "grad_norm": 1.3444762229919434, "learning_rate": 5.241877404393597e-06, "loss": 4.3308, "step": 14684 }, { "epoch": 0.7901958674128282, "grad_norm": 1.8478227853775024, "learning_rate": 5.239288341022489e-06, "loss": 4.2235, "step": 14685 }, { "epoch": 0.7902496771416272, "grad_norm": 2.549950361251831, "learning_rate": 5.236699842359361e-06, "loss": 3.5837, "step": 14686 }, { "epoch": 0.7903034868704262, "grad_norm": 1.5052838325500488, "learning_rate": 5.234111908478195e-06, "loss": 3.7436, "step": 14687 }, { "epoch": 0.7903572965992252, "grad_norm": 3.5114047527313232, "learning_rate": 5.231524539452945e-06, "loss": 3.1734, "step": 14688 }, { "epoch": 0.7904111063280241, "grad_norm": 2.111447811126709, "learning_rate": 5.228937735357547e-06, "loss": 4.0869, "step": 14689 }, { "epoch": 0.7904649160568231, "grad_norm": 3.0101592540740967, "learning_rate": 5.226351496265941e-06, "loss": 3.1318, "step": 14690 }, { "epoch": 0.790518725785622, "grad_norm": 2.0286107063293457, "learning_rate": 5.223765822252019e-06, "loss": 4.6628, "step": 14691 }, { "epoch": 0.790572535514421, "grad_norm": 3.1969380378723145, "learning_rate": 5.221180713389689e-06, "loss": 3.9237, "step": 14692 }, { "epoch": 0.79062634524322, "grad_norm": 2.2012672424316406, "learning_rate": 5.218596169752807e-06, "loss": 4.0908, "step": 14693 }, { "epoch": 0.7906801549720189, "grad_norm": 3.217365264892578, "learning_rate": 5.216012191415235e-06, "loss": 3.4685, "step": 14694 }, { "epoch": 0.7907339647008179, "grad_norm": 3.149604558944702, "learning_rate": 5.2134287784508264e-06, "loss": 3.9267, "step": 14695 }, { "epoch": 0.7907877744296169, "grad_norm": 1.4780833721160889, "learning_rate": 5.2108459309334054e-06, "loss": 3.3363, "step": 14696 }, { "epoch": 0.7908415841584159, "grad_norm": 2.720266342163086, "learning_rate": 5.208263648936779e-06, "loss": 3.4392, "step": 14697 }, { "epoch": 0.7908953938872149, "grad_norm": 2.298027276992798, "learning_rate": 5.205681932534748e-06, "loss": 3.428, "step": 14698 }, { "epoch": 0.7909492036160137, "grad_norm": 1.4860084056854248, "learning_rate": 5.203100781801082e-06, "loss": 4.2356, "step": 14699 }, { "epoch": 0.7910030133448127, "grad_norm": 1.87897789478302, "learning_rate": 5.200520196809552e-06, "loss": 3.7521, "step": 14700 }, { "epoch": 0.7910568230736117, "grad_norm": 4.010353088378906, "learning_rate": 5.197940177633898e-06, "loss": 3.563, "step": 14701 }, { "epoch": 0.7911106328024107, "grad_norm": 2.0042238235473633, "learning_rate": 5.195360724347856e-06, "loss": 4.1051, "step": 14702 }, { "epoch": 0.7911644425312097, "grad_norm": 2.6484527587890625, "learning_rate": 5.192781837025132e-06, "loss": 4.0186, "step": 14703 }, { "epoch": 0.7912182522600086, "grad_norm": 1.8709752559661865, "learning_rate": 5.190203515739431e-06, "loss": 4.3115, "step": 14704 }, { "epoch": 0.7912720619888076, "grad_norm": 2.635028839111328, "learning_rate": 5.187625760564424e-06, "loss": 3.1193, "step": 14705 }, { "epoch": 0.7913258717176065, "grad_norm": 2.666506052017212, "learning_rate": 5.185048571573789e-06, "loss": 3.4589, "step": 14706 }, { "epoch": 0.7913796814464055, "grad_norm": 2.6068196296691895, "learning_rate": 5.182471948841178e-06, "loss": 4.0031, "step": 14707 }, { "epoch": 0.7914334911752045, "grad_norm": 2.37003755569458, "learning_rate": 5.179895892440209e-06, "loss": 3.2733, "step": 14708 }, { "epoch": 0.7914873009040034, "grad_norm": 2.399608612060547, "learning_rate": 5.177320402444496e-06, "loss": 3.5718, "step": 14709 }, { "epoch": 0.7915411106328024, "grad_norm": 2.5448007583618164, "learning_rate": 5.174745478927659e-06, "loss": 3.5607, "step": 14710 }, { "epoch": 0.7915949203616014, "grad_norm": 2.8435258865356445, "learning_rate": 5.172171121963274e-06, "loss": 3.3049, "step": 14711 }, { "epoch": 0.7916487300904004, "grad_norm": 2.9105989933013916, "learning_rate": 5.169597331624904e-06, "loss": 3.8385, "step": 14712 }, { "epoch": 0.7917025398191994, "grad_norm": 2.1768345832824707, "learning_rate": 5.167024107986107e-06, "loss": 3.7499, "step": 14713 }, { "epoch": 0.7917563495479982, "grad_norm": 1.9777987003326416, "learning_rate": 5.164451451120416e-06, "loss": 3.9117, "step": 14714 }, { "epoch": 0.7918101592767972, "grad_norm": 2.3811848163604736, "learning_rate": 5.161879361101351e-06, "loss": 3.6777, "step": 14715 }, { "epoch": 0.7918639690055962, "grad_norm": 2.5077621936798096, "learning_rate": 5.159307838002417e-06, "loss": 4.2461, "step": 14716 }, { "epoch": 0.7919177787343952, "grad_norm": 2.8199379444122314, "learning_rate": 5.156736881897098e-06, "loss": 4.1077, "step": 14717 }, { "epoch": 0.7919715884631942, "grad_norm": 2.2042758464813232, "learning_rate": 5.1541664928588666e-06, "loss": 3.4802, "step": 14718 }, { "epoch": 0.7920253981919931, "grad_norm": 1.433266520500183, "learning_rate": 5.151596670961178e-06, "loss": 4.3365, "step": 14719 }, { "epoch": 0.7920792079207921, "grad_norm": 3.975144624710083, "learning_rate": 5.149027416277466e-06, "loss": 2.9122, "step": 14720 }, { "epoch": 0.7921330176495911, "grad_norm": 2.338385581970215, "learning_rate": 5.1464587288811624e-06, "loss": 4.0507, "step": 14721 }, { "epoch": 0.79218682737839, "grad_norm": 2.476374864578247, "learning_rate": 5.1438906088456665e-06, "loss": 3.8628, "step": 14722 }, { "epoch": 0.792240637107189, "grad_norm": 2.783531665802002, "learning_rate": 5.141323056244382e-06, "loss": 3.2095, "step": 14723 }, { "epoch": 0.7922944468359879, "grad_norm": 3.3401150703430176, "learning_rate": 5.13875607115066e-06, "loss": 4.17, "step": 14724 }, { "epoch": 0.7923482565647869, "grad_norm": 2.0254695415496826, "learning_rate": 5.1361896536378655e-06, "loss": 3.9969, "step": 14725 }, { "epoch": 0.7924020662935859, "grad_norm": 2.290712594985962, "learning_rate": 5.133623803779347e-06, "loss": 3.9373, "step": 14726 }, { "epoch": 0.7924558760223849, "grad_norm": 3.2680623531341553, "learning_rate": 5.13105852164843e-06, "loss": 4.3958, "step": 14727 }, { "epoch": 0.7925096857511839, "grad_norm": 3.5181267261505127, "learning_rate": 5.128493807318416e-06, "loss": 3.8794, "step": 14728 }, { "epoch": 0.7925634954799827, "grad_norm": 3.9633312225341797, "learning_rate": 5.1259296608626e-06, "loss": 3.4172, "step": 14729 }, { "epoch": 0.7926173052087817, "grad_norm": 3.524827718734741, "learning_rate": 5.123366082354261e-06, "loss": 3.4652, "step": 14730 }, { "epoch": 0.7926711149375807, "grad_norm": 2.0592687129974365, "learning_rate": 5.120803071866659e-06, "loss": 4.3601, "step": 14731 }, { "epoch": 0.7927249246663797, "grad_norm": 7.4097580909729, "learning_rate": 5.118240629473034e-06, "loss": 3.9092, "step": 14732 }, { "epoch": 0.7927787343951787, "grad_norm": 2.3367698192596436, "learning_rate": 5.115678755246617e-06, "loss": 3.5837, "step": 14733 }, { "epoch": 0.7928325441239776, "grad_norm": 2.4561901092529297, "learning_rate": 5.113117449260618e-06, "loss": 3.5674, "step": 14734 }, { "epoch": 0.7928863538527766, "grad_norm": 1.4850425720214844, "learning_rate": 5.110556711588227e-06, "loss": 4.3691, "step": 14735 }, { "epoch": 0.7929401635815756, "grad_norm": 1.90302574634552, "learning_rate": 5.107996542302637e-06, "loss": 3.0398, "step": 14736 }, { "epoch": 0.7929939733103745, "grad_norm": 2.0073466300964355, "learning_rate": 5.105436941477002e-06, "loss": 4.0305, "step": 14737 }, { "epoch": 0.7930477830391734, "grad_norm": 2.835571765899658, "learning_rate": 5.102877909184473e-06, "loss": 3.2993, "step": 14738 }, { "epoch": 0.7931015927679724, "grad_norm": 3.478848457336426, "learning_rate": 5.1003194454981725e-06, "loss": 4.009, "step": 14739 }, { "epoch": 0.7931554024967714, "grad_norm": 3.548910140991211, "learning_rate": 5.097761550491209e-06, "loss": 2.9273, "step": 14740 }, { "epoch": 0.7932092122255704, "grad_norm": 3.989931583404541, "learning_rate": 5.095204224236699e-06, "loss": 3.6423, "step": 14741 }, { "epoch": 0.7932630219543694, "grad_norm": 2.77341890335083, "learning_rate": 5.092647466807715e-06, "loss": 3.9439, "step": 14742 }, { "epoch": 0.7933168316831684, "grad_norm": 4.085901260375977, "learning_rate": 5.09009127827732e-06, "loss": 3.8117, "step": 14743 }, { "epoch": 0.7933706414119673, "grad_norm": 2.594085216522217, "learning_rate": 5.087535658718565e-06, "loss": 3.982, "step": 14744 }, { "epoch": 0.7934244511407662, "grad_norm": 2.2441258430480957, "learning_rate": 5.084980608204484e-06, "loss": 4.4898, "step": 14745 }, { "epoch": 0.7934782608695652, "grad_norm": 2.658752202987671, "learning_rate": 5.0824261268080905e-06, "loss": 4.1533, "step": 14746 }, { "epoch": 0.7935320705983642, "grad_norm": 1.9269696474075317, "learning_rate": 5.079872214602388e-06, "loss": 3.7998, "step": 14747 }, { "epoch": 0.7935858803271632, "grad_norm": 2.8378024101257324, "learning_rate": 5.077318871660358e-06, "loss": 3.8376, "step": 14748 }, { "epoch": 0.7936396900559621, "grad_norm": 2.798081159591675, "learning_rate": 5.074766098054967e-06, "loss": 3.8979, "step": 14749 }, { "epoch": 0.7936934997847611, "grad_norm": 3.657538652420044, "learning_rate": 5.072213893859171e-06, "loss": 3.6001, "step": 14750 }, { "epoch": 0.7937473095135601, "grad_norm": 3.785203695297241, "learning_rate": 5.069662259145897e-06, "loss": 3.6266, "step": 14751 }, { "epoch": 0.793801119242359, "grad_norm": 2.8789491653442383, "learning_rate": 5.067111193988072e-06, "loss": 3.4542, "step": 14752 }, { "epoch": 0.793854928971158, "grad_norm": 3.3570821285247803, "learning_rate": 5.064560698458607e-06, "loss": 3.4873, "step": 14753 }, { "epoch": 0.7939087386999569, "grad_norm": 4.464990615844727, "learning_rate": 5.062010772630366e-06, "loss": 3.9439, "step": 14754 }, { "epoch": 0.7939625484287559, "grad_norm": 1.776396632194519, "learning_rate": 5.059461416576233e-06, "loss": 3.2506, "step": 14755 }, { "epoch": 0.7940163581575549, "grad_norm": 2.407956838607788, "learning_rate": 5.0569126303690515e-06, "loss": 4.3212, "step": 14756 }, { "epoch": 0.7940701678863539, "grad_norm": 5.185725212097168, "learning_rate": 5.054364414081672e-06, "loss": 4.3493, "step": 14757 }, { "epoch": 0.7941239776151529, "grad_norm": 4.856955528259277, "learning_rate": 5.051816767786913e-06, "loss": 2.2082, "step": 14758 }, { "epoch": 0.7941777873439518, "grad_norm": 2.7277259826660156, "learning_rate": 5.049269691557573e-06, "loss": 3.9553, "step": 14759 }, { "epoch": 0.7942315970727507, "grad_norm": 3.218013048171997, "learning_rate": 5.046723185466445e-06, "loss": 4.3466, "step": 14760 }, { "epoch": 0.7942854068015497, "grad_norm": 1.6793715953826904, "learning_rate": 5.044177249586302e-06, "loss": 4.7574, "step": 14761 }, { "epoch": 0.7943392165303487, "grad_norm": 2.401130437850952, "learning_rate": 5.041631883989898e-06, "loss": 2.5771, "step": 14762 }, { "epoch": 0.7943930262591476, "grad_norm": 2.4828202724456787, "learning_rate": 5.039087088749972e-06, "loss": 4.0608, "step": 14763 }, { "epoch": 0.7944468359879466, "grad_norm": 1.5398510694503784, "learning_rate": 5.03654286393925e-06, "loss": 4.0619, "step": 14764 }, { "epoch": 0.7945006457167456, "grad_norm": 2.503649950027466, "learning_rate": 5.033999209630435e-06, "loss": 4.1292, "step": 14765 }, { "epoch": 0.7945544554455446, "grad_norm": 1.5817608833312988, "learning_rate": 5.031456125896217e-06, "loss": 4.2786, "step": 14766 }, { "epoch": 0.7946082651743436, "grad_norm": 2.0506608486175537, "learning_rate": 5.028913612809277e-06, "loss": 3.9267, "step": 14767 }, { "epoch": 0.7946620749031424, "grad_norm": 3.4382741451263428, "learning_rate": 5.026371670442273e-06, "loss": 3.3698, "step": 14768 }, { "epoch": 0.7947158846319414, "grad_norm": 2.791940689086914, "learning_rate": 5.0238302988678484e-06, "loss": 3.32, "step": 14769 }, { "epoch": 0.7947696943607404, "grad_norm": 2.7589683532714844, "learning_rate": 5.021289498158618e-06, "loss": 3.9636, "step": 14770 }, { "epoch": 0.7948235040895394, "grad_norm": 3.55710506439209, "learning_rate": 5.0187492683871935e-06, "loss": 3.9197, "step": 14771 }, { "epoch": 0.7948773138183384, "grad_norm": 1.956907033920288, "learning_rate": 5.016209609626174e-06, "loss": 3.6685, "step": 14772 }, { "epoch": 0.7949311235471374, "grad_norm": 4.398040294647217, "learning_rate": 5.013670521948136e-06, "loss": 2.0745, "step": 14773 }, { "epoch": 0.7949849332759363, "grad_norm": 3.083616256713867, "learning_rate": 5.011132005425639e-06, "loss": 3.4955, "step": 14774 }, { "epoch": 0.7950387430047352, "grad_norm": 2.208359479904175, "learning_rate": 5.008594060131222e-06, "loss": 3.9756, "step": 14775 }, { "epoch": 0.7950925527335342, "grad_norm": 2.1977944374084473, "learning_rate": 5.00605668613742e-06, "loss": 3.7698, "step": 14776 }, { "epoch": 0.7951463624623332, "grad_norm": 3.7914206981658936, "learning_rate": 5.003519883516738e-06, "loss": 3.4395, "step": 14777 }, { "epoch": 0.7952001721911321, "grad_norm": 2.3846497535705566, "learning_rate": 5.000983652341673e-06, "loss": 4.131, "step": 14778 }, { "epoch": 0.7952539819199311, "grad_norm": 1.938536286354065, "learning_rate": 4.9984479926847074e-06, "loss": 3.9317, "step": 14779 }, { "epoch": 0.7953077916487301, "grad_norm": 1.793398380279541, "learning_rate": 4.995912904618297e-06, "loss": 3.0125, "step": 14780 }, { "epoch": 0.7953616013775291, "grad_norm": 1.8158354759216309, "learning_rate": 4.993378388214892e-06, "loss": 4.2004, "step": 14781 }, { "epoch": 0.7954154111063281, "grad_norm": 3.240278959274292, "learning_rate": 4.990844443546916e-06, "loss": 3.2031, "step": 14782 }, { "epoch": 0.7954692208351269, "grad_norm": 3.2379157543182373, "learning_rate": 4.988311070686794e-06, "loss": 3.3099, "step": 14783 }, { "epoch": 0.7955230305639259, "grad_norm": 2.293583631515503, "learning_rate": 4.98577826970692e-06, "loss": 4.3643, "step": 14784 }, { "epoch": 0.7955768402927249, "grad_norm": 3.3389015197753906, "learning_rate": 4.983246040679668e-06, "loss": 3.5015, "step": 14785 }, { "epoch": 0.7956306500215239, "grad_norm": 2.627459764480591, "learning_rate": 4.980714383677404e-06, "loss": 4.1384, "step": 14786 }, { "epoch": 0.7956844597503229, "grad_norm": 2.9309871196746826, "learning_rate": 4.9781832987724706e-06, "loss": 3.8623, "step": 14787 }, { "epoch": 0.7957382694791219, "grad_norm": 3.7220897674560547, "learning_rate": 4.975652786037213e-06, "loss": 3.948, "step": 14788 }, { "epoch": 0.7957920792079208, "grad_norm": 4.197524547576904, "learning_rate": 4.97312284554394e-06, "loss": 3.9207, "step": 14789 }, { "epoch": 0.7958458889367198, "grad_norm": 1.327715516090393, "learning_rate": 4.970593477364949e-06, "loss": 4.4593, "step": 14790 }, { "epoch": 0.7958996986655187, "grad_norm": 4.744993209838867, "learning_rate": 4.968064681572523e-06, "loss": 3.448, "step": 14791 }, { "epoch": 0.7959535083943177, "grad_norm": 3.417436361312866, "learning_rate": 4.965536458238931e-06, "loss": 3.4504, "step": 14792 }, { "epoch": 0.7960073181231166, "grad_norm": 1.1906603574752808, "learning_rate": 4.96300880743642e-06, "loss": 4.3529, "step": 14793 }, { "epoch": 0.7960611278519156, "grad_norm": 2.2511816024780273, "learning_rate": 4.960481729237224e-06, "loss": 3.6217, "step": 14794 }, { "epoch": 0.7961149375807146, "grad_norm": 1.2798067331314087, "learning_rate": 4.957955223713559e-06, "loss": 4.5007, "step": 14795 }, { "epoch": 0.7961687473095136, "grad_norm": 2.1220884323120117, "learning_rate": 4.95542929093763e-06, "loss": 4.054, "step": 14796 }, { "epoch": 0.7962225570383126, "grad_norm": 3.417330503463745, "learning_rate": 4.952903930981609e-06, "loss": 3.6443, "step": 14797 }, { "epoch": 0.7962763667671114, "grad_norm": 2.3750476837158203, "learning_rate": 4.95037914391768e-06, "loss": 4.1799, "step": 14798 }, { "epoch": 0.7963301764959104, "grad_norm": 4.2027058601379395, "learning_rate": 4.947854929817997e-06, "loss": 4.2883, "step": 14799 }, { "epoch": 0.7963839862247094, "grad_norm": 3.0664215087890625, "learning_rate": 4.945331288754676e-06, "loss": 2.9795, "step": 14800 }, { "epoch": 0.7964377959535084, "grad_norm": 4.454866409301758, "learning_rate": 4.9428082207998465e-06, "loss": 3.4066, "step": 14801 }, { "epoch": 0.7964916056823074, "grad_norm": 2.767423629760742, "learning_rate": 4.940285726025607e-06, "loss": 3.9747, "step": 14802 }, { "epoch": 0.7965454154111064, "grad_norm": 2.9038171768188477, "learning_rate": 4.937763804504051e-06, "loss": 3.1021, "step": 14803 }, { "epoch": 0.7965992251399053, "grad_norm": 3.9074792861938477, "learning_rate": 4.935242456307246e-06, "loss": 3.2046, "step": 14804 }, { "epoch": 0.7966530348687043, "grad_norm": 2.0360305309295654, "learning_rate": 4.9327216815072436e-06, "loss": 3.4735, "step": 14805 }, { "epoch": 0.7967068445975032, "grad_norm": 2.726351261138916, "learning_rate": 4.9302014801760805e-06, "loss": 3.9204, "step": 14806 }, { "epoch": 0.7967606543263022, "grad_norm": 3.1135706901550293, "learning_rate": 4.927681852385776e-06, "loss": 3.3675, "step": 14807 }, { "epoch": 0.7968144640551011, "grad_norm": 1.7590044736862183, "learning_rate": 4.925162798208338e-06, "loss": 3.7821, "step": 14808 }, { "epoch": 0.7968682737839001, "grad_norm": 2.532470941543579, "learning_rate": 4.922644317715752e-06, "loss": 3.7837, "step": 14809 }, { "epoch": 0.7969220835126991, "grad_norm": 2.9339187145233154, "learning_rate": 4.920126410979989e-06, "loss": 3.8389, "step": 14810 }, { "epoch": 0.7969758932414981, "grad_norm": 3.5850284099578857, "learning_rate": 4.917609078073004e-06, "loss": 3.4385, "step": 14811 }, { "epoch": 0.7970297029702971, "grad_norm": 2.819031238555908, "learning_rate": 4.915092319066739e-06, "loss": 3.8385, "step": 14812 }, { "epoch": 0.7970835126990959, "grad_norm": 3.908620595932007, "learning_rate": 4.9125761340331065e-06, "loss": 3.0098, "step": 14813 }, { "epoch": 0.7971373224278949, "grad_norm": 3.4869115352630615, "learning_rate": 4.91006052304403e-06, "loss": 4.0539, "step": 14814 }, { "epoch": 0.7971911321566939, "grad_norm": 2.4080698490142822, "learning_rate": 4.907545486171384e-06, "loss": 4.587, "step": 14815 }, { "epoch": 0.7972449418854929, "grad_norm": 3.396904468536377, "learning_rate": 4.9050310234870414e-06, "loss": 3.9701, "step": 14816 }, { "epoch": 0.7972987516142919, "grad_norm": 1.5759631395339966, "learning_rate": 4.902517135062868e-06, "loss": 3.894, "step": 14817 }, { "epoch": 0.7973525613430908, "grad_norm": 2.2404515743255615, "learning_rate": 4.900003820970689e-06, "loss": 4.3547, "step": 14818 }, { "epoch": 0.7974063710718898, "grad_norm": 2.011945962905884, "learning_rate": 4.897491081282346e-06, "loss": 4.4525, "step": 14819 }, { "epoch": 0.7974601808006888, "grad_norm": 1.9017784595489502, "learning_rate": 4.8949789160696396e-06, "loss": 3.9889, "step": 14820 }, { "epoch": 0.7975139905294877, "grad_norm": 2.6302475929260254, "learning_rate": 4.892467325404359e-06, "loss": 3.5924, "step": 14821 }, { "epoch": 0.7975678002582867, "grad_norm": 2.391218423843384, "learning_rate": 4.889956309358279e-06, "loss": 4.1451, "step": 14822 }, { "epoch": 0.7976216099870856, "grad_norm": 3.3189828395843506, "learning_rate": 4.887445868003157e-06, "loss": 3.3975, "step": 14823 }, { "epoch": 0.7976754197158846, "grad_norm": 2.122947931289673, "learning_rate": 4.884936001410739e-06, "loss": 4.2228, "step": 14824 }, { "epoch": 0.7977292294446836, "grad_norm": 2.9759678840637207, "learning_rate": 4.882426709652743e-06, "loss": 3.3136, "step": 14825 }, { "epoch": 0.7977830391734826, "grad_norm": 3.1231274604797363, "learning_rate": 4.879917992800884e-06, "loss": 3.1216, "step": 14826 }, { "epoch": 0.7978368489022816, "grad_norm": 2.5219907760620117, "learning_rate": 4.877409850926851e-06, "loss": 4.3734, "step": 14827 }, { "epoch": 0.7978906586310806, "grad_norm": 1.325257420539856, "learning_rate": 4.874902284102315e-06, "loss": 4.6221, "step": 14828 }, { "epoch": 0.7979444683598794, "grad_norm": 3.008678674697876, "learning_rate": 4.872395292398949e-06, "loss": 3.66, "step": 14829 }, { "epoch": 0.7979982780886784, "grad_norm": 3.613950252532959, "learning_rate": 4.869888875888393e-06, "loss": 3.5194, "step": 14830 }, { "epoch": 0.7980520878174774, "grad_norm": 1.3611522912979126, "learning_rate": 4.867383034642265e-06, "loss": 4.2029, "step": 14831 }, { "epoch": 0.7981058975462764, "grad_norm": 1.3685519695281982, "learning_rate": 4.864877768732179e-06, "loss": 4.2159, "step": 14832 }, { "epoch": 0.7981597072750753, "grad_norm": 2.4425156116485596, "learning_rate": 4.862373078229721e-06, "loss": 3.7155, "step": 14833 }, { "epoch": 0.7982135170038743, "grad_norm": 2.197603464126587, "learning_rate": 4.859868963206485e-06, "loss": 3.9457, "step": 14834 }, { "epoch": 0.7982673267326733, "grad_norm": 1.6211609840393066, "learning_rate": 4.8573654237340226e-06, "loss": 4.1011, "step": 14835 }, { "epoch": 0.7983211364614722, "grad_norm": 2.9414117336273193, "learning_rate": 4.85486245988388e-06, "loss": 3.5487, "step": 14836 }, { "epoch": 0.7983749461902712, "grad_norm": 1.1168988943099976, "learning_rate": 4.852360071727588e-06, "loss": 4.3377, "step": 14837 }, { "epoch": 0.7984287559190701, "grad_norm": 1.3608208894729614, "learning_rate": 4.849858259336645e-06, "loss": 4.1377, "step": 14838 }, { "epoch": 0.7984825656478691, "grad_norm": 3.140770673751831, "learning_rate": 4.847357022782559e-06, "loss": 3.3291, "step": 14839 }, { "epoch": 0.7985363753766681, "grad_norm": 2.7217891216278076, "learning_rate": 4.844856362136807e-06, "loss": 3.3987, "step": 14840 }, { "epoch": 0.7985901851054671, "grad_norm": 3.9801673889160156, "learning_rate": 4.84235627747085e-06, "loss": 3.282, "step": 14841 }, { "epoch": 0.7986439948342661, "grad_norm": 2.6908860206604004, "learning_rate": 4.83985676885613e-06, "loss": 3.4612, "step": 14842 }, { "epoch": 0.798697804563065, "grad_norm": 1.4508041143417358, "learning_rate": 4.8373578363640814e-06, "loss": 4.0288, "step": 14843 }, { "epoch": 0.7987516142918639, "grad_norm": 1.6915136575698853, "learning_rate": 4.834859480066106e-06, "loss": 3.5071, "step": 14844 }, { "epoch": 0.7988054240206629, "grad_norm": 1.3453240394592285, "learning_rate": 4.832361700033625e-06, "loss": 4.3168, "step": 14845 }, { "epoch": 0.7988592337494619, "grad_norm": 2.1347484588623047, "learning_rate": 4.829864496337993e-06, "loss": 3.9066, "step": 14846 }, { "epoch": 0.7989130434782609, "grad_norm": 4.486121654510498, "learning_rate": 4.827367869050584e-06, "loss": 2.862, "step": 14847 }, { "epoch": 0.7989668532070598, "grad_norm": 2.4678287506103516, "learning_rate": 4.82487181824274e-06, "loss": 3.1468, "step": 14848 }, { "epoch": 0.7990206629358588, "grad_norm": 3.7641544342041016, "learning_rate": 4.8223763439857905e-06, "loss": 4.0896, "step": 14849 }, { "epoch": 0.7990744726646578, "grad_norm": 6.672435283660889, "learning_rate": 4.81988144635106e-06, "loss": 4.243, "step": 14850 }, { "epoch": 0.7991282823934568, "grad_norm": 2.5301496982574463, "learning_rate": 4.8173871254098416e-06, "loss": 3.694, "step": 14851 }, { "epoch": 0.7991820921222557, "grad_norm": 3.0160458087921143, "learning_rate": 4.8148933812334125e-06, "loss": 3.224, "step": 14852 }, { "epoch": 0.7992359018510546, "grad_norm": 5.57902717590332, "learning_rate": 4.812400213893039e-06, "loss": 3.494, "step": 14853 }, { "epoch": 0.7992897115798536, "grad_norm": 2.919008255004883, "learning_rate": 4.809907623459969e-06, "loss": 3.4537, "step": 14854 }, { "epoch": 0.7993435213086526, "grad_norm": 3.3794517517089844, "learning_rate": 4.807415610005433e-06, "loss": 3.3828, "step": 14855 }, { "epoch": 0.7993973310374516, "grad_norm": 2.8568408489227295, "learning_rate": 4.80492417360065e-06, "loss": 3.6582, "step": 14856 }, { "epoch": 0.7994511407662506, "grad_norm": 2.6998450756073, "learning_rate": 4.802433314316815e-06, "loss": 4.1406, "step": 14857 }, { "epoch": 0.7995049504950495, "grad_norm": 3.5364491939544678, "learning_rate": 4.79994303222511e-06, "loss": 3.2505, "step": 14858 }, { "epoch": 0.7995587602238484, "grad_norm": 1.8992764949798584, "learning_rate": 4.797453327396695e-06, "loss": 4.2596, "step": 14859 }, { "epoch": 0.7996125699526474, "grad_norm": 2.6584677696228027, "learning_rate": 4.794964199902738e-06, "loss": 4.0436, "step": 14860 }, { "epoch": 0.7996663796814464, "grad_norm": 1.6926935911178589, "learning_rate": 4.792475649814351e-06, "loss": 3.4256, "step": 14861 }, { "epoch": 0.7997201894102454, "grad_norm": 3.0332541465759277, "learning_rate": 4.789987677202662e-06, "loss": 4.0391, "step": 14862 }, { "epoch": 0.7997739991390443, "grad_norm": 1.7474976778030396, "learning_rate": 4.787500282138763e-06, "loss": 3.6532, "step": 14863 }, { "epoch": 0.7998278088678433, "grad_norm": 1.4249540567398071, "learning_rate": 4.785013464693736e-06, "loss": 4.551, "step": 14864 }, { "epoch": 0.7998816185966423, "grad_norm": 3.1728150844573975, "learning_rate": 4.78252722493866e-06, "loss": 3.4279, "step": 14865 }, { "epoch": 0.7999354283254413, "grad_norm": 2.102323532104492, "learning_rate": 4.780041562944574e-06, "loss": 3.5973, "step": 14866 }, { "epoch": 0.7999892380542402, "grad_norm": 2.255237102508545, "learning_rate": 4.777556478782516e-06, "loss": 3.9289, "step": 14867 }, { "epoch": 0.8000430477830391, "grad_norm": 3.791304349899292, "learning_rate": 4.775071972523509e-06, "loss": 3.2388, "step": 14868 }, { "epoch": 0.8000968575118381, "grad_norm": 3.6950323581695557, "learning_rate": 4.772588044238535e-06, "loss": 3.6156, "step": 14869 }, { "epoch": 0.8001506672406371, "grad_norm": 3.995396375656128, "learning_rate": 4.770104693998595e-06, "loss": 3.6891, "step": 14870 }, { "epoch": 0.8002044769694361, "grad_norm": 3.895569086074829, "learning_rate": 4.767621921874649e-06, "loss": 3.6724, "step": 14871 }, { "epoch": 0.8002582866982351, "grad_norm": 3.7604684829711914, "learning_rate": 4.765139727937651e-06, "loss": 2.6966, "step": 14872 }, { "epoch": 0.800312096427034, "grad_norm": 3.200908899307251, "learning_rate": 4.762658112258534e-06, "loss": 3.7604, "step": 14873 }, { "epoch": 0.800365906155833, "grad_norm": 2.082557201385498, "learning_rate": 4.760177074908214e-06, "loss": 3.9939, "step": 14874 }, { "epoch": 0.8004197158846319, "grad_norm": 4.01310396194458, "learning_rate": 4.7576966159575905e-06, "loss": 4.2677, "step": 14875 }, { "epoch": 0.8004735256134309, "grad_norm": 2.0871334075927734, "learning_rate": 4.7552167354775665e-06, "loss": 3.6253, "step": 14876 }, { "epoch": 0.8005273353422299, "grad_norm": 3.552640914916992, "learning_rate": 4.7527374335389865e-06, "loss": 3.4547, "step": 14877 }, { "epoch": 0.8005811450710288, "grad_norm": 3.5118908882141113, "learning_rate": 4.750258710212716e-06, "loss": 3.0076, "step": 14878 }, { "epoch": 0.8006349547998278, "grad_norm": 3.3785290718078613, "learning_rate": 4.747780565569582e-06, "loss": 3.2685, "step": 14879 }, { "epoch": 0.8006887645286268, "grad_norm": 3.583791971206665, "learning_rate": 4.7453029996804034e-06, "loss": 3.3465, "step": 14880 }, { "epoch": 0.8007425742574258, "grad_norm": 3.4974749088287354, "learning_rate": 4.742826012615992e-06, "loss": 3.0755, "step": 14881 }, { "epoch": 0.8007963839862247, "grad_norm": 2.1513314247131348, "learning_rate": 4.740349604447128e-06, "loss": 4.3411, "step": 14882 }, { "epoch": 0.8008501937150236, "grad_norm": 2.229206085205078, "learning_rate": 4.737873775244586e-06, "loss": 3.0274, "step": 14883 }, { "epoch": 0.8009040034438226, "grad_norm": 2.9698891639709473, "learning_rate": 4.7353985250790985e-06, "loss": 4.0348, "step": 14884 }, { "epoch": 0.8009578131726216, "grad_norm": 2.4228429794311523, "learning_rate": 4.732923854021426e-06, "loss": 4.0906, "step": 14885 }, { "epoch": 0.8010116229014206, "grad_norm": 2.498357057571411, "learning_rate": 4.730449762142275e-06, "loss": 3.751, "step": 14886 }, { "epoch": 0.8010654326302196, "grad_norm": 2.697432041168213, "learning_rate": 4.72797624951235e-06, "loss": 3.4305, "step": 14887 }, { "epoch": 0.8011192423590185, "grad_norm": 5.438686847686768, "learning_rate": 4.725503316202342e-06, "loss": 2.5968, "step": 14888 }, { "epoch": 0.8011730520878175, "grad_norm": 2.479768991470337, "learning_rate": 4.723030962282915e-06, "loss": 3.461, "step": 14889 }, { "epoch": 0.8012268618166164, "grad_norm": 2.7938365936279297, "learning_rate": 4.720559187824719e-06, "loss": 3.9762, "step": 14890 }, { "epoch": 0.8012806715454154, "grad_norm": 1.7935006618499756, "learning_rate": 4.718087992898407e-06, "loss": 4.0638, "step": 14891 }, { "epoch": 0.8013344812742144, "grad_norm": 3.140148162841797, "learning_rate": 4.715617377574586e-06, "loss": 3.8585, "step": 14892 }, { "epoch": 0.8013882910030133, "grad_norm": 2.3938403129577637, "learning_rate": 4.713147341923857e-06, "loss": 4.7729, "step": 14893 }, { "epoch": 0.8014421007318123, "grad_norm": 2.520695686340332, "learning_rate": 4.7106778860168146e-06, "loss": 3.3592, "step": 14894 }, { "epoch": 0.8014959104606113, "grad_norm": 1.4592750072479248, "learning_rate": 4.70820900992402e-06, "loss": 4.5057, "step": 14895 }, { "epoch": 0.8015497201894103, "grad_norm": 3.5788779258728027, "learning_rate": 4.705740713716036e-06, "loss": 4.7347, "step": 14896 }, { "epoch": 0.8016035299182093, "grad_norm": 3.4867424964904785, "learning_rate": 4.703272997463401e-06, "loss": 3.8032, "step": 14897 }, { "epoch": 0.8016573396470081, "grad_norm": 1.476661205291748, "learning_rate": 4.700805861236632e-06, "loss": 4.1546, "step": 14898 }, { "epoch": 0.8017111493758071, "grad_norm": 2.857830047607422, "learning_rate": 4.698339305106239e-06, "loss": 3.843, "step": 14899 }, { "epoch": 0.8017649591046061, "grad_norm": 2.813519239425659, "learning_rate": 4.695873329142689e-06, "loss": 3.711, "step": 14900 }, { "epoch": 0.8018187688334051, "grad_norm": 3.0269367694854736, "learning_rate": 4.693407933416477e-06, "loss": 4.2421, "step": 14901 }, { "epoch": 0.8018725785622041, "grad_norm": 2.6757874488830566, "learning_rate": 4.690943117998045e-06, "loss": 3.8144, "step": 14902 }, { "epoch": 0.801926388291003, "grad_norm": 3.839974880218506, "learning_rate": 4.688478882957836e-06, "loss": 3.73, "step": 14903 }, { "epoch": 0.801980198019802, "grad_norm": 2.211439609527588, "learning_rate": 4.686015228366267e-06, "loss": 3.5792, "step": 14904 }, { "epoch": 0.8020340077486009, "grad_norm": 2.1942801475524902, "learning_rate": 4.683552154293747e-06, "loss": 4.1389, "step": 14905 }, { "epoch": 0.8020878174773999, "grad_norm": 4.344234466552734, "learning_rate": 4.681089660810659e-06, "loss": 2.3091, "step": 14906 }, { "epoch": 0.8021416272061989, "grad_norm": 2.8474972248077393, "learning_rate": 4.67862774798738e-06, "loss": 3.5444, "step": 14907 }, { "epoch": 0.8021954369349978, "grad_norm": 3.0370700359344482, "learning_rate": 4.676166415894259e-06, "loss": 3.5245, "step": 14908 }, { "epoch": 0.8022492466637968, "grad_norm": 3.643259048461914, "learning_rate": 4.673705664601638e-06, "loss": 3.8264, "step": 14909 }, { "epoch": 0.8023030563925958, "grad_norm": 2.4832918643951416, "learning_rate": 4.671245494179832e-06, "loss": 3.7055, "step": 14910 }, { "epoch": 0.8023568661213948, "grad_norm": 2.4988245964050293, "learning_rate": 4.668785904699158e-06, "loss": 3.6978, "step": 14911 }, { "epoch": 0.8024106758501938, "grad_norm": 3.922409772872925, "learning_rate": 4.666326896229897e-06, "loss": 3.9972, "step": 14912 }, { "epoch": 0.8024644855789926, "grad_norm": 5.010586738586426, "learning_rate": 4.663868468842325e-06, "loss": 3.5802, "step": 14913 }, { "epoch": 0.8025182953077916, "grad_norm": 3.77168869972229, "learning_rate": 4.661410622606699e-06, "loss": 4.5306, "step": 14914 }, { "epoch": 0.8025721050365906, "grad_norm": 3.3941991329193115, "learning_rate": 4.658953357593241e-06, "loss": 4.589, "step": 14915 }, { "epoch": 0.8026259147653896, "grad_norm": 3.069533586502075, "learning_rate": 4.656496673872188e-06, "loss": 3.8481, "step": 14916 }, { "epoch": 0.8026797244941886, "grad_norm": 3.226947784423828, "learning_rate": 4.6540405715137455e-06, "loss": 4.1604, "step": 14917 }, { "epoch": 0.8027335342229875, "grad_norm": 3.2737536430358887, "learning_rate": 4.6515850505881e-06, "loss": 4.1659, "step": 14918 }, { "epoch": 0.8027873439517865, "grad_norm": 2.299903392791748, "learning_rate": 4.649130111165423e-06, "loss": 3.9175, "step": 14919 }, { "epoch": 0.8028411536805854, "grad_norm": 2.7483508586883545, "learning_rate": 4.646675753315868e-06, "loss": 3.9865, "step": 14920 }, { "epoch": 0.8028949634093844, "grad_norm": 2.7893781661987305, "learning_rate": 4.644221977109578e-06, "loss": 3.5195, "step": 14921 }, { "epoch": 0.8029487731381834, "grad_norm": 3.156331777572632, "learning_rate": 4.64176878261667e-06, "loss": 3.0517, "step": 14922 }, { "epoch": 0.8030025828669823, "grad_norm": 2.733189344406128, "learning_rate": 4.6393161699072564e-06, "loss": 3.7726, "step": 14923 }, { "epoch": 0.8030563925957813, "grad_norm": 3.696049451828003, "learning_rate": 4.636864139051423e-06, "loss": 4.2539, "step": 14924 }, { "epoch": 0.8031102023245803, "grad_norm": 3.0657846927642822, "learning_rate": 4.634412690119239e-06, "loss": 4.1898, "step": 14925 }, { "epoch": 0.8031640120533793, "grad_norm": 2.714820146560669, "learning_rate": 4.6319618231807585e-06, "loss": 3.3532, "step": 14926 }, { "epoch": 0.8032178217821783, "grad_norm": 3.541614294052124, "learning_rate": 4.6295115383060335e-06, "loss": 3.5548, "step": 14927 }, { "epoch": 0.8032716315109771, "grad_norm": 4.123254776000977, "learning_rate": 4.6270618355650776e-06, "loss": 3.4034, "step": 14928 }, { "epoch": 0.8033254412397761, "grad_norm": 2.343567371368408, "learning_rate": 4.6246127150279015e-06, "loss": 4.1223, "step": 14929 }, { "epoch": 0.8033792509685751, "grad_norm": 3.0066239833831787, "learning_rate": 4.622164176764487e-06, "loss": 4.082, "step": 14930 }, { "epoch": 0.8034330606973741, "grad_norm": 3.0947515964508057, "learning_rate": 4.619716220844803e-06, "loss": 3.5007, "step": 14931 }, { "epoch": 0.8034868704261731, "grad_norm": 3.5318734645843506, "learning_rate": 4.617268847338821e-06, "loss": 2.9268, "step": 14932 }, { "epoch": 0.803540680154972, "grad_norm": 2.793231248855591, "learning_rate": 4.61482205631647e-06, "loss": 4.1971, "step": 14933 }, { "epoch": 0.803594489883771, "grad_norm": 4.678642272949219, "learning_rate": 4.612375847847674e-06, "loss": 3.6498, "step": 14934 }, { "epoch": 0.80364829961257, "grad_norm": 5.021010875701904, "learning_rate": 4.609930222002342e-06, "loss": 2.8573, "step": 14935 }, { "epoch": 0.8037021093413689, "grad_norm": 2.442154884338379, "learning_rate": 4.607485178850362e-06, "loss": 4.4711, "step": 14936 }, { "epoch": 0.8037559190701679, "grad_norm": 2.246464490890503, "learning_rate": 4.605040718461606e-06, "loss": 3.6718, "step": 14937 }, { "epoch": 0.8038097287989668, "grad_norm": 2.1628494262695312, "learning_rate": 4.602596840905929e-06, "loss": 4.1088, "step": 14938 }, { "epoch": 0.8038635385277658, "grad_norm": 4.619292736053467, "learning_rate": 4.600153546253172e-06, "loss": 3.0338, "step": 14939 }, { "epoch": 0.8039173482565648, "grad_norm": 3.05966854095459, "learning_rate": 4.59771083457316e-06, "loss": 4.1792, "step": 14940 }, { "epoch": 0.8039711579853638, "grad_norm": 3.0981552600860596, "learning_rate": 4.595268705935688e-06, "loss": 4.2678, "step": 14941 }, { "epoch": 0.8040249677141628, "grad_norm": 3.1576313972473145, "learning_rate": 4.592827160410559e-06, "loss": 3.994, "step": 14942 }, { "epoch": 0.8040787774429616, "grad_norm": 3.2008187770843506, "learning_rate": 4.590386198067542e-06, "loss": 3.2961, "step": 14943 }, { "epoch": 0.8041325871717606, "grad_norm": 2.679654598236084, "learning_rate": 4.5879458189764e-06, "loss": 4.154, "step": 14944 }, { "epoch": 0.8041863969005596, "grad_norm": 2.2525713443756104, "learning_rate": 4.585506023206856e-06, "loss": 4.1186, "step": 14945 }, { "epoch": 0.8042402066293586, "grad_norm": 2.2264180183410645, "learning_rate": 4.583066810828637e-06, "loss": 3.9364, "step": 14946 }, { "epoch": 0.8042940163581576, "grad_norm": 4.169255256652832, "learning_rate": 4.5806281819114586e-06, "loss": 3.7663, "step": 14947 }, { "epoch": 0.8043478260869565, "grad_norm": 1.977938175201416, "learning_rate": 4.5781901365250065e-06, "loss": 4.2115, "step": 14948 }, { "epoch": 0.8044016358157555, "grad_norm": 1.3876465559005737, "learning_rate": 4.575752674738951e-06, "loss": 4.3404, "step": 14949 }, { "epoch": 0.8044554455445545, "grad_norm": 3.1334261894226074, "learning_rate": 4.573315796622949e-06, "loss": 4.0469, "step": 14950 }, { "epoch": 0.8045092552733534, "grad_norm": 3.255035638809204, "learning_rate": 4.570879502246642e-06, "loss": 4.103, "step": 14951 }, { "epoch": 0.8045630650021524, "grad_norm": 3.5350637435913086, "learning_rate": 4.568443791679647e-06, "loss": 3.2145, "step": 14952 }, { "epoch": 0.8046168747309513, "grad_norm": 1.4989368915557861, "learning_rate": 4.5660086649915775e-06, "loss": 3.9336, "step": 14953 }, { "epoch": 0.8046706844597503, "grad_norm": 1.8981038331985474, "learning_rate": 4.5635741222520175e-06, "loss": 4.1279, "step": 14954 }, { "epoch": 0.8047244941885493, "grad_norm": 2.3518195152282715, "learning_rate": 4.561140163530542e-06, "loss": 4.3052, "step": 14955 }, { "epoch": 0.8047783039173483, "grad_norm": 1.9681440591812134, "learning_rate": 4.558706788896708e-06, "loss": 3.961, "step": 14956 }, { "epoch": 0.8048321136461473, "grad_norm": 2.750627279281616, "learning_rate": 4.556273998420047e-06, "loss": 4.2223, "step": 14957 }, { "epoch": 0.8048859233749462, "grad_norm": 1.7378870248794556, "learning_rate": 4.553841792170091e-06, "loss": 4.6912, "step": 14958 }, { "epoch": 0.8049397331037451, "grad_norm": 2.2555124759674072, "learning_rate": 4.5514101702163445e-06, "loss": 3.838, "step": 14959 }, { "epoch": 0.8049935428325441, "grad_norm": 1.5699840784072876, "learning_rate": 4.548979132628303e-06, "loss": 4.2637, "step": 14960 }, { "epoch": 0.8050473525613431, "grad_norm": 2.4237797260284424, "learning_rate": 4.546548679475424e-06, "loss": 3.7368, "step": 14961 }, { "epoch": 0.8051011622901421, "grad_norm": 2.873201370239258, "learning_rate": 4.544118810827164e-06, "loss": 3.2983, "step": 14962 }, { "epoch": 0.805154972018941, "grad_norm": 3.859107732772827, "learning_rate": 4.541689526752974e-06, "loss": 3.9068, "step": 14963 }, { "epoch": 0.80520878174774, "grad_norm": 3.865116834640503, "learning_rate": 4.5392608273222725e-06, "loss": 3.7505, "step": 14964 }, { "epoch": 0.805262591476539, "grad_norm": 2.2889950275421143, "learning_rate": 4.536832712604461e-06, "loss": 4.4054, "step": 14965 }, { "epoch": 0.8053164012053379, "grad_norm": 3.9469802379608154, "learning_rate": 4.534405182668933e-06, "loss": 3.6279, "step": 14966 }, { "epoch": 0.8053702109341369, "grad_norm": 2.679589033126831, "learning_rate": 4.531978237585061e-06, "loss": 3.5198, "step": 14967 }, { "epoch": 0.8054240206629358, "grad_norm": 2.6376848220825195, "learning_rate": 4.529551877422195e-06, "loss": 3.4832, "step": 14968 }, { "epoch": 0.8054778303917348, "grad_norm": 2.8349525928497314, "learning_rate": 4.527126102249679e-06, "loss": 3.9611, "step": 14969 }, { "epoch": 0.8055316401205338, "grad_norm": 2.9579882621765137, "learning_rate": 4.524700912136831e-06, "loss": 3.6297, "step": 14970 }, { "epoch": 0.8055854498493328, "grad_norm": 2.977860689163208, "learning_rate": 4.522276307152962e-06, "loss": 4.1354, "step": 14971 }, { "epoch": 0.8056392595781318, "grad_norm": 3.702763080596924, "learning_rate": 4.519852287367351e-06, "loss": 3.0682, "step": 14972 }, { "epoch": 0.8056930693069307, "grad_norm": 2.6605823040008545, "learning_rate": 4.517428852849281e-06, "loss": 3.7425, "step": 14973 }, { "epoch": 0.8057468790357296, "grad_norm": 2.860795021057129, "learning_rate": 4.515006003668004e-06, "loss": 3.7781, "step": 14974 }, { "epoch": 0.8058006887645286, "grad_norm": 2.4676499366760254, "learning_rate": 4.512583739892762e-06, "loss": 3.0151, "step": 14975 }, { "epoch": 0.8058544984933276, "grad_norm": 2.4405171871185303, "learning_rate": 4.510162061592768e-06, "loss": 4.399, "step": 14976 }, { "epoch": 0.8059083082221266, "grad_norm": 3.3871989250183105, "learning_rate": 4.507740968837224e-06, "loss": 3.7549, "step": 14977 }, { "epoch": 0.8059621179509255, "grad_norm": 3.955378770828247, "learning_rate": 4.505320461695331e-06, "loss": 2.975, "step": 14978 }, { "epoch": 0.8060159276797245, "grad_norm": 2.3651621341705322, "learning_rate": 4.502900540236255e-06, "loss": 3.6294, "step": 14979 }, { "epoch": 0.8060697374085235, "grad_norm": 2.3517000675201416, "learning_rate": 4.50048120452915e-06, "loss": 3.7999, "step": 14980 }, { "epoch": 0.8061235471373225, "grad_norm": 1.9274570941925049, "learning_rate": 4.498062454643157e-06, "loss": 3.7688, "step": 14981 }, { "epoch": 0.8061773568661214, "grad_norm": 2.868203639984131, "learning_rate": 4.495644290647394e-06, "loss": 3.6769, "step": 14982 }, { "epoch": 0.8062311665949203, "grad_norm": 4.3660407066345215, "learning_rate": 4.493226712610968e-06, "loss": 4.2188, "step": 14983 }, { "epoch": 0.8062849763237193, "grad_norm": 1.6492637395858765, "learning_rate": 4.490809720602965e-06, "loss": 4.0687, "step": 14984 }, { "epoch": 0.8063387860525183, "grad_norm": 1.7705692052841187, "learning_rate": 4.488393314692457e-06, "loss": 4.0574, "step": 14985 }, { "epoch": 0.8063925957813173, "grad_norm": 2.5525152683258057, "learning_rate": 4.485977494948498e-06, "loss": 3.4554, "step": 14986 }, { "epoch": 0.8064464055101163, "grad_norm": 2.1108429431915283, "learning_rate": 4.483562261440128e-06, "loss": 3.7945, "step": 14987 }, { "epoch": 0.8065002152389152, "grad_norm": 2.280618190765381, "learning_rate": 4.481147614236358e-06, "loss": 4.0525, "step": 14988 }, { "epoch": 0.8065540249677141, "grad_norm": 2.5105972290039062, "learning_rate": 4.478733553406206e-06, "loss": 3.6751, "step": 14989 }, { "epoch": 0.8066078346965131, "grad_norm": 4.035511016845703, "learning_rate": 4.476320079018659e-06, "loss": 3.3572, "step": 14990 }, { "epoch": 0.8066616444253121, "grad_norm": 2.7102863788604736, "learning_rate": 4.473907191142676e-06, "loss": 3.6993, "step": 14991 }, { "epoch": 0.8067154541541111, "grad_norm": 2.518686056137085, "learning_rate": 4.471494889847219e-06, "loss": 2.627, "step": 14992 }, { "epoch": 0.80676926388291, "grad_norm": 3.591547727584839, "learning_rate": 4.469083175201213e-06, "loss": 3.7747, "step": 14993 }, { "epoch": 0.806823073611709, "grad_norm": 4.376964569091797, "learning_rate": 4.466672047273596e-06, "loss": 3.8859, "step": 14994 }, { "epoch": 0.806876883340508, "grad_norm": 3.2485923767089844, "learning_rate": 4.464261506133266e-06, "loss": 3.1125, "step": 14995 }, { "epoch": 0.806930693069307, "grad_norm": 3.056704044342041, "learning_rate": 4.461851551849105e-06, "loss": 3.7503, "step": 14996 }, { "epoch": 0.8069845027981059, "grad_norm": 3.6685822010040283, "learning_rate": 4.459442184489985e-06, "loss": 3.6247, "step": 14997 }, { "epoch": 0.8070383125269048, "grad_norm": 3.49643611907959, "learning_rate": 4.457033404124761e-06, "loss": 3.9747, "step": 14998 }, { "epoch": 0.8070921222557038, "grad_norm": 2.382046937942505, "learning_rate": 4.454625210822269e-06, "loss": 4.5141, "step": 14999 }, { "epoch": 0.8071459319845028, "grad_norm": 2.3317363262176514, "learning_rate": 4.452217604651326e-06, "loss": 4.0815, "step": 15000 }, { "epoch": 0.8071997417133018, "grad_norm": 4.061894416809082, "learning_rate": 4.449810585680739e-06, "loss": 3.3771, "step": 15001 }, { "epoch": 0.8072535514421008, "grad_norm": 3.5905685424804688, "learning_rate": 4.44740415397929e-06, "loss": 3.2476, "step": 15002 }, { "epoch": 0.8073073611708997, "grad_norm": 3.7636172771453857, "learning_rate": 4.444998309615744e-06, "loss": 3.6061, "step": 15003 }, { "epoch": 0.8073611708996986, "grad_norm": 4.013894557952881, "learning_rate": 4.4425930526588665e-06, "loss": 3.8121, "step": 15004 }, { "epoch": 0.8074149806284976, "grad_norm": 2.3870716094970703, "learning_rate": 4.4401883831773934e-06, "loss": 4.401, "step": 15005 }, { "epoch": 0.8074687903572966, "grad_norm": 3.927720069885254, "learning_rate": 4.43778430124003e-06, "loss": 3.14, "step": 15006 }, { "epoch": 0.8075226000860956, "grad_norm": 2.6104979515075684, "learning_rate": 4.4353808069154876e-06, "loss": 4.2063, "step": 15007 }, { "epoch": 0.8075764098148945, "grad_norm": 1.7848010063171387, "learning_rate": 4.432977900272439e-06, "loss": 4.0526, "step": 15008 }, { "epoch": 0.8076302195436935, "grad_norm": 1.7601929903030396, "learning_rate": 4.430575581379573e-06, "loss": 4.1553, "step": 15009 }, { "epoch": 0.8076840292724925, "grad_norm": 2.6808571815490723, "learning_rate": 4.428173850305531e-06, "loss": 3.48, "step": 15010 }, { "epoch": 0.8077378390012915, "grad_norm": 1.9722217321395874, "learning_rate": 4.425772707118947e-06, "loss": 4.5309, "step": 15011 }, { "epoch": 0.8077916487300904, "grad_norm": 2.736057758331299, "learning_rate": 4.423372151888441e-06, "loss": 3.8424, "step": 15012 }, { "epoch": 0.8078454584588893, "grad_norm": 2.5868022441864014, "learning_rate": 4.4209721846826175e-06, "loss": 3.2133, "step": 15013 }, { "epoch": 0.8078992681876883, "grad_norm": 2.4586021900177, "learning_rate": 4.418572805570054e-06, "loss": 4.7059, "step": 15014 }, { "epoch": 0.8079530779164873, "grad_norm": 2.983851432800293, "learning_rate": 4.4161740146193235e-06, "loss": 3.7124, "step": 15015 }, { "epoch": 0.8080068876452863, "grad_norm": 2.6093289852142334, "learning_rate": 4.413775811898976e-06, "loss": 4.3617, "step": 15016 }, { "epoch": 0.8080606973740853, "grad_norm": 3.594411611557007, "learning_rate": 4.411378197477547e-06, "loss": 3.6851, "step": 15017 }, { "epoch": 0.8081145071028842, "grad_norm": 3.0165324211120605, "learning_rate": 4.408981171423549e-06, "loss": 2.3479, "step": 15018 }, { "epoch": 0.8081683168316832, "grad_norm": 2.058311939239502, "learning_rate": 4.4065847338054825e-06, "loss": 4.2244, "step": 15019 }, { "epoch": 0.8082221265604821, "grad_norm": 3.1766934394836426, "learning_rate": 4.40418888469184e-06, "loss": 3.7365, "step": 15020 }, { "epoch": 0.8082759362892811, "grad_norm": 2.858942985534668, "learning_rate": 4.4017936241510875e-06, "loss": 3.9165, "step": 15021 }, { "epoch": 0.80832974601808, "grad_norm": 2.9788942337036133, "learning_rate": 4.3993989522516655e-06, "loss": 3.9037, "step": 15022 }, { "epoch": 0.808383555746879, "grad_norm": 2.222299814224243, "learning_rate": 4.397004869062013e-06, "loss": 3.284, "step": 15023 }, { "epoch": 0.808437365475678, "grad_norm": 2.746687412261963, "learning_rate": 4.394611374650537e-06, "loss": 3.7176, "step": 15024 }, { "epoch": 0.808491175204477, "grad_norm": 3.1015753746032715, "learning_rate": 4.3922184690856545e-06, "loss": 3.7803, "step": 15025 }, { "epoch": 0.808544984933276, "grad_norm": 2.7796504497528076, "learning_rate": 4.389826152435739e-06, "loss": 4.1693, "step": 15026 }, { "epoch": 0.8085987946620748, "grad_norm": 2.0562562942504883, "learning_rate": 4.387434424769158e-06, "loss": 4.1718, "step": 15027 }, { "epoch": 0.8086526043908738, "grad_norm": 2.476508140563965, "learning_rate": 4.385043286154258e-06, "loss": 4.3044, "step": 15028 }, { "epoch": 0.8087064141196728, "grad_norm": 2.142197370529175, "learning_rate": 4.382652736659376e-06, "loss": 4.295, "step": 15029 }, { "epoch": 0.8087602238484718, "grad_norm": 2.7302663326263428, "learning_rate": 4.380262776352823e-06, "loss": 4.1396, "step": 15030 }, { "epoch": 0.8088140335772708, "grad_norm": 2.972090721130371, "learning_rate": 4.377873405302898e-06, "loss": 4.0109, "step": 15031 }, { "epoch": 0.8088678433060698, "grad_norm": 3.2447495460510254, "learning_rate": 4.375484623577885e-06, "loss": 3.6072, "step": 15032 }, { "epoch": 0.8089216530348687, "grad_norm": 2.859407901763916, "learning_rate": 4.373096431246049e-06, "loss": 3.7821, "step": 15033 }, { "epoch": 0.8089754627636677, "grad_norm": 1.9647879600524902, "learning_rate": 4.37070882837563e-06, "loss": 3.9294, "step": 15034 }, { "epoch": 0.8090292724924666, "grad_norm": 3.2300727367401123, "learning_rate": 4.368321815034873e-06, "loss": 3.4599, "step": 15035 }, { "epoch": 0.8090830822212656, "grad_norm": 2.6833906173706055, "learning_rate": 4.365935391291992e-06, "loss": 4.2188, "step": 15036 }, { "epoch": 0.8091368919500646, "grad_norm": 1.5868276357650757, "learning_rate": 4.363549557215172e-06, "loss": 4.4008, "step": 15037 }, { "epoch": 0.8091907016788635, "grad_norm": 3.2767114639282227, "learning_rate": 4.361164312872601e-06, "loss": 3.1443, "step": 15038 }, { "epoch": 0.8092445114076625, "grad_norm": 2.501394510269165, "learning_rate": 4.358779658332434e-06, "loss": 3.9981, "step": 15039 }, { "epoch": 0.8092983211364615, "grad_norm": 2.122373342514038, "learning_rate": 4.3563955936628345e-06, "loss": 3.8006, "step": 15040 }, { "epoch": 0.8093521308652605, "grad_norm": 2.055554151535034, "learning_rate": 4.354012118931922e-06, "loss": 3.4195, "step": 15041 }, { "epoch": 0.8094059405940595, "grad_norm": 3.9253218173980713, "learning_rate": 4.351629234207813e-06, "loss": 3.785, "step": 15042 }, { "epoch": 0.8094597503228583, "grad_norm": 2.813000440597534, "learning_rate": 4.349246939558605e-06, "loss": 3.5033, "step": 15043 }, { "epoch": 0.8095135600516573, "grad_norm": 1.5576491355895996, "learning_rate": 4.346865235052372e-06, "loss": 4.3993, "step": 15044 }, { "epoch": 0.8095673697804563, "grad_norm": 2.480315923690796, "learning_rate": 4.344484120757181e-06, "loss": 3.6057, "step": 15045 }, { "epoch": 0.8096211795092553, "grad_norm": 3.64308500289917, "learning_rate": 4.342103596741076e-06, "loss": 4.3871, "step": 15046 }, { "epoch": 0.8096749892380543, "grad_norm": 2.3141088485717773, "learning_rate": 4.33972366307209e-06, "loss": 3.4018, "step": 15047 }, { "epoch": 0.8097287989668532, "grad_norm": 1.9865556955337524, "learning_rate": 4.337344319818232e-06, "loss": 4.4523, "step": 15048 }, { "epoch": 0.8097826086956522, "grad_norm": 1.334700345993042, "learning_rate": 4.334965567047494e-06, "loss": 4.0663, "step": 15049 }, { "epoch": 0.8098364184244511, "grad_norm": 2.9010472297668457, "learning_rate": 4.332587404827854e-06, "loss": 3.6275, "step": 15050 }, { "epoch": 0.8098902281532501, "grad_norm": 2.6926043033599854, "learning_rate": 4.330209833227289e-06, "loss": 4.1102, "step": 15051 }, { "epoch": 0.809944037882049, "grad_norm": 1.8691835403442383, "learning_rate": 4.327832852313726e-06, "loss": 3.9997, "step": 15052 }, { "epoch": 0.809997847610848, "grad_norm": 2.488252878189087, "learning_rate": 4.325456462155098e-06, "loss": 3.8532, "step": 15053 }, { "epoch": 0.810051657339647, "grad_norm": 2.605091094970703, "learning_rate": 4.323080662819315e-06, "loss": 3.4614, "step": 15054 }, { "epoch": 0.810105467068446, "grad_norm": 2.876232147216797, "learning_rate": 4.320705454374269e-06, "loss": 3.9419, "step": 15055 }, { "epoch": 0.810159276797245, "grad_norm": 2.181075096130371, "learning_rate": 4.318330836887843e-06, "loss": 3.4843, "step": 15056 }, { "epoch": 0.810213086526044, "grad_norm": 2.9730587005615234, "learning_rate": 4.315956810427896e-06, "loss": 4.2272, "step": 15057 }, { "epoch": 0.8102668962548428, "grad_norm": 1.8713423013687134, "learning_rate": 4.313583375062271e-06, "loss": 4.4779, "step": 15058 }, { "epoch": 0.8103207059836418, "grad_norm": 2.965482234954834, "learning_rate": 4.311210530858792e-06, "loss": 3.5398, "step": 15059 }, { "epoch": 0.8103745157124408, "grad_norm": 3.4493534564971924, "learning_rate": 4.308838277885271e-06, "loss": 3.7834, "step": 15060 }, { "epoch": 0.8104283254412398, "grad_norm": 3.233184337615967, "learning_rate": 4.306466616209498e-06, "loss": 4.5485, "step": 15061 }, { "epoch": 0.8104821351700388, "grad_norm": 3.0713796615600586, "learning_rate": 4.30409554589925e-06, "loss": 3.7377, "step": 15062 }, { "epoch": 0.8105359448988377, "grad_norm": 3.3860254287719727, "learning_rate": 4.301725067022286e-06, "loss": 4.1199, "step": 15063 }, { "epoch": 0.8105897546276367, "grad_norm": 1.6548988819122314, "learning_rate": 4.29935517964635e-06, "loss": 4.2709, "step": 15064 }, { "epoch": 0.8106435643564357, "grad_norm": 4.073206424713135, "learning_rate": 4.296985883839155e-06, "loss": 3.0891, "step": 15065 }, { "epoch": 0.8106973740852346, "grad_norm": 2.454742670059204, "learning_rate": 4.2946171796684285e-06, "loss": 3.5132, "step": 15066 }, { "epoch": 0.8107511838140335, "grad_norm": 2.6117682456970215, "learning_rate": 4.292249067201856e-06, "loss": 4.0375, "step": 15067 }, { "epoch": 0.8108049935428325, "grad_norm": 3.011073589324951, "learning_rate": 4.289881546507102e-06, "loss": 2.8642, "step": 15068 }, { "epoch": 0.8108588032716315, "grad_norm": 2.3641464710235596, "learning_rate": 4.287514617651831e-06, "loss": 3.7275, "step": 15069 }, { "epoch": 0.8109126130004305, "grad_norm": 2.09437894821167, "learning_rate": 4.285148280703674e-06, "loss": 4.2234, "step": 15070 }, { "epoch": 0.8109664227292295, "grad_norm": 2.7282605171203613, "learning_rate": 4.28278253573027e-06, "loss": 3.6572, "step": 15071 }, { "epoch": 0.8110202324580285, "grad_norm": 2.0048940181732178, "learning_rate": 4.280417382799217e-06, "loss": 4.0289, "step": 15072 }, { "epoch": 0.8110740421868273, "grad_norm": 3.0291101932525635, "learning_rate": 4.278052821978107e-06, "loss": 4.052, "step": 15073 }, { "epoch": 0.8111278519156263, "grad_norm": 2.2913429737091064, "learning_rate": 4.275688853334519e-06, "loss": 3.8079, "step": 15074 }, { "epoch": 0.8111816616444253, "grad_norm": 1.7897237539291382, "learning_rate": 4.273325476935988e-06, "loss": 3.395, "step": 15075 }, { "epoch": 0.8112354713732243, "grad_norm": 2.461162805557251, "learning_rate": 4.2709626928500755e-06, "loss": 3.555, "step": 15076 }, { "epoch": 0.8112892811020233, "grad_norm": 2.197011947631836, "learning_rate": 4.2686005011442905e-06, "loss": 4.6768, "step": 15077 }, { "epoch": 0.8113430908308222, "grad_norm": 2.1674718856811523, "learning_rate": 4.266238901886147e-06, "loss": 3.4266, "step": 15078 }, { "epoch": 0.8113969005596212, "grad_norm": 2.6571874618530273, "learning_rate": 4.263877895143126e-06, "loss": 4.0362, "step": 15079 }, { "epoch": 0.8114507102884202, "grad_norm": 3.15860915184021, "learning_rate": 4.261517480982699e-06, "loss": 4.0317, "step": 15080 }, { "epoch": 0.8115045200172191, "grad_norm": 2.454490900039673, "learning_rate": 4.259157659472318e-06, "loss": 3.2436, "step": 15081 }, { "epoch": 0.811558329746018, "grad_norm": 1.6887434720993042, "learning_rate": 4.256798430679437e-06, "loss": 4.5478, "step": 15082 }, { "epoch": 0.811612139474817, "grad_norm": 5.019484996795654, "learning_rate": 4.254439794671458e-06, "loss": 3.5025, "step": 15083 }, { "epoch": 0.811665949203616, "grad_norm": 4.201215744018555, "learning_rate": 4.252081751515794e-06, "loss": 4.1315, "step": 15084 }, { "epoch": 0.811719758932415, "grad_norm": 1.2875233888626099, "learning_rate": 4.2497243012798225e-06, "loss": 3.8393, "step": 15085 }, { "epoch": 0.811773568661214, "grad_norm": 4.748217582702637, "learning_rate": 4.247367444030917e-06, "loss": 3.2244, "step": 15086 }, { "epoch": 0.811827378390013, "grad_norm": 2.2900400161743164, "learning_rate": 4.245011179836436e-06, "loss": 4.0966, "step": 15087 }, { "epoch": 0.8118811881188119, "grad_norm": 2.171600341796875, "learning_rate": 4.242655508763713e-06, "loss": 3.5188, "step": 15088 }, { "epoch": 0.8119349978476108, "grad_norm": 2.858612537384033, "learning_rate": 4.240300430880062e-06, "loss": 2.3387, "step": 15089 }, { "epoch": 0.8119888075764098, "grad_norm": 2.776970624923706, "learning_rate": 4.237945946252789e-06, "loss": 3.9972, "step": 15090 }, { "epoch": 0.8120426173052088, "grad_norm": 2.586033582687378, "learning_rate": 4.235592054949178e-06, "loss": 4.2439, "step": 15091 }, { "epoch": 0.8120964270340078, "grad_norm": 2.788764238357544, "learning_rate": 4.233238757036495e-06, "loss": 3.8148, "step": 15092 }, { "epoch": 0.8121502367628067, "grad_norm": 3.427717924118042, "learning_rate": 4.230886052581995e-06, "loss": 2.5604, "step": 15093 }, { "epoch": 0.8122040464916057, "grad_norm": 2.6175308227539062, "learning_rate": 4.228533941652907e-06, "loss": 3.3912, "step": 15094 }, { "epoch": 0.8122578562204047, "grad_norm": 4.043318748474121, "learning_rate": 4.226182424316449e-06, "loss": 2.6228, "step": 15095 }, { "epoch": 0.8123116659492036, "grad_norm": 2.33681058883667, "learning_rate": 4.223831500639819e-06, "loss": 3.6922, "step": 15096 }, { "epoch": 0.8123654756780025, "grad_norm": 3.2686257362365723, "learning_rate": 4.221481170690214e-06, "loss": 4.7766, "step": 15097 }, { "epoch": 0.8124192854068015, "grad_norm": 3.585932731628418, "learning_rate": 4.219131434534785e-06, "loss": 3.5614, "step": 15098 }, { "epoch": 0.8124730951356005, "grad_norm": 2.1062400341033936, "learning_rate": 4.216782292240684e-06, "loss": 3.3834, "step": 15099 }, { "epoch": 0.8125269048643995, "grad_norm": 4.268606185913086, "learning_rate": 4.214433743875046e-06, "loss": 3.9079, "step": 15100 }, { "epoch": 0.8125807145931985, "grad_norm": 2.6132140159606934, "learning_rate": 4.212085789504977e-06, "loss": 4.6375, "step": 15101 }, { "epoch": 0.8126345243219975, "grad_norm": 2.829064130783081, "learning_rate": 4.209738429197591e-06, "loss": 3.9203, "step": 15102 }, { "epoch": 0.8126883340507964, "grad_norm": 1.7996193170547485, "learning_rate": 4.207391663019961e-06, "loss": 3.4394, "step": 15103 }, { "epoch": 0.8127421437795953, "grad_norm": 2.0803239345550537, "learning_rate": 4.205045491039153e-06, "loss": 3.8278, "step": 15104 }, { "epoch": 0.8127959535083943, "grad_norm": 3.1582207679748535, "learning_rate": 4.202699913322217e-06, "loss": 3.7349, "step": 15105 }, { "epoch": 0.8128497632371933, "grad_norm": 2.4258530139923096, "learning_rate": 4.200354929936168e-06, "loss": 3.6903, "step": 15106 }, { "epoch": 0.8129035729659922, "grad_norm": 4.077653884887695, "learning_rate": 4.198010540948036e-06, "loss": 4.4037, "step": 15107 }, { "epoch": 0.8129573826947912, "grad_norm": 1.9213954210281372, "learning_rate": 4.195666746424815e-06, "loss": 4.0795, "step": 15108 }, { "epoch": 0.8130111924235902, "grad_norm": 2.7207937240600586, "learning_rate": 4.193323546433478e-06, "loss": 3.668, "step": 15109 }, { "epoch": 0.8130650021523892, "grad_norm": 1.6147615909576416, "learning_rate": 4.1909809410409926e-06, "loss": 3.7811, "step": 15110 }, { "epoch": 0.8131188118811881, "grad_norm": 2.059082508087158, "learning_rate": 4.1886389303143005e-06, "loss": 3.5242, "step": 15111 }, { "epoch": 0.813172621609987, "grad_norm": 2.8877367973327637, "learning_rate": 4.186297514320331e-06, "loss": 4.0614, "step": 15112 }, { "epoch": 0.813226431338786, "grad_norm": 3.3914291858673096, "learning_rate": 4.183956693125998e-06, "loss": 4.1048, "step": 15113 }, { "epoch": 0.813280241067585, "grad_norm": 2.0327746868133545, "learning_rate": 4.181616466798194e-06, "loss": 3.9361, "step": 15114 }, { "epoch": 0.813334050796384, "grad_norm": 2.4206392765045166, "learning_rate": 4.1792768354037974e-06, "loss": 3.9001, "step": 15115 }, { "epoch": 0.813387860525183, "grad_norm": 4.677939414978027, "learning_rate": 4.1769377990096615e-06, "loss": 2.6955, "step": 15116 }, { "epoch": 0.813441670253982, "grad_norm": 3.1896347999572754, "learning_rate": 4.174599357682641e-06, "loss": 4.1255, "step": 15117 }, { "epoch": 0.8134954799827809, "grad_norm": 2.311027765274048, "learning_rate": 4.172261511489556e-06, "loss": 4.2773, "step": 15118 }, { "epoch": 0.8135492897115798, "grad_norm": 1.6352460384368896, "learning_rate": 4.1699242604972185e-06, "loss": 4.5106, "step": 15119 }, { "epoch": 0.8136030994403788, "grad_norm": 1.3335578441619873, "learning_rate": 4.167587604772425e-06, "loss": 4.3658, "step": 15120 }, { "epoch": 0.8136569091691778, "grad_norm": 2.0426828861236572, "learning_rate": 4.1652515443819315e-06, "loss": 4.6536, "step": 15121 }, { "epoch": 0.8137107188979767, "grad_norm": 3.7879297733306885, "learning_rate": 4.162916079392518e-06, "loss": 4.2307, "step": 15122 }, { "epoch": 0.8137645286267757, "grad_norm": 3.0477659702301025, "learning_rate": 4.160581209870917e-06, "loss": 4.0236, "step": 15123 }, { "epoch": 0.8138183383555747, "grad_norm": 1.9850116968154907, "learning_rate": 4.158246935883855e-06, "loss": 2.8189, "step": 15124 }, { "epoch": 0.8138721480843737, "grad_norm": 2.3190886974334717, "learning_rate": 4.155913257498037e-06, "loss": 3.7813, "step": 15125 }, { "epoch": 0.8139259578131727, "grad_norm": 3.3380329608917236, "learning_rate": 4.153580174780153e-06, "loss": 3.6793, "step": 15126 }, { "epoch": 0.8139797675419715, "grad_norm": 2.758251905441284, "learning_rate": 4.151247687796872e-06, "loss": 3.8213, "step": 15127 }, { "epoch": 0.8140335772707705, "grad_norm": 3.232468843460083, "learning_rate": 4.148915796614869e-06, "loss": 3.5474, "step": 15128 }, { "epoch": 0.8140873869995695, "grad_norm": 2.5510406494140625, "learning_rate": 4.146584501300763e-06, "loss": 4.0433, "step": 15129 }, { "epoch": 0.8141411967283685, "grad_norm": 3.0538387298583984, "learning_rate": 4.14425380192118e-06, "loss": 4.4435, "step": 15130 }, { "epoch": 0.8141950064571675, "grad_norm": 1.4642333984375, "learning_rate": 4.1419236985427324e-06, "loss": 4.216, "step": 15131 }, { "epoch": 0.8142488161859665, "grad_norm": 3.5306811332702637, "learning_rate": 4.139594191231994e-06, "loss": 3.8132, "step": 15132 }, { "epoch": 0.8143026259147654, "grad_norm": 1.9274481534957886, "learning_rate": 4.137265280055555e-06, "loss": 4.7861, "step": 15133 }, { "epoch": 0.8143564356435643, "grad_norm": 2.6390528678894043, "learning_rate": 4.134936965079958e-06, "loss": 3.0592, "step": 15134 }, { "epoch": 0.8144102453723633, "grad_norm": 2.3526861667633057, "learning_rate": 4.132609246371749e-06, "loss": 4.529, "step": 15135 }, { "epoch": 0.8144640551011623, "grad_norm": 2.219822883605957, "learning_rate": 4.1302821239974335e-06, "loss": 3.8762, "step": 15136 }, { "epoch": 0.8145178648299612, "grad_norm": 1.557873010635376, "learning_rate": 4.127955598023517e-06, "loss": 4.0609, "step": 15137 }, { "epoch": 0.8145716745587602, "grad_norm": 3.181530237197876, "learning_rate": 4.125629668516495e-06, "loss": 3.6814, "step": 15138 }, { "epoch": 0.8146254842875592, "grad_norm": 3.370182991027832, "learning_rate": 4.123304335542836e-06, "loss": 3.3841, "step": 15139 }, { "epoch": 0.8146792940163582, "grad_norm": 3.7091290950775146, "learning_rate": 4.120979599168983e-06, "loss": 3.3012, "step": 15140 }, { "epoch": 0.8147331037451572, "grad_norm": 2.241748094558716, "learning_rate": 4.118655459461377e-06, "loss": 3.9807, "step": 15141 }, { "epoch": 0.814786913473956, "grad_norm": 3.698183536529541, "learning_rate": 4.116331916486432e-06, "loss": 4.1036, "step": 15142 }, { "epoch": 0.814840723202755, "grad_norm": 2.4510934352874756, "learning_rate": 4.114008970310551e-06, "loss": 3.5277, "step": 15143 }, { "epoch": 0.814894532931554, "grad_norm": 1.9951202869415283, "learning_rate": 4.111686621000119e-06, "loss": 4.3718, "step": 15144 }, { "epoch": 0.814948342660353, "grad_norm": 2.593456506729126, "learning_rate": 4.109364868621499e-06, "loss": 3.8015, "step": 15145 }, { "epoch": 0.815002152389152, "grad_norm": 1.783371925354004, "learning_rate": 4.1070437132410405e-06, "loss": 4.2209, "step": 15146 }, { "epoch": 0.815055962117951, "grad_norm": 3.1681482791900635, "learning_rate": 4.104723154925075e-06, "loss": 3.4709, "step": 15147 }, { "epoch": 0.8151097718467499, "grad_norm": 3.8607430458068848, "learning_rate": 4.102403193739923e-06, "loss": 3.879, "step": 15148 }, { "epoch": 0.8151635815755489, "grad_norm": 3.7109830379486084, "learning_rate": 4.10008382975188e-06, "loss": 2.6705, "step": 15149 }, { "epoch": 0.8152173913043478, "grad_norm": 3.325875997543335, "learning_rate": 4.097765063027226e-06, "loss": 3.6349, "step": 15150 }, { "epoch": 0.8152712010331468, "grad_norm": 2.6701834201812744, "learning_rate": 4.095446893632235e-06, "loss": 3.4831, "step": 15151 }, { "epoch": 0.8153250107619457, "grad_norm": 3.2008562088012695, "learning_rate": 4.09312932163313e-06, "loss": 3.121, "step": 15152 }, { "epoch": 0.8153788204907447, "grad_norm": 4.21817684173584, "learning_rate": 4.090812347096165e-06, "loss": 3.673, "step": 15153 }, { "epoch": 0.8154326302195437, "grad_norm": 2.8302464485168457, "learning_rate": 4.088495970087541e-06, "loss": 4.1523, "step": 15154 }, { "epoch": 0.8154864399483427, "grad_norm": 1.7528574466705322, "learning_rate": 4.086180190673458e-06, "loss": 4.3158, "step": 15155 }, { "epoch": 0.8155402496771417, "grad_norm": 2.118490695953369, "learning_rate": 4.0838650089200956e-06, "loss": 3.4019, "step": 15156 }, { "epoch": 0.8155940594059405, "grad_norm": 4.928163051605225, "learning_rate": 4.081550424893613e-06, "loss": 3.7425, "step": 15157 }, { "epoch": 0.8156478691347395, "grad_norm": 2.637044906616211, "learning_rate": 4.079236438660153e-06, "loss": 2.6196, "step": 15158 }, { "epoch": 0.8157016788635385, "grad_norm": 2.035531759262085, "learning_rate": 4.076923050285847e-06, "loss": 4.5023, "step": 15159 }, { "epoch": 0.8157554885923375, "grad_norm": 2.2622182369232178, "learning_rate": 4.074610259836803e-06, "loss": 4.015, "step": 15160 }, { "epoch": 0.8158092983211365, "grad_norm": 2.9157488346099854, "learning_rate": 4.072298067379116e-06, "loss": 3.3466, "step": 15161 }, { "epoch": 0.8158631080499354, "grad_norm": 1.9924770593643188, "learning_rate": 4.069986472978859e-06, "loss": 4.1787, "step": 15162 }, { "epoch": 0.8159169177787344, "grad_norm": 3.046088218688965, "learning_rate": 4.06767547670209e-06, "loss": 4.1217, "step": 15163 }, { "epoch": 0.8159707275075334, "grad_norm": 3.103060722351074, "learning_rate": 4.065365078614858e-06, "loss": 3.7694, "step": 15164 }, { "epoch": 0.8160245372363323, "grad_norm": 3.87608003616333, "learning_rate": 4.063055278783187e-06, "loss": 3.6776, "step": 15165 }, { "epoch": 0.8160783469651313, "grad_norm": 2.3595564365386963, "learning_rate": 4.060746077273087e-06, "loss": 3.5721, "step": 15166 }, { "epoch": 0.8161321566939302, "grad_norm": 2.6577773094177246, "learning_rate": 4.058437474150539e-06, "loss": 4.2144, "step": 15167 }, { "epoch": 0.8161859664227292, "grad_norm": 2.3403561115264893, "learning_rate": 4.056129469481515e-06, "loss": 3.547, "step": 15168 }, { "epoch": 0.8162397761515282, "grad_norm": 3.749520778656006, "learning_rate": 4.053822063331985e-06, "loss": 3.4554, "step": 15169 }, { "epoch": 0.8162935858803272, "grad_norm": 3.9909610748291016, "learning_rate": 4.051515255767882e-06, "loss": 3.95, "step": 15170 }, { "epoch": 0.8163473956091262, "grad_norm": 2.561842441558838, "learning_rate": 4.049209046855129e-06, "loss": 4.0678, "step": 15171 }, { "epoch": 0.8164012053379252, "grad_norm": 3.5332436561584473, "learning_rate": 4.04690343665963e-06, "loss": 4.2921, "step": 15172 }, { "epoch": 0.816455015066724, "grad_norm": 3.4200711250305176, "learning_rate": 4.04459842524727e-06, "loss": 3.8282, "step": 15173 }, { "epoch": 0.816508824795523, "grad_norm": 2.5666613578796387, "learning_rate": 4.042294012683928e-06, "loss": 4.0781, "step": 15174 }, { "epoch": 0.816562634524322, "grad_norm": 3.664736747741699, "learning_rate": 4.039990199035451e-06, "loss": 3.2244, "step": 15175 }, { "epoch": 0.816616444253121, "grad_norm": 1.5525002479553223, "learning_rate": 4.037686984367681e-06, "loss": 3.5979, "step": 15176 }, { "epoch": 0.81667025398192, "grad_norm": 2.772707462310791, "learning_rate": 4.035384368746431e-06, "loss": 4.1539, "step": 15177 }, { "epoch": 0.8167240637107189, "grad_norm": 1.3545591831207275, "learning_rate": 4.0330823522375046e-06, "loss": 3.8476, "step": 15178 }, { "epoch": 0.8167778734395179, "grad_norm": 4.538666725158691, "learning_rate": 4.030780934906695e-06, "loss": 3.1582, "step": 15179 }, { "epoch": 0.8168316831683168, "grad_norm": 1.6669410467147827, "learning_rate": 4.028480116819766e-06, "loss": 4.3292, "step": 15180 }, { "epoch": 0.8168854928971158, "grad_norm": 3.5151095390319824, "learning_rate": 4.0261798980424755e-06, "loss": 3.0078, "step": 15181 }, { "epoch": 0.8169393026259147, "grad_norm": 3.3775036334991455, "learning_rate": 4.023880278640544e-06, "loss": 3.036, "step": 15182 }, { "epoch": 0.8169931123547137, "grad_norm": 1.809045433998108, "learning_rate": 4.021581258679688e-06, "loss": 4.3268, "step": 15183 }, { "epoch": 0.8170469220835127, "grad_norm": 5.255438327789307, "learning_rate": 4.019282838225621e-06, "loss": 3.533, "step": 15184 }, { "epoch": 0.8171007318123117, "grad_norm": 3.748845338821411, "learning_rate": 4.016985017344019e-06, "loss": 2.641, "step": 15185 }, { "epoch": 0.8171545415411107, "grad_norm": 1.9891029596328735, "learning_rate": 4.014687796100547e-06, "loss": 4.0704, "step": 15186 }, { "epoch": 0.8172083512699096, "grad_norm": 2.3309552669525146, "learning_rate": 4.012391174560856e-06, "loss": 3.7189, "step": 15187 }, { "epoch": 0.8172621609987085, "grad_norm": 2.8427982330322266, "learning_rate": 4.0100951527905716e-06, "loss": 3.3496, "step": 15188 }, { "epoch": 0.8173159707275075, "grad_norm": 2.3294129371643066, "learning_rate": 4.007799730855313e-06, "loss": 4.1151, "step": 15189 }, { "epoch": 0.8173697804563065, "grad_norm": 1.7910555601119995, "learning_rate": 4.005504908820679e-06, "loss": 3.761, "step": 15190 }, { "epoch": 0.8174235901851055, "grad_norm": 1.776512622833252, "learning_rate": 4.003210686752243e-06, "loss": 4.0946, "step": 15191 }, { "epoch": 0.8174773999139044, "grad_norm": 1.769407868385315, "learning_rate": 4.00091706471557e-06, "loss": 4.3858, "step": 15192 }, { "epoch": 0.8175312096427034, "grad_norm": 3.4970591068267822, "learning_rate": 3.998624042776208e-06, "loss": 4.1737, "step": 15193 }, { "epoch": 0.8175850193715024, "grad_norm": 3.126342296600342, "learning_rate": 3.996331620999677e-06, "loss": 4.3755, "step": 15194 }, { "epoch": 0.8176388291003014, "grad_norm": 2.6526222229003906, "learning_rate": 3.994039799451502e-06, "loss": 3.9517, "step": 15195 }, { "epoch": 0.8176926388291003, "grad_norm": 3.301203966140747, "learning_rate": 3.991748578197169e-06, "loss": 3.6603, "step": 15196 }, { "epoch": 0.8177464485578992, "grad_norm": 3.8171606063842773, "learning_rate": 3.989457957302162e-06, "loss": 3.4043, "step": 15197 }, { "epoch": 0.8178002582866982, "grad_norm": 3.114407539367676, "learning_rate": 3.9871679368319315e-06, "loss": 3.9339, "step": 15198 }, { "epoch": 0.8178540680154972, "grad_norm": 5.021895885467529, "learning_rate": 3.9848785168519146e-06, "loss": 3.9321, "step": 15199 }, { "epoch": 0.8179078777442962, "grad_norm": 3.2428343296051025, "learning_rate": 3.982589697427553e-06, "loss": 3.2624, "step": 15200 }, { "epoch": 0.8179616874730952, "grad_norm": 5.55864143371582, "learning_rate": 3.980301478624246e-06, "loss": 2.4375, "step": 15201 }, { "epoch": 0.8180154972018941, "grad_norm": 3.488738536834717, "learning_rate": 3.978013860507388e-06, "loss": 2.8346, "step": 15202 }, { "epoch": 0.818069306930693, "grad_norm": 2.909621000289917, "learning_rate": 3.97572684314235e-06, "loss": 3.742, "step": 15203 }, { "epoch": 0.818123116659492, "grad_norm": 3.117363214492798, "learning_rate": 3.973440426594491e-06, "loss": 3.6441, "step": 15204 }, { "epoch": 0.818176926388291, "grad_norm": 3.520597219467163, "learning_rate": 3.971154610929151e-06, "loss": 3.8886, "step": 15205 }, { "epoch": 0.81823073611709, "grad_norm": 1.484023094177246, "learning_rate": 3.9688693962116496e-06, "loss": 4.2399, "step": 15206 }, { "epoch": 0.8182845458458889, "grad_norm": 2.5088577270507812, "learning_rate": 3.9665847825072935e-06, "loss": 3.4639, "step": 15207 }, { "epoch": 0.8183383555746879, "grad_norm": 3.1325955390930176, "learning_rate": 3.964300769881374e-06, "loss": 2.9338, "step": 15208 }, { "epoch": 0.8183921653034869, "grad_norm": 4.617611408233643, "learning_rate": 3.962017358399151e-06, "loss": 2.7984, "step": 15209 }, { "epoch": 0.8184459750322859, "grad_norm": 2.5164635181427, "learning_rate": 3.95973454812589e-06, "loss": 3.5305, "step": 15210 }, { "epoch": 0.8184997847610848, "grad_norm": 2.7991440296173096, "learning_rate": 3.957452339126827e-06, "loss": 3.1813, "step": 15211 }, { "epoch": 0.8185535944898837, "grad_norm": 2.2575013637542725, "learning_rate": 3.955170731467184e-06, "loss": 3.7772, "step": 15212 }, { "epoch": 0.8186074042186827, "grad_norm": 2.4574220180511475, "learning_rate": 3.952889725212153e-06, "loss": 3.3069, "step": 15213 }, { "epoch": 0.8186612139474817, "grad_norm": 3.7132527828216553, "learning_rate": 3.9506093204269155e-06, "loss": 3.1953, "step": 15214 }, { "epoch": 0.8187150236762807, "grad_norm": 2.9671108722686768, "learning_rate": 3.948329517176652e-06, "loss": 3.7672, "step": 15215 }, { "epoch": 0.8187688334050797, "grad_norm": 3.562252998352051, "learning_rate": 3.946050315526512e-06, "loss": 4.155, "step": 15216 }, { "epoch": 0.8188226431338786, "grad_norm": 4.440413475036621, "learning_rate": 3.943771715541622e-06, "loss": 4.1916, "step": 15217 }, { "epoch": 0.8188764528626775, "grad_norm": 2.094499349594116, "learning_rate": 3.941493717287104e-06, "loss": 4.0708, "step": 15218 }, { "epoch": 0.8189302625914765, "grad_norm": 3.2120933532714844, "learning_rate": 3.939216320828054e-06, "loss": 4.2029, "step": 15219 }, { "epoch": 0.8189840723202755, "grad_norm": 2.550586462020874, "learning_rate": 3.936939526229555e-06, "loss": 3.9495, "step": 15220 }, { "epoch": 0.8190378820490745, "grad_norm": 2.8597989082336426, "learning_rate": 3.934663333556673e-06, "loss": 4.312, "step": 15221 }, { "epoch": 0.8190916917778734, "grad_norm": 3.361044406890869, "learning_rate": 3.932387742874452e-06, "loss": 3.7572, "step": 15222 }, { "epoch": 0.8191455015066724, "grad_norm": 3.9189510345458984, "learning_rate": 3.930112754247925e-06, "loss": 3.9202, "step": 15223 }, { "epoch": 0.8191993112354714, "grad_norm": 2.710277795791626, "learning_rate": 3.927838367742101e-06, "loss": 3.3018, "step": 15224 }, { "epoch": 0.8192531209642704, "grad_norm": 2.9847412109375, "learning_rate": 3.925564583421976e-06, "loss": 3.5351, "step": 15225 }, { "epoch": 0.8193069306930693, "grad_norm": 4.349259853363037, "learning_rate": 3.923291401352538e-06, "loss": 3.2209, "step": 15226 }, { "epoch": 0.8193607404218682, "grad_norm": 2.946518898010254, "learning_rate": 3.921018821598746e-06, "loss": 3.6078, "step": 15227 }, { "epoch": 0.8194145501506672, "grad_norm": 2.890531539916992, "learning_rate": 3.918746844225537e-06, "loss": 3.303, "step": 15228 }, { "epoch": 0.8194683598794662, "grad_norm": 1.8777498006820679, "learning_rate": 3.916475469297839e-06, "loss": 3.9873, "step": 15229 }, { "epoch": 0.8195221696082652, "grad_norm": 1.9461220502853394, "learning_rate": 3.914204696880558e-06, "loss": 4.478, "step": 15230 }, { "epoch": 0.8195759793370642, "grad_norm": 3.203371286392212, "learning_rate": 3.9119345270385995e-06, "loss": 3.727, "step": 15231 }, { "epoch": 0.8196297890658631, "grad_norm": 4.938841342926025, "learning_rate": 3.909664959836834e-06, "loss": 3.166, "step": 15232 }, { "epoch": 0.8196835987946621, "grad_norm": 3.1370229721069336, "learning_rate": 3.907395995340116e-06, "loss": 3.7666, "step": 15233 }, { "epoch": 0.819737408523461, "grad_norm": 2.3980257511138916, "learning_rate": 3.905127633613287e-06, "loss": 3.7165, "step": 15234 }, { "epoch": 0.81979121825226, "grad_norm": 1.5621278285980225, "learning_rate": 3.902859874721171e-06, "loss": 4.3776, "step": 15235 }, { "epoch": 0.819845027981059, "grad_norm": 2.8941338062286377, "learning_rate": 3.900592718728577e-06, "loss": 3.5273, "step": 15236 }, { "epoch": 0.8198988377098579, "grad_norm": 1.3255951404571533, "learning_rate": 3.898326165700292e-06, "loss": 4.4764, "step": 15237 }, { "epoch": 0.8199526474386569, "grad_norm": 1.9136425256729126, "learning_rate": 3.896060215701086e-06, "loss": 4.0882, "step": 15238 }, { "epoch": 0.8200064571674559, "grad_norm": 2.9033138751983643, "learning_rate": 3.893794868795719e-06, "loss": 3.1459, "step": 15239 }, { "epoch": 0.8200602668962549, "grad_norm": 4.986942291259766, "learning_rate": 3.89153012504892e-06, "loss": 4.0999, "step": 15240 }, { "epoch": 0.8201140766250538, "grad_norm": 3.762913227081299, "learning_rate": 3.88926598452542e-06, "loss": 3.7771, "step": 15241 }, { "epoch": 0.8201678863538527, "grad_norm": 3.2221179008483887, "learning_rate": 3.887002447289923e-06, "loss": 3.9856, "step": 15242 }, { "epoch": 0.8202216960826517, "grad_norm": 2.6762866973876953, "learning_rate": 3.884739513407101e-06, "loss": 4.0556, "step": 15243 }, { "epoch": 0.8202755058114507, "grad_norm": 3.4443359375, "learning_rate": 3.882477182941632e-06, "loss": 3.6781, "step": 15244 }, { "epoch": 0.8203293155402497, "grad_norm": 2.7261359691619873, "learning_rate": 3.880215455958158e-06, "loss": 3.9152, "step": 15245 }, { "epoch": 0.8203831252690487, "grad_norm": 1.8408315181732178, "learning_rate": 3.87795433252133e-06, "loss": 4.5943, "step": 15246 }, { "epoch": 0.8204369349978476, "grad_norm": 1.7861214876174927, "learning_rate": 3.875693812695752e-06, "loss": 4.1698, "step": 15247 }, { "epoch": 0.8204907447266466, "grad_norm": 3.064640998840332, "learning_rate": 3.873433896546031e-06, "loss": 3.7703, "step": 15248 }, { "epoch": 0.8205445544554455, "grad_norm": 2.3692214488983154, "learning_rate": 3.871174584136741e-06, "loss": 4.1499, "step": 15249 }, { "epoch": 0.8205983641842445, "grad_norm": 4.798373222351074, "learning_rate": 3.8689158755324555e-06, "loss": 2.5625, "step": 15250 }, { "epoch": 0.8206521739130435, "grad_norm": 2.798999071121216, "learning_rate": 3.866657770797716e-06, "loss": 3.962, "step": 15251 }, { "epoch": 0.8207059836418424, "grad_norm": 3.9441068172454834, "learning_rate": 3.864400269997057e-06, "loss": 3.6171, "step": 15252 }, { "epoch": 0.8207597933706414, "grad_norm": 1.8350504636764526, "learning_rate": 3.862143373194987e-06, "loss": 4.102, "step": 15253 }, { "epoch": 0.8208136030994404, "grad_norm": 5.725581645965576, "learning_rate": 3.859887080456009e-06, "loss": 4.7453, "step": 15254 }, { "epoch": 0.8208674128282394, "grad_norm": 3.39174747467041, "learning_rate": 3.857631391844596e-06, "loss": 4.4521, "step": 15255 }, { "epoch": 0.8209212225570384, "grad_norm": 4.18747615814209, "learning_rate": 3.855376307425207e-06, "loss": 3.1026, "step": 15256 }, { "epoch": 0.8209750322858372, "grad_norm": 2.8577077388763428, "learning_rate": 3.853121827262296e-06, "loss": 3.8184, "step": 15257 }, { "epoch": 0.8210288420146362, "grad_norm": 3.240959882736206, "learning_rate": 3.8508679514202894e-06, "loss": 3.0525, "step": 15258 }, { "epoch": 0.8210826517434352, "grad_norm": 2.0764834880828857, "learning_rate": 3.848614679963588e-06, "loss": 3.786, "step": 15259 }, { "epoch": 0.8211364614722342, "grad_norm": 2.327852487564087, "learning_rate": 3.8463620129565865e-06, "loss": 4.37, "step": 15260 }, { "epoch": 0.8211902712010332, "grad_norm": 2.143144130706787, "learning_rate": 3.844109950463659e-06, "loss": 3.8993, "step": 15261 }, { "epoch": 0.8212440809298321, "grad_norm": 2.985048294067383, "learning_rate": 3.841858492549169e-06, "loss": 3.29, "step": 15262 }, { "epoch": 0.8212978906586311, "grad_norm": 1.723939061164856, "learning_rate": 3.8396076392774566e-06, "loss": 4.1287, "step": 15263 }, { "epoch": 0.82135170038743, "grad_norm": 1.7073588371276855, "learning_rate": 3.837357390712845e-06, "loss": 4.0277, "step": 15264 }, { "epoch": 0.821405510116229, "grad_norm": 2.351531744003296, "learning_rate": 3.835107746919636e-06, "loss": 3.6294, "step": 15265 }, { "epoch": 0.821459319845028, "grad_norm": 2.103240728378296, "learning_rate": 3.83285870796212e-06, "loss": 3.5915, "step": 15266 }, { "epoch": 0.8215131295738269, "grad_norm": 2.6316957473754883, "learning_rate": 3.83061027390457e-06, "loss": 4.4575, "step": 15267 }, { "epoch": 0.8215669393026259, "grad_norm": 4.124019145965576, "learning_rate": 3.82836244481124e-06, "loss": 3.6717, "step": 15268 }, { "epoch": 0.8216207490314249, "grad_norm": 1.6720836162567139, "learning_rate": 3.826115220746365e-06, "loss": 4.3614, "step": 15269 }, { "epoch": 0.8216745587602239, "grad_norm": 2.0095772743225098, "learning_rate": 3.823868601774169e-06, "loss": 3.6661, "step": 15270 }, { "epoch": 0.8217283684890229, "grad_norm": 3.3683156967163086, "learning_rate": 3.821622587958843e-06, "loss": 3.1362, "step": 15271 }, { "epoch": 0.8217821782178217, "grad_norm": 4.9340362548828125, "learning_rate": 3.819377179364586e-06, "loss": 3.0076, "step": 15272 }, { "epoch": 0.8218359879466207, "grad_norm": 2.649885892868042, "learning_rate": 3.817132376055565e-06, "loss": 3.9039, "step": 15273 }, { "epoch": 0.8218897976754197, "grad_norm": 3.2809901237487793, "learning_rate": 3.814888178095921e-06, "loss": 3.4692, "step": 15274 }, { "epoch": 0.8219436074042187, "grad_norm": 2.8512089252471924, "learning_rate": 3.8126445855497934e-06, "loss": 3.7648, "step": 15275 }, { "epoch": 0.8219974171330177, "grad_norm": 1.7379792928695679, "learning_rate": 3.8104015984812893e-06, "loss": 4.4082, "step": 15276 }, { "epoch": 0.8220512268618166, "grad_norm": 2.446469783782959, "learning_rate": 3.808159216954518e-06, "loss": 3.1284, "step": 15277 }, { "epoch": 0.8221050365906156, "grad_norm": 4.415708541870117, "learning_rate": 3.8059174410335572e-06, "loss": 3.6885, "step": 15278 }, { "epoch": 0.8221588463194146, "grad_norm": 3.706712007522583, "learning_rate": 3.803676270782472e-06, "loss": 3.8099, "step": 15279 }, { "epoch": 0.8222126560482135, "grad_norm": 1.207788109779358, "learning_rate": 3.801435706265308e-06, "loss": 4.0879, "step": 15280 }, { "epoch": 0.8222664657770125, "grad_norm": 2.4229507446289062, "learning_rate": 3.7991957475460914e-06, "loss": 3.954, "step": 15281 }, { "epoch": 0.8223202755058114, "grad_norm": 2.0402166843414307, "learning_rate": 3.7969563946888388e-06, "loss": 4.0412, "step": 15282 }, { "epoch": 0.8223740852346104, "grad_norm": 2.7541842460632324, "learning_rate": 3.794717647757545e-06, "loss": 4.5132, "step": 15283 }, { "epoch": 0.8224278949634094, "grad_norm": 3.6018476486206055, "learning_rate": 3.7924795068161824e-06, "loss": 3.6764, "step": 15284 }, { "epoch": 0.8224817046922084, "grad_norm": 3.1702094078063965, "learning_rate": 3.7902419719287153e-06, "loss": 3.3853, "step": 15285 }, { "epoch": 0.8225355144210074, "grad_norm": 2.3280656337738037, "learning_rate": 3.788005043159085e-06, "loss": 4.114, "step": 15286 }, { "epoch": 0.8225893241498062, "grad_norm": 2.4713873863220215, "learning_rate": 3.785768720571209e-06, "loss": 3.132, "step": 15287 }, { "epoch": 0.8226431338786052, "grad_norm": 2.241687059402466, "learning_rate": 3.7835330042290175e-06, "loss": 4.3518, "step": 15288 }, { "epoch": 0.8226969436074042, "grad_norm": 3.291146993637085, "learning_rate": 3.781297894196381e-06, "loss": 4.12, "step": 15289 }, { "epoch": 0.8227507533362032, "grad_norm": 3.370968818664551, "learning_rate": 3.7790633905371768e-06, "loss": 2.675, "step": 15290 }, { "epoch": 0.8228045630650022, "grad_norm": 4.647873878479004, "learning_rate": 3.776829493315265e-06, "loss": 3.1435, "step": 15291 }, { "epoch": 0.8228583727938011, "grad_norm": 3.2426698207855225, "learning_rate": 3.774596202594477e-06, "loss": 3.7385, "step": 15292 }, { "epoch": 0.8229121825226001, "grad_norm": 2.710115432739258, "learning_rate": 3.772363518438646e-06, "loss": 3.7926, "step": 15293 }, { "epoch": 0.8229659922513991, "grad_norm": 3.1156747341156006, "learning_rate": 3.77013144091157e-06, "loss": 3.7154, "step": 15294 }, { "epoch": 0.823019801980198, "grad_norm": 3.2260234355926514, "learning_rate": 3.767899970077035e-06, "loss": 3.2229, "step": 15295 }, { "epoch": 0.823073611708997, "grad_norm": 3.2928502559661865, "learning_rate": 3.7656691059988118e-06, "loss": 3.1838, "step": 15296 }, { "epoch": 0.8231274214377959, "grad_norm": 2.16372013092041, "learning_rate": 3.7634388487406525e-06, "loss": 3.9697, "step": 15297 }, { "epoch": 0.8231812311665949, "grad_norm": 4.218861103057861, "learning_rate": 3.761209198366289e-06, "loss": 3.4558, "step": 15298 }, { "epoch": 0.8232350408953939, "grad_norm": 4.22200870513916, "learning_rate": 3.7589801549394427e-06, "loss": 3.884, "step": 15299 }, { "epoch": 0.8232888506241929, "grad_norm": 2.6790719032287598, "learning_rate": 3.7567517185238125e-06, "loss": 4.1012, "step": 15300 }, { "epoch": 0.8233426603529919, "grad_norm": 3.8560376167297363, "learning_rate": 3.7545238891830785e-06, "loss": 3.6188, "step": 15301 }, { "epoch": 0.8233964700817907, "grad_norm": 1.7148641347885132, "learning_rate": 3.7522966669809036e-06, "loss": 4.0259, "step": 15302 }, { "epoch": 0.8234502798105897, "grad_norm": 2.2929434776306152, "learning_rate": 3.750070051980953e-06, "loss": 4.2332, "step": 15303 }, { "epoch": 0.8235040895393887, "grad_norm": 2.8526384830474854, "learning_rate": 3.7478440442468373e-06, "loss": 3.9768, "step": 15304 }, { "epoch": 0.8235578992681877, "grad_norm": 2.0758543014526367, "learning_rate": 3.7456186438421775e-06, "loss": 3.1864, "step": 15305 }, { "epoch": 0.8236117089969867, "grad_norm": 2.2519748210906982, "learning_rate": 3.7433938508305704e-06, "loss": 4.2118, "step": 15306 }, { "epoch": 0.8236655187257856, "grad_norm": 2.107764959335327, "learning_rate": 3.7411696652755875e-06, "loss": 3.3208, "step": 15307 }, { "epoch": 0.8237193284545846, "grad_norm": 2.9630801677703857, "learning_rate": 3.7389460872407995e-06, "loss": 3.6377, "step": 15308 }, { "epoch": 0.8237731381833836, "grad_norm": 4.213592052459717, "learning_rate": 3.7367231167897504e-06, "loss": 3.553, "step": 15309 }, { "epoch": 0.8238269479121825, "grad_norm": 4.3894758224487305, "learning_rate": 3.7345007539859617e-06, "loss": 4.1165, "step": 15310 }, { "epoch": 0.8238807576409815, "grad_norm": 2.2968578338623047, "learning_rate": 3.732278998892949e-06, "loss": 3.6625, "step": 15311 }, { "epoch": 0.8239345673697804, "grad_norm": 2.993211269378662, "learning_rate": 3.730057851574187e-06, "loss": 3.7172, "step": 15312 }, { "epoch": 0.8239883770985794, "grad_norm": 1.467020869255066, "learning_rate": 3.7278373120931685e-06, "loss": 4.1885, "step": 15313 }, { "epoch": 0.8240421868273784, "grad_norm": 1.6829454898834229, "learning_rate": 3.725617380513344e-06, "loss": 4.3849, "step": 15314 }, { "epoch": 0.8240959965561774, "grad_norm": 3.204026937484741, "learning_rate": 3.723398056898156e-06, "loss": 4.0947, "step": 15315 }, { "epoch": 0.8241498062849764, "grad_norm": 3.5277271270751953, "learning_rate": 3.7211793413110207e-06, "loss": 3.4862, "step": 15316 }, { "epoch": 0.8242036160137753, "grad_norm": 1.9977847337722778, "learning_rate": 3.718961233815349e-06, "loss": 3.9509, "step": 15317 }, { "epoch": 0.8242574257425742, "grad_norm": 2.1114983558654785, "learning_rate": 3.7167437344745176e-06, "loss": 4.0762, "step": 15318 }, { "epoch": 0.8243112354713732, "grad_norm": 1.6026487350463867, "learning_rate": 3.7145268433519175e-06, "loss": 4.3303, "step": 15319 }, { "epoch": 0.8243650452001722, "grad_norm": 2.529475450515747, "learning_rate": 3.7123105605108843e-06, "loss": 4.5051, "step": 15320 }, { "epoch": 0.8244188549289712, "grad_norm": 1.4727224111557007, "learning_rate": 3.710094886014759e-06, "loss": 4.1222, "step": 15321 }, { "epoch": 0.8244726646577701, "grad_norm": 2.3676888942718506, "learning_rate": 3.7078798199268517e-06, "loss": 3.4345, "step": 15322 }, { "epoch": 0.8245264743865691, "grad_norm": 2.6299936771392822, "learning_rate": 3.705665362310476e-06, "loss": 3.7205, "step": 15323 }, { "epoch": 0.8245802841153681, "grad_norm": 2.714850425720215, "learning_rate": 3.703451513228909e-06, "loss": 3.3435, "step": 15324 }, { "epoch": 0.824634093844167, "grad_norm": 1.6301467418670654, "learning_rate": 3.7012382727454163e-06, "loss": 3.9967, "step": 15325 }, { "epoch": 0.824687903572966, "grad_norm": 3.5722157955169678, "learning_rate": 3.699025640923251e-06, "loss": 3.6029, "step": 15326 }, { "epoch": 0.8247417133017649, "grad_norm": 3.356106758117676, "learning_rate": 3.6968136178256315e-06, "loss": 3.6193, "step": 15327 }, { "epoch": 0.8247955230305639, "grad_norm": 4.953329086303711, "learning_rate": 3.6946022035157844e-06, "loss": 4.7219, "step": 15328 }, { "epoch": 0.8248493327593629, "grad_norm": 4.464394569396973, "learning_rate": 3.692391398056902e-06, "loss": 3.5508, "step": 15329 }, { "epoch": 0.8249031424881619, "grad_norm": 1.3530731201171875, "learning_rate": 3.6901812015121633e-06, "loss": 4.1649, "step": 15330 }, { "epoch": 0.8249569522169609, "grad_norm": 2.173293113708496, "learning_rate": 3.6879716139447267e-06, "loss": 3.2118, "step": 15331 }, { "epoch": 0.8250107619457598, "grad_norm": 3.076673746109009, "learning_rate": 3.6857626354177414e-06, "loss": 3.847, "step": 15332 }, { "epoch": 0.8250645716745587, "grad_norm": 4.440340995788574, "learning_rate": 3.683554265994324e-06, "loss": 4.2415, "step": 15333 }, { "epoch": 0.8251183814033577, "grad_norm": 1.686129093170166, "learning_rate": 3.681346505737604e-06, "loss": 4.3688, "step": 15334 }, { "epoch": 0.8251721911321567, "grad_norm": 3.700455665588379, "learning_rate": 3.6791393547106533e-06, "loss": 3.4416, "step": 15335 }, { "epoch": 0.8252260008609557, "grad_norm": 2.589517116546631, "learning_rate": 3.676932812976555e-06, "loss": 3.9893, "step": 15336 }, { "epoch": 0.8252798105897546, "grad_norm": 3.1533210277557373, "learning_rate": 3.6747268805983642e-06, "loss": 3.7418, "step": 15337 }, { "epoch": 0.8253336203185536, "grad_norm": 2.742006301879883, "learning_rate": 3.6725215576391136e-06, "loss": 3.9792, "step": 15338 }, { "epoch": 0.8253874300473526, "grad_norm": 2.8954365253448486, "learning_rate": 3.6703168441618417e-06, "loss": 3.1795, "step": 15339 }, { "epoch": 0.8254412397761516, "grad_norm": 2.1871654987335205, "learning_rate": 3.66811274022954e-06, "loss": 4.3913, "step": 15340 }, { "epoch": 0.8254950495049505, "grad_norm": 2.620140790939331, "learning_rate": 3.6659092459052024e-06, "loss": 4.0974, "step": 15341 }, { "epoch": 0.8255488592337494, "grad_norm": 1.981162667274475, "learning_rate": 3.6637063612518037e-06, "loss": 4.1653, "step": 15342 }, { "epoch": 0.8256026689625484, "grad_norm": 1.772586464881897, "learning_rate": 3.6615040863322764e-06, "loss": 4.5878, "step": 15343 }, { "epoch": 0.8256564786913474, "grad_norm": 4.085228443145752, "learning_rate": 3.6593024212095734e-06, "loss": 3.353, "step": 15344 }, { "epoch": 0.8257102884201464, "grad_norm": 2.0322988033294678, "learning_rate": 3.657101365946608e-06, "loss": 4.2393, "step": 15345 }, { "epoch": 0.8257640981489454, "grad_norm": 3.493687391281128, "learning_rate": 3.6549009206062802e-06, "loss": 4.0255, "step": 15346 }, { "epoch": 0.8258179078777443, "grad_norm": 4.618289470672607, "learning_rate": 3.6527010852514724e-06, "loss": 3.9266, "step": 15347 }, { "epoch": 0.8258717176065432, "grad_norm": 3.390796184539795, "learning_rate": 3.6505018599450517e-06, "loss": 3.1334, "step": 15348 }, { "epoch": 0.8259255273353422, "grad_norm": 5.064934253692627, "learning_rate": 3.6483032447498624e-06, "loss": 2.6358, "step": 15349 }, { "epoch": 0.8259793370641412, "grad_norm": 2.7262868881225586, "learning_rate": 3.6461052397287365e-06, "loss": 4.1127, "step": 15350 }, { "epoch": 0.8260331467929402, "grad_norm": 1.5231903791427612, "learning_rate": 3.6439078449444884e-06, "loss": 4.0034, "step": 15351 }, { "epoch": 0.8260869565217391, "grad_norm": 2.5685598850250244, "learning_rate": 3.6417110604599153e-06, "loss": 4.4946, "step": 15352 }, { "epoch": 0.8261407662505381, "grad_norm": 2.142548084259033, "learning_rate": 3.6395148863377858e-06, "loss": 3.8526, "step": 15353 }, { "epoch": 0.8261945759793371, "grad_norm": 2.0956637859344482, "learning_rate": 3.6373193226408726e-06, "loss": 3.928, "step": 15354 }, { "epoch": 0.8262483857081361, "grad_norm": 2.4547510147094727, "learning_rate": 3.635124369431914e-06, "loss": 3.9887, "step": 15355 }, { "epoch": 0.826302195436935, "grad_norm": 3.8023581504821777, "learning_rate": 3.632930026773637e-06, "loss": 3.4675, "step": 15356 }, { "epoch": 0.8263560051657339, "grad_norm": 1.8231863975524902, "learning_rate": 3.6307362947287537e-06, "loss": 4.2165, "step": 15357 }, { "epoch": 0.8264098148945329, "grad_norm": 3.292266368865967, "learning_rate": 3.628543173359941e-06, "loss": 4.027, "step": 15358 }, { "epoch": 0.8264636246233319, "grad_norm": 2.0371415615081787, "learning_rate": 3.6263506627298884e-06, "loss": 3.7209, "step": 15359 }, { "epoch": 0.8265174343521309, "grad_norm": 2.5930042266845703, "learning_rate": 3.624158762901242e-06, "loss": 4.2921, "step": 15360 }, { "epoch": 0.8265712440809299, "grad_norm": 2.614039182662964, "learning_rate": 3.6219674739366468e-06, "loss": 3.3236, "step": 15361 }, { "epoch": 0.8266250538097288, "grad_norm": 2.3316516876220703, "learning_rate": 3.6197767958987217e-06, "loss": 3.3811, "step": 15362 }, { "epoch": 0.8266788635385278, "grad_norm": 2.9598281383514404, "learning_rate": 3.617586728850067e-06, "loss": 3.3838, "step": 15363 }, { "epoch": 0.8267326732673267, "grad_norm": 3.0498762130737305, "learning_rate": 3.615397272853266e-06, "loss": 4.094, "step": 15364 }, { "epoch": 0.8267864829961257, "grad_norm": 4.255832672119141, "learning_rate": 3.613208427970907e-06, "loss": 3.2898, "step": 15365 }, { "epoch": 0.8268402927249247, "grad_norm": 2.120603561401367, "learning_rate": 3.6110201942655186e-06, "loss": 3.8169, "step": 15366 }, { "epoch": 0.8268941024537236, "grad_norm": 4.777279376983643, "learning_rate": 3.6088325717996476e-06, "loss": 3.5262, "step": 15367 }, { "epoch": 0.8269479121825226, "grad_norm": 3.326112747192383, "learning_rate": 3.606645560635802e-06, "loss": 3.8199, "step": 15368 }, { "epoch": 0.8270017219113216, "grad_norm": 1.938188076019287, "learning_rate": 3.604459160836482e-06, "loss": 3.281, "step": 15369 }, { "epoch": 0.8270555316401206, "grad_norm": 3.1741771697998047, "learning_rate": 3.6022733724641768e-06, "loss": 3.5647, "step": 15370 }, { "epoch": 0.8271093413689194, "grad_norm": 1.9884085655212402, "learning_rate": 3.6000881955813442e-06, "loss": 3.9639, "step": 15371 }, { "epoch": 0.8271631510977184, "grad_norm": 3.285799026489258, "learning_rate": 3.5979036302504403e-06, "loss": 3.2774, "step": 15372 }, { "epoch": 0.8272169608265174, "grad_norm": 2.2333321571350098, "learning_rate": 3.595719676533879e-06, "loss": 4.6519, "step": 15373 }, { "epoch": 0.8272707705553164, "grad_norm": 3.1419568061828613, "learning_rate": 3.5935363344940716e-06, "loss": 3.6358, "step": 15374 }, { "epoch": 0.8273245802841154, "grad_norm": 2.4718966484069824, "learning_rate": 3.5913536041934258e-06, "loss": 4.2434, "step": 15375 }, { "epoch": 0.8273783900129144, "grad_norm": 4.392849445343018, "learning_rate": 3.589171485694312e-06, "loss": 3.6348, "step": 15376 }, { "epoch": 0.8274321997417133, "grad_norm": 4.00447416305542, "learning_rate": 3.5869899790590885e-06, "loss": 3.2037, "step": 15377 }, { "epoch": 0.8274860094705123, "grad_norm": 1.8847743272781372, "learning_rate": 3.5848090843500964e-06, "loss": 4.7889, "step": 15378 }, { "epoch": 0.8275398191993112, "grad_norm": 3.2554550170898438, "learning_rate": 3.582628801629659e-06, "loss": 3.4989, "step": 15379 }, { "epoch": 0.8275936289281102, "grad_norm": 1.6621989011764526, "learning_rate": 3.5804491309600866e-06, "loss": 4.0759, "step": 15380 }, { "epoch": 0.8276474386569092, "grad_norm": 2.3079891204833984, "learning_rate": 3.5782700724036666e-06, "loss": 4.0856, "step": 15381 }, { "epoch": 0.8277012483857081, "grad_norm": 2.599062204360962, "learning_rate": 3.5760916260226707e-06, "loss": 4.0656, "step": 15382 }, { "epoch": 0.8277550581145071, "grad_norm": 2.0551865100860596, "learning_rate": 3.573913791879352e-06, "loss": 3.1005, "step": 15383 }, { "epoch": 0.8278088678433061, "grad_norm": 2.8096296787261963, "learning_rate": 3.5717365700359412e-06, "loss": 4.5984, "step": 15384 }, { "epoch": 0.8278626775721051, "grad_norm": 2.684363603591919, "learning_rate": 3.569559960554669e-06, "loss": 3.8955, "step": 15385 }, { "epoch": 0.8279164873009041, "grad_norm": 2.429086923599243, "learning_rate": 3.5673839634977334e-06, "loss": 4.2532, "step": 15386 }, { "epoch": 0.8279702970297029, "grad_norm": 2.589148998260498, "learning_rate": 3.5652085789273174e-06, "loss": 3.726, "step": 15387 }, { "epoch": 0.8280241067585019, "grad_norm": 2.833214282989502, "learning_rate": 3.563033806905594e-06, "loss": 3.4207, "step": 15388 }, { "epoch": 0.8280779164873009, "grad_norm": 1.244125247001648, "learning_rate": 3.560859647494691e-06, "loss": 4.3788, "step": 15389 }, { "epoch": 0.8281317262160999, "grad_norm": 3.483609676361084, "learning_rate": 3.558686100756764e-06, "loss": 3.9389, "step": 15390 }, { "epoch": 0.8281855359448989, "grad_norm": 2.9024643898010254, "learning_rate": 3.5565131667539164e-06, "loss": 3.2242, "step": 15391 }, { "epoch": 0.8282393456736978, "grad_norm": 1.8051384687423706, "learning_rate": 3.5543408455482457e-06, "loss": 4.6279, "step": 15392 }, { "epoch": 0.8282931554024968, "grad_norm": 4.484059810638428, "learning_rate": 3.552169137201833e-06, "loss": 3.6147, "step": 15393 }, { "epoch": 0.8283469651312957, "grad_norm": 2.4302518367767334, "learning_rate": 3.5499980417767363e-06, "loss": 3.8522, "step": 15394 }, { "epoch": 0.8284007748600947, "grad_norm": 1.72971510887146, "learning_rate": 3.547827559335004e-06, "loss": 4.1333, "step": 15395 }, { "epoch": 0.8284545845888936, "grad_norm": 3.2250280380249023, "learning_rate": 3.5456576899386585e-06, "loss": 3.7631, "step": 15396 }, { "epoch": 0.8285083943176926, "grad_norm": 3.252791404724121, "learning_rate": 3.543488433649711e-06, "loss": 4.1149, "step": 15397 }, { "epoch": 0.8285622040464916, "grad_norm": 3.7880570888519287, "learning_rate": 3.5413197905301536e-06, "loss": 2.8283, "step": 15398 }, { "epoch": 0.8286160137752906, "grad_norm": 2.8536741733551025, "learning_rate": 3.5391517606419593e-06, "loss": 3.6049, "step": 15399 }, { "epoch": 0.8286698235040896, "grad_norm": 2.825981855392456, "learning_rate": 3.536984344047081e-06, "loss": 3.9801, "step": 15400 }, { "epoch": 0.8287236332328886, "grad_norm": 4.022724628448486, "learning_rate": 3.534817540807464e-06, "loss": 4.2823, "step": 15401 }, { "epoch": 0.8287774429616874, "grad_norm": 3.402495861053467, "learning_rate": 3.5326513509850307e-06, "loss": 3.8413, "step": 15402 }, { "epoch": 0.8288312526904864, "grad_norm": 4.414391040802002, "learning_rate": 3.530485774641684e-06, "loss": 4.0682, "step": 15403 }, { "epoch": 0.8288850624192854, "grad_norm": 2.58237624168396, "learning_rate": 3.528320811839303e-06, "loss": 3.3353, "step": 15404 }, { "epoch": 0.8289388721480844, "grad_norm": 3.6924140453338623, "learning_rate": 3.5261564626397543e-06, "loss": 3.8345, "step": 15405 }, { "epoch": 0.8289926818768834, "grad_norm": 3.078374147415161, "learning_rate": 3.523992727104905e-06, "loss": 3.5566, "step": 15406 }, { "epoch": 0.8290464916056823, "grad_norm": 3.7209253311157227, "learning_rate": 3.5218296052965755e-06, "loss": 4.2714, "step": 15407 }, { "epoch": 0.8291003013344813, "grad_norm": 2.410257339477539, "learning_rate": 3.519667097276591e-06, "loss": 3.5272, "step": 15408 }, { "epoch": 0.8291541110632802, "grad_norm": 2.2144525051116943, "learning_rate": 3.517505203106741e-06, "loss": 4.2308, "step": 15409 }, { "epoch": 0.8292079207920792, "grad_norm": 3.3379855155944824, "learning_rate": 3.5153439228488154e-06, "loss": 3.6572, "step": 15410 }, { "epoch": 0.8292617305208781, "grad_norm": 3.3569653034210205, "learning_rate": 3.5131832565645702e-06, "loss": 3.6629, "step": 15411 }, { "epoch": 0.8293155402496771, "grad_norm": 4.048040390014648, "learning_rate": 3.5110232043157555e-06, "loss": 3.5558, "step": 15412 }, { "epoch": 0.8293693499784761, "grad_norm": 2.691967487335205, "learning_rate": 3.5088637661641e-06, "loss": 4.4347, "step": 15413 }, { "epoch": 0.8294231597072751, "grad_norm": 1.9074516296386719, "learning_rate": 3.5067049421713155e-06, "loss": 4.379, "step": 15414 }, { "epoch": 0.8294769694360741, "grad_norm": 2.8414833545684814, "learning_rate": 3.504546732399083e-06, "loss": 3.6158, "step": 15415 }, { "epoch": 0.8295307791648731, "grad_norm": 2.618440628051758, "learning_rate": 3.502389136909098e-06, "loss": 3.1488, "step": 15416 }, { "epoch": 0.8295845888936719, "grad_norm": 2.467585325241089, "learning_rate": 3.5002321557630084e-06, "loss": 4.393, "step": 15417 }, { "epoch": 0.8296383986224709, "grad_norm": 2.5696163177490234, "learning_rate": 3.4980757890224648e-06, "loss": 3.2476, "step": 15418 }, { "epoch": 0.8296922083512699, "grad_norm": 2.680882692337036, "learning_rate": 3.495920036749073e-06, "loss": 3.6568, "step": 15419 }, { "epoch": 0.8297460180800689, "grad_norm": 3.010655164718628, "learning_rate": 3.4937648990044424e-06, "loss": 4.2317, "step": 15420 }, { "epoch": 0.8297998278088679, "grad_norm": 1.9327061176300049, "learning_rate": 3.491610375850171e-06, "loss": 4.2485, "step": 15421 }, { "epoch": 0.8298536375376668, "grad_norm": 1.777673363685608, "learning_rate": 3.4894564673478264e-06, "loss": 3.4657, "step": 15422 }, { "epoch": 0.8299074472664658, "grad_norm": 1.4354432821273804, "learning_rate": 3.487303173558959e-06, "loss": 4.243, "step": 15423 }, { "epoch": 0.8299612569952648, "grad_norm": 4.498018741607666, "learning_rate": 3.485150494545103e-06, "loss": 3.7168, "step": 15424 }, { "epoch": 0.8300150667240637, "grad_norm": 3.1585533618927, "learning_rate": 3.4829984303677787e-06, "loss": 3.793, "step": 15425 }, { "epoch": 0.8300688764528626, "grad_norm": 3.1986756324768066, "learning_rate": 3.4808469810884843e-06, "loss": 3.8832, "step": 15426 }, { "epoch": 0.8301226861816616, "grad_norm": 3.605860948562622, "learning_rate": 3.4786961467687036e-06, "loss": 3.7507, "step": 15427 }, { "epoch": 0.8301764959104606, "grad_norm": 3.2412359714508057, "learning_rate": 3.476545927469901e-06, "loss": 3.2719, "step": 15428 }, { "epoch": 0.8302303056392596, "grad_norm": 2.9582808017730713, "learning_rate": 3.474396323253526e-06, "loss": 3.9615, "step": 15429 }, { "epoch": 0.8302841153680586, "grad_norm": 1.8055222034454346, "learning_rate": 3.472247334181006e-06, "loss": 3.7685, "step": 15430 }, { "epoch": 0.8303379250968576, "grad_norm": 2.781934976577759, "learning_rate": 3.47009896031375e-06, "loss": 3.509, "step": 15431 }, { "epoch": 0.8303917348256564, "grad_norm": 3.737854242324829, "learning_rate": 3.4679512017131628e-06, "loss": 3.6584, "step": 15432 }, { "epoch": 0.8304455445544554, "grad_norm": 2.521355390548706, "learning_rate": 3.4658040584406194e-06, "loss": 3.9874, "step": 15433 }, { "epoch": 0.8304993542832544, "grad_norm": 3.3918569087982178, "learning_rate": 3.4636575305574708e-06, "loss": 4.9138, "step": 15434 }, { "epoch": 0.8305531640120534, "grad_norm": 3.387990951538086, "learning_rate": 3.4615116181250655e-06, "loss": 2.8888, "step": 15435 }, { "epoch": 0.8306069737408524, "grad_norm": 3.493959903717041, "learning_rate": 3.459366321204721e-06, "loss": 4.1621, "step": 15436 }, { "epoch": 0.8306607834696513, "grad_norm": 2.896686315536499, "learning_rate": 3.457221639857752e-06, "loss": 4.0307, "step": 15437 }, { "epoch": 0.8307145931984503, "grad_norm": 4.46868896484375, "learning_rate": 3.455077574145449e-06, "loss": 3.3321, "step": 15438 }, { "epoch": 0.8307684029272493, "grad_norm": 3.6694910526275635, "learning_rate": 3.4529341241290786e-06, "loss": 3.5166, "step": 15439 }, { "epoch": 0.8308222126560482, "grad_norm": 1.9516454935073853, "learning_rate": 3.4507912898698953e-06, "loss": 3.8621, "step": 15440 }, { "epoch": 0.8308760223848471, "grad_norm": 3.229933261871338, "learning_rate": 3.448649071429136e-06, "loss": 4.4994, "step": 15441 }, { "epoch": 0.8309298321136461, "grad_norm": 3.4632039070129395, "learning_rate": 3.446507468868021e-06, "loss": 2.8409, "step": 15442 }, { "epoch": 0.8309836418424451, "grad_norm": 3.530482053756714, "learning_rate": 3.444366482247752e-06, "loss": 4.4266, "step": 15443 }, { "epoch": 0.8310374515712441, "grad_norm": 2.732954978942871, "learning_rate": 3.4422261116295096e-06, "loss": 3.9775, "step": 15444 }, { "epoch": 0.8310912613000431, "grad_norm": 2.8487603664398193, "learning_rate": 3.4400863570744596e-06, "loss": 3.2951, "step": 15445 }, { "epoch": 0.831145071028842, "grad_norm": 3.331373691558838, "learning_rate": 3.4379472186437473e-06, "loss": 3.2453, "step": 15446 }, { "epoch": 0.831198880757641, "grad_norm": 4.047353744506836, "learning_rate": 3.4358086963985154e-06, "loss": 3.3046, "step": 15447 }, { "epoch": 0.8312526904864399, "grad_norm": 1.9763731956481934, "learning_rate": 3.4336707903998707e-06, "loss": 4.4866, "step": 15448 }, { "epoch": 0.8313065002152389, "grad_norm": 3.0269076824188232, "learning_rate": 3.431533500708911e-06, "loss": 4.3248, "step": 15449 }, { "epoch": 0.8313603099440379, "grad_norm": 2.6781742572784424, "learning_rate": 3.4293968273867076e-06, "loss": 3.5432, "step": 15450 }, { "epoch": 0.8314141196728368, "grad_norm": 2.9400861263275146, "learning_rate": 3.42726077049432e-06, "loss": 4.0094, "step": 15451 }, { "epoch": 0.8314679294016358, "grad_norm": 3.454926013946533, "learning_rate": 3.4251253300927986e-06, "loss": 3.5782, "step": 15452 }, { "epoch": 0.8315217391304348, "grad_norm": 2.955303430557251, "learning_rate": 3.4229905062431677e-06, "loss": 4.0703, "step": 15453 }, { "epoch": 0.8315755488592338, "grad_norm": 3.1984052658081055, "learning_rate": 3.4208562990064338e-06, "loss": 3.4872, "step": 15454 }, { "epoch": 0.8316293585880327, "grad_norm": 2.291963815689087, "learning_rate": 3.4187227084435837e-06, "loss": 4.2577, "step": 15455 }, { "epoch": 0.8316831683168316, "grad_norm": 2.2374379634857178, "learning_rate": 3.416589734615591e-06, "loss": 3.3368, "step": 15456 }, { "epoch": 0.8317369780456306, "grad_norm": 1.188246250152588, "learning_rate": 3.4144573775834134e-06, "loss": 4.5031, "step": 15457 }, { "epoch": 0.8317907877744296, "grad_norm": 2.0356314182281494, "learning_rate": 3.412325637407984e-06, "loss": 4.3111, "step": 15458 }, { "epoch": 0.8318445975032286, "grad_norm": 2.5894482135772705, "learning_rate": 3.410194514150225e-06, "loss": 4.288, "step": 15459 }, { "epoch": 0.8318984072320276, "grad_norm": 4.094282150268555, "learning_rate": 3.408064007871037e-06, "loss": 3.1492, "step": 15460 }, { "epoch": 0.8319522169608266, "grad_norm": 3.0261192321777344, "learning_rate": 3.4059341186313044e-06, "loss": 2.9699, "step": 15461 }, { "epoch": 0.8320060266896255, "grad_norm": 2.687692880630493, "learning_rate": 3.403804846491887e-06, "loss": 3.4812, "step": 15462 }, { "epoch": 0.8320598364184244, "grad_norm": 3.155242681503296, "learning_rate": 3.4016761915136477e-06, "loss": 3.8648, "step": 15463 }, { "epoch": 0.8321136461472234, "grad_norm": 2.776973009109497, "learning_rate": 3.3995481537574146e-06, "loss": 3.518, "step": 15464 }, { "epoch": 0.8321674558760224, "grad_norm": 2.804131507873535, "learning_rate": 3.3974207332839902e-06, "loss": 4.2274, "step": 15465 }, { "epoch": 0.8322212656048213, "grad_norm": 2.1121985912323, "learning_rate": 3.395293930154178e-06, "loss": 4.3288, "step": 15466 }, { "epoch": 0.8322750753336203, "grad_norm": 3.378310441970825, "learning_rate": 3.393167744428749e-06, "loss": 4.0076, "step": 15467 }, { "epoch": 0.8323288850624193, "grad_norm": 2.9483187198638916, "learning_rate": 3.391042176168477e-06, "loss": 3.5128, "step": 15468 }, { "epoch": 0.8323826947912183, "grad_norm": 2.2297420501708984, "learning_rate": 3.388917225434099e-06, "loss": 4.4626, "step": 15469 }, { "epoch": 0.8324365045200173, "grad_norm": 1.4248251914978027, "learning_rate": 3.386792892286336e-06, "loss": 4.2878, "step": 15470 }, { "epoch": 0.8324903142488161, "grad_norm": 3.6553187370300293, "learning_rate": 3.384669176785904e-06, "loss": 4.1954, "step": 15471 }, { "epoch": 0.8325441239776151, "grad_norm": 2.1046061515808105, "learning_rate": 3.382546078993487e-06, "loss": 3.9668, "step": 15472 }, { "epoch": 0.8325979337064141, "grad_norm": 3.68328857421875, "learning_rate": 3.3804235989697563e-06, "loss": 3.7101, "step": 15473 }, { "epoch": 0.8326517434352131, "grad_norm": 3.6974217891693115, "learning_rate": 3.3783017367753717e-06, "loss": 3.2957, "step": 15474 }, { "epoch": 0.8327055531640121, "grad_norm": 3.2551419734954834, "learning_rate": 3.3761804924709676e-06, "loss": 3.1615, "step": 15475 }, { "epoch": 0.832759362892811, "grad_norm": 2.2635467052459717, "learning_rate": 3.3740598661171657e-06, "loss": 3.8379, "step": 15476 }, { "epoch": 0.83281317262161, "grad_norm": 3.0806353092193604, "learning_rate": 3.3719398577745586e-06, "loss": 3.4492, "step": 15477 }, { "epoch": 0.8328669823504089, "grad_norm": 1.902578592300415, "learning_rate": 3.3698204675037425e-06, "loss": 3.2042, "step": 15478 }, { "epoch": 0.8329207920792079, "grad_norm": 1.4052814245224, "learning_rate": 3.3677016953652858e-06, "loss": 4.4316, "step": 15479 }, { "epoch": 0.8329746018080069, "grad_norm": 2.7369344234466553, "learning_rate": 3.3655835414197255e-06, "loss": 3.7029, "step": 15480 }, { "epoch": 0.8330284115368058, "grad_norm": 2.61088490486145, "learning_rate": 3.363466005727595e-06, "loss": 3.4335, "step": 15481 }, { "epoch": 0.8330822212656048, "grad_norm": 1.9180020093917847, "learning_rate": 3.361349088349408e-06, "loss": 4.2435, "step": 15482 }, { "epoch": 0.8331360309944038, "grad_norm": 2.347864866256714, "learning_rate": 3.3592327893456676e-06, "loss": 3.0412, "step": 15483 }, { "epoch": 0.8331898407232028, "grad_norm": 4.943458080291748, "learning_rate": 3.357117108776847e-06, "loss": 3.004, "step": 15484 }, { "epoch": 0.8332436504520018, "grad_norm": 3.3211684226989746, "learning_rate": 3.3550020467034067e-06, "loss": 4.1888, "step": 15485 }, { "epoch": 0.8332974601808006, "grad_norm": 4.81129264831543, "learning_rate": 3.352887603185789e-06, "loss": 3.5447, "step": 15486 }, { "epoch": 0.8333512699095996, "grad_norm": 2.7279059886932373, "learning_rate": 3.350773778284422e-06, "loss": 3.6964, "step": 15487 }, { "epoch": 0.8334050796383986, "grad_norm": 2.4319300651550293, "learning_rate": 3.3486605720597086e-06, "loss": 3.3052, "step": 15488 }, { "epoch": 0.8334588893671976, "grad_norm": 4.10753870010376, "learning_rate": 3.3465479845720433e-06, "loss": 4.1545, "step": 15489 }, { "epoch": 0.8335126990959966, "grad_norm": 2.544548749923706, "learning_rate": 3.344436015881794e-06, "loss": 4.0617, "step": 15490 }, { "epoch": 0.8335665088247955, "grad_norm": 2.4178578853607178, "learning_rate": 3.342324666049318e-06, "loss": 4.083, "step": 15491 }, { "epoch": 0.8336203185535945, "grad_norm": 2.4774158000946045, "learning_rate": 3.3402139351349477e-06, "loss": 3.3985, "step": 15492 }, { "epoch": 0.8336741282823935, "grad_norm": 4.171675205230713, "learning_rate": 3.3381038231990013e-06, "loss": 3.6481, "step": 15493 }, { "epoch": 0.8337279380111924, "grad_norm": 2.3427488803863525, "learning_rate": 3.3359943303017922e-06, "loss": 4.0769, "step": 15494 }, { "epoch": 0.8337817477399914, "grad_norm": 2.927704334259033, "learning_rate": 3.3338854565035964e-06, "loss": 3.2025, "step": 15495 }, { "epoch": 0.8338355574687903, "grad_norm": 3.0125019550323486, "learning_rate": 3.3317772018646777e-06, "loss": 3.8991, "step": 15496 }, { "epoch": 0.8338893671975893, "grad_norm": 3.809864044189453, "learning_rate": 3.329669566445279e-06, "loss": 3.5454, "step": 15497 }, { "epoch": 0.8339431769263883, "grad_norm": 2.5792458057403564, "learning_rate": 3.3275625503056434e-06, "loss": 3.7011, "step": 15498 }, { "epoch": 0.8339969866551873, "grad_norm": 1.802215814590454, "learning_rate": 3.3254561535059762e-06, "loss": 4.4776, "step": 15499 }, { "epoch": 0.8340507963839863, "grad_norm": 3.797351121902466, "learning_rate": 3.3233503761064765e-06, "loss": 3.3975, "step": 15500 }, { "epoch": 0.8341046061127851, "grad_norm": 1.600901484489441, "learning_rate": 3.3212452181673208e-06, "loss": 3.7281, "step": 15501 }, { "epoch": 0.8341584158415841, "grad_norm": 5.648985862731934, "learning_rate": 3.319140679748667e-06, "loss": 4.0135, "step": 15502 }, { "epoch": 0.8342122255703831, "grad_norm": 2.115293502807617, "learning_rate": 3.317036760910655e-06, "loss": 3.7017, "step": 15503 }, { "epoch": 0.8342660352991821, "grad_norm": 2.5220651626586914, "learning_rate": 3.314933461713415e-06, "loss": 3.569, "step": 15504 }, { "epoch": 0.8343198450279811, "grad_norm": 2.330350399017334, "learning_rate": 3.3128307822170496e-06, "loss": 4.0065, "step": 15505 }, { "epoch": 0.83437365475678, "grad_norm": 5.053793430328369, "learning_rate": 3.3107287224816485e-06, "loss": 3.8019, "step": 15506 }, { "epoch": 0.834427464485579, "grad_norm": 3.56124210357666, "learning_rate": 3.308627282567284e-06, "loss": 3.3916, "step": 15507 }, { "epoch": 0.834481274214378, "grad_norm": 2.915259599685669, "learning_rate": 3.3065264625340044e-06, "loss": 3.8241, "step": 15508 }, { "epoch": 0.8345350839431769, "grad_norm": 5.534905910491943, "learning_rate": 3.3044262624418537e-06, "loss": 3.8278, "step": 15509 }, { "epoch": 0.8345888936719759, "grad_norm": 2.3393514156341553, "learning_rate": 3.3023266823508535e-06, "loss": 3.2072, "step": 15510 }, { "epoch": 0.8346427034007748, "grad_norm": 4.196343421936035, "learning_rate": 3.3002277223209892e-06, "loss": 4.1783, "step": 15511 }, { "epoch": 0.8346965131295738, "grad_norm": 2.991452217102051, "learning_rate": 3.2981293824122517e-06, "loss": 3.9237, "step": 15512 }, { "epoch": 0.8347503228583728, "grad_norm": 2.8572580814361572, "learning_rate": 3.296031662684601e-06, "loss": 2.5178, "step": 15513 }, { "epoch": 0.8348041325871718, "grad_norm": 2.5656023025512695, "learning_rate": 3.2939345631979923e-06, "loss": 4.1025, "step": 15514 }, { "epoch": 0.8348579423159708, "grad_norm": 4.429043292999268, "learning_rate": 3.2918380840123523e-06, "loss": 4.2479, "step": 15515 }, { "epoch": 0.8349117520447696, "grad_norm": 2.594548463821411, "learning_rate": 3.289742225187592e-06, "loss": 3.4131, "step": 15516 }, { "epoch": 0.8349655617735686, "grad_norm": 2.45816707611084, "learning_rate": 3.28764698678361e-06, "loss": 4.5767, "step": 15517 }, { "epoch": 0.8350193715023676, "grad_norm": 1.600818395614624, "learning_rate": 3.2855523688602674e-06, "loss": 4.2998, "step": 15518 }, { "epoch": 0.8350731812311666, "grad_norm": 2.339397430419922, "learning_rate": 3.283458371477438e-06, "loss": 4.4394, "step": 15519 }, { "epoch": 0.8351269909599656, "grad_norm": 3.9239890575408936, "learning_rate": 3.281364994694958e-06, "loss": 4.2179, "step": 15520 }, { "epoch": 0.8351808006887645, "grad_norm": 1.462006688117981, "learning_rate": 3.2792722385726476e-06, "loss": 4.0498, "step": 15521 }, { "epoch": 0.8352346104175635, "grad_norm": 2.7642405033111572, "learning_rate": 3.2771801031703185e-06, "loss": 3.3707, "step": 15522 }, { "epoch": 0.8352884201463625, "grad_norm": 1.820805549621582, "learning_rate": 3.2750885885477532e-06, "loss": 4.047, "step": 15523 }, { "epoch": 0.8353422298751614, "grad_norm": 5.0015950202941895, "learning_rate": 3.272997694764718e-06, "loss": 2.9389, "step": 15524 }, { "epoch": 0.8353960396039604, "grad_norm": 2.3426973819732666, "learning_rate": 3.2709074218809782e-06, "loss": 4.1826, "step": 15525 }, { "epoch": 0.8354498493327593, "grad_norm": 1.7616808414459229, "learning_rate": 3.268817769956259e-06, "loss": 4.3909, "step": 15526 }, { "epoch": 0.8355036590615583, "grad_norm": 2.7086193561553955, "learning_rate": 3.2667287390502733e-06, "loss": 3.7558, "step": 15527 }, { "epoch": 0.8355574687903573, "grad_norm": 3.8541080951690674, "learning_rate": 3.2646403292227236e-06, "loss": 4.0827, "step": 15528 }, { "epoch": 0.8356112785191563, "grad_norm": 2.2973921298980713, "learning_rate": 3.2625525405332925e-06, "loss": 3.9268, "step": 15529 }, { "epoch": 0.8356650882479553, "grad_norm": 3.8059022426605225, "learning_rate": 3.260465373041646e-06, "loss": 4.1407, "step": 15530 }, { "epoch": 0.8357188979767542, "grad_norm": 3.7196407318115234, "learning_rate": 3.258378826807426e-06, "loss": 3.3252, "step": 15531 }, { "epoch": 0.8357727077055531, "grad_norm": 1.6109521389007568, "learning_rate": 3.256292901890262e-06, "loss": 3.0174, "step": 15532 }, { "epoch": 0.8358265174343521, "grad_norm": 3.8779962062835693, "learning_rate": 3.2542075983497623e-06, "loss": 3.5875, "step": 15533 }, { "epoch": 0.8358803271631511, "grad_norm": 2.568119525909424, "learning_rate": 3.2521229162455204e-06, "loss": 3.7189, "step": 15534 }, { "epoch": 0.8359341368919501, "grad_norm": 3.401369333267212, "learning_rate": 3.250038855637111e-06, "loss": 2.7972, "step": 15535 }, { "epoch": 0.835987946620749, "grad_norm": 3.729881525039673, "learning_rate": 3.247955416584089e-06, "loss": 3.569, "step": 15536 }, { "epoch": 0.836041756349548, "grad_norm": 3.3466055393218994, "learning_rate": 3.2458725991459967e-06, "loss": 4.759, "step": 15537 }, { "epoch": 0.836095566078347, "grad_norm": 2.1573374271392822, "learning_rate": 3.2437904033823547e-06, "loss": 3.9402, "step": 15538 }, { "epoch": 0.8361493758071459, "grad_norm": 3.081611156463623, "learning_rate": 3.2417088293526575e-06, "loss": 2.9846, "step": 15539 }, { "epoch": 0.8362031855359449, "grad_norm": 1.4206682443618774, "learning_rate": 3.239627877116411e-06, "loss": 4.3273, "step": 15540 }, { "epoch": 0.8362569952647438, "grad_norm": 3.7783985137939453, "learning_rate": 3.237547546733066e-06, "loss": 3.5192, "step": 15541 }, { "epoch": 0.8363108049935428, "grad_norm": 2.560992956161499, "learning_rate": 3.235467838262077e-06, "loss": 3.741, "step": 15542 }, { "epoch": 0.8363646147223418, "grad_norm": 3.48399019241333, "learning_rate": 3.233388751762878e-06, "loss": 3.6205, "step": 15543 }, { "epoch": 0.8364184244511408, "grad_norm": 2.364169120788574, "learning_rate": 3.231310287294878e-06, "loss": 3.5702, "step": 15544 }, { "epoch": 0.8364722341799398, "grad_norm": 3.34061336517334, "learning_rate": 3.229232444917485e-06, "loss": 3.4755, "step": 15545 }, { "epoch": 0.8365260439087387, "grad_norm": 2.4208123683929443, "learning_rate": 3.227155224690073e-06, "loss": 4.1462, "step": 15546 }, { "epoch": 0.8365798536375376, "grad_norm": 3.2867088317871094, "learning_rate": 3.2250786266720012e-06, "loss": 4.2423, "step": 15547 }, { "epoch": 0.8366336633663366, "grad_norm": 1.5822644233703613, "learning_rate": 3.2230026509226213e-06, "loss": 4.3956, "step": 15548 }, { "epoch": 0.8366874730951356, "grad_norm": 3.618624687194824, "learning_rate": 3.2209272975012387e-06, "loss": 3.2671, "step": 15549 }, { "epoch": 0.8367412828239346, "grad_norm": 2.6055521965026855, "learning_rate": 3.2188525664671843e-06, "loss": 4.0653, "step": 15550 }, { "epoch": 0.8367950925527335, "grad_norm": 3.286198139190674, "learning_rate": 3.216778457879735e-06, "loss": 4.1949, "step": 15551 }, { "epoch": 0.8368489022815325, "grad_norm": 2.2709708213806152, "learning_rate": 3.2147049717981713e-06, "loss": 4.1094, "step": 15552 }, { "epoch": 0.8369027120103315, "grad_norm": 4.08903694152832, "learning_rate": 3.2126321082817405e-06, "loss": 3.2397, "step": 15553 }, { "epoch": 0.8369565217391305, "grad_norm": 3.4598329067230225, "learning_rate": 3.210559867389687e-06, "loss": 3.093, "step": 15554 }, { "epoch": 0.8370103314679294, "grad_norm": 3.0998427867889404, "learning_rate": 3.208488249181216e-06, "loss": 4.6209, "step": 15555 }, { "epoch": 0.8370641411967283, "grad_norm": 2.9480302333831787, "learning_rate": 3.206417253715552e-06, "loss": 4.1146, "step": 15556 }, { "epoch": 0.8371179509255273, "grad_norm": 2.0514237880706787, "learning_rate": 3.204346881051859e-06, "loss": 3.9002, "step": 15557 }, { "epoch": 0.8371717606543263, "grad_norm": 3.110598564147949, "learning_rate": 3.2022771312493093e-06, "loss": 3.6149, "step": 15558 }, { "epoch": 0.8372255703831253, "grad_norm": 1.616180658340454, "learning_rate": 3.2002080043670445e-06, "loss": 3.6944, "step": 15559 }, { "epoch": 0.8372793801119243, "grad_norm": 4.488832950592041, "learning_rate": 3.1981395004642063e-06, "loss": 4.2715, "step": 15560 }, { "epoch": 0.8373331898407232, "grad_norm": 2.4497172832489014, "learning_rate": 3.1960716195998995e-06, "loss": 3.8016, "step": 15561 }, { "epoch": 0.8373869995695221, "grad_norm": 2.576296091079712, "learning_rate": 3.1940043618332194e-06, "loss": 2.3036, "step": 15562 }, { "epoch": 0.8374408092983211, "grad_norm": 4.923370838165283, "learning_rate": 3.1919377272232517e-06, "loss": 3.7269, "step": 15563 }, { "epoch": 0.8374946190271201, "grad_norm": 2.3841843605041504, "learning_rate": 3.189871715829035e-06, "loss": 4.0797, "step": 15564 }, { "epoch": 0.8375484287559191, "grad_norm": 2.041604995727539, "learning_rate": 3.1878063277096277e-06, "loss": 4.5731, "step": 15565 }, { "epoch": 0.837602238484718, "grad_norm": 3.850795030593872, "learning_rate": 3.1857415629240465e-06, "loss": 3.681, "step": 15566 }, { "epoch": 0.837656048213517, "grad_norm": 2.0807855129241943, "learning_rate": 3.1836774215313004e-06, "loss": 3.3498, "step": 15567 }, { "epoch": 0.837709857942316, "grad_norm": 2.782310724258423, "learning_rate": 3.181613903590372e-06, "loss": 3.4425, "step": 15568 }, { "epoch": 0.837763667671115, "grad_norm": 4.816100597381592, "learning_rate": 3.1795510091602337e-06, "loss": 3.1097, "step": 15569 }, { "epoch": 0.8378174773999139, "grad_norm": 4.6643877029418945, "learning_rate": 3.1774887382998332e-06, "loss": 3.0288, "step": 15570 }, { "epoch": 0.8378712871287128, "grad_norm": 2.6386446952819824, "learning_rate": 3.17542709106812e-06, "loss": 4.083, "step": 15571 }, { "epoch": 0.8379250968575118, "grad_norm": 4.587379455566406, "learning_rate": 3.1733660675239947e-06, "loss": 3.238, "step": 15572 }, { "epoch": 0.8379789065863108, "grad_norm": 3.667880058288574, "learning_rate": 3.17130566772636e-06, "loss": 4.0328, "step": 15573 }, { "epoch": 0.8380327163151098, "grad_norm": 2.173887014389038, "learning_rate": 3.169245891734093e-06, "loss": 3.3234, "step": 15574 }, { "epoch": 0.8380865260439088, "grad_norm": 2.9213194847106934, "learning_rate": 3.1671867396060595e-06, "loss": 3.5093, "step": 15575 }, { "epoch": 0.8381403357727077, "grad_norm": 2.736543893814087, "learning_rate": 3.165128211401111e-06, "loss": 3.4592, "step": 15576 }, { "epoch": 0.8381941455015067, "grad_norm": 4.400599956512451, "learning_rate": 3.1630703071780677e-06, "loss": 3.0615, "step": 15577 }, { "epoch": 0.8382479552303056, "grad_norm": 2.529052734375, "learning_rate": 3.1610130269957405e-06, "loss": 3.7652, "step": 15578 }, { "epoch": 0.8383017649591046, "grad_norm": 1.7030749320983887, "learning_rate": 3.158956370912927e-06, "loss": 4.3121, "step": 15579 }, { "epoch": 0.8383555746879036, "grad_norm": 2.0846822261810303, "learning_rate": 3.156900338988386e-06, "loss": 3.9071, "step": 15580 }, { "epoch": 0.8384093844167025, "grad_norm": 2.5523886680603027, "learning_rate": 3.154844931280884e-06, "loss": 3.4761, "step": 15581 }, { "epoch": 0.8384631941455015, "grad_norm": 3.7638330459594727, "learning_rate": 3.1527901478491608e-06, "loss": 3.6056, "step": 15582 }, { "epoch": 0.8385170038743005, "grad_norm": 2.976341962814331, "learning_rate": 3.150735988751932e-06, "loss": 2.9322, "step": 15583 }, { "epoch": 0.8385708136030995, "grad_norm": 4.703869342803955, "learning_rate": 3.1486824540478994e-06, "loss": 3.6355, "step": 15584 }, { "epoch": 0.8386246233318984, "grad_norm": 1.9378926753997803, "learning_rate": 3.1466295437957512e-06, "loss": 3.9397, "step": 15585 }, { "epoch": 0.8386784330606973, "grad_norm": 3.1213908195495605, "learning_rate": 3.144577258054149e-06, "loss": 3.7515, "step": 15586 }, { "epoch": 0.8387322427894963, "grad_norm": 2.3379969596862793, "learning_rate": 3.1425255968817487e-06, "loss": 3.7995, "step": 15587 }, { "epoch": 0.8387860525182953, "grad_norm": 3.977320909500122, "learning_rate": 3.1404745603371728e-06, "loss": 3.2008, "step": 15588 }, { "epoch": 0.8388398622470943, "grad_norm": 2.6620190143585205, "learning_rate": 3.138424148479041e-06, "loss": 3.8107, "step": 15589 }, { "epoch": 0.8388936719758933, "grad_norm": 1.928740382194519, "learning_rate": 3.136374361365943e-06, "loss": 3.9522, "step": 15590 }, { "epoch": 0.8389474817046922, "grad_norm": 3.0845391750335693, "learning_rate": 3.134325199056462e-06, "loss": 3.9386, "step": 15591 }, { "epoch": 0.8390012914334912, "grad_norm": 4.223118782043457, "learning_rate": 3.1322766616091543e-06, "loss": 3.7536, "step": 15592 }, { "epoch": 0.8390551011622901, "grad_norm": 2.690901517868042, "learning_rate": 3.1302287490825642e-06, "loss": 3.8976, "step": 15593 }, { "epoch": 0.8391089108910891, "grad_norm": 2.774611234664917, "learning_rate": 3.1281814615352206e-06, "loss": 4.2275, "step": 15594 }, { "epoch": 0.8391627206198881, "grad_norm": 4.8428239822387695, "learning_rate": 3.1261347990256098e-06, "loss": 4.1, "step": 15595 }, { "epoch": 0.839216530348687, "grad_norm": 2.9354937076568604, "learning_rate": 3.124088761612237e-06, "loss": 3.256, "step": 15596 }, { "epoch": 0.839270340077486, "grad_norm": 2.6412792205810547, "learning_rate": 3.1220433493535706e-06, "loss": 3.9382, "step": 15597 }, { "epoch": 0.839324149806285, "grad_norm": 4.346717834472656, "learning_rate": 3.1199985623080573e-06, "loss": 3.2103, "step": 15598 }, { "epoch": 0.839377959535084, "grad_norm": 2.45157790184021, "learning_rate": 3.117954400534137e-06, "loss": 3.934, "step": 15599 }, { "epoch": 0.839431769263883, "grad_norm": 2.1915791034698486, "learning_rate": 3.115910864090224e-06, "loss": 3.7587, "step": 15600 }, { "epoch": 0.8394855789926818, "grad_norm": 4.1088151931762695, "learning_rate": 3.11386795303471e-06, "loss": 3.8082, "step": 15601 }, { "epoch": 0.8395393887214808, "grad_norm": 3.1925153732299805, "learning_rate": 3.1118256674259966e-06, "loss": 3.5916, "step": 15602 }, { "epoch": 0.8395931984502798, "grad_norm": 1.7648365497589111, "learning_rate": 3.1097840073224277e-06, "loss": 4.1363, "step": 15603 }, { "epoch": 0.8396470081790788, "grad_norm": 3.351902723312378, "learning_rate": 3.1077429727823513e-06, "loss": 3.1382, "step": 15604 }, { "epoch": 0.8397008179078778, "grad_norm": 2.214149236679077, "learning_rate": 3.1057025638641018e-06, "loss": 4.0026, "step": 15605 }, { "epoch": 0.8397546276366767, "grad_norm": 3.5548534393310547, "learning_rate": 3.1036627806259765e-06, "loss": 3.7261, "step": 15606 }, { "epoch": 0.8398084373654757, "grad_norm": 2.710293769836426, "learning_rate": 3.101623623126279e-06, "loss": 4.1244, "step": 15607 }, { "epoch": 0.8398622470942746, "grad_norm": 2.1610524654388428, "learning_rate": 3.0995850914232795e-06, "loss": 3.9431, "step": 15608 }, { "epoch": 0.8399160568230736, "grad_norm": 2.237544536590576, "learning_rate": 3.097547185575239e-06, "loss": 3.908, "step": 15609 }, { "epoch": 0.8399698665518726, "grad_norm": 2.624086856842041, "learning_rate": 3.095509905640384e-06, "loss": 3.898, "step": 15610 }, { "epoch": 0.8400236762806715, "grad_norm": 2.9084551334381104, "learning_rate": 3.0934732516769345e-06, "loss": 3.8699, "step": 15611 }, { "epoch": 0.8400774860094705, "grad_norm": 1.7008925676345825, "learning_rate": 3.0914372237431018e-06, "loss": 4.4869, "step": 15612 }, { "epoch": 0.8401312957382695, "grad_norm": 3.949819803237915, "learning_rate": 3.0894018218970673e-06, "loss": 2.9399, "step": 15613 }, { "epoch": 0.8401851054670685, "grad_norm": 3.650570869445801, "learning_rate": 3.0873670461969957e-06, "loss": 3.6219, "step": 15614 }, { "epoch": 0.8402389151958675, "grad_norm": 1.3579820394515991, "learning_rate": 3.0853328967010348e-06, "loss": 3.3054, "step": 15615 }, { "epoch": 0.8402927249246663, "grad_norm": 2.008986711502075, "learning_rate": 3.083299373467316e-06, "loss": 4.062, "step": 15616 }, { "epoch": 0.8403465346534653, "grad_norm": 2.092353582382202, "learning_rate": 3.081266476553954e-06, "loss": 3.0342, "step": 15617 }, { "epoch": 0.8404003443822643, "grad_norm": 2.2299416065216064, "learning_rate": 3.079234206019041e-06, "loss": 3.6921, "step": 15618 }, { "epoch": 0.8404541541110633, "grad_norm": 1.675776720046997, "learning_rate": 3.0772025619206556e-06, "loss": 3.5106, "step": 15619 }, { "epoch": 0.8405079638398623, "grad_norm": 3.4782333374023438, "learning_rate": 3.075171544316854e-06, "loss": 3.3202, "step": 15620 }, { "epoch": 0.8405617735686612, "grad_norm": 2.3534953594207764, "learning_rate": 3.073141153265674e-06, "loss": 4.224, "step": 15621 }, { "epoch": 0.8406155832974602, "grad_norm": 2.741330146789551, "learning_rate": 3.0711113888251485e-06, "loss": 3.4806, "step": 15622 }, { "epoch": 0.8406693930262591, "grad_norm": 1.990795373916626, "learning_rate": 3.0690822510532763e-06, "loss": 3.5565, "step": 15623 }, { "epoch": 0.8407232027550581, "grad_norm": 2.7313756942749023, "learning_rate": 3.067053740008055e-06, "loss": 3.5409, "step": 15624 }, { "epoch": 0.8407770124838571, "grad_norm": 4.654406547546387, "learning_rate": 3.065025855747436e-06, "loss": 3.9999, "step": 15625 }, { "epoch": 0.840830822212656, "grad_norm": 2.2651326656341553, "learning_rate": 3.062998598329378e-06, "loss": 3.8696, "step": 15626 }, { "epoch": 0.840884631941455, "grad_norm": 3.8083126544952393, "learning_rate": 3.060971967811818e-06, "loss": 3.4936, "step": 15627 }, { "epoch": 0.840938441670254, "grad_norm": 3.4352524280548096, "learning_rate": 3.058945964252674e-06, "loss": 3.1677, "step": 15628 }, { "epoch": 0.840992251399053, "grad_norm": 2.750034809112549, "learning_rate": 3.0569205877098383e-06, "loss": 4.5728, "step": 15629 }, { "epoch": 0.841046061127852, "grad_norm": 3.0613343715667725, "learning_rate": 3.0548958382411923e-06, "loss": 3.5233, "step": 15630 }, { "epoch": 0.8410998708566508, "grad_norm": 4.451419830322266, "learning_rate": 3.0528717159045956e-06, "loss": 3.6026, "step": 15631 }, { "epoch": 0.8411536805854498, "grad_norm": 5.164419174194336, "learning_rate": 3.0508482207578985e-06, "loss": 3.152, "step": 15632 }, { "epoch": 0.8412074903142488, "grad_norm": 3.032028913497925, "learning_rate": 3.0488253528589194e-06, "loss": 3.8852, "step": 15633 }, { "epoch": 0.8412613000430478, "grad_norm": 2.735718250274658, "learning_rate": 3.046803112265473e-06, "loss": 3.8523, "step": 15634 }, { "epoch": 0.8413151097718468, "grad_norm": 3.425712823867798, "learning_rate": 3.044781499035343e-06, "loss": 3.8178, "step": 15635 }, { "epoch": 0.8413689195006457, "grad_norm": 2.668013572692871, "learning_rate": 3.0427605132263087e-06, "loss": 3.4802, "step": 15636 }, { "epoch": 0.8414227292294447, "grad_norm": 3.881425380706787, "learning_rate": 3.0407401548961127e-06, "loss": 2.8313, "step": 15637 }, { "epoch": 0.8414765389582437, "grad_norm": 1.9614710807800293, "learning_rate": 3.0387204241025064e-06, "loss": 4.3527, "step": 15638 }, { "epoch": 0.8415303486870426, "grad_norm": 2.325590133666992, "learning_rate": 3.036701320903201e-06, "loss": 3.4687, "step": 15639 }, { "epoch": 0.8415841584158416, "grad_norm": 3.6291093826293945, "learning_rate": 3.0346828453559045e-06, "loss": 3.7218, "step": 15640 }, { "epoch": 0.8416379681446405, "grad_norm": 3.280731201171875, "learning_rate": 3.0326649975182865e-06, "loss": 3.9441, "step": 15641 }, { "epoch": 0.8416917778734395, "grad_norm": 4.82673454284668, "learning_rate": 3.030647777448012e-06, "loss": 3.194, "step": 15642 }, { "epoch": 0.8417455876022385, "grad_norm": 3.5602922439575195, "learning_rate": 3.028631185202738e-06, "loss": 3.1847, "step": 15643 }, { "epoch": 0.8417993973310375, "grad_norm": 2.3001277446746826, "learning_rate": 3.0266152208400874e-06, "loss": 4.0456, "step": 15644 }, { "epoch": 0.8418532070598365, "grad_norm": 1.8806862831115723, "learning_rate": 3.0245998844176756e-06, "loss": 4.0543, "step": 15645 }, { "epoch": 0.8419070167886353, "grad_norm": 3.398381471633911, "learning_rate": 3.0225851759930896e-06, "loss": 3.2355, "step": 15646 }, { "epoch": 0.8419608265174343, "grad_norm": 2.9330191612243652, "learning_rate": 3.0205710956239086e-06, "loss": 3.2918, "step": 15647 }, { "epoch": 0.8420146362462333, "grad_norm": 2.993446111679077, "learning_rate": 3.0185576433676864e-06, "loss": 4.3116, "step": 15648 }, { "epoch": 0.8420684459750323, "grad_norm": 3.8466644287109375, "learning_rate": 3.016544819281966e-06, "loss": 3.1413, "step": 15649 }, { "epoch": 0.8421222557038313, "grad_norm": 1.6115145683288574, "learning_rate": 3.0145326234242627e-06, "loss": 4.41, "step": 15650 }, { "epoch": 0.8421760654326302, "grad_norm": 1.841071605682373, "learning_rate": 3.0125210558520857e-06, "loss": 3.0909, "step": 15651 }, { "epoch": 0.8422298751614292, "grad_norm": 3.3881888389587402, "learning_rate": 3.010510116622911e-06, "loss": 2.7196, "step": 15652 }, { "epoch": 0.8422836848902282, "grad_norm": 1.2745494842529297, "learning_rate": 3.008499805794218e-06, "loss": 4.0729, "step": 15653 }, { "epoch": 0.8423374946190271, "grad_norm": 3.3499886989593506, "learning_rate": 3.0064901234234527e-06, "loss": 3.4019, "step": 15654 }, { "epoch": 0.842391304347826, "grad_norm": 4.771039009094238, "learning_rate": 3.0044810695680466e-06, "loss": 3.2642, "step": 15655 }, { "epoch": 0.842445114076625, "grad_norm": 3.1379363536834717, "learning_rate": 3.0024726442854064e-06, "loss": 3.5243, "step": 15656 }, { "epoch": 0.842498923805424, "grad_norm": 3.335214614868164, "learning_rate": 3.000464847632925e-06, "loss": 3.9671, "step": 15657 }, { "epoch": 0.842552733534223, "grad_norm": 3.128190279006958, "learning_rate": 2.998457679667993e-06, "loss": 3.5942, "step": 15658 }, { "epoch": 0.842606543263022, "grad_norm": 1.9069496393203735, "learning_rate": 2.9964511404479646e-06, "loss": 4.0514, "step": 15659 }, { "epoch": 0.842660352991821, "grad_norm": 2.145048141479492, "learning_rate": 2.994445230030177e-06, "loss": 4.2011, "step": 15660 }, { "epoch": 0.8427141627206199, "grad_norm": 2.193676233291626, "learning_rate": 2.992439948471959e-06, "loss": 3.5472, "step": 15661 }, { "epoch": 0.8427679724494188, "grad_norm": 1.9417222738265991, "learning_rate": 2.9904352958306124e-06, "loss": 3.6672, "step": 15662 }, { "epoch": 0.8428217821782178, "grad_norm": 2.355886220932007, "learning_rate": 2.988431272163428e-06, "loss": 4.3604, "step": 15663 }, { "epoch": 0.8428755919070168, "grad_norm": 1.6737604141235352, "learning_rate": 2.986427877527673e-06, "loss": 4.2255, "step": 15664 }, { "epoch": 0.8429294016358158, "grad_norm": 3.0286056995391846, "learning_rate": 2.984425111980599e-06, "loss": 4.1174, "step": 15665 }, { "epoch": 0.8429832113646147, "grad_norm": 1.6533515453338623, "learning_rate": 2.982422975579438e-06, "loss": 3.6931, "step": 15666 }, { "epoch": 0.8430370210934137, "grad_norm": 3.4533824920654297, "learning_rate": 2.980421468381411e-06, "loss": 4.229, "step": 15667 }, { "epoch": 0.8430908308222127, "grad_norm": 2.828151226043701, "learning_rate": 2.978420590443709e-06, "loss": 3.3594, "step": 15668 }, { "epoch": 0.8431446405510116, "grad_norm": 1.7779756784439087, "learning_rate": 2.976420341823519e-06, "loss": 4.3173, "step": 15669 }, { "epoch": 0.8431984502798106, "grad_norm": 3.2701802253723145, "learning_rate": 2.974420722578003e-06, "loss": 3.3787, "step": 15670 }, { "epoch": 0.8432522600086095, "grad_norm": 3.568376302719116, "learning_rate": 2.9724217327642966e-06, "loss": 3.9024, "step": 15671 }, { "epoch": 0.8433060697374085, "grad_norm": 3.6591899394989014, "learning_rate": 2.970423372439532e-06, "loss": 3.5893, "step": 15672 }, { "epoch": 0.8433598794662075, "grad_norm": 3.2310311794281006, "learning_rate": 2.9684256416608076e-06, "loss": 4.0739, "step": 15673 }, { "epoch": 0.8434136891950065, "grad_norm": 2.797107458114624, "learning_rate": 2.966428540485225e-06, "loss": 3.821, "step": 15674 }, { "epoch": 0.8434674989238055, "grad_norm": 1.4139927625656128, "learning_rate": 2.9644320689698525e-06, "loss": 4.4017, "step": 15675 }, { "epoch": 0.8435213086526044, "grad_norm": 2.0679707527160645, "learning_rate": 2.9624362271717415e-06, "loss": 4.1572, "step": 15676 }, { "epoch": 0.8435751183814033, "grad_norm": 2.5699687004089355, "learning_rate": 2.96044101514793e-06, "loss": 3.9505, "step": 15677 }, { "epoch": 0.8436289281102023, "grad_norm": 2.104917526245117, "learning_rate": 2.9584464329554335e-06, "loss": 3.6241, "step": 15678 }, { "epoch": 0.8436827378390013, "grad_norm": 2.0822150707244873, "learning_rate": 2.956452480651256e-06, "loss": 3.9604, "step": 15679 }, { "epoch": 0.8437365475678003, "grad_norm": 2.263887643814087, "learning_rate": 2.9544591582923747e-06, "loss": 3.0822, "step": 15680 }, { "epoch": 0.8437903572965992, "grad_norm": 2.174639940261841, "learning_rate": 2.952466465935755e-06, "loss": 4.3077, "step": 15681 }, { "epoch": 0.8438441670253982, "grad_norm": 1.337956428527832, "learning_rate": 2.9504744036383426e-06, "loss": 4.0182, "step": 15682 }, { "epoch": 0.8438979767541972, "grad_norm": 3.034821033477783, "learning_rate": 2.9484829714570615e-06, "loss": 3.2991, "step": 15683 }, { "epoch": 0.8439517864829962, "grad_norm": 3.296762704849243, "learning_rate": 2.946492169448828e-06, "loss": 3.9585, "step": 15684 }, { "epoch": 0.844005596211795, "grad_norm": 2.1035008430480957, "learning_rate": 2.9445019976705344e-06, "loss": 4.5431, "step": 15685 }, { "epoch": 0.844059405940594, "grad_norm": 3.210967540740967, "learning_rate": 2.9425124561790556e-06, "loss": 3.847, "step": 15686 }, { "epoch": 0.844113215669393, "grad_norm": 4.331427574157715, "learning_rate": 2.9405235450312375e-06, "loss": 4.2227, "step": 15687 }, { "epoch": 0.844167025398192, "grad_norm": 1.834534764289856, "learning_rate": 2.9385352642839177e-06, "loss": 4.1945, "step": 15688 }, { "epoch": 0.844220835126991, "grad_norm": 3.5727808475494385, "learning_rate": 2.9365476139939284e-06, "loss": 3.241, "step": 15689 }, { "epoch": 0.84427464485579, "grad_norm": 3.0072388648986816, "learning_rate": 2.9345605942180638e-06, "loss": 4.1083, "step": 15690 }, { "epoch": 0.8443284545845889, "grad_norm": 3.1082801818847656, "learning_rate": 2.9325742050131083e-06, "loss": 3.2538, "step": 15691 }, { "epoch": 0.8443822643133878, "grad_norm": 3.2119140625, "learning_rate": 2.930588446435828e-06, "loss": 3.2102, "step": 15692 }, { "epoch": 0.8444360740421868, "grad_norm": 1.4171847105026245, "learning_rate": 2.928603318542969e-06, "loss": 4.3865, "step": 15693 }, { "epoch": 0.8444898837709858, "grad_norm": 3.145660638809204, "learning_rate": 2.9266188213912636e-06, "loss": 3.2497, "step": 15694 }, { "epoch": 0.8445436934997848, "grad_norm": 2.551523447036743, "learning_rate": 2.9246349550374196e-06, "loss": 3.2036, "step": 15695 }, { "epoch": 0.8445975032285837, "grad_norm": 3.7435476779937744, "learning_rate": 2.922651719538136e-06, "loss": 4.0003, "step": 15696 }, { "epoch": 0.8446513129573827, "grad_norm": 3.0346732139587402, "learning_rate": 2.9206691149500836e-06, "loss": 3.0, "step": 15697 }, { "epoch": 0.8447051226861817, "grad_norm": 3.727074384689331, "learning_rate": 2.9186871413299205e-06, "loss": 3.7649, "step": 15698 }, { "epoch": 0.8447589324149807, "grad_norm": 4.428631782531738, "learning_rate": 2.9167057987342844e-06, "loss": 3.919, "step": 15699 }, { "epoch": 0.8448127421437795, "grad_norm": 2.275388240814209, "learning_rate": 2.9147250872198024e-06, "loss": 4.1813, "step": 15700 }, { "epoch": 0.8448665518725785, "grad_norm": 4.8298139572143555, "learning_rate": 2.9127450068430816e-06, "loss": 3.1909, "step": 15701 }, { "epoch": 0.8449203616013775, "grad_norm": 2.3335206508636475, "learning_rate": 2.910765557660694e-06, "loss": 3.7128, "step": 15702 }, { "epoch": 0.8449741713301765, "grad_norm": 2.372939348220825, "learning_rate": 2.9087867397292105e-06, "loss": 4.0144, "step": 15703 }, { "epoch": 0.8450279810589755, "grad_norm": 2.008565902709961, "learning_rate": 2.9068085531051865e-06, "loss": 3.9255, "step": 15704 }, { "epoch": 0.8450817907877745, "grad_norm": 1.586838960647583, "learning_rate": 2.904830997845151e-06, "loss": 4.0366, "step": 15705 }, { "epoch": 0.8451356005165734, "grad_norm": 3.7606985569000244, "learning_rate": 2.9028540740056178e-06, "loss": 4.2127, "step": 15706 }, { "epoch": 0.8451894102453723, "grad_norm": 2.7870116233825684, "learning_rate": 2.90087778164308e-06, "loss": 3.9494, "step": 15707 }, { "epoch": 0.8452432199741713, "grad_norm": 2.913891315460205, "learning_rate": 2.8989021208140147e-06, "loss": 3.655, "step": 15708 }, { "epoch": 0.8452970297029703, "grad_norm": 1.5106812715530396, "learning_rate": 2.8969270915748832e-06, "loss": 4.718, "step": 15709 }, { "epoch": 0.8453508394317693, "grad_norm": 2.3529210090637207, "learning_rate": 2.8949526939821254e-06, "loss": 4.2182, "step": 15710 }, { "epoch": 0.8454046491605682, "grad_norm": 2.636461019515991, "learning_rate": 2.892978928092163e-06, "loss": 3.9094, "step": 15711 }, { "epoch": 0.8454584588893672, "grad_norm": 2.80364727973938, "learning_rate": 2.8910057939614015e-06, "loss": 3.1738, "step": 15712 }, { "epoch": 0.8455122686181662, "grad_norm": 3.2410714626312256, "learning_rate": 2.889033291646229e-06, "loss": 4.1506, "step": 15713 }, { "epoch": 0.8455660783469652, "grad_norm": 2.3790829181671143, "learning_rate": 2.8870614212030105e-06, "loss": 4.1502, "step": 15714 }, { "epoch": 0.845619888075764, "grad_norm": 2.7972824573516846, "learning_rate": 2.8850901826881023e-06, "loss": 3.7263, "step": 15715 }, { "epoch": 0.845673697804563, "grad_norm": 4.334792613983154, "learning_rate": 2.883119576157839e-06, "loss": 4.2799, "step": 15716 }, { "epoch": 0.845727507533362, "grad_norm": 1.7998335361480713, "learning_rate": 2.8811496016685285e-06, "loss": 4.7233, "step": 15717 }, { "epoch": 0.845781317262161, "grad_norm": 3.037881851196289, "learning_rate": 2.8791802592764677e-06, "loss": 3.3401, "step": 15718 }, { "epoch": 0.84583512699096, "grad_norm": 3.6971986293792725, "learning_rate": 2.877211549037931e-06, "loss": 4.5474, "step": 15719 }, { "epoch": 0.845888936719759, "grad_norm": 2.5157952308654785, "learning_rate": 2.8752434710091923e-06, "loss": 4.2392, "step": 15720 }, { "epoch": 0.8459427464485579, "grad_norm": 3.053453207015991, "learning_rate": 2.873276025246485e-06, "loss": 3.9486, "step": 15721 }, { "epoch": 0.8459965561773569, "grad_norm": 1.927722454071045, "learning_rate": 2.8713092118060365e-06, "loss": 3.4407, "step": 15722 }, { "epoch": 0.8460503659061558, "grad_norm": 3.363053798675537, "learning_rate": 2.8693430307440484e-06, "loss": 3.6957, "step": 15723 }, { "epoch": 0.8461041756349548, "grad_norm": 1.561049461364746, "learning_rate": 2.867377482116715e-06, "loss": 4.1619, "step": 15724 }, { "epoch": 0.8461579853637538, "grad_norm": 2.987593650817871, "learning_rate": 2.865412565980202e-06, "loss": 4.0039, "step": 15725 }, { "epoch": 0.8462117950925527, "grad_norm": 2.2661187648773193, "learning_rate": 2.8634482823906656e-06, "loss": 3.3482, "step": 15726 }, { "epoch": 0.8462656048213517, "grad_norm": 2.769282102584839, "learning_rate": 2.861484631404232e-06, "loss": 3.9192, "step": 15727 }, { "epoch": 0.8463194145501507, "grad_norm": 4.412210464477539, "learning_rate": 2.8595216130770265e-06, "loss": 3.0509, "step": 15728 }, { "epoch": 0.8463732242789497, "grad_norm": 1.4253075122833252, "learning_rate": 2.8575592274651396e-06, "loss": 4.4345, "step": 15729 }, { "epoch": 0.8464270340077485, "grad_norm": 3.210754871368408, "learning_rate": 2.8555974746246493e-06, "loss": 3.2104, "step": 15730 }, { "epoch": 0.8464808437365475, "grad_norm": 2.4302592277526855, "learning_rate": 2.8536363546116328e-06, "loss": 4.0358, "step": 15731 }, { "epoch": 0.8465346534653465, "grad_norm": 2.6777799129486084, "learning_rate": 2.8516758674821176e-06, "loss": 3.6738, "step": 15732 }, { "epoch": 0.8465884631941455, "grad_norm": 2.0950920581817627, "learning_rate": 2.8497160132921336e-06, "loss": 4.1379, "step": 15733 }, { "epoch": 0.8466422729229445, "grad_norm": 3.4733951091766357, "learning_rate": 2.8477567920976833e-06, "loss": 3.746, "step": 15734 }, { "epoch": 0.8466960826517435, "grad_norm": 1.958088755607605, "learning_rate": 2.8457982039547665e-06, "loss": 3.2807, "step": 15735 }, { "epoch": 0.8467498923805424, "grad_norm": 1.5465039014816284, "learning_rate": 2.8438402489193493e-06, "loss": 3.7565, "step": 15736 }, { "epoch": 0.8468037021093414, "grad_norm": 3.934674024581909, "learning_rate": 2.8418829270473846e-06, "loss": 3.1635, "step": 15737 }, { "epoch": 0.8468575118381403, "grad_norm": 2.2512664794921875, "learning_rate": 2.8399262383948078e-06, "loss": 3.6654, "step": 15738 }, { "epoch": 0.8469113215669393, "grad_norm": 3.1012489795684814, "learning_rate": 2.8379701830175354e-06, "loss": 3.9664, "step": 15739 }, { "epoch": 0.8469651312957382, "grad_norm": 1.8059724569320679, "learning_rate": 2.836014760971467e-06, "loss": 3.7627, "step": 15740 }, { "epoch": 0.8470189410245372, "grad_norm": 3.310493230819702, "learning_rate": 2.8340599723124833e-06, "loss": 3.7644, "step": 15741 }, { "epoch": 0.8470727507533362, "grad_norm": 3.7133665084838867, "learning_rate": 2.8321058170964446e-06, "loss": 2.5079, "step": 15742 }, { "epoch": 0.8471265604821352, "grad_norm": 4.648776054382324, "learning_rate": 2.8301522953791958e-06, "loss": 3.746, "step": 15743 }, { "epoch": 0.8471803702109342, "grad_norm": 2.4212005138397217, "learning_rate": 2.828199407216567e-06, "loss": 3.6691, "step": 15744 }, { "epoch": 0.8472341799397332, "grad_norm": 2.7675070762634277, "learning_rate": 2.8262471526643577e-06, "loss": 3.2515, "step": 15745 }, { "epoch": 0.847287989668532, "grad_norm": 2.533013105392456, "learning_rate": 2.8242955317783705e-06, "loss": 4.2406, "step": 15746 }, { "epoch": 0.847341799397331, "grad_norm": 2.311300039291382, "learning_rate": 2.822344544614375e-06, "loss": 3.336, "step": 15747 }, { "epoch": 0.84739560912613, "grad_norm": 2.9273860454559326, "learning_rate": 2.8203941912281178e-06, "loss": 4.4477, "step": 15748 }, { "epoch": 0.847449418854929, "grad_norm": 2.683350086212158, "learning_rate": 2.818444471675338e-06, "loss": 4.1524, "step": 15749 }, { "epoch": 0.847503228583728, "grad_norm": 1.6953438520431519, "learning_rate": 2.816495386011747e-06, "loss": 3.6755, "step": 15750 }, { "epoch": 0.8475570383125269, "grad_norm": 2.314317464828491, "learning_rate": 2.814546934293058e-06, "loss": 3.5907, "step": 15751 }, { "epoch": 0.8476108480413259, "grad_norm": 1.2478395700454712, "learning_rate": 2.8125991165749462e-06, "loss": 4.615, "step": 15752 }, { "epoch": 0.8476646577701248, "grad_norm": 3.502568006515503, "learning_rate": 2.810651932913075e-06, "loss": 4.0527, "step": 15753 }, { "epoch": 0.8477184674989238, "grad_norm": 4.908882141113281, "learning_rate": 2.8087053833630917e-06, "loss": 3.4933, "step": 15754 }, { "epoch": 0.8477722772277227, "grad_norm": 1.757770299911499, "learning_rate": 2.806759467980613e-06, "loss": 3.872, "step": 15755 }, { "epoch": 0.8478260869565217, "grad_norm": 2.1299569606781006, "learning_rate": 2.8048141868212614e-06, "loss": 4.3606, "step": 15756 }, { "epoch": 0.8478798966853207, "grad_norm": 2.8347902297973633, "learning_rate": 2.8028695399406195e-06, "loss": 3.6043, "step": 15757 }, { "epoch": 0.8479337064141197, "grad_norm": 2.833583116531372, "learning_rate": 2.800925527394266e-06, "loss": 3.2905, "step": 15758 }, { "epoch": 0.8479875161429187, "grad_norm": 1.6506574153900146, "learning_rate": 2.79898214923775e-06, "loss": 4.3857, "step": 15759 }, { "epoch": 0.8480413258717177, "grad_norm": 2.235955238342285, "learning_rate": 2.7970394055266137e-06, "loss": 3.552, "step": 15760 }, { "epoch": 0.8480951356005165, "grad_norm": 3.0942070484161377, "learning_rate": 2.7950972963163622e-06, "loss": 3.8126, "step": 15761 }, { "epoch": 0.8481489453293155, "grad_norm": 3.261240005493164, "learning_rate": 2.7931558216625216e-06, "loss": 3.6063, "step": 15762 }, { "epoch": 0.8482027550581145, "grad_norm": 3.77956223487854, "learning_rate": 2.791214981620549e-06, "loss": 3.1099, "step": 15763 }, { "epoch": 0.8482565647869135, "grad_norm": 3.438380241394043, "learning_rate": 2.7892747762459175e-06, "loss": 3.2127, "step": 15764 }, { "epoch": 0.8483103745157125, "grad_norm": 2.7450783252716064, "learning_rate": 2.7873352055940717e-06, "loss": 3.6019, "step": 15765 }, { "epoch": 0.8483641842445114, "grad_norm": 3.1569223403930664, "learning_rate": 2.7853962697204417e-06, "loss": 3.2175, "step": 15766 }, { "epoch": 0.8484179939733104, "grad_norm": 2.596889019012451, "learning_rate": 2.783457968680439e-06, "loss": 3.3361, "step": 15767 }, { "epoch": 0.8484718037021094, "grad_norm": 3.3287816047668457, "learning_rate": 2.78152030252945e-06, "loss": 4.0457, "step": 15768 }, { "epoch": 0.8485256134309083, "grad_norm": 2.5948946475982666, "learning_rate": 2.7795832713228526e-06, "loss": 3.8371, "step": 15769 }, { "epoch": 0.8485794231597072, "grad_norm": 3.4939112663269043, "learning_rate": 2.7776468751159967e-06, "loss": 4.1945, "step": 15770 }, { "epoch": 0.8486332328885062, "grad_norm": 2.672516107559204, "learning_rate": 2.7757111139642216e-06, "loss": 3.7792, "step": 15771 }, { "epoch": 0.8486870426173052, "grad_norm": 3.66680645942688, "learning_rate": 2.77377598792285e-06, "loss": 4.0484, "step": 15772 }, { "epoch": 0.8487408523461042, "grad_norm": 1.806073784828186, "learning_rate": 2.771841497047176e-06, "loss": 4.3199, "step": 15773 }, { "epoch": 0.8487946620749032, "grad_norm": 2.7283577919006348, "learning_rate": 2.769907641392486e-06, "loss": 3.2851, "step": 15774 }, { "epoch": 0.8488484718037022, "grad_norm": 2.750905752182007, "learning_rate": 2.767974421014044e-06, "loss": 3.8433, "step": 15775 }, { "epoch": 0.848902281532501, "grad_norm": 4.5106072425842285, "learning_rate": 2.7660418359670923e-06, "loss": 3.0172, "step": 15776 }, { "epoch": 0.8489560912613, "grad_norm": 2.3605973720550537, "learning_rate": 2.7641098863068703e-06, "loss": 3.9795, "step": 15777 }, { "epoch": 0.849009900990099, "grad_norm": 2.1705758571624756, "learning_rate": 2.762178572088578e-06, "loss": 4.3408, "step": 15778 }, { "epoch": 0.849063710718898, "grad_norm": 2.4076595306396484, "learning_rate": 2.760247893367407e-06, "loss": 3.5502, "step": 15779 }, { "epoch": 0.849117520447697, "grad_norm": 1.660574197769165, "learning_rate": 2.7583178501985327e-06, "loss": 4.0209, "step": 15780 }, { "epoch": 0.8491713301764959, "grad_norm": 2.6358187198638916, "learning_rate": 2.7563884426371087e-06, "loss": 3.4882, "step": 15781 }, { "epoch": 0.8492251399052949, "grad_norm": 2.352917194366455, "learning_rate": 2.754459670738277e-06, "loss": 4.0716, "step": 15782 }, { "epoch": 0.8492789496340939, "grad_norm": 4.0408124923706055, "learning_rate": 2.752531534557157e-06, "loss": 4.2348, "step": 15783 }, { "epoch": 0.8493327593628928, "grad_norm": 1.1595031023025513, "learning_rate": 2.750604034148846e-06, "loss": 4.454, "step": 15784 }, { "epoch": 0.8493865690916917, "grad_norm": 3.1634228229522705, "learning_rate": 2.7486771695684338e-06, "loss": 3.4504, "step": 15785 }, { "epoch": 0.8494403788204907, "grad_norm": 2.272735595703125, "learning_rate": 2.746750940870968e-06, "loss": 3.8019, "step": 15786 }, { "epoch": 0.8494941885492897, "grad_norm": 2.4585275650024414, "learning_rate": 2.7448253481115098e-06, "loss": 4.006, "step": 15787 }, { "epoch": 0.8495479982780887, "grad_norm": 2.0625407695770264, "learning_rate": 2.7429003913450853e-06, "loss": 3.4386, "step": 15788 }, { "epoch": 0.8496018080068877, "grad_norm": 4.059527397155762, "learning_rate": 2.7409760706267022e-06, "loss": 3.2613, "step": 15789 }, { "epoch": 0.8496556177356867, "grad_norm": 2.0375592708587646, "learning_rate": 2.7390523860113537e-06, "loss": 4.1118, "step": 15790 }, { "epoch": 0.8497094274644856, "grad_norm": 2.2729594707489014, "learning_rate": 2.7371293375540146e-06, "loss": 4.3594, "step": 15791 }, { "epoch": 0.8497632371932845, "grad_norm": 2.3138771057128906, "learning_rate": 2.735206925309633e-06, "loss": 3.8166, "step": 15792 }, { "epoch": 0.8498170469220835, "grad_norm": 3.489459276199341, "learning_rate": 2.7332851493331617e-06, "loss": 4.0395, "step": 15793 }, { "epoch": 0.8498708566508825, "grad_norm": 3.612365484237671, "learning_rate": 2.7313640096795047e-06, "loss": 3.611, "step": 15794 }, { "epoch": 0.8499246663796814, "grad_norm": 3.2563393115997314, "learning_rate": 2.7294435064035703e-06, "loss": 3.3739, "step": 15795 }, { "epoch": 0.8499784761084804, "grad_norm": 1.5389670133590698, "learning_rate": 2.727523639560234e-06, "loss": 4.1845, "step": 15796 }, { "epoch": 0.8500322858372794, "grad_norm": 1.5325300693511963, "learning_rate": 2.7256044092043713e-06, "loss": 3.7039, "step": 15797 }, { "epoch": 0.8500860955660784, "grad_norm": 3.6641910076141357, "learning_rate": 2.7236858153908224e-06, "loss": 3.1056, "step": 15798 }, { "epoch": 0.8501399052948773, "grad_norm": 3.724139451980591, "learning_rate": 2.7217678581744176e-06, "loss": 3.7876, "step": 15799 }, { "epoch": 0.8501937150236762, "grad_norm": 2.7051568031311035, "learning_rate": 2.719850537609972e-06, "loss": 3.8397, "step": 15800 }, { "epoch": 0.8502475247524752, "grad_norm": 3.0195865631103516, "learning_rate": 2.7179338537522607e-06, "loss": 2.7267, "step": 15801 }, { "epoch": 0.8503013344812742, "grad_norm": 2.768247365951538, "learning_rate": 2.716017806656071e-06, "loss": 3.718, "step": 15802 }, { "epoch": 0.8503551442100732, "grad_norm": 1.8706519603729248, "learning_rate": 2.7141023963761586e-06, "loss": 3.3533, "step": 15803 }, { "epoch": 0.8504089539388722, "grad_norm": 2.465226888656616, "learning_rate": 2.712187622967255e-06, "loss": 3.3027, "step": 15804 }, { "epoch": 0.8504627636676712, "grad_norm": 3.9236061573028564, "learning_rate": 2.7102734864840856e-06, "loss": 3.489, "step": 15805 }, { "epoch": 0.8505165733964701, "grad_norm": 1.9129977226257324, "learning_rate": 2.7083599869813458e-06, "loss": 3.9577, "step": 15806 }, { "epoch": 0.850570383125269, "grad_norm": 4.508559226989746, "learning_rate": 2.706447124513714e-06, "loss": 3.8508, "step": 15807 }, { "epoch": 0.850624192854068, "grad_norm": 1.9749504327774048, "learning_rate": 2.7045348991358715e-06, "loss": 4.0472, "step": 15808 }, { "epoch": 0.850678002582867, "grad_norm": 1.738258719444275, "learning_rate": 2.7026233109024495e-06, "loss": 4.0312, "step": 15809 }, { "epoch": 0.850731812311666, "grad_norm": 3.160100221633911, "learning_rate": 2.7007123598680795e-06, "loss": 3.8232, "step": 15810 }, { "epoch": 0.8507856220404649, "grad_norm": 2.8736443519592285, "learning_rate": 2.698802046087373e-06, "loss": 3.5452, "step": 15811 }, { "epoch": 0.8508394317692639, "grad_norm": 2.6972365379333496, "learning_rate": 2.6968923696149147e-06, "loss": 3.8157, "step": 15812 }, { "epoch": 0.8508932414980629, "grad_norm": 2.3552615642547607, "learning_rate": 2.6949833305052906e-06, "loss": 3.5641, "step": 15813 }, { "epoch": 0.8509470512268618, "grad_norm": 1.9831063747406006, "learning_rate": 2.693074928813047e-06, "loss": 4.4631, "step": 15814 }, { "epoch": 0.8510008609556607, "grad_norm": 2.9289093017578125, "learning_rate": 2.6911671645927313e-06, "loss": 4.1143, "step": 15815 }, { "epoch": 0.8510546706844597, "grad_norm": 3.036679983139038, "learning_rate": 2.689260037898847e-06, "loss": 4.1412, "step": 15816 }, { "epoch": 0.8511084804132587, "grad_norm": 2.750875234603882, "learning_rate": 2.687353548785898e-06, "loss": 3.5252, "step": 15817 }, { "epoch": 0.8511622901420577, "grad_norm": 1.3606220483779907, "learning_rate": 2.685447697308377e-06, "loss": 4.4442, "step": 15818 }, { "epoch": 0.8512160998708567, "grad_norm": 3.05671763420105, "learning_rate": 2.68354248352074e-06, "loss": 3.5175, "step": 15819 }, { "epoch": 0.8512699095996556, "grad_norm": 3.610250234603882, "learning_rate": 2.6816379074774355e-06, "loss": 4.0086, "step": 15820 }, { "epoch": 0.8513237193284546, "grad_norm": 3.236138105392456, "learning_rate": 2.6797339692328894e-06, "loss": 4.1911, "step": 15821 }, { "epoch": 0.8513775290572535, "grad_norm": 3.0558547973632812, "learning_rate": 2.6778306688415106e-06, "loss": 4.5032, "step": 15822 }, { "epoch": 0.8514313387860525, "grad_norm": 1.8056048154830933, "learning_rate": 2.6759280063576946e-06, "loss": 4.3828, "step": 15823 }, { "epoch": 0.8514851485148515, "grad_norm": 1.471354365348816, "learning_rate": 2.674025981835809e-06, "loss": 4.2981, "step": 15824 }, { "epoch": 0.8515389582436504, "grad_norm": 3.3423731327056885, "learning_rate": 2.672124595330214e-06, "loss": 3.3655, "step": 15825 }, { "epoch": 0.8515927679724494, "grad_norm": 3.0369820594787598, "learning_rate": 2.6702238468952395e-06, "loss": 2.9666, "step": 15826 }, { "epoch": 0.8516465777012484, "grad_norm": 3.5174520015716553, "learning_rate": 2.668323736585204e-06, "loss": 3.4691, "step": 15827 }, { "epoch": 0.8517003874300474, "grad_norm": 4.5365753173828125, "learning_rate": 2.6664242644544174e-06, "loss": 2.8446, "step": 15828 }, { "epoch": 0.8517541971588464, "grad_norm": 2.9881680011749268, "learning_rate": 2.6645254305571548e-06, "loss": 3.4527, "step": 15829 }, { "epoch": 0.8518080068876452, "grad_norm": 3.763340711593628, "learning_rate": 2.6626272349476787e-06, "loss": 3.8522, "step": 15830 }, { "epoch": 0.8518618166164442, "grad_norm": 4.7897539138793945, "learning_rate": 2.6607296776802405e-06, "loss": 4.0281, "step": 15831 }, { "epoch": 0.8519156263452432, "grad_norm": 3.206862688064575, "learning_rate": 2.6588327588090544e-06, "loss": 3.6493, "step": 15832 }, { "epoch": 0.8519694360740422, "grad_norm": 2.0325021743774414, "learning_rate": 2.6569364783883416e-06, "loss": 3.8321, "step": 15833 }, { "epoch": 0.8520232458028412, "grad_norm": 2.0719053745269775, "learning_rate": 2.655040836472286e-06, "loss": 4.1012, "step": 15834 }, { "epoch": 0.8520770555316401, "grad_norm": 2.444178819656372, "learning_rate": 2.653145833115067e-06, "loss": 4.1598, "step": 15835 }, { "epoch": 0.8521308652604391, "grad_norm": 1.6910165548324585, "learning_rate": 2.6512514683708302e-06, "loss": 3.9079, "step": 15836 }, { "epoch": 0.852184674989238, "grad_norm": 2.1515092849731445, "learning_rate": 2.649357742293718e-06, "loss": 4.2939, "step": 15837 }, { "epoch": 0.852238484718037, "grad_norm": 1.2970281839370728, "learning_rate": 2.6474646549378425e-06, "loss": 4.5183, "step": 15838 }, { "epoch": 0.852292294446836, "grad_norm": 3.4411768913269043, "learning_rate": 2.645572206357308e-06, "loss": 3.2962, "step": 15839 }, { "epoch": 0.8523461041756349, "grad_norm": 2.891904830932617, "learning_rate": 2.6436803966061933e-06, "loss": 4.0081, "step": 15840 }, { "epoch": 0.8523999139044339, "grad_norm": 1.8725316524505615, "learning_rate": 2.641789225738561e-06, "loss": 4.0877, "step": 15841 }, { "epoch": 0.8524537236332329, "grad_norm": 2.5359299182891846, "learning_rate": 2.639898693808457e-06, "loss": 4.0933, "step": 15842 }, { "epoch": 0.8525075333620319, "grad_norm": 2.099820852279663, "learning_rate": 2.6380088008699013e-06, "loss": 4.1309, "step": 15843 }, { "epoch": 0.8525613430908309, "grad_norm": 2.391650438308716, "learning_rate": 2.636119546976912e-06, "loss": 3.5675, "step": 15844 }, { "epoch": 0.8526151528196297, "grad_norm": 2.8913118839263916, "learning_rate": 2.6342309321834734e-06, "loss": 3.5144, "step": 15845 }, { "epoch": 0.8526689625484287, "grad_norm": 2.4775583744049072, "learning_rate": 2.6323429565435653e-06, "loss": 3.4773, "step": 15846 }, { "epoch": 0.8527227722772277, "grad_norm": 2.8118960857391357, "learning_rate": 2.630455620111125e-06, "loss": 3.3959, "step": 15847 }, { "epoch": 0.8527765820060267, "grad_norm": 3.882405996322632, "learning_rate": 2.6285689229400946e-06, "loss": 3.3629, "step": 15848 }, { "epoch": 0.8528303917348257, "grad_norm": 2.1555888652801514, "learning_rate": 2.6266828650843956e-06, "loss": 3.4398, "step": 15849 }, { "epoch": 0.8528842014636246, "grad_norm": 2.499920129776001, "learning_rate": 2.6247974465979236e-06, "loss": 4.8327, "step": 15850 }, { "epoch": 0.8529380111924236, "grad_norm": 2.096097707748413, "learning_rate": 2.6229126675345576e-06, "loss": 4.3267, "step": 15851 }, { "epoch": 0.8529918209212226, "grad_norm": 2.5902042388916016, "learning_rate": 2.6210285279481604e-06, "loss": 3.557, "step": 15852 }, { "epoch": 0.8530456306500215, "grad_norm": 2.5999770164489746, "learning_rate": 2.619145027892578e-06, "loss": 3.5654, "step": 15853 }, { "epoch": 0.8530994403788205, "grad_norm": 3.3760061264038086, "learning_rate": 2.61726216742163e-06, "loss": 3.6338, "step": 15854 }, { "epoch": 0.8531532501076194, "grad_norm": 1.9641402959823608, "learning_rate": 2.615379946589128e-06, "loss": 4.3751, "step": 15855 }, { "epoch": 0.8532070598364184, "grad_norm": 4.260737419128418, "learning_rate": 2.6134983654488605e-06, "loss": 3.6111, "step": 15856 }, { "epoch": 0.8532608695652174, "grad_norm": 2.608962059020996, "learning_rate": 2.6116174240545966e-06, "loss": 3.8538, "step": 15857 }, { "epoch": 0.8533146792940164, "grad_norm": 4.092266082763672, "learning_rate": 2.609737122460082e-06, "loss": 3.1897, "step": 15858 }, { "epoch": 0.8533684890228154, "grad_norm": 2.183053970336914, "learning_rate": 2.6078574607190652e-06, "loss": 3.5275, "step": 15859 }, { "epoch": 0.8534222987516142, "grad_norm": 2.134587049484253, "learning_rate": 2.6059784388852537e-06, "loss": 4.0892, "step": 15860 }, { "epoch": 0.8534761084804132, "grad_norm": 2.106419324874878, "learning_rate": 2.6041000570123488e-06, "loss": 3.7579, "step": 15861 }, { "epoch": 0.8535299182092122, "grad_norm": 2.202552080154419, "learning_rate": 2.6022223151540236e-06, "loss": 4.0943, "step": 15862 }, { "epoch": 0.8535837279380112, "grad_norm": 2.0619964599609375, "learning_rate": 2.600345213363936e-06, "loss": 3.8113, "step": 15863 }, { "epoch": 0.8536375376668102, "grad_norm": 2.630436658859253, "learning_rate": 2.59846875169574e-06, "loss": 3.5186, "step": 15864 }, { "epoch": 0.8536913473956091, "grad_norm": 4.478359699249268, "learning_rate": 2.596592930203054e-06, "loss": 3.4066, "step": 15865 }, { "epoch": 0.8537451571244081, "grad_norm": 2.5576112270355225, "learning_rate": 2.594717748939482e-06, "loss": 3.4045, "step": 15866 }, { "epoch": 0.8537989668532071, "grad_norm": 5.9064130783081055, "learning_rate": 2.5928432079586144e-06, "loss": 4.4748, "step": 15867 }, { "epoch": 0.853852776582006, "grad_norm": 1.5363019704818726, "learning_rate": 2.59096930731402e-06, "loss": 4.3687, "step": 15868 }, { "epoch": 0.853906586310805, "grad_norm": 2.3073606491088867, "learning_rate": 2.58909604705925e-06, "loss": 4.3375, "step": 15869 }, { "epoch": 0.8539603960396039, "grad_norm": 3.372072696685791, "learning_rate": 2.5872234272478367e-06, "loss": 3.235, "step": 15870 }, { "epoch": 0.8540142057684029, "grad_norm": 2.3225207328796387, "learning_rate": 2.5853514479332956e-06, "loss": 3.8618, "step": 15871 }, { "epoch": 0.8540680154972019, "grad_norm": 3.303581953048706, "learning_rate": 2.5834801091691204e-06, "loss": 3.9026, "step": 15872 }, { "epoch": 0.8541218252260009, "grad_norm": 3.228151798248291, "learning_rate": 2.5816094110087896e-06, "loss": 2.7924, "step": 15873 }, { "epoch": 0.8541756349547999, "grad_norm": 3.6027748584747314, "learning_rate": 2.5797393535057612e-06, "loss": 3.9162, "step": 15874 }, { "epoch": 0.8542294446835988, "grad_norm": 3.9614245891571045, "learning_rate": 2.5778699367134814e-06, "loss": 3.5361, "step": 15875 }, { "epoch": 0.8542832544123977, "grad_norm": 2.010899305343628, "learning_rate": 2.5760011606853707e-06, "loss": 4.1521, "step": 15876 }, { "epoch": 0.8543370641411967, "grad_norm": 1.3887033462524414, "learning_rate": 2.574133025474837e-06, "loss": 3.6915, "step": 15877 }, { "epoch": 0.8543908738699957, "grad_norm": 1.7995171546936035, "learning_rate": 2.5722655311352537e-06, "loss": 4.1132, "step": 15878 }, { "epoch": 0.8544446835987947, "grad_norm": 2.9895596504211426, "learning_rate": 2.570398677720004e-06, "loss": 3.2896, "step": 15879 }, { "epoch": 0.8544984933275936, "grad_norm": 1.6632983684539795, "learning_rate": 2.5685324652824334e-06, "loss": 3.3408, "step": 15880 }, { "epoch": 0.8545523030563926, "grad_norm": 2.5659708976745605, "learning_rate": 2.5666668938758685e-06, "loss": 3.627, "step": 15881 }, { "epoch": 0.8546061127851916, "grad_norm": 3.875750780105591, "learning_rate": 2.564801963553626e-06, "loss": 4.1412, "step": 15882 }, { "epoch": 0.8546599225139905, "grad_norm": 2.5977375507354736, "learning_rate": 2.562937674368998e-06, "loss": 3.4355, "step": 15883 }, { "epoch": 0.8547137322427895, "grad_norm": 2.2191784381866455, "learning_rate": 2.561074026375265e-06, "loss": 4.3387, "step": 15884 }, { "epoch": 0.8547675419715884, "grad_norm": 2.3528006076812744, "learning_rate": 2.559211019625682e-06, "loss": 4.6946, "step": 15885 }, { "epoch": 0.8548213517003874, "grad_norm": 3.9771459102630615, "learning_rate": 2.5573486541734886e-06, "loss": 4.3747, "step": 15886 }, { "epoch": 0.8548751614291864, "grad_norm": 1.8139334917068481, "learning_rate": 2.55548693007191e-06, "loss": 3.9306, "step": 15887 }, { "epoch": 0.8549289711579854, "grad_norm": 3.0078678131103516, "learning_rate": 2.553625847374144e-06, "loss": 4.0762, "step": 15888 }, { "epoch": 0.8549827808867844, "grad_norm": 4.246279239654541, "learning_rate": 2.5517654061333716e-06, "loss": 3.7096, "step": 15889 }, { "epoch": 0.8550365906155833, "grad_norm": 1.810964822769165, "learning_rate": 2.549905606402772e-06, "loss": 4.048, "step": 15890 }, { "epoch": 0.8550904003443822, "grad_norm": 4.476691246032715, "learning_rate": 2.548046448235486e-06, "loss": 3.3861, "step": 15891 }, { "epoch": 0.8551442100731812, "grad_norm": 2.636727809906006, "learning_rate": 2.546187931684649e-06, "loss": 2.7689, "step": 15892 }, { "epoch": 0.8551980198019802, "grad_norm": 2.3863794803619385, "learning_rate": 2.544330056803362e-06, "loss": 4.0033, "step": 15893 }, { "epoch": 0.8552518295307792, "grad_norm": 2.153635025024414, "learning_rate": 2.5424728236447174e-06, "loss": 4.3038, "step": 15894 }, { "epoch": 0.8553056392595781, "grad_norm": 3.4261744022369385, "learning_rate": 2.5406162322618025e-06, "loss": 3.8991, "step": 15895 }, { "epoch": 0.8553594489883771, "grad_norm": 2.163604736328125, "learning_rate": 2.5387602827076667e-06, "loss": 2.9077, "step": 15896 }, { "epoch": 0.8554132587171761, "grad_norm": 2.6004157066345215, "learning_rate": 2.536904975035348e-06, "loss": 4.1931, "step": 15897 }, { "epoch": 0.8554670684459751, "grad_norm": 1.0809539556503296, "learning_rate": 2.5350503092978652e-06, "loss": 3.8966, "step": 15898 }, { "epoch": 0.855520878174774, "grad_norm": 4.290594577789307, "learning_rate": 2.5331962855482227e-06, "loss": 3.6533, "step": 15899 }, { "epoch": 0.8555746879035729, "grad_norm": 1.5701075792312622, "learning_rate": 2.531342903839401e-06, "loss": 4.5249, "step": 15900 }, { "epoch": 0.8556284976323719, "grad_norm": 2.818253755569458, "learning_rate": 2.529490164224366e-06, "loss": 4.0279, "step": 15901 }, { "epoch": 0.8556823073611709, "grad_norm": 3.842268466949463, "learning_rate": 2.5276380667560633e-06, "loss": 4.1358, "step": 15902 }, { "epoch": 0.8557361170899699, "grad_norm": 1.6911625862121582, "learning_rate": 2.525786611487421e-06, "loss": 4.3861, "step": 15903 }, { "epoch": 0.8557899268187689, "grad_norm": 3.0245838165283203, "learning_rate": 2.52393579847135e-06, "loss": 2.5176, "step": 15904 }, { "epoch": 0.8558437365475678, "grad_norm": 3.2559447288513184, "learning_rate": 2.5220856277607343e-06, "loss": 3.8935, "step": 15905 }, { "epoch": 0.8558975462763667, "grad_norm": 1.7307379245758057, "learning_rate": 2.5202360994084573e-06, "loss": 4.1956, "step": 15906 }, { "epoch": 0.8559513560051657, "grad_norm": 2.2446422576904297, "learning_rate": 2.518387213467374e-06, "loss": 4.2171, "step": 15907 }, { "epoch": 0.8560051657339647, "grad_norm": 3.9063618183135986, "learning_rate": 2.5165389699903117e-06, "loss": 3.727, "step": 15908 }, { "epoch": 0.8560589754627637, "grad_norm": 4.002928256988525, "learning_rate": 2.5146913690300868e-06, "loss": 3.0672, "step": 15909 }, { "epoch": 0.8561127851915626, "grad_norm": 3.2200515270233154, "learning_rate": 2.512844410639509e-06, "loss": 3.7618, "step": 15910 }, { "epoch": 0.8561665949203616, "grad_norm": 3.3169054985046387, "learning_rate": 2.5109980948713558e-06, "loss": 4.6616, "step": 15911 }, { "epoch": 0.8562204046491606, "grad_norm": 2.9792587757110596, "learning_rate": 2.509152421778388e-06, "loss": 3.5493, "step": 15912 }, { "epoch": 0.8562742143779596, "grad_norm": 3.488245725631714, "learning_rate": 2.5073073914133495e-06, "loss": 3.6971, "step": 15913 }, { "epoch": 0.8563280241067585, "grad_norm": 2.2691001892089844, "learning_rate": 2.50546300382897e-06, "loss": 3.9802, "step": 15914 }, { "epoch": 0.8563818338355574, "grad_norm": 4.217804908752441, "learning_rate": 2.503619259077952e-06, "loss": 3.8575, "step": 15915 }, { "epoch": 0.8564356435643564, "grad_norm": 4.72660493850708, "learning_rate": 2.50177615721299e-06, "loss": 3.4757, "step": 15916 }, { "epoch": 0.8564894532931554, "grad_norm": 2.8037657737731934, "learning_rate": 2.4999336982867495e-06, "loss": 3.8378, "step": 15917 }, { "epoch": 0.8565432630219544, "grad_norm": 4.070857048034668, "learning_rate": 2.4980918823518882e-06, "loss": 3.3058, "step": 15918 }, { "epoch": 0.8565970727507534, "grad_norm": 2.2418856620788574, "learning_rate": 2.496250709461037e-06, "loss": 3.9186, "step": 15919 }, { "epoch": 0.8566508824795523, "grad_norm": 2.704888343811035, "learning_rate": 2.494410179666809e-06, "loss": 3.6521, "step": 15920 }, { "epoch": 0.8567046922083512, "grad_norm": 2.9548604488372803, "learning_rate": 2.4925702930218066e-06, "loss": 3.5245, "step": 15921 }, { "epoch": 0.8567585019371502, "grad_norm": 2.8623545169830322, "learning_rate": 2.490731049578615e-06, "loss": 2.6925, "step": 15922 }, { "epoch": 0.8568123116659492, "grad_norm": 3.421051502227783, "learning_rate": 2.488892449389782e-06, "loss": 3.4795, "step": 15923 }, { "epoch": 0.8568661213947482, "grad_norm": 2.706963300704956, "learning_rate": 2.487054492507854e-06, "loss": 3.8288, "step": 15924 }, { "epoch": 0.8569199311235471, "grad_norm": 3.650289535522461, "learning_rate": 2.4852171789853524e-06, "loss": 3.0131, "step": 15925 }, { "epoch": 0.8569737408523461, "grad_norm": 3.3940465450286865, "learning_rate": 2.4833805088747913e-06, "loss": 3.6301, "step": 15926 }, { "epoch": 0.8570275505811451, "grad_norm": 2.7000510692596436, "learning_rate": 2.481544482228651e-06, "loss": 4.2845, "step": 15927 }, { "epoch": 0.8570813603099441, "grad_norm": 2.1681034564971924, "learning_rate": 2.4797090990994034e-06, "loss": 4.0664, "step": 15928 }, { "epoch": 0.857135170038743, "grad_norm": 2.34696102142334, "learning_rate": 2.477874359539495e-06, "loss": 3.8347, "step": 15929 }, { "epoch": 0.8571889797675419, "grad_norm": 1.7392319440841675, "learning_rate": 2.4760402636013618e-06, "loss": 4.1171, "step": 15930 }, { "epoch": 0.8572427894963409, "grad_norm": 3.45389986038208, "learning_rate": 2.474206811337415e-06, "loss": 3.1234, "step": 15931 }, { "epoch": 0.8572965992251399, "grad_norm": 1.5193878412246704, "learning_rate": 2.4723740028000516e-06, "loss": 4.2396, "step": 15932 }, { "epoch": 0.8573504089539389, "grad_norm": 3.4401426315307617, "learning_rate": 2.4705418380416455e-06, "loss": 3.5992, "step": 15933 }, { "epoch": 0.8574042186827379, "grad_norm": 3.066471815109253, "learning_rate": 2.468710317114556e-06, "loss": 3.5383, "step": 15934 }, { "epoch": 0.8574580284115368, "grad_norm": 3.2389070987701416, "learning_rate": 2.4668794400711237e-06, "loss": 3.3785, "step": 15935 }, { "epoch": 0.8575118381403358, "grad_norm": 2.319072961807251, "learning_rate": 2.4650492069636657e-06, "loss": 4.5626, "step": 15936 }, { "epoch": 0.8575656478691347, "grad_norm": 1.5584057569503784, "learning_rate": 2.463219617844495e-06, "loss": 4.2274, "step": 15937 }, { "epoch": 0.8576194575979337, "grad_norm": 2.542506217956543, "learning_rate": 2.461390672765895e-06, "loss": 3.4145, "step": 15938 }, { "epoch": 0.8576732673267327, "grad_norm": 3.5659584999084473, "learning_rate": 2.4595623717801247e-06, "loss": 3.4718, "step": 15939 }, { "epoch": 0.8577270770555316, "grad_norm": 3.7728664875030518, "learning_rate": 2.4577347149394274e-06, "loss": 3.4394, "step": 15940 }, { "epoch": 0.8577808867843306, "grad_norm": 4.23232889175415, "learning_rate": 2.455907702296048e-06, "loss": 4.1708, "step": 15941 }, { "epoch": 0.8578346965131296, "grad_norm": 3.8449885845184326, "learning_rate": 2.454081333902186e-06, "loss": 3.2072, "step": 15942 }, { "epoch": 0.8578885062419286, "grad_norm": 1.3564871549606323, "learning_rate": 2.4522556098100418e-06, "loss": 3.6978, "step": 15943 }, { "epoch": 0.8579423159707275, "grad_norm": 3.44100022315979, "learning_rate": 2.4504305300717846e-06, "loss": 3.422, "step": 15944 }, { "epoch": 0.8579961256995264, "grad_norm": 4.242687702178955, "learning_rate": 2.4486060947395724e-06, "loss": 3.8356, "step": 15945 }, { "epoch": 0.8580499354283254, "grad_norm": 3.4058303833007812, "learning_rate": 2.4467823038655413e-06, "loss": 3.4442, "step": 15946 }, { "epoch": 0.8581037451571244, "grad_norm": 1.967463731765747, "learning_rate": 2.444959157501811e-06, "loss": 3.6356, "step": 15947 }, { "epoch": 0.8581575548859234, "grad_norm": 4.0904107093811035, "learning_rate": 2.4431366557004815e-06, "loss": 3.5049, "step": 15948 }, { "epoch": 0.8582113646147224, "grad_norm": 3.979508638381958, "learning_rate": 2.441314798513636e-06, "loss": 2.7627, "step": 15949 }, { "epoch": 0.8582651743435213, "grad_norm": 2.8001723289489746, "learning_rate": 2.439493585993338e-06, "loss": 3.3859, "step": 15950 }, { "epoch": 0.8583189840723203, "grad_norm": 1.7643003463745117, "learning_rate": 2.4376730181916274e-06, "loss": 3.6432, "step": 15951 }, { "epoch": 0.8583727938011192, "grad_norm": 6.0150299072265625, "learning_rate": 2.4358530951605424e-06, "loss": 4.0433, "step": 15952 }, { "epoch": 0.8584266035299182, "grad_norm": 2.9473443031311035, "learning_rate": 2.434033816952089e-06, "loss": 4.0623, "step": 15953 }, { "epoch": 0.8584804132587172, "grad_norm": 1.713468074798584, "learning_rate": 2.43221518361825e-06, "loss": 4.4259, "step": 15954 }, { "epoch": 0.8585342229875161, "grad_norm": 4.660099506378174, "learning_rate": 2.430397195211001e-06, "loss": 3.7303, "step": 15955 }, { "epoch": 0.8585880327163151, "grad_norm": 4.55757999420166, "learning_rate": 2.4285798517822893e-06, "loss": 2.1819, "step": 15956 }, { "epoch": 0.8586418424451141, "grad_norm": 2.826477289199829, "learning_rate": 2.4267631533840594e-06, "loss": 3.9886, "step": 15957 }, { "epoch": 0.8586956521739131, "grad_norm": 2.021723508834839, "learning_rate": 2.4249471000682256e-06, "loss": 4.075, "step": 15958 }, { "epoch": 0.8587494619027121, "grad_norm": 2.993572950363159, "learning_rate": 2.423131691886682e-06, "loss": 3.4719, "step": 15959 }, { "epoch": 0.8588032716315109, "grad_norm": 1.7088298797607422, "learning_rate": 2.4213169288913124e-06, "loss": 3.9354, "step": 15960 }, { "epoch": 0.8588570813603099, "grad_norm": 4.931737899780273, "learning_rate": 2.4195028111339722e-06, "loss": 3.7622, "step": 15961 }, { "epoch": 0.8589108910891089, "grad_norm": 2.9211301803588867, "learning_rate": 2.4176893386665093e-06, "loss": 3.6341, "step": 15962 }, { "epoch": 0.8589647008179079, "grad_norm": 3.6008853912353516, "learning_rate": 2.4158765115407463e-06, "loss": 3.4124, "step": 15963 }, { "epoch": 0.8590185105467069, "grad_norm": 3.589435577392578, "learning_rate": 2.4140643298084883e-06, "loss": 4.0942, "step": 15964 }, { "epoch": 0.8590723202755058, "grad_norm": 2.1754915714263916, "learning_rate": 2.4122527935215215e-06, "loss": 2.8395, "step": 15965 }, { "epoch": 0.8591261300043048, "grad_norm": 2.581273078918457, "learning_rate": 2.410441902731619e-06, "loss": 3.9507, "step": 15966 }, { "epoch": 0.8591799397331037, "grad_norm": 2.9040048122406006, "learning_rate": 2.4086316574905202e-06, "loss": 3.9297, "step": 15967 }, { "epoch": 0.8592337494619027, "grad_norm": 2.4776275157928467, "learning_rate": 2.406822057849975e-06, "loss": 3.9797, "step": 15968 }, { "epoch": 0.8592875591907017, "grad_norm": 1.4747596979141235, "learning_rate": 2.4050131038616837e-06, "loss": 3.9576, "step": 15969 }, { "epoch": 0.8593413689195006, "grad_norm": 2.984614610671997, "learning_rate": 2.4032047955773434e-06, "loss": 4.2485, "step": 15970 }, { "epoch": 0.8593951786482996, "grad_norm": 3.073883295059204, "learning_rate": 2.4013971330486274e-06, "loss": 3.8897, "step": 15971 }, { "epoch": 0.8594489883770986, "grad_norm": 2.715993881225586, "learning_rate": 2.399590116327202e-06, "loss": 3.1926, "step": 15972 }, { "epoch": 0.8595027981058976, "grad_norm": 2.264807939529419, "learning_rate": 2.3977837454647047e-06, "loss": 4.3241, "step": 15973 }, { "epoch": 0.8595566078346966, "grad_norm": 1.2809343338012695, "learning_rate": 2.3959780205127543e-06, "loss": 4.7535, "step": 15974 }, { "epoch": 0.8596104175634954, "grad_norm": 1.8208894729614258, "learning_rate": 2.394172941522954e-06, "loss": 4.0828, "step": 15975 }, { "epoch": 0.8596642272922944, "grad_norm": 3.1919209957122803, "learning_rate": 2.3923685085468884e-06, "loss": 3.8668, "step": 15976 }, { "epoch": 0.8597180370210934, "grad_norm": 2.3052778244018555, "learning_rate": 2.3905647216361237e-06, "loss": 3.9641, "step": 15977 }, { "epoch": 0.8597718467498924, "grad_norm": 3.148057222366333, "learning_rate": 2.388761580842205e-06, "loss": 2.4682, "step": 15978 }, { "epoch": 0.8598256564786914, "grad_norm": 2.598341703414917, "learning_rate": 2.386959086216667e-06, "loss": 3.4335, "step": 15979 }, { "epoch": 0.8598794662074903, "grad_norm": 2.871577024459839, "learning_rate": 2.3851572378110144e-06, "loss": 3.8875, "step": 15980 }, { "epoch": 0.8599332759362893, "grad_norm": 3.6144254207611084, "learning_rate": 2.3833560356767427e-06, "loss": 4.4155, "step": 15981 }, { "epoch": 0.8599870856650883, "grad_norm": 1.7097549438476562, "learning_rate": 2.3815554798653163e-06, "loss": 4.0517, "step": 15982 }, { "epoch": 0.8600408953938872, "grad_norm": 2.6861040592193604, "learning_rate": 2.379755570428205e-06, "loss": 3.2575, "step": 15983 }, { "epoch": 0.8600947051226862, "grad_norm": 1.6461880207061768, "learning_rate": 2.3779563074168426e-06, "loss": 3.6251, "step": 15984 }, { "epoch": 0.8601485148514851, "grad_norm": 2.498377561569214, "learning_rate": 2.3761576908826357e-06, "loss": 3.4, "step": 15985 }, { "epoch": 0.8602023245802841, "grad_norm": 2.46751070022583, "learning_rate": 2.374359720876995e-06, "loss": 3.5595, "step": 15986 }, { "epoch": 0.8602561343090831, "grad_norm": 1.7508882284164429, "learning_rate": 2.372562397451289e-06, "loss": 3.9606, "step": 15987 }, { "epoch": 0.8603099440378821, "grad_norm": 3.9884164333343506, "learning_rate": 2.370765720656895e-06, "loss": 3.8844, "step": 15988 }, { "epoch": 0.8603637537666811, "grad_norm": 2.8247742652893066, "learning_rate": 2.368969690545153e-06, "loss": 3.3163, "step": 15989 }, { "epoch": 0.8604175634954799, "grad_norm": 2.898862838745117, "learning_rate": 2.3671743071673856e-06, "loss": 3.4797, "step": 15990 }, { "epoch": 0.8604713732242789, "grad_norm": 2.5304086208343506, "learning_rate": 2.365379570574905e-06, "loss": 4.1903, "step": 15991 }, { "epoch": 0.8605251829530779, "grad_norm": 3.8831632137298584, "learning_rate": 2.363585480818989e-06, "loss": 2.8209, "step": 15992 }, { "epoch": 0.8605789926818769, "grad_norm": 3.463047504425049, "learning_rate": 2.361792037950919e-06, "loss": 3.8567, "step": 15993 }, { "epoch": 0.8606328024106759, "grad_norm": 2.2083661556243896, "learning_rate": 2.359999242021943e-06, "loss": 3.805, "step": 15994 }, { "epoch": 0.8606866121394748, "grad_norm": 3.8660340309143066, "learning_rate": 2.358207093083295e-06, "loss": 3.0564, "step": 15995 }, { "epoch": 0.8607404218682738, "grad_norm": 2.308455467224121, "learning_rate": 2.3564155911861867e-06, "loss": 4.3689, "step": 15996 }, { "epoch": 0.8607942315970728, "grad_norm": 2.8336901664733887, "learning_rate": 2.354624736381819e-06, "loss": 3.382, "step": 15997 }, { "epoch": 0.8608480413258717, "grad_norm": 3.742502212524414, "learning_rate": 2.352834528721362e-06, "loss": 3.7742, "step": 15998 }, { "epoch": 0.8609018510546707, "grad_norm": 2.8137176036834717, "learning_rate": 2.3510449682559887e-06, "loss": 3.7001, "step": 15999 }, { "epoch": 0.8609556607834696, "grad_norm": 2.1697514057159424, "learning_rate": 2.3492560550368273e-06, "loss": 4.1437, "step": 16000 }, { "epoch": 0.8610094705122686, "grad_norm": 3.4096322059631348, "learning_rate": 2.347467789115004e-06, "loss": 3.9076, "step": 16001 }, { "epoch": 0.8610632802410676, "grad_norm": 2.10662841796875, "learning_rate": 2.3456801705416197e-06, "loss": 4.0698, "step": 16002 }, { "epoch": 0.8611170899698666, "grad_norm": 4.962210178375244, "learning_rate": 2.343893199367769e-06, "loss": 3.1343, "step": 16003 }, { "epoch": 0.8611708996986656, "grad_norm": 2.535738945007324, "learning_rate": 2.342106875644512e-06, "loss": 3.4375, "step": 16004 }, { "epoch": 0.8612247094274645, "grad_norm": 2.4948806762695312, "learning_rate": 2.340321199422896e-06, "loss": 3.9491, "step": 16005 }, { "epoch": 0.8612785191562634, "grad_norm": 3.7326622009277344, "learning_rate": 2.338536170753955e-06, "loss": 3.5797, "step": 16006 }, { "epoch": 0.8613323288850624, "grad_norm": 2.5950822830200195, "learning_rate": 2.3367517896886985e-06, "loss": 3.835, "step": 16007 }, { "epoch": 0.8613861386138614, "grad_norm": 2.550530195236206, "learning_rate": 2.3349680562781167e-06, "loss": 3.6082, "step": 16008 }, { "epoch": 0.8614399483426604, "grad_norm": 2.3405873775482178, "learning_rate": 2.333184970573188e-06, "loss": 3.4238, "step": 16009 }, { "epoch": 0.8614937580714593, "grad_norm": 2.9748282432556152, "learning_rate": 2.3314025326248656e-06, "loss": 3.6838, "step": 16010 }, { "epoch": 0.8615475678002583, "grad_norm": 2.5592234134674072, "learning_rate": 2.329620742484087e-06, "loss": 3.5191, "step": 16011 }, { "epoch": 0.8616013775290573, "grad_norm": 3.0175998210906982, "learning_rate": 2.32783960020177e-06, "loss": 3.3772, "step": 16012 }, { "epoch": 0.8616551872578562, "grad_norm": 2.3098442554473877, "learning_rate": 2.3260591058288152e-06, "loss": 4.4369, "step": 16013 }, { "epoch": 0.8617089969866552, "grad_norm": 2.378401279449463, "learning_rate": 2.3242792594161123e-06, "loss": 3.9502, "step": 16014 }, { "epoch": 0.8617628067154541, "grad_norm": 1.7049779891967773, "learning_rate": 2.3225000610145125e-06, "loss": 3.7671, "step": 16015 }, { "epoch": 0.8618166164442531, "grad_norm": 2.575366258621216, "learning_rate": 2.320721510674867e-06, "loss": 3.8388, "step": 16016 }, { "epoch": 0.8618704261730521, "grad_norm": 3.948315382003784, "learning_rate": 2.318943608447999e-06, "loss": 3.5523, "step": 16017 }, { "epoch": 0.8619242359018511, "grad_norm": 2.494506597518921, "learning_rate": 2.3171663543847145e-06, "loss": 3.5176, "step": 16018 }, { "epoch": 0.8619780456306501, "grad_norm": 1.388746738433838, "learning_rate": 2.3153897485358123e-06, "loss": 4.2392, "step": 16019 }, { "epoch": 0.862031855359449, "grad_norm": 2.962477445602417, "learning_rate": 2.3136137909520545e-06, "loss": 3.9545, "step": 16020 }, { "epoch": 0.8620856650882479, "grad_norm": 3.290658950805664, "learning_rate": 2.311838481684195e-06, "loss": 3.4629, "step": 16021 }, { "epoch": 0.8621394748170469, "grad_norm": 2.8038980960845947, "learning_rate": 2.3100638207829733e-06, "loss": 3.1607, "step": 16022 }, { "epoch": 0.8621932845458459, "grad_norm": 1.6380075216293335, "learning_rate": 2.3082898082990885e-06, "loss": 4.4144, "step": 16023 }, { "epoch": 0.8622470942746449, "grad_norm": 1.6310333013534546, "learning_rate": 2.3065164442832523e-06, "loss": 4.4018, "step": 16024 }, { "epoch": 0.8623009040034438, "grad_norm": 1.4810954332351685, "learning_rate": 2.304743728786138e-06, "loss": 3.6746, "step": 16025 }, { "epoch": 0.8623547137322428, "grad_norm": 2.413407564163208, "learning_rate": 2.302971661858405e-06, "loss": 3.2057, "step": 16026 }, { "epoch": 0.8624085234610418, "grad_norm": 2.383197069168091, "learning_rate": 2.301200243550694e-06, "loss": 3.7922, "step": 16027 }, { "epoch": 0.8624623331898407, "grad_norm": 5.497185707092285, "learning_rate": 2.299429473913628e-06, "loss": 3.5479, "step": 16028 }, { "epoch": 0.8625161429186397, "grad_norm": 3.323641777038574, "learning_rate": 2.2976593529978107e-06, "loss": 3.1303, "step": 16029 }, { "epoch": 0.8625699526474386, "grad_norm": 3.4120304584503174, "learning_rate": 2.295889880853827e-06, "loss": 3.3834, "step": 16030 }, { "epoch": 0.8626237623762376, "grad_norm": 2.6537082195281982, "learning_rate": 2.294121057532242e-06, "loss": 4.1847, "step": 16031 }, { "epoch": 0.8626775721050366, "grad_norm": 1.6555376052856445, "learning_rate": 2.2923528830836065e-06, "loss": 4.0357, "step": 16032 }, { "epoch": 0.8627313818338356, "grad_norm": 3.467306613922119, "learning_rate": 2.2905853575584444e-06, "loss": 2.2624, "step": 16033 }, { "epoch": 0.8627851915626346, "grad_norm": 1.8814886808395386, "learning_rate": 2.2888184810072765e-06, "loss": 3.7942, "step": 16034 }, { "epoch": 0.8628390012914335, "grad_norm": 2.4184658527374268, "learning_rate": 2.28705225348059e-06, "loss": 4.0657, "step": 16035 }, { "epoch": 0.8628928110202324, "grad_norm": 2.268386125564575, "learning_rate": 2.285286675028861e-06, "loss": 3.3728, "step": 16036 }, { "epoch": 0.8629466207490314, "grad_norm": 2.842696189880371, "learning_rate": 2.2835217457025463e-06, "loss": 4.2292, "step": 16037 }, { "epoch": 0.8630004304778304, "grad_norm": 2.238255023956299, "learning_rate": 2.2817574655520703e-06, "loss": 4.035, "step": 16038 }, { "epoch": 0.8630542402066294, "grad_norm": 4.502350330352783, "learning_rate": 2.2799938346278666e-06, "loss": 3.8772, "step": 16039 }, { "epoch": 0.8631080499354283, "grad_norm": 3.5762197971343994, "learning_rate": 2.2782308529803315e-06, "loss": 3.7298, "step": 16040 }, { "epoch": 0.8631618596642273, "grad_norm": 3.0356392860412598, "learning_rate": 2.276468520659841e-06, "loss": 3.3429, "step": 16041 }, { "epoch": 0.8632156693930263, "grad_norm": 2.1366896629333496, "learning_rate": 2.274706837716761e-06, "loss": 4.124, "step": 16042 }, { "epoch": 0.8632694791218253, "grad_norm": 2.3704984188079834, "learning_rate": 2.272945804201437e-06, "loss": 4.149, "step": 16043 }, { "epoch": 0.8633232888506241, "grad_norm": 1.8410704135894775, "learning_rate": 2.27118542016419e-06, "loss": 3.484, "step": 16044 }, { "epoch": 0.8633770985794231, "grad_norm": 1.6667554378509521, "learning_rate": 2.269425685655338e-06, "loss": 4.1477, "step": 16045 }, { "epoch": 0.8634309083082221, "grad_norm": 2.786034345626831, "learning_rate": 2.2676666007251575e-06, "loss": 3.88, "step": 16046 }, { "epoch": 0.8634847180370211, "grad_norm": 3.6366147994995117, "learning_rate": 2.265908165423922e-06, "loss": 3.9532, "step": 16047 }, { "epoch": 0.8635385277658201, "grad_norm": 2.6864285469055176, "learning_rate": 2.264150379801885e-06, "loss": 4.1121, "step": 16048 }, { "epoch": 0.8635923374946191, "grad_norm": 2.9623496532440186, "learning_rate": 2.262393243909272e-06, "loss": 3.7219, "step": 16049 }, { "epoch": 0.863646147223418, "grad_norm": 3.4816079139709473, "learning_rate": 2.260636757796308e-06, "loss": 4.0495, "step": 16050 }, { "epoch": 0.8636999569522169, "grad_norm": 3.859318494796753, "learning_rate": 2.2588809215131845e-06, "loss": 3.3518, "step": 16051 }, { "epoch": 0.8637537666810159, "grad_norm": 4.62245512008667, "learning_rate": 2.2571257351100828e-06, "loss": 3.521, "step": 16052 }, { "epoch": 0.8638075764098149, "grad_norm": 3.450190544128418, "learning_rate": 2.2553711986371517e-06, "loss": 3.9544, "step": 16053 }, { "epoch": 0.8638613861386139, "grad_norm": 1.8620461225509644, "learning_rate": 2.2536173121445293e-06, "loss": 3.6468, "step": 16054 }, { "epoch": 0.8639151958674128, "grad_norm": 5.88154411315918, "learning_rate": 2.25186407568235e-06, "loss": 3.1116, "step": 16055 }, { "epoch": 0.8639690055962118, "grad_norm": 2.9659879207611084, "learning_rate": 2.25011148930071e-06, "loss": 4.0045, "step": 16056 }, { "epoch": 0.8640228153250108, "grad_norm": 3.630899667739868, "learning_rate": 2.248359553049692e-06, "loss": 4.1339, "step": 16057 }, { "epoch": 0.8640766250538098, "grad_norm": 2.0079543590545654, "learning_rate": 2.2466082669793665e-06, "loss": 3.8919, "step": 16058 }, { "epoch": 0.8641304347826086, "grad_norm": 2.486797571182251, "learning_rate": 2.244857631139774e-06, "loss": 4.0, "step": 16059 }, { "epoch": 0.8641842445114076, "grad_norm": 3.2286927700042725, "learning_rate": 2.2431076455809467e-06, "loss": 3.528, "step": 16060 }, { "epoch": 0.8642380542402066, "grad_norm": 2.2341129779815674, "learning_rate": 2.241358310352895e-06, "loss": 4.3239, "step": 16061 }, { "epoch": 0.8642918639690056, "grad_norm": 1.7640184164047241, "learning_rate": 2.2396096255056094e-06, "loss": 4.0791, "step": 16062 }, { "epoch": 0.8643456736978046, "grad_norm": 2.3109710216522217, "learning_rate": 2.2378615910890633e-06, "loss": 3.1319, "step": 16063 }, { "epoch": 0.8643994834266036, "grad_norm": 2.2868711948394775, "learning_rate": 2.2361142071532033e-06, "loss": 3.3455, "step": 16064 }, { "epoch": 0.8644532931554025, "grad_norm": 3.7425029277801514, "learning_rate": 2.234367473747978e-06, "loss": 4.5228, "step": 16065 }, { "epoch": 0.8645071028842015, "grad_norm": 3.638113021850586, "learning_rate": 2.232621390923298e-06, "loss": 2.9535, "step": 16066 }, { "epoch": 0.8645609126130004, "grad_norm": 3.018387794494629, "learning_rate": 2.230875958729059e-06, "loss": 2.9551, "step": 16067 }, { "epoch": 0.8646147223417994, "grad_norm": 2.4851059913635254, "learning_rate": 2.2291311772151518e-06, "loss": 4.0291, "step": 16068 }, { "epoch": 0.8646685320705984, "grad_norm": 2.1756131649017334, "learning_rate": 2.2273870464314175e-06, "loss": 4.0048, "step": 16069 }, { "epoch": 0.8647223417993973, "grad_norm": 2.624462604522705, "learning_rate": 2.2256435664277154e-06, "loss": 3.7521, "step": 16070 }, { "epoch": 0.8647761515281963, "grad_norm": 4.028698444366455, "learning_rate": 2.2239007372538617e-06, "loss": 3.2735, "step": 16071 }, { "epoch": 0.8648299612569953, "grad_norm": 3.015659809112549, "learning_rate": 2.2221585589596666e-06, "loss": 3.6871, "step": 16072 }, { "epoch": 0.8648837709857943, "grad_norm": 2.7074263095855713, "learning_rate": 2.2204170315949153e-06, "loss": 4.0361, "step": 16073 }, { "epoch": 0.8649375807145931, "grad_norm": 2.7126564979553223, "learning_rate": 2.218676155209376e-06, "loss": 3.8475, "step": 16074 }, { "epoch": 0.8649913904433921, "grad_norm": 4.107422351837158, "learning_rate": 2.2169359298527954e-06, "loss": 3.6568, "step": 16075 }, { "epoch": 0.8650452001721911, "grad_norm": 3.683398485183716, "learning_rate": 2.2151963555749084e-06, "loss": 3.5196, "step": 16076 }, { "epoch": 0.8650990099009901, "grad_norm": 1.8532021045684814, "learning_rate": 2.2134574324254255e-06, "loss": 4.393, "step": 16077 }, { "epoch": 0.8651528196297891, "grad_norm": 1.6717877388000488, "learning_rate": 2.21171916045404e-06, "loss": 4.3003, "step": 16078 }, { "epoch": 0.865206629358588, "grad_norm": 3.0358593463897705, "learning_rate": 2.209981539710429e-06, "loss": 3.5595, "step": 16079 }, { "epoch": 0.865260439087387, "grad_norm": 1.8021042346954346, "learning_rate": 2.2082445702442415e-06, "loss": 4.4479, "step": 16080 }, { "epoch": 0.865314248816186, "grad_norm": 2.026810646057129, "learning_rate": 2.2065082521051247e-06, "loss": 3.9213, "step": 16081 }, { "epoch": 0.8653680585449849, "grad_norm": 3.910724401473999, "learning_rate": 2.204772585342696e-06, "loss": 4.3948, "step": 16082 }, { "epoch": 0.8654218682737839, "grad_norm": 1.9434280395507812, "learning_rate": 2.2030375700065607e-06, "loss": 4.1231, "step": 16083 }, { "epoch": 0.8654756780025828, "grad_norm": 3.0582926273345947, "learning_rate": 2.201303206146285e-06, "loss": 3.2163, "step": 16084 }, { "epoch": 0.8655294877313818, "grad_norm": 3.2687816619873047, "learning_rate": 2.1995694938114485e-06, "loss": 3.9714, "step": 16085 }, { "epoch": 0.8655832974601808, "grad_norm": 3.8788459300994873, "learning_rate": 2.1978364330515867e-06, "loss": 3.3872, "step": 16086 }, { "epoch": 0.8656371071889798, "grad_norm": 2.344463348388672, "learning_rate": 2.1961040239162316e-06, "loss": 3.6092, "step": 16087 }, { "epoch": 0.8656909169177788, "grad_norm": 2.344141721725464, "learning_rate": 2.194372266454889e-06, "loss": 3.9321, "step": 16088 }, { "epoch": 0.8657447266465778, "grad_norm": 2.7639660835266113, "learning_rate": 2.1926411607170432e-06, "loss": 3.2919, "step": 16089 }, { "epoch": 0.8657985363753766, "grad_norm": 2.5956783294677734, "learning_rate": 2.1909107067521667e-06, "loss": 3.8077, "step": 16090 }, { "epoch": 0.8658523461041756, "grad_norm": 3.416840076446533, "learning_rate": 2.189180904609722e-06, "loss": 3.6853, "step": 16091 }, { "epoch": 0.8659061558329746, "grad_norm": 3.100961446762085, "learning_rate": 2.1874517543391286e-06, "loss": 3.8034, "step": 16092 }, { "epoch": 0.8659599655617736, "grad_norm": 4.011720657348633, "learning_rate": 2.185723255989805e-06, "loss": 3.3701, "step": 16093 }, { "epoch": 0.8660137752905726, "grad_norm": 2.164639472961426, "learning_rate": 2.1839954096111478e-06, "loss": 4.2812, "step": 16094 }, { "epoch": 0.8660675850193715, "grad_norm": 2.691152811050415, "learning_rate": 2.1822682152525283e-06, "loss": 4.1583, "step": 16095 }, { "epoch": 0.8661213947481705, "grad_norm": 4.2013678550720215, "learning_rate": 2.1805416729633154e-06, "loss": 3.8167, "step": 16096 }, { "epoch": 0.8661752044769694, "grad_norm": 3.0130679607391357, "learning_rate": 2.1788157827928454e-06, "loss": 3.8454, "step": 16097 }, { "epoch": 0.8662290142057684, "grad_norm": 4.077219009399414, "learning_rate": 2.1770905447904442e-06, "loss": 3.8295, "step": 16098 }, { "epoch": 0.8662828239345673, "grad_norm": 3.223737955093384, "learning_rate": 2.1753659590054014e-06, "loss": 3.6697, "step": 16099 }, { "epoch": 0.8663366336633663, "grad_norm": 2.3758456707000732, "learning_rate": 2.1736420254870076e-06, "loss": 4.2302, "step": 16100 }, { "epoch": 0.8663904433921653, "grad_norm": 2.761169195175171, "learning_rate": 2.171918744284529e-06, "loss": 3.0472, "step": 16101 }, { "epoch": 0.8664442531209643, "grad_norm": 1.8670605421066284, "learning_rate": 2.170196115447215e-06, "loss": 4.0375, "step": 16102 }, { "epoch": 0.8664980628497633, "grad_norm": 2.525512456893921, "learning_rate": 2.168474139024293e-06, "loss": 3.936, "step": 16103 }, { "epoch": 0.8665518725785623, "grad_norm": 2.0435729026794434, "learning_rate": 2.166752815064968e-06, "loss": 4.3895, "step": 16104 }, { "epoch": 0.8666056823073611, "grad_norm": 2.575913667678833, "learning_rate": 2.165032143618434e-06, "loss": 2.9764, "step": 16105 }, { "epoch": 0.8666594920361601, "grad_norm": 3.782475233078003, "learning_rate": 2.16331212473386e-06, "loss": 3.6698, "step": 16106 }, { "epoch": 0.8667133017649591, "grad_norm": 3.1355042457580566, "learning_rate": 2.161592758460404e-06, "loss": 4.0601, "step": 16107 }, { "epoch": 0.8667671114937581, "grad_norm": 2.961533546447754, "learning_rate": 2.1598740448471987e-06, "loss": 3.9144, "step": 16108 }, { "epoch": 0.866820921222557, "grad_norm": 4.409099578857422, "learning_rate": 2.1581559839433605e-06, "loss": 3.4644, "step": 16109 }, { "epoch": 0.866874730951356, "grad_norm": 3.1389451026916504, "learning_rate": 2.1564385757979894e-06, "loss": 4.0405, "step": 16110 }, { "epoch": 0.866928540680155, "grad_norm": 3.6690800189971924, "learning_rate": 2.154721820460154e-06, "loss": 3.2067, "step": 16111 }, { "epoch": 0.8669823504089539, "grad_norm": 1.5395978689193726, "learning_rate": 2.1530057179789285e-06, "loss": 4.733, "step": 16112 }, { "epoch": 0.8670361601377529, "grad_norm": 3.236724853515625, "learning_rate": 2.1512902684033528e-06, "loss": 3.2975, "step": 16113 }, { "epoch": 0.8670899698665518, "grad_norm": 4.185103416442871, "learning_rate": 2.149575471782439e-06, "loss": 3.9319, "step": 16114 }, { "epoch": 0.8671437795953508, "grad_norm": 1.7531936168670654, "learning_rate": 2.147861328165196e-06, "loss": 4.3623, "step": 16115 }, { "epoch": 0.8671975893241498, "grad_norm": 3.5354957580566406, "learning_rate": 2.146147837600615e-06, "loss": 3.8092, "step": 16116 }, { "epoch": 0.8672513990529488, "grad_norm": 4.155491828918457, "learning_rate": 2.144435000137657e-06, "loss": 3.0367, "step": 16117 }, { "epoch": 0.8673052087817478, "grad_norm": 3.816871404647827, "learning_rate": 2.1427228158252736e-06, "loss": 3.8327, "step": 16118 }, { "epoch": 0.8673590185105468, "grad_norm": 2.2600255012512207, "learning_rate": 2.1410112847123964e-06, "loss": 3.2304, "step": 16119 }, { "epoch": 0.8674128282393456, "grad_norm": 1.5500283241271973, "learning_rate": 2.13930040684793e-06, "loss": 4.0339, "step": 16120 }, { "epoch": 0.8674666379681446, "grad_norm": 2.311675786972046, "learning_rate": 2.137590182280769e-06, "loss": 3.8482, "step": 16121 }, { "epoch": 0.8675204476969436, "grad_norm": 2.299426794052124, "learning_rate": 2.13588061105979e-06, "loss": 3.6179, "step": 16122 }, { "epoch": 0.8675742574257426, "grad_norm": 4.080630302429199, "learning_rate": 2.1341716932338467e-06, "loss": 3.3546, "step": 16123 }, { "epoch": 0.8676280671545415, "grad_norm": 2.914656162261963, "learning_rate": 2.132463428851772e-06, "loss": 4.9112, "step": 16124 }, { "epoch": 0.8676818768833405, "grad_norm": 2.4000277519226074, "learning_rate": 2.1307558179623875e-06, "loss": 4.396, "step": 16125 }, { "epoch": 0.8677356866121395, "grad_norm": 2.0588037967681885, "learning_rate": 2.129048860614485e-06, "loss": 4.1585, "step": 16126 }, { "epoch": 0.8677894963409385, "grad_norm": 1.679634928703308, "learning_rate": 2.1273425568568566e-06, "loss": 4.4668, "step": 16127 }, { "epoch": 0.8678433060697374, "grad_norm": 2.3798117637634277, "learning_rate": 2.125636906738257e-06, "loss": 3.6787, "step": 16128 }, { "epoch": 0.8678971157985363, "grad_norm": 3.046936511993408, "learning_rate": 2.1239319103074336e-06, "loss": 4.6148, "step": 16129 }, { "epoch": 0.8679509255273353, "grad_norm": 3.8240044116973877, "learning_rate": 2.1222275676131027e-06, "loss": 2.438, "step": 16130 }, { "epoch": 0.8680047352561343, "grad_norm": 2.062401533126831, "learning_rate": 2.12052387870397e-06, "loss": 3.3545, "step": 16131 }, { "epoch": 0.8680585449849333, "grad_norm": 3.6643106937408447, "learning_rate": 2.11882084362873e-06, "loss": 2.4197, "step": 16132 }, { "epoch": 0.8681123547137323, "grad_norm": 3.4704806804656982, "learning_rate": 2.117118462436049e-06, "loss": 3.6018, "step": 16133 }, { "epoch": 0.8681661644425313, "grad_norm": 3.6330318450927734, "learning_rate": 2.1154167351745717e-06, "loss": 3.2908, "step": 16134 }, { "epoch": 0.8682199741713301, "grad_norm": 3.9357872009277344, "learning_rate": 2.1137156618929342e-06, "loss": 2.8645, "step": 16135 }, { "epoch": 0.8682737839001291, "grad_norm": 1.7635219097137451, "learning_rate": 2.112015242639745e-06, "loss": 4.4863, "step": 16136 }, { "epoch": 0.8683275936289281, "grad_norm": 2.5653159618377686, "learning_rate": 2.1103154774636007e-06, "loss": 4.0347, "step": 16137 }, { "epoch": 0.8683814033577271, "grad_norm": 3.2663748264312744, "learning_rate": 2.1086163664130716e-06, "loss": 3.1181, "step": 16138 }, { "epoch": 0.868435213086526, "grad_norm": 4.071037292480469, "learning_rate": 2.106917909536718e-06, "loss": 3.3976, "step": 16139 }, { "epoch": 0.868489022815325, "grad_norm": 2.5840582847595215, "learning_rate": 2.105220106883074e-06, "loss": 3.6219, "step": 16140 }, { "epoch": 0.868542832544124, "grad_norm": 2.879399061203003, "learning_rate": 2.1035229585006586e-06, "loss": 3.8989, "step": 16141 }, { "epoch": 0.868596642272923, "grad_norm": 3.328436851501465, "learning_rate": 2.1018264644379696e-06, "loss": 3.9706, "step": 16142 }, { "epoch": 0.8686504520017219, "grad_norm": 3.079622268676758, "learning_rate": 2.100130624743496e-06, "loss": 4.3277, "step": 16143 }, { "epoch": 0.8687042617305208, "grad_norm": 2.4342386722564697, "learning_rate": 2.0984354394657013e-06, "loss": 4.1586, "step": 16144 }, { "epoch": 0.8687580714593198, "grad_norm": 2.5629982948303223, "learning_rate": 2.0967409086530166e-06, "loss": 3.7814, "step": 16145 }, { "epoch": 0.8688118811881188, "grad_norm": 3.568089008331299, "learning_rate": 2.0950470323538724e-06, "loss": 3.1108, "step": 16146 }, { "epoch": 0.8688656909169178, "grad_norm": 3.898810625076294, "learning_rate": 2.09335381061668e-06, "loss": 2.2223, "step": 16147 }, { "epoch": 0.8689195006457168, "grad_norm": 1.8201018571853638, "learning_rate": 2.091661243489823e-06, "loss": 3.9096, "step": 16148 }, { "epoch": 0.8689733103745158, "grad_norm": 4.766844749450684, "learning_rate": 2.089969331021674e-06, "loss": 3.4334, "step": 16149 }, { "epoch": 0.8690271201033147, "grad_norm": 2.7135109901428223, "learning_rate": 2.08827807326058e-06, "loss": 3.86, "step": 16150 }, { "epoch": 0.8690809298321136, "grad_norm": 3.3833656311035156, "learning_rate": 2.086587470254872e-06, "loss": 4.4323, "step": 16151 }, { "epoch": 0.8691347395609126, "grad_norm": 2.9279093742370605, "learning_rate": 2.0848975220528644e-06, "loss": 4.0477, "step": 16152 }, { "epoch": 0.8691885492897116, "grad_norm": 1.960762858390808, "learning_rate": 2.0832082287028544e-06, "loss": 3.9394, "step": 16153 }, { "epoch": 0.8692423590185105, "grad_norm": 3.71162486076355, "learning_rate": 2.0815195902531117e-06, "loss": 3.2911, "step": 16154 }, { "epoch": 0.8692961687473095, "grad_norm": 3.26236891746521, "learning_rate": 2.0798316067518947e-06, "loss": 3.8407, "step": 16155 }, { "epoch": 0.8693499784761085, "grad_norm": 3.1395301818847656, "learning_rate": 2.0781442782474433e-06, "loss": 3.9427, "step": 16156 }, { "epoch": 0.8694037882049075, "grad_norm": 1.7232630252838135, "learning_rate": 2.076457604787971e-06, "loss": 4.1629, "step": 16157 }, { "epoch": 0.8694575979337064, "grad_norm": 2.5812253952026367, "learning_rate": 2.0747715864216895e-06, "loss": 4.0706, "step": 16158 }, { "epoch": 0.8695114076625053, "grad_norm": 2.1786882877349854, "learning_rate": 2.073086223196777e-06, "loss": 3.8211, "step": 16159 }, { "epoch": 0.8695652173913043, "grad_norm": 2.8866734504699707, "learning_rate": 2.071401515161392e-06, "loss": 3.3229, "step": 16160 }, { "epoch": 0.8696190271201033, "grad_norm": 2.4992852210998535, "learning_rate": 2.0697174623636794e-06, "loss": 3.3447, "step": 16161 }, { "epoch": 0.8696728368489023, "grad_norm": 3.2628676891326904, "learning_rate": 2.068034064851762e-06, "loss": 4.4288, "step": 16162 }, { "epoch": 0.8697266465777013, "grad_norm": 2.5378172397613525, "learning_rate": 2.066351322673754e-06, "loss": 3.8569, "step": 16163 }, { "epoch": 0.8697804563065002, "grad_norm": 3.4758317470550537, "learning_rate": 2.064669235877745e-06, "loss": 3.7133, "step": 16164 }, { "epoch": 0.8698342660352992, "grad_norm": 1.8484793901443481, "learning_rate": 2.0629878045117957e-06, "loss": 3.1525, "step": 16165 }, { "epoch": 0.8698880757640981, "grad_norm": 2.3505773544311523, "learning_rate": 2.0613070286239657e-06, "loss": 4.1764, "step": 16166 }, { "epoch": 0.8699418854928971, "grad_norm": 1.7301852703094482, "learning_rate": 2.05962690826228e-06, "loss": 4.264, "step": 16167 }, { "epoch": 0.8699956952216961, "grad_norm": 2.894878387451172, "learning_rate": 2.0579474434747557e-06, "loss": 4.367, "step": 16168 }, { "epoch": 0.870049504950495, "grad_norm": 3.4561076164245605, "learning_rate": 2.0562686343093886e-06, "loss": 3.5306, "step": 16169 }, { "epoch": 0.870103314679294, "grad_norm": 5.900324821472168, "learning_rate": 2.0545904808141503e-06, "loss": 3.1647, "step": 16170 }, { "epoch": 0.870157124408093, "grad_norm": 3.18249249458313, "learning_rate": 2.052912983037e-06, "loss": 3.328, "step": 16171 }, { "epoch": 0.870210934136892, "grad_norm": 1.4887442588806152, "learning_rate": 2.0512361410258778e-06, "loss": 4.6621, "step": 16172 }, { "epoch": 0.870264743865691, "grad_norm": 2.776853561401367, "learning_rate": 2.0495599548286977e-06, "loss": 3.9282, "step": 16173 }, { "epoch": 0.8703185535944898, "grad_norm": 3.764387607574463, "learning_rate": 2.047884424493368e-06, "loss": 3.3067, "step": 16174 }, { "epoch": 0.8703723633232888, "grad_norm": 4.319684982299805, "learning_rate": 2.046209550067771e-06, "loss": 3.7809, "step": 16175 }, { "epoch": 0.8704261730520878, "grad_norm": 2.9390995502471924, "learning_rate": 2.0445353315997646e-06, "loss": 3.5038, "step": 16176 }, { "epoch": 0.8704799827808868, "grad_norm": 1.7946486473083496, "learning_rate": 2.042861769137189e-06, "loss": 4.1692, "step": 16177 }, { "epoch": 0.8705337925096858, "grad_norm": 1.8832412958145142, "learning_rate": 2.041188862727883e-06, "loss": 4.2218, "step": 16178 }, { "epoch": 0.8705876022384847, "grad_norm": 3.4895074367523193, "learning_rate": 2.0395166124196454e-06, "loss": 4.0357, "step": 16179 }, { "epoch": 0.8706414119672837, "grad_norm": 2.6844892501831055, "learning_rate": 2.0378450182602676e-06, "loss": 3.2508, "step": 16180 }, { "epoch": 0.8706952216960826, "grad_norm": 3.080387830734253, "learning_rate": 2.036174080297518e-06, "loss": 3.6689, "step": 16181 }, { "epoch": 0.8707490314248816, "grad_norm": 1.6373882293701172, "learning_rate": 2.034503798579146e-06, "loss": 3.3695, "step": 16182 }, { "epoch": 0.8708028411536806, "grad_norm": 2.604762315750122, "learning_rate": 2.0328341731528865e-06, "loss": 3.9277, "step": 16183 }, { "epoch": 0.8708566508824795, "grad_norm": 2.877291440963745, "learning_rate": 2.031165204066454e-06, "loss": 3.6108, "step": 16184 }, { "epoch": 0.8709104606112785, "grad_norm": 3.2435319423675537, "learning_rate": 2.0294968913675382e-06, "loss": 3.5883, "step": 16185 }, { "epoch": 0.8709642703400775, "grad_norm": 3.3019747734069824, "learning_rate": 2.02782923510382e-06, "loss": 4.0291, "step": 16186 }, { "epoch": 0.8710180800688765, "grad_norm": 3.9008426666259766, "learning_rate": 2.026162235322954e-06, "loss": 3.7744, "step": 16187 }, { "epoch": 0.8710718897976755, "grad_norm": 1.9498332738876343, "learning_rate": 2.0244958920725752e-06, "loss": 3.9279, "step": 16188 }, { "epoch": 0.8711256995264743, "grad_norm": 2.095000982284546, "learning_rate": 2.0228302054003083e-06, "loss": 4.4614, "step": 16189 }, { "epoch": 0.8711795092552733, "grad_norm": 2.979436159133911, "learning_rate": 2.0211651753537593e-06, "loss": 3.8413, "step": 16190 }, { "epoch": 0.8712333189840723, "grad_norm": 3.9974093437194824, "learning_rate": 2.0195008019805005e-06, "loss": 3.248, "step": 16191 }, { "epoch": 0.8712871287128713, "grad_norm": 2.677827835083008, "learning_rate": 2.0178370853280975e-06, "loss": 3.7509, "step": 16192 }, { "epoch": 0.8713409384416703, "grad_norm": 4.426120758056641, "learning_rate": 2.0161740254440896e-06, "loss": 3.3256, "step": 16193 }, { "epoch": 0.8713947481704692, "grad_norm": 3.621845006942749, "learning_rate": 2.014511622376017e-06, "loss": 3.2462, "step": 16194 }, { "epoch": 0.8714485578992682, "grad_norm": 4.205682754516602, "learning_rate": 2.0128498761713744e-06, "loss": 2.8735, "step": 16195 }, { "epoch": 0.8715023676280672, "grad_norm": 2.2836153507232666, "learning_rate": 2.0111887868776575e-06, "loss": 3.6572, "step": 16196 }, { "epoch": 0.8715561773568661, "grad_norm": 2.827731132507324, "learning_rate": 2.009528354542331e-06, "loss": 3.8862, "step": 16197 }, { "epoch": 0.8716099870856651, "grad_norm": 1.5571343898773193, "learning_rate": 2.007868579212846e-06, "loss": 3.811, "step": 16198 }, { "epoch": 0.871663796814464, "grad_norm": 1.8386982679367065, "learning_rate": 2.0062094609366367e-06, "loss": 4.2264, "step": 16199 }, { "epoch": 0.871717606543263, "grad_norm": 2.051187753677368, "learning_rate": 2.004550999761115e-06, "loss": 4.0378, "step": 16200 }, { "epoch": 0.871771416272062, "grad_norm": 2.0314512252807617, "learning_rate": 2.0028931957336765e-06, "loss": 3.9942, "step": 16201 }, { "epoch": 0.871825226000861, "grad_norm": 2.4238383769989014, "learning_rate": 2.001236048901692e-06, "loss": 3.3576, "step": 16202 }, { "epoch": 0.87187903572966, "grad_norm": 2.2856180667877197, "learning_rate": 1.9995795593125255e-06, "loss": 4.1026, "step": 16203 }, { "epoch": 0.8719328454584588, "grad_norm": 2.7410035133361816, "learning_rate": 1.9979237270135036e-06, "loss": 4.1981, "step": 16204 }, { "epoch": 0.8719866551872578, "grad_norm": 3.167027711868286, "learning_rate": 1.9962685520519635e-06, "loss": 3.0834, "step": 16205 }, { "epoch": 0.8720404649160568, "grad_norm": 2.8052561283111572, "learning_rate": 1.9946140344751925e-06, "loss": 3.5096, "step": 16206 }, { "epoch": 0.8720942746448558, "grad_norm": 2.230736494064331, "learning_rate": 1.9929601743304745e-06, "loss": 4.1223, "step": 16207 }, { "epoch": 0.8721480843736548, "grad_norm": 3.054201126098633, "learning_rate": 1.991306971665069e-06, "loss": 2.9768, "step": 16208 }, { "epoch": 0.8722018941024537, "grad_norm": 2.14536190032959, "learning_rate": 1.9896544265262275e-06, "loss": 3.2119, "step": 16209 }, { "epoch": 0.8722557038312527, "grad_norm": 3.0282375812530518, "learning_rate": 1.98800253896117e-06, "loss": 4.3592, "step": 16210 }, { "epoch": 0.8723095135600517, "grad_norm": 2.628243923187256, "learning_rate": 1.9863513090171093e-06, "loss": 3.7284, "step": 16211 }, { "epoch": 0.8723633232888506, "grad_norm": 3.062135696411133, "learning_rate": 1.984700736741224e-06, "loss": 3.6827, "step": 16212 }, { "epoch": 0.8724171330176496, "grad_norm": 3.236098051071167, "learning_rate": 1.9830508221806906e-06, "loss": 2.9524, "step": 16213 }, { "epoch": 0.8724709427464485, "grad_norm": 1.173203468322754, "learning_rate": 1.9814015653826567e-06, "loss": 3.7966, "step": 16214 }, { "epoch": 0.8725247524752475, "grad_norm": 2.5064964294433594, "learning_rate": 1.9797529663942523e-06, "loss": 4.3655, "step": 16215 }, { "epoch": 0.8725785622040465, "grad_norm": 5.136068344116211, "learning_rate": 1.9781050252625917e-06, "loss": 4.2643, "step": 16216 }, { "epoch": 0.8726323719328455, "grad_norm": 2.17372989654541, "learning_rate": 1.976457742034768e-06, "loss": 4.2255, "step": 16217 }, { "epoch": 0.8726861816616445, "grad_norm": 2.6396188735961914, "learning_rate": 1.974811116757855e-06, "loss": 4.1403, "step": 16218 }, { "epoch": 0.8727399913904433, "grad_norm": 2.7118968963623047, "learning_rate": 1.973165149478906e-06, "loss": 3.5655, "step": 16219 }, { "epoch": 0.8727938011192423, "grad_norm": 1.7962119579315186, "learning_rate": 1.9715198402449705e-06, "loss": 3.7508, "step": 16220 }, { "epoch": 0.8728476108480413, "grad_norm": 1.3330167531967163, "learning_rate": 1.9698751891030543e-06, "loss": 4.0936, "step": 16221 }, { "epoch": 0.8729014205768403, "grad_norm": 2.4967665672302246, "learning_rate": 1.9682311961001622e-06, "loss": 3.8783, "step": 16222 }, { "epoch": 0.8729552303056393, "grad_norm": 1.936029314994812, "learning_rate": 1.9665878612832727e-06, "loss": 4.5877, "step": 16223 }, { "epoch": 0.8730090400344382, "grad_norm": 3.615551233291626, "learning_rate": 1.964945184699346e-06, "loss": 4.3708, "step": 16224 }, { "epoch": 0.8730628497632372, "grad_norm": 3.1740026473999023, "learning_rate": 1.9633031663953333e-06, "loss": 3.8537, "step": 16225 }, { "epoch": 0.8731166594920362, "grad_norm": 3.8101894855499268, "learning_rate": 1.961661806418155e-06, "loss": 3.3566, "step": 16226 }, { "epoch": 0.8731704692208351, "grad_norm": 3.527812957763672, "learning_rate": 1.960021104814716e-06, "loss": 3.2538, "step": 16227 }, { "epoch": 0.8732242789496341, "grad_norm": 2.1635499000549316, "learning_rate": 1.9583810616319086e-06, "loss": 3.9468, "step": 16228 }, { "epoch": 0.873278088678433, "grad_norm": 3.235900402069092, "learning_rate": 1.9567416769165848e-06, "loss": 3.9537, "step": 16229 }, { "epoch": 0.873331898407232, "grad_norm": 2.0043647289276123, "learning_rate": 1.955102950715612e-06, "loss": 3.735, "step": 16230 }, { "epoch": 0.873385708136031, "grad_norm": 3.711181402206421, "learning_rate": 1.9534648830758118e-06, "loss": 3.9693, "step": 16231 }, { "epoch": 0.87343951786483, "grad_norm": 2.0164101123809814, "learning_rate": 1.951827474043999e-06, "loss": 4.3119, "step": 16232 }, { "epoch": 0.873493327593629, "grad_norm": 4.129360198974609, "learning_rate": 1.9501907236669642e-06, "loss": 4.1909, "step": 16233 }, { "epoch": 0.873547137322428, "grad_norm": 2.697875738143921, "learning_rate": 1.948554631991481e-06, "loss": 4.1854, "step": 16234 }, { "epoch": 0.8736009470512268, "grad_norm": 2.0555882453918457, "learning_rate": 1.946919199064301e-06, "loss": 4.0196, "step": 16235 }, { "epoch": 0.8736547567800258, "grad_norm": 3.860313653945923, "learning_rate": 1.945284424932173e-06, "loss": 4.0907, "step": 16236 }, { "epoch": 0.8737085665088248, "grad_norm": 1.297465443611145, "learning_rate": 1.943650309641801e-06, "loss": 4.3669, "step": 16237 }, { "epoch": 0.8737623762376238, "grad_norm": 2.3936538696289062, "learning_rate": 1.942016853239892e-06, "loss": 3.7277, "step": 16238 }, { "epoch": 0.8738161859664227, "grad_norm": 1.8015332221984863, "learning_rate": 1.9403840557731145e-06, "loss": 4.311, "step": 16239 }, { "epoch": 0.8738699956952217, "grad_norm": 4.223681926727295, "learning_rate": 1.9387519172881453e-06, "loss": 3.65, "step": 16240 }, { "epoch": 0.8739238054240207, "grad_norm": 2.2950756549835205, "learning_rate": 1.9371204378316186e-06, "loss": 3.9659, "step": 16241 }, { "epoch": 0.8739776151528196, "grad_norm": 3.0249226093292236, "learning_rate": 1.9354896174501564e-06, "loss": 3.9174, "step": 16242 }, { "epoch": 0.8740314248816186, "grad_norm": 2.1210944652557373, "learning_rate": 1.933859456190368e-06, "loss": 4.2349, "step": 16243 }, { "epoch": 0.8740852346104175, "grad_norm": 2.3252062797546387, "learning_rate": 1.9322299540988296e-06, "loss": 4.1053, "step": 16244 }, { "epoch": 0.8741390443392165, "grad_norm": 3.181565046310425, "learning_rate": 1.9306011112221163e-06, "loss": 3.7218, "step": 16245 }, { "epoch": 0.8741928540680155, "grad_norm": 2.6156399250030518, "learning_rate": 1.9289729276067757e-06, "loss": 3.6646, "step": 16246 }, { "epoch": 0.8742466637968145, "grad_norm": 4.672358989715576, "learning_rate": 1.9273454032993353e-06, "loss": 2.364, "step": 16247 }, { "epoch": 0.8743004735256135, "grad_norm": 3.2615108489990234, "learning_rate": 1.9257185383463024e-06, "loss": 4.0235, "step": 16248 }, { "epoch": 0.8743542832544124, "grad_norm": 2.522613048553467, "learning_rate": 1.924092332794175e-06, "loss": 3.1972, "step": 16249 }, { "epoch": 0.8744080929832113, "grad_norm": 4.337637424468994, "learning_rate": 1.9224667866894143e-06, "loss": 3.3997, "step": 16250 }, { "epoch": 0.8744619027120103, "grad_norm": 4.382656097412109, "learning_rate": 1.9208419000784906e-06, "loss": 3.6855, "step": 16251 }, { "epoch": 0.8745157124408093, "grad_norm": 2.952263355255127, "learning_rate": 1.919217673007828e-06, "loss": 3.0832, "step": 16252 }, { "epoch": 0.8745695221696083, "grad_norm": 5.017435073852539, "learning_rate": 1.91759410552384e-06, "loss": 3.8587, "step": 16253 }, { "epoch": 0.8746233318984072, "grad_norm": 2.966597318649292, "learning_rate": 1.9159711976729304e-06, "loss": 4.0141, "step": 16254 }, { "epoch": 0.8746771416272062, "grad_norm": 1.433056116104126, "learning_rate": 1.9143489495014736e-06, "loss": 4.302, "step": 16255 }, { "epoch": 0.8747309513560052, "grad_norm": 3.2986559867858887, "learning_rate": 1.91272736105583e-06, "loss": 2.6385, "step": 16256 }, { "epoch": 0.8747847610848042, "grad_norm": 2.7010955810546875, "learning_rate": 1.9111064323823454e-06, "loss": 4.0877, "step": 16257 }, { "epoch": 0.8748385708136031, "grad_norm": 1.4859282970428467, "learning_rate": 1.909486163527335e-06, "loss": 4.3866, "step": 16258 }, { "epoch": 0.874892380542402, "grad_norm": 1.7043135166168213, "learning_rate": 1.9078665545371023e-06, "loss": 3.4193, "step": 16259 }, { "epoch": 0.874946190271201, "grad_norm": 2.96624755859375, "learning_rate": 1.9062476054579364e-06, "loss": 3.8138, "step": 16260 }, { "epoch": 0.875, "grad_norm": 3.6715760231018066, "learning_rate": 1.9046293163360957e-06, "loss": 3.1113, "step": 16261 }, { "epoch": 0.875053809728799, "grad_norm": 3.0156078338623047, "learning_rate": 1.9030116872178316e-06, "loss": 4.2893, "step": 16262 }, { "epoch": 0.875107619457598, "grad_norm": 4.834550857543945, "learning_rate": 1.9013947181493713e-06, "loss": 3.4739, "step": 16263 }, { "epoch": 0.8751614291863969, "grad_norm": 3.213468074798584, "learning_rate": 1.8997784091769195e-06, "loss": 2.2567, "step": 16264 }, { "epoch": 0.8752152389151958, "grad_norm": 3.6085526943206787, "learning_rate": 1.8981627603466695e-06, "loss": 2.9642, "step": 16265 }, { "epoch": 0.8752690486439948, "grad_norm": 1.8346046209335327, "learning_rate": 1.8965477717047902e-06, "loss": 3.2192, "step": 16266 }, { "epoch": 0.8753228583727938, "grad_norm": 2.1812899112701416, "learning_rate": 1.8949334432974364e-06, "loss": 3.5239, "step": 16267 }, { "epoch": 0.8753766681015928, "grad_norm": 3.645660877227783, "learning_rate": 1.8933197751707377e-06, "loss": 4.063, "step": 16268 }, { "epoch": 0.8754304778303917, "grad_norm": 2.6553707122802734, "learning_rate": 1.8917067673708127e-06, "loss": 3.5324, "step": 16269 }, { "epoch": 0.8754842875591907, "grad_norm": 2.888808488845825, "learning_rate": 1.890094419943747e-06, "loss": 4.2196, "step": 16270 }, { "epoch": 0.8755380972879897, "grad_norm": 1.8701103925704956, "learning_rate": 1.8884827329356286e-06, "loss": 3.6022, "step": 16271 }, { "epoch": 0.8755919070167887, "grad_norm": 3.816862106323242, "learning_rate": 1.886871706392515e-06, "loss": 3.7659, "step": 16272 }, { "epoch": 0.8756457167455876, "grad_norm": 2.085829019546509, "learning_rate": 1.8852613403604364e-06, "loss": 4.3107, "step": 16273 }, { "epoch": 0.8756995264743865, "grad_norm": 2.769503116607666, "learning_rate": 1.8836516348854249e-06, "loss": 3.0075, "step": 16274 }, { "epoch": 0.8757533362031855, "grad_norm": 4.695303916931152, "learning_rate": 1.8820425900134637e-06, "loss": 3.8737, "step": 16275 }, { "epoch": 0.8758071459319845, "grad_norm": 3.773163080215454, "learning_rate": 1.8804342057905489e-06, "loss": 3.3364, "step": 16276 }, { "epoch": 0.8758609556607835, "grad_norm": 1.8803114891052246, "learning_rate": 1.878826482262641e-06, "loss": 4.0321, "step": 16277 }, { "epoch": 0.8759147653895825, "grad_norm": 4.411999702453613, "learning_rate": 1.8772194194756842e-06, "loss": 3.2019, "step": 16278 }, { "epoch": 0.8759685751183814, "grad_norm": 2.8594563007354736, "learning_rate": 1.8756130174756054e-06, "loss": 4.2804, "step": 16279 }, { "epoch": 0.8760223848471804, "grad_norm": 2.5884222984313965, "learning_rate": 1.8740072763083065e-06, "loss": 3.5281, "step": 16280 }, { "epoch": 0.8760761945759793, "grad_norm": 3.7104110717773438, "learning_rate": 1.8724021960196736e-06, "loss": 3.3968, "step": 16281 }, { "epoch": 0.8761300043047783, "grad_norm": 3.946836233139038, "learning_rate": 1.870797776655589e-06, "loss": 3.6169, "step": 16282 }, { "epoch": 0.8761838140335773, "grad_norm": 2.7335500717163086, "learning_rate": 1.8691940182618883e-06, "loss": 4.0056, "step": 16283 }, { "epoch": 0.8762376237623762, "grad_norm": 3.542510986328125, "learning_rate": 1.86759092088441e-06, "loss": 3.0124, "step": 16284 }, { "epoch": 0.8762914334911752, "grad_norm": 3.1297214031219482, "learning_rate": 1.8659884845689645e-06, "loss": 3.9328, "step": 16285 }, { "epoch": 0.8763452432199742, "grad_norm": 1.4476463794708252, "learning_rate": 1.8643867093613405e-06, "loss": 4.3061, "step": 16286 }, { "epoch": 0.8763990529487732, "grad_norm": 2.1082870960235596, "learning_rate": 1.8627855953073204e-06, "loss": 4.2975, "step": 16287 }, { "epoch": 0.876452862677572, "grad_norm": 3.865734338760376, "learning_rate": 1.861185142452654e-06, "loss": 3.8416, "step": 16288 }, { "epoch": 0.876506672406371, "grad_norm": 2.0269923210144043, "learning_rate": 1.8595853508430876e-06, "loss": 3.8905, "step": 16289 }, { "epoch": 0.87656048213517, "grad_norm": 3.508486032485962, "learning_rate": 1.8579862205243215e-06, "loss": 3.4198, "step": 16290 }, { "epoch": 0.876614291863969, "grad_norm": 3.1785988807678223, "learning_rate": 1.8563877515420685e-06, "loss": 3.0348, "step": 16291 }, { "epoch": 0.876668101592768, "grad_norm": 2.514450788497925, "learning_rate": 1.8547899439420064e-06, "loss": 3.3992, "step": 16292 }, { "epoch": 0.876721911321567, "grad_norm": 5.823044776916504, "learning_rate": 1.8531927977697928e-06, "loss": 4.4699, "step": 16293 }, { "epoch": 0.8767757210503659, "grad_norm": 2.640249729156494, "learning_rate": 1.8515963130710716e-06, "loss": 2.9648, "step": 16294 }, { "epoch": 0.8768295307791649, "grad_norm": 2.255851984024048, "learning_rate": 1.850000489891468e-06, "loss": 4.1674, "step": 16295 }, { "epoch": 0.8768833405079638, "grad_norm": 3.9769155979156494, "learning_rate": 1.8484053282765755e-06, "loss": 3.606, "step": 16296 }, { "epoch": 0.8769371502367628, "grad_norm": 3.1398422718048096, "learning_rate": 1.8468108282719998e-06, "loss": 2.8911, "step": 16297 }, { "epoch": 0.8769909599655618, "grad_norm": 4.114217758178711, "learning_rate": 1.8452169899232928e-06, "loss": 4.5212, "step": 16298 }, { "epoch": 0.8770447696943607, "grad_norm": 3.5842113494873047, "learning_rate": 1.843623813276002e-06, "loss": 3.962, "step": 16299 }, { "epoch": 0.8770985794231597, "grad_norm": 3.3338370323181152, "learning_rate": 1.8420312983756626e-06, "loss": 3.1078, "step": 16300 }, { "epoch": 0.8771523891519587, "grad_norm": 2.7984235286712646, "learning_rate": 1.8404394452677749e-06, "loss": 3.7585, "step": 16301 }, { "epoch": 0.8772061988807577, "grad_norm": 3.00002121925354, "learning_rate": 1.8388482539978407e-06, "loss": 4.0445, "step": 16302 }, { "epoch": 0.8772600086095567, "grad_norm": 2.376385450363159, "learning_rate": 1.8372577246113271e-06, "loss": 4.176, "step": 16303 }, { "epoch": 0.8773138183383555, "grad_norm": 3.2287094593048096, "learning_rate": 1.8356678571536861e-06, "loss": 3.864, "step": 16304 }, { "epoch": 0.8773676280671545, "grad_norm": 3.8237831592559814, "learning_rate": 1.8340786516703568e-06, "loss": 4.1784, "step": 16305 }, { "epoch": 0.8774214377959535, "grad_norm": 3.5657920837402344, "learning_rate": 1.8324901082067442e-06, "loss": 3.0268, "step": 16306 }, { "epoch": 0.8774752475247525, "grad_norm": 2.843376874923706, "learning_rate": 1.8309022268082538e-06, "loss": 3.3369, "step": 16307 }, { "epoch": 0.8775290572535515, "grad_norm": 2.233088970184326, "learning_rate": 1.829315007520263e-06, "loss": 4.0767, "step": 16308 }, { "epoch": 0.8775828669823504, "grad_norm": 3.166752576828003, "learning_rate": 1.8277284503881249e-06, "loss": 3.7055, "step": 16309 }, { "epoch": 0.8776366767111494, "grad_norm": 2.597264289855957, "learning_rate": 1.8261425554571804e-06, "loss": 3.0545, "step": 16310 }, { "epoch": 0.8776904864399483, "grad_norm": 2.7850379943847656, "learning_rate": 1.8245573227727548e-06, "loss": 4.0686, "step": 16311 }, { "epoch": 0.8777442961687473, "grad_norm": 2.420325517654419, "learning_rate": 1.8229727523801448e-06, "loss": 2.8934, "step": 16312 }, { "epoch": 0.8777981058975463, "grad_norm": 2.6522538661956787, "learning_rate": 1.821388844324634e-06, "loss": 3.9141, "step": 16313 }, { "epoch": 0.8778519156263452, "grad_norm": 1.8909245729446411, "learning_rate": 1.8198055986514862e-06, "loss": 4.1239, "step": 16314 }, { "epoch": 0.8779057253551442, "grad_norm": 3.0449368953704834, "learning_rate": 1.8182230154059481e-06, "loss": 3.9776, "step": 16315 }, { "epoch": 0.8779595350839432, "grad_norm": 6.465951919555664, "learning_rate": 1.816641094633245e-06, "loss": 3.4661, "step": 16316 }, { "epoch": 0.8780133448127422, "grad_norm": 2.3997576236724854, "learning_rate": 1.8150598363785799e-06, "loss": 3.8641, "step": 16317 }, { "epoch": 0.8780671545415412, "grad_norm": 2.5547943115234375, "learning_rate": 1.8134792406871465e-06, "loss": 3.8637, "step": 16318 }, { "epoch": 0.87812096427034, "grad_norm": 2.426276445388794, "learning_rate": 1.8118993076041146e-06, "loss": 3.5532, "step": 16319 }, { "epoch": 0.878174773999139, "grad_norm": 2.41517972946167, "learning_rate": 1.8103200371746343e-06, "loss": 3.9746, "step": 16320 }, { "epoch": 0.878228583727938, "grad_norm": 2.577446699142456, "learning_rate": 1.808741429443825e-06, "loss": 3.2575, "step": 16321 }, { "epoch": 0.878282393456737, "grad_norm": 1.497401237487793, "learning_rate": 1.8071634844568141e-06, "loss": 3.3141, "step": 16322 }, { "epoch": 0.878336203185536, "grad_norm": 3.19758677482605, "learning_rate": 1.8055862022586911e-06, "loss": 4.0192, "step": 16323 }, { "epoch": 0.8783900129143349, "grad_norm": 2.569795608520508, "learning_rate": 1.8040095828945253e-06, "loss": 4.2195, "step": 16324 }, { "epoch": 0.8784438226431339, "grad_norm": 3.5038702487945557, "learning_rate": 1.8024336264093777e-06, "loss": 3.9584, "step": 16325 }, { "epoch": 0.8784976323719328, "grad_norm": 2.9758541584014893, "learning_rate": 1.800858332848282e-06, "loss": 3.0203, "step": 16326 }, { "epoch": 0.8785514421007318, "grad_norm": 2.0620851516723633, "learning_rate": 1.7992837022562576e-06, "loss": 3.6246, "step": 16327 }, { "epoch": 0.8786052518295308, "grad_norm": 4.003640651702881, "learning_rate": 1.7977097346783018e-06, "loss": 3.3785, "step": 16328 }, { "epoch": 0.8786590615583297, "grad_norm": 2.986532211303711, "learning_rate": 1.7961364301593954e-06, "loss": 2.8364, "step": 16329 }, { "epoch": 0.8787128712871287, "grad_norm": 3.4763271808624268, "learning_rate": 1.7945637887444995e-06, "loss": 2.6516, "step": 16330 }, { "epoch": 0.8787666810159277, "grad_norm": 3.1281068325042725, "learning_rate": 1.792991810478556e-06, "loss": 4.1217, "step": 16331 }, { "epoch": 0.8788204907447267, "grad_norm": 2.0664849281311035, "learning_rate": 1.7914204954064816e-06, "loss": 4.0361, "step": 16332 }, { "epoch": 0.8788743004735257, "grad_norm": 1.3755515813827515, "learning_rate": 1.7898498435731881e-06, "loss": 4.3538, "step": 16333 }, { "epoch": 0.8789281102023245, "grad_norm": 3.5497212409973145, "learning_rate": 1.7882798550235585e-06, "loss": 3.5062, "step": 16334 }, { "epoch": 0.8789819199311235, "grad_norm": 1.8444639444351196, "learning_rate": 1.7867105298024656e-06, "loss": 4.3159, "step": 16335 }, { "epoch": 0.8790357296599225, "grad_norm": 2.045776844024658, "learning_rate": 1.7851418679547427e-06, "loss": 3.7726, "step": 16336 }, { "epoch": 0.8790895393887215, "grad_norm": 3.871042013168335, "learning_rate": 1.7835738695252207e-06, "loss": 4.1225, "step": 16337 }, { "epoch": 0.8791433491175205, "grad_norm": 3.885430335998535, "learning_rate": 1.7820065345587167e-06, "loss": 3.4203, "step": 16338 }, { "epoch": 0.8791971588463194, "grad_norm": 2.1880815029144287, "learning_rate": 1.7804398631000168e-06, "loss": 4.0748, "step": 16339 }, { "epoch": 0.8792509685751184, "grad_norm": 2.379606008529663, "learning_rate": 1.7788738551938938e-06, "loss": 3.2691, "step": 16340 }, { "epoch": 0.8793047783039174, "grad_norm": 1.4366438388824463, "learning_rate": 1.7773085108850978e-06, "loss": 4.1187, "step": 16341 }, { "epoch": 0.8793585880327163, "grad_norm": 1.788304090499878, "learning_rate": 1.7757438302183627e-06, "loss": 4.4266, "step": 16342 }, { "epoch": 0.8794123977615153, "grad_norm": 3.054683208465576, "learning_rate": 1.7741798132384025e-06, "loss": 4.0852, "step": 16343 }, { "epoch": 0.8794662074903142, "grad_norm": 2.206869125366211, "learning_rate": 1.7726164599899148e-06, "loss": 3.9346, "step": 16344 }, { "epoch": 0.8795200172191132, "grad_norm": 3.3306994438171387, "learning_rate": 1.7710537705175722e-06, "loss": 3.8621, "step": 16345 }, { "epoch": 0.8795738269479122, "grad_norm": 3.257429361343384, "learning_rate": 1.7694917448660364e-06, "loss": 4.3096, "step": 16346 }, { "epoch": 0.8796276366767112, "grad_norm": 1.720251202583313, "learning_rate": 1.7679303830799409e-06, "loss": 4.3516, "step": 16347 }, { "epoch": 0.8796814464055102, "grad_norm": 3.561716079711914, "learning_rate": 1.7663696852039058e-06, "loss": 2.7918, "step": 16348 }, { "epoch": 0.879735256134309, "grad_norm": 3.3587868213653564, "learning_rate": 1.7648096512825397e-06, "loss": 3.9048, "step": 16349 }, { "epoch": 0.879789065863108, "grad_norm": 2.2724123001098633, "learning_rate": 1.7632502813604206e-06, "loss": 3.7866, "step": 16350 }, { "epoch": 0.879842875591907, "grad_norm": 2.945988178253174, "learning_rate": 1.7616915754821052e-06, "loss": 3.2648, "step": 16351 }, { "epoch": 0.879896685320706, "grad_norm": 3.243408203125, "learning_rate": 1.7601335336921348e-06, "loss": 4.2288, "step": 16352 }, { "epoch": 0.879950495049505, "grad_norm": 2.7819182872772217, "learning_rate": 1.7585761560350467e-06, "loss": 3.998, "step": 16353 }, { "epoch": 0.8800043047783039, "grad_norm": 1.9670768976211548, "learning_rate": 1.757019442555341e-06, "loss": 3.7546, "step": 16354 }, { "epoch": 0.8800581145071029, "grad_norm": 4.2575883865356445, "learning_rate": 1.7554633932975017e-06, "loss": 3.143, "step": 16355 }, { "epoch": 0.8801119242359019, "grad_norm": 1.6384360790252686, "learning_rate": 1.753908008305996e-06, "loss": 4.2281, "step": 16356 }, { "epoch": 0.8801657339647008, "grad_norm": 2.2044622898101807, "learning_rate": 1.7523532876252774e-06, "loss": 3.9437, "step": 16357 }, { "epoch": 0.8802195436934998, "grad_norm": 3.300477981567383, "learning_rate": 1.750799231299774e-06, "loss": 3.2927, "step": 16358 }, { "epoch": 0.8802733534222987, "grad_norm": 3.2617733478546143, "learning_rate": 1.749245839373892e-06, "loss": 3.3539, "step": 16359 }, { "epoch": 0.8803271631510977, "grad_norm": 3.0510783195495605, "learning_rate": 1.7476931118920291e-06, "loss": 3.2918, "step": 16360 }, { "epoch": 0.8803809728798967, "grad_norm": 2.234952688217163, "learning_rate": 1.7461410488985558e-06, "loss": 4.0714, "step": 16361 }, { "epoch": 0.8804347826086957, "grad_norm": 4.1797966957092285, "learning_rate": 1.7445896504378251e-06, "loss": 3.7293, "step": 16362 }, { "epoch": 0.8804885923374947, "grad_norm": 2.064260482788086, "learning_rate": 1.743038916554171e-06, "loss": 4.2777, "step": 16363 }, { "epoch": 0.8805424020662936, "grad_norm": 2.1702933311462402, "learning_rate": 1.7414888472919111e-06, "loss": 3.926, "step": 16364 }, { "epoch": 0.8805962117950925, "grad_norm": 2.826125144958496, "learning_rate": 1.739939442695343e-06, "loss": 3.6058, "step": 16365 }, { "epoch": 0.8806500215238915, "grad_norm": 3.3397328853607178, "learning_rate": 1.7383907028087482e-06, "loss": 3.5954, "step": 16366 }, { "epoch": 0.8807038312526905, "grad_norm": 2.5547940731048584, "learning_rate": 1.7368426276763772e-06, "loss": 4.3291, "step": 16367 }, { "epoch": 0.8807576409814895, "grad_norm": 3.3124101161956787, "learning_rate": 1.735295217342467e-06, "loss": 3.6402, "step": 16368 }, { "epoch": 0.8808114507102884, "grad_norm": 3.1711232662200928, "learning_rate": 1.7337484718512514e-06, "loss": 3.4952, "step": 16369 }, { "epoch": 0.8808652604390874, "grad_norm": 1.9180253744125366, "learning_rate": 1.7322023912469232e-06, "loss": 3.6989, "step": 16370 }, { "epoch": 0.8809190701678864, "grad_norm": 2.4174795150756836, "learning_rate": 1.730656975573669e-06, "loss": 4.1141, "step": 16371 }, { "epoch": 0.8809728798966853, "grad_norm": 3.1754720211029053, "learning_rate": 1.7291122248756535e-06, "loss": 3.2311, "step": 16372 }, { "epoch": 0.8810266896254842, "grad_norm": 2.428748369216919, "learning_rate": 1.7275681391970166e-06, "loss": 3.6625, "step": 16373 }, { "epoch": 0.8810804993542832, "grad_norm": 1.8193925619125366, "learning_rate": 1.7260247185818868e-06, "loss": 4.0993, "step": 16374 }, { "epoch": 0.8811343090830822, "grad_norm": 4.078227519989014, "learning_rate": 1.7244819630743702e-06, "loss": 2.8639, "step": 16375 }, { "epoch": 0.8811881188118812, "grad_norm": 1.818718433380127, "learning_rate": 1.722939872718557e-06, "loss": 4.2924, "step": 16376 }, { "epoch": 0.8812419285406802, "grad_norm": 2.640019178390503, "learning_rate": 1.7213984475585144e-06, "loss": 4.05, "step": 16377 }, { "epoch": 0.8812957382694792, "grad_norm": 2.6417644023895264, "learning_rate": 1.7198576876382905e-06, "loss": 3.8112, "step": 16378 }, { "epoch": 0.8813495479982781, "grad_norm": 1.9166799783706665, "learning_rate": 1.718317593001914e-06, "loss": 2.9487, "step": 16379 }, { "epoch": 0.881403357727077, "grad_norm": 3.772735118865967, "learning_rate": 1.7167781636934054e-06, "loss": 2.6574, "step": 16380 }, { "epoch": 0.881457167455876, "grad_norm": 2.8929009437561035, "learning_rate": 1.7152393997567545e-06, "loss": 3.2106, "step": 16381 }, { "epoch": 0.881510977184675, "grad_norm": 3.8679723739624023, "learning_rate": 1.7137013012359315e-06, "loss": 4.0068, "step": 16382 }, { "epoch": 0.881564786913474, "grad_norm": 2.3265905380249023, "learning_rate": 1.7121638681748874e-06, "loss": 2.8435, "step": 16383 }, { "epoch": 0.8816185966422729, "grad_norm": 1.9814146757125854, "learning_rate": 1.7106271006175677e-06, "loss": 3.512, "step": 16384 }, { "epoch": 0.8816724063710719, "grad_norm": 3.4037349224090576, "learning_rate": 1.7090909986078817e-06, "loss": 3.212, "step": 16385 }, { "epoch": 0.8817262160998709, "grad_norm": 2.06255841255188, "learning_rate": 1.7075555621897332e-06, "loss": 3.7512, "step": 16386 }, { "epoch": 0.8817800258286699, "grad_norm": 3.546050548553467, "learning_rate": 1.7060207914069953e-06, "loss": 3.9162, "step": 16387 }, { "epoch": 0.8818338355574687, "grad_norm": 1.7959564924240112, "learning_rate": 1.7044866863035302e-06, "loss": 4.2639, "step": 16388 }, { "epoch": 0.8818876452862677, "grad_norm": 3.235370635986328, "learning_rate": 1.7029532469231779e-06, "loss": 3.621, "step": 16389 }, { "epoch": 0.8819414550150667, "grad_norm": 2.014716386795044, "learning_rate": 1.7014204733097616e-06, "loss": 3.8169, "step": 16390 }, { "epoch": 0.8819952647438657, "grad_norm": 1.9377405643463135, "learning_rate": 1.6998883655070797e-06, "loss": 4.3014, "step": 16391 }, { "epoch": 0.8820490744726647, "grad_norm": 1.8630210161209106, "learning_rate": 1.6983569235589192e-06, "loss": 4.1328, "step": 16392 }, { "epoch": 0.8821028842014637, "grad_norm": 3.604327917098999, "learning_rate": 1.6968261475090453e-06, "loss": 3.7727, "step": 16393 }, { "epoch": 0.8821566939302626, "grad_norm": 2.2535059452056885, "learning_rate": 1.6952960374011978e-06, "loss": 3.6749, "step": 16394 }, { "epoch": 0.8822105036590615, "grad_norm": 3.8058295249938965, "learning_rate": 1.6937665932791086e-06, "loss": 3.2137, "step": 16395 }, { "epoch": 0.8822643133878605, "grad_norm": 4.892290115356445, "learning_rate": 1.69223781518649e-06, "loss": 4.1594, "step": 16396 }, { "epoch": 0.8823181231166595, "grad_norm": 3.8485004901885986, "learning_rate": 1.6907097031670204e-06, "loss": 3.1825, "step": 16397 }, { "epoch": 0.8823719328454585, "grad_norm": 2.109783411026001, "learning_rate": 1.6891822572643712e-06, "loss": 4.1981, "step": 16398 }, { "epoch": 0.8824257425742574, "grad_norm": 3.179619073867798, "learning_rate": 1.6876554775221932e-06, "loss": 3.4373, "step": 16399 }, { "epoch": 0.8824795523030564, "grad_norm": 2.543682336807251, "learning_rate": 1.6861293639841207e-06, "loss": 3.7441, "step": 16400 }, { "epoch": 0.8825333620318554, "grad_norm": 3.239267349243164, "learning_rate": 1.6846039166937638e-06, "loss": 3.8151, "step": 16401 }, { "epoch": 0.8825871717606544, "grad_norm": 3.9570326805114746, "learning_rate": 1.683079135694715e-06, "loss": 4.2552, "step": 16402 }, { "epoch": 0.8826409814894532, "grad_norm": 4.528079509735107, "learning_rate": 1.681555021030551e-06, "loss": 3.4807, "step": 16403 }, { "epoch": 0.8826947912182522, "grad_norm": 2.889256238937378, "learning_rate": 1.680031572744825e-06, "loss": 3.4998, "step": 16404 }, { "epoch": 0.8827486009470512, "grad_norm": 2.9753615856170654, "learning_rate": 1.6785087908810727e-06, "loss": 3.52, "step": 16405 }, { "epoch": 0.8828024106758502, "grad_norm": 2.666783094406128, "learning_rate": 1.676986675482814e-06, "loss": 4.1949, "step": 16406 }, { "epoch": 0.8828562204046492, "grad_norm": 3.036268949508667, "learning_rate": 1.6754652265935422e-06, "loss": 3.1691, "step": 16407 }, { "epoch": 0.8829100301334482, "grad_norm": 2.9610435962677, "learning_rate": 1.6739444442567393e-06, "loss": 3.9648, "step": 16408 }, { "epoch": 0.8829638398622471, "grad_norm": 2.583125352859497, "learning_rate": 1.6724243285158647e-06, "loss": 3.6717, "step": 16409 }, { "epoch": 0.8830176495910461, "grad_norm": 2.2976107597351074, "learning_rate": 1.6709048794143535e-06, "loss": 4.2397, "step": 16410 }, { "epoch": 0.883071459319845, "grad_norm": 2.578061819076538, "learning_rate": 1.6693860969956398e-06, "loss": 3.3258, "step": 16411 }, { "epoch": 0.883125269048644, "grad_norm": 3.3261895179748535, "learning_rate": 1.66786798130312e-06, "loss": 3.3902, "step": 16412 }, { "epoch": 0.883179078777443, "grad_norm": 3.1921255588531494, "learning_rate": 1.6663505323801759e-06, "loss": 3.9741, "step": 16413 }, { "epoch": 0.8832328885062419, "grad_norm": 5.387322425842285, "learning_rate": 1.66483375027017e-06, "loss": 3.5958, "step": 16414 }, { "epoch": 0.8832866982350409, "grad_norm": 2.6044976711273193, "learning_rate": 1.6633176350164536e-06, "loss": 3.5258, "step": 16415 }, { "epoch": 0.8833405079638399, "grad_norm": 4.318754196166992, "learning_rate": 1.6618021866623508e-06, "loss": 2.4268, "step": 16416 }, { "epoch": 0.8833943176926389, "grad_norm": 3.695369243621826, "learning_rate": 1.660287405251168e-06, "loss": 3.5112, "step": 16417 }, { "epoch": 0.8834481274214377, "grad_norm": 3.8030846118927, "learning_rate": 1.6587732908261961e-06, "loss": 4.1376, "step": 16418 }, { "epoch": 0.8835019371502367, "grad_norm": 3.7080142498016357, "learning_rate": 1.657259843430703e-06, "loss": 3.5673, "step": 16419 }, { "epoch": 0.8835557468790357, "grad_norm": 5.039783000946045, "learning_rate": 1.6557470631079402e-06, "loss": 2.836, "step": 16420 }, { "epoch": 0.8836095566078347, "grad_norm": 2.1122124195098877, "learning_rate": 1.6542349499011372e-06, "loss": 3.6877, "step": 16421 }, { "epoch": 0.8836633663366337, "grad_norm": 2.7082951068878174, "learning_rate": 1.6527235038535037e-06, "loss": 3.9795, "step": 16422 }, { "epoch": 0.8837171760654327, "grad_norm": 1.7425318956375122, "learning_rate": 1.6512127250082387e-06, "loss": 3.9281, "step": 16423 }, { "epoch": 0.8837709857942316, "grad_norm": 1.2864184379577637, "learning_rate": 1.649702613408513e-06, "loss": 3.6864, "step": 16424 }, { "epoch": 0.8838247955230306, "grad_norm": 5.364386558532715, "learning_rate": 1.6481931690974783e-06, "loss": 3.1597, "step": 16425 }, { "epoch": 0.8838786052518295, "grad_norm": 3.813383102416992, "learning_rate": 1.646684392118275e-06, "loss": 3.1785, "step": 16426 }, { "epoch": 0.8839324149806285, "grad_norm": 1.8030520677566528, "learning_rate": 1.6451762825140244e-06, "loss": 4.0598, "step": 16427 }, { "epoch": 0.8839862247094274, "grad_norm": 2.6366560459136963, "learning_rate": 1.643668840327814e-06, "loss": 4.39, "step": 16428 }, { "epoch": 0.8840400344382264, "grad_norm": 2.5026421546936035, "learning_rate": 1.6421620656027286e-06, "loss": 3.5565, "step": 16429 }, { "epoch": 0.8840938441670254, "grad_norm": 3.1314380168914795, "learning_rate": 1.6406559583818204e-06, "loss": 3.5122, "step": 16430 }, { "epoch": 0.8841476538958244, "grad_norm": 3.589073896408081, "learning_rate": 1.6391505187081407e-06, "loss": 3.8411, "step": 16431 }, { "epoch": 0.8842014636246234, "grad_norm": 1.9664201736450195, "learning_rate": 1.6376457466247054e-06, "loss": 4.1045, "step": 16432 }, { "epoch": 0.8842552733534222, "grad_norm": 4.1038618087768555, "learning_rate": 1.6361416421745184e-06, "loss": 3.1701, "step": 16433 }, { "epoch": 0.8843090830822212, "grad_norm": 3.1456403732299805, "learning_rate": 1.6346382054005627e-06, "loss": 3.9482, "step": 16434 }, { "epoch": 0.8843628928110202, "grad_norm": 2.0380055904388428, "learning_rate": 1.633135436345798e-06, "loss": 4.1884, "step": 16435 }, { "epoch": 0.8844167025398192, "grad_norm": 1.9056364297866821, "learning_rate": 1.6316333350531732e-06, "loss": 4.081, "step": 16436 }, { "epoch": 0.8844705122686182, "grad_norm": 3.0338289737701416, "learning_rate": 1.6301319015656152e-06, "loss": 3.1544, "step": 16437 }, { "epoch": 0.8845243219974172, "grad_norm": 1.9480646848678589, "learning_rate": 1.6286311359260314e-06, "loss": 3.2818, "step": 16438 }, { "epoch": 0.8845781317262161, "grad_norm": 2.1401898860931396, "learning_rate": 1.6271310381773069e-06, "loss": 4.3133, "step": 16439 }, { "epoch": 0.8846319414550151, "grad_norm": 2.0419600009918213, "learning_rate": 1.625631608362313e-06, "loss": 3.7663, "step": 16440 }, { "epoch": 0.884685751183814, "grad_norm": 1.8261228799819946, "learning_rate": 1.624132846523893e-06, "loss": 3.4083, "step": 16441 }, { "epoch": 0.884739560912613, "grad_norm": 2.811508893966675, "learning_rate": 1.6226347527048907e-06, "loss": 4.0116, "step": 16442 }, { "epoch": 0.884793370641412, "grad_norm": 3.156832695007324, "learning_rate": 1.621137326948105e-06, "loss": 3.6941, "step": 16443 }, { "epoch": 0.8848471803702109, "grad_norm": 3.282045602798462, "learning_rate": 1.6196405692963324e-06, "loss": 3.9185, "step": 16444 }, { "epoch": 0.8849009900990099, "grad_norm": 2.3146791458129883, "learning_rate": 1.618144479792344e-06, "loss": 3.8648, "step": 16445 }, { "epoch": 0.8849547998278089, "grad_norm": 2.543436288833618, "learning_rate": 1.6166490584789001e-06, "loss": 3.6682, "step": 16446 }, { "epoch": 0.8850086095566079, "grad_norm": 3.163297653198242, "learning_rate": 1.6151543053987305e-06, "loss": 3.511, "step": 16447 }, { "epoch": 0.8850624192854069, "grad_norm": 2.445789098739624, "learning_rate": 1.6136602205945566e-06, "loss": 3.8914, "step": 16448 }, { "epoch": 0.8851162290142057, "grad_norm": 3.176578998565674, "learning_rate": 1.6121668041090693e-06, "loss": 3.5897, "step": 16449 }, { "epoch": 0.8851700387430047, "grad_norm": 1.9336167573928833, "learning_rate": 1.6106740559849482e-06, "loss": 3.7874, "step": 16450 }, { "epoch": 0.8852238484718037, "grad_norm": 1.6773205995559692, "learning_rate": 1.6091819762648535e-06, "loss": 3.8883, "step": 16451 }, { "epoch": 0.8852776582006027, "grad_norm": 3.7934072017669678, "learning_rate": 1.6076905649914236e-06, "loss": 1.8803, "step": 16452 }, { "epoch": 0.8853314679294016, "grad_norm": 1.4045668840408325, "learning_rate": 1.60619982220728e-06, "loss": 3.8107, "step": 16453 }, { "epoch": 0.8853852776582006, "grad_norm": 1.9302566051483154, "learning_rate": 1.6047097479550243e-06, "loss": 3.6071, "step": 16454 }, { "epoch": 0.8854390873869996, "grad_norm": 2.484492301940918, "learning_rate": 1.603220342277237e-06, "loss": 3.6667, "step": 16455 }, { "epoch": 0.8854928971157985, "grad_norm": 3.3687877655029297, "learning_rate": 1.6017316052164805e-06, "loss": 3.2994, "step": 16456 }, { "epoch": 0.8855467068445975, "grad_norm": 3.5477454662323, "learning_rate": 1.6002435368153047e-06, "loss": 4.241, "step": 16457 }, { "epoch": 0.8856005165733964, "grad_norm": 2.9859566688537598, "learning_rate": 1.5987561371162308e-06, "loss": 3.0591, "step": 16458 }, { "epoch": 0.8856543263021954, "grad_norm": 2.5414974689483643, "learning_rate": 1.597269406161761e-06, "loss": 4.0612, "step": 16459 }, { "epoch": 0.8857081360309944, "grad_norm": 2.0585038661956787, "learning_rate": 1.5957833439943892e-06, "loss": 4.0635, "step": 16460 }, { "epoch": 0.8857619457597934, "grad_norm": 1.987746238708496, "learning_rate": 1.594297950656573e-06, "loss": 3.7884, "step": 16461 }, { "epoch": 0.8858157554885924, "grad_norm": 5.1627607345581055, "learning_rate": 1.5928132261907702e-06, "loss": 3.6686, "step": 16462 }, { "epoch": 0.8858695652173914, "grad_norm": 2.676225423812866, "learning_rate": 1.5913291706394106e-06, "loss": 3.723, "step": 16463 }, { "epoch": 0.8859233749461902, "grad_norm": 3.687925338745117, "learning_rate": 1.5898457840448994e-06, "loss": 3.3356, "step": 16464 }, { "epoch": 0.8859771846749892, "grad_norm": 2.566493272781372, "learning_rate": 1.5883630664496303e-06, "loss": 3.435, "step": 16465 }, { "epoch": 0.8860309944037882, "grad_norm": 2.229154586791992, "learning_rate": 1.5868810178959748e-06, "loss": 3.7871, "step": 16466 }, { "epoch": 0.8860848041325872, "grad_norm": 3.0630085468292236, "learning_rate": 1.5853996384262882e-06, "loss": 3.9784, "step": 16467 }, { "epoch": 0.8861386138613861, "grad_norm": 2.713473081588745, "learning_rate": 1.5839189280828975e-06, "loss": 3.4325, "step": 16468 }, { "epoch": 0.8861924235901851, "grad_norm": 5.69204568862915, "learning_rate": 1.5824388869081247e-06, "loss": 3.5023, "step": 16469 }, { "epoch": 0.8862462333189841, "grad_norm": 2.8715317249298096, "learning_rate": 1.5809595149442635e-06, "loss": 4.1407, "step": 16470 }, { "epoch": 0.8863000430477831, "grad_norm": 2.50087571144104, "learning_rate": 1.579480812233583e-06, "loss": 3.9107, "step": 16471 }, { "epoch": 0.886353852776582, "grad_norm": 2.28338623046875, "learning_rate": 1.5780027788183548e-06, "loss": 3.3812, "step": 16472 }, { "epoch": 0.8864076625053809, "grad_norm": 1.9497942924499512, "learning_rate": 1.5765254147408092e-06, "loss": 3.7643, "step": 16473 }, { "epoch": 0.8864614722341799, "grad_norm": 2.8441407680511475, "learning_rate": 1.575048720043165e-06, "loss": 4.0915, "step": 16474 }, { "epoch": 0.8865152819629789, "grad_norm": 2.468705892562866, "learning_rate": 1.5735726947676193e-06, "loss": 3.9561, "step": 16475 }, { "epoch": 0.8865690916917779, "grad_norm": 2.6844561100006104, "learning_rate": 1.5720973389563549e-06, "loss": 3.7027, "step": 16476 }, { "epoch": 0.8866229014205769, "grad_norm": 2.1568846702575684, "learning_rate": 1.5706226526515378e-06, "loss": 3.7625, "step": 16477 }, { "epoch": 0.8866767111493759, "grad_norm": 3.904468059539795, "learning_rate": 1.5691486358953094e-06, "loss": 3.8878, "step": 16478 }, { "epoch": 0.8867305208781747, "grad_norm": 3.1217477321624756, "learning_rate": 1.5676752887297892e-06, "loss": 2.7138, "step": 16479 }, { "epoch": 0.8867843306069737, "grad_norm": 3.129354953765869, "learning_rate": 1.5662026111970874e-06, "loss": 3.6126, "step": 16480 }, { "epoch": 0.8868381403357727, "grad_norm": 3.8161349296569824, "learning_rate": 1.5647306033392788e-06, "loss": 4.0692, "step": 16481 }, { "epoch": 0.8868919500645717, "grad_norm": 2.831145763397217, "learning_rate": 1.5632592651984413e-06, "loss": 4.2889, "step": 16482 }, { "epoch": 0.8869457597933706, "grad_norm": 2.9338178634643555, "learning_rate": 1.561788596816613e-06, "loss": 2.24, "step": 16483 }, { "epoch": 0.8869995695221696, "grad_norm": 3.2421255111694336, "learning_rate": 1.5603185982358271e-06, "loss": 3.5916, "step": 16484 }, { "epoch": 0.8870533792509686, "grad_norm": 2.52547550201416, "learning_rate": 1.5588492694980917e-06, "loss": 2.1617, "step": 16485 }, { "epoch": 0.8871071889797676, "grad_norm": 2.163810968399048, "learning_rate": 1.5573806106453926e-06, "loss": 3.5354, "step": 16486 }, { "epoch": 0.8871609987085665, "grad_norm": 2.294887065887451, "learning_rate": 1.5559126217197018e-06, "loss": 3.7091, "step": 16487 }, { "epoch": 0.8872148084373654, "grad_norm": 2.3808441162109375, "learning_rate": 1.5544453027629746e-06, "loss": 3.0846, "step": 16488 }, { "epoch": 0.8872686181661644, "grad_norm": 1.4976763725280762, "learning_rate": 1.5529786538171388e-06, "loss": 4.6413, "step": 16489 }, { "epoch": 0.8873224278949634, "grad_norm": 2.8406996726989746, "learning_rate": 1.5515126749241078e-06, "loss": 4.2157, "step": 16490 }, { "epoch": 0.8873762376237624, "grad_norm": 2.6907479763031006, "learning_rate": 1.550047366125773e-06, "loss": 3.4243, "step": 16491 }, { "epoch": 0.8874300473525614, "grad_norm": 3.4020984172821045, "learning_rate": 1.5485827274640097e-06, "loss": 2.7347, "step": 16492 }, { "epoch": 0.8874838570813603, "grad_norm": 2.7805817127227783, "learning_rate": 1.5471187589806785e-06, "loss": 3.8109, "step": 16493 }, { "epoch": 0.8875376668101593, "grad_norm": 4.27655029296875, "learning_rate": 1.5456554607176128e-06, "loss": 1.9702, "step": 16494 }, { "epoch": 0.8875914765389582, "grad_norm": 2.403273105621338, "learning_rate": 1.5441928327166289e-06, "loss": 3.7815, "step": 16495 }, { "epoch": 0.8876452862677572, "grad_norm": 3.511897325515747, "learning_rate": 1.542730875019524e-06, "loss": 3.5693, "step": 16496 }, { "epoch": 0.8876990959965562, "grad_norm": 2.039255380630493, "learning_rate": 1.5412695876680789e-06, "loss": 3.8724, "step": 16497 }, { "epoch": 0.8877529057253551, "grad_norm": 2.0515763759613037, "learning_rate": 1.5398089707040542e-06, "loss": 4.1635, "step": 16498 }, { "epoch": 0.8878067154541541, "grad_norm": 1.8555010557174683, "learning_rate": 1.538349024169186e-06, "loss": 4.4816, "step": 16499 }, { "epoch": 0.8878605251829531, "grad_norm": 2.383805274963379, "learning_rate": 1.5368897481051997e-06, "loss": 2.6612, "step": 16500 }, { "epoch": 0.8879143349117521, "grad_norm": 2.769057035446167, "learning_rate": 1.5354311425537948e-06, "loss": 3.4044, "step": 16501 }, { "epoch": 0.887968144640551, "grad_norm": 3.2051186561584473, "learning_rate": 1.533973207556652e-06, "loss": 3.0381, "step": 16502 }, { "epoch": 0.8880219543693499, "grad_norm": 3.090968132019043, "learning_rate": 1.5325159431554492e-06, "loss": 3.4896, "step": 16503 }, { "epoch": 0.8880757640981489, "grad_norm": 2.870154857635498, "learning_rate": 1.531059349391814e-06, "loss": 3.0013, "step": 16504 }, { "epoch": 0.8881295738269479, "grad_norm": 2.2196624279022217, "learning_rate": 1.5296034263073799e-06, "loss": 3.7565, "step": 16505 }, { "epoch": 0.8881833835557469, "grad_norm": 3.227738857269287, "learning_rate": 1.5281481739437497e-06, "loss": 3.2936, "step": 16506 }, { "epoch": 0.8882371932845459, "grad_norm": 2.845947504043579, "learning_rate": 1.5266935923425096e-06, "loss": 3.0473, "step": 16507 }, { "epoch": 0.8882910030133448, "grad_norm": 1.8414380550384521, "learning_rate": 1.5252396815452375e-06, "loss": 4.4458, "step": 16508 }, { "epoch": 0.8883448127421438, "grad_norm": 3.7691948413848877, "learning_rate": 1.5237864415934721e-06, "loss": 3.7637, "step": 16509 }, { "epoch": 0.8883986224709427, "grad_norm": 3.94630765914917, "learning_rate": 1.52233387252875e-06, "loss": 3.251, "step": 16510 }, { "epoch": 0.8884524321997417, "grad_norm": 3.125056028366089, "learning_rate": 1.5208819743925796e-06, "loss": 3.4056, "step": 16511 }, { "epoch": 0.8885062419285407, "grad_norm": 2.2329695224761963, "learning_rate": 1.5194307472264442e-06, "loss": 3.9053, "step": 16512 }, { "epoch": 0.8885600516573396, "grad_norm": 3.5336947441101074, "learning_rate": 1.5179801910718245e-06, "loss": 3.2891, "step": 16513 }, { "epoch": 0.8886138613861386, "grad_norm": 3.390193223953247, "learning_rate": 1.5165303059701735e-06, "loss": 4.2619, "step": 16514 }, { "epoch": 0.8886676711149376, "grad_norm": 2.7226879596710205, "learning_rate": 1.5150810919629249e-06, "loss": 3.4008, "step": 16515 }, { "epoch": 0.8887214808437366, "grad_norm": 1.6939400434494019, "learning_rate": 1.51363254909149e-06, "loss": 3.8271, "step": 16516 }, { "epoch": 0.8887752905725355, "grad_norm": 3.5907740592956543, "learning_rate": 1.512184677397266e-06, "loss": 3.8204, "step": 16517 }, { "epoch": 0.8888291003013344, "grad_norm": 3.443300724029541, "learning_rate": 1.5107374769216282e-06, "loss": 3.6114, "step": 16518 }, { "epoch": 0.8888829100301334, "grad_norm": 4.101982116699219, "learning_rate": 1.5092909477059352e-06, "loss": 3.2831, "step": 16519 }, { "epoch": 0.8889367197589324, "grad_norm": 3.290656328201294, "learning_rate": 1.5078450897915264e-06, "loss": 3.4426, "step": 16520 }, { "epoch": 0.8889905294877314, "grad_norm": 3.1228742599487305, "learning_rate": 1.5063999032197157e-06, "loss": 3.6803, "step": 16521 }, { "epoch": 0.8890443392165304, "grad_norm": 2.8160219192504883, "learning_rate": 1.5049553880318062e-06, "loss": 3.769, "step": 16522 }, { "epoch": 0.8890981489453293, "grad_norm": 3.4759931564331055, "learning_rate": 1.5035115442690734e-06, "loss": 3.9876, "step": 16523 }, { "epoch": 0.8891519586741283, "grad_norm": 4.636040687561035, "learning_rate": 1.5020683719727868e-06, "loss": 3.7077, "step": 16524 }, { "epoch": 0.8892057684029272, "grad_norm": 3.9065537452697754, "learning_rate": 1.5006258711841858e-06, "loss": 3.281, "step": 16525 }, { "epoch": 0.8892595781317262, "grad_norm": 2.182539224624634, "learning_rate": 1.499184041944493e-06, "loss": 3.4142, "step": 16526 }, { "epoch": 0.8893133878605252, "grad_norm": 2.0715909004211426, "learning_rate": 1.4977428842949032e-06, "loss": 3.8062, "step": 16527 }, { "epoch": 0.8893671975893241, "grad_norm": 1.9285175800323486, "learning_rate": 1.4963023982766138e-06, "loss": 3.784, "step": 16528 }, { "epoch": 0.8894210073181231, "grad_norm": 3.0305869579315186, "learning_rate": 1.4948625839307812e-06, "loss": 3.6923, "step": 16529 }, { "epoch": 0.8894748170469221, "grad_norm": 2.700509786605835, "learning_rate": 1.4934234412985581e-06, "loss": 3.2718, "step": 16530 }, { "epoch": 0.8895286267757211, "grad_norm": 3.5662686824798584, "learning_rate": 1.4919849704210647e-06, "loss": 3.4286, "step": 16531 }, { "epoch": 0.8895824365045201, "grad_norm": 2.58833384513855, "learning_rate": 1.4905471713394125e-06, "loss": 3.5557, "step": 16532 }, { "epoch": 0.8896362462333189, "grad_norm": 2.0580532550811768, "learning_rate": 1.4891100440946854e-06, "loss": 3.9899, "step": 16533 }, { "epoch": 0.8896900559621179, "grad_norm": 2.4612114429473877, "learning_rate": 1.4876735887279641e-06, "loss": 3.8073, "step": 16534 }, { "epoch": 0.8897438656909169, "grad_norm": 4.008347034454346, "learning_rate": 1.4862378052802884e-06, "loss": 3.2837, "step": 16535 }, { "epoch": 0.8897976754197159, "grad_norm": 4.005817413330078, "learning_rate": 1.4848026937926918e-06, "loss": 3.2037, "step": 16536 }, { "epoch": 0.8898514851485149, "grad_norm": 2.22103214263916, "learning_rate": 1.4833682543061832e-06, "loss": 3.5111, "step": 16537 }, { "epoch": 0.8899052948773138, "grad_norm": 3.2561681270599365, "learning_rate": 1.4819344868617551e-06, "loss": 3.0099, "step": 16538 }, { "epoch": 0.8899591046061128, "grad_norm": 4.2135210037231445, "learning_rate": 1.4805013915003857e-06, "loss": 3.1699, "step": 16539 }, { "epoch": 0.8900129143349117, "grad_norm": 2.8025999069213867, "learning_rate": 1.4790689682630281e-06, "loss": 3.3049, "step": 16540 }, { "epoch": 0.8900667240637107, "grad_norm": 3.336214303970337, "learning_rate": 1.4776372171906195e-06, "loss": 4.3628, "step": 16541 }, { "epoch": 0.8901205337925097, "grad_norm": 1.6994861364364624, "learning_rate": 1.4762061383240682e-06, "loss": 3.8862, "step": 16542 }, { "epoch": 0.8901743435213086, "grad_norm": 2.62359881401062, "learning_rate": 1.4747757317042698e-06, "loss": 4.1316, "step": 16543 }, { "epoch": 0.8902281532501076, "grad_norm": 2.9008944034576416, "learning_rate": 1.4733459973721082e-06, "loss": 2.6682, "step": 16544 }, { "epoch": 0.8902819629789066, "grad_norm": 3.8998703956604004, "learning_rate": 1.4719169353684392e-06, "loss": 3.3116, "step": 16545 }, { "epoch": 0.8903357727077056, "grad_norm": 3.9388718605041504, "learning_rate": 1.4704885457341e-06, "loss": 3.6929, "step": 16546 }, { "epoch": 0.8903895824365046, "grad_norm": 3.929818868637085, "learning_rate": 1.4690608285099132e-06, "loss": 4.0202, "step": 16547 }, { "epoch": 0.8904433921653034, "grad_norm": 3.615227699279785, "learning_rate": 1.4676337837366743e-06, "loss": 3.9856, "step": 16548 }, { "epoch": 0.8904972018941024, "grad_norm": 4.93194055557251, "learning_rate": 1.46620741145517e-06, "loss": 3.9537, "step": 16549 }, { "epoch": 0.8905510116229014, "grad_norm": 1.7900649309158325, "learning_rate": 1.464781711706159e-06, "loss": 4.2045, "step": 16550 }, { "epoch": 0.8906048213517004, "grad_norm": 2.2199208736419678, "learning_rate": 1.4633566845303841e-06, "loss": 4.1131, "step": 16551 }, { "epoch": 0.8906586310804994, "grad_norm": 3.2374274730682373, "learning_rate": 1.4619323299685684e-06, "loss": 3.1365, "step": 16552 }, { "epoch": 0.8907124408092983, "grad_norm": 3.074883222579956, "learning_rate": 1.4605086480614178e-06, "loss": 4.1328, "step": 16553 }, { "epoch": 0.8907662505380973, "grad_norm": 3.005598306655884, "learning_rate": 1.459085638849611e-06, "loss": 3.6921, "step": 16554 }, { "epoch": 0.8908200602668963, "grad_norm": 1.9194281101226807, "learning_rate": 1.457663302373824e-06, "loss": 3.6406, "step": 16555 }, { "epoch": 0.8908738699956952, "grad_norm": 2.611069679260254, "learning_rate": 1.456241638674699e-06, "loss": 3.0398, "step": 16556 }, { "epoch": 0.8909276797244942, "grad_norm": 4.396774768829346, "learning_rate": 1.454820647792865e-06, "loss": 3.1766, "step": 16557 }, { "epoch": 0.8909814894532931, "grad_norm": 3.51877498626709, "learning_rate": 1.4534003297689197e-06, "loss": 3.8078, "step": 16558 }, { "epoch": 0.8910352991820921, "grad_norm": 2.630533456802368, "learning_rate": 1.4519806846434668e-06, "loss": 3.5942, "step": 16559 }, { "epoch": 0.8910891089108911, "grad_norm": 1.9603854417800903, "learning_rate": 1.450561712457066e-06, "loss": 3.9239, "step": 16560 }, { "epoch": 0.8911429186396901, "grad_norm": 3.3783669471740723, "learning_rate": 1.4491434132502729e-06, "loss": 3.2698, "step": 16561 }, { "epoch": 0.8911967283684891, "grad_norm": 2.892760992050171, "learning_rate": 1.4477257870636168e-06, "loss": 4.0545, "step": 16562 }, { "epoch": 0.8912505380972879, "grad_norm": 2.6892106533050537, "learning_rate": 1.4463088339376068e-06, "loss": 3.97, "step": 16563 }, { "epoch": 0.8913043478260869, "grad_norm": 2.7729992866516113, "learning_rate": 1.4448925539127412e-06, "loss": 4.1952, "step": 16564 }, { "epoch": 0.8913581575548859, "grad_norm": 4.255680084228516, "learning_rate": 1.44347694702949e-06, "loss": 3.1566, "step": 16565 }, { "epoch": 0.8914119672836849, "grad_norm": 2.270599126815796, "learning_rate": 1.4420620133283075e-06, "loss": 4.5692, "step": 16566 }, { "epoch": 0.8914657770124839, "grad_norm": 1.5878236293792725, "learning_rate": 1.4406477528496276e-06, "loss": 4.2139, "step": 16567 }, { "epoch": 0.8915195867412828, "grad_norm": 1.897399663925171, "learning_rate": 1.4392341656338708e-06, "loss": 4.1798, "step": 16568 }, { "epoch": 0.8915733964700818, "grad_norm": 2.1350321769714355, "learning_rate": 1.4378212517214247e-06, "loss": 3.5565, "step": 16569 }, { "epoch": 0.8916272061988808, "grad_norm": 4.715610027313232, "learning_rate": 1.4364090111526784e-06, "loss": 2.3397, "step": 16570 }, { "epoch": 0.8916810159276797, "grad_norm": 1.3486506938934326, "learning_rate": 1.434997443967981e-06, "loss": 4.3751, "step": 16571 }, { "epoch": 0.8917348256564787, "grad_norm": 1.993151068687439, "learning_rate": 1.43358655020768e-06, "loss": 3.3492, "step": 16572 }, { "epoch": 0.8917886353852776, "grad_norm": 2.266570568084717, "learning_rate": 1.4321763299120855e-06, "loss": 3.2825, "step": 16573 }, { "epoch": 0.8918424451140766, "grad_norm": 4.017113208770752, "learning_rate": 1.4307667831214982e-06, "loss": 3.4029, "step": 16574 }, { "epoch": 0.8918962548428756, "grad_norm": 2.0994889736175537, "learning_rate": 1.4293579098762055e-06, "loss": 4.1345, "step": 16575 }, { "epoch": 0.8919500645716746, "grad_norm": 2.628305196762085, "learning_rate": 1.427949710216464e-06, "loss": 3.7295, "step": 16576 }, { "epoch": 0.8920038743004736, "grad_norm": 4.843989849090576, "learning_rate": 1.4265421841825222e-06, "loss": 4.4507, "step": 16577 }, { "epoch": 0.8920576840292725, "grad_norm": 2.274293899536133, "learning_rate": 1.4251353318145976e-06, "loss": 3.8064, "step": 16578 }, { "epoch": 0.8921114937580714, "grad_norm": 1.6227076053619385, "learning_rate": 1.4237291531528945e-06, "loss": 3.8528, "step": 16579 }, { "epoch": 0.8921653034868704, "grad_norm": 2.0114998817443848, "learning_rate": 1.4223236482376028e-06, "loss": 4.421, "step": 16580 }, { "epoch": 0.8922191132156694, "grad_norm": 2.290963888168335, "learning_rate": 1.4209188171088823e-06, "loss": 3.1018, "step": 16581 }, { "epoch": 0.8922729229444684, "grad_norm": 1.8547452688217163, "learning_rate": 1.4195146598068836e-06, "loss": 4.1466, "step": 16582 }, { "epoch": 0.8923267326732673, "grad_norm": 3.875645399093628, "learning_rate": 1.418111176371731e-06, "loss": 3.7712, "step": 16583 }, { "epoch": 0.8923805424020663, "grad_norm": 2.192556142807007, "learning_rate": 1.4167083668435332e-06, "loss": 4.1639, "step": 16584 }, { "epoch": 0.8924343521308653, "grad_norm": 1.7733877897262573, "learning_rate": 1.4153062312623728e-06, "loss": 4.4208, "step": 16585 }, { "epoch": 0.8924881618596642, "grad_norm": 2.7406768798828125, "learning_rate": 1.413904769668331e-06, "loss": 3.2676, "step": 16586 }, { "epoch": 0.8925419715884632, "grad_norm": 3.2357704639434814, "learning_rate": 1.4125039821014568e-06, "loss": 3.8264, "step": 16587 }, { "epoch": 0.8925957813172621, "grad_norm": 3.2729251384735107, "learning_rate": 1.4111038686017707e-06, "loss": 3.7005, "step": 16588 }, { "epoch": 0.8926495910460611, "grad_norm": 2.209820032119751, "learning_rate": 1.4097044292092854e-06, "loss": 4.417, "step": 16589 }, { "epoch": 0.8927034007748601, "grad_norm": 3.6863417625427246, "learning_rate": 1.4083056639639991e-06, "loss": 4.2202, "step": 16590 }, { "epoch": 0.8927572105036591, "grad_norm": 3.488321542739868, "learning_rate": 1.4069075729058856e-06, "loss": 3.8861, "step": 16591 }, { "epoch": 0.8928110202324581, "grad_norm": 2.255706787109375, "learning_rate": 1.4055101560748935e-06, "loss": 4.0946, "step": 16592 }, { "epoch": 0.892864829961257, "grad_norm": 3.4966366291046143, "learning_rate": 1.404113413510963e-06, "loss": 3.4563, "step": 16593 }, { "epoch": 0.8929186396900559, "grad_norm": 4.254940986633301, "learning_rate": 1.402717345254001e-06, "loss": 2.7208, "step": 16594 }, { "epoch": 0.8929724494188549, "grad_norm": 1.631209373474121, "learning_rate": 1.4013219513439118e-06, "loss": 4.1051, "step": 16595 }, { "epoch": 0.8930262591476539, "grad_norm": 3.032315731048584, "learning_rate": 1.3999272318205665e-06, "loss": 3.3578, "step": 16596 }, { "epoch": 0.8930800688764529, "grad_norm": 1.6466354131698608, "learning_rate": 1.3985331867238243e-06, "loss": 4.405, "step": 16597 }, { "epoch": 0.8931338786052518, "grad_norm": 3.3757591247558594, "learning_rate": 1.3971398160935234e-06, "loss": 4.1143, "step": 16598 }, { "epoch": 0.8931876883340508, "grad_norm": 2.440340995788574, "learning_rate": 1.3957471199694817e-06, "loss": 3.9262, "step": 16599 }, { "epoch": 0.8932414980628498, "grad_norm": 4.230158805847168, "learning_rate": 1.394355098391495e-06, "loss": 3.3645, "step": 16600 }, { "epoch": 0.8932953077916488, "grad_norm": 3.1773016452789307, "learning_rate": 1.3929637513993537e-06, "loss": 3.4556, "step": 16601 }, { "epoch": 0.8933491175204477, "grad_norm": 2.067028045654297, "learning_rate": 1.3915730790328124e-06, "loss": 3.9821, "step": 16602 }, { "epoch": 0.8934029272492466, "grad_norm": 2.3640894889831543, "learning_rate": 1.3901830813316142e-06, "loss": 3.9472, "step": 16603 }, { "epoch": 0.8934567369780456, "grad_norm": 3.33280348777771, "learning_rate": 1.3887937583354799e-06, "loss": 3.2559, "step": 16604 }, { "epoch": 0.8935105467068446, "grad_norm": 2.106147050857544, "learning_rate": 1.3874051100841084e-06, "loss": 3.7322, "step": 16605 }, { "epoch": 0.8935643564356436, "grad_norm": 2.4185431003570557, "learning_rate": 1.3860171366171932e-06, "loss": 4.3846, "step": 16606 }, { "epoch": 0.8936181661644426, "grad_norm": 3.465439796447754, "learning_rate": 1.3846298379743938e-06, "loss": 3.0207, "step": 16607 }, { "epoch": 0.8936719758932415, "grad_norm": 3.55111026763916, "learning_rate": 1.3832432141953538e-06, "loss": 4.547, "step": 16608 }, { "epoch": 0.8937257856220404, "grad_norm": 2.41139817237854, "learning_rate": 1.3818572653197026e-06, "loss": 3.208, "step": 16609 }, { "epoch": 0.8937795953508394, "grad_norm": 2.1998543739318848, "learning_rate": 1.3804719913870474e-06, "loss": 4.1006, "step": 16610 }, { "epoch": 0.8938334050796384, "grad_norm": 2.404296875, "learning_rate": 1.3790873924369702e-06, "loss": 3.1711, "step": 16611 }, { "epoch": 0.8938872148084374, "grad_norm": 1.5373923778533936, "learning_rate": 1.377703468509045e-06, "loss": 4.1152, "step": 16612 }, { "epoch": 0.8939410245372363, "grad_norm": 3.4721779823303223, "learning_rate": 1.3763202196428155e-06, "loss": 3.3997, "step": 16613 }, { "epoch": 0.8939948342660353, "grad_norm": 3.7336063385009766, "learning_rate": 1.3749376458778163e-06, "loss": 3.6909, "step": 16614 }, { "epoch": 0.8940486439948343, "grad_norm": 4.921079635620117, "learning_rate": 1.3735557472535548e-06, "loss": 3.2436, "step": 16615 }, { "epoch": 0.8941024537236333, "grad_norm": 2.123847484588623, "learning_rate": 1.3721745238095191e-06, "loss": 4.1665, "step": 16616 }, { "epoch": 0.8941562634524322, "grad_norm": 1.495810627937317, "learning_rate": 1.3707939755851856e-06, "loss": 4.2079, "step": 16617 }, { "epoch": 0.8942100731812311, "grad_norm": 2.5930850505828857, "learning_rate": 1.369414102620012e-06, "loss": 3.4059, "step": 16618 }, { "epoch": 0.8942638829100301, "grad_norm": 2.8979029655456543, "learning_rate": 1.368034904953419e-06, "loss": 3.5856, "step": 16619 }, { "epoch": 0.8943176926388291, "grad_norm": 2.374514579772949, "learning_rate": 1.366656382624823e-06, "loss": 3.7973, "step": 16620 }, { "epoch": 0.8943715023676281, "grad_norm": 2.0255239009857178, "learning_rate": 1.3652785356736225e-06, "loss": 3.2434, "step": 16621 }, { "epoch": 0.8944253120964271, "grad_norm": 4.148611545562744, "learning_rate": 1.3639013641391945e-06, "loss": 3.0671, "step": 16622 }, { "epoch": 0.894479121825226, "grad_norm": 2.7765419483184814, "learning_rate": 1.362524868060891e-06, "loss": 3.7198, "step": 16623 }, { "epoch": 0.8945329315540249, "grad_norm": 1.846591830253601, "learning_rate": 1.3611490474780496e-06, "loss": 4.3717, "step": 16624 }, { "epoch": 0.8945867412828239, "grad_norm": 2.5017247200012207, "learning_rate": 1.3597739024299866e-06, "loss": 2.6241, "step": 16625 }, { "epoch": 0.8946405510116229, "grad_norm": 2.270634412765503, "learning_rate": 1.3583994329560006e-06, "loss": 3.4134, "step": 16626 }, { "epoch": 0.8946943607404219, "grad_norm": 2.7061445713043213, "learning_rate": 1.3570256390953717e-06, "loss": 3.9718, "step": 16627 }, { "epoch": 0.8947481704692208, "grad_norm": 2.8166797161102295, "learning_rate": 1.3556525208873571e-06, "loss": 3.2376, "step": 16628 }, { "epoch": 0.8948019801980198, "grad_norm": 2.98046612739563, "learning_rate": 1.3542800783711978e-06, "loss": 3.8094, "step": 16629 }, { "epoch": 0.8948557899268188, "grad_norm": 3.09566593170166, "learning_rate": 1.3529083115861125e-06, "loss": 3.5339, "step": 16630 }, { "epoch": 0.8949095996556178, "grad_norm": 3.7827088832855225, "learning_rate": 1.3515372205713028e-06, "loss": 3.1896, "step": 16631 }, { "epoch": 0.8949634093844167, "grad_norm": 2.440211534500122, "learning_rate": 1.3501668053659572e-06, "loss": 4.1145, "step": 16632 }, { "epoch": 0.8950172191132156, "grad_norm": 1.253645420074463, "learning_rate": 1.3487970660092359e-06, "loss": 4.3465, "step": 16633 }, { "epoch": 0.8950710288420146, "grad_norm": 4.54675817489624, "learning_rate": 1.347428002540277e-06, "loss": 3.1081, "step": 16634 }, { "epoch": 0.8951248385708136, "grad_norm": 2.259748935699463, "learning_rate": 1.3460596149982075e-06, "loss": 3.3919, "step": 16635 }, { "epoch": 0.8951786482996126, "grad_norm": 2.8132803440093994, "learning_rate": 1.3446919034221267e-06, "loss": 3.8008, "step": 16636 }, { "epoch": 0.8952324580284116, "grad_norm": 2.985311508178711, "learning_rate": 1.343324867851134e-06, "loss": 3.9949, "step": 16637 }, { "epoch": 0.8952862677572105, "grad_norm": 3.433690071105957, "learning_rate": 1.341958508324284e-06, "loss": 3.9725, "step": 16638 }, { "epoch": 0.8953400774860095, "grad_norm": 2.8583791255950928, "learning_rate": 1.3405928248806294e-06, "loss": 3.9181, "step": 16639 }, { "epoch": 0.8953938872148084, "grad_norm": 2.0604209899902344, "learning_rate": 1.3392278175591938e-06, "loss": 3.206, "step": 16640 }, { "epoch": 0.8954476969436074, "grad_norm": 3.302908420562744, "learning_rate": 1.3378634863989881e-06, "loss": 3.0585, "step": 16641 }, { "epoch": 0.8955015066724064, "grad_norm": 2.6082024574279785, "learning_rate": 1.3364998314390004e-06, "loss": 3.947, "step": 16642 }, { "epoch": 0.8955553164012053, "grad_norm": 1.2631736993789673, "learning_rate": 1.3351368527181997e-06, "loss": 4.1274, "step": 16643 }, { "epoch": 0.8956091261300043, "grad_norm": 2.8875505924224854, "learning_rate": 1.3337745502755378e-06, "loss": 3.1629, "step": 16644 }, { "epoch": 0.8956629358588033, "grad_norm": 2.853590488433838, "learning_rate": 1.332412924149945e-06, "loss": 3.9087, "step": 16645 }, { "epoch": 0.8957167455876023, "grad_norm": 3.4638566970825195, "learning_rate": 1.331051974380329e-06, "loss": 3.4529, "step": 16646 }, { "epoch": 0.8957705553164012, "grad_norm": 3.7663824558258057, "learning_rate": 1.3296917010055864e-06, "loss": 3.3758, "step": 16647 }, { "epoch": 0.8958243650452001, "grad_norm": 3.039767265319824, "learning_rate": 1.3283321040645946e-06, "loss": 3.4549, "step": 16648 }, { "epoch": 0.8958781747739991, "grad_norm": 3.3563263416290283, "learning_rate": 1.3269731835961975e-06, "loss": 3.5122, "step": 16649 }, { "epoch": 0.8959319845027981, "grad_norm": 2.493326187133789, "learning_rate": 1.3256149396392358e-06, "loss": 3.9904, "step": 16650 }, { "epoch": 0.8959857942315971, "grad_norm": 2.6588523387908936, "learning_rate": 1.3242573722325151e-06, "loss": 3.8648, "step": 16651 }, { "epoch": 0.8960396039603961, "grad_norm": 2.154472827911377, "learning_rate": 1.322900481414846e-06, "loss": 4.1635, "step": 16652 }, { "epoch": 0.896093413689195, "grad_norm": 3.5501067638397217, "learning_rate": 1.3215442672249973e-06, "loss": 3.8462, "step": 16653 }, { "epoch": 0.896147223417994, "grad_norm": 4.5376105308532715, "learning_rate": 1.320188729701724e-06, "loss": 4.1901, "step": 16654 }, { "epoch": 0.8962010331467929, "grad_norm": 3.282684087753296, "learning_rate": 1.3188338688837648e-06, "loss": 4.0853, "step": 16655 }, { "epoch": 0.8962548428755919, "grad_norm": 2.8839988708496094, "learning_rate": 1.3174796848098415e-06, "loss": 3.306, "step": 16656 }, { "epoch": 0.8963086526043909, "grad_norm": 3.512467622756958, "learning_rate": 1.3161261775186478e-06, "loss": 3.3072, "step": 16657 }, { "epoch": 0.8963624623331898, "grad_norm": 2.7026336193084717, "learning_rate": 1.3147733470488671e-06, "loss": 3.5295, "step": 16658 }, { "epoch": 0.8964162720619888, "grad_norm": 2.0526578426361084, "learning_rate": 1.313421193439157e-06, "loss": 4.3519, "step": 16659 }, { "epoch": 0.8964700817907878, "grad_norm": 2.7903218269348145, "learning_rate": 1.312069716728162e-06, "loss": 3.804, "step": 16660 }, { "epoch": 0.8965238915195868, "grad_norm": 1.7812401056289673, "learning_rate": 1.310718916954501e-06, "loss": 4.4488, "step": 16661 }, { "epoch": 0.8965777012483858, "grad_norm": 3.781589984893799, "learning_rate": 1.3093687941567705e-06, "loss": 3.2499, "step": 16662 }, { "epoch": 0.8966315109771846, "grad_norm": 3.040976047515869, "learning_rate": 1.3080193483735654e-06, "loss": 3.208, "step": 16663 }, { "epoch": 0.8966853207059836, "grad_norm": 3.107191324234009, "learning_rate": 1.3066705796434458e-06, "loss": 4.4828, "step": 16664 }, { "epoch": 0.8967391304347826, "grad_norm": 3.20876407623291, "learning_rate": 1.3053224880049508e-06, "loss": 1.879, "step": 16665 }, { "epoch": 0.8967929401635816, "grad_norm": 2.5811941623687744, "learning_rate": 1.3039750734966078e-06, "loss": 4.1619, "step": 16666 }, { "epoch": 0.8968467498923806, "grad_norm": 2.18595027923584, "learning_rate": 1.3026283361569191e-06, "loss": 3.9769, "step": 16667 }, { "epoch": 0.8969005596211795, "grad_norm": 1.5337234735488892, "learning_rate": 1.3012822760243793e-06, "loss": 4.4331, "step": 16668 }, { "epoch": 0.8969543693499785, "grad_norm": 1.3428829908370972, "learning_rate": 1.299936893137446e-06, "loss": 4.618, "step": 16669 }, { "epoch": 0.8970081790787774, "grad_norm": 2.3891279697418213, "learning_rate": 1.2985921875345725e-06, "loss": 3.6378, "step": 16670 }, { "epoch": 0.8970619888075764, "grad_norm": 1.9528828859329224, "learning_rate": 1.2972481592541858e-06, "loss": 3.5172, "step": 16671 }, { "epoch": 0.8971157985363754, "grad_norm": 2.3293440341949463, "learning_rate": 1.295904808334694e-06, "loss": 3.9306, "step": 16672 }, { "epoch": 0.8971696082651743, "grad_norm": 2.392761468887329, "learning_rate": 1.2945621348144837e-06, "loss": 3.4432, "step": 16673 }, { "epoch": 0.8972234179939733, "grad_norm": 2.88395094871521, "learning_rate": 1.2932201387319292e-06, "loss": 3.9587, "step": 16674 }, { "epoch": 0.8972772277227723, "grad_norm": 3.6624505519866943, "learning_rate": 1.2918788201253807e-06, "loss": 4.161, "step": 16675 }, { "epoch": 0.8973310374515713, "grad_norm": 3.3064446449279785, "learning_rate": 1.2905381790331654e-06, "loss": 3.3652, "step": 16676 }, { "epoch": 0.8973848471803703, "grad_norm": 4.311639785766602, "learning_rate": 1.2891982154935977e-06, "loss": 2.4941, "step": 16677 }, { "epoch": 0.8974386569091691, "grad_norm": 3.4117648601531982, "learning_rate": 1.2878589295449717e-06, "loss": 3.3319, "step": 16678 }, { "epoch": 0.8974924666379681, "grad_norm": 3.1094582080841064, "learning_rate": 1.2865203212255621e-06, "loss": 3.6535, "step": 16679 }, { "epoch": 0.8975462763667671, "grad_norm": 2.4242289066314697, "learning_rate": 1.2851823905736192e-06, "loss": 4.5161, "step": 16680 }, { "epoch": 0.8976000860955661, "grad_norm": 2.9442291259765625, "learning_rate": 1.2838451376273764e-06, "loss": 2.5822, "step": 16681 }, { "epoch": 0.8976538958243651, "grad_norm": 2.5879526138305664, "learning_rate": 1.2825085624250472e-06, "loss": 3.9428, "step": 16682 }, { "epoch": 0.897707705553164, "grad_norm": 2.594769239425659, "learning_rate": 1.2811726650048344e-06, "loss": 3.6527, "step": 16683 }, { "epoch": 0.897761515281963, "grad_norm": 2.076432228088379, "learning_rate": 1.2798374454049105e-06, "loss": 4.1402, "step": 16684 }, { "epoch": 0.897815325010762, "grad_norm": 1.2495876550674438, "learning_rate": 1.2785029036634311e-06, "loss": 4.3568, "step": 16685 }, { "epoch": 0.8978691347395609, "grad_norm": 1.9202113151550293, "learning_rate": 1.2771690398185375e-06, "loss": 4.2403, "step": 16686 }, { "epoch": 0.8979229444683599, "grad_norm": 4.487907886505127, "learning_rate": 1.275835853908347e-06, "loss": 3.7516, "step": 16687 }, { "epoch": 0.8979767541971588, "grad_norm": 3.449333667755127, "learning_rate": 1.2745033459709539e-06, "loss": 3.6758, "step": 16688 }, { "epoch": 0.8980305639259578, "grad_norm": 2.7004237174987793, "learning_rate": 1.273171516044444e-06, "loss": 3.8158, "step": 16689 }, { "epoch": 0.8980843736547568, "grad_norm": 1.3145508766174316, "learning_rate": 1.2718403641668737e-06, "loss": 3.88, "step": 16690 }, { "epoch": 0.8981381833835558, "grad_norm": 3.5399324893951416, "learning_rate": 1.270509890376284e-06, "loss": 3.8542, "step": 16691 }, { "epoch": 0.8981919931123548, "grad_norm": 3.364193916320801, "learning_rate": 1.2691800947106952e-06, "loss": 4.1734, "step": 16692 }, { "epoch": 0.8982458028411536, "grad_norm": 3.64436936378479, "learning_rate": 1.2678509772081098e-06, "loss": 3.725, "step": 16693 }, { "epoch": 0.8982996125699526, "grad_norm": 2.414562225341797, "learning_rate": 1.266522537906517e-06, "loss": 3.6387, "step": 16694 }, { "epoch": 0.8983534222987516, "grad_norm": 4.606238842010498, "learning_rate": 1.2651947768438727e-06, "loss": 3.4031, "step": 16695 }, { "epoch": 0.8984072320275506, "grad_norm": 3.1172871589660645, "learning_rate": 1.2638676940581213e-06, "loss": 3.5182, "step": 16696 }, { "epoch": 0.8984610417563496, "grad_norm": 3.2802834510803223, "learning_rate": 1.2625412895871907e-06, "loss": 3.4114, "step": 16697 }, { "epoch": 0.8985148514851485, "grad_norm": 4.9047346115112305, "learning_rate": 1.2612155634689788e-06, "loss": 4.0395, "step": 16698 }, { "epoch": 0.8985686612139475, "grad_norm": 2.5643184185028076, "learning_rate": 1.259890515741377e-06, "loss": 3.7844, "step": 16699 }, { "epoch": 0.8986224709427465, "grad_norm": 4.3166351318359375, "learning_rate": 1.2585661464422555e-06, "loss": 3.6206, "step": 16700 }, { "epoch": 0.8986762806715454, "grad_norm": 3.248413324356079, "learning_rate": 1.257242455609453e-06, "loss": 3.3243, "step": 16701 }, { "epoch": 0.8987300904003444, "grad_norm": 3.351223945617676, "learning_rate": 1.2559194432808035e-06, "loss": 3.8383, "step": 16702 }, { "epoch": 0.8987839001291433, "grad_norm": 1.9075390100479126, "learning_rate": 1.2545971094941101e-06, "loss": 4.0911, "step": 16703 }, { "epoch": 0.8988377098579423, "grad_norm": 2.167346715927124, "learning_rate": 1.2532754542871643e-06, "loss": 3.2239, "step": 16704 }, { "epoch": 0.8988915195867413, "grad_norm": 2.177521228790283, "learning_rate": 1.2519544776977338e-06, "loss": 3.3254, "step": 16705 }, { "epoch": 0.8989453293155403, "grad_norm": 2.2802863121032715, "learning_rate": 1.2506341797635711e-06, "loss": 3.4151, "step": 16706 }, { "epoch": 0.8989991390443393, "grad_norm": 2.0363035202026367, "learning_rate": 1.249314560522405e-06, "loss": 3.4395, "step": 16707 }, { "epoch": 0.8990529487731382, "grad_norm": 5.143031120300293, "learning_rate": 1.2479956200119435e-06, "loss": 3.498, "step": 16708 }, { "epoch": 0.8991067585019371, "grad_norm": 3.52709698677063, "learning_rate": 1.246677358269885e-06, "loss": 3.6235, "step": 16709 }, { "epoch": 0.8991605682307361, "grad_norm": 2.2114391326904297, "learning_rate": 1.2453597753339013e-06, "loss": 4.0828, "step": 16710 }, { "epoch": 0.8992143779595351, "grad_norm": 3.169046640396118, "learning_rate": 1.2440428712416408e-06, "loss": 4.1157, "step": 16711 }, { "epoch": 0.899268187688334, "grad_norm": 1.3757493495941162, "learning_rate": 1.2427266460307368e-06, "loss": 4.5621, "step": 16712 }, { "epoch": 0.899321997417133, "grad_norm": 3.7800631523132324, "learning_rate": 1.241411099738804e-06, "loss": 2.3101, "step": 16713 }, { "epoch": 0.899375807145932, "grad_norm": 4.13539981842041, "learning_rate": 1.2400962324034427e-06, "loss": 3.424, "step": 16714 }, { "epoch": 0.899429616874731, "grad_norm": 2.8792927265167236, "learning_rate": 1.2387820440622256e-06, "loss": 3.2246, "step": 16715 }, { "epoch": 0.8994834266035299, "grad_norm": 1.4891283512115479, "learning_rate": 1.2374685347527031e-06, "loss": 3.8247, "step": 16716 }, { "epoch": 0.8995372363323288, "grad_norm": 2.61332106590271, "learning_rate": 1.2361557045124233e-06, "loss": 4.5526, "step": 16717 }, { "epoch": 0.8995910460611278, "grad_norm": 2.93103289604187, "learning_rate": 1.2348435533788894e-06, "loss": 3.3953, "step": 16718 }, { "epoch": 0.8996448557899268, "grad_norm": 3.1666202545166016, "learning_rate": 1.2335320813896073e-06, "loss": 3.4833, "step": 16719 }, { "epoch": 0.8996986655187258, "grad_norm": 3.3076469898223877, "learning_rate": 1.2322212885820556e-06, "loss": 3.0619, "step": 16720 }, { "epoch": 0.8997524752475248, "grad_norm": 1.3772313594818115, "learning_rate": 1.2309111749936902e-06, "loss": 4.3345, "step": 16721 }, { "epoch": 0.8998062849763238, "grad_norm": 1.6887422800064087, "learning_rate": 1.2296017406619537e-06, "loss": 4.3626, "step": 16722 }, { "epoch": 0.8998600947051227, "grad_norm": 3.989063024520874, "learning_rate": 1.228292985624263e-06, "loss": 3.4448, "step": 16723 }, { "epoch": 0.8999139044339216, "grad_norm": 3.8154232501983643, "learning_rate": 1.2269849099180192e-06, "loss": 2.6644, "step": 16724 }, { "epoch": 0.8999677141627206, "grad_norm": 2.580003499984741, "learning_rate": 1.2256775135806087e-06, "loss": 4.6662, "step": 16725 }, { "epoch": 0.9000215238915196, "grad_norm": 4.5596137046813965, "learning_rate": 1.2243707966493878e-06, "loss": 2.7388, "step": 16726 }, { "epoch": 0.9000753336203186, "grad_norm": 1.8229364156723022, "learning_rate": 1.2230647591617017e-06, "loss": 3.9104, "step": 16727 }, { "epoch": 0.9001291433491175, "grad_norm": 2.431328296661377, "learning_rate": 1.2217594011548706e-06, "loss": 4.2646, "step": 16728 }, { "epoch": 0.9001829530779165, "grad_norm": 4.4996747970581055, "learning_rate": 1.2204547226661978e-06, "loss": 2.4075, "step": 16729 }, { "epoch": 0.9002367628067155, "grad_norm": 1.5663594007492065, "learning_rate": 1.2191507237329702e-06, "loss": 4.167, "step": 16730 }, { "epoch": 0.9002905725355144, "grad_norm": 1.8670157194137573, "learning_rate": 1.2178474043924554e-06, "loss": 3.9619, "step": 16731 }, { "epoch": 0.9003443822643133, "grad_norm": 1.9751516580581665, "learning_rate": 1.2165447646818957e-06, "loss": 3.2689, "step": 16732 }, { "epoch": 0.9003981919931123, "grad_norm": 3.643089771270752, "learning_rate": 1.215242804638511e-06, "loss": 3.1704, "step": 16733 }, { "epoch": 0.9004520017219113, "grad_norm": 3.4105284214019775, "learning_rate": 1.2139415242995168e-06, "loss": 3.7024, "step": 16734 }, { "epoch": 0.9005058114507103, "grad_norm": 2.5730812549591064, "learning_rate": 1.2126409237020992e-06, "loss": 3.8213, "step": 16735 }, { "epoch": 0.9005596211795093, "grad_norm": 2.326301336288452, "learning_rate": 1.2113410028834205e-06, "loss": 3.6907, "step": 16736 }, { "epoch": 0.9006134309083083, "grad_norm": 3.0875332355499268, "learning_rate": 1.2100417618806341e-06, "loss": 3.381, "step": 16737 }, { "epoch": 0.9006672406371072, "grad_norm": 2.443880558013916, "learning_rate": 1.2087432007308636e-06, "loss": 3.4853, "step": 16738 }, { "epoch": 0.9007210503659061, "grad_norm": 3.010498046875, "learning_rate": 1.2074453194712204e-06, "loss": 4.2399, "step": 16739 }, { "epoch": 0.9007748600947051, "grad_norm": 5.1844587326049805, "learning_rate": 1.206148118138803e-06, "loss": 4.7869, "step": 16740 }, { "epoch": 0.9008286698235041, "grad_norm": 2.6905415058135986, "learning_rate": 1.2048515967706702e-06, "loss": 3.9042, "step": 16741 }, { "epoch": 0.900882479552303, "grad_norm": 4.744611740112305, "learning_rate": 1.2035557554038762e-06, "loss": 3.9786, "step": 16742 }, { "epoch": 0.900936289281102, "grad_norm": 2.6119132041931152, "learning_rate": 1.202260594075455e-06, "loss": 3.0619, "step": 16743 }, { "epoch": 0.900990099009901, "grad_norm": 1.2819010019302368, "learning_rate": 1.2009661128224132e-06, "loss": 4.4231, "step": 16744 }, { "epoch": 0.9010439087387, "grad_norm": 2.526768207550049, "learning_rate": 1.1996723116817516e-06, "loss": 3.5369, "step": 16745 }, { "epoch": 0.901097718467499, "grad_norm": 2.00797700881958, "learning_rate": 1.1983791906904406e-06, "loss": 4.0716, "step": 16746 }, { "epoch": 0.9011515281962978, "grad_norm": 2.405961513519287, "learning_rate": 1.1970867498854343e-06, "loss": 3.7031, "step": 16747 }, { "epoch": 0.9012053379250968, "grad_norm": 1.6754124164581299, "learning_rate": 1.1957949893036668e-06, "loss": 3.7822, "step": 16748 }, { "epoch": 0.9012591476538958, "grad_norm": 3.201415538787842, "learning_rate": 1.1945039089820504e-06, "loss": 3.6567, "step": 16749 }, { "epoch": 0.9013129573826948, "grad_norm": 2.339289903640747, "learning_rate": 1.193213508957483e-06, "loss": 2.9213, "step": 16750 }, { "epoch": 0.9013667671114938, "grad_norm": 1.602095603942871, "learning_rate": 1.1919237892668412e-06, "loss": 3.7947, "step": 16751 }, { "epoch": 0.9014205768402928, "grad_norm": 3.0855934619903564, "learning_rate": 1.1906347499469812e-06, "loss": 3.9084, "step": 16752 }, { "epoch": 0.9014743865690917, "grad_norm": 3.027343511581421, "learning_rate": 1.189346391034743e-06, "loss": 3.7412, "step": 16753 }, { "epoch": 0.9015281962978906, "grad_norm": 3.437859296798706, "learning_rate": 1.1880587125669391e-06, "loss": 3.1156, "step": 16754 }, { "epoch": 0.9015820060266896, "grad_norm": 3.2103166580200195, "learning_rate": 1.1867717145803704e-06, "loss": 3.521, "step": 16755 }, { "epoch": 0.9016358157554886, "grad_norm": 3.669273614883423, "learning_rate": 1.1854853971118185e-06, "loss": 3.7921, "step": 16756 }, { "epoch": 0.9016896254842875, "grad_norm": 2.5386672019958496, "learning_rate": 1.1841997601980376e-06, "loss": 3.6822, "step": 16757 }, { "epoch": 0.9017434352130865, "grad_norm": 6.107025146484375, "learning_rate": 1.1829148038757731e-06, "loss": 3.0124, "step": 16758 }, { "epoch": 0.9017972449418855, "grad_norm": 1.8546525239944458, "learning_rate": 1.1816305281817403e-06, "loss": 4.2216, "step": 16759 }, { "epoch": 0.9018510546706845, "grad_norm": 2.9338645935058594, "learning_rate": 1.1803469331526428e-06, "loss": 3.3915, "step": 16760 }, { "epoch": 0.9019048643994835, "grad_norm": 3.691506862640381, "learning_rate": 1.1790640188251628e-06, "loss": 2.7471, "step": 16761 }, { "epoch": 0.9019586741282823, "grad_norm": 3.762178897857666, "learning_rate": 1.1777817852359652e-06, "loss": 3.9261, "step": 16762 }, { "epoch": 0.9020124838570813, "grad_norm": 2.50777530670166, "learning_rate": 1.1765002324216901e-06, "loss": 3.6405, "step": 16763 }, { "epoch": 0.9020662935858803, "grad_norm": 2.676936388015747, "learning_rate": 1.1752193604189583e-06, "loss": 3.7239, "step": 16764 }, { "epoch": 0.9021201033146793, "grad_norm": 5.201009273529053, "learning_rate": 1.1739391692643763e-06, "loss": 3.4798, "step": 16765 }, { "epoch": 0.9021739130434783, "grad_norm": 2.25460147857666, "learning_rate": 1.1726596589945293e-06, "loss": 4.0492, "step": 16766 }, { "epoch": 0.9022277227722773, "grad_norm": 2.896679162979126, "learning_rate": 1.1713808296459794e-06, "loss": 4.7031, "step": 16767 }, { "epoch": 0.9022815325010762, "grad_norm": 1.711830496788025, "learning_rate": 1.170102681255275e-06, "loss": 4.2544, "step": 16768 }, { "epoch": 0.9023353422298752, "grad_norm": 3.7355899810791016, "learning_rate": 1.1688252138589429e-06, "loss": 3.5917, "step": 16769 }, { "epoch": 0.9023891519586741, "grad_norm": 4.61480188369751, "learning_rate": 1.167548427493484e-06, "loss": 3.2121, "step": 16770 }, { "epoch": 0.9024429616874731, "grad_norm": 2.0555131435394287, "learning_rate": 1.1662723221953941e-06, "loss": 3.9561, "step": 16771 }, { "epoch": 0.902496771416272, "grad_norm": 1.9622076749801636, "learning_rate": 1.1649968980011334e-06, "loss": 3.5241, "step": 16772 }, { "epoch": 0.902550581145071, "grad_norm": 4.376534938812256, "learning_rate": 1.1637221549471527e-06, "loss": 3.5578, "step": 16773 }, { "epoch": 0.90260439087387, "grad_norm": 1.9686088562011719, "learning_rate": 1.1624480930698816e-06, "loss": 3.6011, "step": 16774 }, { "epoch": 0.902658200602669, "grad_norm": 3.039416551589966, "learning_rate": 1.1611747124057243e-06, "loss": 3.1705, "step": 16775 }, { "epoch": 0.902712010331468, "grad_norm": 4.319668769836426, "learning_rate": 1.1599020129910792e-06, "loss": 2.7961, "step": 16776 }, { "epoch": 0.9027658200602668, "grad_norm": 2.500061511993408, "learning_rate": 1.158629994862312e-06, "loss": 3.9684, "step": 16777 }, { "epoch": 0.9028196297890658, "grad_norm": 3.021484136581421, "learning_rate": 1.1573586580557766e-06, "loss": 3.5032, "step": 16778 }, { "epoch": 0.9028734395178648, "grad_norm": 2.5831871032714844, "learning_rate": 1.1560880026077969e-06, "loss": 3.7377, "step": 16779 }, { "epoch": 0.9029272492466638, "grad_norm": 4.734507083892822, "learning_rate": 1.1548180285546883e-06, "loss": 3.9177, "step": 16780 }, { "epoch": 0.9029810589754628, "grad_norm": 2.64750599861145, "learning_rate": 1.1535487359327469e-06, "loss": 3.4494, "step": 16781 }, { "epoch": 0.9030348687042618, "grad_norm": 4.14835262298584, "learning_rate": 1.1522801247782434e-06, "loss": 3.5868, "step": 16782 }, { "epoch": 0.9030886784330607, "grad_norm": 4.821924686431885, "learning_rate": 1.1510121951274322e-06, "loss": 3.2823, "step": 16783 }, { "epoch": 0.9031424881618597, "grad_norm": 3.1328649520874023, "learning_rate": 1.1497449470165428e-06, "loss": 4.2126, "step": 16784 }, { "epoch": 0.9031962978906586, "grad_norm": 3.3387601375579834, "learning_rate": 1.1484783804817962e-06, "loss": 3.3314, "step": 16785 }, { "epoch": 0.9032501076194576, "grad_norm": 2.3784801959991455, "learning_rate": 1.1472124955593828e-06, "loss": 3.1782, "step": 16786 }, { "epoch": 0.9033039173482565, "grad_norm": 1.1788569688796997, "learning_rate": 1.145947292285482e-06, "loss": 4.5094, "step": 16787 }, { "epoch": 0.9033577270770555, "grad_norm": 2.6292312145233154, "learning_rate": 1.1446827706962454e-06, "loss": 3.8369, "step": 16788 }, { "epoch": 0.9034115368058545, "grad_norm": 2.8675665855407715, "learning_rate": 1.1434189308278138e-06, "loss": 4.4229, "step": 16789 }, { "epoch": 0.9034653465346535, "grad_norm": 2.174921989440918, "learning_rate": 1.1421557727163024e-06, "loss": 3.7897, "step": 16790 }, { "epoch": 0.9035191562634525, "grad_norm": 2.560851573944092, "learning_rate": 1.1408932963978048e-06, "loss": 3.1549, "step": 16791 }, { "epoch": 0.9035729659922515, "grad_norm": 4.809910297393799, "learning_rate": 1.1396315019084059e-06, "loss": 2.6192, "step": 16792 }, { "epoch": 0.9036267757210503, "grad_norm": 4.541513442993164, "learning_rate": 1.1383703892841629e-06, "loss": 3.3632, "step": 16793 }, { "epoch": 0.9036805854498493, "grad_norm": 2.8017866611480713, "learning_rate": 1.1371099585611168e-06, "loss": 3.5593, "step": 16794 }, { "epoch": 0.9037343951786483, "grad_norm": 1.8787761926651, "learning_rate": 1.135850209775277e-06, "loss": 3.904, "step": 16795 }, { "epoch": 0.9037882049074473, "grad_norm": 3.2235279083251953, "learning_rate": 1.1345911429626571e-06, "loss": 3.4107, "step": 16796 }, { "epoch": 0.9038420146362462, "grad_norm": 2.8271167278289795, "learning_rate": 1.1333327581592306e-06, "loss": 3.213, "step": 16797 }, { "epoch": 0.9038958243650452, "grad_norm": 1.9782696962356567, "learning_rate": 1.1320750554009578e-06, "loss": 4.1034, "step": 16798 }, { "epoch": 0.9039496340938442, "grad_norm": 2.11883807182312, "learning_rate": 1.130818034723785e-06, "loss": 3.8135, "step": 16799 }, { "epoch": 0.9040034438226431, "grad_norm": 3.125657081604004, "learning_rate": 1.1295616961636336e-06, "loss": 3.3607, "step": 16800 }, { "epoch": 0.9040572535514421, "grad_norm": 3.236198663711548, "learning_rate": 1.1283060397564022e-06, "loss": 3.4844, "step": 16801 }, { "epoch": 0.904111063280241, "grad_norm": 1.5576261281967163, "learning_rate": 1.127051065537979e-06, "loss": 2.7211, "step": 16802 }, { "epoch": 0.90416487300904, "grad_norm": 2.652024984359741, "learning_rate": 1.1257967735442243e-06, "loss": 3.9356, "step": 16803 }, { "epoch": 0.904218682737839, "grad_norm": 3.2213633060455322, "learning_rate": 1.1245431638109843e-06, "loss": 3.8662, "step": 16804 }, { "epoch": 0.904272492466638, "grad_norm": 1.7866766452789307, "learning_rate": 1.1232902363740833e-06, "loss": 4.0969, "step": 16805 }, { "epoch": 0.904326302195437, "grad_norm": 1.3946232795715332, "learning_rate": 1.1220379912693229e-06, "loss": 4.3958, "step": 16806 }, { "epoch": 0.904380111924236, "grad_norm": 3.616795539855957, "learning_rate": 1.1207864285324943e-06, "loss": 4.0293, "step": 16807 }, { "epoch": 0.9044339216530348, "grad_norm": 1.526207685470581, "learning_rate": 1.1195355481993657e-06, "loss": 4.227, "step": 16808 }, { "epoch": 0.9044877313818338, "grad_norm": 2.8926239013671875, "learning_rate": 1.1182853503056812e-06, "loss": 3.5918, "step": 16809 }, { "epoch": 0.9045415411106328, "grad_norm": 4.040789604187012, "learning_rate": 1.1170358348871618e-06, "loss": 3.8757, "step": 16810 }, { "epoch": 0.9045953508394318, "grad_norm": 3.736337900161743, "learning_rate": 1.1157870019795207e-06, "loss": 3.4824, "step": 16811 }, { "epoch": 0.9046491605682307, "grad_norm": 2.1477890014648438, "learning_rate": 1.1145388516184491e-06, "loss": 3.7778, "step": 16812 }, { "epoch": 0.9047029702970297, "grad_norm": 3.3701014518737793, "learning_rate": 1.1132913838396125e-06, "loss": 3.3673, "step": 16813 }, { "epoch": 0.9047567800258287, "grad_norm": 3.4360527992248535, "learning_rate": 1.1120445986786577e-06, "loss": 4.063, "step": 16814 }, { "epoch": 0.9048105897546277, "grad_norm": 3.3307363986968994, "learning_rate": 1.1107984961712197e-06, "loss": 3.5085, "step": 16815 }, { "epoch": 0.9048643994834266, "grad_norm": 5.030375003814697, "learning_rate": 1.1095530763529067e-06, "loss": 3.9689, "step": 16816 }, { "epoch": 0.9049182092122255, "grad_norm": 3.636991500854492, "learning_rate": 1.108308339259309e-06, "loss": 3.671, "step": 16817 }, { "epoch": 0.9049720189410245, "grad_norm": 2.224543809890747, "learning_rate": 1.107064284925996e-06, "loss": 4.0776, "step": 16818 }, { "epoch": 0.9050258286698235, "grad_norm": 3.819467067718506, "learning_rate": 1.1058209133885222e-06, "loss": 3.7396, "step": 16819 }, { "epoch": 0.9050796383986225, "grad_norm": 3.605452299118042, "learning_rate": 1.1045782246824205e-06, "loss": 3.3556, "step": 16820 }, { "epoch": 0.9051334481274215, "grad_norm": 1.416365623474121, "learning_rate": 1.1033362188432012e-06, "loss": 4.2727, "step": 16821 }, { "epoch": 0.9051872578562205, "grad_norm": 2.4487686157226562, "learning_rate": 1.1020948959063526e-06, "loss": 3.9749, "step": 16822 }, { "epoch": 0.9052410675850193, "grad_norm": 2.7093050479888916, "learning_rate": 1.1008542559073604e-06, "loss": 3.4343, "step": 16823 }, { "epoch": 0.9052948773138183, "grad_norm": 1.9972617626190186, "learning_rate": 1.0996142988816739e-06, "loss": 4.0401, "step": 16824 }, { "epoch": 0.9053486870426173, "grad_norm": 3.2487027645111084, "learning_rate": 1.0983750248647228e-06, "loss": 3.4004, "step": 16825 }, { "epoch": 0.9054024967714163, "grad_norm": 2.513089656829834, "learning_rate": 1.0971364338919238e-06, "loss": 3.284, "step": 16826 }, { "epoch": 0.9054563065002152, "grad_norm": 3.6609246730804443, "learning_rate": 1.0958985259986787e-06, "loss": 3.2973, "step": 16827 }, { "epoch": 0.9055101162290142, "grad_norm": 2.2236082553863525, "learning_rate": 1.0946613012203567e-06, "loss": 3.3628, "step": 16828 }, { "epoch": 0.9055639259578132, "grad_norm": 3.556685447692871, "learning_rate": 1.093424759592318e-06, "loss": 2.8621, "step": 16829 }, { "epoch": 0.9056177356866122, "grad_norm": 2.2463676929473877, "learning_rate": 1.0921889011498988e-06, "loss": 4.0814, "step": 16830 }, { "epoch": 0.9056715454154111, "grad_norm": 2.972407341003418, "learning_rate": 1.0909537259284148e-06, "loss": 3.7323, "step": 16831 }, { "epoch": 0.90572535514421, "grad_norm": 3.5606985092163086, "learning_rate": 1.0897192339631657e-06, "loss": 3.7336, "step": 16832 }, { "epoch": 0.905779164873009, "grad_norm": 3.889153242111206, "learning_rate": 1.0884854252894316e-06, "loss": 4.7911, "step": 16833 }, { "epoch": 0.905832974601808, "grad_norm": 2.987272024154663, "learning_rate": 1.0872522999424678e-06, "loss": 3.3328, "step": 16834 }, { "epoch": 0.905886784330607, "grad_norm": 3.766451358795166, "learning_rate": 1.0860198579575182e-06, "loss": 3.8257, "step": 16835 }, { "epoch": 0.905940594059406, "grad_norm": 3.7740416526794434, "learning_rate": 1.084788099369799e-06, "loss": 3.0588, "step": 16836 }, { "epoch": 0.905994403788205, "grad_norm": 2.724583148956299, "learning_rate": 1.0835570242145071e-06, "loss": 3.9195, "step": 16837 }, { "epoch": 0.9060482135170038, "grad_norm": 2.229283332824707, "learning_rate": 1.082326632526831e-06, "loss": 3.3666, "step": 16838 }, { "epoch": 0.9061020232458028, "grad_norm": 1.6091970205307007, "learning_rate": 1.0810969243419317e-06, "loss": 3.9208, "step": 16839 }, { "epoch": 0.9061558329746018, "grad_norm": 3.420586347579956, "learning_rate": 1.0798678996949475e-06, "loss": 3.5337, "step": 16840 }, { "epoch": 0.9062096427034008, "grad_norm": 2.0276718139648438, "learning_rate": 1.0786395586209974e-06, "loss": 3.6921, "step": 16841 }, { "epoch": 0.9062634524321997, "grad_norm": 1.8411489725112915, "learning_rate": 1.077411901155187e-06, "loss": 4.529, "step": 16842 }, { "epoch": 0.9063172621609987, "grad_norm": 2.934091091156006, "learning_rate": 1.076184927332602e-06, "loss": 3.832, "step": 16843 }, { "epoch": 0.9063710718897977, "grad_norm": 4.023948669433594, "learning_rate": 1.0749586371883059e-06, "loss": 4.0052, "step": 16844 }, { "epoch": 0.9064248816185967, "grad_norm": 3.2291901111602783, "learning_rate": 1.0737330307573402e-06, "loss": 3.484, "step": 16845 }, { "epoch": 0.9064786913473956, "grad_norm": 2.0151779651641846, "learning_rate": 1.0725081080747296e-06, "loss": 3.789, "step": 16846 }, { "epoch": 0.9065325010761945, "grad_norm": 2.441909074783325, "learning_rate": 1.0712838691754822e-06, "loss": 4.1434, "step": 16847 }, { "epoch": 0.9065863108049935, "grad_norm": 3.1290647983551025, "learning_rate": 1.0700603140945786e-06, "loss": 3.9298, "step": 16848 }, { "epoch": 0.9066401205337925, "grad_norm": 2.5399484634399414, "learning_rate": 1.068837442866988e-06, "loss": 3.7383, "step": 16849 }, { "epoch": 0.9066939302625915, "grad_norm": 4.037333011627197, "learning_rate": 1.067615255527657e-06, "loss": 4.4862, "step": 16850 }, { "epoch": 0.9067477399913905, "grad_norm": 2.9654226303100586, "learning_rate": 1.066393752111511e-06, "loss": 3.66, "step": 16851 }, { "epoch": 0.9068015497201894, "grad_norm": 4.316861629486084, "learning_rate": 1.0651729326534548e-06, "loss": 3.359, "step": 16852 }, { "epoch": 0.9068553594489884, "grad_norm": 2.6203999519348145, "learning_rate": 1.0639527971883806e-06, "loss": 3.861, "step": 16853 }, { "epoch": 0.9069091691777873, "grad_norm": 4.131375789642334, "learning_rate": 1.0627333457511574e-06, "loss": 2.7224, "step": 16854 }, { "epoch": 0.9069629789065863, "grad_norm": 4.413945198059082, "learning_rate": 1.0615145783766322e-06, "loss": 3.1219, "step": 16855 }, { "epoch": 0.9070167886353853, "grad_norm": 1.6107107400894165, "learning_rate": 1.060296495099633e-06, "loss": 3.4164, "step": 16856 }, { "epoch": 0.9070705983641842, "grad_norm": 1.9086555242538452, "learning_rate": 1.059079095954965e-06, "loss": 4.1519, "step": 16857 }, { "epoch": 0.9071244080929832, "grad_norm": 2.6662445068359375, "learning_rate": 1.0578623809774258e-06, "loss": 4.1631, "step": 16858 }, { "epoch": 0.9071782178217822, "grad_norm": 2.231311321258545, "learning_rate": 1.0566463502017842e-06, "loss": 3.622, "step": 16859 }, { "epoch": 0.9072320275505812, "grad_norm": 2.190176248550415, "learning_rate": 1.0554310036627878e-06, "loss": 4.0294, "step": 16860 }, { "epoch": 0.9072858372793801, "grad_norm": 3.0670554637908936, "learning_rate": 1.0542163413951727e-06, "loss": 3.5275, "step": 16861 }, { "epoch": 0.907339647008179, "grad_norm": 1.949329137802124, "learning_rate": 1.0530023634336473e-06, "loss": 3.7006, "step": 16862 }, { "epoch": 0.907393456736978, "grad_norm": 2.74826979637146, "learning_rate": 1.051789069812903e-06, "loss": 4.0103, "step": 16863 }, { "epoch": 0.907447266465777, "grad_norm": 3.6275525093078613, "learning_rate": 1.0505764605676149e-06, "loss": 3.7209, "step": 16864 }, { "epoch": 0.907501076194576, "grad_norm": 2.0604612827301025, "learning_rate": 1.0493645357324333e-06, "loss": 3.7191, "step": 16865 }, { "epoch": 0.907554885923375, "grad_norm": 3.629671573638916, "learning_rate": 1.048153295341997e-06, "loss": 3.4686, "step": 16866 }, { "epoch": 0.907608695652174, "grad_norm": 1.2976034879684448, "learning_rate": 1.0469427394309145e-06, "loss": 4.3447, "step": 16867 }, { "epoch": 0.9076625053809729, "grad_norm": 1.7263249158859253, "learning_rate": 1.0457328680337803e-06, "loss": 3.8966, "step": 16868 }, { "epoch": 0.9077163151097718, "grad_norm": 1.8409987688064575, "learning_rate": 1.0445236811851721e-06, "loss": 3.9249, "step": 16869 }, { "epoch": 0.9077701248385708, "grad_norm": 2.599863052368164, "learning_rate": 1.043315178919649e-06, "loss": 3.9962, "step": 16870 }, { "epoch": 0.9078239345673698, "grad_norm": 2.671410322189331, "learning_rate": 1.0421073612717407e-06, "loss": 4.1363, "step": 16871 }, { "epoch": 0.9078777442961687, "grad_norm": 2.3078906536102295, "learning_rate": 1.0409002282759623e-06, "loss": 4.8346, "step": 16872 }, { "epoch": 0.9079315540249677, "grad_norm": 2.735989570617676, "learning_rate": 1.0396937799668106e-06, "loss": 3.8496, "step": 16873 }, { "epoch": 0.9079853637537667, "grad_norm": 3.769669771194458, "learning_rate": 1.0384880163787692e-06, "loss": 3.6751, "step": 16874 }, { "epoch": 0.9080391734825657, "grad_norm": 1.1097601652145386, "learning_rate": 1.0372829375462912e-06, "loss": 4.2826, "step": 16875 }, { "epoch": 0.9080929832113647, "grad_norm": 4.243960380554199, "learning_rate": 1.0360785435038128e-06, "loss": 2.7354, "step": 16876 }, { "epoch": 0.9081467929401635, "grad_norm": 3.9970433712005615, "learning_rate": 1.0348748342857567e-06, "loss": 3.8492, "step": 16877 }, { "epoch": 0.9082006026689625, "grad_norm": 1.7568578720092773, "learning_rate": 1.0336718099265175e-06, "loss": 3.6418, "step": 16878 }, { "epoch": 0.9082544123977615, "grad_norm": 3.976672649383545, "learning_rate": 1.032469470460476e-06, "loss": 3.6108, "step": 16879 }, { "epoch": 0.9083082221265605, "grad_norm": 3.3280742168426514, "learning_rate": 1.0312678159219935e-06, "loss": 3.653, "step": 16880 }, { "epoch": 0.9083620318553595, "grad_norm": 3.0563931465148926, "learning_rate": 1.0300668463454066e-06, "loss": 4.1294, "step": 16881 }, { "epoch": 0.9084158415841584, "grad_norm": 2.323596954345703, "learning_rate": 1.0288665617650405e-06, "loss": 3.9519, "step": 16882 }, { "epoch": 0.9084696513129574, "grad_norm": 2.80413556098938, "learning_rate": 1.0276669622151874e-06, "loss": 3.5204, "step": 16883 }, { "epoch": 0.9085234610417563, "grad_norm": 1.2800477743148804, "learning_rate": 1.026468047730139e-06, "loss": 4.6634, "step": 16884 }, { "epoch": 0.9085772707705553, "grad_norm": 3.737060546875, "learning_rate": 1.0252698183441573e-06, "loss": 2.933, "step": 16885 }, { "epoch": 0.9086310804993543, "grad_norm": 2.1130640506744385, "learning_rate": 1.0240722740914727e-06, "loss": 3.5208, "step": 16886 }, { "epoch": 0.9086848902281532, "grad_norm": 2.279919147491455, "learning_rate": 1.0228754150063164e-06, "loss": 3.7708, "step": 16887 }, { "epoch": 0.9087386999569522, "grad_norm": 1.9251347780227661, "learning_rate": 1.0216792411228887e-06, "loss": 3.6529, "step": 16888 }, { "epoch": 0.9087925096857512, "grad_norm": 4.297361850738525, "learning_rate": 1.0204837524753762e-06, "loss": 3.5636, "step": 16889 }, { "epoch": 0.9088463194145502, "grad_norm": 2.3658716678619385, "learning_rate": 1.0192889490979407e-06, "loss": 3.2324, "step": 16890 }, { "epoch": 0.9089001291433492, "grad_norm": 2.668532371520996, "learning_rate": 1.018094831024724e-06, "loss": 3.7295, "step": 16891 }, { "epoch": 0.908953938872148, "grad_norm": 2.4803497791290283, "learning_rate": 1.0169013982898574e-06, "loss": 3.6457, "step": 16892 }, { "epoch": 0.909007748600947, "grad_norm": 3.691328525543213, "learning_rate": 1.0157086509274383e-06, "loss": 3.3302, "step": 16893 }, { "epoch": 0.909061558329746, "grad_norm": 3.5834343433380127, "learning_rate": 1.014516588971559e-06, "loss": 3.2951, "step": 16894 }, { "epoch": 0.909115368058545, "grad_norm": 2.7337238788604736, "learning_rate": 1.0133252124562787e-06, "loss": 4.5008, "step": 16895 }, { "epoch": 0.909169177787344, "grad_norm": 3.6173698902130127, "learning_rate": 1.0121345214156503e-06, "loss": 4.2004, "step": 16896 }, { "epoch": 0.9092229875161429, "grad_norm": 5.589611530303955, "learning_rate": 1.0109445158836967e-06, "loss": 3.6866, "step": 16897 }, { "epoch": 0.9092767972449419, "grad_norm": 1.5594332218170166, "learning_rate": 1.009755195894424e-06, "loss": 4.446, "step": 16898 }, { "epoch": 0.9093306069737409, "grad_norm": 1.9299843311309814, "learning_rate": 1.0085665614818219e-06, "loss": 4.1748, "step": 16899 }, { "epoch": 0.9093844167025398, "grad_norm": 4.954711437225342, "learning_rate": 1.0073786126798572e-06, "loss": 4.1588, "step": 16900 }, { "epoch": 0.9094382264313388, "grad_norm": 2.6113247871398926, "learning_rate": 1.0061913495224839e-06, "loss": 3.9258, "step": 16901 }, { "epoch": 0.9094920361601377, "grad_norm": 3.4228744506835938, "learning_rate": 1.0050047720436246e-06, "loss": 3.1942, "step": 16902 }, { "epoch": 0.9095458458889367, "grad_norm": 2.980039119720459, "learning_rate": 1.003818880277188e-06, "loss": 4.2566, "step": 16903 }, { "epoch": 0.9095996556177357, "grad_norm": 4.335516929626465, "learning_rate": 1.002633674257064e-06, "loss": 3.2886, "step": 16904 }, { "epoch": 0.9096534653465347, "grad_norm": 2.1084485054016113, "learning_rate": 1.0014491540171283e-06, "loss": 4.2704, "step": 16905 }, { "epoch": 0.9097072750753337, "grad_norm": 2.165347099304199, "learning_rate": 1.0002653195912231e-06, "loss": 3.7514, "step": 16906 }, { "epoch": 0.9097610848041325, "grad_norm": 3.197967052459717, "learning_rate": 9.990821710131882e-07, "loss": 3.691, "step": 16907 }, { "epoch": 0.9098148945329315, "grad_norm": 4.282433986663818, "learning_rate": 9.978997083168268e-07, "loss": 3.8817, "step": 16908 }, { "epoch": 0.9098687042617305, "grad_norm": 2.298999071121216, "learning_rate": 9.967179315359343e-07, "loss": 4.3965, "step": 16909 }, { "epoch": 0.9099225139905295, "grad_norm": 2.753031015396118, "learning_rate": 9.955368407042836e-07, "loss": 3.9466, "step": 16910 }, { "epoch": 0.9099763237193285, "grad_norm": 3.1067402362823486, "learning_rate": 9.94356435855623e-07, "loss": 3.5894, "step": 16911 }, { "epoch": 0.9100301334481274, "grad_norm": 2.5348780155181885, "learning_rate": 9.931767170236888e-07, "loss": 4.0327, "step": 16912 }, { "epoch": 0.9100839431769264, "grad_norm": 3.1924986839294434, "learning_rate": 9.919976842421935e-07, "loss": 3.6341, "step": 16913 }, { "epoch": 0.9101377529057254, "grad_norm": 2.100280284881592, "learning_rate": 9.908193375448294e-07, "loss": 3.7092, "step": 16914 }, { "epoch": 0.9101915626345243, "grad_norm": 2.610927104949951, "learning_rate": 9.896416769652722e-07, "loss": 3.8708, "step": 16915 }, { "epoch": 0.9102453723633233, "grad_norm": 2.6512556076049805, "learning_rate": 9.884647025371786e-07, "loss": 4.3859, "step": 16916 }, { "epoch": 0.9102991820921222, "grad_norm": 1.9534597396850586, "learning_rate": 9.872884142941768e-07, "loss": 4.2432, "step": 16917 }, { "epoch": 0.9103529918209212, "grad_norm": 2.758659601211548, "learning_rate": 9.861128122698876e-07, "loss": 3.3502, "step": 16918 }, { "epoch": 0.9104068015497202, "grad_norm": 2.642216444015503, "learning_rate": 9.849378964979005e-07, "loss": 3.5835, "step": 16919 }, { "epoch": 0.9104606112785192, "grad_norm": 2.1686718463897705, "learning_rate": 9.837636670117973e-07, "loss": 4.0044, "step": 16920 }, { "epoch": 0.9105144210073182, "grad_norm": 1.8124626874923706, "learning_rate": 9.82590123845134e-07, "loss": 4.138, "step": 16921 }, { "epoch": 0.910568230736117, "grad_norm": 3.36155104637146, "learning_rate": 9.814172670314454e-07, "loss": 3.5591, "step": 16922 }, { "epoch": 0.910622040464916, "grad_norm": 3.043733835220337, "learning_rate": 9.802450966042516e-07, "loss": 3.8953, "step": 16923 }, { "epoch": 0.910675850193715, "grad_norm": 4.4666748046875, "learning_rate": 9.790736125970423e-07, "loss": 3.4003, "step": 16924 }, { "epoch": 0.910729659922514, "grad_norm": 1.6158350706100464, "learning_rate": 9.779028150433024e-07, "loss": 3.7657, "step": 16925 }, { "epoch": 0.910783469651313, "grad_norm": 2.0340046882629395, "learning_rate": 9.767327039764878e-07, "loss": 4.1334, "step": 16926 }, { "epoch": 0.9108372793801119, "grad_norm": 3.4080207347869873, "learning_rate": 9.75563279430039e-07, "loss": 3.0101, "step": 16927 }, { "epoch": 0.9108910891089109, "grad_norm": 3.395576238632202, "learning_rate": 9.743945414373707e-07, "loss": 4.0069, "step": 16928 }, { "epoch": 0.9109448988377099, "grad_norm": 2.6161928176879883, "learning_rate": 9.732264900318866e-07, "loss": 4.3921, "step": 16929 }, { "epoch": 0.9109987085665088, "grad_norm": 1.537599802017212, "learning_rate": 9.720591252469629e-07, "loss": 4.0134, "step": 16930 }, { "epoch": 0.9110525182953078, "grad_norm": 3.0056309700012207, "learning_rate": 9.708924471159674e-07, "loss": 3.3645, "step": 16931 }, { "epoch": 0.9111063280241067, "grad_norm": 3.2307844161987305, "learning_rate": 9.697264556722318e-07, "loss": 2.7786, "step": 16932 }, { "epoch": 0.9111601377529057, "grad_norm": 2.350404739379883, "learning_rate": 9.685611509490822e-07, "loss": 3.2709, "step": 16933 }, { "epoch": 0.9112139474817047, "grad_norm": 2.3614814281463623, "learning_rate": 9.67396532979814e-07, "loss": 4.2298, "step": 16934 }, { "epoch": 0.9112677572105037, "grad_norm": 4.523143768310547, "learning_rate": 9.662326017977119e-07, "loss": 2.9677, "step": 16935 }, { "epoch": 0.9113215669393027, "grad_norm": 2.4742298126220703, "learning_rate": 9.650693574360437e-07, "loss": 3.5257, "step": 16936 }, { "epoch": 0.9113753766681016, "grad_norm": 2.0902063846588135, "learning_rate": 9.639067999280438e-07, "loss": 3.6096, "step": 16937 }, { "epoch": 0.9114291863969005, "grad_norm": 1.1960369348526, "learning_rate": 9.627449293069412e-07, "loss": 4.1888, "step": 16938 }, { "epoch": 0.9114829961256995, "grad_norm": 2.1250712871551514, "learning_rate": 9.615837456059318e-07, "loss": 4.1531, "step": 16939 }, { "epoch": 0.9115368058544985, "grad_norm": 1.8590494394302368, "learning_rate": 9.604232488582055e-07, "loss": 3.8612, "step": 16940 }, { "epoch": 0.9115906155832975, "grad_norm": 2.7439849376678467, "learning_rate": 9.592634390969246e-07, "loss": 4.0536, "step": 16941 }, { "epoch": 0.9116444253120964, "grad_norm": 2.7772293090820312, "learning_rate": 9.581043163552322e-07, "loss": 4.3393, "step": 16942 }, { "epoch": 0.9116982350408954, "grad_norm": 1.9424688816070557, "learning_rate": 9.569458806662519e-07, "loss": 4.1423, "step": 16943 }, { "epoch": 0.9117520447696944, "grad_norm": 3.6393678188323975, "learning_rate": 9.55788132063093e-07, "loss": 4.0369, "step": 16944 }, { "epoch": 0.9118058544984933, "grad_norm": 3.891942024230957, "learning_rate": 9.54631070578832e-07, "loss": 3.2097, "step": 16945 }, { "epoch": 0.9118596642272923, "grad_norm": 3.365912914276123, "learning_rate": 9.53474696246548e-07, "loss": 2.8009, "step": 16946 }, { "epoch": 0.9119134739560912, "grad_norm": 6.988043308258057, "learning_rate": 9.523190090992756e-07, "loss": 3.9227, "step": 16947 }, { "epoch": 0.9119672836848902, "grad_norm": 2.408639907836914, "learning_rate": 9.511640091700469e-07, "loss": 3.6347, "step": 16948 }, { "epoch": 0.9120210934136892, "grad_norm": 2.514948844909668, "learning_rate": 9.500096964918659e-07, "loss": 3.6452, "step": 16949 }, { "epoch": 0.9120749031424882, "grad_norm": 3.818162202835083, "learning_rate": 9.488560710977173e-07, "loss": 3.0103, "step": 16950 }, { "epoch": 0.9121287128712872, "grad_norm": 5.020842552185059, "learning_rate": 9.477031330205749e-07, "loss": 3.2324, "step": 16951 }, { "epoch": 0.9121825226000861, "grad_norm": 2.5886917114257812, "learning_rate": 9.465508822933872e-07, "loss": 3.2497, "step": 16952 }, { "epoch": 0.912236332328885, "grad_norm": 1.532326579093933, "learning_rate": 9.453993189490751e-07, "loss": 4.6363, "step": 16953 }, { "epoch": 0.912290142057684, "grad_norm": 2.476130247116089, "learning_rate": 9.442484430205567e-07, "loss": 3.0443, "step": 16954 }, { "epoch": 0.912343951786483, "grad_norm": 4.392304420471191, "learning_rate": 9.430982545407085e-07, "loss": 3.6758, "step": 16955 }, { "epoch": 0.912397761515282, "grad_norm": 2.042206048965454, "learning_rate": 9.419487535424099e-07, "loss": 4.1766, "step": 16956 }, { "epoch": 0.9124515712440809, "grad_norm": 1.9250061511993408, "learning_rate": 9.407999400585066e-07, "loss": 3.7566, "step": 16957 }, { "epoch": 0.9125053809728799, "grad_norm": 2.630261182785034, "learning_rate": 9.396518141218307e-07, "loss": 3.8741, "step": 16958 }, { "epoch": 0.9125591907016789, "grad_norm": 3.3299977779388428, "learning_rate": 9.385043757651924e-07, "loss": 3.667, "step": 16959 }, { "epoch": 0.9126130004304779, "grad_norm": 1.5674598217010498, "learning_rate": 9.373576250213789e-07, "loss": 4.1814, "step": 16960 }, { "epoch": 0.9126668101592768, "grad_norm": 3.1938061714172363, "learning_rate": 9.362115619231616e-07, "loss": 3.3876, "step": 16961 }, { "epoch": 0.9127206198880757, "grad_norm": 3.6814303398132324, "learning_rate": 9.350661865032972e-07, "loss": 3.2111, "step": 16962 }, { "epoch": 0.9127744296168747, "grad_norm": 3.2528393268585205, "learning_rate": 9.339214987945155e-07, "loss": 3.5554, "step": 16963 }, { "epoch": 0.9128282393456737, "grad_norm": 2.586529493331909, "learning_rate": 9.327774988295235e-07, "loss": 4.1823, "step": 16964 }, { "epoch": 0.9128820490744727, "grad_norm": 4.679811954498291, "learning_rate": 9.3163418664102e-07, "loss": 3.3525, "step": 16965 }, { "epoch": 0.9129358588032717, "grad_norm": 4.570944786071777, "learning_rate": 9.304915622616705e-07, "loss": 3.8437, "step": 16966 }, { "epoch": 0.9129896685320706, "grad_norm": 4.225039482116699, "learning_rate": 9.293496257241352e-07, "loss": 3.3805, "step": 16967 }, { "epoch": 0.9130434782608695, "grad_norm": 1.3245952129364014, "learning_rate": 9.282083770610462e-07, "loss": 4.2796, "step": 16968 }, { "epoch": 0.9130972879896685, "grad_norm": 3.4397215843200684, "learning_rate": 9.270678163050217e-07, "loss": 3.6831, "step": 16969 }, { "epoch": 0.9131510977184675, "grad_norm": 1.7585256099700928, "learning_rate": 9.259279434886414e-07, "loss": 3.7142, "step": 16970 }, { "epoch": 0.9132049074472665, "grad_norm": 2.0462799072265625, "learning_rate": 9.247887586444931e-07, "loss": 3.7713, "step": 16971 }, { "epoch": 0.9132587171760654, "grad_norm": 2.453235387802124, "learning_rate": 9.236502618051257e-07, "loss": 3.6237, "step": 16972 }, { "epoch": 0.9133125269048644, "grad_norm": 1.4956692457199097, "learning_rate": 9.225124530030771e-07, "loss": 3.5119, "step": 16973 }, { "epoch": 0.9133663366336634, "grad_norm": 2.570966958999634, "learning_rate": 9.213753322708629e-07, "loss": 3.9488, "step": 16974 }, { "epoch": 0.9134201463624624, "grad_norm": 1.6987367868423462, "learning_rate": 9.202388996409767e-07, "loss": 4.0512, "step": 16975 }, { "epoch": 0.9134739560912613, "grad_norm": 2.866471529006958, "learning_rate": 9.191031551458922e-07, "loss": 3.6739, "step": 16976 }, { "epoch": 0.9135277658200602, "grad_norm": 3.1484620571136475, "learning_rate": 9.179680988180756e-07, "loss": 3.5946, "step": 16977 }, { "epoch": 0.9135815755488592, "grad_norm": 4.08015775680542, "learning_rate": 9.16833730689956e-07, "loss": 3.579, "step": 16978 }, { "epoch": 0.9136353852776582, "grad_norm": 4.013497829437256, "learning_rate": 9.157000507939494e-07, "loss": 3.8449, "step": 16979 }, { "epoch": 0.9136891950064572, "grad_norm": 1.3067675828933716, "learning_rate": 9.145670591624605e-07, "loss": 4.2574, "step": 16980 }, { "epoch": 0.9137430047352562, "grad_norm": 3.850163459777832, "learning_rate": 9.134347558278578e-07, "loss": 2.6387, "step": 16981 }, { "epoch": 0.9137968144640551, "grad_norm": 3.1571884155273438, "learning_rate": 9.123031408225069e-07, "loss": 3.5416, "step": 16982 }, { "epoch": 0.9138506241928541, "grad_norm": 2.208167314529419, "learning_rate": 9.111722141787432e-07, "loss": 3.916, "step": 16983 }, { "epoch": 0.913904433921653, "grad_norm": 3.4049079418182373, "learning_rate": 9.100419759288881e-07, "loss": 3.6261, "step": 16984 }, { "epoch": 0.913958243650452, "grad_norm": 5.260213851928711, "learning_rate": 9.089124261052406e-07, "loss": 3.24, "step": 16985 }, { "epoch": 0.914012053379251, "grad_norm": 2.856666088104248, "learning_rate": 9.077835647400723e-07, "loss": 3.5398, "step": 16986 }, { "epoch": 0.9140658631080499, "grad_norm": 1.2720131874084473, "learning_rate": 9.066553918656545e-07, "loss": 4.4253, "step": 16987 }, { "epoch": 0.9141196728368489, "grad_norm": 2.34175705909729, "learning_rate": 9.055279075142198e-07, "loss": 4.5608, "step": 16988 }, { "epoch": 0.9141734825656479, "grad_norm": 3.2255704402923584, "learning_rate": 9.044011117179923e-07, "loss": 3.6585, "step": 16989 }, { "epoch": 0.9142272922944469, "grad_norm": 3.5152947902679443, "learning_rate": 9.032750045091715e-07, "loss": 3.8788, "step": 16990 }, { "epoch": 0.9142811020232458, "grad_norm": 2.513241767883301, "learning_rate": 9.021495859199397e-07, "loss": 2.9468, "step": 16991 }, { "epoch": 0.9143349117520447, "grad_norm": 3.454484701156616, "learning_rate": 9.010248559824547e-07, "loss": 3.7624, "step": 16992 }, { "epoch": 0.9143887214808437, "grad_norm": 2.977776288986206, "learning_rate": 8.999008147288601e-07, "loss": 3.6485, "step": 16993 }, { "epoch": 0.9144425312096427, "grad_norm": 3.2702975273132324, "learning_rate": 8.987774621912803e-07, "loss": 3.2701, "step": 16994 }, { "epoch": 0.9144963409384417, "grad_norm": 2.670142412185669, "learning_rate": 8.976547984018174e-07, "loss": 3.9849, "step": 16995 }, { "epoch": 0.9145501506672407, "grad_norm": 2.408252716064453, "learning_rate": 8.965328233925512e-07, "loss": 3.9801, "step": 16996 }, { "epoch": 0.9146039603960396, "grad_norm": 2.508270740509033, "learning_rate": 8.954115371955424e-07, "loss": 3.1511, "step": 16997 }, { "epoch": 0.9146577701248386, "grad_norm": 3.1918530464172363, "learning_rate": 8.942909398428428e-07, "loss": 3.4698, "step": 16998 }, { "epoch": 0.9147115798536375, "grad_norm": 3.651235580444336, "learning_rate": 8.931710313664687e-07, "loss": 3.5026, "step": 16999 }, { "epoch": 0.9147653895824365, "grad_norm": 1.6009142398834229, "learning_rate": 8.920518117984305e-07, "loss": 3.7967, "step": 17000 }, { "epoch": 0.9148191993112355, "grad_norm": 1.9754313230514526, "learning_rate": 8.909332811707056e-07, "loss": 4.5819, "step": 17001 }, { "epoch": 0.9148730090400344, "grad_norm": 4.286118984222412, "learning_rate": 8.898154395152625e-07, "loss": 2.5295, "step": 17002 }, { "epoch": 0.9149268187688334, "grad_norm": 2.8490731716156006, "learning_rate": 8.886982868640454e-07, "loss": 3.7543, "step": 17003 }, { "epoch": 0.9149806284976324, "grad_norm": 3.8439433574676514, "learning_rate": 8.875818232489786e-07, "loss": 3.999, "step": 17004 }, { "epoch": 0.9150344382264314, "grad_norm": 6.623786926269531, "learning_rate": 8.8646604870197e-07, "loss": 3.1238, "step": 17005 }, { "epoch": 0.9150882479552304, "grad_norm": 1.4493813514709473, "learning_rate": 8.853509632549051e-07, "loss": 4.3563, "step": 17006 }, { "epoch": 0.9151420576840292, "grad_norm": 2.598595142364502, "learning_rate": 8.842365669396446e-07, "loss": 3.5136, "step": 17007 }, { "epoch": 0.9151958674128282, "grad_norm": 4.429836273193359, "learning_rate": 8.831228597880436e-07, "loss": 3.564, "step": 17008 }, { "epoch": 0.9152496771416272, "grad_norm": 2.853634834289551, "learning_rate": 8.820098418319239e-07, "loss": 4.2378, "step": 17009 }, { "epoch": 0.9153034868704262, "grad_norm": 4.0566911697387695, "learning_rate": 8.808975131030906e-07, "loss": 3.1146, "step": 17010 }, { "epoch": 0.9153572965992252, "grad_norm": 3.412771224975586, "learning_rate": 8.797858736333347e-07, "loss": 3.6805, "step": 17011 }, { "epoch": 0.9154111063280241, "grad_norm": 3.237447500228882, "learning_rate": 8.786749234544201e-07, "loss": 3.5281, "step": 17012 }, { "epoch": 0.9154649160568231, "grad_norm": 2.1531858444213867, "learning_rate": 8.775646625981015e-07, "loss": 4.1879, "step": 17013 }, { "epoch": 0.915518725785622, "grad_norm": 4.401803016662598, "learning_rate": 8.764550910961011e-07, "loss": 3.1572, "step": 17014 }, { "epoch": 0.915572535514421, "grad_norm": 3.068331003189087, "learning_rate": 8.753462089801351e-07, "loss": 4.2935, "step": 17015 }, { "epoch": 0.91562634524322, "grad_norm": 3.317286729812622, "learning_rate": 8.742380162818809e-07, "loss": 2.5357, "step": 17016 }, { "epoch": 0.9156801549720189, "grad_norm": 2.761953115463257, "learning_rate": 8.731305130330131e-07, "loss": 3.7354, "step": 17017 }, { "epoch": 0.9157339647008179, "grad_norm": 3.3114688396453857, "learning_rate": 8.720236992651814e-07, "loss": 4.157, "step": 17018 }, { "epoch": 0.9157877744296169, "grad_norm": 4.259372234344482, "learning_rate": 8.70917575010019e-07, "loss": 3.135, "step": 17019 }, { "epoch": 0.9158415841584159, "grad_norm": 2.1944727897644043, "learning_rate": 8.698121402991311e-07, "loss": 3.6509, "step": 17020 }, { "epoch": 0.9158953938872149, "grad_norm": 4.776910781860352, "learning_rate": 8.687073951641089e-07, "loss": 2.9959, "step": 17021 }, { "epoch": 0.9159492036160137, "grad_norm": 3.7194151878356934, "learning_rate": 8.676033396365246e-07, "loss": 3.8574, "step": 17022 }, { "epoch": 0.9160030133448127, "grad_norm": 2.886206865310669, "learning_rate": 8.664999737479307e-07, "loss": 4.2948, "step": 17023 }, { "epoch": 0.9160568230736117, "grad_norm": 2.0746381282806396, "learning_rate": 8.653972975298519e-07, "loss": 4.2208, "step": 17024 }, { "epoch": 0.9161106328024107, "grad_norm": 2.595463752746582, "learning_rate": 8.642953110138074e-07, "loss": 3.6902, "step": 17025 }, { "epoch": 0.9161644425312097, "grad_norm": 1.5967285633087158, "learning_rate": 8.631940142312833e-07, "loss": 3.7718, "step": 17026 }, { "epoch": 0.9162182522600086, "grad_norm": 3.9884932041168213, "learning_rate": 8.620934072137544e-07, "loss": 2.9867, "step": 17027 }, { "epoch": 0.9162720619888076, "grad_norm": 2.6612913608551025, "learning_rate": 8.609934899926703e-07, "loss": 4.241, "step": 17028 }, { "epoch": 0.9163258717176065, "grad_norm": 3.1485519409179688, "learning_rate": 8.598942625994672e-07, "loss": 4.1577, "step": 17029 }, { "epoch": 0.9163796814464055, "grad_norm": 2.501244306564331, "learning_rate": 8.587957250655615e-07, "loss": 3.6919, "step": 17030 }, { "epoch": 0.9164334911752045, "grad_norm": 2.1484532356262207, "learning_rate": 8.576978774223393e-07, "loss": 4.0107, "step": 17031 }, { "epoch": 0.9164873009040034, "grad_norm": 3.7153358459472656, "learning_rate": 8.566007197011728e-07, "loss": 3.9113, "step": 17032 }, { "epoch": 0.9165411106328024, "grad_norm": 3.0534799098968506, "learning_rate": 8.5550425193342e-07, "loss": 3.9417, "step": 17033 }, { "epoch": 0.9165949203616014, "grad_norm": 2.4742417335510254, "learning_rate": 8.544084741504171e-07, "loss": 3.905, "step": 17034 }, { "epoch": 0.9166487300904004, "grad_norm": 1.5912628173828125, "learning_rate": 8.53313386383478e-07, "loss": 4.4911, "step": 17035 }, { "epoch": 0.9167025398191994, "grad_norm": 2.8003652095794678, "learning_rate": 8.522189886638915e-07, "loss": 3.0993, "step": 17036 }, { "epoch": 0.9167563495479982, "grad_norm": 2.4589738845825195, "learning_rate": 8.511252810229381e-07, "loss": 4.2368, "step": 17037 }, { "epoch": 0.9168101592767972, "grad_norm": 2.1178231239318848, "learning_rate": 8.500322634918706e-07, "loss": 4.3444, "step": 17038 }, { "epoch": 0.9168639690055962, "grad_norm": 3.2806453704833984, "learning_rate": 8.489399361019279e-07, "loss": 4.0826, "step": 17039 }, { "epoch": 0.9169177787343952, "grad_norm": 1.4982542991638184, "learning_rate": 8.478482988843212e-07, "loss": 4.1206, "step": 17040 }, { "epoch": 0.9169715884631942, "grad_norm": 2.425945281982422, "learning_rate": 8.467573518702477e-07, "loss": 4.0085, "step": 17041 }, { "epoch": 0.9170253981919931, "grad_norm": 1.4934313297271729, "learning_rate": 8.456670950908851e-07, "loss": 4.4112, "step": 17042 }, { "epoch": 0.9170792079207921, "grad_norm": 2.8987233638763428, "learning_rate": 8.445775285773866e-07, "loss": 4.02, "step": 17043 }, { "epoch": 0.9171330176495911, "grad_norm": 2.19844913482666, "learning_rate": 8.434886523608937e-07, "loss": 3.8456, "step": 17044 }, { "epoch": 0.91718682737839, "grad_norm": 2.826693058013916, "learning_rate": 8.424004664725232e-07, "loss": 4.0287, "step": 17045 }, { "epoch": 0.917240637107189, "grad_norm": 1.9340803623199463, "learning_rate": 8.413129709433754e-07, "loss": 4.3293, "step": 17046 }, { "epoch": 0.9172944468359879, "grad_norm": 3.1337568759918213, "learning_rate": 8.402261658045168e-07, "loss": 3.664, "step": 17047 }, { "epoch": 0.9173482565647869, "grad_norm": 4.38338041305542, "learning_rate": 8.391400510870117e-07, "loss": 3.7362, "step": 17048 }, { "epoch": 0.9174020662935859, "grad_norm": 1.8482078313827515, "learning_rate": 8.380546268219019e-07, "loss": 3.6642, "step": 17049 }, { "epoch": 0.9174558760223849, "grad_norm": 2.862762928009033, "learning_rate": 8.369698930402043e-07, "loss": 3.1149, "step": 17050 }, { "epoch": 0.9175096857511839, "grad_norm": 3.3964717388153076, "learning_rate": 8.358858497729133e-07, "loss": 3.5045, "step": 17051 }, { "epoch": 0.9175634954799827, "grad_norm": 1.9299288988113403, "learning_rate": 8.348024970510127e-07, "loss": 3.9691, "step": 17052 }, { "epoch": 0.9176173052087817, "grad_norm": 2.733668327331543, "learning_rate": 8.337198349054581e-07, "loss": 3.5758, "step": 17053 }, { "epoch": 0.9176711149375807, "grad_norm": 2.8594467639923096, "learning_rate": 8.326378633671916e-07, "loss": 3.8122, "step": 17054 }, { "epoch": 0.9177249246663797, "grad_norm": 7.645090579986572, "learning_rate": 8.315565824671329e-07, "loss": 4.5383, "step": 17055 }, { "epoch": 0.9177787343951787, "grad_norm": 3.0659894943237305, "learning_rate": 8.304759922361821e-07, "loss": 4.2693, "step": 17056 }, { "epoch": 0.9178325441239776, "grad_norm": 2.369962215423584, "learning_rate": 8.293960927052175e-07, "loss": 3.7242, "step": 17057 }, { "epoch": 0.9178863538527766, "grad_norm": 3.4372072219848633, "learning_rate": 8.283168839051004e-07, "loss": 3.9084, "step": 17058 }, { "epoch": 0.9179401635815756, "grad_norm": 2.1398487091064453, "learning_rate": 8.272383658666755e-07, "loss": 3.7338, "step": 17059 }, { "epoch": 0.9179939733103745, "grad_norm": 2.55507493019104, "learning_rate": 8.261605386207599e-07, "loss": 3.0516, "step": 17060 }, { "epoch": 0.9180477830391734, "grad_norm": 3.326040506362915, "learning_rate": 8.250834021981596e-07, "loss": 3.1336, "step": 17061 }, { "epoch": 0.9181015927679724, "grad_norm": 2.8305563926696777, "learning_rate": 8.240069566296499e-07, "loss": 3.1274, "step": 17062 }, { "epoch": 0.9181554024967714, "grad_norm": 3.8346431255340576, "learning_rate": 8.229312019459922e-07, "loss": 3.9224, "step": 17063 }, { "epoch": 0.9182092122255704, "grad_norm": 3.2766289710998535, "learning_rate": 8.218561381779344e-07, "loss": 3.7099, "step": 17064 }, { "epoch": 0.9182630219543694, "grad_norm": 1.5024011135101318, "learning_rate": 8.207817653561961e-07, "loss": 4.394, "step": 17065 }, { "epoch": 0.9183168316831684, "grad_norm": 3.351396083831787, "learning_rate": 8.197080835114807e-07, "loss": 3.6965, "step": 17066 }, { "epoch": 0.9183706414119673, "grad_norm": 1.9289206266403198, "learning_rate": 8.186350926744718e-07, "loss": 4.2398, "step": 17067 }, { "epoch": 0.9184244511407662, "grad_norm": 3.134073495864868, "learning_rate": 8.175627928758339e-07, "loss": 3.1474, "step": 17068 }, { "epoch": 0.9184782608695652, "grad_norm": 4.807254314422607, "learning_rate": 8.164911841462064e-07, "loss": 4.0078, "step": 17069 }, { "epoch": 0.9185320705983642, "grad_norm": 4.123622417449951, "learning_rate": 8.154202665162147e-07, "loss": 3.5604, "step": 17070 }, { "epoch": 0.9185858803271632, "grad_norm": 3.500654697418213, "learning_rate": 8.143500400164622e-07, "loss": 4.4034, "step": 17071 }, { "epoch": 0.9186396900559621, "grad_norm": 2.493010997772217, "learning_rate": 8.132805046775327e-07, "loss": 3.8927, "step": 17072 }, { "epoch": 0.9186934997847611, "grad_norm": 3.2041256427764893, "learning_rate": 8.122116605299935e-07, "loss": 3.4737, "step": 17073 }, { "epoch": 0.9187473095135601, "grad_norm": 3.2414422035217285, "learning_rate": 8.111435076043866e-07, "loss": 3.6922, "step": 17074 }, { "epoch": 0.918801119242359, "grad_norm": 2.6453206539154053, "learning_rate": 8.100760459312379e-07, "loss": 3.567, "step": 17075 }, { "epoch": 0.918854928971158, "grad_norm": 3.7623367309570312, "learning_rate": 8.090092755410561e-07, "loss": 3.7185, "step": 17076 }, { "epoch": 0.9189087386999569, "grad_norm": 4.188459873199463, "learning_rate": 8.079431964643197e-07, "loss": 3.6484, "step": 17077 }, { "epoch": 0.9189625484287559, "grad_norm": 2.7874915599823, "learning_rate": 8.068778087314987e-07, "loss": 3.5401, "step": 17078 }, { "epoch": 0.9190163581575549, "grad_norm": 1.9887686967849731, "learning_rate": 8.058131123730355e-07, "loss": 4.2537, "step": 17079 }, { "epoch": 0.9190701678863539, "grad_norm": 4.012415409088135, "learning_rate": 8.047491074193614e-07, "loss": 3.5753, "step": 17080 }, { "epoch": 0.9191239776151529, "grad_norm": 3.0653083324432373, "learning_rate": 8.036857939008796e-07, "loss": 3.7479, "step": 17081 }, { "epoch": 0.9191777873439518, "grad_norm": 2.3270392417907715, "learning_rate": 8.026231718479771e-07, "loss": 3.5096, "step": 17082 }, { "epoch": 0.9192315970727507, "grad_norm": 1.686123251914978, "learning_rate": 8.015612412910211e-07, "loss": 3.837, "step": 17083 }, { "epoch": 0.9192854068015497, "grad_norm": 3.9164724349975586, "learning_rate": 8.005000022603598e-07, "loss": 4.118, "step": 17084 }, { "epoch": 0.9193392165303487, "grad_norm": 2.4721157550811768, "learning_rate": 7.994394547863188e-07, "loss": 3.8557, "step": 17085 }, { "epoch": 0.9193930262591476, "grad_norm": 2.8728935718536377, "learning_rate": 7.983795988992071e-07, "loss": 3.1694, "step": 17086 }, { "epoch": 0.9194468359879466, "grad_norm": 3.8791909217834473, "learning_rate": 7.973204346293089e-07, "loss": 3.0061, "step": 17087 }, { "epoch": 0.9195006457167456, "grad_norm": 3.357719898223877, "learning_rate": 7.962619620068973e-07, "loss": 3.8865, "step": 17088 }, { "epoch": 0.9195544554455446, "grad_norm": 2.135329008102417, "learning_rate": 7.952041810622174e-07, "loss": 3.1474, "step": 17089 }, { "epoch": 0.9196082651743436, "grad_norm": 2.2789113521575928, "learning_rate": 7.941470918254979e-07, "loss": 3.5748, "step": 17090 }, { "epoch": 0.9196620749031424, "grad_norm": 4.59016227722168, "learning_rate": 7.930906943269506e-07, "loss": 2.6282, "step": 17091 }, { "epoch": 0.9197158846319414, "grad_norm": 4.176050662994385, "learning_rate": 7.920349885967654e-07, "loss": 3.3533, "step": 17092 }, { "epoch": 0.9197696943607404, "grad_norm": 3.3938279151916504, "learning_rate": 7.909799746651042e-07, "loss": 3.6834, "step": 17093 }, { "epoch": 0.9198235040895394, "grad_norm": 2.65397572517395, "learning_rate": 7.899256525621207e-07, "loss": 4.1744, "step": 17094 }, { "epoch": 0.9198773138183384, "grad_norm": 3.48152756690979, "learning_rate": 7.888720223179436e-07, "loss": 3.8768, "step": 17095 }, { "epoch": 0.9199311235471374, "grad_norm": 2.454073190689087, "learning_rate": 7.878190839626875e-07, "loss": 3.7613, "step": 17096 }, { "epoch": 0.9199849332759363, "grad_norm": 1.719165563583374, "learning_rate": 7.86766837526437e-07, "loss": 3.8831, "step": 17097 }, { "epoch": 0.9200387430047352, "grad_norm": 1.8062210083007812, "learning_rate": 7.857152830392622e-07, "loss": 4.4647, "step": 17098 }, { "epoch": 0.9200925527335342, "grad_norm": 2.9900810718536377, "learning_rate": 7.846644205312198e-07, "loss": 4.2397, "step": 17099 }, { "epoch": 0.9201463624623332, "grad_norm": 3.2848610877990723, "learning_rate": 7.836142500323329e-07, "loss": 3.1543, "step": 17100 }, { "epoch": 0.9202001721911321, "grad_norm": 1.6475064754486084, "learning_rate": 7.825647715726192e-07, "loss": 4.3891, "step": 17101 }, { "epoch": 0.9202539819199311, "grad_norm": 3.1719048023223877, "learning_rate": 7.815159851820658e-07, "loss": 3.7423, "step": 17102 }, { "epoch": 0.9203077916487301, "grad_norm": 3.2496140003204346, "learning_rate": 7.80467890890646e-07, "loss": 3.8231, "step": 17103 }, { "epoch": 0.9203616013775291, "grad_norm": 2.9422199726104736, "learning_rate": 7.794204887283108e-07, "loss": 3.7772, "step": 17104 }, { "epoch": 0.9204154111063281, "grad_norm": 2.614607810974121, "learning_rate": 7.783737787249889e-07, "loss": 4.6197, "step": 17105 }, { "epoch": 0.9204692208351269, "grad_norm": 3.7278504371643066, "learning_rate": 7.773277609105983e-07, "loss": 3.8782, "step": 17106 }, { "epoch": 0.9205230305639259, "grad_norm": 2.5753204822540283, "learning_rate": 7.762824353150344e-07, "loss": 3.9321, "step": 17107 }, { "epoch": 0.9205768402927249, "grad_norm": 2.208376407623291, "learning_rate": 7.752378019681594e-07, "loss": 3.4907, "step": 17108 }, { "epoch": 0.9206306500215239, "grad_norm": 2.7171833515167236, "learning_rate": 7.7419386089983e-07, "loss": 3.934, "step": 17109 }, { "epoch": 0.9206844597503229, "grad_norm": 2.9010393619537354, "learning_rate": 7.731506121398807e-07, "loss": 4.201, "step": 17110 }, { "epoch": 0.9207382694791219, "grad_norm": 2.3412787914276123, "learning_rate": 7.721080557181265e-07, "loss": 4.0182, "step": 17111 }, { "epoch": 0.9207920792079208, "grad_norm": 2.5637755393981934, "learning_rate": 7.710661916643575e-07, "loss": 4.2803, "step": 17112 }, { "epoch": 0.9208458889367198, "grad_norm": 2.2277705669403076, "learning_rate": 7.700250200083469e-07, "loss": 3.6247, "step": 17113 }, { "epoch": 0.9208996986655187, "grad_norm": 1.3204156160354614, "learning_rate": 7.689845407798518e-07, "loss": 4.104, "step": 17114 }, { "epoch": 0.9209535083943177, "grad_norm": 3.461740493774414, "learning_rate": 7.679447540086065e-07, "loss": 3.3117, "step": 17115 }, { "epoch": 0.9210073181231166, "grad_norm": 1.9102729558944702, "learning_rate": 7.669056597243207e-07, "loss": 4.0385, "step": 17116 }, { "epoch": 0.9210611278519156, "grad_norm": 5.001313209533691, "learning_rate": 7.658672579566928e-07, "loss": 3.4115, "step": 17117 }, { "epoch": 0.9211149375807146, "grad_norm": 2.6285459995269775, "learning_rate": 7.64829548735399e-07, "loss": 4.0124, "step": 17118 }, { "epoch": 0.9211687473095136, "grad_norm": 2.891787052154541, "learning_rate": 7.637925320900879e-07, "loss": 3.9514, "step": 17119 }, { "epoch": 0.9212225570383126, "grad_norm": 2.185177803039551, "learning_rate": 7.62756208050397e-07, "loss": 4.1025, "step": 17120 }, { "epoch": 0.9212763667671114, "grad_norm": 2.8679022789001465, "learning_rate": 7.617205766459467e-07, "loss": 2.8442, "step": 17121 }, { "epoch": 0.9213301764959104, "grad_norm": 2.5247244834899902, "learning_rate": 7.606856379063332e-07, "loss": 3.9918, "step": 17122 }, { "epoch": 0.9213839862247094, "grad_norm": 1.9356048107147217, "learning_rate": 7.596513918611214e-07, "loss": 4.0129, "step": 17123 }, { "epoch": 0.9214377959535084, "grad_norm": 3.839275360107422, "learning_rate": 7.586178385398768e-07, "loss": 3.6031, "step": 17124 }, { "epoch": 0.9214916056823074, "grad_norm": 1.999398946762085, "learning_rate": 7.575849779721284e-07, "loss": 4.2337, "step": 17125 }, { "epoch": 0.9215454154111064, "grad_norm": 1.909530758857727, "learning_rate": 7.565528101873998e-07, "loss": 4.4727, "step": 17126 }, { "epoch": 0.9215992251399053, "grad_norm": 2.657205104827881, "learning_rate": 7.555213352151868e-07, "loss": 4.0347, "step": 17127 }, { "epoch": 0.9216530348687043, "grad_norm": 3.313884735107422, "learning_rate": 7.544905530849633e-07, "loss": 3.5014, "step": 17128 }, { "epoch": 0.9217068445975032, "grad_norm": 2.8899283409118652, "learning_rate": 7.534604638261861e-07, "loss": 3.3001, "step": 17129 }, { "epoch": 0.9217606543263022, "grad_norm": 2.0626587867736816, "learning_rate": 7.524310674682928e-07, "loss": 3.8644, "step": 17130 }, { "epoch": 0.9218144640551011, "grad_norm": 1.2092052698135376, "learning_rate": 7.514023640407014e-07, "loss": 4.5139, "step": 17131 }, { "epoch": 0.9218682737839001, "grad_norm": 4.29391622543335, "learning_rate": 7.503743535728109e-07, "loss": 3.0616, "step": 17132 }, { "epoch": 0.9219220835126991, "grad_norm": 4.269790172576904, "learning_rate": 7.493470360939975e-07, "loss": 3.2053, "step": 17133 }, { "epoch": 0.9219758932414981, "grad_norm": 2.7372663021087646, "learning_rate": 7.483204116336156e-07, "loss": 4.6104, "step": 17134 }, { "epoch": 0.9220297029702971, "grad_norm": 3.467106819152832, "learning_rate": 7.472944802210113e-07, "loss": 3.8984, "step": 17135 }, { "epoch": 0.9220835126990959, "grad_norm": 3.7723586559295654, "learning_rate": 7.462692418854944e-07, "loss": 4.0454, "step": 17136 }, { "epoch": 0.9221373224278949, "grad_norm": 1.436369776725769, "learning_rate": 7.45244696656372e-07, "loss": 3.8402, "step": 17137 }, { "epoch": 0.9221911321566939, "grad_norm": 2.1900601387023926, "learning_rate": 7.442208445629179e-07, "loss": 3.9994, "step": 17138 }, { "epoch": 0.9222449418854929, "grad_norm": 2.0945897102355957, "learning_rate": 7.431976856343891e-07, "loss": 4.3776, "step": 17139 }, { "epoch": 0.9222987516142919, "grad_norm": 2.2544045448303223, "learning_rate": 7.421752199000292e-07, "loss": 4.0254, "step": 17140 }, { "epoch": 0.9223525613430908, "grad_norm": 1.662520170211792, "learning_rate": 7.411534473890536e-07, "loss": 3.7402, "step": 17141 }, { "epoch": 0.9224063710718898, "grad_norm": 2.630573272705078, "learning_rate": 7.401323681306666e-07, "loss": 4.0058, "step": 17142 }, { "epoch": 0.9224601808006888, "grad_norm": 2.539963960647583, "learning_rate": 7.39111982154042e-07, "loss": 3.9368, "step": 17143 }, { "epoch": 0.9225139905294877, "grad_norm": 2.1985721588134766, "learning_rate": 7.380922894883458e-07, "loss": 4.001, "step": 17144 }, { "epoch": 0.9225678002582867, "grad_norm": 2.0811612606048584, "learning_rate": 7.370732901627153e-07, "loss": 4.3763, "step": 17145 }, { "epoch": 0.9226216099870856, "grad_norm": 2.9406206607818604, "learning_rate": 7.360549842062691e-07, "loss": 4.3459, "step": 17146 }, { "epoch": 0.9226754197158846, "grad_norm": 3.3031396865844727, "learning_rate": 7.35037371648109e-07, "loss": 4.4022, "step": 17147 }, { "epoch": 0.9227292294446836, "grad_norm": 3.4345271587371826, "learning_rate": 7.340204525173144e-07, "loss": 3.7466, "step": 17148 }, { "epoch": 0.9227830391734826, "grad_norm": 2.6370623111724854, "learning_rate": 7.33004226842951e-07, "loss": 4.4291, "step": 17149 }, { "epoch": 0.9228368489022816, "grad_norm": 2.9915904998779297, "learning_rate": 7.319886946540539e-07, "loss": 4.4721, "step": 17150 }, { "epoch": 0.9228906586310806, "grad_norm": 2.115257501602173, "learning_rate": 7.309738559796442e-07, "loss": 3.9392, "step": 17151 }, { "epoch": 0.9229444683598794, "grad_norm": 2.692324638366699, "learning_rate": 7.299597108487294e-07, "loss": 3.5923, "step": 17152 }, { "epoch": 0.9229982780886784, "grad_norm": 2.947101593017578, "learning_rate": 7.28946259290289e-07, "loss": 3.4671, "step": 17153 }, { "epoch": 0.9230520878174774, "grad_norm": 3.8314595222473145, "learning_rate": 7.279335013332805e-07, "loss": 2.7982, "step": 17154 }, { "epoch": 0.9231058975462764, "grad_norm": 1.6967438459396362, "learning_rate": 7.269214370066474e-07, "loss": 4.4653, "step": 17155 }, { "epoch": 0.9231597072750753, "grad_norm": 2.806821584701538, "learning_rate": 7.259100663393109e-07, "loss": 3.1413, "step": 17156 }, { "epoch": 0.9232135170038743, "grad_norm": 2.6818277835845947, "learning_rate": 7.248993893601786e-07, "loss": 3.9147, "step": 17157 }, { "epoch": 0.9232673267326733, "grad_norm": 1.857085943222046, "learning_rate": 7.238894060981299e-07, "loss": 3.8127, "step": 17158 }, { "epoch": 0.9233211364614722, "grad_norm": 2.2768642902374268, "learning_rate": 7.228801165820253e-07, "loss": 3.8009, "step": 17159 }, { "epoch": 0.9233749461902712, "grad_norm": 3.4749112129211426, "learning_rate": 7.218715208407112e-07, "loss": 3.672, "step": 17160 }, { "epoch": 0.9234287559190701, "grad_norm": 2.7786192893981934, "learning_rate": 7.208636189030061e-07, "loss": 3.6514, "step": 17161 }, { "epoch": 0.9234825656478691, "grad_norm": 2.983121395111084, "learning_rate": 7.198564107977146e-07, "loss": 3.8934, "step": 17162 }, { "epoch": 0.9235363753766681, "grad_norm": 2.261195182800293, "learning_rate": 7.18849896553625e-07, "loss": 3.175, "step": 17163 }, { "epoch": 0.9235901851054671, "grad_norm": 2.0439159870147705, "learning_rate": 7.178440761994948e-07, "loss": 3.7348, "step": 17164 }, { "epoch": 0.9236439948342661, "grad_norm": 3.5184407234191895, "learning_rate": 7.168389497640677e-07, "loss": 3.6646, "step": 17165 }, { "epoch": 0.923697804563065, "grad_norm": 3.540968179702759, "learning_rate": 7.158345172760705e-07, "loss": 3.4954, "step": 17166 }, { "epoch": 0.9237516142918639, "grad_norm": 1.9097752571105957, "learning_rate": 7.148307787642056e-07, "loss": 4.0015, "step": 17167 }, { "epoch": 0.9238054240206629, "grad_norm": 2.1690447330474854, "learning_rate": 7.138277342571609e-07, "loss": 4.0742, "step": 17168 }, { "epoch": 0.9238592337494619, "grad_norm": 3.072031259536743, "learning_rate": 7.128253837835941e-07, "loss": 3.6648, "step": 17169 }, { "epoch": 0.9239130434782609, "grad_norm": 3.099191665649414, "learning_rate": 7.118237273721545e-07, "loss": 3.3895, "step": 17170 }, { "epoch": 0.9239668532070598, "grad_norm": 2.341118574142456, "learning_rate": 7.108227650514637e-07, "loss": 4.2873, "step": 17171 }, { "epoch": 0.9240206629358588, "grad_norm": 1.4628440141677856, "learning_rate": 7.098224968501266e-07, "loss": 3.7607, "step": 17172 }, { "epoch": 0.9240744726646578, "grad_norm": 1.9905507564544678, "learning_rate": 7.088229227967341e-07, "loss": 4.3519, "step": 17173 }, { "epoch": 0.9241282823934568, "grad_norm": 2.6691648960113525, "learning_rate": 7.078240429198441e-07, "loss": 3.6638, "step": 17174 }, { "epoch": 0.9241820921222557, "grad_norm": 1.9705129861831665, "learning_rate": 7.068258572480058e-07, "loss": 4.3365, "step": 17175 }, { "epoch": 0.9242359018510546, "grad_norm": 2.974489450454712, "learning_rate": 7.058283658097437e-07, "loss": 3.9359, "step": 17176 }, { "epoch": 0.9242897115798536, "grad_norm": 3.865044355392456, "learning_rate": 7.048315686335627e-07, "loss": 3.2839, "step": 17177 }, { "epoch": 0.9243435213086526, "grad_norm": 1.6000369787216187, "learning_rate": 7.038354657479485e-07, "loss": 4.3262, "step": 17178 }, { "epoch": 0.9243973310374516, "grad_norm": 2.5796337127685547, "learning_rate": 7.028400571813698e-07, "loss": 3.7325, "step": 17179 }, { "epoch": 0.9244511407662506, "grad_norm": 2.2855982780456543, "learning_rate": 7.018453429622679e-07, "loss": 2.7116, "step": 17180 }, { "epoch": 0.9245049504950495, "grad_norm": 3.336915969848633, "learning_rate": 7.008513231190728e-07, "loss": 3.7055, "step": 17181 }, { "epoch": 0.9245587602238484, "grad_norm": 2.638087272644043, "learning_rate": 6.998579976801867e-07, "loss": 4.1076, "step": 17182 }, { "epoch": 0.9246125699526474, "grad_norm": 3.102238655090332, "learning_rate": 6.988653666740064e-07, "loss": 3.8035, "step": 17183 }, { "epoch": 0.9246663796814464, "grad_norm": 2.504514694213867, "learning_rate": 6.97873430128887e-07, "loss": 3.5184, "step": 17184 }, { "epoch": 0.9247201894102454, "grad_norm": 2.1457338333129883, "learning_rate": 6.968821880731807e-07, "loss": 3.9669, "step": 17185 }, { "epoch": 0.9247739991390443, "grad_norm": 3.243206739425659, "learning_rate": 6.958916405352151e-07, "loss": 4.1269, "step": 17186 }, { "epoch": 0.9248278088678433, "grad_norm": 2.0598180294036865, "learning_rate": 6.949017875432923e-07, "loss": 3.5775, "step": 17187 }, { "epoch": 0.9248816185966423, "grad_norm": 2.5643537044525146, "learning_rate": 6.939126291257065e-07, "loss": 2.9908, "step": 17188 }, { "epoch": 0.9249354283254413, "grad_norm": 3.235046863555908, "learning_rate": 6.92924165310721e-07, "loss": 4.0249, "step": 17189 }, { "epoch": 0.9249892380542402, "grad_norm": 3.167802572250366, "learning_rate": 6.919363961265857e-07, "loss": 3.7502, "step": 17190 }, { "epoch": 0.9250430477830391, "grad_norm": 3.284914016723633, "learning_rate": 6.909493216015279e-07, "loss": 3.7597, "step": 17191 }, { "epoch": 0.9250968575118381, "grad_norm": 2.9961798191070557, "learning_rate": 6.899629417637499e-07, "loss": 3.9467, "step": 17192 }, { "epoch": 0.9251506672406371, "grad_norm": 3.3807644844055176, "learning_rate": 6.889772566414487e-07, "loss": 3.4972, "step": 17193 }, { "epoch": 0.9252044769694361, "grad_norm": 3.522597074508667, "learning_rate": 6.87992266262788e-07, "loss": 3.5833, "step": 17194 }, { "epoch": 0.9252582866982351, "grad_norm": 2.4929237365722656, "learning_rate": 6.870079706559174e-07, "loss": 3.609, "step": 17195 }, { "epoch": 0.925312096427034, "grad_norm": 4.98357629776001, "learning_rate": 6.860243698489644e-07, "loss": 3.2568, "step": 17196 }, { "epoch": 0.925365906155833, "grad_norm": 3.2429003715515137, "learning_rate": 6.850414638700369e-07, "loss": 4.1771, "step": 17197 }, { "epoch": 0.9254197158846319, "grad_norm": 1.9043869972229004, "learning_rate": 6.840592527472239e-07, "loss": 3.6853, "step": 17198 }, { "epoch": 0.9254735256134309, "grad_norm": 3.9124791622161865, "learning_rate": 6.830777365085972e-07, "loss": 2.8012, "step": 17199 }, { "epoch": 0.9255273353422299, "grad_norm": 2.167149305343628, "learning_rate": 6.820969151822038e-07, "loss": 3.7641, "step": 17200 }, { "epoch": 0.9255811450710288, "grad_norm": 2.363025426864624, "learning_rate": 6.81116788796074e-07, "loss": 3.8556, "step": 17201 }, { "epoch": 0.9256349547998278, "grad_norm": 3.748687744140625, "learning_rate": 6.80137357378216e-07, "loss": 3.2299, "step": 17202 }, { "epoch": 0.9256887645286268, "grad_norm": 2.2425150871276855, "learning_rate": 6.791586209566158e-07, "loss": 4.501, "step": 17203 }, { "epoch": 0.9257425742574258, "grad_norm": 1.7328112125396729, "learning_rate": 6.781805795592483e-07, "loss": 4.1638, "step": 17204 }, { "epoch": 0.9257963839862247, "grad_norm": 2.990095615386963, "learning_rate": 6.772032332140633e-07, "loss": 3.708, "step": 17205 }, { "epoch": 0.9258501937150236, "grad_norm": 4.218732833862305, "learning_rate": 6.762265819489938e-07, "loss": 3.8123, "step": 17206 }, { "epoch": 0.9259040034438226, "grad_norm": 1.8458470106124878, "learning_rate": 6.752506257919372e-07, "loss": 4.0646, "step": 17207 }, { "epoch": 0.9259578131726216, "grad_norm": 2.8037378787994385, "learning_rate": 6.742753647707961e-07, "loss": 3.612, "step": 17208 }, { "epoch": 0.9260116229014206, "grad_norm": 2.8438096046447754, "learning_rate": 6.733007989134343e-07, "loss": 3.5786, "step": 17209 }, { "epoch": 0.9260654326302196, "grad_norm": 1.6960859298706055, "learning_rate": 6.723269282477073e-07, "loss": 4.3052, "step": 17210 }, { "epoch": 0.9261192423590185, "grad_norm": 1.8488895893096924, "learning_rate": 6.713537528014402e-07, "loss": 3.7435, "step": 17211 }, { "epoch": 0.9261730520878175, "grad_norm": 4.21805477142334, "learning_rate": 6.703812726024494e-07, "loss": 3.6029, "step": 17212 }, { "epoch": 0.9262268618166164, "grad_norm": 4.234607219696045, "learning_rate": 6.694094876785184e-07, "loss": 2.8152, "step": 17213 }, { "epoch": 0.9262806715454154, "grad_norm": 2.7346878051757812, "learning_rate": 6.684383980574277e-07, "loss": 3.6705, "step": 17214 }, { "epoch": 0.9263344812742144, "grad_norm": 4.297918319702148, "learning_rate": 6.674680037669218e-07, "loss": 3.3753, "step": 17215 }, { "epoch": 0.9263882910030133, "grad_norm": 4.118720531463623, "learning_rate": 6.66498304834734e-07, "loss": 3.9604, "step": 17216 }, { "epoch": 0.9264421007318123, "grad_norm": 4.4856648445129395, "learning_rate": 6.655293012885727e-07, "loss": 4.7175, "step": 17217 }, { "epoch": 0.9264959104606113, "grad_norm": 3.9993975162506104, "learning_rate": 6.645609931561325e-07, "loss": 3.2176, "step": 17218 }, { "epoch": 0.9265497201894103, "grad_norm": 2.4441845417022705, "learning_rate": 6.635933804650857e-07, "loss": 3.8603, "step": 17219 }, { "epoch": 0.9266035299182093, "grad_norm": 3.134878158569336, "learning_rate": 6.626264632430823e-07, "loss": 3.0947, "step": 17220 }, { "epoch": 0.9266573396470081, "grad_norm": 3.2909018993377686, "learning_rate": 6.616602415177558e-07, "loss": 3.6519, "step": 17221 }, { "epoch": 0.9267111493758071, "grad_norm": 2.5000250339508057, "learning_rate": 6.606947153167176e-07, "loss": 4.579, "step": 17222 }, { "epoch": 0.9267649591046061, "grad_norm": 2.6494197845458984, "learning_rate": 6.597298846675565e-07, "loss": 3.4929, "step": 17223 }, { "epoch": 0.9268187688334051, "grad_norm": 3.411343574523926, "learning_rate": 6.587657495978477e-07, "loss": 3.655, "step": 17224 }, { "epoch": 0.9268725785622041, "grad_norm": 3.186985731124878, "learning_rate": 6.578023101351472e-07, "loss": 4.0431, "step": 17225 }, { "epoch": 0.926926388291003, "grad_norm": 2.5805866718292236, "learning_rate": 6.568395663069798e-07, "loss": 3.8194, "step": 17226 }, { "epoch": 0.926980198019802, "grad_norm": 3.48079776763916, "learning_rate": 6.558775181408655e-07, "loss": 3.8286, "step": 17227 }, { "epoch": 0.9270340077486009, "grad_norm": 1.9131232500076294, "learning_rate": 6.549161656642933e-07, "loss": 4.0491, "step": 17228 }, { "epoch": 0.9270878174773999, "grad_norm": 2.687854528427124, "learning_rate": 6.539555089047356e-07, "loss": 3.6306, "step": 17229 }, { "epoch": 0.9271416272061989, "grad_norm": 3.206327199935913, "learning_rate": 6.529955478896455e-07, "loss": 3.8028, "step": 17230 }, { "epoch": 0.9271954369349978, "grad_norm": 1.6597661972045898, "learning_rate": 6.520362826464593e-07, "loss": 4.2618, "step": 17231 }, { "epoch": 0.9272492466637968, "grad_norm": 3.322317361831665, "learning_rate": 6.510777132025858e-07, "loss": 4.059, "step": 17232 }, { "epoch": 0.9273030563925958, "grad_norm": 2.3326961994171143, "learning_rate": 6.501198395854169e-07, "loss": 3.555, "step": 17233 }, { "epoch": 0.9273568661213948, "grad_norm": 3.5052027702331543, "learning_rate": 6.491626618223334e-07, "loss": 3.2288, "step": 17234 }, { "epoch": 0.9274106758501938, "grad_norm": 3.5861294269561768, "learning_rate": 6.482061799406857e-07, "loss": 3.2959, "step": 17235 }, { "epoch": 0.9274644855789926, "grad_norm": 1.6220484972000122, "learning_rate": 6.472503939678049e-07, "loss": 4.4431, "step": 17236 }, { "epoch": 0.9275182953077916, "grad_norm": 2.614975929260254, "learning_rate": 6.462953039310104e-07, "loss": 3.7637, "step": 17237 }, { "epoch": 0.9275721050365906, "grad_norm": 4.667035102844238, "learning_rate": 6.453409098575891e-07, "loss": 3.4531, "step": 17238 }, { "epoch": 0.9276259147653896, "grad_norm": 2.1334846019744873, "learning_rate": 6.44387211774819e-07, "loss": 4.0793, "step": 17239 }, { "epoch": 0.9276797244941886, "grad_norm": 1.9620778560638428, "learning_rate": 6.434342097099533e-07, "loss": 4.3683, "step": 17240 }, { "epoch": 0.9277335342229875, "grad_norm": 5.314066410064697, "learning_rate": 6.424819036902257e-07, "loss": 3.7482, "step": 17241 }, { "epoch": 0.9277873439517865, "grad_norm": 2.1190085411071777, "learning_rate": 6.415302937428508e-07, "loss": 4.033, "step": 17242 }, { "epoch": 0.9278411536805854, "grad_norm": 3.2195541858673096, "learning_rate": 6.40579379895026e-07, "loss": 4.4247, "step": 17243 }, { "epoch": 0.9278949634093844, "grad_norm": 5.248188018798828, "learning_rate": 6.396291621739215e-07, "loss": 3.3137, "step": 17244 }, { "epoch": 0.9279487731381834, "grad_norm": 2.661160707473755, "learning_rate": 6.386796406066958e-07, "loss": 3.8512, "step": 17245 }, { "epoch": 0.9280025828669823, "grad_norm": 2.3108437061309814, "learning_rate": 6.377308152204803e-07, "loss": 4.4545, "step": 17246 }, { "epoch": 0.9280563925957813, "grad_norm": 3.2552075386047363, "learning_rate": 6.36782686042392e-07, "loss": 4.1119, "step": 17247 }, { "epoch": 0.9281102023245803, "grad_norm": 2.7554171085357666, "learning_rate": 6.358352530995232e-07, "loss": 4.5088, "step": 17248 }, { "epoch": 0.9281640120533793, "grad_norm": 4.048270225524902, "learning_rate": 6.348885164189494e-07, "loss": 3.2365, "step": 17249 }, { "epoch": 0.9282178217821783, "grad_norm": 2.379456043243408, "learning_rate": 6.339424760277296e-07, "loss": 3.0657, "step": 17250 }, { "epoch": 0.9282716315109771, "grad_norm": 3.4700767993927, "learning_rate": 6.329971319528977e-07, "loss": 3.8076, "step": 17251 }, { "epoch": 0.9283254412397761, "grad_norm": 3.266602039337158, "learning_rate": 6.320524842214709e-07, "loss": 3.6366, "step": 17252 }, { "epoch": 0.9283792509685751, "grad_norm": 3.683781862258911, "learning_rate": 6.311085328604388e-07, "loss": 4.0948, "step": 17253 }, { "epoch": 0.9284330606973741, "grad_norm": 4.932372570037842, "learning_rate": 6.301652778967798e-07, "loss": 3.1485, "step": 17254 }, { "epoch": 0.9284868704261731, "grad_norm": 2.9551239013671875, "learning_rate": 6.292227193574501e-07, "loss": 3.3542, "step": 17255 }, { "epoch": 0.928540680154972, "grad_norm": 4.700669288635254, "learning_rate": 6.282808572693865e-07, "loss": 3.8376, "step": 17256 }, { "epoch": 0.928594489883771, "grad_norm": 3.2284348011016846, "learning_rate": 6.273396916595037e-07, "loss": 4.0312, "step": 17257 }, { "epoch": 0.92864829961257, "grad_norm": 1.3404273986816406, "learning_rate": 6.263992225546967e-07, "loss": 4.0401, "step": 17258 }, { "epoch": 0.9287021093413689, "grad_norm": 2.274897336959839, "learning_rate": 6.254594499818439e-07, "loss": 3.9567, "step": 17259 }, { "epoch": 0.9287559190701679, "grad_norm": 3.054821491241455, "learning_rate": 6.245203739677991e-07, "loss": 2.7345, "step": 17260 }, { "epoch": 0.9288097287989668, "grad_norm": 3.523491859436035, "learning_rate": 6.235819945393989e-07, "loss": 4.2472, "step": 17261 }, { "epoch": 0.9288635385277658, "grad_norm": 2.043344736099243, "learning_rate": 6.226443117234637e-07, "loss": 3.7908, "step": 17262 }, { "epoch": 0.9289173482565648, "grad_norm": 3.1754870414733887, "learning_rate": 6.217073255467832e-07, "loss": 3.0254, "step": 17263 }, { "epoch": 0.9289711579853638, "grad_norm": 3.5324885845184326, "learning_rate": 6.207710360361385e-07, "loss": 3.6291, "step": 17264 }, { "epoch": 0.9290249677141628, "grad_norm": 3.257089614868164, "learning_rate": 6.198354432182835e-07, "loss": 3.0942, "step": 17265 }, { "epoch": 0.9290787774429616, "grad_norm": 2.403637170791626, "learning_rate": 6.189005471199605e-07, "loss": 2.6389, "step": 17266 }, { "epoch": 0.9291325871717606, "grad_norm": 2.458050012588501, "learning_rate": 6.179663477678816e-07, "loss": 3.7605, "step": 17267 }, { "epoch": 0.9291863969005596, "grad_norm": 3.73755145072937, "learning_rate": 6.170328451887447e-07, "loss": 3.7116, "step": 17268 }, { "epoch": 0.9292402066293586, "grad_norm": 2.8141472339630127, "learning_rate": 6.161000394092232e-07, "loss": 3.6989, "step": 17269 }, { "epoch": 0.9292940163581576, "grad_norm": 3.9190497398376465, "learning_rate": 6.151679304559788e-07, "loss": 3.0803, "step": 17270 }, { "epoch": 0.9293478260869565, "grad_norm": 3.1514153480529785, "learning_rate": 6.142365183556487e-07, "loss": 4.2252, "step": 17271 }, { "epoch": 0.9294016358157555, "grad_norm": 2.2602274417877197, "learning_rate": 6.133058031348476e-07, "loss": 3.1465, "step": 17272 }, { "epoch": 0.9294554455445545, "grad_norm": 2.685539484024048, "learning_rate": 6.123757848201767e-07, "loss": 3.4103, "step": 17273 }, { "epoch": 0.9295092552733534, "grad_norm": 3.2066810131073, "learning_rate": 6.114464634382089e-07, "loss": 3.5484, "step": 17274 }, { "epoch": 0.9295630650021524, "grad_norm": 3.2652928829193115, "learning_rate": 6.105178390155036e-07, "loss": 3.596, "step": 17275 }, { "epoch": 0.9296168747309513, "grad_norm": 3.0130655765533447, "learning_rate": 6.095899115786008e-07, "loss": 4.0216, "step": 17276 }, { "epoch": 0.9296706844597503, "grad_norm": 1.6957318782806396, "learning_rate": 6.086626811540124e-07, "loss": 4.3596, "step": 17277 }, { "epoch": 0.9297244941885493, "grad_norm": 2.888380289077759, "learning_rate": 6.077361477682425e-07, "loss": 2.9714, "step": 17278 }, { "epoch": 0.9297783039173483, "grad_norm": 1.606671929359436, "learning_rate": 6.068103114477642e-07, "loss": 3.7743, "step": 17279 }, { "epoch": 0.9298321136461473, "grad_norm": 1.9685291051864624, "learning_rate": 6.058851722190339e-07, "loss": 4.0137, "step": 17280 }, { "epoch": 0.9298859233749462, "grad_norm": 1.7300127744674683, "learning_rate": 6.049607301084975e-07, "loss": 3.5154, "step": 17281 }, { "epoch": 0.9299397331037451, "grad_norm": 1.9830536842346191, "learning_rate": 6.04036985142567e-07, "loss": 4.1434, "step": 17282 }, { "epoch": 0.9299935428325441, "grad_norm": 4.999814987182617, "learning_rate": 6.031139373476463e-07, "loss": 3.5233, "step": 17283 }, { "epoch": 0.9300473525613431, "grad_norm": 3.917837381362915, "learning_rate": 6.02191586750106e-07, "loss": 3.4945, "step": 17284 }, { "epoch": 0.9301011622901421, "grad_norm": 2.1740715503692627, "learning_rate": 6.012699333763056e-07, "loss": 3.7986, "step": 17285 }, { "epoch": 0.930154972018941, "grad_norm": 4.190574645996094, "learning_rate": 6.003489772525878e-07, "loss": 3.6533, "step": 17286 }, { "epoch": 0.93020878174774, "grad_norm": 4.126689434051514, "learning_rate": 5.994287184052677e-07, "loss": 3.2685, "step": 17287 }, { "epoch": 0.930262591476539, "grad_norm": 2.551792860031128, "learning_rate": 5.985091568606466e-07, "loss": 3.5489, "step": 17288 }, { "epoch": 0.9303164012053379, "grad_norm": 1.892985224723816, "learning_rate": 5.975902926450006e-07, "loss": 3.863, "step": 17289 }, { "epoch": 0.9303702109341369, "grad_norm": 3.7775111198425293, "learning_rate": 5.966721257845892e-07, "loss": 3.9511, "step": 17290 }, { "epoch": 0.9304240206629358, "grad_norm": 3.9725325107574463, "learning_rate": 5.957546563056526e-07, "loss": 2.9563, "step": 17291 }, { "epoch": 0.9304778303917348, "grad_norm": 3.230353355407715, "learning_rate": 5.94837884234406e-07, "loss": 3.5867, "step": 17292 }, { "epoch": 0.9305316401205338, "grad_norm": 1.7777986526489258, "learning_rate": 5.939218095970534e-07, "loss": 3.9113, "step": 17293 }, { "epoch": 0.9305854498493328, "grad_norm": 3.6231260299682617, "learning_rate": 5.930064324197682e-07, "loss": 2.5931, "step": 17294 }, { "epoch": 0.9306392595781318, "grad_norm": 2.9873275756835938, "learning_rate": 5.920917527287101e-07, "loss": 3.7823, "step": 17295 }, { "epoch": 0.9306930693069307, "grad_norm": 1.9247018098831177, "learning_rate": 5.911777705500221e-07, "loss": 4.5792, "step": 17296 }, { "epoch": 0.9307468790357296, "grad_norm": 2.2295539379119873, "learning_rate": 5.90264485909825e-07, "loss": 3.9737, "step": 17297 }, { "epoch": 0.9308006887645286, "grad_norm": 3.758580446243286, "learning_rate": 5.893518988342117e-07, "loss": 3.1966, "step": 17298 }, { "epoch": 0.9308544984933276, "grad_norm": 2.444805383682251, "learning_rate": 5.884400093492642e-07, "loss": 3.831, "step": 17299 }, { "epoch": 0.9309083082221266, "grad_norm": 3.9995577335357666, "learning_rate": 5.875288174810395e-07, "loss": 3.3322, "step": 17300 }, { "epoch": 0.9309621179509255, "grad_norm": 3.7450599670410156, "learning_rate": 5.866183232555833e-07, "loss": 4.012, "step": 17301 }, { "epoch": 0.9310159276797245, "grad_norm": 3.797201633453369, "learning_rate": 5.857085266989082e-07, "loss": 2.9667, "step": 17302 }, { "epoch": 0.9310697374085235, "grad_norm": 2.3794541358947754, "learning_rate": 5.847994278370184e-07, "loss": 4.2271, "step": 17303 }, { "epoch": 0.9311235471373225, "grad_norm": 2.2546215057373047, "learning_rate": 5.83891026695893e-07, "loss": 4.1452, "step": 17304 }, { "epoch": 0.9311773568661214, "grad_norm": 2.053816795349121, "learning_rate": 5.829833233014892e-07, "loss": 4.0318, "step": 17305 }, { "epoch": 0.9312311665949203, "grad_norm": 3.6689085960388184, "learning_rate": 5.820763176797473e-07, "loss": 3.516, "step": 17306 }, { "epoch": 0.9312849763237193, "grad_norm": 1.802626609802246, "learning_rate": 5.811700098565881e-07, "loss": 4.005, "step": 17307 }, { "epoch": 0.9313387860525183, "grad_norm": 2.908231496810913, "learning_rate": 5.802643998579104e-07, "loss": 3.735, "step": 17308 }, { "epoch": 0.9313925957813173, "grad_norm": 2.9235424995422363, "learning_rate": 5.793594877095965e-07, "loss": 3.495, "step": 17309 }, { "epoch": 0.9314464055101163, "grad_norm": 2.7956454753875732, "learning_rate": 5.784552734375031e-07, "loss": 2.8728, "step": 17310 }, { "epoch": 0.9315002152389152, "grad_norm": 4.046078681945801, "learning_rate": 5.775517570674682e-07, "loss": 3.1557, "step": 17311 }, { "epoch": 0.9315540249677141, "grad_norm": 2.6693472862243652, "learning_rate": 5.76648938625321e-07, "loss": 3.7948, "step": 17312 }, { "epoch": 0.9316078346965131, "grad_norm": 2.6735827922821045, "learning_rate": 5.757468181368547e-07, "loss": 3.9438, "step": 17313 }, { "epoch": 0.9316616444253121, "grad_norm": 2.1610875129699707, "learning_rate": 5.748453956278515e-07, "loss": 3.3374, "step": 17314 }, { "epoch": 0.9317154541541111, "grad_norm": 3.901702642440796, "learning_rate": 5.739446711240714e-07, "loss": 4.1291, "step": 17315 }, { "epoch": 0.93176926388291, "grad_norm": 3.247105598449707, "learning_rate": 5.730446446512494e-07, "loss": 4.1829, "step": 17316 }, { "epoch": 0.931823073611709, "grad_norm": 2.779637098312378, "learning_rate": 5.721453162351148e-07, "loss": 3.2617, "step": 17317 }, { "epoch": 0.931876883340508, "grad_norm": 2.9796156883239746, "learning_rate": 5.712466859013637e-07, "loss": 3.2644, "step": 17318 }, { "epoch": 0.931930693069307, "grad_norm": 2.8451108932495117, "learning_rate": 5.703487536756757e-07, "loss": 3.9071, "step": 17319 }, { "epoch": 0.9319845027981059, "grad_norm": 3.4572854042053223, "learning_rate": 5.694515195837107e-07, "loss": 3.4507, "step": 17320 }, { "epoch": 0.9320383125269048, "grad_norm": 6.4310736656188965, "learning_rate": 5.68554983651115e-07, "loss": 4.3378, "step": 17321 }, { "epoch": 0.9320921222557038, "grad_norm": 4.0809736251831055, "learning_rate": 5.676591459035014e-07, "loss": 4.0697, "step": 17322 }, { "epoch": 0.9321459319845028, "grad_norm": 3.3120627403259277, "learning_rate": 5.66764006366477e-07, "loss": 4.1166, "step": 17323 }, { "epoch": 0.9321997417133018, "grad_norm": 4.321122169494629, "learning_rate": 5.658695650656159e-07, "loss": 4.3381, "step": 17324 }, { "epoch": 0.9322535514421008, "grad_norm": 1.795825719833374, "learning_rate": 5.649758220264867e-07, "loss": 4.268, "step": 17325 }, { "epoch": 0.9323073611708997, "grad_norm": 4.49925422668457, "learning_rate": 5.640827772746215e-07, "loss": 4.0199, "step": 17326 }, { "epoch": 0.9323611708996986, "grad_norm": 2.342115640640259, "learning_rate": 5.631904308355474e-07, "loss": 3.5808, "step": 17327 }, { "epoch": 0.9324149806284976, "grad_norm": 4.627705097198486, "learning_rate": 5.622987827347659e-07, "loss": 3.9818, "step": 17328 }, { "epoch": 0.9324687903572966, "grad_norm": 1.43027663230896, "learning_rate": 5.614078329977541e-07, "loss": 4.4872, "step": 17329 }, { "epoch": 0.9325226000860956, "grad_norm": 3.6938648223876953, "learning_rate": 5.605175816499747e-07, "loss": 2.7219, "step": 17330 }, { "epoch": 0.9325764098148945, "grad_norm": 4.204806804656982, "learning_rate": 5.596280287168659e-07, "loss": 3.6503, "step": 17331 }, { "epoch": 0.9326302195436935, "grad_norm": 3.638155937194824, "learning_rate": 5.587391742238518e-07, "loss": 3.2746, "step": 17332 }, { "epoch": 0.9326840292724925, "grad_norm": 1.7764251232147217, "learning_rate": 5.578510181963343e-07, "loss": 3.803, "step": 17333 }, { "epoch": 0.9327378390012915, "grad_norm": 3.647897243499756, "learning_rate": 5.56963560659693e-07, "loss": 3.592, "step": 17334 }, { "epoch": 0.9327916487300904, "grad_norm": 3.0872204303741455, "learning_rate": 5.560768016392909e-07, "loss": 3.9644, "step": 17335 }, { "epoch": 0.9328454584588893, "grad_norm": 2.027506113052368, "learning_rate": 5.551907411604635e-07, "loss": 4.5495, "step": 17336 }, { "epoch": 0.9328992681876883, "grad_norm": 3.377019166946411, "learning_rate": 5.543053792485375e-07, "loss": 4.033, "step": 17337 }, { "epoch": 0.9329530779164873, "grad_norm": 2.898646354675293, "learning_rate": 5.534207159288152e-07, "loss": 4.503, "step": 17338 }, { "epoch": 0.9330068876452863, "grad_norm": 3.4350147247314453, "learning_rate": 5.525367512265705e-07, "loss": 3.3525, "step": 17339 }, { "epoch": 0.9330606973740853, "grad_norm": 2.9497644901275635, "learning_rate": 5.516534851670724e-07, "loss": 3.5473, "step": 17340 }, { "epoch": 0.9331145071028842, "grad_norm": 2.9914774894714355, "learning_rate": 5.507709177755588e-07, "loss": 3.735, "step": 17341 }, { "epoch": 0.9331683168316832, "grad_norm": 1.328188180923462, "learning_rate": 5.498890490772512e-07, "loss": 4.0166, "step": 17342 }, { "epoch": 0.9332221265604821, "grad_norm": 1.6967735290527344, "learning_rate": 5.490078790973519e-07, "loss": 4.1136, "step": 17343 }, { "epoch": 0.9332759362892811, "grad_norm": 1.3358906507492065, "learning_rate": 5.481274078610432e-07, "loss": 4.2223, "step": 17344 }, { "epoch": 0.93332974601808, "grad_norm": 1.8800400495529175, "learning_rate": 5.472476353934858e-07, "loss": 4.7492, "step": 17345 }, { "epoch": 0.933383555746879, "grad_norm": 2.7726709842681885, "learning_rate": 5.463685617198178e-07, "loss": 3.9014, "step": 17346 }, { "epoch": 0.933437365475678, "grad_norm": 3.8695263862609863, "learning_rate": 5.454901868651635e-07, "loss": 3.5039, "step": 17347 }, { "epoch": 0.933491175204477, "grad_norm": 3.6919758319854736, "learning_rate": 5.446125108546251e-07, "loss": 3.1309, "step": 17348 }, { "epoch": 0.933544984933276, "grad_norm": 3.312523126602173, "learning_rate": 5.437355337132854e-07, "loss": 3.8586, "step": 17349 }, { "epoch": 0.9335987946620748, "grad_norm": 2.30429744720459, "learning_rate": 5.428592554662048e-07, "loss": 3.2082, "step": 17350 }, { "epoch": 0.9336526043908738, "grad_norm": 1.3355032205581665, "learning_rate": 5.419836761384245e-07, "loss": 3.7806, "step": 17351 }, { "epoch": 0.9337064141196728, "grad_norm": 3.2950122356414795, "learning_rate": 5.41108795754966e-07, "loss": 3.345, "step": 17352 }, { "epoch": 0.9337602238484718, "grad_norm": 3.017477035522461, "learning_rate": 5.402346143408316e-07, "loss": 4.4457, "step": 17353 }, { "epoch": 0.9338140335772708, "grad_norm": 2.590280532836914, "learning_rate": 5.39361131921004e-07, "loss": 3.6709, "step": 17354 }, { "epoch": 0.9338678433060698, "grad_norm": 3.005629062652588, "learning_rate": 5.384883485204439e-07, "loss": 3.3179, "step": 17355 }, { "epoch": 0.9339216530348687, "grad_norm": 3.946840763092041, "learning_rate": 5.376162641640897e-07, "loss": 3.0709, "step": 17356 }, { "epoch": 0.9339754627636677, "grad_norm": 3.178985595703125, "learning_rate": 5.367448788768687e-07, "loss": 3.7065, "step": 17357 }, { "epoch": 0.9340292724924666, "grad_norm": 2.9269864559173584, "learning_rate": 5.358741926836802e-07, "loss": 2.8745, "step": 17358 }, { "epoch": 0.9340830822212656, "grad_norm": 3.2470695972442627, "learning_rate": 5.350042056094073e-07, "loss": 4.3771, "step": 17359 }, { "epoch": 0.9341368919500646, "grad_norm": 2.474271535873413, "learning_rate": 5.341349176789135e-07, "loss": 3.6436, "step": 17360 }, { "epoch": 0.9341907016788635, "grad_norm": 1.6661033630371094, "learning_rate": 5.332663289170342e-07, "loss": 4.3068, "step": 17361 }, { "epoch": 0.9342445114076625, "grad_norm": 2.956228494644165, "learning_rate": 5.323984393485942e-07, "loss": 4.0709, "step": 17362 }, { "epoch": 0.9342983211364615, "grad_norm": 2.979151487350464, "learning_rate": 5.315312489983987e-07, "loss": 2.9268, "step": 17363 }, { "epoch": 0.9343521308652605, "grad_norm": 2.2811150550842285, "learning_rate": 5.306647578912305e-07, "loss": 3.6781, "step": 17364 }, { "epoch": 0.9344059405940595, "grad_norm": 2.514167308807373, "learning_rate": 5.297989660518448e-07, "loss": 4.2273, "step": 17365 }, { "epoch": 0.9344597503228583, "grad_norm": 2.5980076789855957, "learning_rate": 5.289338735049915e-07, "loss": 3.1087, "step": 17366 }, { "epoch": 0.9345135600516573, "grad_norm": 2.5528650283813477, "learning_rate": 5.280694802753839e-07, "loss": 3.7796, "step": 17367 }, { "epoch": 0.9345673697804563, "grad_norm": 3.787593126296997, "learning_rate": 5.272057863877328e-07, "loss": 3.7099, "step": 17368 }, { "epoch": 0.9346211795092553, "grad_norm": 2.8667290210723877, "learning_rate": 5.263427918667157e-07, "loss": 2.9954, "step": 17369 }, { "epoch": 0.9346749892380543, "grad_norm": 2.8940963745117188, "learning_rate": 5.254804967369936e-07, "loss": 3.6658, "step": 17370 }, { "epoch": 0.9347287989668532, "grad_norm": 2.9139885902404785, "learning_rate": 5.246189010232106e-07, "loss": 3.7672, "step": 17371 }, { "epoch": 0.9347826086956522, "grad_norm": 3.3254098892211914, "learning_rate": 5.237580047499885e-07, "loss": 3.2031, "step": 17372 }, { "epoch": 0.9348364184244511, "grad_norm": 2.3677382469177246, "learning_rate": 5.228978079419272e-07, "loss": 3.8352, "step": 17373 }, { "epoch": 0.9348902281532501, "grad_norm": 2.728745698928833, "learning_rate": 5.220383106236154e-07, "loss": 3.1044, "step": 17374 }, { "epoch": 0.934944037882049, "grad_norm": 5.686651229858398, "learning_rate": 5.211795128196084e-07, "loss": 3.6144, "step": 17375 }, { "epoch": 0.934997847610848, "grad_norm": 2.5595133304595947, "learning_rate": 5.203214145544505e-07, "loss": 3.5282, "step": 17376 }, { "epoch": 0.935051657339647, "grad_norm": 2.8758249282836914, "learning_rate": 5.194640158526637e-07, "loss": 3.6185, "step": 17377 }, { "epoch": 0.935105467068446, "grad_norm": 2.8303170204162598, "learning_rate": 5.186073167387479e-07, "loss": 3.4402, "step": 17378 }, { "epoch": 0.935159276797245, "grad_norm": 1.9452780485153198, "learning_rate": 5.177513172371917e-07, "loss": 4.0866, "step": 17379 }, { "epoch": 0.935213086526044, "grad_norm": 2.813884735107422, "learning_rate": 5.168960173724535e-07, "loss": 3.5306, "step": 17380 }, { "epoch": 0.9352668962548428, "grad_norm": 2.4573845863342285, "learning_rate": 5.160414171689721e-07, "loss": 3.4271, "step": 17381 }, { "epoch": 0.9353207059836418, "grad_norm": 2.9171302318573, "learning_rate": 5.151875166511749e-07, "loss": 3.3557, "step": 17382 }, { "epoch": 0.9353745157124408, "grad_norm": 2.4612295627593994, "learning_rate": 5.143343158434621e-07, "loss": 3.7246, "step": 17383 }, { "epoch": 0.9354283254412398, "grad_norm": 2.3478565216064453, "learning_rate": 5.134818147702169e-07, "loss": 4.4092, "step": 17384 }, { "epoch": 0.9354821351700388, "grad_norm": 2.768629550933838, "learning_rate": 5.126300134558004e-07, "loss": 4.5118, "step": 17385 }, { "epoch": 0.9355359448988377, "grad_norm": 2.8389880657196045, "learning_rate": 5.117789119245515e-07, "loss": 3.7754, "step": 17386 }, { "epoch": 0.9355897546276367, "grad_norm": 1.4430139064788818, "learning_rate": 5.109285102007977e-07, "loss": 3.9875, "step": 17387 }, { "epoch": 0.9356435643564357, "grad_norm": 1.2469615936279297, "learning_rate": 5.100788083088392e-07, "loss": 4.6133, "step": 17388 }, { "epoch": 0.9356973740852346, "grad_norm": 1.934620976448059, "learning_rate": 5.092298062729567e-07, "loss": 4.1749, "step": 17389 }, { "epoch": 0.9357511838140335, "grad_norm": 3.5333054065704346, "learning_rate": 5.083815041174194e-07, "loss": 3.3389, "step": 17390 }, { "epoch": 0.9358049935428325, "grad_norm": 1.183376431465149, "learning_rate": 5.07533901866461e-07, "loss": 4.3332, "step": 17391 }, { "epoch": 0.9358588032716315, "grad_norm": 3.2185616493225098, "learning_rate": 5.066869995443063e-07, "loss": 3.7229, "step": 17392 }, { "epoch": 0.9359126130004305, "grad_norm": 2.7376480102539062, "learning_rate": 5.058407971751527e-07, "loss": 4.1736, "step": 17393 }, { "epoch": 0.9359664227292295, "grad_norm": 2.3550865650177, "learning_rate": 5.049952947831948e-07, "loss": 4.7704, "step": 17394 }, { "epoch": 0.9360202324580285, "grad_norm": 2.3337061405181885, "learning_rate": 5.041504923925855e-07, "loss": 3.9301, "step": 17395 }, { "epoch": 0.9360740421868273, "grad_norm": 2.7910079956054688, "learning_rate": 5.033063900274665e-07, "loss": 3.6586, "step": 17396 }, { "epoch": 0.9361278519156263, "grad_norm": 2.209531307220459, "learning_rate": 5.024629877119685e-07, "loss": 3.966, "step": 17397 }, { "epoch": 0.9361816616444253, "grad_norm": 2.9835703372955322, "learning_rate": 5.016202854701807e-07, "loss": 3.8481, "step": 17398 }, { "epoch": 0.9362354713732243, "grad_norm": 2.0315756797790527, "learning_rate": 5.007782833261949e-07, "loss": 4.1711, "step": 17399 }, { "epoch": 0.9362892811020233, "grad_norm": 3.236236333847046, "learning_rate": 4.999369813040722e-07, "loss": 3.8708, "step": 17400 }, { "epoch": 0.9363430908308222, "grad_norm": 3.2383244037628174, "learning_rate": 4.990963794278519e-07, "loss": 3.3744, "step": 17401 }, { "epoch": 0.9363969005596212, "grad_norm": 1.5328742265701294, "learning_rate": 4.982564777215565e-07, "loss": 3.3299, "step": 17402 }, { "epoch": 0.9364507102884202, "grad_norm": 2.7814033031463623, "learning_rate": 4.974172762091916e-07, "loss": 3.8246, "step": 17403 }, { "epoch": 0.9365045200172191, "grad_norm": 4.487266540527344, "learning_rate": 4.965787749147327e-07, "loss": 3.6936, "step": 17404 }, { "epoch": 0.936558329746018, "grad_norm": 1.638056993484497, "learning_rate": 4.957409738621494e-07, "loss": 4.4407, "step": 17405 }, { "epoch": 0.936612139474817, "grad_norm": 1.8579727411270142, "learning_rate": 4.949038730753807e-07, "loss": 4.2055, "step": 17406 }, { "epoch": 0.936665949203616, "grad_norm": 3.588736057281494, "learning_rate": 4.940674725783467e-07, "loss": 3.9251, "step": 17407 }, { "epoch": 0.936719758932415, "grad_norm": 2.898749589920044, "learning_rate": 4.932317723949531e-07, "loss": 3.2765, "step": 17408 }, { "epoch": 0.936773568661214, "grad_norm": 2.7335574626922607, "learning_rate": 4.923967725490752e-07, "loss": 4.4656, "step": 17409 }, { "epoch": 0.936827378390013, "grad_norm": 1.7258124351501465, "learning_rate": 4.915624730645829e-07, "loss": 3.7456, "step": 17410 }, { "epoch": 0.9368811881188119, "grad_norm": 1.4612109661102295, "learning_rate": 4.907288739653154e-07, "loss": 4.6432, "step": 17411 }, { "epoch": 0.9369349978476108, "grad_norm": 2.5564002990722656, "learning_rate": 4.898959752750953e-07, "loss": 3.7099, "step": 17412 }, { "epoch": 0.9369888075764098, "grad_norm": 2.0157594680786133, "learning_rate": 4.890637770177204e-07, "loss": 4.1454, "step": 17413 }, { "epoch": 0.9370426173052088, "grad_norm": 3.071307420730591, "learning_rate": 4.882322792169797e-07, "loss": 3.2825, "step": 17414 }, { "epoch": 0.9370964270340078, "grad_norm": 4.987387180328369, "learning_rate": 4.874014818966293e-07, "loss": 2.903, "step": 17415 }, { "epoch": 0.9371502367628067, "grad_norm": 3.0139849185943604, "learning_rate": 4.865713850804143e-07, "loss": 3.6348, "step": 17416 }, { "epoch": 0.9372040464916057, "grad_norm": 2.4140543937683105, "learning_rate": 4.857419887920572e-07, "loss": 3.8829, "step": 17417 }, { "epoch": 0.9372578562204047, "grad_norm": 1.7597215175628662, "learning_rate": 4.849132930552558e-07, "loss": 3.7615, "step": 17418 }, { "epoch": 0.9373116659492036, "grad_norm": 2.3008503913879395, "learning_rate": 4.840852978936939e-07, "loss": 4.0689, "step": 17419 }, { "epoch": 0.9373654756780025, "grad_norm": 3.3337385654449463, "learning_rate": 4.832580033310386e-07, "loss": 4.0703, "step": 17420 }, { "epoch": 0.9374192854068015, "grad_norm": 3.6248035430908203, "learning_rate": 4.824314093909266e-07, "loss": 3.0777, "step": 17421 }, { "epoch": 0.9374730951356005, "grad_norm": 3.0653207302093506, "learning_rate": 4.816055160969779e-07, "loss": 3.1344, "step": 17422 }, { "epoch": 0.9375269048643995, "grad_norm": 1.8333243131637573, "learning_rate": 4.807803234727987e-07, "loss": 4.7585, "step": 17423 }, { "epoch": 0.9375807145931985, "grad_norm": 2.5746288299560547, "learning_rate": 4.799558315419644e-07, "loss": 3.2395, "step": 17424 }, { "epoch": 0.9376345243219975, "grad_norm": 2.903783082962036, "learning_rate": 4.791320403280452e-07, "loss": 3.2263, "step": 17425 }, { "epoch": 0.9376883340507964, "grad_norm": 2.0306570529937744, "learning_rate": 4.783089498545779e-07, "loss": 4.2978, "step": 17426 }, { "epoch": 0.9377421437795953, "grad_norm": 2.8836987018585205, "learning_rate": 4.774865601450851e-07, "loss": 4.4933, "step": 17427 }, { "epoch": 0.9377959535083943, "grad_norm": 2.260582685470581, "learning_rate": 4.7666487122307314e-07, "loss": 3.6687, "step": 17428 }, { "epoch": 0.9378497632371933, "grad_norm": 2.398548126220703, "learning_rate": 4.758438831120121e-07, "loss": 3.6717, "step": 17429 }, { "epoch": 0.9379035729659922, "grad_norm": 2.699765920639038, "learning_rate": 4.750235958353749e-07, "loss": 4.3828, "step": 17430 }, { "epoch": 0.9379573826947912, "grad_norm": 3.0075833797454834, "learning_rate": 4.742040094165956e-07, "loss": 4.1401, "step": 17431 }, { "epoch": 0.9380111924235902, "grad_norm": 2.7841124534606934, "learning_rate": 4.733851238791026e-07, "loss": 3.1509, "step": 17432 }, { "epoch": 0.9380650021523892, "grad_norm": 2.157636880874634, "learning_rate": 4.7256693924629115e-07, "loss": 3.6386, "step": 17433 }, { "epoch": 0.9381188118811881, "grad_norm": 1.6344980001449585, "learning_rate": 4.7174945554154803e-07, "loss": 4.2856, "step": 17434 }, { "epoch": 0.938172621609987, "grad_norm": 2.3789541721343994, "learning_rate": 4.709326727882296e-07, "loss": 3.4662, "step": 17435 }, { "epoch": 0.938226431338786, "grad_norm": 2.302203893661499, "learning_rate": 4.701165910096811e-07, "loss": 2.413, "step": 17436 }, { "epoch": 0.938280241067585, "grad_norm": 2.5768778324127197, "learning_rate": 4.693012102292255e-07, "loss": 4.1285, "step": 17437 }, { "epoch": 0.938334050796384, "grad_norm": 3.2444534301757812, "learning_rate": 4.68486530470158e-07, "loss": 2.8129, "step": 17438 }, { "epoch": 0.938387860525183, "grad_norm": 2.1468863487243652, "learning_rate": 4.6767255175576286e-07, "loss": 3.6594, "step": 17439 }, { "epoch": 0.938441670253982, "grad_norm": 3.219127655029297, "learning_rate": 4.66859274109302e-07, "loss": 4.0138, "step": 17440 }, { "epoch": 0.9384954799827809, "grad_norm": 3.829000473022461, "learning_rate": 4.6604669755402064e-07, "loss": 3.609, "step": 17441 }, { "epoch": 0.9385492897115798, "grad_norm": 1.3002368211746216, "learning_rate": 4.6523482211313365e-07, "loss": 4.0704, "step": 17442 }, { "epoch": 0.9386030994403788, "grad_norm": 2.754570245742798, "learning_rate": 4.644236478098446e-07, "loss": 4.4635, "step": 17443 }, { "epoch": 0.9386569091691778, "grad_norm": 3.3925352096557617, "learning_rate": 4.63613174667335e-07, "loss": 3.7796, "step": 17444 }, { "epoch": 0.9387107188979767, "grad_norm": 3.082730293273926, "learning_rate": 4.628034027087641e-07, "loss": 3.3035, "step": 17445 }, { "epoch": 0.9387645286267757, "grad_norm": 2.0619282722473145, "learning_rate": 4.6199433195727726e-07, "loss": 4.1956, "step": 17446 }, { "epoch": 0.9388183383555747, "grad_norm": 2.064704179763794, "learning_rate": 4.611859624359921e-07, "loss": 3.6559, "step": 17447 }, { "epoch": 0.9388721480843737, "grad_norm": 1.9577038288116455, "learning_rate": 4.6037829416800957e-07, "loss": 3.3676, "step": 17448 }, { "epoch": 0.9389259578131727, "grad_norm": 3.0717477798461914, "learning_rate": 4.5957132717641126e-07, "loss": 3.5691, "step": 17449 }, { "epoch": 0.9389797675419715, "grad_norm": 4.080902576446533, "learning_rate": 4.587650614842592e-07, "loss": 3.343, "step": 17450 }, { "epoch": 0.9390335772707705, "grad_norm": 5.915733337402344, "learning_rate": 4.579594971145962e-07, "loss": 2.4507, "step": 17451 }, { "epoch": 0.9390873869995695, "grad_norm": 3.0692362785339355, "learning_rate": 4.5715463409043703e-07, "loss": 1.7091, "step": 17452 }, { "epoch": 0.9391411967283685, "grad_norm": 4.481287002563477, "learning_rate": 4.5635047243478556e-07, "loss": 4.1592, "step": 17453 }, { "epoch": 0.9391950064571675, "grad_norm": 2.4467198848724365, "learning_rate": 4.5554701217062625e-07, "loss": 3.7984, "step": 17454 }, { "epoch": 0.9392488161859665, "grad_norm": 3.1488006114959717, "learning_rate": 4.5474425332091286e-07, "loss": 2.659, "step": 17455 }, { "epoch": 0.9393026259147654, "grad_norm": 1.8970974683761597, "learning_rate": 4.53942195908591e-07, "loss": 4.0624, "step": 17456 }, { "epoch": 0.9393564356435643, "grad_norm": 3.8248138427734375, "learning_rate": 4.531408399565784e-07, "loss": 3.9123, "step": 17457 }, { "epoch": 0.9394102453723633, "grad_norm": 3.7815957069396973, "learning_rate": 4.523401854877818e-07, "loss": 4.1277, "step": 17458 }, { "epoch": 0.9394640551011623, "grad_norm": 2.507615804672241, "learning_rate": 4.515402325250745e-07, "loss": 3.9763, "step": 17459 }, { "epoch": 0.9395178648299612, "grad_norm": 3.7950453758239746, "learning_rate": 4.507409810913188e-07, "loss": 3.3927, "step": 17460 }, { "epoch": 0.9395716745587602, "grad_norm": 2.70049786567688, "learning_rate": 4.4994243120935753e-07, "loss": 3.8072, "step": 17461 }, { "epoch": 0.9396254842875592, "grad_norm": 3.4191112518310547, "learning_rate": 4.4914458290200857e-07, "loss": 4.1904, "step": 17462 }, { "epoch": 0.9396792940163582, "grad_norm": 2.448333501815796, "learning_rate": 4.4834743619207587e-07, "loss": 3.6181, "step": 17463 }, { "epoch": 0.9397331037451572, "grad_norm": 2.726351737976074, "learning_rate": 4.4755099110233566e-07, "loss": 3.8363, "step": 17464 }, { "epoch": 0.939786913473956, "grad_norm": 2.792600631713867, "learning_rate": 4.4675524765554757e-07, "loss": 3.2273, "step": 17465 }, { "epoch": 0.939840723202755, "grad_norm": 2.7954070568084717, "learning_rate": 4.459602058744572e-07, "loss": 3.4416, "step": 17466 }, { "epoch": 0.939894532931554, "grad_norm": 1.4458194971084595, "learning_rate": 4.4516586578177974e-07, "loss": 3.3249, "step": 17467 }, { "epoch": 0.939948342660353, "grad_norm": 2.4804112911224365, "learning_rate": 4.4437222740021934e-07, "loss": 4.0559, "step": 17468 }, { "epoch": 0.940002152389152, "grad_norm": 3.3498032093048096, "learning_rate": 4.435792907524522e-07, "loss": 4.4811, "step": 17469 }, { "epoch": 0.940055962117951, "grad_norm": 1.9126442670822144, "learning_rate": 4.42787055861138e-07, "loss": 4.4186, "step": 17470 }, { "epoch": 0.9401097718467499, "grad_norm": 2.733145236968994, "learning_rate": 4.4199552274891977e-07, "loss": 3.8991, "step": 17471 }, { "epoch": 0.9401635815755489, "grad_norm": 2.399280309677124, "learning_rate": 4.4120469143841825e-07, "loss": 2.7462, "step": 17472 }, { "epoch": 0.9402173913043478, "grad_norm": 2.952014446258545, "learning_rate": 4.404145619522293e-07, "loss": 2.8405, "step": 17473 }, { "epoch": 0.9402712010331468, "grad_norm": 1.9087752103805542, "learning_rate": 4.396251343129376e-07, "loss": 3.5194, "step": 17474 }, { "epoch": 0.9403250107619457, "grad_norm": 3.104332685470581, "learning_rate": 4.388364085430974e-07, "loss": 3.3943, "step": 17475 }, { "epoch": 0.9403788204907447, "grad_norm": 4.2583417892456055, "learning_rate": 4.3804838466524887e-07, "loss": 4.1428, "step": 17476 }, { "epoch": 0.9404326302195437, "grad_norm": 3.8318779468536377, "learning_rate": 4.372610627019186e-07, "loss": 3.9887, "step": 17477 }, { "epoch": 0.9404864399483427, "grad_norm": 1.587444543838501, "learning_rate": 4.3647444267559677e-07, "loss": 3.9901, "step": 17478 }, { "epoch": 0.9405402496771417, "grad_norm": 2.2446377277374268, "learning_rate": 4.356885246087683e-07, "loss": 3.3617, "step": 17479 }, { "epoch": 0.9405940594059405, "grad_norm": 1.5997918844223022, "learning_rate": 4.3490330852389294e-07, "loss": 4.0618, "step": 17480 }, { "epoch": 0.9406478691347395, "grad_norm": 2.1625852584838867, "learning_rate": 4.341187944434083e-07, "loss": 2.6555, "step": 17481 }, { "epoch": 0.9407016788635385, "grad_norm": 2.82831072807312, "learning_rate": 4.3333498238973537e-07, "loss": 3.9381, "step": 17482 }, { "epoch": 0.9407554885923375, "grad_norm": 3.4041433334350586, "learning_rate": 4.325518723852701e-07, "loss": 3.5056, "step": 17483 }, { "epoch": 0.9408092983211365, "grad_norm": 2.395244598388672, "learning_rate": 4.3176946445239455e-07, "loss": 3.9545, "step": 17484 }, { "epoch": 0.9408631080499354, "grad_norm": 3.500990867614746, "learning_rate": 4.309877586134659e-07, "loss": 3.4433, "step": 17485 }, { "epoch": 0.9409169177787344, "grad_norm": 2.677781581878662, "learning_rate": 4.3020675489082176e-07, "loss": 3.3704, "step": 17486 }, { "epoch": 0.9409707275075334, "grad_norm": 2.5936641693115234, "learning_rate": 4.29426453306786e-07, "loss": 3.9726, "step": 17487 }, { "epoch": 0.9410245372363323, "grad_norm": 3.5674893856048584, "learning_rate": 4.286468538836574e-07, "loss": 2.645, "step": 17488 }, { "epoch": 0.9410783469651313, "grad_norm": 2.5171799659729004, "learning_rate": 4.278679566437127e-07, "loss": 3.8159, "step": 17489 }, { "epoch": 0.9411321566939302, "grad_norm": 4.55013370513916, "learning_rate": 4.27089761609209e-07, "loss": 3.5389, "step": 17490 }, { "epoch": 0.9411859664227292, "grad_norm": 2.332695484161377, "learning_rate": 4.2631226880238407e-07, "loss": 3.8278, "step": 17491 }, { "epoch": 0.9412397761515282, "grad_norm": 4.734914302825928, "learning_rate": 4.25535478245459e-07, "loss": 3.1801, "step": 17492 }, { "epoch": 0.9412935858803272, "grad_norm": 2.3184151649475098, "learning_rate": 4.247593899606356e-07, "loss": 3.7647, "step": 17493 }, { "epoch": 0.9413473956091262, "grad_norm": 2.6697022914886475, "learning_rate": 4.2398400397008765e-07, "loss": 3.4977, "step": 17494 }, { "epoch": 0.9414012053379252, "grad_norm": 3.4004132747650146, "learning_rate": 4.2320932029597524e-07, "loss": 4.3312, "step": 17495 }, { "epoch": 0.941455015066724, "grad_norm": 2.3799571990966797, "learning_rate": 4.2243533896043906e-07, "loss": 3.6118, "step": 17496 }, { "epoch": 0.941508824795523, "grad_norm": 3.622138023376465, "learning_rate": 4.2166205998559196e-07, "loss": 4.1851, "step": 17497 }, { "epoch": 0.941562634524322, "grad_norm": 1.6210614442825317, "learning_rate": 4.208894833935356e-07, "loss": 3.9461, "step": 17498 }, { "epoch": 0.941616444253121, "grad_norm": 3.6821699142456055, "learning_rate": 4.201176092063497e-07, "loss": 4.3587, "step": 17499 }, { "epoch": 0.94167025398192, "grad_norm": 2.5949907302856445, "learning_rate": 4.193464374460887e-07, "loss": 4.1726, "step": 17500 }, { "epoch": 0.9417240637107189, "grad_norm": 2.6086106300354004, "learning_rate": 4.185759681347906e-07, "loss": 3.8033, "step": 17501 }, { "epoch": 0.9417778734395179, "grad_norm": 2.4642179012298584, "learning_rate": 4.1780620129447666e-07, "loss": 3.6479, "step": 17502 }, { "epoch": 0.9418316831683168, "grad_norm": 2.7973427772521973, "learning_rate": 4.1703713694714596e-07, "loss": 4.0434, "step": 17503 }, { "epoch": 0.9418854928971158, "grad_norm": 3.145735025405884, "learning_rate": 4.162687751147726e-07, "loss": 2.9752, "step": 17504 }, { "epoch": 0.9419393026259147, "grad_norm": 3.4763245582580566, "learning_rate": 4.1550111581931396e-07, "loss": 3.5951, "step": 17505 }, { "epoch": 0.9419931123547137, "grad_norm": 1.8475391864776611, "learning_rate": 4.147341590827053e-07, "loss": 4.0041, "step": 17506 }, { "epoch": 0.9420469220835127, "grad_norm": 2.3245656490325928, "learning_rate": 4.1396790492687355e-07, "loss": 4.1566, "step": 17507 }, { "epoch": 0.9421007318123117, "grad_norm": 1.7934411764144897, "learning_rate": 4.1320235337370673e-07, "loss": 3.9038, "step": 17508 }, { "epoch": 0.9421545415411107, "grad_norm": 4.1959662437438965, "learning_rate": 4.1243750444508734e-07, "loss": 3.609, "step": 17509 }, { "epoch": 0.9422083512699096, "grad_norm": 3.7477972507476807, "learning_rate": 4.1167335816287013e-07, "loss": 3.6247, "step": 17510 }, { "epoch": 0.9422621609987085, "grad_norm": 3.654773235321045, "learning_rate": 4.1090991454889596e-07, "loss": 4.2217, "step": 17511 }, { "epoch": 0.9423159707275075, "grad_norm": 2.578855514526367, "learning_rate": 4.101471736249779e-07, "loss": 3.9787, "step": 17512 }, { "epoch": 0.9423697804563065, "grad_norm": 3.6566362380981445, "learning_rate": 4.0938513541291524e-07, "loss": 2.9339, "step": 17513 }, { "epoch": 0.9424235901851055, "grad_norm": 2.6352696418762207, "learning_rate": 4.0862379993448495e-07, "loss": 3.1274, "step": 17514 }, { "epoch": 0.9424773999139044, "grad_norm": 2.760113477706909, "learning_rate": 4.078631672114419e-07, "loss": 3.4447, "step": 17515 }, { "epoch": 0.9425312096427034, "grad_norm": 1.8954938650131226, "learning_rate": 4.0710323726552426e-07, "loss": 3.6726, "step": 17516 }, { "epoch": 0.9425850193715024, "grad_norm": 3.9963607788085938, "learning_rate": 4.0634401011844793e-07, "loss": 4.1455, "step": 17517 }, { "epoch": 0.9426388291003014, "grad_norm": 1.6232110261917114, "learning_rate": 4.0558548579191503e-07, "loss": 3.9652, "step": 17518 }, { "epoch": 0.9426926388291003, "grad_norm": 2.2253315448760986, "learning_rate": 4.0482766430759435e-07, "loss": 4.1427, "step": 17519 }, { "epoch": 0.9427464485578992, "grad_norm": 2.6862967014312744, "learning_rate": 4.040705456871491e-07, "loss": 4.0692, "step": 17520 }, { "epoch": 0.9428002582866982, "grad_norm": 2.204987049102783, "learning_rate": 4.0331412995220916e-07, "loss": 3.9122, "step": 17521 }, { "epoch": 0.9428540680154972, "grad_norm": 3.7757551670074463, "learning_rate": 4.0255841712439346e-07, "loss": 2.5301, "step": 17522 }, { "epoch": 0.9429078777442962, "grad_norm": 1.9341408014297485, "learning_rate": 4.018034072253013e-07, "loss": 4.0246, "step": 17523 }, { "epoch": 0.9429616874730952, "grad_norm": 2.222752571105957, "learning_rate": 4.0104910027650435e-07, "loss": 4.2722, "step": 17524 }, { "epoch": 0.9430154972018941, "grad_norm": 2.385877847671509, "learning_rate": 4.0029549629956307e-07, "loss": 3.9329, "step": 17525 }, { "epoch": 0.943069306930693, "grad_norm": 2.966463565826416, "learning_rate": 3.9954259531601034e-07, "loss": 3.9935, "step": 17526 }, { "epoch": 0.943123116659492, "grad_norm": 2.5073726177215576, "learning_rate": 3.9879039734736223e-07, "loss": 3.6246, "step": 17527 }, { "epoch": 0.943176926388291, "grad_norm": 2.948456048965454, "learning_rate": 3.9803890241511266e-07, "loss": 3.719, "step": 17528 }, { "epoch": 0.94323073611709, "grad_norm": 2.9122183322906494, "learning_rate": 3.9728811054074446e-07, "loss": 2.7594, "step": 17529 }, { "epoch": 0.9432845458458889, "grad_norm": 2.0612080097198486, "learning_rate": 3.965380217457043e-07, "loss": 4.235, "step": 17530 }, { "epoch": 0.9433383555746879, "grad_norm": 2.628882884979248, "learning_rate": 3.9578863605143624e-07, "loss": 3.3588, "step": 17531 }, { "epoch": 0.9433921653034869, "grad_norm": 1.3664608001708984, "learning_rate": 3.950399534793453e-07, "loss": 4.5654, "step": 17532 }, { "epoch": 0.9434459750322859, "grad_norm": 2.0568525791168213, "learning_rate": 3.942919740508366e-07, "loss": 3.5869, "step": 17533 }, { "epoch": 0.9434997847610848, "grad_norm": 1.7048176527023315, "learning_rate": 3.93544697787282e-07, "loss": 4.1388, "step": 17534 }, { "epoch": 0.9435535944898837, "grad_norm": 3.131354570388794, "learning_rate": 3.927981247100393e-07, "loss": 3.2703, "step": 17535 }, { "epoch": 0.9436074042186827, "grad_norm": 2.5158536434173584, "learning_rate": 3.9205225484043593e-07, "loss": 2.9579, "step": 17536 }, { "epoch": 0.9436612139474817, "grad_norm": 2.1062991619110107, "learning_rate": 3.91307088199791e-07, "loss": 4.058, "step": 17537 }, { "epoch": 0.9437150236762807, "grad_norm": 4.073610782623291, "learning_rate": 3.905626248094041e-07, "loss": 3.2198, "step": 17538 }, { "epoch": 0.9437688334050797, "grad_norm": 2.688103437423706, "learning_rate": 3.8981886469054153e-07, "loss": 3.0571, "step": 17539 }, { "epoch": 0.9438226431338786, "grad_norm": 2.9039053916931152, "learning_rate": 3.8907580786446406e-07, "loss": 3.2014, "step": 17540 }, { "epoch": 0.9438764528626775, "grad_norm": 2.9183714389801025, "learning_rate": 3.8833345435240474e-07, "loss": 3.4616, "step": 17541 }, { "epoch": 0.9439302625914765, "grad_norm": 3.9963297843933105, "learning_rate": 3.8759180417557714e-07, "loss": 3.4133, "step": 17542 }, { "epoch": 0.9439840723202755, "grad_norm": 3.1453757286071777, "learning_rate": 3.868508573551782e-07, "loss": 3.4832, "step": 17543 }, { "epoch": 0.9440378820490745, "grad_norm": 2.052143096923828, "learning_rate": 3.8611061391237715e-07, "loss": 4.3214, "step": 17544 }, { "epoch": 0.9440916917778734, "grad_norm": 2.910562038421631, "learning_rate": 3.853710738683347e-07, "loss": 3.579, "step": 17545 }, { "epoch": 0.9441455015066724, "grad_norm": 2.1986708641052246, "learning_rate": 3.846322372441785e-07, "loss": 3.427, "step": 17546 }, { "epoch": 0.9441993112354714, "grad_norm": 3.107760190963745, "learning_rate": 3.83894104061025e-07, "loss": 3.7789, "step": 17547 }, { "epoch": 0.9442531209642704, "grad_norm": 3.090524911880493, "learning_rate": 3.831566743399684e-07, "loss": 3.3551, "step": 17548 }, { "epoch": 0.9443069306930693, "grad_norm": 3.1609747409820557, "learning_rate": 3.824199481020835e-07, "loss": 3.778, "step": 17549 }, { "epoch": 0.9443607404218682, "grad_norm": 3.753891944885254, "learning_rate": 3.8168392536842567e-07, "loss": 3.9693, "step": 17550 }, { "epoch": 0.9444145501506672, "grad_norm": 2.8262057304382324, "learning_rate": 3.809486061600226e-07, "loss": 4.2127, "step": 17551 }, { "epoch": 0.9444683598794662, "grad_norm": 2.9523134231567383, "learning_rate": 3.8021399049789074e-07, "loss": 3.5625, "step": 17552 }, { "epoch": 0.9445221696082652, "grad_norm": 2.557494878768921, "learning_rate": 3.7948007840302444e-07, "loss": 4.2546, "step": 17553 }, { "epoch": 0.9445759793370642, "grad_norm": 3.7553586959838867, "learning_rate": 3.7874686989639585e-07, "loss": 4.4314, "step": 17554 }, { "epoch": 0.9446297890658631, "grad_norm": 2.447120428085327, "learning_rate": 3.780143649989576e-07, "loss": 3.7398, "step": 17555 }, { "epoch": 0.9446835987946621, "grad_norm": 3.277977705001831, "learning_rate": 3.772825637316457e-07, "loss": 3.0731, "step": 17556 }, { "epoch": 0.944737408523461, "grad_norm": 2.819648504257202, "learning_rate": 3.765514661153685e-07, "loss": 3.7376, "step": 17557 }, { "epoch": 0.94479121825226, "grad_norm": 2.8374035358428955, "learning_rate": 3.7582107217102316e-07, "loss": 4.3538, "step": 17558 }, { "epoch": 0.944845027981059, "grad_norm": 3.3520190715789795, "learning_rate": 3.75091381919479e-07, "loss": 3.6976, "step": 17559 }, { "epoch": 0.9448988377098579, "grad_norm": 2.2853009700775146, "learning_rate": 3.743623953815889e-07, "loss": 3.9003, "step": 17560 }, { "epoch": 0.9449526474386569, "grad_norm": 3.7920212745666504, "learning_rate": 3.736341125781889e-07, "loss": 2.792, "step": 17561 }, { "epoch": 0.9450064571674559, "grad_norm": 2.2778408527374268, "learning_rate": 3.729065335300874e-07, "loss": 3.4228, "step": 17562 }, { "epoch": 0.9450602668962549, "grad_norm": 4.707878589630127, "learning_rate": 3.721796582580761e-07, "loss": 3.6436, "step": 17563 }, { "epoch": 0.9451140766250538, "grad_norm": 1.6462297439575195, "learning_rate": 3.7145348678293e-07, "loss": 4.0815, "step": 17564 }, { "epoch": 0.9451678863538527, "grad_norm": 2.183807373046875, "learning_rate": 3.7072801912540476e-07, "loss": 4.0395, "step": 17565 }, { "epoch": 0.9452216960826517, "grad_norm": 2.737151622772217, "learning_rate": 3.700032553062227e-07, "loss": 3.7806, "step": 17566 }, { "epoch": 0.9452755058114507, "grad_norm": 3.6795077323913574, "learning_rate": 3.6927919534610335e-07, "loss": 3.7175, "step": 17567 }, { "epoch": 0.9453293155402497, "grad_norm": 1.3551300764083862, "learning_rate": 3.685558392657329e-07, "loss": 4.3933, "step": 17568 }, { "epoch": 0.9453831252690487, "grad_norm": 4.430497646331787, "learning_rate": 3.678331870857865e-07, "loss": 3.3622, "step": 17569 }, { "epoch": 0.9454369349978476, "grad_norm": 1.8669248819351196, "learning_rate": 3.6711123882691713e-07, "loss": 4.1025, "step": 17570 }, { "epoch": 0.9454907447266466, "grad_norm": 2.3877952098846436, "learning_rate": 3.6638999450975265e-07, "loss": 3.9654, "step": 17571 }, { "epoch": 0.9455445544554455, "grad_norm": 3.584786891937256, "learning_rate": 3.656694541549044e-07, "loss": 3.7086, "step": 17572 }, { "epoch": 0.9455983641842445, "grad_norm": 3.2730712890625, "learning_rate": 3.64949617782967e-07, "loss": 4.2494, "step": 17573 }, { "epoch": 0.9456521739130435, "grad_norm": 1.6398515701293945, "learning_rate": 3.642304854145073e-07, "loss": 3.8304, "step": 17574 }, { "epoch": 0.9457059836418424, "grad_norm": 3.567897081375122, "learning_rate": 3.635120570700784e-07, "loss": 3.1323, "step": 17575 }, { "epoch": 0.9457597933706414, "grad_norm": 1.8687063455581665, "learning_rate": 3.62794332770211e-07, "loss": 3.7067, "step": 17576 }, { "epoch": 0.9458136030994404, "grad_norm": 1.5166367292404175, "learning_rate": 3.620773125354138e-07, "loss": 3.7758, "step": 17577 }, { "epoch": 0.9458674128282394, "grad_norm": 2.62630295753479, "learning_rate": 3.613609963861814e-07, "loss": 3.7087, "step": 17578 }, { "epoch": 0.9459212225570384, "grad_norm": 2.505908966064453, "learning_rate": 3.60645384342978e-07, "loss": 3.3208, "step": 17579 }, { "epoch": 0.9459750322858372, "grad_norm": 3.364896774291992, "learning_rate": 3.5993047642625954e-07, "loss": 3.4059, "step": 17580 }, { "epoch": 0.9460288420146362, "grad_norm": 3.437335252761841, "learning_rate": 3.5921627265645407e-07, "loss": 3.7001, "step": 17581 }, { "epoch": 0.9460826517434352, "grad_norm": 2.92415189743042, "learning_rate": 3.585027730539731e-07, "loss": 3.7161, "step": 17582 }, { "epoch": 0.9461364614722342, "grad_norm": 3.7853305339813232, "learning_rate": 3.57789977639203e-07, "loss": 3.3732, "step": 17583 }, { "epoch": 0.9461902712010332, "grad_norm": 2.8809707164764404, "learning_rate": 3.5707788643251363e-07, "loss": 3.7699, "step": 17584 }, { "epoch": 0.9462440809298321, "grad_norm": 2.249772310256958, "learning_rate": 3.5636649945425817e-07, "loss": 4.4415, "step": 17585 }, { "epoch": 0.9462978906586311, "grad_norm": 5.162206649780273, "learning_rate": 3.5565581672476757e-07, "loss": 3.505, "step": 17586 }, { "epoch": 0.94635170038743, "grad_norm": 2.754953622817993, "learning_rate": 3.5494583826434504e-07, "loss": 2.8058, "step": 17587 }, { "epoch": 0.946405510116229, "grad_norm": 4.104697227478027, "learning_rate": 3.5423656409328263e-07, "loss": 3.1076, "step": 17588 }, { "epoch": 0.946459319845028, "grad_norm": 2.3700461387634277, "learning_rate": 3.5352799423185313e-07, "loss": 3.6442, "step": 17589 }, { "epoch": 0.9465131295738269, "grad_norm": 2.9593019485473633, "learning_rate": 3.5282012870029856e-07, "loss": 3.9973, "step": 17590 }, { "epoch": 0.9465669393026259, "grad_norm": 2.0743234157562256, "learning_rate": 3.521129675188556e-07, "loss": 3.7281, "step": 17591 }, { "epoch": 0.9466207490314249, "grad_norm": 4.074182510375977, "learning_rate": 3.5140651070772746e-07, "loss": 3.5623, "step": 17592 }, { "epoch": 0.9466745587602239, "grad_norm": 2.391205072402954, "learning_rate": 3.507007582871036e-07, "loss": 3.5133, "step": 17593 }, { "epoch": 0.9467283684890229, "grad_norm": 2.804670572280884, "learning_rate": 3.499957102771512e-07, "loss": 4.4353, "step": 17594 }, { "epoch": 0.9467821782178217, "grad_norm": 2.8715932369232178, "learning_rate": 3.4929136669802075e-07, "loss": 3.68, "step": 17595 }, { "epoch": 0.9468359879466207, "grad_norm": 2.712750196456909, "learning_rate": 3.4858772756984627e-07, "loss": 3.3322, "step": 17596 }, { "epoch": 0.9468897976754197, "grad_norm": 2.6622488498687744, "learning_rate": 3.4788479291272547e-07, "loss": 3.9374, "step": 17597 }, { "epoch": 0.9469436074042187, "grad_norm": 3.028240919113159, "learning_rate": 3.4718256274675064e-07, "loss": 2.6984, "step": 17598 }, { "epoch": 0.9469974171330177, "grad_norm": 4.350924015045166, "learning_rate": 3.4648103709198907e-07, "loss": 3.9894, "step": 17599 }, { "epoch": 0.9470512268618166, "grad_norm": 4.031878471374512, "learning_rate": 3.4578021596849144e-07, "loss": 3.3936, "step": 17600 }, { "epoch": 0.9471050365906156, "grad_norm": 3.2343392372131348, "learning_rate": 3.4508009939628326e-07, "loss": 3.1839, "step": 17601 }, { "epoch": 0.9471588463194146, "grad_norm": 2.6295833587646484, "learning_rate": 3.4438068739537086e-07, "loss": 4.1898, "step": 17602 }, { "epoch": 0.9472126560482135, "grad_norm": 3.4117562770843506, "learning_rate": 3.436819799857438e-07, "loss": 4.3064, "step": 17603 }, { "epoch": 0.9472664657770125, "grad_norm": 3.381986141204834, "learning_rate": 3.429839771873694e-07, "loss": 4.4521, "step": 17604 }, { "epoch": 0.9473202755058114, "grad_norm": 3.5817508697509766, "learning_rate": 3.422866790201901e-07, "loss": 3.1814, "step": 17605 }, { "epoch": 0.9473740852346104, "grad_norm": 2.214766025543213, "learning_rate": 3.415900855041371e-07, "loss": 3.2437, "step": 17606 }, { "epoch": 0.9474278949634094, "grad_norm": 3.557913303375244, "learning_rate": 3.408941966591167e-07, "loss": 4.0913, "step": 17607 }, { "epoch": 0.9474817046922084, "grad_norm": 2.9859366416931152, "learning_rate": 3.4019901250501587e-07, "loss": 3.5745, "step": 17608 }, { "epoch": 0.9475355144210074, "grad_norm": 4.403428077697754, "learning_rate": 3.3950453306169917e-07, "loss": 3.9077, "step": 17609 }, { "epoch": 0.9475893241498062, "grad_norm": 2.8752059936523438, "learning_rate": 3.388107583490119e-07, "loss": 3.6305, "step": 17610 }, { "epoch": 0.9476431338786052, "grad_norm": 2.0421833992004395, "learning_rate": 3.3811768838678536e-07, "loss": 3.772, "step": 17611 }, { "epoch": 0.9476969436074042, "grad_norm": 2.6112852096557617, "learning_rate": 3.3742532319482044e-07, "loss": 3.7128, "step": 17612 }, { "epoch": 0.9477507533362032, "grad_norm": 5.738295078277588, "learning_rate": 3.367336627929069e-07, "loss": 3.7776, "step": 17613 }, { "epoch": 0.9478045630650022, "grad_norm": 3.829023599624634, "learning_rate": 3.3604270720080934e-07, "loss": 3.6129, "step": 17614 }, { "epoch": 0.9478583727938011, "grad_norm": 3.683119773864746, "learning_rate": 3.353524564382676e-07, "loss": 3.5941, "step": 17615 }, { "epoch": 0.9479121825226001, "grad_norm": 3.349238634109497, "learning_rate": 3.3466291052501874e-07, "loss": 3.3062, "step": 17616 }, { "epoch": 0.9479659922513991, "grad_norm": 2.0413753986358643, "learning_rate": 3.339740694807608e-07, "loss": 3.7702, "step": 17617 }, { "epoch": 0.948019801980198, "grad_norm": 2.7729063034057617, "learning_rate": 3.332859333251781e-07, "loss": 3.4028, "step": 17618 }, { "epoch": 0.948073611708997, "grad_norm": 4.731912136077881, "learning_rate": 3.3259850207793817e-07, "loss": 3.6426, "step": 17619 }, { "epoch": 0.9481274214377959, "grad_norm": 1.9112156629562378, "learning_rate": 3.319117757586865e-07, "loss": 3.8623, "step": 17620 }, { "epoch": 0.9481812311665949, "grad_norm": 2.401357650756836, "learning_rate": 3.312257543870462e-07, "loss": 3.3755, "step": 17621 }, { "epoch": 0.9482350408953939, "grad_norm": 4.005674362182617, "learning_rate": 3.305404379826238e-07, "loss": 3.2864, "step": 17622 }, { "epoch": 0.9482888506241929, "grad_norm": 2.0325117111206055, "learning_rate": 3.298558265650037e-07, "loss": 3.94, "step": 17623 }, { "epoch": 0.9483426603529919, "grad_norm": 2.6680893898010254, "learning_rate": 3.2917192015374797e-07, "loss": 3.6361, "step": 17624 }, { "epoch": 0.9483964700817907, "grad_norm": 2.616391897201538, "learning_rate": 3.284887187683994e-07, "loss": 4.0399, "step": 17625 }, { "epoch": 0.9484502798105897, "grad_norm": 2.1916937828063965, "learning_rate": 3.278062224284867e-07, "loss": 4.5983, "step": 17626 }, { "epoch": 0.9485040895393887, "grad_norm": 4.239321708679199, "learning_rate": 3.271244311535138e-07, "loss": 4.246, "step": 17627 }, { "epoch": 0.9485578992681877, "grad_norm": 3.7510974407196045, "learning_rate": 3.264433449629595e-07, "loss": 3.5481, "step": 17628 }, { "epoch": 0.9486117089969867, "grad_norm": 3.065542459487915, "learning_rate": 3.2576296387629156e-07, "loss": 3.7358, "step": 17629 }, { "epoch": 0.9486655187257856, "grad_norm": 2.8079447746276855, "learning_rate": 3.2508328791295007e-07, "loss": 3.7238, "step": 17630 }, { "epoch": 0.9487193284545846, "grad_norm": 2.5095176696777344, "learning_rate": 3.2440431709236387e-07, "loss": 4.1909, "step": 17631 }, { "epoch": 0.9487731381833836, "grad_norm": 3.7993385791778564, "learning_rate": 3.237260514339313e-07, "loss": 3.5347, "step": 17632 }, { "epoch": 0.9488269479121825, "grad_norm": 2.171579360961914, "learning_rate": 3.2304849095703696e-07, "loss": 4.1496, "step": 17633 }, { "epoch": 0.9488807576409815, "grad_norm": 1.579815149307251, "learning_rate": 3.22371635681043e-07, "loss": 4.1649, "step": 17634 }, { "epoch": 0.9489345673697804, "grad_norm": 2.1052405834198, "learning_rate": 3.216954856252924e-07, "loss": 4.4334, "step": 17635 }, { "epoch": 0.9489883770985794, "grad_norm": 2.740884780883789, "learning_rate": 3.210200408091085e-07, "loss": 3.1953, "step": 17636 }, { "epoch": 0.9490421868273784, "grad_norm": 2.7442710399627686, "learning_rate": 3.2034530125179265e-07, "loss": 4.0263, "step": 17637 }, { "epoch": 0.9490959965561774, "grad_norm": 2.615269184112549, "learning_rate": 3.196712669726293e-07, "loss": 3.3036, "step": 17638 }, { "epoch": 0.9491498062849764, "grad_norm": 1.7793105840682983, "learning_rate": 3.1899793799087806e-07, "loss": 4.0221, "step": 17639 }, { "epoch": 0.9492036160137753, "grad_norm": 3.2460289001464844, "learning_rate": 3.1832531432578196e-07, "loss": 2.8439, "step": 17640 }, { "epoch": 0.9492574257425742, "grad_norm": 4.08527946472168, "learning_rate": 3.1765339599655885e-07, "loss": 3.8505, "step": 17641 }, { "epoch": 0.9493112354713732, "grad_norm": 3.7868802547454834, "learning_rate": 3.169821830224184e-07, "loss": 3.1513, "step": 17642 }, { "epoch": 0.9493650452001722, "grad_norm": 2.78788161277771, "learning_rate": 3.1631167542253703e-07, "loss": 4.1516, "step": 17643 }, { "epoch": 0.9494188549289712, "grad_norm": 2.9641597270965576, "learning_rate": 3.156418732160743e-07, "loss": 3.9679, "step": 17644 }, { "epoch": 0.9494726646577701, "grad_norm": 2.7530229091644287, "learning_rate": 3.14972776422176e-07, "loss": 4.3058, "step": 17645 }, { "epoch": 0.9495264743865691, "grad_norm": 5.567333698272705, "learning_rate": 3.1430438505996027e-07, "loss": 3.1753, "step": 17646 }, { "epoch": 0.9495802841153681, "grad_norm": 2.7542686462402344, "learning_rate": 3.1363669914852843e-07, "loss": 4.1214, "step": 17647 }, { "epoch": 0.949634093844167, "grad_norm": 1.8364893198013306, "learning_rate": 3.129697187069597e-07, "loss": 4.3719, "step": 17648 }, { "epoch": 0.949687903572966, "grad_norm": 3.404585361480713, "learning_rate": 3.123034437543193e-07, "loss": 3.4633, "step": 17649 }, { "epoch": 0.9497417133017649, "grad_norm": 2.8786096572875977, "learning_rate": 3.1163787430964207e-07, "loss": 4.1847, "step": 17650 }, { "epoch": 0.9497955230305639, "grad_norm": 3.6855063438415527, "learning_rate": 3.1097301039194893e-07, "loss": 3.2928, "step": 17651 }, { "epoch": 0.9498493327593629, "grad_norm": 1.5892784595489502, "learning_rate": 3.103088520202441e-07, "loss": 3.7138, "step": 17652 }, { "epoch": 0.9499031424881619, "grad_norm": 4.15505838394165, "learning_rate": 3.09645399213504e-07, "loss": 3.8576, "step": 17653 }, { "epoch": 0.9499569522169609, "grad_norm": 3.5256118774414062, "learning_rate": 3.089826519906913e-07, "loss": 3.5899, "step": 17654 }, { "epoch": 0.9500107619457598, "grad_norm": 2.9866397380828857, "learning_rate": 3.083206103707409e-07, "loss": 4.2303, "step": 17655 }, { "epoch": 0.9500645716745587, "grad_norm": 3.1529877185821533, "learning_rate": 3.076592743725737e-07, "loss": 3.6704, "step": 17656 }, { "epoch": 0.9501183814033577, "grad_norm": 1.5349386930465698, "learning_rate": 3.0699864401509126e-07, "loss": 4.4711, "step": 17657 }, { "epoch": 0.9501721911321567, "grad_norm": 2.5483028888702393, "learning_rate": 3.0633871931717296e-07, "loss": 3.9886, "step": 17658 }, { "epoch": 0.9502260008609557, "grad_norm": 4.4980974197387695, "learning_rate": 3.056795002976731e-07, "loss": 3.069, "step": 17659 }, { "epoch": 0.9502798105897546, "grad_norm": 2.7534146308898926, "learning_rate": 3.0502098697543503e-07, "loss": 3.5133, "step": 17660 }, { "epoch": 0.9503336203185536, "grad_norm": 2.4559149742126465, "learning_rate": 3.043631793692742e-07, "loss": 3.6508, "step": 17661 }, { "epoch": 0.9503874300473526, "grad_norm": 2.316732883453369, "learning_rate": 3.0370607749798943e-07, "loss": 3.3956, "step": 17662 }, { "epoch": 0.9504412397761516, "grad_norm": 3.2595231533050537, "learning_rate": 3.0304968138036016e-07, "loss": 4.1135, "step": 17663 }, { "epoch": 0.9504950495049505, "grad_norm": 2.025019407272339, "learning_rate": 3.0239399103514644e-07, "loss": 3.8645, "step": 17664 }, { "epoch": 0.9505488592337494, "grad_norm": 1.399032473564148, "learning_rate": 3.017390064810832e-07, "loss": 4.2636, "step": 17665 }, { "epoch": 0.9506026689625484, "grad_norm": 2.430800676345825, "learning_rate": 3.010847277368861e-07, "loss": 4.3016, "step": 17666 }, { "epoch": 0.9506564786913474, "grad_norm": 2.330375909805298, "learning_rate": 3.0043115482125684e-07, "loss": 3.9727, "step": 17667 }, { "epoch": 0.9507102884201464, "grad_norm": 2.1729648113250732, "learning_rate": 2.997782877528721e-07, "loss": 3.5558, "step": 17668 }, { "epoch": 0.9507640981489454, "grad_norm": 3.1427788734436035, "learning_rate": 2.9912612655038643e-07, "loss": 3.7856, "step": 17669 }, { "epoch": 0.9508179078777443, "grad_norm": 3.0903232097625732, "learning_rate": 2.9847467123244045e-07, "loss": 4.3041, "step": 17670 }, { "epoch": 0.9508717176065432, "grad_norm": 2.9520814418792725, "learning_rate": 2.978239218176471e-07, "loss": 3.3788, "step": 17671 }, { "epoch": 0.9509255273353422, "grad_norm": 2.965754508972168, "learning_rate": 2.971738783246053e-07, "loss": 3.7116, "step": 17672 }, { "epoch": 0.9509793370641412, "grad_norm": 2.3628756999969482, "learning_rate": 2.96524540771892e-07, "loss": 4.3252, "step": 17673 }, { "epoch": 0.9510331467929402, "grad_norm": 2.0344784259796143, "learning_rate": 2.9587590917806163e-07, "loss": 3.8444, "step": 17674 }, { "epoch": 0.9510869565217391, "grad_norm": 3.835629463195801, "learning_rate": 2.9522798356165227e-07, "loss": 4.2496, "step": 17675 }, { "epoch": 0.9511407662505381, "grad_norm": 2.94012713432312, "learning_rate": 2.9458076394117684e-07, "loss": 4.0048, "step": 17676 }, { "epoch": 0.9511945759793371, "grad_norm": 2.6851255893707275, "learning_rate": 2.939342503351372e-07, "loss": 4.2213, "step": 17677 }, { "epoch": 0.9512483857081361, "grad_norm": 2.1899919509887695, "learning_rate": 2.9328844276200197e-07, "loss": 3.6585, "step": 17678 }, { "epoch": 0.951302195436935, "grad_norm": 1.651828646659851, "learning_rate": 2.926433412402313e-07, "loss": 4.5928, "step": 17679 }, { "epoch": 0.9513560051657339, "grad_norm": 2.913179874420166, "learning_rate": 2.9199894578826327e-07, "loss": 3.343, "step": 17680 }, { "epoch": 0.9514098148945329, "grad_norm": 2.8559298515319824, "learning_rate": 2.9135525642450256e-07, "loss": 3.2137, "step": 17681 }, { "epoch": 0.9514636246233319, "grad_norm": 3.070709705352783, "learning_rate": 2.907122731673512e-07, "loss": 3.9701, "step": 17682 }, { "epoch": 0.9515174343521309, "grad_norm": 2.861017942428589, "learning_rate": 2.9006999603518325e-07, "loss": 2.8037, "step": 17683 }, { "epoch": 0.9515712440809299, "grad_norm": 2.251434087753296, "learning_rate": 2.894284250463536e-07, "loss": 4.0057, "step": 17684 }, { "epoch": 0.9516250538097288, "grad_norm": 1.4191582202911377, "learning_rate": 2.887875602191975e-07, "loss": 4.3724, "step": 17685 }, { "epoch": 0.9516788635385278, "grad_norm": 2.117633819580078, "learning_rate": 2.881474015720254e-07, "loss": 2.7392, "step": 17686 }, { "epoch": 0.9517326732673267, "grad_norm": 1.4737225770950317, "learning_rate": 2.8750794912313083e-07, "loss": 4.1117, "step": 17687 }, { "epoch": 0.9517864829961257, "grad_norm": 3.160710334777832, "learning_rate": 2.8686920289079654e-07, "loss": 3.9652, "step": 17688 }, { "epoch": 0.9518402927249247, "grad_norm": 3.8158931732177734, "learning_rate": 2.8623116289326625e-07, "loss": 3.5613, "step": 17689 }, { "epoch": 0.9518941024537236, "grad_norm": 2.605400323867798, "learning_rate": 2.855938291487781e-07, "loss": 4.255, "step": 17690 }, { "epoch": 0.9519479121825226, "grad_norm": 3.3223798274993896, "learning_rate": 2.8495720167554254e-07, "loss": 4.312, "step": 17691 }, { "epoch": 0.9520017219113216, "grad_norm": 3.5597639083862305, "learning_rate": 2.8432128049175613e-07, "loss": 3.1841, "step": 17692 }, { "epoch": 0.9520555316401206, "grad_norm": 2.477543592453003, "learning_rate": 2.836860656155904e-07, "loss": 4.5794, "step": 17693 }, { "epoch": 0.9521093413689194, "grad_norm": 2.1751043796539307, "learning_rate": 2.830515570651948e-07, "loss": 3.6532, "step": 17694 }, { "epoch": 0.9521631510977184, "grad_norm": 1.5454373359680176, "learning_rate": 2.8241775485871037e-07, "loss": 4.2142, "step": 17695 }, { "epoch": 0.9522169608265174, "grad_norm": 4.498870849609375, "learning_rate": 2.81784659014242e-07, "loss": 3.4353, "step": 17696 }, { "epoch": 0.9522707705553164, "grad_norm": 2.9908065795898438, "learning_rate": 2.8115226954988084e-07, "loss": 3.6333, "step": 17697 }, { "epoch": 0.9523245802841154, "grad_norm": 1.4171881675720215, "learning_rate": 2.805205864837041e-07, "loss": 4.2189, "step": 17698 }, { "epoch": 0.9523783900129144, "grad_norm": 3.359849691390991, "learning_rate": 2.798896098337611e-07, "loss": 3.0538, "step": 17699 }, { "epoch": 0.9524321997417133, "grad_norm": 2.9352073669433594, "learning_rate": 2.792593396180848e-07, "loss": 4.4893, "step": 17700 }, { "epoch": 0.9524860094705123, "grad_norm": 2.640474557876587, "learning_rate": 2.7862977585468296e-07, "loss": 3.8702, "step": 17701 }, { "epoch": 0.9525398191993112, "grad_norm": 3.386230707168579, "learning_rate": 2.780009185615523e-07, "loss": 3.3961, "step": 17702 }, { "epoch": 0.9525936289281102, "grad_norm": 2.2625732421875, "learning_rate": 2.77372767756659e-07, "loss": 3.8804, "step": 17703 }, { "epoch": 0.9526474386569092, "grad_norm": 1.8785401582717896, "learning_rate": 2.767453234579581e-07, "loss": 3.2564, "step": 17704 }, { "epoch": 0.9527012483857081, "grad_norm": 3.268944501876831, "learning_rate": 2.76118585683377e-07, "loss": 4.1941, "step": 17705 }, { "epoch": 0.9527550581145071, "grad_norm": 4.54304838180542, "learning_rate": 2.7549255445082634e-07, "loss": 3.8893, "step": 17706 }, { "epoch": 0.9528088678433061, "grad_norm": 1.7583585977554321, "learning_rate": 2.7486722977819736e-07, "loss": 4.3705, "step": 17707 }, { "epoch": 0.9528626775721051, "grad_norm": 2.5010504722595215, "learning_rate": 2.742426116833618e-07, "loss": 3.6605, "step": 17708 }, { "epoch": 0.9529164873009041, "grad_norm": 3.9216978549957275, "learning_rate": 2.736187001841667e-07, "loss": 3.607, "step": 17709 }, { "epoch": 0.9529702970297029, "grad_norm": 2.8022348880767822, "learning_rate": 2.729954952984448e-07, "loss": 3.4773, "step": 17710 }, { "epoch": 0.9530241067585019, "grad_norm": 2.756682872772217, "learning_rate": 2.723729970440042e-07, "loss": 3.9496, "step": 17711 }, { "epoch": 0.9530779164873009, "grad_norm": 2.9553275108337402, "learning_rate": 2.717512054386306e-07, "loss": 3.3092, "step": 17712 }, { "epoch": 0.9531317262160999, "grad_norm": 2.5999162197113037, "learning_rate": 2.71130120500096e-07, "loss": 3.1202, "step": 17713 }, { "epoch": 0.9531855359448989, "grad_norm": 2.3694956302642822, "learning_rate": 2.7050974224615277e-07, "loss": 3.7285, "step": 17714 }, { "epoch": 0.9532393456736978, "grad_norm": 2.4555795192718506, "learning_rate": 2.6989007069452565e-07, "loss": 3.9662, "step": 17715 }, { "epoch": 0.9532931554024968, "grad_norm": 3.0370566844940186, "learning_rate": 2.692711058629227e-07, "loss": 3.4234, "step": 17716 }, { "epoch": 0.9533469651312957, "grad_norm": 4.054095268249512, "learning_rate": 2.686528477690353e-07, "loss": 3.2481, "step": 17717 }, { "epoch": 0.9534007748600947, "grad_norm": 2.8344521522521973, "learning_rate": 2.6803529643052995e-07, "loss": 4.1436, "step": 17718 }, { "epoch": 0.9534545845888936, "grad_norm": 1.8661644458770752, "learning_rate": 2.6741845186505356e-07, "loss": 4.1821, "step": 17719 }, { "epoch": 0.9535083943176926, "grad_norm": 1.2885721921920776, "learning_rate": 2.668023140902365e-07, "loss": 4.3588, "step": 17720 }, { "epoch": 0.9535622040464916, "grad_norm": 1.843676209449768, "learning_rate": 2.661868831236841e-07, "loss": 3.2327, "step": 17721 }, { "epoch": 0.9536160137752906, "grad_norm": 3.3343088626861572, "learning_rate": 2.6557215898298513e-07, "loss": 3.8508, "step": 17722 }, { "epoch": 0.9536698235040896, "grad_norm": 2.6580042839050293, "learning_rate": 2.6495814168570334e-07, "loss": 4.0803, "step": 17723 }, { "epoch": 0.9537236332328886, "grad_norm": 2.8928213119506836, "learning_rate": 2.643448312493912e-07, "loss": 4.3045, "step": 17724 }, { "epoch": 0.9537774429616874, "grad_norm": 4.196476459503174, "learning_rate": 2.6373222769157103e-07, "loss": 3.8918, "step": 17725 }, { "epoch": 0.9538312526904864, "grad_norm": 2.392534017562866, "learning_rate": 2.6312033102975365e-07, "loss": 3.4233, "step": 17726 }, { "epoch": 0.9538850624192854, "grad_norm": 3.3667101860046387, "learning_rate": 2.6250914128142235e-07, "loss": 3.6163, "step": 17727 }, { "epoch": 0.9539388721480844, "grad_norm": 2.6201958656311035, "learning_rate": 2.6189865846404095e-07, "loss": 3.7162, "step": 17728 }, { "epoch": 0.9539926818768834, "grad_norm": 3.557352066040039, "learning_rate": 2.6128888259505933e-07, "loss": 3.5546, "step": 17729 }, { "epoch": 0.9540464916056823, "grad_norm": 3.304502010345459, "learning_rate": 2.6067981369190255e-07, "loss": 3.9853, "step": 17730 }, { "epoch": 0.9541003013344813, "grad_norm": 2.219482183456421, "learning_rate": 2.6007145177197603e-07, "loss": 3.684, "step": 17731 }, { "epoch": 0.9541541110632802, "grad_norm": 3.1774065494537354, "learning_rate": 2.594637968526631e-07, "loss": 3.4494, "step": 17732 }, { "epoch": 0.9542079207920792, "grad_norm": 3.3250136375427246, "learning_rate": 2.5885684895133323e-07, "loss": 3.1932, "step": 17733 }, { "epoch": 0.9542617305208781, "grad_norm": 2.2791168689727783, "learning_rate": 2.582506080853281e-07, "loss": 3.8413, "step": 17734 }, { "epoch": 0.9543155402496771, "grad_norm": 2.1228580474853516, "learning_rate": 2.576450742719727e-07, "loss": 3.8604, "step": 17735 }, { "epoch": 0.9543693499784761, "grad_norm": 3.0012753009796143, "learning_rate": 2.570402475285699e-07, "loss": 3.8951, "step": 17736 }, { "epoch": 0.9544231597072751, "grad_norm": 2.2281532287597656, "learning_rate": 2.564361278724087e-07, "loss": 3.2086, "step": 17737 }, { "epoch": 0.9544769694360741, "grad_norm": 3.58752703666687, "learning_rate": 2.558327153207474e-07, "loss": 3.8127, "step": 17738 }, { "epoch": 0.9545307791648731, "grad_norm": 2.261704921722412, "learning_rate": 2.552300098908361e-07, "loss": 3.8612, "step": 17739 }, { "epoch": 0.9545845888936719, "grad_norm": 1.8225805759429932, "learning_rate": 2.5462801159989444e-07, "loss": 4.0765, "step": 17740 }, { "epoch": 0.9546383986224709, "grad_norm": 2.1895246505737305, "learning_rate": 2.5402672046513085e-07, "loss": 3.8384, "step": 17741 }, { "epoch": 0.9546922083512699, "grad_norm": 3.397066593170166, "learning_rate": 2.534261365037205e-07, "loss": 3.5606, "step": 17742 }, { "epoch": 0.9547460180800689, "grad_norm": 1.3744494915008545, "learning_rate": 2.5282625973283015e-07, "loss": 4.1164, "step": 17743 }, { "epoch": 0.9547998278088679, "grad_norm": 3.472989797592163, "learning_rate": 2.5222709016960443e-07, "loss": 4.2285, "step": 17744 }, { "epoch": 0.9548536375376668, "grad_norm": 4.68049955368042, "learning_rate": 2.5162862783116583e-07, "loss": 3.0174, "step": 17745 }, { "epoch": 0.9549074472664658, "grad_norm": 3.409438133239746, "learning_rate": 2.5103087273461445e-07, "loss": 4.1409, "step": 17746 }, { "epoch": 0.9549612569952648, "grad_norm": 2.2422404289245605, "learning_rate": 2.5043382489703394e-07, "loss": 4.1199, "step": 17747 }, { "epoch": 0.9550150667240637, "grad_norm": 1.9687442779541016, "learning_rate": 2.4983748433548836e-07, "loss": 4.249, "step": 17748 }, { "epoch": 0.9550688764528626, "grad_norm": 3.2936935424804688, "learning_rate": 2.4924185106701414e-07, "loss": 3.378, "step": 17749 }, { "epoch": 0.9551226861816616, "grad_norm": 3.345634937286377, "learning_rate": 2.486469251086393e-07, "loss": 3.6874, "step": 17750 }, { "epoch": 0.9551764959104606, "grad_norm": 4.1068596839904785, "learning_rate": 2.4805270647735857e-07, "loss": 3.3798, "step": 17751 }, { "epoch": 0.9552303056392596, "grad_norm": 2.496723175048828, "learning_rate": 2.474591951901584e-07, "loss": 4.2331, "step": 17752 }, { "epoch": 0.9552841153680586, "grad_norm": 2.450782537460327, "learning_rate": 2.468663912639974e-07, "loss": 3.6532, "step": 17753 }, { "epoch": 0.9553379250968576, "grad_norm": 4.678988456726074, "learning_rate": 2.4627429471581754e-07, "loss": 3.9751, "step": 17754 }, { "epoch": 0.9553917348256564, "grad_norm": 3.602121353149414, "learning_rate": 2.456829055625387e-07, "loss": 2.7231, "step": 17755 }, { "epoch": 0.9554455445544554, "grad_norm": 1.8926217555999756, "learning_rate": 2.450922238210612e-07, "loss": 4.1324, "step": 17756 }, { "epoch": 0.9554993542832544, "grad_norm": 2.212717056274414, "learning_rate": 2.4450224950826604e-07, "loss": 4.1725, "step": 17757 }, { "epoch": 0.9555531640120534, "grad_norm": 2.9251842498779297, "learning_rate": 2.4391298264100916e-07, "loss": 3.8864, "step": 17758 }, { "epoch": 0.9556069737408524, "grad_norm": 2.168666124343872, "learning_rate": 2.433244232361326e-07, "loss": 3.4431, "step": 17759 }, { "epoch": 0.9556607834696513, "grad_norm": 3.5261313915252686, "learning_rate": 2.4273657131045903e-07, "loss": 2.3504, "step": 17760 }, { "epoch": 0.9557145931984503, "grad_norm": 2.134406328201294, "learning_rate": 2.421494268807861e-07, "loss": 4.2754, "step": 17761 }, { "epoch": 0.9557684029272493, "grad_norm": 2.7073636054992676, "learning_rate": 2.415629899638894e-07, "loss": 3.3618, "step": 17762 }, { "epoch": 0.9558222126560482, "grad_norm": 3.2067010402679443, "learning_rate": 2.4097726057653037e-07, "loss": 3.5156, "step": 17763 }, { "epoch": 0.9558760223848471, "grad_norm": 1.9210597276687622, "learning_rate": 2.403922387354485e-07, "loss": 4.3659, "step": 17764 }, { "epoch": 0.9559298321136461, "grad_norm": 3.8526365756988525, "learning_rate": 2.398079244573609e-07, "loss": 2.7956, "step": 17765 }, { "epoch": 0.9559836418424451, "grad_norm": 2.0075647830963135, "learning_rate": 2.392243177589654e-07, "loss": 4.234, "step": 17766 }, { "epoch": 0.9560374515712441, "grad_norm": 2.156263828277588, "learning_rate": 2.3864141865693745e-07, "loss": 3.7701, "step": 17767 }, { "epoch": 0.9560912613000431, "grad_norm": 2.4546003341674805, "learning_rate": 2.380592271679416e-07, "loss": 4.0112, "step": 17768 }, { "epoch": 0.956145071028842, "grad_norm": 3.2293167114257812, "learning_rate": 2.3747774330860618e-07, "loss": 3.3451, "step": 17769 }, { "epoch": 0.956198880757641, "grad_norm": 2.921464443206787, "learning_rate": 2.3689696709555674e-07, "loss": 4.2583, "step": 17770 }, { "epoch": 0.9562526904864399, "grad_norm": 1.9953114986419678, "learning_rate": 2.363168985453884e-07, "loss": 3.6046, "step": 17771 }, { "epoch": 0.9563065002152389, "grad_norm": 2.155001640319824, "learning_rate": 2.3573753767467676e-07, "loss": 2.8243, "step": 17772 }, { "epoch": 0.9563603099440379, "grad_norm": 3.043057680130005, "learning_rate": 2.3515888449997803e-07, "loss": 3.3351, "step": 17773 }, { "epoch": 0.9564141196728368, "grad_norm": 2.419684886932373, "learning_rate": 2.3458093903782618e-07, "loss": 3.8921, "step": 17774 }, { "epoch": 0.9564679294016358, "grad_norm": 4.838660717010498, "learning_rate": 2.3400370130474137e-07, "loss": 3.3517, "step": 17775 }, { "epoch": 0.9565217391304348, "grad_norm": 2.6309850215911865, "learning_rate": 2.3342717131721868e-07, "loss": 3.9684, "step": 17776 }, { "epoch": 0.9565755488592338, "grad_norm": 3.0320980548858643, "learning_rate": 2.3285134909173112e-07, "loss": 3.1015, "step": 17777 }, { "epoch": 0.9566293585880327, "grad_norm": 2.380399227142334, "learning_rate": 2.322762346447377e-07, "loss": 3.8074, "step": 17778 }, { "epoch": 0.9566831683168316, "grad_norm": 3.8213582038879395, "learning_rate": 2.3170182799267248e-07, "loss": 4.0127, "step": 17779 }, { "epoch": 0.9567369780456306, "grad_norm": 3.4220376014709473, "learning_rate": 2.3112812915195014e-07, "loss": 3.8735, "step": 17780 }, { "epoch": 0.9567907877744296, "grad_norm": 2.6137750148773193, "learning_rate": 2.305551381389659e-07, "loss": 3.9041, "step": 17781 }, { "epoch": 0.9568445975032286, "grad_norm": 2.294398307800293, "learning_rate": 2.2998285497009275e-07, "loss": 4.3064, "step": 17782 }, { "epoch": 0.9568984072320276, "grad_norm": 1.812604308128357, "learning_rate": 2.294112796616843e-07, "loss": 3.5325, "step": 17783 }, { "epoch": 0.9569522169608266, "grad_norm": 1.3255267143249512, "learning_rate": 2.2884041223008024e-07, "loss": 4.7323, "step": 17784 }, { "epoch": 0.9570060266896255, "grad_norm": 2.7961506843566895, "learning_rate": 2.2827025269158698e-07, "loss": 3.0941, "step": 17785 }, { "epoch": 0.9570598364184244, "grad_norm": 2.1438214778900146, "learning_rate": 2.277008010625026e-07, "loss": 4.1691, "step": 17786 }, { "epoch": 0.9571136461472234, "grad_norm": 2.7997827529907227, "learning_rate": 2.2713205735910292e-07, "loss": 3.2631, "step": 17787 }, { "epoch": 0.9571674558760224, "grad_norm": 1.4006032943725586, "learning_rate": 2.2656402159763613e-07, "loss": 4.082, "step": 17788 }, { "epoch": 0.9572212656048213, "grad_norm": 1.4377928972244263, "learning_rate": 2.2599669379433641e-07, "loss": 4.295, "step": 17789 }, { "epoch": 0.9572750753336203, "grad_norm": 3.15384578704834, "learning_rate": 2.2543007396541583e-07, "loss": 3.0507, "step": 17790 }, { "epoch": 0.9573288850624193, "grad_norm": 4.048977375030518, "learning_rate": 2.2486416212706696e-07, "loss": 3.5587, "step": 17791 }, { "epoch": 0.9573826947912183, "grad_norm": 1.8688805103302002, "learning_rate": 2.2429895829546576e-07, "loss": 3.8, "step": 17792 }, { "epoch": 0.9574365045200173, "grad_norm": 3.685981273651123, "learning_rate": 2.2373446248676045e-07, "loss": 3.5055, "step": 17793 }, { "epoch": 0.9574903142488161, "grad_norm": 1.9660019874572754, "learning_rate": 2.231706747170853e-07, "loss": 2.9705, "step": 17794 }, { "epoch": 0.9575441239776151, "grad_norm": 4.997103691101074, "learning_rate": 2.226075950025497e-07, "loss": 2.9531, "step": 17795 }, { "epoch": 0.9575979337064141, "grad_norm": 1.989441990852356, "learning_rate": 2.2204522335924628e-07, "loss": 4.371, "step": 17796 }, { "epoch": 0.9576517434352131, "grad_norm": 2.6175155639648438, "learning_rate": 2.2148355980324276e-07, "loss": 3.6136, "step": 17797 }, { "epoch": 0.9577055531640121, "grad_norm": 1.8611921072006226, "learning_rate": 2.2092260435059574e-07, "loss": 3.4279, "step": 17798 }, { "epoch": 0.957759362892811, "grad_norm": 1.5009092092514038, "learning_rate": 2.2036235701733132e-07, "loss": 4.1014, "step": 17799 }, { "epoch": 0.95781317262161, "grad_norm": 2.1993048191070557, "learning_rate": 2.1980281781945887e-07, "loss": 3.8855, "step": 17800 }, { "epoch": 0.9578669823504089, "grad_norm": 2.9364013671875, "learning_rate": 2.1924398677297397e-07, "loss": 3.6391, "step": 17801 }, { "epoch": 0.9579207920792079, "grad_norm": 2.8364651203155518, "learning_rate": 2.186858638938444e-07, "loss": 3.4659, "step": 17802 }, { "epoch": 0.9579746018080069, "grad_norm": 3.4172298908233643, "learning_rate": 2.1812844919801846e-07, "loss": 2.487, "step": 17803 }, { "epoch": 0.9580284115368058, "grad_norm": 3.42627215385437, "learning_rate": 2.175717427014251e-07, "loss": 4.4544, "step": 17804 }, { "epoch": 0.9580822212656048, "grad_norm": 1.7234001159667969, "learning_rate": 2.1701574441997385e-07, "loss": 4.2255, "step": 17805 }, { "epoch": 0.9581360309944038, "grad_norm": 3.565216541290283, "learning_rate": 2.1646045436955476e-07, "loss": 3.107, "step": 17806 }, { "epoch": 0.9581898407232028, "grad_norm": 3.190513849258423, "learning_rate": 2.1590587256603844e-07, "loss": 4.3288, "step": 17807 }, { "epoch": 0.9582436504520018, "grad_norm": 2.417437791824341, "learning_rate": 2.1535199902526782e-07, "loss": 3.4563, "step": 17808 }, { "epoch": 0.9582974601808006, "grad_norm": 6.524138450622559, "learning_rate": 2.1479883376307464e-07, "loss": 4.2635, "step": 17809 }, { "epoch": 0.9583512699095996, "grad_norm": 1.5107976198196411, "learning_rate": 2.142463767952685e-07, "loss": 3.582, "step": 17810 }, { "epoch": 0.9584050796383986, "grad_norm": 4.009124755859375, "learning_rate": 2.136946281376312e-07, "loss": 3.4124, "step": 17811 }, { "epoch": 0.9584588893671976, "grad_norm": 1.9392926692962646, "learning_rate": 2.1314358780593901e-07, "loss": 3.6152, "step": 17812 }, { "epoch": 0.9585126990959966, "grad_norm": 2.698124885559082, "learning_rate": 2.1259325581592937e-07, "loss": 3.9918, "step": 17813 }, { "epoch": 0.9585665088247955, "grad_norm": 2.1017932891845703, "learning_rate": 2.120436321833369e-07, "loss": 3.85, "step": 17814 }, { "epoch": 0.9586203185535945, "grad_norm": 2.752211809158325, "learning_rate": 2.114947169238657e-07, "loss": 3.1842, "step": 17815 }, { "epoch": 0.9586741282823935, "grad_norm": 3.657409429550171, "learning_rate": 2.1094651005320043e-07, "loss": 3.4839, "step": 17816 }, { "epoch": 0.9587279380111924, "grad_norm": 3.005392074584961, "learning_rate": 2.1039901158701193e-07, "loss": 3.5066, "step": 17817 }, { "epoch": 0.9587817477399914, "grad_norm": 3.6758198738098145, "learning_rate": 2.098522215409432e-07, "loss": 3.3295, "step": 17818 }, { "epoch": 0.9588355574687903, "grad_norm": 2.2884509563446045, "learning_rate": 2.0930613993061788e-07, "loss": 4.0789, "step": 17819 }, { "epoch": 0.9588893671975893, "grad_norm": 2.313023328781128, "learning_rate": 2.087607667716457e-07, "loss": 3.9054, "step": 17820 }, { "epoch": 0.9589431769263883, "grad_norm": 3.6670234203338623, "learning_rate": 2.0821610207960862e-07, "loss": 3.8516, "step": 17821 }, { "epoch": 0.9589969866551873, "grad_norm": 2.719388484954834, "learning_rate": 2.0767214587007476e-07, "loss": 4.0024, "step": 17822 }, { "epoch": 0.9590507963839863, "grad_norm": 2.4123616218566895, "learning_rate": 2.0712889815858728e-07, "loss": 3.8698, "step": 17823 }, { "epoch": 0.9591046061127851, "grad_norm": 2.4531917572021484, "learning_rate": 2.065863589606698e-07, "loss": 4.218, "step": 17824 }, { "epoch": 0.9591584158415841, "grad_norm": 3.3559765815734863, "learning_rate": 2.060445282918294e-07, "loss": 3.577, "step": 17825 }, { "epoch": 0.9592122255703831, "grad_norm": 3.437995672225952, "learning_rate": 2.0550340616754815e-07, "loss": 3.7216, "step": 17826 }, { "epoch": 0.9592660352991821, "grad_norm": 3.7235071659088135, "learning_rate": 2.0496299260328866e-07, "loss": 3.8303, "step": 17827 }, { "epoch": 0.9593198450279811, "grad_norm": 3.872509002685547, "learning_rate": 2.0442328761449693e-07, "loss": 3.1936, "step": 17828 }, { "epoch": 0.95937365475678, "grad_norm": 2.7274811267852783, "learning_rate": 2.038842912165967e-07, "loss": 3.7402, "step": 17829 }, { "epoch": 0.959427464485579, "grad_norm": 3.376631021499634, "learning_rate": 2.0334600342498955e-07, "loss": 4.138, "step": 17830 }, { "epoch": 0.959481274214378, "grad_norm": 1.658697247505188, "learning_rate": 2.0280842425505486e-07, "loss": 4.3499, "step": 17831 }, { "epoch": 0.9595350839431769, "grad_norm": 2.45917010307312, "learning_rate": 2.0227155372216088e-07, "loss": 3.9518, "step": 17832 }, { "epoch": 0.9595888936719759, "grad_norm": 3.619171142578125, "learning_rate": 2.0173539184165091e-07, "loss": 3.8363, "step": 17833 }, { "epoch": 0.9596427034007748, "grad_norm": 2.804363489151001, "learning_rate": 2.0119993862884045e-07, "loss": 3.7788, "step": 17834 }, { "epoch": 0.9596965131295738, "grad_norm": 3.4006104469299316, "learning_rate": 2.0066519409903673e-07, "loss": 4.2419, "step": 17835 }, { "epoch": 0.9597503228583728, "grad_norm": 3.368529796600342, "learning_rate": 2.0013115826751638e-07, "loss": 3.3368, "step": 17836 }, { "epoch": 0.9598041325871718, "grad_norm": 2.252383232116699, "learning_rate": 1.9959783114954778e-07, "loss": 3.3873, "step": 17837 }, { "epoch": 0.9598579423159708, "grad_norm": 2.00565242767334, "learning_rate": 1.9906521276036593e-07, "loss": 4.0323, "step": 17838 }, { "epoch": 0.9599117520447696, "grad_norm": 2.120307683944702, "learning_rate": 1.9853330311519202e-07, "loss": 3.2381, "step": 17839 }, { "epoch": 0.9599655617735686, "grad_norm": 3.826761484146118, "learning_rate": 1.9800210222923054e-07, "loss": 2.9271, "step": 17840 }, { "epoch": 0.9600193715023676, "grad_norm": 2.9883220195770264, "learning_rate": 1.9747161011765825e-07, "loss": 3.0079, "step": 17841 }, { "epoch": 0.9600731812311666, "grad_norm": 2.9099698066711426, "learning_rate": 1.96941826795638e-07, "loss": 3.4957, "step": 17842 }, { "epoch": 0.9601269909599656, "grad_norm": 2.460188388824463, "learning_rate": 1.964127522783049e-07, "loss": 4.1301, "step": 17843 }, { "epoch": 0.9601808006887645, "grad_norm": 3.0744822025299072, "learning_rate": 1.95884386580783e-07, "loss": 3.6602, "step": 17844 }, { "epoch": 0.9602346104175635, "grad_norm": 2.24343204498291, "learning_rate": 1.9535672971817133e-07, "loss": 4.4331, "step": 17845 }, { "epoch": 0.9602884201463625, "grad_norm": 3.0391407012939453, "learning_rate": 1.9482978170554666e-07, "loss": 3.2075, "step": 17846 }, { "epoch": 0.9603422298751614, "grad_norm": 3.3243894577026367, "learning_rate": 1.9430354255796924e-07, "loss": 3.3953, "step": 17847 }, { "epoch": 0.9603960396039604, "grad_norm": 2.653780698776245, "learning_rate": 1.9377801229047697e-07, "loss": 3.2268, "step": 17848 }, { "epoch": 0.9604498493327593, "grad_norm": 1.2206988334655762, "learning_rate": 1.9325319091808847e-07, "loss": 4.1106, "step": 17849 }, { "epoch": 0.9605036590615583, "grad_norm": 1.7798197269439697, "learning_rate": 1.9272907845580002e-07, "loss": 4.2774, "step": 17850 }, { "epoch": 0.9605574687903573, "grad_norm": 3.288947820663452, "learning_rate": 1.9220567491859133e-07, "loss": 3.8627, "step": 17851 }, { "epoch": 0.9606112785191563, "grad_norm": 3.4463260173797607, "learning_rate": 1.9168298032141985e-07, "loss": 3.7788, "step": 17852 }, { "epoch": 0.9606650882479553, "grad_norm": 4.59929084777832, "learning_rate": 1.9116099467922088e-07, "loss": 2.9151, "step": 17853 }, { "epoch": 0.9607188979767542, "grad_norm": 3.6809334754943848, "learning_rate": 1.9063971800691581e-07, "loss": 3.7208, "step": 17854 }, { "epoch": 0.9607727077055531, "grad_norm": 3.554107904434204, "learning_rate": 1.9011915031939553e-07, "loss": 3.085, "step": 17855 }, { "epoch": 0.9608265174343521, "grad_norm": 4.584633827209473, "learning_rate": 1.8959929163153977e-07, "loss": 2.9879, "step": 17856 }, { "epoch": 0.9608803271631511, "grad_norm": 2.1046109199523926, "learning_rate": 1.890801419582061e-07, "loss": 4.0524, "step": 17857 }, { "epoch": 0.9609341368919501, "grad_norm": 2.8247265815734863, "learning_rate": 1.885617013142271e-07, "loss": 2.9235, "step": 17858 }, { "epoch": 0.960987946620749, "grad_norm": 3.6094751358032227, "learning_rate": 1.8804396971441872e-07, "loss": 3.5445, "step": 17859 }, { "epoch": 0.961041756349548, "grad_norm": 4.666646480560303, "learning_rate": 1.8752694717357743e-07, "loss": 3.5707, "step": 17860 }, { "epoch": 0.961095566078347, "grad_norm": 1.4569602012634277, "learning_rate": 1.8701063370648032e-07, "loss": 4.3335, "step": 17861 }, { "epoch": 0.9611493758071459, "grad_norm": 2.905010938644409, "learning_rate": 1.8649502932787666e-07, "loss": 4.4957, "step": 17862 }, { "epoch": 0.9612031855359449, "grad_norm": 2.059828042984009, "learning_rate": 1.8598013405250748e-07, "loss": 4.2182, "step": 17863 }, { "epoch": 0.9612569952647438, "grad_norm": 3.6759486198425293, "learning_rate": 1.8546594789508321e-07, "loss": 3.5664, "step": 17864 }, { "epoch": 0.9613108049935428, "grad_norm": 2.434134006500244, "learning_rate": 1.8495247087030042e-07, "loss": 3.3427, "step": 17865 }, { "epoch": 0.9613646147223418, "grad_norm": 2.2389321327209473, "learning_rate": 1.8443970299283075e-07, "loss": 3.5557, "step": 17866 }, { "epoch": 0.9614184244511408, "grad_norm": 5.851468086242676, "learning_rate": 1.8392764427732633e-07, "loss": 4.294, "step": 17867 }, { "epoch": 0.9614722341799398, "grad_norm": 3.5134522914886475, "learning_rate": 1.834162947384227e-07, "loss": 3.0351, "step": 17868 }, { "epoch": 0.9615260439087387, "grad_norm": 2.3191330432891846, "learning_rate": 1.8290565439073315e-07, "loss": 3.6088, "step": 17869 }, { "epoch": 0.9615798536375376, "grad_norm": 2.7269465923309326, "learning_rate": 1.8239572324885157e-07, "loss": 3.6289, "step": 17870 }, { "epoch": 0.9616336633663366, "grad_norm": 5.130191802978516, "learning_rate": 1.8188650132734963e-07, "loss": 3.6583, "step": 17871 }, { "epoch": 0.9616874730951356, "grad_norm": 3.3482611179351807, "learning_rate": 1.8137798864077405e-07, "loss": 3.194, "step": 17872 }, { "epoch": 0.9617412828239346, "grad_norm": 3.9205565452575684, "learning_rate": 1.8087018520366316e-07, "loss": 2.8901, "step": 17873 }, { "epoch": 0.9617950925527335, "grad_norm": 1.6514708995819092, "learning_rate": 1.8036309103052762e-07, "loss": 3.6514, "step": 17874 }, { "epoch": 0.9618489022815325, "grad_norm": 3.468502998352051, "learning_rate": 1.798567061358586e-07, "loss": 3.0421, "step": 17875 }, { "epoch": 0.9619027120103315, "grad_norm": 5.106856346130371, "learning_rate": 1.7935103053412506e-07, "loss": 3.7577, "step": 17876 }, { "epoch": 0.9619565217391305, "grad_norm": 2.644575595855713, "learning_rate": 1.7884606423977934e-07, "loss": 3.438, "step": 17877 }, { "epoch": 0.9620103314679294, "grad_norm": 2.935192108154297, "learning_rate": 1.7834180726725158e-07, "loss": 4.1996, "step": 17878 }, { "epoch": 0.9620641411967283, "grad_norm": 1.7393823862075806, "learning_rate": 1.7783825963095523e-07, "loss": 4.1057, "step": 17879 }, { "epoch": 0.9621179509255273, "grad_norm": 4.725035190582275, "learning_rate": 1.7733542134527603e-07, "loss": 2.7352, "step": 17880 }, { "epoch": 0.9621717606543263, "grad_norm": 4.280158042907715, "learning_rate": 1.768332924245858e-07, "loss": 4.3751, "step": 17881 }, { "epoch": 0.9622255703831253, "grad_norm": 4.386611461639404, "learning_rate": 1.7633187288323138e-07, "loss": 2.8846, "step": 17882 }, { "epoch": 0.9622793801119243, "grad_norm": 2.095046043395996, "learning_rate": 1.758311627355458e-07, "loss": 3.9765, "step": 17883 }, { "epoch": 0.9623331898407232, "grad_norm": 1.255638599395752, "learning_rate": 1.75331161995837e-07, "loss": 4.6329, "step": 17884 }, { "epoch": 0.9623869995695221, "grad_norm": 2.1823642253875732, "learning_rate": 1.7483187067839358e-07, "loss": 4.137, "step": 17885 }, { "epoch": 0.9624408092983211, "grad_norm": 2.9137051105499268, "learning_rate": 1.7433328879748469e-07, "loss": 3.9028, "step": 17886 }, { "epoch": 0.9624946190271201, "grad_norm": 1.5791932344436646, "learning_rate": 1.7383541636735167e-07, "loss": 4.1964, "step": 17887 }, { "epoch": 0.9625484287559191, "grad_norm": 3.6947877407073975, "learning_rate": 1.733382534022332e-07, "loss": 3.9304, "step": 17888 }, { "epoch": 0.962602238484718, "grad_norm": 3.11079478263855, "learning_rate": 1.72841799916329e-07, "loss": 3.7721, "step": 17889 }, { "epoch": 0.962656048213517, "grad_norm": 3.7938895225524902, "learning_rate": 1.7234605592383047e-07, "loss": 3.4453, "step": 17890 }, { "epoch": 0.962709857942316, "grad_norm": 3.024951219558716, "learning_rate": 1.718510214389013e-07, "loss": 4.4917, "step": 17891 }, { "epoch": 0.962763667671115, "grad_norm": 3.407371997833252, "learning_rate": 1.713566964756913e-07, "loss": 3.3391, "step": 17892 }, { "epoch": 0.9628174773999139, "grad_norm": 3.4730119705200195, "learning_rate": 1.708630810483225e-07, "loss": 3.8429, "step": 17893 }, { "epoch": 0.9628712871287128, "grad_norm": 4.763893127441406, "learning_rate": 1.7037017517090857e-07, "loss": 3.4698, "step": 17894 }, { "epoch": 0.9629250968575118, "grad_norm": 3.460379123687744, "learning_rate": 1.6987797885753e-07, "loss": 3.3908, "step": 17895 }, { "epoch": 0.9629789065863108, "grad_norm": 3.8981146812438965, "learning_rate": 1.69386492122256e-07, "loss": 2.9325, "step": 17896 }, { "epoch": 0.9630327163151098, "grad_norm": 2.9396324157714844, "learning_rate": 1.6889571497912538e-07, "loss": 4.4134, "step": 17897 }, { "epoch": 0.9630865260439088, "grad_norm": 3.1411993503570557, "learning_rate": 1.6840564744216859e-07, "loss": 2.9228, "step": 17898 }, { "epoch": 0.9631403357727077, "grad_norm": 1.8883717060089111, "learning_rate": 1.679162895253883e-07, "loss": 4.6154, "step": 17899 }, { "epoch": 0.9631941455015067, "grad_norm": 2.6130716800689697, "learning_rate": 1.6742764124277333e-07, "loss": 4.1127, "step": 17900 }, { "epoch": 0.9632479552303056, "grad_norm": 1.8010050058364868, "learning_rate": 1.6693970260828196e-07, "loss": 4.0114, "step": 17901 }, { "epoch": 0.9633017649591046, "grad_norm": 4.841637134552002, "learning_rate": 1.6645247363586137e-07, "loss": 4.2493, "step": 17902 }, { "epoch": 0.9633555746879036, "grad_norm": 3.0526576042175293, "learning_rate": 1.6596595433943375e-07, "loss": 3.3553, "step": 17903 }, { "epoch": 0.9634093844167025, "grad_norm": 1.8821355104446411, "learning_rate": 1.6548014473290462e-07, "loss": 4.253, "step": 17904 }, { "epoch": 0.9634631941455015, "grad_norm": 3.484363317489624, "learning_rate": 1.6499504483015738e-07, "loss": 3.5211, "step": 17905 }, { "epoch": 0.9635170038743005, "grad_norm": 2.0994906425476074, "learning_rate": 1.6451065464505034e-07, "loss": 4.1113, "step": 17906 }, { "epoch": 0.9635708136030995, "grad_norm": 3.0503573417663574, "learning_rate": 1.6402697419143077e-07, "loss": 3.6728, "step": 17907 }, { "epoch": 0.9636246233318984, "grad_norm": 3.416520595550537, "learning_rate": 1.6354400348312092e-07, "loss": 3.4338, "step": 17908 }, { "epoch": 0.9636784330606973, "grad_norm": 3.4666669368743896, "learning_rate": 1.6306174253391814e-07, "loss": 3.5854, "step": 17909 }, { "epoch": 0.9637322427894963, "grad_norm": 3.721679925918579, "learning_rate": 1.625801913576086e-07, "loss": 2.7857, "step": 17910 }, { "epoch": 0.9637860525182953, "grad_norm": 2.031259059906006, "learning_rate": 1.6209934996795351e-07, "loss": 3.464, "step": 17911 }, { "epoch": 0.9638398622470943, "grad_norm": 2.022825241088867, "learning_rate": 1.6161921837869187e-07, "loss": 3.6677, "step": 17912 }, { "epoch": 0.9638936719758933, "grad_norm": 3.13031005859375, "learning_rate": 1.6113979660354327e-07, "loss": 2.9229, "step": 17913 }, { "epoch": 0.9639474817046922, "grad_norm": 3.182321310043335, "learning_rate": 1.6066108465621344e-07, "loss": 4.043, "step": 17914 }, { "epoch": 0.9640012914334912, "grad_norm": 1.2992466688156128, "learning_rate": 1.6018308255038028e-07, "loss": 3.9362, "step": 17915 }, { "epoch": 0.9640551011622901, "grad_norm": 2.11633563041687, "learning_rate": 1.5970579029970235e-07, "loss": 4.0263, "step": 17916 }, { "epoch": 0.9641089108910891, "grad_norm": 2.806899070739746, "learning_rate": 1.592292079178215e-07, "loss": 4.065, "step": 17917 }, { "epoch": 0.9641627206198881, "grad_norm": 2.4652388095855713, "learning_rate": 1.5875333541835457e-07, "loss": 4.1134, "step": 17918 }, { "epoch": 0.964216530348687, "grad_norm": 4.530702590942383, "learning_rate": 1.5827817281490186e-07, "loss": 3.4846, "step": 17919 }, { "epoch": 0.964270340077486, "grad_norm": 2.335440158843994, "learning_rate": 1.5780372012104418e-07, "loss": 4.0972, "step": 17920 }, { "epoch": 0.964324149806285, "grad_norm": 2.1138787269592285, "learning_rate": 1.573299773503373e-07, "loss": 3.7113, "step": 17921 }, { "epoch": 0.964377959535084, "grad_norm": 2.861875057220459, "learning_rate": 1.568569445163204e-07, "loss": 3.4837, "step": 17922 }, { "epoch": 0.964431769263883, "grad_norm": 3.591798782348633, "learning_rate": 1.563846216325132e-07, "loss": 3.5871, "step": 17923 }, { "epoch": 0.9644855789926818, "grad_norm": 1.4745795726776123, "learning_rate": 1.5591300871241054e-07, "loss": 4.5486, "step": 17924 }, { "epoch": 0.9645393887214808, "grad_norm": 2.5144543647766113, "learning_rate": 1.5544210576949326e-07, "loss": 3.6882, "step": 17925 }, { "epoch": 0.9645931984502798, "grad_norm": 1.8563768863677979, "learning_rate": 1.5497191281721447e-07, "loss": 4.2824, "step": 17926 }, { "epoch": 0.9646470081790788, "grad_norm": 3.3573577404022217, "learning_rate": 1.545024298690162e-07, "loss": 4.4322, "step": 17927 }, { "epoch": 0.9647008179078778, "grad_norm": 3.0156939029693604, "learning_rate": 1.5403365693830994e-07, "loss": 3.315, "step": 17928 }, { "epoch": 0.9647546276366767, "grad_norm": 3.302306652069092, "learning_rate": 1.5356559403849058e-07, "loss": 3.4884, "step": 17929 }, { "epoch": 0.9648084373654757, "grad_norm": 3.2407333850860596, "learning_rate": 1.530982411829418e-07, "loss": 3.5694, "step": 17930 }, { "epoch": 0.9648622470942746, "grad_norm": 1.7531675100326538, "learning_rate": 1.5263159838501407e-07, "loss": 3.986, "step": 17931 }, { "epoch": 0.9649160568230736, "grad_norm": 3.6180496215820312, "learning_rate": 1.521656656580439e-07, "loss": 3.9373, "step": 17932 }, { "epoch": 0.9649698665518726, "grad_norm": 1.7701358795166016, "learning_rate": 1.517004430153457e-07, "loss": 4.534, "step": 17933 }, { "epoch": 0.9650236762806715, "grad_norm": 3.621613025665283, "learning_rate": 1.5123593047021433e-07, "loss": 3.4192, "step": 17934 }, { "epoch": 0.9650774860094705, "grad_norm": 1.4440422058105469, "learning_rate": 1.5077212803592532e-07, "loss": 3.7654, "step": 17935 }, { "epoch": 0.9651312957382695, "grad_norm": 1.5310462713241577, "learning_rate": 1.5030903572573197e-07, "loss": 4.4527, "step": 17936 }, { "epoch": 0.9651851054670685, "grad_norm": 2.42451810836792, "learning_rate": 1.4984665355287086e-07, "loss": 3.1159, "step": 17937 }, { "epoch": 0.9652389151958675, "grad_norm": 2.263153314590454, "learning_rate": 1.493849815305509e-07, "loss": 3.7278, "step": 17938 }, { "epoch": 0.9652927249246663, "grad_norm": 3.8525607585906982, "learning_rate": 1.4892401967196713e-07, "loss": 3.3838, "step": 17939 }, { "epoch": 0.9653465346534653, "grad_norm": 2.6420414447784424, "learning_rate": 1.4846376799029504e-07, "loss": 3.7348, "step": 17940 }, { "epoch": 0.9654003443822643, "grad_norm": 2.9184155464172363, "learning_rate": 1.4800422649868528e-07, "loss": 3.7236, "step": 17941 }, { "epoch": 0.9654541541110633, "grad_norm": 2.86684250831604, "learning_rate": 1.4754539521027177e-07, "loss": 3.7614, "step": 17942 }, { "epoch": 0.9655079638398623, "grad_norm": 2.620422124862671, "learning_rate": 1.4708727413816347e-07, "loss": 3.6416, "step": 17943 }, { "epoch": 0.9655617735686612, "grad_norm": 1.7480179071426392, "learning_rate": 1.4662986329545548e-07, "loss": 3.9247, "step": 17944 }, { "epoch": 0.9656155832974602, "grad_norm": 5.351312160491943, "learning_rate": 1.4617316269521786e-07, "loss": 4.1684, "step": 17945 }, { "epoch": 0.9656693930262591, "grad_norm": 2.4513001441955566, "learning_rate": 1.4571717235050408e-07, "loss": 4.1959, "step": 17946 }, { "epoch": 0.9657232027550581, "grad_norm": 1.9539066553115845, "learning_rate": 1.4526189227434262e-07, "loss": 3.9766, "step": 17947 }, { "epoch": 0.9657770124838571, "grad_norm": 2.91438364982605, "learning_rate": 1.4480732247974248e-07, "loss": 3.8607, "step": 17948 }, { "epoch": 0.965830822212656, "grad_norm": 2.9820594787597656, "learning_rate": 1.4435346297969888e-07, "loss": 2.9395, "step": 17949 }, { "epoch": 0.965884631941455, "grad_norm": 2.1992998123168945, "learning_rate": 1.4390031378717917e-07, "loss": 3.7565, "step": 17950 }, { "epoch": 0.965938441670254, "grad_norm": 1.8741521835327148, "learning_rate": 1.4344787491513135e-07, "loss": 3.915, "step": 17951 }, { "epoch": 0.965992251399053, "grad_norm": 2.2424585819244385, "learning_rate": 1.4299614637648951e-07, "loss": 3.9363, "step": 17952 }, { "epoch": 0.966046061127852, "grad_norm": 4.103163242340088, "learning_rate": 1.4254512818416e-07, "loss": 3.4587, "step": 17953 }, { "epoch": 0.9660998708566508, "grad_norm": 4.473808288574219, "learning_rate": 1.4209482035102973e-07, "loss": 3.1306, "step": 17954 }, { "epoch": 0.9661536805854498, "grad_norm": 3.831937789916992, "learning_rate": 1.4164522288997173e-07, "loss": 3.6547, "step": 17955 }, { "epoch": 0.9662074903142488, "grad_norm": 3.6355676651000977, "learning_rate": 1.4119633581383406e-07, "loss": 3.9854, "step": 17956 }, { "epoch": 0.9662613000430478, "grad_norm": 5.458300590515137, "learning_rate": 1.407481591354398e-07, "loss": 2.8774, "step": 17957 }, { "epoch": 0.9663151097718468, "grad_norm": 2.830618143081665, "learning_rate": 1.4030069286760095e-07, "loss": 3.9564, "step": 17958 }, { "epoch": 0.9663689195006457, "grad_norm": 1.7250614166259766, "learning_rate": 1.3985393702310167e-07, "loss": 4.3795, "step": 17959 }, { "epoch": 0.9664227292294447, "grad_norm": 3.73329496383667, "learning_rate": 1.3940789161471235e-07, "loss": 2.8198, "step": 17960 }, { "epoch": 0.9664765389582437, "grad_norm": 2.063570261001587, "learning_rate": 1.3896255665517832e-07, "loss": 4.0168, "step": 17961 }, { "epoch": 0.9665303486870426, "grad_norm": 2.4839470386505127, "learning_rate": 1.3851793215722553e-07, "loss": 3.7202, "step": 17962 }, { "epoch": 0.9665841584158416, "grad_norm": 1.7013425827026367, "learning_rate": 1.3807401813356045e-07, "loss": 4.2227, "step": 17963 }, { "epoch": 0.9666379681446405, "grad_norm": 3.295901298522949, "learning_rate": 1.3763081459687022e-07, "loss": 2.9355, "step": 17964 }, { "epoch": 0.9666917778734395, "grad_norm": 1.586020588874817, "learning_rate": 1.3718832155981964e-07, "loss": 4.0751, "step": 17965 }, { "epoch": 0.9667455876022385, "grad_norm": 3.6541812419891357, "learning_rate": 1.367465390350514e-07, "loss": 3.2849, "step": 17966 }, { "epoch": 0.9667993973310375, "grad_norm": 2.9402577877044678, "learning_rate": 1.363054670351943e-07, "loss": 3.6881, "step": 17967 }, { "epoch": 0.9668532070598365, "grad_norm": 2.845172882080078, "learning_rate": 1.3586510557285216e-07, "loss": 3.6251, "step": 17968 }, { "epoch": 0.9669070167886353, "grad_norm": 2.867311954498291, "learning_rate": 1.354254546606093e-07, "loss": 4.1838, "step": 17969 }, { "epoch": 0.9669608265174343, "grad_norm": 3.0506186485290527, "learning_rate": 1.3498651431102793e-07, "loss": 3.6252, "step": 17970 }, { "epoch": 0.9670146362462333, "grad_norm": 3.2679996490478516, "learning_rate": 1.3454828453665357e-07, "loss": 3.4697, "step": 17971 }, { "epoch": 0.9670684459750323, "grad_norm": 2.6419246196746826, "learning_rate": 1.3411076535000677e-07, "loss": 3.6978, "step": 17972 }, { "epoch": 0.9671222557038313, "grad_norm": 2.429194450378418, "learning_rate": 1.3367395676359418e-07, "loss": 3.8185, "step": 17973 }, { "epoch": 0.9671760654326302, "grad_norm": 3.459181547164917, "learning_rate": 1.3323785878990024e-07, "loss": 3.3191, "step": 17974 }, { "epoch": 0.9672298751614292, "grad_norm": 2.5925633907318115, "learning_rate": 1.328024714413789e-07, "loss": 3.7828, "step": 17975 }, { "epoch": 0.9672836848902282, "grad_norm": 3.2844176292419434, "learning_rate": 1.3236779473048132e-07, "loss": 4.175, "step": 17976 }, { "epoch": 0.9673374946190271, "grad_norm": 2.666466474533081, "learning_rate": 1.3193382866962812e-07, "loss": 3.9879, "step": 17977 }, { "epoch": 0.967391304347826, "grad_norm": 3.1683764457702637, "learning_rate": 1.3150057327121767e-07, "loss": 3.8886, "step": 17978 }, { "epoch": 0.967445114076625, "grad_norm": 2.9627928733825684, "learning_rate": 1.31068028547629e-07, "loss": 3.6503, "step": 17979 }, { "epoch": 0.967498923805424, "grad_norm": 2.5783636569976807, "learning_rate": 1.3063619451122999e-07, "loss": 3.6106, "step": 17980 }, { "epoch": 0.967552733534223, "grad_norm": 3.306040048599243, "learning_rate": 1.302050711743552e-07, "loss": 3.7574, "step": 17981 }, { "epoch": 0.967606543263022, "grad_norm": 3.5659663677215576, "learning_rate": 1.297746585493309e-07, "loss": 3.9674, "step": 17982 }, { "epoch": 0.967660352991821, "grad_norm": 2.488690137863159, "learning_rate": 1.2934495664845004e-07, "loss": 3.3659, "step": 17983 }, { "epoch": 0.9677141627206199, "grad_norm": 4.383261680603027, "learning_rate": 1.2891596548399997e-07, "loss": 3.5106, "step": 17984 }, { "epoch": 0.9677679724494188, "grad_norm": 1.7732616662979126, "learning_rate": 1.2848768506823483e-07, "loss": 4.0179, "step": 17985 }, { "epoch": 0.9678217821782178, "grad_norm": 3.181718349456787, "learning_rate": 1.280601154133948e-07, "loss": 3.9501, "step": 17986 }, { "epoch": 0.9678755919070168, "grad_norm": 3.197392702102661, "learning_rate": 1.276332565316979e-07, "loss": 3.0192, "step": 17987 }, { "epoch": 0.9679294016358158, "grad_norm": 3.7044594287872314, "learning_rate": 1.2720710843534545e-07, "loss": 3.9044, "step": 17988 }, { "epoch": 0.9679832113646147, "grad_norm": 3.7744390964508057, "learning_rate": 1.2678167113651384e-07, "loss": 3.8414, "step": 17989 }, { "epoch": 0.9680370210934137, "grad_norm": 4.150675296783447, "learning_rate": 1.2635694464736002e-07, "loss": 3.4008, "step": 17990 }, { "epoch": 0.9680908308222127, "grad_norm": 4.250492095947266, "learning_rate": 1.259329289800215e-07, "loss": 3.0286, "step": 17991 }, { "epoch": 0.9681446405510116, "grad_norm": 2.829827308654785, "learning_rate": 1.2550962414661638e-07, "loss": 3.6686, "step": 17992 }, { "epoch": 0.9681984502798106, "grad_norm": 1.5040041208267212, "learning_rate": 1.2508703015924605e-07, "loss": 4.0483, "step": 17993 }, { "epoch": 0.9682522600086095, "grad_norm": 2.2967751026153564, "learning_rate": 1.2466514702997866e-07, "loss": 4.134, "step": 17994 }, { "epoch": 0.9683060697374085, "grad_norm": 4.5965189933776855, "learning_rate": 1.242439747708768e-07, "loss": 3.521, "step": 17995 }, { "epoch": 0.9683598794662075, "grad_norm": 3.0090994834899902, "learning_rate": 1.2382351339396968e-07, "loss": 3.9991, "step": 17996 }, { "epoch": 0.9684136891950065, "grad_norm": 2.1691043376922607, "learning_rate": 1.2340376291128108e-07, "loss": 4.2225, "step": 17997 }, { "epoch": 0.9684674989238055, "grad_norm": 3.1286063194274902, "learning_rate": 1.2298472333480416e-07, "loss": 3.1671, "step": 17998 }, { "epoch": 0.9685213086526044, "grad_norm": 1.7171958684921265, "learning_rate": 1.2256639467650988e-07, "loss": 4.5516, "step": 17999 }, { "epoch": 0.9685751183814033, "grad_norm": 3.075937509536743, "learning_rate": 1.2214877694835812e-07, "loss": 3.4564, "step": 18000 }, { "epoch": 0.9686289281102023, "grad_norm": 2.5815062522888184, "learning_rate": 1.2173187016227828e-07, "loss": 3.7359, "step": 18001 }, { "epoch": 0.9686827378390013, "grad_norm": 3.461198091506958, "learning_rate": 1.2131567433018854e-07, "loss": 3.2095, "step": 18002 }, { "epoch": 0.9687365475678003, "grad_norm": 3.5841996669769287, "learning_rate": 1.209001894639794e-07, "loss": 3.2912, "step": 18003 }, { "epoch": 0.9687903572965992, "grad_norm": 3.531320571899414, "learning_rate": 1.204854155755275e-07, "loss": 2.8076, "step": 18004 }, { "epoch": 0.9688441670253982, "grad_norm": 2.7223739624023438, "learning_rate": 1.2007135267668445e-07, "loss": 3.4226, "step": 18005 }, { "epoch": 0.9688979767541972, "grad_norm": 3.255258083343506, "learning_rate": 1.1965800077927968e-07, "loss": 2.8886, "step": 18006 }, { "epoch": 0.9689517864829962, "grad_norm": 1.4319267272949219, "learning_rate": 1.192453598951343e-07, "loss": 4.1228, "step": 18007 }, { "epoch": 0.969005596211795, "grad_norm": 3.5987915992736816, "learning_rate": 1.1883343003603053e-07, "loss": 3.3753, "step": 18008 }, { "epoch": 0.969059405940594, "grad_norm": 4.221282482147217, "learning_rate": 1.1842221121374786e-07, "loss": 3.3753, "step": 18009 }, { "epoch": 0.969113215669393, "grad_norm": 1.70293128490448, "learning_rate": 1.1801170344003521e-07, "loss": 3.2523, "step": 18010 }, { "epoch": 0.969167025398192, "grad_norm": 3.660951614379883, "learning_rate": 1.176019067266193e-07, "loss": 2.7222, "step": 18011 }, { "epoch": 0.969220835126991, "grad_norm": 3.5715062618255615, "learning_rate": 1.1719282108521856e-07, "loss": 3.2936, "step": 18012 }, { "epoch": 0.96927464485579, "grad_norm": 3.0075767040252686, "learning_rate": 1.1678444652752086e-07, "loss": 3.8842, "step": 18013 }, { "epoch": 0.9693284545845889, "grad_norm": 2.596564531326294, "learning_rate": 1.1637678306519184e-07, "loss": 4.4321, "step": 18014 }, { "epoch": 0.9693822643133878, "grad_norm": 2.229752779006958, "learning_rate": 1.1596983070988887e-07, "loss": 4.5176, "step": 18015 }, { "epoch": 0.9694360740421868, "grad_norm": 2.421135902404785, "learning_rate": 1.1556358947323598e-07, "loss": 3.9599, "step": 18016 }, { "epoch": 0.9694898837709858, "grad_norm": 3.352844476699829, "learning_rate": 1.151580593668461e-07, "loss": 4.0216, "step": 18017 }, { "epoch": 0.9695436934997848, "grad_norm": 3.3667562007904053, "learning_rate": 1.1475324040230439e-07, "loss": 3.9718, "step": 18018 }, { "epoch": 0.9695975032285837, "grad_norm": 3.79532790184021, "learning_rate": 1.1434913259118495e-07, "loss": 3.2454, "step": 18019 }, { "epoch": 0.9696513129573827, "grad_norm": 2.451540470123291, "learning_rate": 1.1394573594502856e-07, "loss": 3.8439, "step": 18020 }, { "epoch": 0.9697051226861817, "grad_norm": 3.6435797214508057, "learning_rate": 1.135430504753704e-07, "loss": 3.2708, "step": 18021 }, { "epoch": 0.9697589324149807, "grad_norm": 1.7406084537506104, "learning_rate": 1.1314107619371239e-07, "loss": 3.6263, "step": 18022 }, { "epoch": 0.9698127421437795, "grad_norm": 2.9565229415893555, "learning_rate": 1.1273981311154814e-07, "loss": 4.1926, "step": 18023 }, { "epoch": 0.9698665518725785, "grad_norm": 1.9998090267181396, "learning_rate": 1.1233926124034067e-07, "loss": 3.5906, "step": 18024 }, { "epoch": 0.9699203616013775, "grad_norm": 4.37139892578125, "learning_rate": 1.1193942059153639e-07, "loss": 3.7212, "step": 18025 }, { "epoch": 0.9699741713301765, "grad_norm": 3.175172805786133, "learning_rate": 1.115402911765595e-07, "loss": 3.6583, "step": 18026 }, { "epoch": 0.9700279810589755, "grad_norm": 2.9172897338867188, "learning_rate": 1.1114187300682311e-07, "loss": 3.7825, "step": 18027 }, { "epoch": 0.9700817907877745, "grad_norm": 3.109226942062378, "learning_rate": 1.1074416609370697e-07, "loss": 3.2692, "step": 18028 }, { "epoch": 0.9701356005165734, "grad_norm": 3.3459925651550293, "learning_rate": 1.1034717044857701e-07, "loss": 4.0865, "step": 18029 }, { "epoch": 0.9701894102453723, "grad_norm": 3.2748537063598633, "learning_rate": 1.0995088608278248e-07, "loss": 4.0849, "step": 18030 }, { "epoch": 0.9702432199741713, "grad_norm": 3.761545419692993, "learning_rate": 1.0955531300764488e-07, "loss": 2.5815, "step": 18031 }, { "epoch": 0.9702970297029703, "grad_norm": 2.628000020980835, "learning_rate": 1.0916045123446628e-07, "loss": 4.3056, "step": 18032 }, { "epoch": 0.9703508394317693, "grad_norm": 2.4464282989501953, "learning_rate": 1.0876630077453487e-07, "loss": 3.0144, "step": 18033 }, { "epoch": 0.9704046491605682, "grad_norm": 5.217584609985352, "learning_rate": 1.0837286163911386e-07, "loss": 3.8867, "step": 18034 }, { "epoch": 0.9704584588893672, "grad_norm": 2.0267982482910156, "learning_rate": 1.0798013383944705e-07, "loss": 4.1447, "step": 18035 }, { "epoch": 0.9705122686181662, "grad_norm": 3.0529110431671143, "learning_rate": 1.0758811738675323e-07, "loss": 2.7931, "step": 18036 }, { "epoch": 0.9705660783469652, "grad_norm": 2.418147325515747, "learning_rate": 1.071968122922401e-07, "loss": 4.1343, "step": 18037 }, { "epoch": 0.970619888075764, "grad_norm": 3.5166122913360596, "learning_rate": 1.0680621856708761e-07, "loss": 3.6392, "step": 18038 }, { "epoch": 0.970673697804563, "grad_norm": 3.370760440826416, "learning_rate": 1.0641633622245906e-07, "loss": 3.0501, "step": 18039 }, { "epoch": 0.970727507533362, "grad_norm": 2.906635046005249, "learning_rate": 1.0602716526949553e-07, "loss": 3.2879, "step": 18040 }, { "epoch": 0.970781317262161, "grad_norm": 3.1193766593933105, "learning_rate": 1.0563870571931867e-07, "loss": 3.3113, "step": 18041 }, { "epoch": 0.97083512699096, "grad_norm": 2.16816782951355, "learning_rate": 1.0525095758303072e-07, "loss": 4.0232, "step": 18042 }, { "epoch": 0.970888936719759, "grad_norm": 2.552889347076416, "learning_rate": 1.0486392087170893e-07, "loss": 4.3762, "step": 18043 }, { "epoch": 0.9709427464485579, "grad_norm": 3.6882224082946777, "learning_rate": 1.0447759559641945e-07, "loss": 3.3081, "step": 18044 }, { "epoch": 0.9709965561773569, "grad_norm": 2.1807076930999756, "learning_rate": 1.040919817681979e-07, "loss": 4.171, "step": 18045 }, { "epoch": 0.9710503659061558, "grad_norm": 2.961254119873047, "learning_rate": 1.0370707939806324e-07, "loss": 2.9169, "step": 18046 }, { "epoch": 0.9711041756349548, "grad_norm": 1.802993655204773, "learning_rate": 1.0332288849702055e-07, "loss": 4.4162, "step": 18047 }, { "epoch": 0.9711579853637538, "grad_norm": 3.1257710456848145, "learning_rate": 1.0293940907604161e-07, "loss": 3.7639, "step": 18048 }, { "epoch": 0.9712117950925527, "grad_norm": 1.8140459060668945, "learning_rate": 1.0255664114609265e-07, "loss": 4.3567, "step": 18049 }, { "epoch": 0.9712656048213517, "grad_norm": 3.5907273292541504, "learning_rate": 1.0217458471810659e-07, "loss": 3.046, "step": 18050 }, { "epoch": 0.9713194145501507, "grad_norm": 1.5920813083648682, "learning_rate": 1.0179323980300526e-07, "loss": 4.5098, "step": 18051 }, { "epoch": 0.9713732242789497, "grad_norm": 1.5899338722229004, "learning_rate": 1.014126064116827e-07, "loss": 4.3903, "step": 18052 }, { "epoch": 0.9714270340077485, "grad_norm": 2.54728102684021, "learning_rate": 1.0103268455501913e-07, "loss": 3.9341, "step": 18053 }, { "epoch": 0.9714808437365475, "grad_norm": 3.8859729766845703, "learning_rate": 1.006534742438725e-07, "loss": 4.3718, "step": 18054 }, { "epoch": 0.9715346534653465, "grad_norm": 1.5855169296264648, "learning_rate": 1.002749754890786e-07, "loss": 4.3379, "step": 18055 }, { "epoch": 0.9715884631941455, "grad_norm": 3.682467222213745, "learning_rate": 9.989718830145101e-08, "loss": 2.9896, "step": 18056 }, { "epoch": 0.9716422729229445, "grad_norm": 1.9253205060958862, "learning_rate": 9.95201126917894e-08, "loss": 3.9317, "step": 18057 }, { "epoch": 0.9716960826517435, "grad_norm": 2.0280680656433105, "learning_rate": 9.914374867086851e-08, "loss": 3.3136, "step": 18058 }, { "epoch": 0.9717498923805424, "grad_norm": 2.182814121246338, "learning_rate": 9.876809624944361e-08, "loss": 4.1161, "step": 18059 }, { "epoch": 0.9718037021093414, "grad_norm": 3.7402491569519043, "learning_rate": 9.839315543825056e-08, "loss": 2.6718, "step": 18060 }, { "epoch": 0.9718575118381403, "grad_norm": 1.5939568281173706, "learning_rate": 9.801892624800302e-08, "loss": 4.113, "step": 18061 }, { "epoch": 0.9719113215669393, "grad_norm": 2.854823112487793, "learning_rate": 9.764540868939798e-08, "loss": 3.3254, "step": 18062 }, { "epoch": 0.9719651312957382, "grad_norm": 2.8000030517578125, "learning_rate": 9.727260277310746e-08, "loss": 3.2814, "step": 18063 }, { "epoch": 0.9720189410245372, "grad_norm": 1.9752676486968994, "learning_rate": 9.690050850978404e-08, "loss": 3.6427, "step": 18064 }, { "epoch": 0.9720727507533362, "grad_norm": 3.3112871646881104, "learning_rate": 9.65291259100637e-08, "loss": 3.7425, "step": 18065 }, { "epoch": 0.9721265604821352, "grad_norm": 2.7186172008514404, "learning_rate": 9.615845498455733e-08, "loss": 3.6268, "step": 18066 }, { "epoch": 0.9721803702109342, "grad_norm": 2.182950735092163, "learning_rate": 9.578849574385928e-08, "loss": 2.8938, "step": 18067 }, { "epoch": 0.9722341799397332, "grad_norm": 4.8163862228393555, "learning_rate": 9.541924819854164e-08, "loss": 3.3588, "step": 18068 }, { "epoch": 0.972287989668532, "grad_norm": 2.46325421333313, "learning_rate": 9.50507123591543e-08, "loss": 3.4928, "step": 18069 }, { "epoch": 0.972341799397331, "grad_norm": 2.587451934814453, "learning_rate": 9.468288823623605e-08, "loss": 2.7847, "step": 18070 }, { "epoch": 0.97239560912613, "grad_norm": 2.585263967514038, "learning_rate": 9.431577584028961e-08, "loss": 3.7363, "step": 18071 }, { "epoch": 0.972449418854929, "grad_norm": 1.787610411643982, "learning_rate": 9.394937518181213e-08, "loss": 4.5798, "step": 18072 }, { "epoch": 0.972503228583728, "grad_norm": 2.680032730102539, "learning_rate": 9.358368627127023e-08, "loss": 3.3005, "step": 18073 }, { "epoch": 0.9725570383125269, "grad_norm": 1.6599735021591187, "learning_rate": 9.321870911911668e-08, "loss": 3.8097, "step": 18074 }, { "epoch": 0.9726108480413259, "grad_norm": 1.9252161979675293, "learning_rate": 9.285444373577923e-08, "loss": 3.2272, "step": 18075 }, { "epoch": 0.9726646577701248, "grad_norm": 3.622610330581665, "learning_rate": 9.249089013167178e-08, "loss": 4.1348, "step": 18076 }, { "epoch": 0.9727184674989238, "grad_norm": 3.4886999130249023, "learning_rate": 9.212804831718324e-08, "loss": 3.8084, "step": 18077 }, { "epoch": 0.9727722772277227, "grad_norm": 4.201951026916504, "learning_rate": 9.176591830267756e-08, "loss": 3.3576, "step": 18078 }, { "epoch": 0.9728260869565217, "grad_norm": 2.799654245376587, "learning_rate": 9.140450009850754e-08, "loss": 3.6434, "step": 18079 }, { "epoch": 0.9728798966853207, "grad_norm": 2.1105964183807373, "learning_rate": 9.104379371500105e-08, "loss": 3.5987, "step": 18080 }, { "epoch": 0.9729337064141197, "grad_norm": 4.477572917938232, "learning_rate": 9.068379916246372e-08, "loss": 3.639, "step": 18081 }, { "epoch": 0.9729875161429187, "grad_norm": 3.334108829498291, "learning_rate": 9.032451645118733e-08, "loss": 3.1214, "step": 18082 }, { "epoch": 0.9730413258717177, "grad_norm": 2.004478693008423, "learning_rate": 8.99659455914359e-08, "loss": 3.9714, "step": 18083 }, { "epoch": 0.9730951356005165, "grad_norm": 2.1189568042755127, "learning_rate": 8.960808659345954e-08, "loss": 4.0279, "step": 18084 }, { "epoch": 0.9731489453293155, "grad_norm": 3.310675621032715, "learning_rate": 8.925093946748065e-08, "loss": 4.1419, "step": 18085 }, { "epoch": 0.9732027550581145, "grad_norm": 3.1396284103393555, "learning_rate": 8.889450422371048e-08, "loss": 3.4381, "step": 18086 }, { "epoch": 0.9732565647869135, "grad_norm": 2.5444328784942627, "learning_rate": 8.85387808723298e-08, "loss": 4.013, "step": 18087 }, { "epoch": 0.9733103745157125, "grad_norm": 4.444502353668213, "learning_rate": 8.818376942350825e-08, "loss": 3.6226, "step": 18088 }, { "epoch": 0.9733641842445114, "grad_norm": 4.580112934112549, "learning_rate": 8.782946988739049e-08, "loss": 4.5022, "step": 18089 }, { "epoch": 0.9734179939733104, "grad_norm": 2.2751293182373047, "learning_rate": 8.747588227409898e-08, "loss": 4.0579, "step": 18090 }, { "epoch": 0.9734718037021094, "grad_norm": 3.2545206546783447, "learning_rate": 8.712300659373951e-08, "loss": 3.61, "step": 18091 }, { "epoch": 0.9735256134309083, "grad_norm": 2.3836073875427246, "learning_rate": 8.677084285639847e-08, "loss": 4.0438, "step": 18092 }, { "epoch": 0.9735794231597072, "grad_norm": 2.743016004562378, "learning_rate": 8.641939107213726e-08, "loss": 4.2261, "step": 18093 }, { "epoch": 0.9736332328885062, "grad_norm": 2.59222412109375, "learning_rate": 8.60686512510006e-08, "loss": 3.5338, "step": 18094 }, { "epoch": 0.9736870426173052, "grad_norm": 4.026246070861816, "learning_rate": 8.571862340301106e-08, "loss": 2.9828, "step": 18095 }, { "epoch": 0.9737408523461042, "grad_norm": 1.339986801147461, "learning_rate": 8.536930753816896e-08, "loss": 3.8568, "step": 18096 }, { "epoch": 0.9737946620749032, "grad_norm": 2.3595614433288574, "learning_rate": 8.502070366646353e-08, "loss": 3.3481, "step": 18097 }, { "epoch": 0.9738484718037022, "grad_norm": 1.907099962234497, "learning_rate": 8.467281179785069e-08, "loss": 4.0386, "step": 18098 }, { "epoch": 0.973902281532501, "grad_norm": 3.6014416217803955, "learning_rate": 8.432563194227527e-08, "loss": 3.5097, "step": 18099 }, { "epoch": 0.9739560912613, "grad_norm": 3.3133232593536377, "learning_rate": 8.397916410965989e-08, "loss": 3.0374, "step": 18100 }, { "epoch": 0.974009900990099, "grad_norm": 3.0658388137817383, "learning_rate": 8.363340830990219e-08, "loss": 3.1591, "step": 18101 }, { "epoch": 0.974063710718898, "grad_norm": 2.962888240814209, "learning_rate": 8.328836455288314e-08, "loss": 3.748, "step": 18102 }, { "epoch": 0.974117520447697, "grad_norm": 4.058201313018799, "learning_rate": 8.294403284846708e-08, "loss": 3.609, "step": 18103 }, { "epoch": 0.9741713301764959, "grad_norm": 3.6924405097961426, "learning_rate": 8.260041320648781e-08, "loss": 3.0493, "step": 18104 }, { "epoch": 0.9742251399052949, "grad_norm": 2.6462395191192627, "learning_rate": 8.225750563677082e-08, "loss": 3.7276, "step": 18105 }, { "epoch": 0.9742789496340939, "grad_norm": 2.317310333251953, "learning_rate": 8.19153101491138e-08, "loss": 4.0696, "step": 18106 }, { "epoch": 0.9743327593628928, "grad_norm": 3.8362083435058594, "learning_rate": 8.157382675329506e-08, "loss": 3.6133, "step": 18107 }, { "epoch": 0.9743865690916917, "grad_norm": 2.3281056880950928, "learning_rate": 8.123305545907622e-08, "loss": 2.7437, "step": 18108 }, { "epoch": 0.9744403788204907, "grad_norm": 2.353236436843872, "learning_rate": 8.089299627619118e-08, "loss": 4.1138, "step": 18109 }, { "epoch": 0.9744941885492897, "grad_norm": 1.470204472541809, "learning_rate": 8.055364921435715e-08, "loss": 3.0201, "step": 18110 }, { "epoch": 0.9745479982780887, "grad_norm": 2.635831117630005, "learning_rate": 8.02150142832775e-08, "loss": 3.53, "step": 18111 }, { "epoch": 0.9746018080068877, "grad_norm": 3.035078287124634, "learning_rate": 7.987709149262501e-08, "loss": 3.423, "step": 18112 }, { "epoch": 0.9746556177356867, "grad_norm": 3.3661181926727295, "learning_rate": 7.953988085205866e-08, "loss": 3.3688, "step": 18113 }, { "epoch": 0.9747094274644856, "grad_norm": 1.247155785560608, "learning_rate": 7.920338237121516e-08, "loss": 4.1449, "step": 18114 }, { "epoch": 0.9747632371932845, "grad_norm": 4.135477066040039, "learning_rate": 7.886759605970907e-08, "loss": 2.783, "step": 18115 }, { "epoch": 0.9748170469220835, "grad_norm": 1.9620707035064697, "learning_rate": 7.853252192713823e-08, "loss": 4.0852, "step": 18116 }, { "epoch": 0.9748708566508825, "grad_norm": 1.3215900659561157, "learning_rate": 7.819815998307556e-08, "loss": 4.3136, "step": 18117 }, { "epoch": 0.9749246663796814, "grad_norm": 3.7193918228149414, "learning_rate": 7.786451023707731e-08, "loss": 3.9585, "step": 18118 }, { "epoch": 0.9749784761084804, "grad_norm": 3.426165819168091, "learning_rate": 7.75315726986775e-08, "loss": 3.5744, "step": 18119 }, { "epoch": 0.9750322858372794, "grad_norm": 1.919506549835205, "learning_rate": 7.719934737739353e-08, "loss": 4.2108, "step": 18120 }, { "epoch": 0.9750860955660784, "grad_norm": 1.7232446670532227, "learning_rate": 7.686783428271782e-08, "loss": 3.6983, "step": 18121 }, { "epoch": 0.9751399052948773, "grad_norm": 3.7026777267456055, "learning_rate": 7.65370334241261e-08, "loss": 3.4695, "step": 18122 }, { "epoch": 0.9751937150236762, "grad_norm": 3.4312689304351807, "learning_rate": 7.620694481106916e-08, "loss": 3.7727, "step": 18123 }, { "epoch": 0.9752475247524752, "grad_norm": 2.402998685836792, "learning_rate": 7.587756845297833e-08, "loss": 3.2214, "step": 18124 }, { "epoch": 0.9753013344812742, "grad_norm": 1.9377105236053467, "learning_rate": 7.554890435926832e-08, "loss": 3.3329, "step": 18125 }, { "epoch": 0.9753551442100732, "grad_norm": 3.1319916248321533, "learning_rate": 7.522095253933159e-08, "loss": 3.936, "step": 18126 }, { "epoch": 0.9754089539388722, "grad_norm": 6.136085033416748, "learning_rate": 7.4893713002544e-08, "loss": 3.8268, "step": 18127 }, { "epoch": 0.9754627636676712, "grad_norm": 2.9938666820526123, "learning_rate": 7.456718575825084e-08, "loss": 4.2129, "step": 18128 }, { "epoch": 0.9755165733964701, "grad_norm": 2.3717093467712402, "learning_rate": 7.42413708157863e-08, "loss": 3.7124, "step": 18129 }, { "epoch": 0.975570383125269, "grad_norm": 3.0355162620544434, "learning_rate": 7.391626818445963e-08, "loss": 4.0759, "step": 18130 }, { "epoch": 0.975624192854068, "grad_norm": 3.579054594039917, "learning_rate": 7.359187787356336e-08, "loss": 3.7577, "step": 18131 }, { "epoch": 0.975678002582867, "grad_norm": 2.9938840866088867, "learning_rate": 7.326819989236788e-08, "loss": 3.8981, "step": 18132 }, { "epoch": 0.975731812311666, "grad_norm": 3.230377197265625, "learning_rate": 7.294523425012134e-08, "loss": 2.3605, "step": 18133 }, { "epoch": 0.9757856220404649, "grad_norm": 2.5608134269714355, "learning_rate": 7.262298095605524e-08, "loss": 3.2919, "step": 18134 }, { "epoch": 0.9758394317692639, "grad_norm": 3.6304659843444824, "learning_rate": 7.23014400193761e-08, "loss": 3.1294, "step": 18135 }, { "epoch": 0.9758932414980629, "grad_norm": 5.469776153564453, "learning_rate": 7.198061144927659e-08, "loss": 1.6644, "step": 18136 }, { "epoch": 0.9759470512268618, "grad_norm": 2.9623961448669434, "learning_rate": 7.16604952549188e-08, "loss": 2.8679, "step": 18137 }, { "epoch": 0.9760008609556607, "grad_norm": 2.974698781967163, "learning_rate": 7.13410914454593e-08, "loss": 3.8794, "step": 18138 }, { "epoch": 0.9760546706844597, "grad_norm": 1.3535172939300537, "learning_rate": 7.102240003001859e-08, "loss": 4.4281, "step": 18139 }, { "epoch": 0.9761084804132587, "grad_norm": 4.759344100952148, "learning_rate": 7.070442101770602e-08, "loss": 3.7126, "step": 18140 }, { "epoch": 0.9761622901420577, "grad_norm": 2.6265978813171387, "learning_rate": 7.038715441761157e-08, "loss": 2.986, "step": 18141 }, { "epoch": 0.9762160998708567, "grad_norm": 1.591904878616333, "learning_rate": 7.007060023879742e-08, "loss": 4.2422, "step": 18142 }, { "epoch": 0.9762699095996556, "grad_norm": 2.690336227416992, "learning_rate": 6.975475849031188e-08, "loss": 3.7138, "step": 18143 }, { "epoch": 0.9763237193284546, "grad_norm": 1.8004072904586792, "learning_rate": 6.943962918118107e-08, "loss": 4.2338, "step": 18144 }, { "epoch": 0.9763775290572535, "grad_norm": 3.171792507171631, "learning_rate": 6.912521232041169e-08, "loss": 3.8252, "step": 18145 }, { "epoch": 0.9764313387860525, "grad_norm": 1.3365639448165894, "learning_rate": 6.881150791698543e-08, "loss": 4.3591, "step": 18146 }, { "epoch": 0.9764851485148515, "grad_norm": 3.0394082069396973, "learning_rate": 6.849851597987012e-08, "loss": 2.93, "step": 18147 }, { "epoch": 0.9765389582436504, "grad_norm": 3.303924322128296, "learning_rate": 6.818623651801137e-08, "loss": 3.802, "step": 18148 }, { "epoch": 0.9765927679724494, "grad_norm": 2.372507333755493, "learning_rate": 6.787466954032984e-08, "loss": 4.4317, "step": 18149 }, { "epoch": 0.9766465777012484, "grad_norm": 3.254687786102295, "learning_rate": 6.756381505572951e-08, "loss": 3.7771, "step": 18150 }, { "epoch": 0.9767003874300474, "grad_norm": 2.9699225425720215, "learning_rate": 6.725367307309494e-08, "loss": 4.3548, "step": 18151 }, { "epoch": 0.9767541971588464, "grad_norm": 1.9126968383789062, "learning_rate": 6.694424360129126e-08, "loss": 3.962, "step": 18152 }, { "epoch": 0.9768080068876452, "grad_norm": 2.43857479095459, "learning_rate": 6.663552664915585e-08, "loss": 4.2439, "step": 18153 }, { "epoch": 0.9768618166164442, "grad_norm": 1.691702127456665, "learning_rate": 6.632752222551774e-08, "loss": 4.26, "step": 18154 }, { "epoch": 0.9769156263452432, "grad_norm": 1.8616200685501099, "learning_rate": 6.602023033917271e-08, "loss": 4.0653, "step": 18155 }, { "epoch": 0.9769694360740422, "grad_norm": 3.8215725421905518, "learning_rate": 6.571365099890814e-08, "loss": 3.6126, "step": 18156 }, { "epoch": 0.9770232458028412, "grad_norm": 3.7514708042144775, "learning_rate": 6.540778421347815e-08, "loss": 4.2413, "step": 18157 }, { "epoch": 0.9770770555316401, "grad_norm": 2.6057920455932617, "learning_rate": 6.51026299916313e-08, "loss": 3.5174, "step": 18158 }, { "epoch": 0.9771308652604391, "grad_norm": 2.6918277740478516, "learning_rate": 6.479818834208285e-08, "loss": 3.8867, "step": 18159 }, { "epoch": 0.977184674989238, "grad_norm": 3.8370800018310547, "learning_rate": 6.449445927353138e-08, "loss": 3.2005, "step": 18160 }, { "epoch": 0.977238484718037, "grad_norm": 2.1708076000213623, "learning_rate": 6.419144279466438e-08, "loss": 4.0869, "step": 18161 }, { "epoch": 0.977292294446836, "grad_norm": 2.3295722007751465, "learning_rate": 6.388913891413328e-08, "loss": 4.112, "step": 18162 }, { "epoch": 0.9773461041756349, "grad_norm": 4.3525071144104, "learning_rate": 6.358754764058117e-08, "loss": 2.8359, "step": 18163 }, { "epoch": 0.9773999139044339, "grad_norm": 2.397927761077881, "learning_rate": 6.328666898262614e-08, "loss": 3.6346, "step": 18164 }, { "epoch": 0.9774537236332329, "grad_norm": 1.611127495765686, "learning_rate": 6.298650294886687e-08, "loss": 4.1965, "step": 18165 }, { "epoch": 0.9775075333620319, "grad_norm": 2.480020046234131, "learning_rate": 6.268704954787985e-08, "loss": 3.6181, "step": 18166 }, { "epoch": 0.9775613430908309, "grad_norm": 2.1196093559265137, "learning_rate": 6.238830878822211e-08, "loss": 4.0377, "step": 18167 }, { "epoch": 0.9776151528196297, "grad_norm": 2.793893337249756, "learning_rate": 6.209028067843404e-08, "loss": 3.8052, "step": 18168 }, { "epoch": 0.9776689625484287, "grad_norm": 4.8277058601379395, "learning_rate": 6.179296522703104e-08, "loss": 3.2609, "step": 18169 }, { "epoch": 0.9777227722772277, "grad_norm": 2.738929510116577, "learning_rate": 6.149636244250911e-08, "loss": 3.3314, "step": 18170 }, { "epoch": 0.9777765820060267, "grad_norm": 4.010640621185303, "learning_rate": 6.120047233334203e-08, "loss": 3.1883, "step": 18171 }, { "epoch": 0.9778303917348257, "grad_norm": 2.923299789428711, "learning_rate": 6.090529490798968e-08, "loss": 3.5673, "step": 18172 }, { "epoch": 0.9778842014636246, "grad_norm": 5.791275978088379, "learning_rate": 6.0610830174887e-08, "loss": 2.055, "step": 18173 }, { "epoch": 0.9779380111924236, "grad_norm": 3.5086607933044434, "learning_rate": 6.03170781424467e-08, "loss": 3.4442, "step": 18174 }, { "epoch": 0.9779918209212226, "grad_norm": 2.918790817260742, "learning_rate": 6.002403881906204e-08, "loss": 3.9802, "step": 18175 }, { "epoch": 0.9780456306500215, "grad_norm": 2.846771240234375, "learning_rate": 5.973171221311247e-08, "loss": 3.0847, "step": 18176 }, { "epoch": 0.9780994403788205, "grad_norm": 1.7225145101547241, "learning_rate": 5.944009833294961e-08, "loss": 4.212, "step": 18177 }, { "epoch": 0.9781532501076194, "grad_norm": 3.0597126483917236, "learning_rate": 5.9149197186905704e-08, "loss": 3.4874, "step": 18178 }, { "epoch": 0.9782070598364184, "grad_norm": 2.835777997970581, "learning_rate": 5.885900878329353e-08, "loss": 3.5398, "step": 18179 }, { "epoch": 0.9782608695652174, "grad_norm": 2.3001623153686523, "learning_rate": 5.8569533130409247e-08, "loss": 4.3088, "step": 18180 }, { "epoch": 0.9783146792940164, "grad_norm": 4.231229782104492, "learning_rate": 5.8280770236518456e-08, "loss": 3.2646, "step": 18181 }, { "epoch": 0.9783684890228154, "grad_norm": 3.604706048965454, "learning_rate": 5.799272010988399e-08, "loss": 4.1311, "step": 18182 }, { "epoch": 0.9784222987516142, "grad_norm": 2.325517177581787, "learning_rate": 5.770538275872706e-08, "loss": 3.9477, "step": 18183 }, { "epoch": 0.9784761084804132, "grad_norm": 4.219847679138184, "learning_rate": 5.7418758191266076e-08, "loss": 2.6633, "step": 18184 }, { "epoch": 0.9785299182092122, "grad_norm": 1.5131505727767944, "learning_rate": 5.7132846415688946e-08, "loss": 4.2195, "step": 18185 }, { "epoch": 0.9785837279380112, "grad_norm": 2.736572027206421, "learning_rate": 5.684764744016413e-08, "loss": 3.9926, "step": 18186 }, { "epoch": 0.9786375376668102, "grad_norm": 2.831817150115967, "learning_rate": 5.656316127284622e-08, "loss": 3.4719, "step": 18187 }, { "epoch": 0.9786913473956091, "grad_norm": 3.9464986324310303, "learning_rate": 5.6279387921864826e-08, "loss": 3.9006, "step": 18188 }, { "epoch": 0.9787451571244081, "grad_norm": 4.918781280517578, "learning_rate": 5.5996327395324566e-08, "loss": 3.55, "step": 18189 }, { "epoch": 0.9787989668532071, "grad_norm": 3.8898003101348877, "learning_rate": 5.571397970132175e-08, "loss": 2.9395, "step": 18190 }, { "epoch": 0.978852776582006, "grad_norm": 2.445451021194458, "learning_rate": 5.5432344847916595e-08, "loss": 3.2278, "step": 18191 }, { "epoch": 0.978906586310805, "grad_norm": 2.383924722671509, "learning_rate": 5.5151422843166544e-08, "loss": 4.1104, "step": 18192 }, { "epoch": 0.9789603960396039, "grad_norm": 2.199211597442627, "learning_rate": 5.487121369509296e-08, "loss": 2.8268, "step": 18193 }, { "epoch": 0.9790142057684029, "grad_norm": 2.972935438156128, "learning_rate": 5.4591717411703325e-08, "loss": 4.4, "step": 18194 }, { "epoch": 0.9790680154972019, "grad_norm": 3.6068081855773926, "learning_rate": 5.4312934000991244e-08, "loss": 3.2716, "step": 18195 }, { "epoch": 0.9791218252260009, "grad_norm": 3.914083480834961, "learning_rate": 5.403486347091702e-08, "loss": 3.4077, "step": 18196 }, { "epoch": 0.9791756349547999, "grad_norm": 1.9216102361679077, "learning_rate": 5.3757505829429844e-08, "loss": 3.8701, "step": 18197 }, { "epoch": 0.9792294446835988, "grad_norm": 1.4974615573883057, "learning_rate": 5.3480861084453936e-08, "loss": 4.3928, "step": 18198 }, { "epoch": 0.9792832544123977, "grad_norm": 2.2277956008911133, "learning_rate": 5.3204929243899636e-08, "loss": 3.6866, "step": 18199 }, { "epoch": 0.9793370641411967, "grad_norm": 3.1571671962738037, "learning_rate": 5.2929710315649526e-08, "loss": 2.9908, "step": 18200 }, { "epoch": 0.9793908738699957, "grad_norm": 2.720830202102661, "learning_rate": 5.2655204307566765e-08, "loss": 3.8001, "step": 18201 }, { "epoch": 0.9794446835987947, "grad_norm": 4.63127326965332, "learning_rate": 5.238141122749784e-08, "loss": 3.8144, "step": 18202 }, { "epoch": 0.9794984933275936, "grad_norm": 3.852362632751465, "learning_rate": 5.210833108326707e-08, "loss": 3.7038, "step": 18203 }, { "epoch": 0.9795523030563926, "grad_norm": 3.4377124309539795, "learning_rate": 5.18359638826793e-08, "loss": 3.279, "step": 18204 }, { "epoch": 0.9796061127851916, "grad_norm": 2.5290207862854004, "learning_rate": 5.1564309633517217e-08, "loss": 3.5987, "step": 18205 }, { "epoch": 0.9796599225139905, "grad_norm": 2.7727715969085693, "learning_rate": 5.1293368343544036e-08, "loss": 3.6373, "step": 18206 }, { "epoch": 0.9797137322427895, "grad_norm": 3.2798969745635986, "learning_rate": 5.102314002050079e-08, "loss": 2.851, "step": 18207 }, { "epoch": 0.9797675419715884, "grad_norm": 1.8018711805343628, "learning_rate": 5.075362467211187e-08, "loss": 3.6374, "step": 18208 }, { "epoch": 0.9798213517003874, "grad_norm": 3.1509134769439697, "learning_rate": 5.0484822306079426e-08, "loss": 3.9165, "step": 18209 }, { "epoch": 0.9798751614291864, "grad_norm": 3.9575042724609375, "learning_rate": 5.021673293008344e-08, "loss": 3.7529, "step": 18210 }, { "epoch": 0.9799289711579854, "grad_norm": 2.801454544067383, "learning_rate": 4.9949356551784453e-08, "loss": 4.2654, "step": 18211 }, { "epoch": 0.9799827808867844, "grad_norm": 2.999929428100586, "learning_rate": 4.968269317882912e-08, "loss": 3.1487, "step": 18212 }, { "epoch": 0.9800365906155833, "grad_norm": 3.2442877292633057, "learning_rate": 4.9416742818830796e-08, "loss": 3.278, "step": 18213 }, { "epoch": 0.9800904003443822, "grad_norm": 2.3905200958251953, "learning_rate": 4.915150547939451e-08, "loss": 3.775, "step": 18214 }, { "epoch": 0.9801442100731812, "grad_norm": 2.348130941390991, "learning_rate": 4.8886981168097537e-08, "loss": 3.4438, "step": 18215 }, { "epoch": 0.9801980198019802, "grad_norm": 2.409749984741211, "learning_rate": 4.862316989250049e-08, "loss": 4.3035, "step": 18216 }, { "epoch": 0.9802518295307792, "grad_norm": 4.184374809265137, "learning_rate": 4.836007166014178e-08, "loss": 2.8471, "step": 18217 }, { "epoch": 0.9803056392595781, "grad_norm": 2.555687189102173, "learning_rate": 4.8097686478540406e-08, "loss": 4.2503, "step": 18218 }, { "epoch": 0.9803594489883771, "grad_norm": 3.741128444671631, "learning_rate": 4.783601435519314e-08, "loss": 3.2385, "step": 18219 }, { "epoch": 0.9804132587171761, "grad_norm": 3.620835781097412, "learning_rate": 4.7575055297580107e-08, "loss": 3.0699, "step": 18220 }, { "epoch": 0.9804670684459751, "grad_norm": 2.5148537158966064, "learning_rate": 4.731480931315924e-08, "loss": 4.069, "step": 18221 }, { "epoch": 0.980520878174774, "grad_norm": 4.4838972091674805, "learning_rate": 4.705527640936347e-08, "loss": 2.8923, "step": 18222 }, { "epoch": 0.9805746879035729, "grad_norm": 4.595857620239258, "learning_rate": 4.679645659361464e-08, "loss": 4.0334, "step": 18223 }, { "epoch": 0.9806284976323719, "grad_norm": 2.7304012775421143, "learning_rate": 4.6538349873306855e-08, "loss": 3.5931, "step": 18224 }, { "epoch": 0.9806823073611709, "grad_norm": 2.392312526702881, "learning_rate": 4.6280956255814745e-08, "loss": 3.8541, "step": 18225 }, { "epoch": 0.9807361170899699, "grad_norm": 1.8878703117370605, "learning_rate": 4.602427574849633e-08, "loss": 4.0557, "step": 18226 }, { "epoch": 0.9807899268187689, "grad_norm": 2.2367103099823, "learning_rate": 4.576830835868462e-08, "loss": 4.1016, "step": 18227 }, { "epoch": 0.9808437365475678, "grad_norm": 3.987492561340332, "learning_rate": 4.5513054093695995e-08, "loss": 3.5483, "step": 18228 }, { "epoch": 0.9808975462763667, "grad_norm": 3.2704918384552, "learning_rate": 4.5258512960824616e-08, "loss": 2.9119, "step": 18229 }, { "epoch": 0.9809513560051657, "grad_norm": 3.9520132541656494, "learning_rate": 4.5004684967345226e-08, "loss": 3.896, "step": 18230 }, { "epoch": 0.9810051657339647, "grad_norm": 3.8463077545166016, "learning_rate": 4.4751570120510347e-08, "loss": 3.7842, "step": 18231 }, { "epoch": 0.9810589754627637, "grad_norm": 3.0211169719696045, "learning_rate": 4.449916842755308e-08, "loss": 3.9197, "step": 18232 }, { "epoch": 0.9811127851915626, "grad_norm": 3.2429697513580322, "learning_rate": 4.424747989568989e-08, "loss": 2.8622, "step": 18233 }, { "epoch": 0.9811665949203616, "grad_norm": 1.864222526550293, "learning_rate": 4.399650453210669e-08, "loss": 4.2739, "step": 18234 }, { "epoch": 0.9812204046491606, "grad_norm": 4.395823001861572, "learning_rate": 4.3746242343983836e-08, "loss": 3.8663, "step": 18235 }, { "epoch": 0.9812742143779596, "grad_norm": 2.253894090652466, "learning_rate": 4.3496693338465624e-08, "loss": 3.9375, "step": 18236 }, { "epoch": 0.9813280241067585, "grad_norm": 2.7607905864715576, "learning_rate": 4.3247857522688006e-08, "loss": 4.5713, "step": 18237 }, { "epoch": 0.9813818338355574, "grad_norm": 2.073394298553467, "learning_rate": 4.299973490376197e-08, "loss": 3.2106, "step": 18238 }, { "epoch": 0.9814356435643564, "grad_norm": 4.43211555480957, "learning_rate": 4.275232548877628e-08, "loss": 3.7121, "step": 18239 }, { "epoch": 0.9814894532931554, "grad_norm": 2.6940009593963623, "learning_rate": 4.2505629284800284e-08, "loss": 3.5703, "step": 18240 }, { "epoch": 0.9815432630219544, "grad_norm": 2.8688316345214844, "learning_rate": 4.225964629888668e-08, "loss": 3.7455, "step": 18241 }, { "epoch": 0.9815970727507534, "grad_norm": 3.520550012588501, "learning_rate": 4.201437653806595e-08, "loss": 3.1919, "step": 18242 }, { "epoch": 0.9816508824795523, "grad_norm": 2.132937431335449, "learning_rate": 4.17698200093436e-08, "loss": 3.9434, "step": 18243 }, { "epoch": 0.9817046922083512, "grad_norm": 2.3036882877349854, "learning_rate": 4.152597671970848e-08, "loss": 4.4992, "step": 18244 }, { "epoch": 0.9817585019371502, "grad_norm": 3.494574546813965, "learning_rate": 4.1282846676132804e-08, "loss": 3.8629, "step": 18245 }, { "epoch": 0.9818123116659492, "grad_norm": 3.443840503692627, "learning_rate": 4.1040429885561005e-08, "loss": 3.7182, "step": 18246 }, { "epoch": 0.9818661213947482, "grad_norm": 4.2109055519104, "learning_rate": 4.079872635492366e-08, "loss": 3.3828, "step": 18247 }, { "epoch": 0.9819199311235471, "grad_norm": 2.469731092453003, "learning_rate": 4.0557736091123566e-08, "loss": 3.6224, "step": 18248 }, { "epoch": 0.9819737408523461, "grad_norm": 3.1069977283477783, "learning_rate": 4.031745910105245e-08, "loss": 3.0412, "step": 18249 }, { "epoch": 0.9820275505811451, "grad_norm": 2.3147380352020264, "learning_rate": 4.007789539157425e-08, "loss": 3.5507, "step": 18250 }, { "epoch": 0.9820813603099441, "grad_norm": 1.9528957605361938, "learning_rate": 3.9839044969536276e-08, "loss": 4.2016, "step": 18251 }, { "epoch": 0.982135170038743, "grad_norm": 2.064997434616089, "learning_rate": 3.9600907841763627e-08, "loss": 4.2595, "step": 18252 }, { "epoch": 0.9821889797675419, "grad_norm": 3.4473679065704346, "learning_rate": 3.936348401505918e-08, "loss": 2.9062, "step": 18253 }, { "epoch": 0.9822427894963409, "grad_norm": 1.8863900899887085, "learning_rate": 3.9126773496211965e-08, "loss": 4.0379, "step": 18254 }, { "epoch": 0.9822965992251399, "grad_norm": 2.2885918617248535, "learning_rate": 3.889077629198601e-08, "loss": 4.3297, "step": 18255 }, { "epoch": 0.9823504089539389, "grad_norm": 3.2768406867980957, "learning_rate": 3.8655492409120364e-08, "loss": 3.1961, "step": 18256 }, { "epoch": 0.9824042186827379, "grad_norm": 2.2613654136657715, "learning_rate": 3.842092185434576e-08, "loss": 3.3432, "step": 18257 }, { "epoch": 0.9824580284115368, "grad_norm": 3.4630465507507324, "learning_rate": 3.8187064634362393e-08, "loss": 3.9175, "step": 18258 }, { "epoch": 0.9825118381403358, "grad_norm": 2.9758880138397217, "learning_rate": 3.7953920755851026e-08, "loss": 3.5592, "step": 18259 }, { "epoch": 0.9825656478691347, "grad_norm": 3.275771379470825, "learning_rate": 3.772149022547855e-08, "loss": 3.6829, "step": 18260 }, { "epoch": 0.9826194575979337, "grad_norm": 5.1576690673828125, "learning_rate": 3.7489773049884104e-08, "loss": 4.2476, "step": 18261 }, { "epoch": 0.9826732673267327, "grad_norm": 4.926238536834717, "learning_rate": 3.725876923569294e-08, "loss": 3.6953, "step": 18262 }, { "epoch": 0.9827270770555316, "grad_norm": 2.8068110942840576, "learning_rate": 3.7028478789499775e-08, "loss": 3.8245, "step": 18263 }, { "epoch": 0.9827808867843306, "grad_norm": 2.459162950515747, "learning_rate": 3.67989017178938e-08, "loss": 4.0302, "step": 18264 }, { "epoch": 0.9828346965131296, "grad_norm": 3.5497937202453613, "learning_rate": 3.6570038027430866e-08, "loss": 2.9719, "step": 18265 }, { "epoch": 0.9828885062419286, "grad_norm": 1.687328577041626, "learning_rate": 3.634188772465297e-08, "loss": 4.08, "step": 18266 }, { "epoch": 0.9829423159707275, "grad_norm": 4.407498359680176, "learning_rate": 3.6114450816079895e-08, "loss": 3.3797, "step": 18267 }, { "epoch": 0.9829961256995264, "grad_norm": 3.199627161026001, "learning_rate": 3.5887727308209216e-08, "loss": 3.5289, "step": 18268 }, { "epoch": 0.9830499354283254, "grad_norm": 1.7392243146896362, "learning_rate": 3.5661717207524645e-08, "loss": 4.4509, "step": 18269 }, { "epoch": 0.9831037451571244, "grad_norm": 2.366208553314209, "learning_rate": 3.5436420520479355e-08, "loss": 3.6397, "step": 18270 }, { "epoch": 0.9831575548859234, "grad_norm": 3.4725515842437744, "learning_rate": 3.52118372535154e-08, "loss": 3.5178, "step": 18271 }, { "epoch": 0.9832113646147224, "grad_norm": 4.088657855987549, "learning_rate": 3.498796741304988e-08, "loss": 2.7474, "step": 18272 }, { "epoch": 0.9832651743435213, "grad_norm": 2.766594409942627, "learning_rate": 3.476481100548046e-08, "loss": 3.6537, "step": 18273 }, { "epoch": 0.9833189840723203, "grad_norm": 3.9757652282714844, "learning_rate": 3.454236803718258e-08, "loss": 3.8103, "step": 18274 }, { "epoch": 0.9833727938011192, "grad_norm": 2.8741588592529297, "learning_rate": 3.432063851451506e-08, "loss": 3.4339, "step": 18275 }, { "epoch": 0.9834266035299182, "grad_norm": 3.614325523376465, "learning_rate": 3.4099622443814486e-08, "loss": 3.6711, "step": 18276 }, { "epoch": 0.9834804132587172, "grad_norm": 2.905724048614502, "learning_rate": 3.3879319831398024e-08, "loss": 3.7205, "step": 18277 }, { "epoch": 0.9835342229875161, "grad_norm": 1.9587723016738892, "learning_rate": 3.3659730683557876e-08, "loss": 3.4395, "step": 18278 }, { "epoch": 0.9835880327163151, "grad_norm": 2.2432339191436768, "learning_rate": 3.344085500656957e-08, "loss": 3.2961, "step": 18279 }, { "epoch": 0.9836418424451141, "grad_norm": 1.9937551021575928, "learning_rate": 3.322269280669199e-08, "loss": 3.4841, "step": 18280 }, { "epoch": 0.9836956521739131, "grad_norm": 2.29494047164917, "learning_rate": 3.300524409015626e-08, "loss": 3.9874, "step": 18281 }, { "epoch": 0.9837494619027121, "grad_norm": 2.5833961963653564, "learning_rate": 3.278850886317686e-08, "loss": 3.9912, "step": 18282 }, { "epoch": 0.9838032716315109, "grad_norm": 3.710858106613159, "learning_rate": 3.257248713194882e-08, "loss": 3.18, "step": 18283 }, { "epoch": 0.9838570813603099, "grad_norm": 2.6803910732269287, "learning_rate": 3.2357178902645e-08, "loss": 3.8283, "step": 18284 }, { "epoch": 0.9839108910891089, "grad_norm": 2.963101387023926, "learning_rate": 3.2142584181416026e-08, "loss": 3.2101, "step": 18285 }, { "epoch": 0.9839647008179079, "grad_norm": 2.3871994018554688, "learning_rate": 3.192870297439588e-08, "loss": 3.8177, "step": 18286 }, { "epoch": 0.9840185105467069, "grad_norm": 3.710745096206665, "learning_rate": 3.1715535287699106e-08, "loss": 3.7785, "step": 18287 }, { "epoch": 0.9840723202755058, "grad_norm": 2.4298999309539795, "learning_rate": 3.150308112741529e-08, "loss": 3.2072, "step": 18288 }, { "epoch": 0.9841261300043048, "grad_norm": 2.806389570236206, "learning_rate": 3.129134049961735e-08, "loss": 4.6903, "step": 18289 }, { "epoch": 0.9841799397331037, "grad_norm": 3.2094197273254395, "learning_rate": 3.1080313410353226e-08, "loss": 3.1505, "step": 18290 }, { "epoch": 0.9842337494619027, "grad_norm": 1.6990537643432617, "learning_rate": 3.08699998656542e-08, "loss": 4.4326, "step": 18291 }, { "epoch": 0.9842875591907017, "grad_norm": 3.315664529800415, "learning_rate": 3.0660399871534907e-08, "loss": 4.0523, "step": 18292 }, { "epoch": 0.9843413689195006, "grad_norm": 2.1878862380981445, "learning_rate": 3.045151343397945e-08, "loss": 3.5838, "step": 18293 }, { "epoch": 0.9843951786482996, "grad_norm": 4.226400852203369, "learning_rate": 3.024334055895806e-08, "loss": 2.6143, "step": 18294 }, { "epoch": 0.9844489883770986, "grad_norm": 3.8978207111358643, "learning_rate": 3.003588125242429e-08, "loss": 3.1075, "step": 18295 }, { "epoch": 0.9845027981058976, "grad_norm": 2.771270275115967, "learning_rate": 2.98291355203012e-08, "loss": 3.6498, "step": 18296 }, { "epoch": 0.9845566078346966, "grad_norm": 3.8967549800872803, "learning_rate": 2.9623103368500714e-08, "loss": 2.8304, "step": 18297 }, { "epoch": 0.9846104175634954, "grad_norm": 4.640801429748535, "learning_rate": 2.9417784802909796e-08, "loss": 3.3725, "step": 18298 }, { "epoch": 0.9846642272922944, "grad_norm": 2.6789748668670654, "learning_rate": 2.9213179829395977e-08, "loss": 3.7126, "step": 18299 }, { "epoch": 0.9847180370210934, "grad_norm": 2.433891773223877, "learning_rate": 2.9009288453804573e-08, "loss": 4.3231, "step": 18300 }, { "epoch": 0.9847718467498924, "grad_norm": 1.3238344192504883, "learning_rate": 2.880611068196426e-08, "loss": 4.3068, "step": 18301 }, { "epoch": 0.9848256564786914, "grad_norm": 2.147706985473633, "learning_rate": 2.8603646519681503e-08, "loss": 3.4537, "step": 18302 }, { "epoch": 0.9848794662074903, "grad_norm": 2.834498167037964, "learning_rate": 2.8401895972740566e-08, "loss": 4.125, "step": 18303 }, { "epoch": 0.9849332759362893, "grad_norm": 2.7281970977783203, "learning_rate": 2.820085904690628e-08, "loss": 3.7449, "step": 18304 }, { "epoch": 0.9849870856650883, "grad_norm": 2.986020565032959, "learning_rate": 2.8000535747926824e-08, "loss": 3.7446, "step": 18305 }, { "epoch": 0.9850408953938872, "grad_norm": 3.3114094734191895, "learning_rate": 2.7800926081525404e-08, "loss": 3.2229, "step": 18306 }, { "epoch": 0.9850947051226862, "grad_norm": 2.9299662113189697, "learning_rate": 2.7602030053405782e-08, "loss": 2.8793, "step": 18307 }, { "epoch": 0.9851485148514851, "grad_norm": 2.824291229248047, "learning_rate": 2.74038476692523e-08, "loss": 3.8455, "step": 18308 }, { "epoch": 0.9852023245802841, "grad_norm": 2.4226019382476807, "learning_rate": 2.7206378934729882e-08, "loss": 3.057, "step": 18309 }, { "epoch": 0.9852561343090831, "grad_norm": 4.03048849105835, "learning_rate": 2.700962385547845e-08, "loss": 3.8712, "step": 18310 }, { "epoch": 0.9853099440378821, "grad_norm": 2.800344705581665, "learning_rate": 2.681358243712129e-08, "loss": 3.1348, "step": 18311 }, { "epoch": 0.9853637537666811, "grad_norm": 3.5896215438842773, "learning_rate": 2.6618254685265022e-08, "loss": 3.4306, "step": 18312 }, { "epoch": 0.9854175634954799, "grad_norm": 3.610140085220337, "learning_rate": 2.6423640605485743e-08, "loss": 3.2134, "step": 18313 }, { "epoch": 0.9854713732242789, "grad_norm": 3.86946702003479, "learning_rate": 2.6229740203351227e-08, "loss": 3.5426, "step": 18314 }, { "epoch": 0.9855251829530779, "grad_norm": 5.676111698150635, "learning_rate": 2.603655348439593e-08, "loss": 3.9567, "step": 18315 }, { "epoch": 0.9855789926818769, "grad_norm": 2.1332969665527344, "learning_rate": 2.584408045414599e-08, "loss": 3.8732, "step": 18316 }, { "epoch": 0.9856328024106759, "grad_norm": 3.2784717082977295, "learning_rate": 2.5652321118097013e-08, "loss": 3.2574, "step": 18317 }, { "epoch": 0.9856866121394748, "grad_norm": 1.8728607892990112, "learning_rate": 2.5461275481733492e-08, "loss": 4.288, "step": 18318 }, { "epoch": 0.9857404218682738, "grad_norm": 4.352018356323242, "learning_rate": 2.527094355051496e-08, "loss": 3.0521, "step": 18319 }, { "epoch": 0.9857942315970728, "grad_norm": 1.3288017511367798, "learning_rate": 2.5081325329875948e-08, "loss": 4.5172, "step": 18320 }, { "epoch": 0.9858480413258717, "grad_norm": 3.2943828105926514, "learning_rate": 2.489242082523713e-08, "loss": 4.386, "step": 18321 }, { "epoch": 0.9859018510546707, "grad_norm": 2.9734082221984863, "learning_rate": 2.4704230041999733e-08, "loss": 3.7218, "step": 18322 }, { "epoch": 0.9859556607834696, "grad_norm": 2.726048707962036, "learning_rate": 2.4516752985540014e-08, "loss": 3.2562, "step": 18323 }, { "epoch": 0.9860094705122686, "grad_norm": 1.9619996547698975, "learning_rate": 2.4329989661214803e-08, "loss": 3.9112, "step": 18324 }, { "epoch": 0.9860632802410676, "grad_norm": 2.9064981937408447, "learning_rate": 2.4143940074361494e-08, "loss": 3.1273, "step": 18325 }, { "epoch": 0.9861170899698666, "grad_norm": 18.422222137451172, "learning_rate": 2.3958604230298053e-08, "loss": 3.5602, "step": 18326 }, { "epoch": 0.9861708996986656, "grad_norm": 2.2072789669036865, "learning_rate": 2.377398213432025e-08, "loss": 4.0382, "step": 18327 }, { "epoch": 0.9862247094274645, "grad_norm": 3.8944876194000244, "learning_rate": 2.359007379170164e-08, "loss": 3.9743, "step": 18328 }, { "epoch": 0.9862785191562634, "grad_norm": 5.224994659423828, "learning_rate": 2.3406879207701905e-08, "loss": 3.3423, "step": 18329 }, { "epoch": 0.9863323288850624, "grad_norm": 4.532790660858154, "learning_rate": 2.3224398387555747e-08, "loss": 3.6968, "step": 18330 }, { "epoch": 0.9863861386138614, "grad_norm": 2.806821823120117, "learning_rate": 2.3042631336472888e-08, "loss": 3.6869, "step": 18331 }, { "epoch": 0.9864399483426604, "grad_norm": 3.673759937286377, "learning_rate": 2.286157805965472e-08, "loss": 3.0995, "step": 18332 }, { "epoch": 0.9864937580714593, "grad_norm": 3.918381452560425, "learning_rate": 2.2681238562269337e-08, "loss": 4.065, "step": 18333 }, { "epoch": 0.9865475678002583, "grad_norm": 3.5410025119781494, "learning_rate": 2.2501612849476496e-08, "loss": 3.3662, "step": 18334 }, { "epoch": 0.9866013775290573, "grad_norm": 2.4310028553009033, "learning_rate": 2.2322700926402652e-08, "loss": 4.1544, "step": 18335 }, { "epoch": 0.9866551872578562, "grad_norm": 3.4629969596862793, "learning_rate": 2.2144502798165933e-08, "loss": 3.6964, "step": 18336 }, { "epoch": 0.9867089969866552, "grad_norm": 2.190382480621338, "learning_rate": 2.1967018469856716e-08, "loss": 3.7988, "step": 18337 }, { "epoch": 0.9867628067154541, "grad_norm": 4.412228584289551, "learning_rate": 2.179024794654594e-08, "loss": 2.9948, "step": 18338 }, { "epoch": 0.9868166164442531, "grad_norm": 6.040307998657227, "learning_rate": 2.1614191233287894e-08, "loss": 3.3779, "step": 18339 }, { "epoch": 0.9868704261730521, "grad_norm": 3.226639986038208, "learning_rate": 2.1438848335111895e-08, "loss": 4.1375, "step": 18340 }, { "epoch": 0.9869242359018511, "grad_norm": 2.940192699432373, "learning_rate": 2.1264219257027818e-08, "loss": 3.3597, "step": 18341 }, { "epoch": 0.9869780456306501, "grad_norm": 3.0550262928009033, "learning_rate": 2.1090304004028892e-08, "loss": 3.0027, "step": 18342 }, { "epoch": 0.987031855359449, "grad_norm": 2.097517251968384, "learning_rate": 2.091710258108337e-08, "loss": 3.8704, "step": 18343 }, { "epoch": 0.9870856650882479, "grad_norm": 2.6176955699920654, "learning_rate": 2.0744614993140067e-08, "loss": 3.9924, "step": 18344 }, { "epoch": 0.9871394748170469, "grad_norm": 2.6261191368103027, "learning_rate": 2.0572841245131147e-08, "loss": 3.5729, "step": 18345 }, { "epoch": 0.9871932845458459, "grad_norm": 5.890965461730957, "learning_rate": 2.04017813419638e-08, "loss": 2.6493, "step": 18346 }, { "epoch": 0.9872470942746449, "grad_norm": 2.7122018337249756, "learning_rate": 2.0231435288523004e-08, "loss": 4.2496, "step": 18347 }, { "epoch": 0.9873009040034438, "grad_norm": 2.0828781127929688, "learning_rate": 2.006180308968264e-08, "loss": 3.7184, "step": 18348 }, { "epoch": 0.9873547137322428, "grad_norm": 2.292067766189575, "learning_rate": 1.9892884750288832e-08, "loss": 3.6294, "step": 18349 }, { "epoch": 0.9874085234610418, "grad_norm": 3.802145004272461, "learning_rate": 1.9724680275165496e-08, "loss": 3.6892, "step": 18350 }, { "epoch": 0.9874623331898407, "grad_norm": 3.6642022132873535, "learning_rate": 1.9557189669122678e-08, "loss": 3.5747, "step": 18351 }, { "epoch": 0.9875161429186397, "grad_norm": 3.8753457069396973, "learning_rate": 1.939041293694821e-08, "loss": 3.5864, "step": 18352 }, { "epoch": 0.9875699526474386, "grad_norm": 2.2847840785980225, "learning_rate": 1.9224350083402176e-08, "loss": 3.6259, "step": 18353 }, { "epoch": 0.9876237623762376, "grad_norm": 2.9539477825164795, "learning_rate": 1.905900111323633e-08, "loss": 3.9596, "step": 18354 }, { "epoch": 0.9876775721050366, "grad_norm": 3.96108341217041, "learning_rate": 1.8894366031171896e-08, "loss": 4.1792, "step": 18355 }, { "epoch": 0.9877313818338356, "grad_norm": 3.0869035720825195, "learning_rate": 1.873044484191622e-08, "loss": 3.77, "step": 18356 }, { "epoch": 0.9877851915626346, "grad_norm": 1.5565940141677856, "learning_rate": 1.856723755015166e-08, "loss": 4.3131, "step": 18357 }, { "epoch": 0.9878390012914335, "grad_norm": 3.881072759628296, "learning_rate": 1.840474416054394e-08, "loss": 3.9537, "step": 18358 }, { "epoch": 0.9878928110202324, "grad_norm": 1.9525701999664307, "learning_rate": 1.8242964677733787e-08, "loss": 3.2798, "step": 18359 }, { "epoch": 0.9879466207490314, "grad_norm": 3.20855975151062, "learning_rate": 1.808189910635083e-08, "loss": 3.7083, "step": 18360 }, { "epoch": 0.9880004304778304, "grad_norm": 2.1088898181915283, "learning_rate": 1.7921547450991395e-08, "loss": 3.6866, "step": 18361 }, { "epoch": 0.9880542402066294, "grad_norm": 2.1838135719299316, "learning_rate": 1.77619097162407e-08, "loss": 3.8566, "step": 18362 }, { "epoch": 0.9881080499354283, "grad_norm": 2.4139277935028076, "learning_rate": 1.7602985906658985e-08, "loss": 3.123, "step": 18363 }, { "epoch": 0.9881618596642273, "grad_norm": 1.7126623392105103, "learning_rate": 1.7444776026789845e-08, "loss": 4.2005, "step": 18364 }, { "epoch": 0.9882156693930263, "grad_norm": 1.6693370342254639, "learning_rate": 1.7287280081154655e-08, "loss": 3.674, "step": 18365 }, { "epoch": 0.9882694791218253, "grad_norm": 3.1159985065460205, "learning_rate": 1.7130498074252597e-08, "loss": 3.8519, "step": 18366 }, { "epoch": 0.9883232888506241, "grad_norm": 3.2643606662750244, "learning_rate": 1.6974430010566202e-08, "loss": 2.7256, "step": 18367 }, { "epoch": 0.9883770985794231, "grad_norm": 1.5454834699630737, "learning_rate": 1.6819075894553005e-08, "loss": 4.3302, "step": 18368 }, { "epoch": 0.9884309083082221, "grad_norm": 3.5876822471618652, "learning_rate": 1.6664435730653905e-08, "loss": 3.2244, "step": 18369 }, { "epoch": 0.9884847180370211, "grad_norm": 2.930250406265259, "learning_rate": 1.6510509523287588e-08, "loss": 3.7171, "step": 18370 }, { "epoch": 0.9885385277658201, "grad_norm": 5.977454662322998, "learning_rate": 1.6357297276853312e-08, "loss": 3.9365, "step": 18371 }, { "epoch": 0.9885923374946191, "grad_norm": 5.476215839385986, "learning_rate": 1.6204798995730908e-08, "loss": 3.0429, "step": 18372 }, { "epoch": 0.988646147223418, "grad_norm": 3.367771625518799, "learning_rate": 1.6053014684275225e-08, "loss": 3.8763, "step": 18373 }, { "epoch": 0.9886999569522169, "grad_norm": 3.6931257247924805, "learning_rate": 1.590194434682446e-08, "loss": 3.999, "step": 18374 }, { "epoch": 0.9887537666810159, "grad_norm": 2.9793059825897217, "learning_rate": 1.5751587987700157e-08, "loss": 3.8761, "step": 18375 }, { "epoch": 0.9888075764098149, "grad_norm": 1.9054170846939087, "learning_rate": 1.5601945611193324e-08, "loss": 3.8816, "step": 18376 }, { "epoch": 0.9888613861386139, "grad_norm": 3.80035400390625, "learning_rate": 1.5453017221583877e-08, "loss": 4.1172, "step": 18377 }, { "epoch": 0.9889151958674128, "grad_norm": 3.8415493965148926, "learning_rate": 1.5304802823123963e-08, "loss": 3.7977, "step": 18378 }, { "epoch": 0.9889690055962118, "grad_norm": 1.8009830713272095, "learning_rate": 1.5157302420054642e-08, "loss": 4.2167, "step": 18379 }, { "epoch": 0.9890228153250108, "grad_norm": 2.2302138805389404, "learning_rate": 1.501051601658643e-08, "loss": 3.9392, "step": 18380 }, { "epoch": 0.9890766250538098, "grad_norm": 2.8940179347991943, "learning_rate": 1.4864443616918744e-08, "loss": 3.8944, "step": 18381 }, { "epoch": 0.9891304347826086, "grad_norm": 3.8320019245147705, "learning_rate": 1.4719085225220475e-08, "loss": 3.6713, "step": 18382 }, { "epoch": 0.9891842445114076, "grad_norm": 3.0645339488983154, "learning_rate": 1.4574440845649407e-08, "loss": 4.1258, "step": 18383 }, { "epoch": 0.9892380542402066, "grad_norm": 3.493326187133789, "learning_rate": 1.4430510482338344e-08, "loss": 4.2966, "step": 18384 }, { "epoch": 0.9892918639690056, "grad_norm": 2.273737907409668, "learning_rate": 1.4287294139397888e-08, "loss": 3.5762, "step": 18385 }, { "epoch": 0.9893456736978046, "grad_norm": 1.4771146774291992, "learning_rate": 1.4144791820924763e-08, "loss": 4.0989, "step": 18386 }, { "epoch": 0.9893994834266036, "grad_norm": 2.068272590637207, "learning_rate": 1.4003003530987935e-08, "loss": 3.9492, "step": 18387 }, { "epoch": 0.9894532931554025, "grad_norm": 2.9964261054992676, "learning_rate": 1.3861929273642493e-08, "loss": 3.737, "step": 18388 }, { "epoch": 0.9895071028842015, "grad_norm": 1.5094670057296753, "learning_rate": 1.3721569052918547e-08, "loss": 4.0228, "step": 18389 }, { "epoch": 0.9895609126130004, "grad_norm": 2.564523935317993, "learning_rate": 1.358192287282678e-08, "loss": 4.1394, "step": 18390 }, { "epoch": 0.9896147223417994, "grad_norm": 1.7087606191635132, "learning_rate": 1.3442990737355665e-08, "loss": 4.3014, "step": 18391 }, { "epoch": 0.9896685320705984, "grad_norm": 2.628225564956665, "learning_rate": 1.3304772650479801e-08, "loss": 3.3186, "step": 18392 }, { "epoch": 0.9897223417993973, "grad_norm": 2.8605480194091797, "learning_rate": 1.316726861614881e-08, "loss": 3.5839, "step": 18393 }, { "epoch": 0.9897761515281963, "grad_norm": 2.695133924484253, "learning_rate": 1.3030478638287324e-08, "loss": 3.3031, "step": 18394 }, { "epoch": 0.9898299612569953, "grad_norm": 1.5576069355010986, "learning_rate": 1.2894402720808885e-08, "loss": 3.5999, "step": 18395 }, { "epoch": 0.9898837709857943, "grad_norm": 3.7014076709747314, "learning_rate": 1.2759040867602045e-08, "loss": 3.7112, "step": 18396 }, { "epoch": 0.9899375807145931, "grad_norm": 2.0989603996276855, "learning_rate": 1.2624393082533159e-08, "loss": 3.7727, "step": 18397 }, { "epoch": 0.9899913904433921, "grad_norm": 2.3486387729644775, "learning_rate": 1.2490459369451923e-08, "loss": 3.6908, "step": 18398 }, { "epoch": 0.9900452001721911, "grad_norm": 4.068663120269775, "learning_rate": 1.2357239732183056e-08, "loss": 3.2641, "step": 18399 }, { "epoch": 0.9900990099009901, "grad_norm": 2.7001328468322754, "learning_rate": 1.22247341745374e-08, "loss": 3.867, "step": 18400 }, { "epoch": 0.9901528196297891, "grad_norm": 2.7716891765594482, "learning_rate": 1.2092942700298038e-08, "loss": 4.4372, "step": 18401 }, { "epoch": 0.990206629358588, "grad_norm": 3.519587755203247, "learning_rate": 1.1961865313234177e-08, "loss": 3.9679, "step": 18402 }, { "epoch": 0.990260439087387, "grad_norm": 3.375354290008545, "learning_rate": 1.1831502017090046e-08, "loss": 3.6962, "step": 18403 }, { "epoch": 0.990314248816186, "grad_norm": 2.306715488433838, "learning_rate": 1.1701852815590441e-08, "loss": 3.9567, "step": 18404 }, { "epoch": 0.9903680585449849, "grad_norm": 2.3438146114349365, "learning_rate": 1.1572917712440734e-08, "loss": 3.3397, "step": 18405 }, { "epoch": 0.9904218682737839, "grad_norm": 3.407588481903076, "learning_rate": 1.1444696711326864e-08, "loss": 2.8511, "step": 18406 }, { "epoch": 0.9904756780025828, "grad_norm": 2.0972323417663574, "learning_rate": 1.1317189815912565e-08, "loss": 4.309, "step": 18407 }, { "epoch": 0.9905294877313818, "grad_norm": 3.357370376586914, "learning_rate": 1.1190397029842147e-08, "loss": 3.9975, "step": 18408 }, { "epoch": 0.9905832974601808, "grad_norm": 2.94114351272583, "learning_rate": 1.1064318356734938e-08, "loss": 4.3411, "step": 18409 }, { "epoch": 0.9906371071889798, "grad_norm": 2.772258758544922, "learning_rate": 1.0938953800201934e-08, "loss": 3.0122, "step": 18410 }, { "epoch": 0.9906909169177788, "grad_norm": 3.1307532787323, "learning_rate": 1.0814303363818057e-08, "loss": 3.2006, "step": 18411 }, { "epoch": 0.9907447266465778, "grad_norm": 1.847332239151001, "learning_rate": 1.0690367051147121e-08, "loss": 3.8625, "step": 18412 }, { "epoch": 0.9907985363753766, "grad_norm": 2.4454092979431152, "learning_rate": 1.0567144865733513e-08, "loss": 3.9946, "step": 18413 }, { "epoch": 0.9908523461041756, "grad_norm": 2.011245012283325, "learning_rate": 1.0444636811099417e-08, "loss": 3.853, "step": 18414 }, { "epoch": 0.9909061558329746, "grad_norm": 2.4789392948150635, "learning_rate": 1.032284289073926e-08, "loss": 4.2563, "step": 18415 }, { "epoch": 0.9909599655617736, "grad_norm": 5.3263468742370605, "learning_rate": 1.0201763108141915e-08, "loss": 3.1179, "step": 18416 }, { "epoch": 0.9910137752905726, "grad_norm": 3.9810962677001953, "learning_rate": 1.008139746676018e-08, "loss": 2.4292, "step": 18417 }, { "epoch": 0.9910675850193715, "grad_norm": 2.16343092918396, "learning_rate": 9.961745970038516e-09, "loss": 3.7352, "step": 18418 }, { "epoch": 0.9911213947481705, "grad_norm": 2.679295539855957, "learning_rate": 9.842808621396416e-09, "loss": 3.4294, "step": 18419 }, { "epoch": 0.9911752044769694, "grad_norm": 4.468550205230713, "learning_rate": 9.724585424228383e-09, "loss": 3.6648, "step": 18420 }, { "epoch": 0.9912290142057684, "grad_norm": 3.4529025554656982, "learning_rate": 9.607076381917823e-09, "loss": 3.4911, "step": 18421 }, { "epoch": 0.9912828239345673, "grad_norm": 2.430100917816162, "learning_rate": 9.490281497820385e-09, "loss": 3.8527, "step": 18422 }, { "epoch": 0.9913366336633663, "grad_norm": 2.1961827278137207, "learning_rate": 9.374200775275066e-09, "loss": 4.2781, "step": 18423 }, { "epoch": 0.9913904433921653, "grad_norm": 3.1672589778900146, "learning_rate": 9.258834217595879e-09, "loss": 3.6502, "step": 18424 }, { "epoch": 0.9914442531209643, "grad_norm": 2.605588674545288, "learning_rate": 9.144181828082965e-09, "loss": 3.7032, "step": 18425 }, { "epoch": 0.9914980628497633, "grad_norm": 1.962275505065918, "learning_rate": 9.030243610014256e-09, "loss": 4.0189, "step": 18426 }, { "epoch": 0.9915518725785623, "grad_norm": 1.5384182929992676, "learning_rate": 8.917019566639928e-09, "loss": 3.6826, "step": 18427 }, { "epoch": 0.9916056823073611, "grad_norm": 2.368276834487915, "learning_rate": 8.804509701199059e-09, "loss": 2.9936, "step": 18428 }, { "epoch": 0.9916594920361601, "grad_norm": 2.121147871017456, "learning_rate": 8.692714016908522e-09, "loss": 4.3647, "step": 18429 }, { "epoch": 0.9917133017649591, "grad_norm": 2.8046224117279053, "learning_rate": 8.581632516962979e-09, "loss": 3.838, "step": 18430 }, { "epoch": 0.9917671114937581, "grad_norm": 3.283864974975586, "learning_rate": 8.47126520453212e-09, "loss": 3.6463, "step": 18431 }, { "epoch": 0.991820921222557, "grad_norm": 2.3376290798187256, "learning_rate": 8.361612082774527e-09, "loss": 2.7628, "step": 18432 }, { "epoch": 0.991874730951356, "grad_norm": 3.9714531898498535, "learning_rate": 8.252673154823808e-09, "loss": 3.2569, "step": 18433 }, { "epoch": 0.991928540680155, "grad_norm": 3.1395013332366943, "learning_rate": 8.144448423788587e-09, "loss": 3.8126, "step": 18434 }, { "epoch": 0.9919823504089539, "grad_norm": 3.7557525634765625, "learning_rate": 8.036937892766383e-09, "loss": 3.3308, "step": 18435 }, { "epoch": 0.9920361601377529, "grad_norm": 1.5413161516189575, "learning_rate": 7.93014156482974e-09, "loss": 4.1471, "step": 18436 }, { "epoch": 0.9920899698665518, "grad_norm": 2.1883602142333984, "learning_rate": 7.824059443028998e-09, "loss": 3.2693, "step": 18437 }, { "epoch": 0.9921437795953508, "grad_norm": 2.053330898284912, "learning_rate": 7.718691530392285e-09, "loss": 3.7285, "step": 18438 }, { "epoch": 0.9921975893241498, "grad_norm": 3.8152637481689453, "learning_rate": 7.614037829936638e-09, "loss": 3.4041, "step": 18439 }, { "epoch": 0.9922513990529488, "grad_norm": 2.3844830989837646, "learning_rate": 7.510098344648553e-09, "loss": 3.0116, "step": 18440 }, { "epoch": 0.9923052087817478, "grad_norm": 4.0434250831604, "learning_rate": 7.406873077500653e-09, "loss": 3.8475, "step": 18441 }, { "epoch": 0.9923590185105468, "grad_norm": 2.2520651817321777, "learning_rate": 7.304362031443357e-09, "loss": 4.3213, "step": 18442 }, { "epoch": 0.9924128282393456, "grad_norm": 3.3893446922302246, "learning_rate": 7.202565209402101e-09, "loss": 2.9506, "step": 18443 }, { "epoch": 0.9924666379681446, "grad_norm": 2.716413736343384, "learning_rate": 7.101482614291222e-09, "loss": 4.0967, "step": 18444 }, { "epoch": 0.9925204476969436, "grad_norm": 2.5656304359436035, "learning_rate": 7.0011142489972984e-09, "loss": 3.697, "step": 18445 }, { "epoch": 0.9925742574257426, "grad_norm": 2.6313560009002686, "learning_rate": 6.901460116387481e-09, "loss": 3.6369, "step": 18446 }, { "epoch": 0.9926280671545415, "grad_norm": 2.348994016647339, "learning_rate": 6.802520219309494e-09, "loss": 4.3169, "step": 18447 }, { "epoch": 0.9926818768833405, "grad_norm": 3.491093158721924, "learning_rate": 6.704294560591629e-09, "loss": 3.409, "step": 18448 }, { "epoch": 0.9927356866121395, "grad_norm": 3.2585701942443848, "learning_rate": 6.60678314304275e-09, "loss": 3.4169, "step": 18449 }, { "epoch": 0.9927894963409385, "grad_norm": 2.280266284942627, "learning_rate": 6.509985969446741e-09, "loss": 3.4654, "step": 18450 }, { "epoch": 0.9928433060697374, "grad_norm": 2.622296094894409, "learning_rate": 6.413903042568059e-09, "loss": 3.1615, "step": 18451 }, { "epoch": 0.9928971157985363, "grad_norm": 2.2761993408203125, "learning_rate": 6.318534365160056e-09, "loss": 4.2082, "step": 18452 }, { "epoch": 0.9929509255273353, "grad_norm": 3.360898733139038, "learning_rate": 6.223879939940003e-09, "loss": 3.3674, "step": 18453 }, { "epoch": 0.9930047352561343, "grad_norm": 3.8271968364715576, "learning_rate": 6.129939769616844e-09, "loss": 3.0329, "step": 18454 }, { "epoch": 0.9930585449849333, "grad_norm": 1.990582823753357, "learning_rate": 6.036713856874543e-09, "loss": 4.3434, "step": 18455 }, { "epoch": 0.9931123547137323, "grad_norm": 3.147526264190674, "learning_rate": 5.944202204377636e-09, "loss": 3.4382, "step": 18456 }, { "epoch": 0.9931661644425313, "grad_norm": 2.126753807067871, "learning_rate": 5.852404814768453e-09, "loss": 3.99, "step": 18457 }, { "epoch": 0.9932199741713301, "grad_norm": 2.922856092453003, "learning_rate": 5.761321690669897e-09, "loss": 3.3889, "step": 18458 }, { "epoch": 0.9932737839001291, "grad_norm": 1.431128740310669, "learning_rate": 5.670952834688214e-09, "loss": 4.4616, "step": 18459 }, { "epoch": 0.9933275936289281, "grad_norm": 2.3843257427215576, "learning_rate": 5.581298249404676e-09, "loss": 3.8202, "step": 18460 }, { "epoch": 0.9933814033577271, "grad_norm": 2.7288153171539307, "learning_rate": 5.492357937378345e-09, "loss": 3.9995, "step": 18461 }, { "epoch": 0.993435213086526, "grad_norm": 3.6505789756774902, "learning_rate": 5.404131901154408e-09, "loss": 2.7306, "step": 18462 }, { "epoch": 0.993489022815325, "grad_norm": 3.244433879852295, "learning_rate": 5.31662014325307e-09, "loss": 3.3366, "step": 18463 }, { "epoch": 0.993542832544124, "grad_norm": 1.9438190460205078, "learning_rate": 5.229822666172335e-09, "loss": 3.8352, "step": 18464 }, { "epoch": 0.993596642272923, "grad_norm": 1.9346884489059448, "learning_rate": 5.143739472399101e-09, "loss": 4.0198, "step": 18465 }, { "epoch": 0.9936504520017219, "grad_norm": 3.4845163822174072, "learning_rate": 5.058370564386961e-09, "loss": 4.1211, "step": 18466 }, { "epoch": 0.9937042617305208, "grad_norm": 3.0233330726623535, "learning_rate": 4.973715944578405e-09, "loss": 3.7615, "step": 18467 }, { "epoch": 0.9937580714593198, "grad_norm": 3.897331714630127, "learning_rate": 4.889775615393721e-09, "loss": 3.1134, "step": 18468 }, { "epoch": 0.9938118811881188, "grad_norm": 2.222169876098633, "learning_rate": 4.806549579228214e-09, "loss": 3.4822, "step": 18469 }, { "epoch": 0.9938656909169178, "grad_norm": 1.8221086263656616, "learning_rate": 4.724037838463313e-09, "loss": 3.6659, "step": 18470 }, { "epoch": 0.9939195006457168, "grad_norm": 3.3279149532318115, "learning_rate": 4.6422403954554664e-09, "loss": 2.8906, "step": 18471 }, { "epoch": 0.9939733103745158, "grad_norm": 2.1248745918273926, "learning_rate": 4.561157252544468e-09, "loss": 4.4173, "step": 18472 }, { "epoch": 0.9940271201033147, "grad_norm": 3.866806745529175, "learning_rate": 4.4807884120423585e-09, "loss": 2.9972, "step": 18473 }, { "epoch": 0.9940809298321136, "grad_norm": 3.410717010498047, "learning_rate": 4.4011338762528495e-09, "loss": 3.451, "step": 18474 }, { "epoch": 0.9941347395609126, "grad_norm": 3.4389991760253906, "learning_rate": 4.322193647446349e-09, "loss": 3.4358, "step": 18475 }, { "epoch": 0.9941885492897116, "grad_norm": 1.7823336124420166, "learning_rate": 4.2439677278821585e-09, "loss": 3.3665, "step": 18476 }, { "epoch": 0.9942423590185105, "grad_norm": 1.9956752061843872, "learning_rate": 4.166456119794604e-09, "loss": 3.8684, "step": 18477 }, { "epoch": 0.9942961687473095, "grad_norm": 2.661310911178589, "learning_rate": 4.089658825398579e-09, "loss": 3.8942, "step": 18478 }, { "epoch": 0.9943499784761085, "grad_norm": 2.038975715637207, "learning_rate": 4.01357584688955e-09, "loss": 3.8107, "step": 18479 }, { "epoch": 0.9944037882049075, "grad_norm": 1.931241750717163, "learning_rate": 3.938207186440779e-09, "loss": 4.2506, "step": 18480 }, { "epoch": 0.9944575979337064, "grad_norm": 3.8738200664520264, "learning_rate": 3.863552846208873e-09, "loss": 4.1105, "step": 18481 }, { "epoch": 0.9945114076625053, "grad_norm": 2.880983352661133, "learning_rate": 3.789612828322686e-09, "loss": 3.559, "step": 18482 }, { "epoch": 0.9945652173913043, "grad_norm": 3.0417139530181885, "learning_rate": 3.716387134897192e-09, "loss": 3.8008, "step": 18483 }, { "epoch": 0.9946190271201033, "grad_norm": 3.0787389278411865, "learning_rate": 3.643875768025162e-09, "loss": 3.7163, "step": 18484 }, { "epoch": 0.9946728368489023, "grad_norm": 2.5802929401397705, "learning_rate": 3.5720787297799376e-09, "loss": 4.2376, "step": 18485 }, { "epoch": 0.9947266465777013, "grad_norm": 2.1298844814300537, "learning_rate": 3.500996022209879e-09, "loss": 3.7981, "step": 18486 }, { "epoch": 0.9947804563065002, "grad_norm": 2.5854146480560303, "learning_rate": 3.4306276473494712e-09, "loss": 3.655, "step": 18487 }, { "epoch": 0.9948342660352992, "grad_norm": 4.18443489074707, "learning_rate": 3.360973607210993e-09, "loss": 3.6803, "step": 18488 }, { "epoch": 0.9948880757640981, "grad_norm": 2.8728699684143066, "learning_rate": 3.292033903781744e-09, "loss": 4.4977, "step": 18489 }, { "epoch": 0.9949418854928971, "grad_norm": 3.3272478580474854, "learning_rate": 3.223808539032369e-09, "loss": 3.5597, "step": 18490 }, { "epoch": 0.9949956952216961, "grad_norm": 3.0355939865112305, "learning_rate": 3.1562975149140863e-09, "loss": 2.8894, "step": 18491 }, { "epoch": 0.995049504950495, "grad_norm": 1.3446848392486572, "learning_rate": 3.0895008333531316e-09, "loss": 4.397, "step": 18492 }, { "epoch": 0.995103314679294, "grad_norm": 2.1960105895996094, "learning_rate": 3.023418496261865e-09, "loss": 3.5792, "step": 18493 }, { "epoch": 0.995157124408093, "grad_norm": 2.211515426635742, "learning_rate": 2.9580505055276653e-09, "loss": 3.6991, "step": 18494 }, { "epoch": 0.995210934136892, "grad_norm": 3.472890615463257, "learning_rate": 2.8933968630184826e-09, "loss": 3.4005, "step": 18495 }, { "epoch": 0.995264743865691, "grad_norm": 4.032965183258057, "learning_rate": 2.829457570580063e-09, "loss": 3.2078, "step": 18496 }, { "epoch": 0.9953185535944898, "grad_norm": 4.548664569854736, "learning_rate": 2.7662326300442742e-09, "loss": 3.0084, "step": 18497 }, { "epoch": 0.9953723633232888, "grad_norm": 2.4728622436523438, "learning_rate": 2.7037220432124533e-09, "loss": 3.6466, "step": 18498 }, { "epoch": 0.9954261730520878, "grad_norm": 2.458226203918457, "learning_rate": 2.6419258118748346e-09, "loss": 3.847, "step": 18499 }, { "epoch": 0.9954799827808868, "grad_norm": 1.524813175201416, "learning_rate": 2.5808439377938974e-09, "loss": 3.6296, "step": 18500 }, { "epoch": 0.9955337925096858, "grad_norm": 3.315277099609375, "learning_rate": 2.520476422718243e-09, "loss": 3.7375, "step": 18501 }, { "epoch": 0.9955876022384847, "grad_norm": 1.7579160928726196, "learning_rate": 2.460823268371493e-09, "loss": 4.0418, "step": 18502 }, { "epoch": 0.9956414119672837, "grad_norm": 4.470170021057129, "learning_rate": 2.401884476460614e-09, "loss": 3.973, "step": 18503 }, { "epoch": 0.9956952216960826, "grad_norm": 1.9081225395202637, "learning_rate": 2.3436600486675954e-09, "loss": 4.2224, "step": 18504 }, { "epoch": 0.9957490314248816, "grad_norm": 3.1725997924804688, "learning_rate": 2.286149986654995e-09, "loss": 3.6012, "step": 18505 }, { "epoch": 0.9958028411536806, "grad_norm": 2.9718711376190186, "learning_rate": 2.229354292071495e-09, "loss": 3.585, "step": 18506 }, { "epoch": 0.9958566508824795, "grad_norm": 3.6616225242614746, "learning_rate": 2.173272966535245e-09, "loss": 3.7132, "step": 18507 }, { "epoch": 0.9959104606112785, "grad_norm": 2.9937705993652344, "learning_rate": 2.117906011650517e-09, "loss": 4.1978, "step": 18508 }, { "epoch": 0.9959642703400775, "grad_norm": 3.935248613357544, "learning_rate": 2.0632534289993787e-09, "loss": 2.5783, "step": 18509 }, { "epoch": 0.9960180800688765, "grad_norm": 3.3993313312530518, "learning_rate": 2.0093152201444696e-09, "loss": 3.1776, "step": 18510 }, { "epoch": 0.9960718897976755, "grad_norm": 2.7351503372192383, "learning_rate": 1.956091386626224e-09, "loss": 3.8923, "step": 18511 }, { "epoch": 0.9961256995264743, "grad_norm": 5.68120002746582, "learning_rate": 1.903581929968423e-09, "loss": 3.2194, "step": 18512 }, { "epoch": 0.9961795092552733, "grad_norm": 2.4144437313079834, "learning_rate": 1.8517868516670923e-09, "loss": 4.2454, "step": 18513 }, { "epoch": 0.9962333189840723, "grad_norm": 2.7762691974639893, "learning_rate": 1.8007061532043789e-09, "loss": 3.4945, "step": 18514 }, { "epoch": 0.9962871287128713, "grad_norm": 2.397820472717285, "learning_rate": 1.7503398360402267e-09, "loss": 3.531, "step": 18515 }, { "epoch": 0.9963409384416703, "grad_norm": 3.6274642944335938, "learning_rate": 1.70068790161515e-09, "loss": 2.7652, "step": 18516 }, { "epoch": 0.9963947481704692, "grad_norm": 2.8045589923858643, "learning_rate": 1.6517503513446831e-09, "loss": 4.46, "step": 18517 }, { "epoch": 0.9964485578992682, "grad_norm": 2.692413091659546, "learning_rate": 1.6035271866304825e-09, "loss": 4.3446, "step": 18518 }, { "epoch": 0.9965023676280672, "grad_norm": 2.195692300796509, "learning_rate": 1.5560184088520002e-09, "loss": 3.981, "step": 18519 }, { "epoch": 0.9965561773568661, "grad_norm": 3.93803071975708, "learning_rate": 1.509224019360933e-09, "loss": 2.9079, "step": 18520 }, { "epoch": 0.9966099870856651, "grad_norm": 2.8114993572235107, "learning_rate": 1.4631440195006508e-09, "loss": 3.1669, "step": 18521 }, { "epoch": 0.996663796814464, "grad_norm": 2.2733843326568604, "learning_rate": 1.417778410583992e-09, "loss": 3.6145, "step": 18522 }, { "epoch": 0.996717606543263, "grad_norm": 3.1295812129974365, "learning_rate": 1.3731271939099178e-09, "loss": 3.4453, "step": 18523 }, { "epoch": 0.996771416272062, "grad_norm": 3.178436040878296, "learning_rate": 1.3291903707551845e-09, "loss": 4.1619, "step": 18524 }, { "epoch": 0.996825226000861, "grad_norm": 3.748464822769165, "learning_rate": 1.2859679423715688e-09, "loss": 2.5962, "step": 18525 }, { "epoch": 0.99687903572966, "grad_norm": 3.5085601806640625, "learning_rate": 1.2434599099941936e-09, "loss": 3.8174, "step": 18526 }, { "epoch": 0.9969328454584588, "grad_norm": 1.7291595935821533, "learning_rate": 1.2016662748443042e-09, "loss": 4.5176, "step": 18527 }, { "epoch": 0.9969866551872578, "grad_norm": 2.3502252101898193, "learning_rate": 1.1605870381098394e-09, "loss": 4.0867, "step": 18528 }, { "epoch": 0.9970404649160568, "grad_norm": 2.631885051727295, "learning_rate": 1.1202222009676354e-09, "loss": 3.4033, "step": 18529 }, { "epoch": 0.9970942746448558, "grad_norm": 1.4687353372573853, "learning_rate": 1.080571764569549e-09, "loss": 4.0645, "step": 18530 }, { "epoch": 0.9971480843736548, "grad_norm": 2.37113094329834, "learning_rate": 1.0416357300480072e-09, "loss": 3.9205, "step": 18531 }, { "epoch": 0.9972018941024537, "grad_norm": 3.295262575149536, "learning_rate": 1.0034140985187844e-09, "loss": 3.4985, "step": 18532 }, { "epoch": 0.9972557038312527, "grad_norm": 3.1645028591156006, "learning_rate": 9.65906871072675e-10, "loss": 3.68, "step": 18533 }, { "epoch": 0.9973095135600517, "grad_norm": 3.5355825424194336, "learning_rate": 9.291140487810434e-10, "loss": 3.5572, "step": 18534 }, { "epoch": 0.9973633232888506, "grad_norm": 2.843689441680908, "learning_rate": 8.930356326986022e-10, "loss": 3.7626, "step": 18535 }, { "epoch": 0.9974171330176496, "grad_norm": 2.3322038650512695, "learning_rate": 8.57671623849532e-10, "loss": 4.1259, "step": 18536 }, { "epoch": 0.9974709427464485, "grad_norm": 1.8111257553100586, "learning_rate": 8.230220232496866e-10, "loss": 4.1582, "step": 18537 }, { "epoch": 0.9975247524752475, "grad_norm": 4.09287166595459, "learning_rate": 7.890868318899403e-10, "loss": 3.8048, "step": 18538 }, { "epoch": 0.9975785622040465, "grad_norm": 1.8836581707000732, "learning_rate": 7.55866050736187e-10, "loss": 2.8345, "step": 18539 }, { "epoch": 0.9976323719328455, "grad_norm": 1.9578782320022583, "learning_rate": 7.233596807404431e-10, "loss": 4.458, "step": 18540 }, { "epoch": 0.9976861816616445, "grad_norm": 3.5359718799591064, "learning_rate": 6.915677228297445e-10, "loss": 3.5209, "step": 18541 }, { "epoch": 0.9977399913904433, "grad_norm": 1.1667375564575195, "learning_rate": 6.604901779144745e-10, "loss": 3.9252, "step": 18542 }, { "epoch": 0.9977938011192423, "grad_norm": 1.627855896949768, "learning_rate": 6.301270468828113e-10, "loss": 4.3714, "step": 18543 }, { "epoch": 0.9978476108480413, "grad_norm": 3.069333553314209, "learning_rate": 6.004783306007288e-10, "loss": 3.8999, "step": 18544 }, { "epoch": 0.9979014205768403, "grad_norm": 5.6317243576049805, "learning_rate": 5.715440299147723e-10, "loss": 4.2399, "step": 18545 }, { "epoch": 0.9979552303056393, "grad_norm": 2.947197914123535, "learning_rate": 5.433241456576088e-10, "loss": 3.6278, "step": 18546 }, { "epoch": 0.9980090400344382, "grad_norm": 5.2253031730651855, "learning_rate": 5.15818678628599e-10, "loss": 3.8723, "step": 18547 }, { "epoch": 0.9980628497632372, "grad_norm": 3.731041431427002, "learning_rate": 4.890276296160013e-10, "loss": 3.9143, "step": 18548 }, { "epoch": 0.9981166594920362, "grad_norm": 4.623533725738525, "learning_rate": 4.629509993886449e-10, "loss": 3.2477, "step": 18549 }, { "epoch": 0.9981704692208351, "grad_norm": 3.2157859802246094, "learning_rate": 4.37588788687604e-10, "loss": 3.7157, "step": 18550 }, { "epoch": 0.9982242789496341, "grad_norm": 3.2576849460601807, "learning_rate": 4.1294099824285004e-10, "loss": 3.6877, "step": 18551 }, { "epoch": 0.998278088678433, "grad_norm": 5.330691814422607, "learning_rate": 3.8900762875104803e-10, "loss": 2.977, "step": 18552 }, { "epoch": 0.998331898407232, "grad_norm": 1.8310428857803345, "learning_rate": 3.6578868090331173e-10, "loss": 4.564, "step": 18553 }, { "epoch": 0.998385708136031, "grad_norm": 2.8416588306427, "learning_rate": 3.432841553574484e-10, "loss": 2.6874, "step": 18554 }, { "epoch": 0.99843951786483, "grad_norm": 2.5514063835144043, "learning_rate": 3.214940527601629e-10, "loss": 3.4865, "step": 18555 }, { "epoch": 0.998493327593629, "grad_norm": 2.915027379989624, "learning_rate": 3.004183737359556e-10, "loss": 3.2821, "step": 18556 }, { "epoch": 0.998547137322428, "grad_norm": 1.5331778526306152, "learning_rate": 2.800571188815715e-10, "loss": 4.5665, "step": 18557 }, { "epoch": 0.9986009470512268, "grad_norm": 3.589862108230591, "learning_rate": 2.6041028878265316e-10, "loss": 3.1553, "step": 18558 }, { "epoch": 0.9986547567800258, "grad_norm": 2.7790989875793457, "learning_rate": 2.414778839998633e-10, "loss": 3.12, "step": 18559 }, { "epoch": 0.9987085665088248, "grad_norm": 3.5696938037872314, "learning_rate": 2.232599050744355e-10, "loss": 4.0446, "step": 18560 }, { "epoch": 0.9987623762376238, "grad_norm": 2.282670021057129, "learning_rate": 2.0575635252539916e-10, "loss": 3.3707, "step": 18561 }, { "epoch": 0.9988161859664227, "grad_norm": 2.8271474838256836, "learning_rate": 1.8896722685513012e-10, "loss": 4.2175, "step": 18562 }, { "epoch": 0.9988699956952217, "grad_norm": 2.1426663398742676, "learning_rate": 1.728925285437999e-10, "loss": 4.1573, "step": 18563 }, { "epoch": 0.9989238054240207, "grad_norm": 4.252437591552734, "learning_rate": 1.5753225804937544e-10, "loss": 3.4231, "step": 18564 }, { "epoch": 0.9989776151528196, "grad_norm": 1.332157015800476, "learning_rate": 1.4288641581039486e-10, "loss": 4.2952, "step": 18565 }, { "epoch": 0.9990314248816186, "grad_norm": 1.8833017349243164, "learning_rate": 1.2895500224596736e-10, "loss": 4.1488, "step": 18566 }, { "epoch": 0.9990852346104175, "grad_norm": 2.2789790630340576, "learning_rate": 1.1573801775299764e-10, "loss": 4.0959, "step": 18567 }, { "epoch": 0.9991390443392165, "grad_norm": 3.0186972618103027, "learning_rate": 1.0323546271173712e-10, "loss": 3.7894, "step": 18568 }, { "epoch": 0.9991928540680155, "grad_norm": 3.465585470199585, "learning_rate": 9.144733747745715e-11, "loss": 3.2334, "step": 18569 }, { "epoch": 0.9992466637968145, "grad_norm": 2.35532283782959, "learning_rate": 8.037364238877577e-11, "loss": 3.3557, "step": 18570 }, { "epoch": 0.9993004735256135, "grad_norm": 3.2238261699676514, "learning_rate": 7.001437775933095e-11, "loss": 3.9523, "step": 18571 }, { "epoch": 0.9993542832544124, "grad_norm": 1.093326210975647, "learning_rate": 6.036954388888294e-11, "loss": 4.1993, "step": 18572 }, { "epoch": 0.9994080929832113, "grad_norm": 2.425280809402466, "learning_rate": 5.1439141052211925e-11, "loss": 3.509, "step": 18573 }, { "epoch": 0.9994619027120103, "grad_norm": 2.703733205795288, "learning_rate": 4.322316950189365e-11, "loss": 3.5912, "step": 18574 }, { "epoch": 0.9995157124408093, "grad_norm": 1.6971442699432373, "learning_rate": 3.5721629473850495e-11, "loss": 4.2284, "step": 18575 }, { "epoch": 0.9995695221696083, "grad_norm": 1.8581767082214355, "learning_rate": 2.89345211818004e-11, "loss": 3.8908, "step": 18576 }, { "epoch": 0.9996233318984072, "grad_norm": 2.691443920135498, "learning_rate": 2.2861844822807955e-11, "loss": 3.593, "step": 18577 }, { "epoch": 0.9996771416272062, "grad_norm": 3.59021258354187, "learning_rate": 1.7503600568957723e-11, "loss": 3.1606, "step": 18578 }, { "epoch": 0.9997309513560052, "grad_norm": 1.5741283893585205, "learning_rate": 1.2859788570129815e-11, "loss": 3.8172, "step": 18579 }, { "epoch": 0.9997847610848042, "grad_norm": 1.2659062147140503, "learning_rate": 8.930408962326554e-12, "loss": 4.3436, "step": 18580 }, { "epoch": 0.9998385708136031, "grad_norm": 4.523577690124512, "learning_rate": 5.715461859345794e-12, "loss": 2.9658, "step": 18581 }, { "epoch": 0.999892380542402, "grad_norm": 2.5908424854278564, "learning_rate": 3.2149473500053818e-12, "loss": 3.8752, "step": 18582 }, { "epoch": 0.999946190271201, "grad_norm": 3.785860776901245, "learning_rate": 1.428865506469812e-12, "loss": 3.6036, "step": 18583 }, { "epoch": 1.0, "grad_norm": 2.7243049144744873, "learning_rate": 3.5721637869912115e-13, "loss": 3.2577, "step": 18584 } ], "logging_steps": 1, "max_steps": 18584, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 12000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.583013599309988e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }