{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.139925904816187, "eval_steps": 500, "global_step": 8000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00014249073810202338, "grad_norm": 24.47828661711726, "learning_rate": 0.0, "loss": 1.5058, "step": 1 }, { "epoch": 0.00028498147620404675, "grad_norm": 24.765584576903038, "learning_rate": 1.4245014245014247e-08, "loss": 1.3976, "step": 2 }, { "epoch": 0.0004274722143060701, "grad_norm": 27.40006541505503, "learning_rate": 2.8490028490028493e-08, "loss": 1.5245, "step": 3 }, { "epoch": 0.0005699629524080935, "grad_norm": 24.521875761206054, "learning_rate": 4.273504273504274e-08, "loss": 1.4908, "step": 4 }, { "epoch": 0.0007124536905101168, "grad_norm": 24.673749048693153, "learning_rate": 5.6980056980056986e-08, "loss": 1.4852, "step": 5 }, { "epoch": 0.0008549444286121402, "grad_norm": 24.9662689412983, "learning_rate": 7.122507122507124e-08, "loss": 1.4958, "step": 6 }, { "epoch": 0.0009974351667141636, "grad_norm": 25.58210609036648, "learning_rate": 8.547008547008549e-08, "loss": 1.487, "step": 7 }, { "epoch": 0.001139925904816187, "grad_norm": 27.789506003137518, "learning_rate": 9.971509971509972e-08, "loss": 1.5799, "step": 8 }, { "epoch": 0.0012824166429182104, "grad_norm": 24.846712135152924, "learning_rate": 1.1396011396011397e-07, "loss": 1.4062, "step": 9 }, { "epoch": 0.0014249073810202336, "grad_norm": 27.61049767947098, "learning_rate": 1.282051282051282e-07, "loss": 1.5091, "step": 10 }, { "epoch": 0.001567398119122257, "grad_norm": 23.566884841087195, "learning_rate": 1.4245014245014247e-07, "loss": 1.4078, "step": 11 }, { "epoch": 0.0017098888572242804, "grad_norm": 24.01073516760279, "learning_rate": 1.566951566951567e-07, "loss": 1.4548, "step": 12 }, { "epoch": 0.0018523795953263038, "grad_norm": 28.914072203205972, "learning_rate": 1.7094017094017097e-07, "loss": 1.501, "step": 13 }, { "epoch": 0.001994870333428327, "grad_norm": 22.59806903146085, "learning_rate": 1.8518518518518518e-07, "loss": 1.4549, "step": 14 }, { "epoch": 0.0021373610715303506, "grad_norm": 22.279131033829135, "learning_rate": 1.9943019943019944e-07, "loss": 1.3973, "step": 15 }, { "epoch": 0.002279851809632374, "grad_norm": 25.96277477075946, "learning_rate": 2.136752136752137e-07, "loss": 1.5358, "step": 16 }, { "epoch": 0.0024223425477343974, "grad_norm": 23.97165361062431, "learning_rate": 2.2792022792022794e-07, "loss": 1.406, "step": 17 }, { "epoch": 0.002564833285836421, "grad_norm": 25.525073252817172, "learning_rate": 2.4216524216524215e-07, "loss": 1.5438, "step": 18 }, { "epoch": 0.002707324023938444, "grad_norm": 25.970325633398268, "learning_rate": 2.564102564102564e-07, "loss": 1.5808, "step": 19 }, { "epoch": 0.002849814762040467, "grad_norm": 21.328568917818192, "learning_rate": 2.706552706552707e-07, "loss": 1.419, "step": 20 }, { "epoch": 0.0029923055001424906, "grad_norm": 23.511588765530778, "learning_rate": 2.8490028490028494e-07, "loss": 1.4084, "step": 21 }, { "epoch": 0.003134796238244514, "grad_norm": 22.97472239002064, "learning_rate": 2.991452991452992e-07, "loss": 1.5036, "step": 22 }, { "epoch": 0.0032772869763465374, "grad_norm": 22.455388961840807, "learning_rate": 3.133903133903134e-07, "loss": 1.3997, "step": 23 }, { "epoch": 0.003419777714448561, "grad_norm": 26.577613711608727, "learning_rate": 3.276353276353277e-07, "loss": 1.4919, "step": 24 }, { "epoch": 0.003562268452550584, "grad_norm": 23.99299939120995, "learning_rate": 3.4188034188034194e-07, "loss": 1.3891, "step": 25 }, { "epoch": 0.0037047591906526076, "grad_norm": 17.994730450666385, "learning_rate": 3.5612535612535615e-07, "loss": 1.2865, "step": 26 }, { "epoch": 0.003847249928754631, "grad_norm": 17.208311042718798, "learning_rate": 3.7037037037037036e-07, "loss": 1.3616, "step": 27 }, { "epoch": 0.003989740666856654, "grad_norm": 18.723637299649333, "learning_rate": 3.846153846153847e-07, "loss": 1.3651, "step": 28 }, { "epoch": 0.004132231404958678, "grad_norm": 18.622376251620416, "learning_rate": 3.988603988603989e-07, "loss": 1.3588, "step": 29 }, { "epoch": 0.004274722143060701, "grad_norm": 17.22259233544321, "learning_rate": 4.131054131054131e-07, "loss": 1.3495, "step": 30 }, { "epoch": 0.004417212881162725, "grad_norm": 16.84023828128756, "learning_rate": 4.273504273504274e-07, "loss": 1.3486, "step": 31 }, { "epoch": 0.004559703619264748, "grad_norm": 17.53894324781334, "learning_rate": 4.415954415954416e-07, "loss": 1.3184, "step": 32 }, { "epoch": 0.004702194357366771, "grad_norm": 16.41256368942536, "learning_rate": 4.558404558404559e-07, "loss": 1.4056, "step": 33 }, { "epoch": 0.004844685095468795, "grad_norm": 14.827318821887445, "learning_rate": 4.700854700854701e-07, "loss": 1.2459, "step": 34 }, { "epoch": 0.004987175833570818, "grad_norm": 11.559749490090743, "learning_rate": 4.843304843304843e-07, "loss": 1.169, "step": 35 }, { "epoch": 0.005129666571672842, "grad_norm": 10.09468408014834, "learning_rate": 4.985754985754987e-07, "loss": 1.2033, "step": 36 }, { "epoch": 0.005272157309774865, "grad_norm": 10.268222378571735, "learning_rate": 5.128205128205128e-07, "loss": 1.2229, "step": 37 }, { "epoch": 0.005414648047876888, "grad_norm": 8.837147279086295, "learning_rate": 5.270655270655271e-07, "loss": 1.2364, "step": 38 }, { "epoch": 0.005557138785978911, "grad_norm": 9.145331570344581, "learning_rate": 5.413105413105414e-07, "loss": 1.1048, "step": 39 }, { "epoch": 0.005699629524080934, "grad_norm": 8.576033907056658, "learning_rate": 5.555555555555555e-07, "loss": 1.1992, "step": 40 }, { "epoch": 0.005842120262182958, "grad_norm": 8.465518193405428, "learning_rate": 5.698005698005699e-07, "loss": 1.1494, "step": 41 }, { "epoch": 0.005984611000284981, "grad_norm": 8.442415892236188, "learning_rate": 5.84045584045584e-07, "loss": 1.09, "step": 42 }, { "epoch": 0.0061271017383870046, "grad_norm": 7.982892982695008, "learning_rate": 5.982905982905984e-07, "loss": 1.2075, "step": 43 }, { "epoch": 0.006269592476489028, "grad_norm": 7.639944923998619, "learning_rate": 6.125356125356126e-07, "loss": 1.182, "step": 44 }, { "epoch": 0.006412083214591051, "grad_norm": 7.105330994114983, "learning_rate": 6.267806267806268e-07, "loss": 1.1174, "step": 45 }, { "epoch": 0.006554573952693075, "grad_norm": 6.609660424563045, "learning_rate": 6.41025641025641e-07, "loss": 1.0402, "step": 46 }, { "epoch": 0.006697064690795098, "grad_norm": 5.850339899857292, "learning_rate": 6.552706552706554e-07, "loss": 1.1124, "step": 47 }, { "epoch": 0.006839555428897122, "grad_norm": 5.804648218569975, "learning_rate": 6.695156695156696e-07, "loss": 1.1194, "step": 48 }, { "epoch": 0.006982046166999145, "grad_norm": 5.524965429374446, "learning_rate": 6.837606837606839e-07, "loss": 0.9867, "step": 49 }, { "epoch": 0.007124536905101168, "grad_norm": 4.711884468806079, "learning_rate": 6.98005698005698e-07, "loss": 1.0032, "step": 50 }, { "epoch": 0.007267027643203192, "grad_norm": 4.956438896578468, "learning_rate": 7.122507122507123e-07, "loss": 0.9187, "step": 51 }, { "epoch": 0.007409518381305215, "grad_norm": 5.446716756679033, "learning_rate": 7.264957264957266e-07, "loss": 0.9495, "step": 52 }, { "epoch": 0.007552009119407239, "grad_norm": 4.673504683296022, "learning_rate": 7.407407407407407e-07, "loss": 0.9834, "step": 53 }, { "epoch": 0.007694499857509262, "grad_norm": 4.9292046296105685, "learning_rate": 7.549857549857551e-07, "loss": 0.9341, "step": 54 }, { "epoch": 0.007836990595611285, "grad_norm": 4.52957753742139, "learning_rate": 7.692307692307694e-07, "loss": 0.9305, "step": 55 }, { "epoch": 0.007979481333713309, "grad_norm": 4.587998516889364, "learning_rate": 7.834757834757835e-07, "loss": 0.9679, "step": 56 }, { "epoch": 0.008121972071815331, "grad_norm": 4.184997765578424, "learning_rate": 7.977207977207978e-07, "loss": 0.8892, "step": 57 }, { "epoch": 0.008264462809917356, "grad_norm": 5.677944174681949, "learning_rate": 8.11965811965812e-07, "loss": 0.946, "step": 58 }, { "epoch": 0.008406953548019378, "grad_norm": 3.8105562987250643, "learning_rate": 8.262108262108262e-07, "loss": 0.8983, "step": 59 }, { "epoch": 0.008549444286121402, "grad_norm": 4.5447075098481555, "learning_rate": 8.404558404558405e-07, "loss": 0.8947, "step": 60 }, { "epoch": 0.008691935024223425, "grad_norm": 3.647200858604676, "learning_rate": 8.547008547008548e-07, "loss": 1.0255, "step": 61 }, { "epoch": 0.00883442576232545, "grad_norm": 3.7555804525046286, "learning_rate": 8.689458689458691e-07, "loss": 0.891, "step": 62 }, { "epoch": 0.008976916500427472, "grad_norm": 4.141165666252753, "learning_rate": 8.831908831908833e-07, "loss": 0.9181, "step": 63 }, { "epoch": 0.009119407238529496, "grad_norm": 3.8239707809524486, "learning_rate": 8.974358974358975e-07, "loss": 0.9509, "step": 64 }, { "epoch": 0.009261897976631519, "grad_norm": 4.556169468753723, "learning_rate": 9.116809116809118e-07, "loss": 0.9347, "step": 65 }, { "epoch": 0.009404388714733543, "grad_norm": 3.325466728190847, "learning_rate": 9.259259259259259e-07, "loss": 0.9255, "step": 66 }, { "epoch": 0.009546879452835565, "grad_norm": 4.9724809989832925, "learning_rate": 9.401709401709402e-07, "loss": 0.8504, "step": 67 }, { "epoch": 0.00968937019093759, "grad_norm": 6.513729244581304, "learning_rate": 9.544159544159546e-07, "loss": 0.9192, "step": 68 }, { "epoch": 0.009831860929039612, "grad_norm": 3.7699898580089473, "learning_rate": 9.686609686609686e-07, "loss": 0.9051, "step": 69 }, { "epoch": 0.009974351667141636, "grad_norm": 3.580524998905241, "learning_rate": 9.829059829059829e-07, "loss": 0.8815, "step": 70 }, { "epoch": 0.010116842405243659, "grad_norm": 3.6127438754043073, "learning_rate": 9.971509971509974e-07, "loss": 0.8773, "step": 71 }, { "epoch": 0.010259333143345683, "grad_norm": 3.6119025737792922, "learning_rate": 1.0113960113960116e-06, "loss": 0.9103, "step": 72 }, { "epoch": 0.010401823881447706, "grad_norm": 3.8135358214816484, "learning_rate": 1.0256410256410257e-06, "loss": 0.9081, "step": 73 }, { "epoch": 0.01054431461954973, "grad_norm": 4.26156035765008, "learning_rate": 1.03988603988604e-06, "loss": 0.803, "step": 74 }, { "epoch": 0.010686805357651753, "grad_norm": 3.816022163860714, "learning_rate": 1.0541310541310542e-06, "loss": 0.9025, "step": 75 }, { "epoch": 0.010829296095753777, "grad_norm": 3.3042520080493585, "learning_rate": 1.0683760683760685e-06, "loss": 0.8892, "step": 76 }, { "epoch": 0.0109717868338558, "grad_norm": 3.602160493760988, "learning_rate": 1.0826210826210827e-06, "loss": 0.8881, "step": 77 }, { "epoch": 0.011114277571957822, "grad_norm": 3.949804651017862, "learning_rate": 1.096866096866097e-06, "loss": 0.7499, "step": 78 }, { "epoch": 0.011256768310059846, "grad_norm": 4.697242390231384, "learning_rate": 1.111111111111111e-06, "loss": 0.7808, "step": 79 }, { "epoch": 0.011399259048161869, "grad_norm": 3.4013214632146584, "learning_rate": 1.1253561253561255e-06, "loss": 0.9172, "step": 80 }, { "epoch": 0.011541749786263893, "grad_norm": 3.582667718124238, "learning_rate": 1.1396011396011398e-06, "loss": 0.8274, "step": 81 }, { "epoch": 0.011684240524365916, "grad_norm": 3.5293757916764887, "learning_rate": 1.153846153846154e-06, "loss": 0.9005, "step": 82 }, { "epoch": 0.01182673126246794, "grad_norm": 3.6261149210697514, "learning_rate": 1.168091168091168e-06, "loss": 0.8647, "step": 83 }, { "epoch": 0.011969222000569962, "grad_norm": 5.476916418893654, "learning_rate": 1.1823361823361824e-06, "loss": 0.8469, "step": 84 }, { "epoch": 0.012111712738671987, "grad_norm": 3.6395577276730853, "learning_rate": 1.1965811965811968e-06, "loss": 0.8533, "step": 85 }, { "epoch": 0.012254203476774009, "grad_norm": 3.6661176951693153, "learning_rate": 1.2108262108262109e-06, "loss": 0.887, "step": 86 }, { "epoch": 0.012396694214876033, "grad_norm": 3.2557081079046726, "learning_rate": 1.2250712250712251e-06, "loss": 0.8593, "step": 87 }, { "epoch": 0.012539184952978056, "grad_norm": 3.9045788106446477, "learning_rate": 1.2393162393162394e-06, "loss": 0.8651, "step": 88 }, { "epoch": 0.01268167569108008, "grad_norm": 3.4566395222166473, "learning_rate": 1.2535612535612537e-06, "loss": 0.8732, "step": 89 }, { "epoch": 0.012824166429182103, "grad_norm": 3.396957598968685, "learning_rate": 1.267806267806268e-06, "loss": 0.7633, "step": 90 }, { "epoch": 0.012966657167284127, "grad_norm": 3.119077521628561, "learning_rate": 1.282051282051282e-06, "loss": 0.8823, "step": 91 }, { "epoch": 0.01310914790538615, "grad_norm": 3.368400468386458, "learning_rate": 1.2962962962962962e-06, "loss": 0.8781, "step": 92 }, { "epoch": 0.013251638643488174, "grad_norm": 3.6520590601818324, "learning_rate": 1.3105413105413107e-06, "loss": 0.8229, "step": 93 }, { "epoch": 0.013394129381590196, "grad_norm": 3.62751863826295, "learning_rate": 1.324786324786325e-06, "loss": 0.839, "step": 94 }, { "epoch": 0.01353662011969222, "grad_norm": 3.371986479117824, "learning_rate": 1.3390313390313392e-06, "loss": 0.8146, "step": 95 }, { "epoch": 0.013679110857794243, "grad_norm": 3.348016301080103, "learning_rate": 1.3532763532763535e-06, "loss": 0.8186, "step": 96 }, { "epoch": 0.013821601595896267, "grad_norm": 3.826439835552942, "learning_rate": 1.3675213675213678e-06, "loss": 0.8118, "step": 97 }, { "epoch": 0.01396409233399829, "grad_norm": 3.574909352448806, "learning_rate": 1.3817663817663818e-06, "loss": 0.8967, "step": 98 }, { "epoch": 0.014106583072100314, "grad_norm": 4.016496578400064, "learning_rate": 1.396011396011396e-06, "loss": 0.8348, "step": 99 }, { "epoch": 0.014249073810202337, "grad_norm": 3.8219315193583867, "learning_rate": 1.4102564102564104e-06, "loss": 0.7999, "step": 100 }, { "epoch": 0.014391564548304361, "grad_norm": 3.5771885277887994, "learning_rate": 1.4245014245014246e-06, "loss": 0.9243, "step": 101 }, { "epoch": 0.014534055286406384, "grad_norm": 3.717173534540446, "learning_rate": 1.4387464387464389e-06, "loss": 0.8424, "step": 102 }, { "epoch": 0.014676546024508406, "grad_norm": 4.961834367532948, "learning_rate": 1.4529914529914531e-06, "loss": 0.9302, "step": 103 }, { "epoch": 0.01481903676261043, "grad_norm": 3.717170873871834, "learning_rate": 1.4672364672364672e-06, "loss": 0.9159, "step": 104 }, { "epoch": 0.014961527500712453, "grad_norm": 3.5275141079458487, "learning_rate": 1.4814814814814815e-06, "loss": 0.7645, "step": 105 }, { "epoch": 0.015104018238814477, "grad_norm": 3.4767806734148112, "learning_rate": 1.4957264957264957e-06, "loss": 0.7938, "step": 106 }, { "epoch": 0.0152465089769165, "grad_norm": 2.888834535585864, "learning_rate": 1.5099715099715102e-06, "loss": 0.8036, "step": 107 }, { "epoch": 0.015388999715018524, "grad_norm": 4.069490287650536, "learning_rate": 1.5242165242165245e-06, "loss": 0.8282, "step": 108 }, { "epoch": 0.015531490453120547, "grad_norm": 3.3367897441438292, "learning_rate": 1.5384615384615387e-06, "loss": 0.8498, "step": 109 }, { "epoch": 0.01567398119122257, "grad_norm": 3.7868746926074093, "learning_rate": 1.552706552706553e-06, "loss": 0.8096, "step": 110 }, { "epoch": 0.015816471929324595, "grad_norm": 3.8220897713699626, "learning_rate": 1.566951566951567e-06, "loss": 0.8012, "step": 111 }, { "epoch": 0.015958962667426618, "grad_norm": 3.760761803545142, "learning_rate": 1.5811965811965813e-06, "loss": 0.8838, "step": 112 }, { "epoch": 0.01610145340552864, "grad_norm": 3.4158819226682304, "learning_rate": 1.5954415954415956e-06, "loss": 0.7779, "step": 113 }, { "epoch": 0.016243944143630663, "grad_norm": 3.745042883924438, "learning_rate": 1.6096866096866098e-06, "loss": 0.7905, "step": 114 }, { "epoch": 0.01638643488173269, "grad_norm": 3.5459426433604126, "learning_rate": 1.623931623931624e-06, "loss": 0.8145, "step": 115 }, { "epoch": 0.01652892561983471, "grad_norm": 3.4713777520954414, "learning_rate": 1.6381766381766383e-06, "loss": 0.8951, "step": 116 }, { "epoch": 0.016671416357936734, "grad_norm": 3.6027508917667728, "learning_rate": 1.6524216524216524e-06, "loss": 0.8562, "step": 117 }, { "epoch": 0.016813907096038756, "grad_norm": 3.5417714618434126, "learning_rate": 1.6666666666666667e-06, "loss": 0.7715, "step": 118 }, { "epoch": 0.016956397834140782, "grad_norm": 4.010109346751245, "learning_rate": 1.680911680911681e-06, "loss": 0.8226, "step": 119 }, { "epoch": 0.017098888572242805, "grad_norm": 3.2820140628996137, "learning_rate": 1.6951566951566952e-06, "loss": 0.7133, "step": 120 }, { "epoch": 0.017241379310344827, "grad_norm": 3.4926916508486303, "learning_rate": 1.7094017094017097e-06, "loss": 0.8312, "step": 121 }, { "epoch": 0.01738387004844685, "grad_norm": 8.435604861975902, "learning_rate": 1.723646723646724e-06, "loss": 0.734, "step": 122 }, { "epoch": 0.017526360786548876, "grad_norm": 3.43292475615291, "learning_rate": 1.7378917378917382e-06, "loss": 0.7158, "step": 123 }, { "epoch": 0.0176688515246509, "grad_norm": 4.227293265121555, "learning_rate": 1.7521367521367522e-06, "loss": 0.8188, "step": 124 }, { "epoch": 0.01781134226275292, "grad_norm": 3.5536413484901406, "learning_rate": 1.7663817663817665e-06, "loss": 0.8159, "step": 125 }, { "epoch": 0.017953833000854943, "grad_norm": 3.518836468777323, "learning_rate": 1.7806267806267808e-06, "loss": 0.7375, "step": 126 }, { "epoch": 0.01809632373895697, "grad_norm": 3.748357990263804, "learning_rate": 1.794871794871795e-06, "loss": 0.7559, "step": 127 }, { "epoch": 0.018238814477058992, "grad_norm": 3.492392902761556, "learning_rate": 1.8091168091168093e-06, "loss": 0.7715, "step": 128 }, { "epoch": 0.018381305215161015, "grad_norm": 3.4674723252745756, "learning_rate": 1.8233618233618236e-06, "loss": 0.7761, "step": 129 }, { "epoch": 0.018523795953263037, "grad_norm": 3.5661473043447307, "learning_rate": 1.8376068376068378e-06, "loss": 0.8519, "step": 130 }, { "epoch": 0.01866628669136506, "grad_norm": 3.4706607852718365, "learning_rate": 1.8518518518518519e-06, "loss": 0.808, "step": 131 }, { "epoch": 0.018808777429467086, "grad_norm": 3.4461636592652534, "learning_rate": 1.8660968660968661e-06, "loss": 0.7837, "step": 132 }, { "epoch": 0.018951268167569108, "grad_norm": 3.1686835365989414, "learning_rate": 1.8803418803418804e-06, "loss": 0.7787, "step": 133 }, { "epoch": 0.01909375890567113, "grad_norm": 3.518729844142843, "learning_rate": 1.8945868945868947e-06, "loss": 0.7659, "step": 134 }, { "epoch": 0.019236249643773153, "grad_norm": 3.809255985421104, "learning_rate": 1.908831908831909e-06, "loss": 0.7663, "step": 135 }, { "epoch": 0.01937874038187518, "grad_norm": 3.765169885417333, "learning_rate": 1.9230769230769234e-06, "loss": 0.7149, "step": 136 }, { "epoch": 0.019521231119977202, "grad_norm": 3.3265895801822642, "learning_rate": 1.9373219373219372e-06, "loss": 0.8202, "step": 137 }, { "epoch": 0.019663721858079224, "grad_norm": 3.7562647670996094, "learning_rate": 1.9515669515669515e-06, "loss": 0.8217, "step": 138 }, { "epoch": 0.019806212596181247, "grad_norm": 3.649836242459198, "learning_rate": 1.9658119658119658e-06, "loss": 0.7415, "step": 139 }, { "epoch": 0.019948703334283273, "grad_norm": 3.1056154180057334, "learning_rate": 1.98005698005698e-06, "loss": 0.8232, "step": 140 }, { "epoch": 0.020091194072385295, "grad_norm": 3.684770500476751, "learning_rate": 1.9943019943019947e-06, "loss": 0.7784, "step": 141 }, { "epoch": 0.020233684810487318, "grad_norm": 3.3325030823856636, "learning_rate": 2.008547008547009e-06, "loss": 0.7456, "step": 142 }, { "epoch": 0.02037617554858934, "grad_norm": 3.850134444665664, "learning_rate": 2.0227920227920232e-06, "loss": 0.6787, "step": 143 }, { "epoch": 0.020518666286691366, "grad_norm": 3.349228227127145, "learning_rate": 2.037037037037037e-06, "loss": 0.7645, "step": 144 }, { "epoch": 0.02066115702479339, "grad_norm": 3.36763749703118, "learning_rate": 2.0512820512820513e-06, "loss": 0.7199, "step": 145 }, { "epoch": 0.02080364776289541, "grad_norm": 3.2642876323101264, "learning_rate": 2.0655270655270656e-06, "loss": 0.7676, "step": 146 }, { "epoch": 0.020946138500997434, "grad_norm": 3.2518439078666974, "learning_rate": 2.07977207977208e-06, "loss": 0.7747, "step": 147 }, { "epoch": 0.02108862923909946, "grad_norm": 3.789860243264878, "learning_rate": 2.094017094017094e-06, "loss": 0.7954, "step": 148 }, { "epoch": 0.021231119977201483, "grad_norm": 3.426785355441181, "learning_rate": 2.1082621082621084e-06, "loss": 0.7128, "step": 149 }, { "epoch": 0.021373610715303505, "grad_norm": 3.568966002401439, "learning_rate": 2.1225071225071227e-06, "loss": 0.7788, "step": 150 }, { "epoch": 0.021516101453405528, "grad_norm": 3.7611065495371068, "learning_rate": 2.136752136752137e-06, "loss": 0.8621, "step": 151 }, { "epoch": 0.021658592191507554, "grad_norm": 2.9689371217574454, "learning_rate": 2.150997150997151e-06, "loss": 0.8016, "step": 152 }, { "epoch": 0.021801082929609576, "grad_norm": 3.475025180248518, "learning_rate": 2.1652421652421654e-06, "loss": 0.8054, "step": 153 }, { "epoch": 0.0219435736677116, "grad_norm": 3.3947035784580297, "learning_rate": 2.1794871794871797e-06, "loss": 0.8463, "step": 154 }, { "epoch": 0.02208606440581362, "grad_norm": 3.4646208665499456, "learning_rate": 2.193732193732194e-06, "loss": 0.7829, "step": 155 }, { "epoch": 0.022228555143915644, "grad_norm": 2.9535463018124126, "learning_rate": 2.2079772079772082e-06, "loss": 0.7935, "step": 156 }, { "epoch": 0.02237104588201767, "grad_norm": 3.594539106865843, "learning_rate": 2.222222222222222e-06, "loss": 0.8505, "step": 157 }, { "epoch": 0.022513536620119692, "grad_norm": 3.4601181885555796, "learning_rate": 2.2364672364672368e-06, "loss": 0.7417, "step": 158 }, { "epoch": 0.022656027358221715, "grad_norm": 3.259307182009347, "learning_rate": 2.250712250712251e-06, "loss": 0.7469, "step": 159 }, { "epoch": 0.022798518096323737, "grad_norm": 3.3290564233932023, "learning_rate": 2.2649572649572653e-06, "loss": 0.8009, "step": 160 }, { "epoch": 0.022941008834425763, "grad_norm": 3.378877450372592, "learning_rate": 2.2792022792022796e-06, "loss": 0.8173, "step": 161 }, { "epoch": 0.023083499572527786, "grad_norm": 3.3928081117530096, "learning_rate": 2.293447293447294e-06, "loss": 0.842, "step": 162 }, { "epoch": 0.02322599031062981, "grad_norm": 3.1485383792419825, "learning_rate": 2.307692307692308e-06, "loss": 0.8568, "step": 163 }, { "epoch": 0.02336848104873183, "grad_norm": 3.256559323235982, "learning_rate": 2.321937321937322e-06, "loss": 0.9203, "step": 164 }, { "epoch": 0.023510971786833857, "grad_norm": 3.4968210005637874, "learning_rate": 2.336182336182336e-06, "loss": 0.831, "step": 165 }, { "epoch": 0.02365346252493588, "grad_norm": 3.393381962961166, "learning_rate": 2.3504273504273504e-06, "loss": 0.821, "step": 166 }, { "epoch": 0.023795953263037902, "grad_norm": 3.5342264622557322, "learning_rate": 2.3646723646723647e-06, "loss": 0.8166, "step": 167 }, { "epoch": 0.023938444001139925, "grad_norm": 3.3386380954533195, "learning_rate": 2.378917378917379e-06, "loss": 0.8282, "step": 168 }, { "epoch": 0.02408093473924195, "grad_norm": 3.7927869036656547, "learning_rate": 2.3931623931623937e-06, "loss": 0.751, "step": 169 }, { "epoch": 0.024223425477343973, "grad_norm": 2.9464642808231396, "learning_rate": 2.4074074074074075e-06, "loss": 0.7816, "step": 170 }, { "epoch": 0.024365916215445996, "grad_norm": 3.390922957483592, "learning_rate": 2.4216524216524218e-06, "loss": 0.7665, "step": 171 }, { "epoch": 0.024508406953548018, "grad_norm": 3.2372098240898612, "learning_rate": 2.435897435897436e-06, "loss": 0.7379, "step": 172 }, { "epoch": 0.024650897691650044, "grad_norm": 3.544280525942591, "learning_rate": 2.4501424501424503e-06, "loss": 0.8517, "step": 173 }, { "epoch": 0.024793388429752067, "grad_norm": 5.2108384646613795, "learning_rate": 2.4643874643874645e-06, "loss": 0.7302, "step": 174 }, { "epoch": 0.02493587916785409, "grad_norm": 3.346021056669233, "learning_rate": 2.478632478632479e-06, "loss": 0.8388, "step": 175 }, { "epoch": 0.025078369905956112, "grad_norm": 3.541155933137064, "learning_rate": 2.492877492877493e-06, "loss": 0.7923, "step": 176 }, { "epoch": 0.025220860644058138, "grad_norm": 4.7678330826283135, "learning_rate": 2.5071225071225073e-06, "loss": 0.6883, "step": 177 }, { "epoch": 0.02536335138216016, "grad_norm": 4.017048723449808, "learning_rate": 2.5213675213675216e-06, "loss": 0.7483, "step": 178 }, { "epoch": 0.025505842120262183, "grad_norm": 3.950247702994045, "learning_rate": 2.535612535612536e-06, "loss": 0.768, "step": 179 }, { "epoch": 0.025648332858364205, "grad_norm": 3.405410565593636, "learning_rate": 2.54985754985755e-06, "loss": 0.7619, "step": 180 }, { "epoch": 0.025790823596466228, "grad_norm": 3.333672585226186, "learning_rate": 2.564102564102564e-06, "loss": 0.8175, "step": 181 }, { "epoch": 0.025933314334568254, "grad_norm": 3.4370440537581124, "learning_rate": 2.5783475783475787e-06, "loss": 0.7432, "step": 182 }, { "epoch": 0.026075805072670277, "grad_norm": 4.21544166327058, "learning_rate": 2.5925925925925925e-06, "loss": 0.8229, "step": 183 }, { "epoch": 0.0262182958107723, "grad_norm": 2.850671866340608, "learning_rate": 2.606837606837607e-06, "loss": 0.7906, "step": 184 }, { "epoch": 0.02636078654887432, "grad_norm": 3.085408781287073, "learning_rate": 2.6210826210826214e-06, "loss": 0.8702, "step": 185 }, { "epoch": 0.026503277286976348, "grad_norm": 3.40947204007433, "learning_rate": 2.6353276353276357e-06, "loss": 0.7488, "step": 186 }, { "epoch": 0.02664576802507837, "grad_norm": 3.4841423081414833, "learning_rate": 2.64957264957265e-06, "loss": 0.7754, "step": 187 }, { "epoch": 0.026788258763180393, "grad_norm": 3.867537216371181, "learning_rate": 2.663817663817664e-06, "loss": 0.77, "step": 188 }, { "epoch": 0.026930749501282415, "grad_norm": 3.0717336520293714, "learning_rate": 2.6780626780626785e-06, "loss": 0.7754, "step": 189 }, { "epoch": 0.02707324023938444, "grad_norm": 3.3143443418171685, "learning_rate": 2.6923076923076923e-06, "loss": 0.785, "step": 190 }, { "epoch": 0.027215730977486464, "grad_norm": 3.3524091829552396, "learning_rate": 2.706552706552707e-06, "loss": 0.7712, "step": 191 }, { "epoch": 0.027358221715588486, "grad_norm": 3.327991517026223, "learning_rate": 2.720797720797721e-06, "loss": 0.7568, "step": 192 }, { "epoch": 0.02750071245369051, "grad_norm": 3.28460999606182, "learning_rate": 2.7350427350427355e-06, "loss": 0.8241, "step": 193 }, { "epoch": 0.027643203191792535, "grad_norm": 3.4062906952615495, "learning_rate": 2.7492877492877494e-06, "loss": 0.8043, "step": 194 }, { "epoch": 0.027785693929894557, "grad_norm": 3.1656090323893262, "learning_rate": 2.7635327635327636e-06, "loss": 0.8663, "step": 195 }, { "epoch": 0.02792818466799658, "grad_norm": 3.7032150416384146, "learning_rate": 2.7777777777777783e-06, "loss": 0.7151, "step": 196 }, { "epoch": 0.028070675406098602, "grad_norm": 3.3732365808494333, "learning_rate": 2.792022792022792e-06, "loss": 0.7783, "step": 197 }, { "epoch": 0.02821316614420063, "grad_norm": 3.426025838401232, "learning_rate": 2.806267806267807e-06, "loss": 0.7155, "step": 198 }, { "epoch": 0.02835565688230265, "grad_norm": 4.149085004577369, "learning_rate": 2.8205128205128207e-06, "loss": 0.6958, "step": 199 }, { "epoch": 0.028498147620404674, "grad_norm": 3.7877573181879, "learning_rate": 2.8347578347578345e-06, "loss": 0.726, "step": 200 }, { "epoch": 0.028640638358506696, "grad_norm": 4.385678197965012, "learning_rate": 2.8490028490028492e-06, "loss": 0.6797, "step": 201 }, { "epoch": 0.028783129096608722, "grad_norm": 3.2908253375234926, "learning_rate": 2.8632478632478635e-06, "loss": 0.7722, "step": 202 }, { "epoch": 0.028925619834710745, "grad_norm": 3.123651023479681, "learning_rate": 2.8774928774928778e-06, "loss": 0.7564, "step": 203 }, { "epoch": 0.029068110572812767, "grad_norm": 3.3859973611321337, "learning_rate": 2.891737891737892e-06, "loss": 0.8055, "step": 204 }, { "epoch": 0.02921060131091479, "grad_norm": 3.391558925953373, "learning_rate": 2.9059829059829063e-06, "loss": 0.7009, "step": 205 }, { "epoch": 0.029353092049016812, "grad_norm": 3.4319437790872906, "learning_rate": 2.9202279202279205e-06, "loss": 0.7909, "step": 206 }, { "epoch": 0.029495582787118838, "grad_norm": 3.5242407992627913, "learning_rate": 2.9344729344729344e-06, "loss": 0.7494, "step": 207 }, { "epoch": 0.02963807352522086, "grad_norm": 3.199695870552718, "learning_rate": 2.948717948717949e-06, "loss": 0.7729, "step": 208 }, { "epoch": 0.029780564263322883, "grad_norm": 3.251126612478386, "learning_rate": 2.962962962962963e-06, "loss": 0.8567, "step": 209 }, { "epoch": 0.029923055001424906, "grad_norm": 3.8149742303261367, "learning_rate": 2.9772079772079776e-06, "loss": 0.7943, "step": 210 }, { "epoch": 0.030065545739526932, "grad_norm": 8.453337716927612, "learning_rate": 2.9914529914529914e-06, "loss": 0.7594, "step": 211 }, { "epoch": 0.030208036477628954, "grad_norm": 3.7586426172747096, "learning_rate": 3.005698005698006e-06, "loss": 0.7188, "step": 212 }, { "epoch": 0.030350527215730977, "grad_norm": 3.114362099523379, "learning_rate": 3.0199430199430204e-06, "loss": 0.7996, "step": 213 }, { "epoch": 0.030493017953833, "grad_norm": 3.481512322718082, "learning_rate": 3.0341880341880342e-06, "loss": 0.7655, "step": 214 }, { "epoch": 0.030635508691935025, "grad_norm": 3.110409676893608, "learning_rate": 3.048433048433049e-06, "loss": 0.8012, "step": 215 }, { "epoch": 0.030777999430037048, "grad_norm": 3.2988262715514813, "learning_rate": 3.0626780626780627e-06, "loss": 0.7935, "step": 216 }, { "epoch": 0.03092049016813907, "grad_norm": 3.2682168416825528, "learning_rate": 3.0769230769230774e-06, "loss": 0.7385, "step": 217 }, { "epoch": 0.031062980906241093, "grad_norm": 3.329094305544456, "learning_rate": 3.0911680911680913e-06, "loss": 0.7208, "step": 218 }, { "epoch": 0.03120547164434312, "grad_norm": 2.9516545825208507, "learning_rate": 3.105413105413106e-06, "loss": 0.7137, "step": 219 }, { "epoch": 0.03134796238244514, "grad_norm": 8.126418308651427, "learning_rate": 3.11965811965812e-06, "loss": 0.7706, "step": 220 }, { "epoch": 0.031490453120547164, "grad_norm": 3.1884137438456372, "learning_rate": 3.133903133903134e-06, "loss": 0.7928, "step": 221 }, { "epoch": 0.03163294385864919, "grad_norm": 3.58336943408868, "learning_rate": 3.1481481481481483e-06, "loss": 0.7668, "step": 222 }, { "epoch": 0.03177543459675121, "grad_norm": 3.308227716080362, "learning_rate": 3.1623931623931626e-06, "loss": 0.8589, "step": 223 }, { "epoch": 0.031917925334853235, "grad_norm": 3.2812694861890637, "learning_rate": 3.1766381766381773e-06, "loss": 0.645, "step": 224 }, { "epoch": 0.03206041607295526, "grad_norm": 4.396164750874792, "learning_rate": 3.190883190883191e-06, "loss": 0.8099, "step": 225 }, { "epoch": 0.03220290681105728, "grad_norm": 3.7088418081748467, "learning_rate": 3.205128205128206e-06, "loss": 0.6978, "step": 226 }, { "epoch": 0.032345397549159306, "grad_norm": 3.4223395544765016, "learning_rate": 3.2193732193732196e-06, "loss": 0.8544, "step": 227 }, { "epoch": 0.032487888287261325, "grad_norm": 3.538402219620001, "learning_rate": 3.2336182336182335e-06, "loss": 0.722, "step": 228 }, { "epoch": 0.03263037902536335, "grad_norm": 3.405820797501253, "learning_rate": 3.247863247863248e-06, "loss": 0.7919, "step": 229 }, { "epoch": 0.03277286976346538, "grad_norm": 3.2652228222268382, "learning_rate": 3.2621082621082624e-06, "loss": 0.7569, "step": 230 }, { "epoch": 0.032915360501567396, "grad_norm": 3.4566266582368406, "learning_rate": 3.2763532763532767e-06, "loss": 0.792, "step": 231 }, { "epoch": 0.03305785123966942, "grad_norm": 3.320910672931902, "learning_rate": 3.290598290598291e-06, "loss": 0.7621, "step": 232 }, { "epoch": 0.03320034197777144, "grad_norm": 4.178770369196653, "learning_rate": 3.304843304843305e-06, "loss": 0.7225, "step": 233 }, { "epoch": 0.03334283271587347, "grad_norm": 2.9644065661464123, "learning_rate": 3.3190883190883195e-06, "loss": 0.7502, "step": 234 }, { "epoch": 0.033485323453975493, "grad_norm": 3.157547064308074, "learning_rate": 3.3333333333333333e-06, "loss": 0.7137, "step": 235 }, { "epoch": 0.03362781419207751, "grad_norm": 3.602551761141754, "learning_rate": 3.347578347578348e-06, "loss": 0.735, "step": 236 }, { "epoch": 0.03377030493017954, "grad_norm": 3.33262911755675, "learning_rate": 3.361823361823362e-06, "loss": 0.8212, "step": 237 }, { "epoch": 0.033912795668281565, "grad_norm": 3.400605581658481, "learning_rate": 3.3760683760683765e-06, "loss": 0.8, "step": 238 }, { "epoch": 0.034055286406383584, "grad_norm": 3.0407972451944767, "learning_rate": 3.3903133903133904e-06, "loss": 0.7965, "step": 239 }, { "epoch": 0.03419777714448561, "grad_norm": 3.067125989700281, "learning_rate": 3.4045584045584046e-06, "loss": 0.7319, "step": 240 }, { "epoch": 0.03434026788258763, "grad_norm": 3.1041982430786286, "learning_rate": 3.4188034188034193e-06, "loss": 0.6915, "step": 241 }, { "epoch": 0.034482758620689655, "grad_norm": 3.4376584678882756, "learning_rate": 3.433048433048433e-06, "loss": 0.8253, "step": 242 }, { "epoch": 0.03462524935879168, "grad_norm": 2.9103409769300055, "learning_rate": 3.447293447293448e-06, "loss": 0.7908, "step": 243 }, { "epoch": 0.0347677400968937, "grad_norm": 3.2686350972610465, "learning_rate": 3.4615384615384617e-06, "loss": 0.6846, "step": 244 }, { "epoch": 0.034910230834995726, "grad_norm": 2.9894255184294143, "learning_rate": 3.4757834757834764e-06, "loss": 0.8553, "step": 245 }, { "epoch": 0.03505272157309775, "grad_norm": 3.2472971748402215, "learning_rate": 3.4900284900284902e-06, "loss": 0.7656, "step": 246 }, { "epoch": 0.03519521231119977, "grad_norm": 3.0645151583983257, "learning_rate": 3.5042735042735045e-06, "loss": 0.8125, "step": 247 }, { "epoch": 0.0353377030493018, "grad_norm": 2.997195426579397, "learning_rate": 3.5185185185185187e-06, "loss": 0.7399, "step": 248 }, { "epoch": 0.035480193787403816, "grad_norm": 3.3478489974136356, "learning_rate": 3.532763532763533e-06, "loss": 0.7444, "step": 249 }, { "epoch": 0.03562268452550584, "grad_norm": 3.6885098243459096, "learning_rate": 3.5470085470085473e-06, "loss": 0.6994, "step": 250 }, { "epoch": 0.03576517526360787, "grad_norm": 3.414426288739171, "learning_rate": 3.5612535612535615e-06, "loss": 0.7907, "step": 251 }, { "epoch": 0.03590766600170989, "grad_norm": 3.029039884456215, "learning_rate": 3.5754985754985762e-06, "loss": 0.6849, "step": 252 }, { "epoch": 0.03605015673981191, "grad_norm": 3.408038780901494, "learning_rate": 3.58974358974359e-06, "loss": 0.7252, "step": 253 }, { "epoch": 0.03619264747791394, "grad_norm": 6.229408348740692, "learning_rate": 3.603988603988604e-06, "loss": 0.8258, "step": 254 }, { "epoch": 0.03633513821601596, "grad_norm": 3.1340094207247247, "learning_rate": 3.6182336182336186e-06, "loss": 0.7453, "step": 255 }, { "epoch": 0.036477628954117984, "grad_norm": 3.1930777344329635, "learning_rate": 3.632478632478633e-06, "loss": 0.771, "step": 256 }, { "epoch": 0.03662011969222, "grad_norm": 3.483629618196097, "learning_rate": 3.646723646723647e-06, "loss": 0.6792, "step": 257 }, { "epoch": 0.03676261043032203, "grad_norm": 3.44892386483572, "learning_rate": 3.6609686609686614e-06, "loss": 0.6976, "step": 258 }, { "epoch": 0.036905101168424055, "grad_norm": 3.5627466243571746, "learning_rate": 3.6752136752136756e-06, "loss": 0.7394, "step": 259 }, { "epoch": 0.037047591906526074, "grad_norm": 3.4279379478474437, "learning_rate": 3.68945868945869e-06, "loss": 0.6665, "step": 260 }, { "epoch": 0.0371900826446281, "grad_norm": 3.4011069331314463, "learning_rate": 3.7037037037037037e-06, "loss": 0.7587, "step": 261 }, { "epoch": 0.03733257338273012, "grad_norm": 3.2854994862881393, "learning_rate": 3.7179487179487184e-06, "loss": 0.7331, "step": 262 }, { "epoch": 0.037475064120832145, "grad_norm": 3.3633990693291462, "learning_rate": 3.7321937321937323e-06, "loss": 0.7135, "step": 263 }, { "epoch": 0.03761755485893417, "grad_norm": 3.216914685244194, "learning_rate": 3.746438746438747e-06, "loss": 0.734, "step": 264 }, { "epoch": 0.03776004559703619, "grad_norm": 3.177820973008209, "learning_rate": 3.760683760683761e-06, "loss": 0.7817, "step": 265 }, { "epoch": 0.037902536335138216, "grad_norm": 3.3467140932661072, "learning_rate": 3.774928774928775e-06, "loss": 0.7297, "step": 266 }, { "epoch": 0.03804502707324024, "grad_norm": 3.206369352192466, "learning_rate": 3.7891737891737893e-06, "loss": 0.7725, "step": 267 }, { "epoch": 0.03818751781134226, "grad_norm": 3.198766028364188, "learning_rate": 3.8034188034188036e-06, "loss": 0.7615, "step": 268 }, { "epoch": 0.03833000854944429, "grad_norm": 3.2619302933057988, "learning_rate": 3.817663817663818e-06, "loss": 0.7704, "step": 269 }, { "epoch": 0.038472499287546306, "grad_norm": 3.5131560079447426, "learning_rate": 3.8319088319088325e-06, "loss": 0.8069, "step": 270 }, { "epoch": 0.03861499002564833, "grad_norm": 2.9049878841594694, "learning_rate": 3.846153846153847e-06, "loss": 0.6433, "step": 271 }, { "epoch": 0.03875748076375036, "grad_norm": 3.1803924162721393, "learning_rate": 3.860398860398861e-06, "loss": 0.7554, "step": 272 }, { "epoch": 0.03889997150185238, "grad_norm": 3.130352646494494, "learning_rate": 3.8746438746438745e-06, "loss": 0.7152, "step": 273 }, { "epoch": 0.039042462239954404, "grad_norm": 3.259867321061896, "learning_rate": 3.88888888888889e-06, "loss": 0.6665, "step": 274 }, { "epoch": 0.03918495297805643, "grad_norm": 3.5040968028949093, "learning_rate": 3.903133903133903e-06, "loss": 0.763, "step": 275 }, { "epoch": 0.03932744371615845, "grad_norm": 3.3363639242546137, "learning_rate": 3.917378917378918e-06, "loss": 0.7226, "step": 276 }, { "epoch": 0.039469934454260475, "grad_norm": 3.3018264742837364, "learning_rate": 3.9316239316239315e-06, "loss": 0.8297, "step": 277 }, { "epoch": 0.039612425192362494, "grad_norm": 3.3133356474848847, "learning_rate": 3.945868945868947e-06, "loss": 0.727, "step": 278 }, { "epoch": 0.03975491593046452, "grad_norm": 3.6807818074180956, "learning_rate": 3.96011396011396e-06, "loss": 0.7762, "step": 279 }, { "epoch": 0.039897406668566546, "grad_norm": 3.959773110737951, "learning_rate": 3.974358974358974e-06, "loss": 0.6776, "step": 280 }, { "epoch": 0.040039897406668565, "grad_norm": 2.9462619143858673, "learning_rate": 3.9886039886039894e-06, "loss": 0.7155, "step": 281 }, { "epoch": 0.04018238814477059, "grad_norm": 2.8543370246744337, "learning_rate": 4.002849002849003e-06, "loss": 0.7392, "step": 282 }, { "epoch": 0.04032487888287261, "grad_norm": 3.354550473132489, "learning_rate": 4.017094017094018e-06, "loss": 0.6802, "step": 283 }, { "epoch": 0.040467369620974636, "grad_norm": 2.821324599192894, "learning_rate": 4.031339031339031e-06, "loss": 0.707, "step": 284 }, { "epoch": 0.04060986035907666, "grad_norm": 2.9673246505991973, "learning_rate": 4.0455840455840465e-06, "loss": 0.6981, "step": 285 }, { "epoch": 0.04075235109717868, "grad_norm": 3.290137824086271, "learning_rate": 4.05982905982906e-06, "loss": 0.7507, "step": 286 }, { "epoch": 0.04089484183528071, "grad_norm": 3.6972929670723813, "learning_rate": 4.074074074074074e-06, "loss": 0.6873, "step": 287 }, { "epoch": 0.04103733257338273, "grad_norm": 3.2219324847319557, "learning_rate": 4.088319088319088e-06, "loss": 0.7591, "step": 288 }, { "epoch": 0.04117982331148475, "grad_norm": 3.48521231742634, "learning_rate": 4.102564102564103e-06, "loss": 0.8462, "step": 289 }, { "epoch": 0.04132231404958678, "grad_norm": 3.001957624923259, "learning_rate": 4.116809116809117e-06, "loss": 0.771, "step": 290 }, { "epoch": 0.0414648047876888, "grad_norm": 3.148219059167559, "learning_rate": 4.131054131054131e-06, "loss": 0.7238, "step": 291 }, { "epoch": 0.04160729552579082, "grad_norm": 2.8368165514588943, "learning_rate": 4.145299145299146e-06, "loss": 0.71, "step": 292 }, { "epoch": 0.04174978626389285, "grad_norm": 3.45606374901211, "learning_rate": 4.15954415954416e-06, "loss": 0.8003, "step": 293 }, { "epoch": 0.04189227700199487, "grad_norm": 3.2488879717888626, "learning_rate": 4.173789173789174e-06, "loss": 0.8034, "step": 294 }, { "epoch": 0.042034767740096894, "grad_norm": 3.2812739735712237, "learning_rate": 4.188034188034188e-06, "loss": 0.7875, "step": 295 }, { "epoch": 0.04217725847819892, "grad_norm": 3.0880917406966355, "learning_rate": 4.2022792022792025e-06, "loss": 0.6593, "step": 296 }, { "epoch": 0.04231974921630094, "grad_norm": 3.4469506826592844, "learning_rate": 4.216524216524217e-06, "loss": 0.639, "step": 297 }, { "epoch": 0.042462239954402965, "grad_norm": 2.855802366748273, "learning_rate": 4.230769230769231e-06, "loss": 0.7032, "step": 298 }, { "epoch": 0.042604730692504984, "grad_norm": 3.0572569125550544, "learning_rate": 4.245014245014245e-06, "loss": 0.6972, "step": 299 }, { "epoch": 0.04274722143060701, "grad_norm": 3.5425393726983763, "learning_rate": 4.2592592592592596e-06, "loss": 0.6454, "step": 300 }, { "epoch": 0.042889712168709036, "grad_norm": 5.2690057440434135, "learning_rate": 4.273504273504274e-06, "loss": 0.6488, "step": 301 }, { "epoch": 0.043032202906811055, "grad_norm": 3.1256492079075606, "learning_rate": 4.287749287749288e-06, "loss": 0.7197, "step": 302 }, { "epoch": 0.04317469364491308, "grad_norm": 3.204537773696315, "learning_rate": 4.301994301994302e-06, "loss": 0.8096, "step": 303 }, { "epoch": 0.04331718438301511, "grad_norm": 3.5624331700005616, "learning_rate": 4.316239316239317e-06, "loss": 0.6225, "step": 304 }, { "epoch": 0.043459675121117126, "grad_norm": 3.1145439532802537, "learning_rate": 4.330484330484331e-06, "loss": 0.7081, "step": 305 }, { "epoch": 0.04360216585921915, "grad_norm": 3.543422384677409, "learning_rate": 4.344729344729345e-06, "loss": 0.7698, "step": 306 }, { "epoch": 0.04374465659732117, "grad_norm": 3.230164851158346, "learning_rate": 4.358974358974359e-06, "loss": 0.7131, "step": 307 }, { "epoch": 0.0438871473354232, "grad_norm": 3.403843126314785, "learning_rate": 4.373219373219374e-06, "loss": 0.7592, "step": 308 }, { "epoch": 0.044029638073525224, "grad_norm": 3.123264209183804, "learning_rate": 4.387464387464388e-06, "loss": 0.6809, "step": 309 }, { "epoch": 0.04417212881162724, "grad_norm": 4.746237279975416, "learning_rate": 4.401709401709402e-06, "loss": 0.8199, "step": 310 }, { "epoch": 0.04431461954972927, "grad_norm": 3.125307381243512, "learning_rate": 4.4159544159544165e-06, "loss": 0.6947, "step": 311 }, { "epoch": 0.04445711028783129, "grad_norm": 3.457970509383978, "learning_rate": 4.430199430199431e-06, "loss": 0.7513, "step": 312 }, { "epoch": 0.044599601025933314, "grad_norm": 3.0319981622563366, "learning_rate": 4.444444444444444e-06, "loss": 0.7109, "step": 313 }, { "epoch": 0.04474209176403534, "grad_norm": 3.523809591584821, "learning_rate": 4.458689458689459e-06, "loss": 0.8303, "step": 314 }, { "epoch": 0.04488458250213736, "grad_norm": 3.3033798439929694, "learning_rate": 4.4729344729344735e-06, "loss": 0.6835, "step": 315 }, { "epoch": 0.045027073240239385, "grad_norm": 3.107948444252176, "learning_rate": 4.487179487179488e-06, "loss": 0.74, "step": 316 }, { "epoch": 0.04516956397834141, "grad_norm": 2.8980343483916418, "learning_rate": 4.501424501424502e-06, "loss": 0.6964, "step": 317 }, { "epoch": 0.04531205471644343, "grad_norm": 3.169764197259851, "learning_rate": 4.515669515669516e-06, "loss": 0.715, "step": 318 }, { "epoch": 0.045454545454545456, "grad_norm": 3.263577340378944, "learning_rate": 4.5299145299145306e-06, "loss": 0.676, "step": 319 }, { "epoch": 0.045597036192647475, "grad_norm": 4.681285172953315, "learning_rate": 4.544159544159544e-06, "loss": 0.7457, "step": 320 }, { "epoch": 0.0457395269307495, "grad_norm": 3.0729043783498264, "learning_rate": 4.558404558404559e-06, "loss": 0.7366, "step": 321 }, { "epoch": 0.04588201766885153, "grad_norm": 3.1001933790242604, "learning_rate": 4.5726495726495725e-06, "loss": 0.8042, "step": 322 }, { "epoch": 0.046024508406953546, "grad_norm": 3.099189620689611, "learning_rate": 4.586894586894588e-06, "loss": 0.7252, "step": 323 }, { "epoch": 0.04616699914505557, "grad_norm": 3.556872085677553, "learning_rate": 4.601139601139601e-06, "loss": 0.6623, "step": 324 }, { "epoch": 0.0463094898831576, "grad_norm": 3.1404180715353656, "learning_rate": 4.615384615384616e-06, "loss": 0.76, "step": 325 }, { "epoch": 0.04645198062125962, "grad_norm": 3.4816470204176824, "learning_rate": 4.62962962962963e-06, "loss": 0.6722, "step": 326 }, { "epoch": 0.04659447135936164, "grad_norm": 3.247621637182805, "learning_rate": 4.643874643874644e-06, "loss": 0.7363, "step": 327 }, { "epoch": 0.04673696209746366, "grad_norm": 3.204408349792765, "learning_rate": 4.658119658119659e-06, "loss": 0.7988, "step": 328 }, { "epoch": 0.04687945283556569, "grad_norm": 3.5693096268386624, "learning_rate": 4.672364672364672e-06, "loss": 0.75, "step": 329 }, { "epoch": 0.047021943573667714, "grad_norm": 3.7646679072173677, "learning_rate": 4.6866096866096875e-06, "loss": 0.709, "step": 330 }, { "epoch": 0.04716443431176973, "grad_norm": 3.0264498831611113, "learning_rate": 4.700854700854701e-06, "loss": 0.8039, "step": 331 }, { "epoch": 0.04730692504987176, "grad_norm": 3.5300085778430565, "learning_rate": 4.715099715099716e-06, "loss": 0.8292, "step": 332 }, { "epoch": 0.04744941578797378, "grad_norm": 3.3439076532614385, "learning_rate": 4.729344729344729e-06, "loss": 0.7689, "step": 333 }, { "epoch": 0.047591906526075804, "grad_norm": 3.899421981002133, "learning_rate": 4.743589743589744e-06, "loss": 0.7849, "step": 334 }, { "epoch": 0.04773439726417783, "grad_norm": 3.529960869012391, "learning_rate": 4.757834757834758e-06, "loss": 0.6919, "step": 335 }, { "epoch": 0.04787688800227985, "grad_norm": 3.3212453855874613, "learning_rate": 4.772079772079772e-06, "loss": 0.7487, "step": 336 }, { "epoch": 0.048019378740381875, "grad_norm": 3.309143435846352, "learning_rate": 4.786324786324787e-06, "loss": 0.706, "step": 337 }, { "epoch": 0.0481618694784839, "grad_norm": 2.8980619816809408, "learning_rate": 4.800569800569801e-06, "loss": 0.7628, "step": 338 }, { "epoch": 0.04830436021658592, "grad_norm": 3.022587428914145, "learning_rate": 4.814814814814815e-06, "loss": 0.7584, "step": 339 }, { "epoch": 0.048446850954687946, "grad_norm": 3.266015041192417, "learning_rate": 4.829059829059829e-06, "loss": 0.783, "step": 340 }, { "epoch": 0.048589341692789965, "grad_norm": 3.0599235634903104, "learning_rate": 4.8433048433048435e-06, "loss": 0.7638, "step": 341 }, { "epoch": 0.04873183243089199, "grad_norm": 3.6453707144112513, "learning_rate": 4.857549857549858e-06, "loss": 0.7849, "step": 342 }, { "epoch": 0.04887432316899402, "grad_norm": 3.887057055582669, "learning_rate": 4.871794871794872e-06, "loss": 0.7628, "step": 343 }, { "epoch": 0.049016813907096037, "grad_norm": 3.0403896465539177, "learning_rate": 4.886039886039886e-06, "loss": 0.7519, "step": 344 }, { "epoch": 0.04915930464519806, "grad_norm": 3.213861947584396, "learning_rate": 4.9002849002849006e-06, "loss": 0.7026, "step": 345 }, { "epoch": 0.04930179538330009, "grad_norm": 2.903254181448724, "learning_rate": 4.914529914529915e-06, "loss": 0.6553, "step": 346 }, { "epoch": 0.04944428612140211, "grad_norm": 3.7079248614225455, "learning_rate": 4.928774928774929e-06, "loss": 0.7327, "step": 347 }, { "epoch": 0.049586776859504134, "grad_norm": 2.8165887495814808, "learning_rate": 4.943019943019943e-06, "loss": 0.8102, "step": 348 }, { "epoch": 0.04972926759760615, "grad_norm": 3.3748732690238303, "learning_rate": 4.957264957264958e-06, "loss": 0.7015, "step": 349 }, { "epoch": 0.04987175833570818, "grad_norm": 3.173443794869743, "learning_rate": 4.971509971509972e-06, "loss": 0.793, "step": 350 }, { "epoch": 0.050014249073810205, "grad_norm": 3.1864026035065094, "learning_rate": 4.985754985754986e-06, "loss": 0.7573, "step": 351 }, { "epoch": 0.050156739811912224, "grad_norm": 3.315259867825777, "learning_rate": 5e-06, "loss": 0.7963, "step": 352 }, { "epoch": 0.05029923055001425, "grad_norm": 2.9947784815826406, "learning_rate": 5.014245014245015e-06, "loss": 0.7487, "step": 353 }, { "epoch": 0.050441721288116276, "grad_norm": 3.071013441572079, "learning_rate": 5.028490028490028e-06, "loss": 0.7063, "step": 354 }, { "epoch": 0.050584212026218295, "grad_norm": 3.1778535135879644, "learning_rate": 5.042735042735043e-06, "loss": 0.7537, "step": 355 }, { "epoch": 0.05072670276432032, "grad_norm": 3.157279298511064, "learning_rate": 5.0569800569800575e-06, "loss": 0.7122, "step": 356 }, { "epoch": 0.05086919350242234, "grad_norm": 3.827180555028948, "learning_rate": 5.071225071225072e-06, "loss": 0.7231, "step": 357 }, { "epoch": 0.051011684240524366, "grad_norm": 3.3873483291727178, "learning_rate": 5.085470085470086e-06, "loss": 0.7016, "step": 358 }, { "epoch": 0.05115417497862639, "grad_norm": 3.220024113286463, "learning_rate": 5.0997150997151e-06, "loss": 0.6255, "step": 359 }, { "epoch": 0.05129666571672841, "grad_norm": 3.1757376533997173, "learning_rate": 5.1139601139601145e-06, "loss": 0.7341, "step": 360 }, { "epoch": 0.05143915645483044, "grad_norm": 2.9532893535843305, "learning_rate": 5.128205128205128e-06, "loss": 0.8434, "step": 361 }, { "epoch": 0.051581647192932456, "grad_norm": 3.1969994772656345, "learning_rate": 5.142450142450143e-06, "loss": 0.7492, "step": 362 }, { "epoch": 0.05172413793103448, "grad_norm": 4.187990125260131, "learning_rate": 5.156695156695157e-06, "loss": 0.7151, "step": 363 }, { "epoch": 0.05186662866913651, "grad_norm": 2.9968108827069266, "learning_rate": 5.1709401709401716e-06, "loss": 0.7224, "step": 364 }, { "epoch": 0.05200911940723853, "grad_norm": 3.0985855362071586, "learning_rate": 5.185185185185185e-06, "loss": 0.7146, "step": 365 }, { "epoch": 0.05215161014534055, "grad_norm": 2.9460109655043545, "learning_rate": 5.1994301994302e-06, "loss": 0.7407, "step": 366 }, { "epoch": 0.05229410088344258, "grad_norm": 2.890870835169928, "learning_rate": 5.213675213675214e-06, "loss": 0.6475, "step": 367 }, { "epoch": 0.0524365916215446, "grad_norm": 4.787743799576897, "learning_rate": 5.227920227920228e-06, "loss": 0.6898, "step": 368 }, { "epoch": 0.052579082359646624, "grad_norm": 3.033092593960332, "learning_rate": 5.242165242165243e-06, "loss": 0.6897, "step": 369 }, { "epoch": 0.05272157309774864, "grad_norm": 2.993687663770682, "learning_rate": 5.256410256410257e-06, "loss": 0.6918, "step": 370 }, { "epoch": 0.05286406383585067, "grad_norm": 3.213431825834363, "learning_rate": 5.270655270655271e-06, "loss": 0.6529, "step": 371 }, { "epoch": 0.053006554573952695, "grad_norm": 2.996703759764305, "learning_rate": 5.284900284900285e-06, "loss": 0.7009, "step": 372 }, { "epoch": 0.053149045312054714, "grad_norm": 3.4078725617369057, "learning_rate": 5.2991452991453e-06, "loss": 0.73, "step": 373 }, { "epoch": 0.05329153605015674, "grad_norm": 3.3952652621774435, "learning_rate": 5.313390313390314e-06, "loss": 0.6474, "step": 374 }, { "epoch": 0.053434026788258766, "grad_norm": 3.470682701023208, "learning_rate": 5.327635327635328e-06, "loss": 0.7284, "step": 375 }, { "epoch": 0.053576517526360785, "grad_norm": 3.180093225491522, "learning_rate": 5.341880341880342e-06, "loss": 0.6582, "step": 376 }, { "epoch": 0.05371900826446281, "grad_norm": 3.3775071309089864, "learning_rate": 5.356125356125357e-06, "loss": 0.7074, "step": 377 }, { "epoch": 0.05386149900256483, "grad_norm": 3.613075562234947, "learning_rate": 5.370370370370371e-06, "loss": 0.6629, "step": 378 }, { "epoch": 0.054003989740666856, "grad_norm": 2.9773487419311095, "learning_rate": 5.384615384615385e-06, "loss": 0.6935, "step": 379 }, { "epoch": 0.05414648047876888, "grad_norm": 3.2674825011307154, "learning_rate": 5.3988603988604e-06, "loss": 0.7703, "step": 380 }, { "epoch": 0.0542889712168709, "grad_norm": 3.0555488491008203, "learning_rate": 5.413105413105414e-06, "loss": 0.6791, "step": 381 }, { "epoch": 0.05443146195497293, "grad_norm": 2.99505237977203, "learning_rate": 5.4273504273504275e-06, "loss": 0.6692, "step": 382 }, { "epoch": 0.054573952693074954, "grad_norm": 3.3493895126629, "learning_rate": 5.441595441595442e-06, "loss": 0.7438, "step": 383 }, { "epoch": 0.05471644343117697, "grad_norm": 3.020704579138723, "learning_rate": 5.455840455840457e-06, "loss": 0.739, "step": 384 }, { "epoch": 0.054858934169279, "grad_norm": 2.875382657497656, "learning_rate": 5.470085470085471e-06, "loss": 0.7372, "step": 385 }, { "epoch": 0.05500142490738102, "grad_norm": 2.98857005103632, "learning_rate": 5.4843304843304845e-06, "loss": 0.7131, "step": 386 }, { "epoch": 0.055143915645483044, "grad_norm": 3.126320366882102, "learning_rate": 5.498575498575499e-06, "loss": 0.7336, "step": 387 }, { "epoch": 0.05528640638358507, "grad_norm": 3.1712885167881497, "learning_rate": 5.512820512820514e-06, "loss": 0.8019, "step": 388 }, { "epoch": 0.05542889712168709, "grad_norm": 3.503730174320255, "learning_rate": 5.527065527065527e-06, "loss": 0.7742, "step": 389 }, { "epoch": 0.055571387859789115, "grad_norm": 2.8527930387383362, "learning_rate": 5.5413105413105416e-06, "loss": 0.7377, "step": 390 }, { "epoch": 0.055713878597891134, "grad_norm": 3.081753797274145, "learning_rate": 5.555555555555557e-06, "loss": 0.7175, "step": 391 }, { "epoch": 0.05585636933599316, "grad_norm": 3.2833263853707697, "learning_rate": 5.56980056980057e-06, "loss": 0.6337, "step": 392 }, { "epoch": 0.055998860074095186, "grad_norm": 3.0159408151553406, "learning_rate": 5.584045584045584e-06, "loss": 0.6723, "step": 393 }, { "epoch": 0.056141350812197205, "grad_norm": 3.5797888978843795, "learning_rate": 5.598290598290599e-06, "loss": 0.7338, "step": 394 }, { "epoch": 0.05628384155029923, "grad_norm": 3.871421030374268, "learning_rate": 5.612535612535614e-06, "loss": 0.6433, "step": 395 }, { "epoch": 0.05642633228840126, "grad_norm": 4.569552625900308, "learning_rate": 5.626780626780627e-06, "loss": 0.7072, "step": 396 }, { "epoch": 0.056568823026503276, "grad_norm": 3.6652659356968496, "learning_rate": 5.641025641025641e-06, "loss": 0.7408, "step": 397 }, { "epoch": 0.0567113137646053, "grad_norm": 3.796500232225144, "learning_rate": 5.655270655270656e-06, "loss": 0.78, "step": 398 }, { "epoch": 0.05685380450270732, "grad_norm": 4.175897067830801, "learning_rate": 5.669515669515669e-06, "loss": 0.668, "step": 399 }, { "epoch": 0.05699629524080935, "grad_norm": 3.5141138301591526, "learning_rate": 5.683760683760684e-06, "loss": 0.6804, "step": 400 }, { "epoch": 0.05713878597891137, "grad_norm": 3.0192833856725563, "learning_rate": 5.6980056980056985e-06, "loss": 0.6681, "step": 401 }, { "epoch": 0.05728127671701339, "grad_norm": 3.2081290351941503, "learning_rate": 5.7122507122507136e-06, "loss": 0.7623, "step": 402 }, { "epoch": 0.05742376745511542, "grad_norm": 2.926939179958309, "learning_rate": 5.726495726495727e-06, "loss": 0.6662, "step": 403 }, { "epoch": 0.057566258193217444, "grad_norm": 3.149919164666255, "learning_rate": 5.740740740740741e-06, "loss": 0.6985, "step": 404 }, { "epoch": 0.05770874893131946, "grad_norm": 3.2721715142380896, "learning_rate": 5.7549857549857555e-06, "loss": 0.7257, "step": 405 }, { "epoch": 0.05785123966942149, "grad_norm": 3.3882478751957184, "learning_rate": 5.769230769230769e-06, "loss": 0.7656, "step": 406 }, { "epoch": 0.05799373040752351, "grad_norm": 3.6497506683648813, "learning_rate": 5.783475783475784e-06, "loss": 0.7369, "step": 407 }, { "epoch": 0.058136221145625534, "grad_norm": 6.174297778905327, "learning_rate": 5.797720797720798e-06, "loss": 0.7094, "step": 408 }, { "epoch": 0.05827871188372756, "grad_norm": 3.035581613069742, "learning_rate": 5.8119658119658126e-06, "loss": 0.6525, "step": 409 }, { "epoch": 0.05842120262182958, "grad_norm": 2.874189566892807, "learning_rate": 5.826210826210826e-06, "loss": 0.6846, "step": 410 }, { "epoch": 0.058563693359931605, "grad_norm": 3.1399460257905667, "learning_rate": 5.840455840455841e-06, "loss": 0.6369, "step": 411 }, { "epoch": 0.058706184098033624, "grad_norm": 3.5969900069289436, "learning_rate": 5.854700854700855e-06, "loss": 0.6858, "step": 412 }, { "epoch": 0.05884867483613565, "grad_norm": 3.052769513904413, "learning_rate": 5.868945868945869e-06, "loss": 0.7287, "step": 413 }, { "epoch": 0.058991165574237676, "grad_norm": 2.959510414476829, "learning_rate": 5.883190883190884e-06, "loss": 0.7308, "step": 414 }, { "epoch": 0.059133656312339695, "grad_norm": 3.4198832055841093, "learning_rate": 5.897435897435898e-06, "loss": 0.717, "step": 415 }, { "epoch": 0.05927614705044172, "grad_norm": 4.049002056724144, "learning_rate": 5.911680911680912e-06, "loss": 0.6505, "step": 416 }, { "epoch": 0.05941863778854375, "grad_norm": 13.344651839524508, "learning_rate": 5.925925925925926e-06, "loss": 0.7256, "step": 417 }, { "epoch": 0.05956112852664577, "grad_norm": 3.52624313626056, "learning_rate": 5.940170940170941e-06, "loss": 0.8847, "step": 418 }, { "epoch": 0.05970361926474779, "grad_norm": 3.1503801545144055, "learning_rate": 5.954415954415955e-06, "loss": 0.7011, "step": 419 }, { "epoch": 0.05984611000284981, "grad_norm": 2.9658796763483743, "learning_rate": 5.968660968660969e-06, "loss": 0.7176, "step": 420 }, { "epoch": 0.05998860074095184, "grad_norm": 2.957190398643039, "learning_rate": 5.982905982905983e-06, "loss": 0.7448, "step": 421 }, { "epoch": 0.060131091479053864, "grad_norm": 3.597718896824828, "learning_rate": 5.997150997150998e-06, "loss": 0.7649, "step": 422 }, { "epoch": 0.06027358221715588, "grad_norm": 5.212360889774992, "learning_rate": 6.011396011396012e-06, "loss": 0.7356, "step": 423 }, { "epoch": 0.06041607295525791, "grad_norm": 3.1597002694870495, "learning_rate": 6.025641025641026e-06, "loss": 0.7724, "step": 424 }, { "epoch": 0.060558563693359935, "grad_norm": 2.969428251094122, "learning_rate": 6.039886039886041e-06, "loss": 0.8206, "step": 425 }, { "epoch": 0.060701054431461954, "grad_norm": 6.527395679320453, "learning_rate": 6.054131054131055e-06, "loss": 0.594, "step": 426 }, { "epoch": 0.06084354516956398, "grad_norm": 2.8957854676537496, "learning_rate": 6.0683760683760684e-06, "loss": 0.7364, "step": 427 }, { "epoch": 0.060986035907666, "grad_norm": 3.6849526979380713, "learning_rate": 6.082621082621083e-06, "loss": 0.7144, "step": 428 }, { "epoch": 0.061128526645768025, "grad_norm": 2.8677564175206838, "learning_rate": 6.096866096866098e-06, "loss": 0.6856, "step": 429 }, { "epoch": 0.06127101738387005, "grad_norm": 3.274381800322499, "learning_rate": 6.111111111111112e-06, "loss": 0.7557, "step": 430 }, { "epoch": 0.06141350812197207, "grad_norm": 5.417765175257785, "learning_rate": 6.1253561253561255e-06, "loss": 0.7938, "step": 431 }, { "epoch": 0.061555998860074096, "grad_norm": 3.5116598383896096, "learning_rate": 6.13960113960114e-06, "loss": 0.6871, "step": 432 }, { "epoch": 0.06169848959817612, "grad_norm": 3.2671718081849868, "learning_rate": 6.153846153846155e-06, "loss": 0.7409, "step": 433 }, { "epoch": 0.06184098033627814, "grad_norm": 2.925252259142536, "learning_rate": 6.168091168091168e-06, "loss": 0.7116, "step": 434 }, { "epoch": 0.06198347107438017, "grad_norm": 4.864114540239264, "learning_rate": 6.1823361823361825e-06, "loss": 0.7277, "step": 435 }, { "epoch": 0.062125961812482186, "grad_norm": 3.426913917758871, "learning_rate": 6.196581196581198e-06, "loss": 0.7113, "step": 436 }, { "epoch": 0.06226845255058421, "grad_norm": 3.5007213309749474, "learning_rate": 6.210826210826212e-06, "loss": 0.745, "step": 437 }, { "epoch": 0.06241094328868624, "grad_norm": 3.1574484071468216, "learning_rate": 6.225071225071225e-06, "loss": 0.6985, "step": 438 }, { "epoch": 0.06255343402678826, "grad_norm": 3.2724142432029137, "learning_rate": 6.23931623931624e-06, "loss": 0.6765, "step": 439 }, { "epoch": 0.06269592476489028, "grad_norm": 2.926015622605394, "learning_rate": 6.253561253561255e-06, "loss": 0.7607, "step": 440 }, { "epoch": 0.06283841550299231, "grad_norm": 3.329404612017595, "learning_rate": 6.267806267806268e-06, "loss": 0.7522, "step": 441 }, { "epoch": 0.06298090624109433, "grad_norm": 3.3844533284943945, "learning_rate": 6.282051282051282e-06, "loss": 0.7325, "step": 442 }, { "epoch": 0.06312339697919635, "grad_norm": 3.0094951195484247, "learning_rate": 6.296296296296297e-06, "loss": 0.6983, "step": 443 }, { "epoch": 0.06326588771729838, "grad_norm": 3.637387682724253, "learning_rate": 6.310541310541312e-06, "loss": 0.7441, "step": 444 }, { "epoch": 0.0634083784554004, "grad_norm": 2.949846294637682, "learning_rate": 6.324786324786325e-06, "loss": 0.6962, "step": 445 }, { "epoch": 0.06355086919350242, "grad_norm": 3.0874238563196084, "learning_rate": 6.3390313390313394e-06, "loss": 0.8091, "step": 446 }, { "epoch": 0.06369335993160445, "grad_norm": 4.359071467769291, "learning_rate": 6.3532763532763546e-06, "loss": 0.7119, "step": 447 }, { "epoch": 0.06383585066970647, "grad_norm": 3.6942144960427057, "learning_rate": 6.367521367521368e-06, "loss": 0.6602, "step": 448 }, { "epoch": 0.06397834140780849, "grad_norm": 3.194444848296068, "learning_rate": 6.381766381766382e-06, "loss": 0.7112, "step": 449 }, { "epoch": 0.06412083214591052, "grad_norm": 3.1701746264923525, "learning_rate": 6.3960113960113965e-06, "loss": 0.7328, "step": 450 }, { "epoch": 0.06426332288401254, "grad_norm": 2.9759923392866106, "learning_rate": 6.410256410256412e-06, "loss": 0.6796, "step": 451 }, { "epoch": 0.06440581362211456, "grad_norm": 3.013627709453202, "learning_rate": 6.424501424501425e-06, "loss": 0.7778, "step": 452 }, { "epoch": 0.06454830436021658, "grad_norm": 2.9990800405224554, "learning_rate": 6.438746438746439e-06, "loss": 0.6937, "step": 453 }, { "epoch": 0.06469079509831861, "grad_norm": 3.2981440717875383, "learning_rate": 6.4529914529914535e-06, "loss": 0.6996, "step": 454 }, { "epoch": 0.06483328583642063, "grad_norm": 3.29619794758151, "learning_rate": 6.467236467236467e-06, "loss": 0.7229, "step": 455 }, { "epoch": 0.06497577657452265, "grad_norm": 2.884920900880022, "learning_rate": 6.481481481481482e-06, "loss": 0.792, "step": 456 }, { "epoch": 0.06511826731262468, "grad_norm": 2.699242837296372, "learning_rate": 6.495726495726496e-06, "loss": 0.6634, "step": 457 }, { "epoch": 0.0652607580507267, "grad_norm": 2.852439445231008, "learning_rate": 6.50997150997151e-06, "loss": 0.7361, "step": 458 }, { "epoch": 0.06540324878882872, "grad_norm": 2.9066610132760324, "learning_rate": 6.524216524216525e-06, "loss": 0.6914, "step": 459 }, { "epoch": 0.06554573952693075, "grad_norm": 2.756931897161034, "learning_rate": 6.538461538461539e-06, "loss": 0.8089, "step": 460 }, { "epoch": 0.06568823026503277, "grad_norm": 2.971761020848845, "learning_rate": 6.552706552706553e-06, "loss": 0.7509, "step": 461 }, { "epoch": 0.06583072100313479, "grad_norm": 3.5602438958236378, "learning_rate": 6.566951566951567e-06, "loss": 0.711, "step": 462 }, { "epoch": 0.06597321174123683, "grad_norm": 3.0631293246715035, "learning_rate": 6.581196581196582e-06, "loss": 0.7603, "step": 463 }, { "epoch": 0.06611570247933884, "grad_norm": 2.8659526995392266, "learning_rate": 6.595441595441596e-06, "loss": 0.7219, "step": 464 }, { "epoch": 0.06625819321744086, "grad_norm": 3.291562622850939, "learning_rate": 6.60968660968661e-06, "loss": 0.6184, "step": 465 }, { "epoch": 0.06640068395554288, "grad_norm": 3.0544353429306934, "learning_rate": 6.623931623931624e-06, "loss": 0.7704, "step": 466 }, { "epoch": 0.06654317469364492, "grad_norm": 2.6497702759697326, "learning_rate": 6.638176638176639e-06, "loss": 0.744, "step": 467 }, { "epoch": 0.06668566543174693, "grad_norm": 2.94978105545108, "learning_rate": 6.652421652421653e-06, "loss": 0.6825, "step": 468 }, { "epoch": 0.06682815616984895, "grad_norm": 3.312385899489317, "learning_rate": 6.666666666666667e-06, "loss": 0.7121, "step": 469 }, { "epoch": 0.06697064690795099, "grad_norm": 2.898445392573557, "learning_rate": 6.680911680911682e-06, "loss": 0.6821, "step": 470 }, { "epoch": 0.067113137646053, "grad_norm": 2.595417253578255, "learning_rate": 6.695156695156696e-06, "loss": 0.7105, "step": 471 }, { "epoch": 0.06725562838415503, "grad_norm": 3.7932630240253693, "learning_rate": 6.7094017094017094e-06, "loss": 0.788, "step": 472 }, { "epoch": 0.06739811912225706, "grad_norm": 3.0209455335336135, "learning_rate": 6.723646723646724e-06, "loss": 0.7359, "step": 473 }, { "epoch": 0.06754060986035908, "grad_norm": 3.068505641300396, "learning_rate": 6.737891737891739e-06, "loss": 0.756, "step": 474 }, { "epoch": 0.0676831005984611, "grad_norm": 2.9369803393245997, "learning_rate": 6.752136752136753e-06, "loss": 0.7095, "step": 475 }, { "epoch": 0.06782559133656313, "grad_norm": 2.7555381469982527, "learning_rate": 6.7663817663817665e-06, "loss": 0.6475, "step": 476 }, { "epoch": 0.06796808207466515, "grad_norm": 2.959714963874515, "learning_rate": 6.780626780626781e-06, "loss": 0.6397, "step": 477 }, { "epoch": 0.06811057281276717, "grad_norm": 3.2850324990459265, "learning_rate": 6.794871794871796e-06, "loss": 0.7655, "step": 478 }, { "epoch": 0.0682530635508692, "grad_norm": 2.8918342235517556, "learning_rate": 6.809116809116809e-06, "loss": 0.6914, "step": 479 }, { "epoch": 0.06839555428897122, "grad_norm": 3.0991667788748063, "learning_rate": 6.8233618233618235e-06, "loss": 0.7335, "step": 480 }, { "epoch": 0.06853804502707324, "grad_norm": 2.6217453542340956, "learning_rate": 6.837606837606839e-06, "loss": 0.7053, "step": 481 }, { "epoch": 0.06868053576517526, "grad_norm": 2.917234605580598, "learning_rate": 6.851851851851853e-06, "loss": 0.7185, "step": 482 }, { "epoch": 0.06882302650327729, "grad_norm": 2.9925231739712173, "learning_rate": 6.866096866096866e-06, "loss": 0.7428, "step": 483 }, { "epoch": 0.06896551724137931, "grad_norm": 2.6324133795974847, "learning_rate": 6.880341880341881e-06, "loss": 0.6802, "step": 484 }, { "epoch": 0.06910800797948133, "grad_norm": 2.6510553422352663, "learning_rate": 6.894586894586896e-06, "loss": 0.69, "step": 485 }, { "epoch": 0.06925049871758336, "grad_norm": 2.8816413624510386, "learning_rate": 6.908831908831909e-06, "loss": 0.7637, "step": 486 }, { "epoch": 0.06939298945568538, "grad_norm": 2.957026956216249, "learning_rate": 6.923076923076923e-06, "loss": 0.7254, "step": 487 }, { "epoch": 0.0695354801937874, "grad_norm": 2.7099839006254283, "learning_rate": 6.937321937321938e-06, "loss": 0.7378, "step": 488 }, { "epoch": 0.06967797093188943, "grad_norm": 2.751997261356077, "learning_rate": 6.951566951566953e-06, "loss": 0.6757, "step": 489 }, { "epoch": 0.06982046166999145, "grad_norm": 2.7714252095649896, "learning_rate": 6.965811965811966e-06, "loss": 0.7766, "step": 490 }, { "epoch": 0.06996295240809347, "grad_norm": 3.7116944861702055, "learning_rate": 6.9800569800569804e-06, "loss": 0.7425, "step": 491 }, { "epoch": 0.0701054431461955, "grad_norm": 2.9535772291861413, "learning_rate": 6.9943019943019955e-06, "loss": 0.6973, "step": 492 }, { "epoch": 0.07024793388429752, "grad_norm": 2.9439475421787424, "learning_rate": 7.008547008547009e-06, "loss": 0.7205, "step": 493 }, { "epoch": 0.07039042462239954, "grad_norm": 3.2701207646100623, "learning_rate": 7.022792022792023e-06, "loss": 0.7246, "step": 494 }, { "epoch": 0.07053291536050156, "grad_norm": 2.6442718167589003, "learning_rate": 7.0370370370370375e-06, "loss": 0.6883, "step": 495 }, { "epoch": 0.0706754060986036, "grad_norm": 3.0243540138978804, "learning_rate": 7.051282051282053e-06, "loss": 0.6756, "step": 496 }, { "epoch": 0.07081789683670561, "grad_norm": 2.920917778716643, "learning_rate": 7.065527065527066e-06, "loss": 0.6555, "step": 497 }, { "epoch": 0.07096038757480763, "grad_norm": 6.393334858140783, "learning_rate": 7.07977207977208e-06, "loss": 0.725, "step": 498 }, { "epoch": 0.07110287831290966, "grad_norm": 2.727165078965002, "learning_rate": 7.0940170940170945e-06, "loss": 0.6958, "step": 499 }, { "epoch": 0.07124536905101168, "grad_norm": 3.0396671815175025, "learning_rate": 7.108262108262109e-06, "loss": 0.7169, "step": 500 }, { "epoch": 0.0713878597891137, "grad_norm": 3.3634091055355215, "learning_rate": 7.122507122507123e-06, "loss": 0.7836, "step": 501 }, { "epoch": 0.07153035052721574, "grad_norm": 2.7222162935316754, "learning_rate": 7.136752136752137e-06, "loss": 0.7349, "step": 502 }, { "epoch": 0.07167284126531775, "grad_norm": 3.0749826395088538, "learning_rate": 7.1509971509971524e-06, "loss": 0.6454, "step": 503 }, { "epoch": 0.07181533200341977, "grad_norm": 2.8999580727680514, "learning_rate": 7.165242165242166e-06, "loss": 0.6593, "step": 504 }, { "epoch": 0.0719578227415218, "grad_norm": 2.877485659881208, "learning_rate": 7.17948717948718e-06, "loss": 0.7177, "step": 505 }, { "epoch": 0.07210031347962383, "grad_norm": 3.217865060864709, "learning_rate": 7.193732193732194e-06, "loss": 0.6933, "step": 506 }, { "epoch": 0.07224280421772585, "grad_norm": 3.052319024808623, "learning_rate": 7.207977207977208e-06, "loss": 0.7476, "step": 507 }, { "epoch": 0.07238529495582788, "grad_norm": 2.735312048421727, "learning_rate": 7.222222222222223e-06, "loss": 0.765, "step": 508 }, { "epoch": 0.0725277856939299, "grad_norm": 2.926292937202078, "learning_rate": 7.236467236467237e-06, "loss": 0.7509, "step": 509 }, { "epoch": 0.07267027643203192, "grad_norm": 2.746124820212095, "learning_rate": 7.2507122507122514e-06, "loss": 0.7689, "step": 510 }, { "epoch": 0.07281276717013394, "grad_norm": 3.015662400044505, "learning_rate": 7.264957264957266e-06, "loss": 0.7706, "step": 511 }, { "epoch": 0.07295525790823597, "grad_norm": 2.901817079337981, "learning_rate": 7.27920227920228e-06, "loss": 0.7061, "step": 512 }, { "epoch": 0.07309774864633799, "grad_norm": 3.2404524713443528, "learning_rate": 7.293447293447294e-06, "loss": 0.6986, "step": 513 }, { "epoch": 0.07324023938444, "grad_norm": 2.847518151521893, "learning_rate": 7.307692307692308e-06, "loss": 0.7215, "step": 514 }, { "epoch": 0.07338273012254204, "grad_norm": 2.8641356140247467, "learning_rate": 7.321937321937323e-06, "loss": 0.6931, "step": 515 }, { "epoch": 0.07352522086064406, "grad_norm": 3.4398723610892774, "learning_rate": 7.336182336182337e-06, "loss": 0.7198, "step": 516 }, { "epoch": 0.07366771159874608, "grad_norm": 3.3134586662007357, "learning_rate": 7.350427350427351e-06, "loss": 0.6945, "step": 517 }, { "epoch": 0.07381020233684811, "grad_norm": 3.0903419802466514, "learning_rate": 7.364672364672365e-06, "loss": 0.6875, "step": 518 }, { "epoch": 0.07395269307495013, "grad_norm": 2.577305686444157, "learning_rate": 7.37891737891738e-06, "loss": 0.6967, "step": 519 }, { "epoch": 0.07409518381305215, "grad_norm": 2.656553740694208, "learning_rate": 7.393162393162394e-06, "loss": 0.738, "step": 520 }, { "epoch": 0.07423767455115418, "grad_norm": 2.959370438710984, "learning_rate": 7.4074074074074075e-06, "loss": 0.7341, "step": 521 }, { "epoch": 0.0743801652892562, "grad_norm": 2.8332673002536146, "learning_rate": 7.421652421652423e-06, "loss": 0.6832, "step": 522 }, { "epoch": 0.07452265602735822, "grad_norm": 13.287996129965707, "learning_rate": 7.435897435897437e-06, "loss": 0.7849, "step": 523 }, { "epoch": 0.07466514676546024, "grad_norm": 2.7321920534970734, "learning_rate": 7.450142450142451e-06, "loss": 0.65, "step": 524 }, { "epoch": 0.07480763750356227, "grad_norm": 2.7176732873920346, "learning_rate": 7.4643874643874645e-06, "loss": 0.7837, "step": 525 }, { "epoch": 0.07495012824166429, "grad_norm": 2.4025714761972585, "learning_rate": 7.47863247863248e-06, "loss": 0.759, "step": 526 }, { "epoch": 0.07509261897976631, "grad_norm": 3.304267923860555, "learning_rate": 7.492877492877494e-06, "loss": 0.7248, "step": 527 }, { "epoch": 0.07523510971786834, "grad_norm": 3.4313494458779448, "learning_rate": 7.507122507122507e-06, "loss": 0.7196, "step": 528 }, { "epoch": 0.07537760045597036, "grad_norm": 2.719588954210084, "learning_rate": 7.521367521367522e-06, "loss": 0.6864, "step": 529 }, { "epoch": 0.07552009119407238, "grad_norm": 2.9059744987654894, "learning_rate": 7.535612535612537e-06, "loss": 0.6676, "step": 530 }, { "epoch": 0.07566258193217441, "grad_norm": 2.609066061320428, "learning_rate": 7.54985754985755e-06, "loss": 0.6984, "step": 531 }, { "epoch": 0.07580507267027643, "grad_norm": 5.874986585276126, "learning_rate": 7.564102564102564e-06, "loss": 0.6849, "step": 532 }, { "epoch": 0.07594756340837845, "grad_norm": 2.9422750924510273, "learning_rate": 7.578347578347579e-06, "loss": 0.7602, "step": 533 }, { "epoch": 0.07609005414648048, "grad_norm": 2.6719241347096756, "learning_rate": 7.592592592592594e-06, "loss": 0.7429, "step": 534 }, { "epoch": 0.0762325448845825, "grad_norm": 3.0844793771420917, "learning_rate": 7.606837606837607e-06, "loss": 0.7773, "step": 535 }, { "epoch": 0.07637503562268452, "grad_norm": 2.76297721378024, "learning_rate": 7.6210826210826214e-06, "loss": 0.6711, "step": 536 }, { "epoch": 0.07651752636078656, "grad_norm": 2.8206952235180975, "learning_rate": 7.635327635327637e-06, "loss": 0.7021, "step": 537 }, { "epoch": 0.07666001709888857, "grad_norm": 2.623952567312783, "learning_rate": 7.649572649572649e-06, "loss": 0.6823, "step": 538 }, { "epoch": 0.0768025078369906, "grad_norm": 3.0775796147012717, "learning_rate": 7.663817663817665e-06, "loss": 0.7076, "step": 539 }, { "epoch": 0.07694499857509261, "grad_norm": 2.643089741009517, "learning_rate": 7.67806267806268e-06, "loss": 0.7578, "step": 540 }, { "epoch": 0.07708748931319465, "grad_norm": 2.8815430183001713, "learning_rate": 7.692307692307694e-06, "loss": 0.7626, "step": 541 }, { "epoch": 0.07722998005129666, "grad_norm": 2.9887228146880873, "learning_rate": 7.706552706552706e-06, "loss": 0.7725, "step": 542 }, { "epoch": 0.07737247078939868, "grad_norm": 2.699115158545873, "learning_rate": 7.720797720797722e-06, "loss": 0.6952, "step": 543 }, { "epoch": 0.07751496152750072, "grad_norm": 2.8590368465039786, "learning_rate": 7.735042735042736e-06, "loss": 0.6647, "step": 544 }, { "epoch": 0.07765745226560274, "grad_norm": 2.8766530134039536, "learning_rate": 7.749287749287749e-06, "loss": 0.7293, "step": 545 }, { "epoch": 0.07779994300370476, "grad_norm": 2.9321465357011265, "learning_rate": 7.763532763532763e-06, "loss": 0.7521, "step": 546 }, { "epoch": 0.07794243374180679, "grad_norm": 2.7736523480843074, "learning_rate": 7.77777777777778e-06, "loss": 0.7322, "step": 547 }, { "epoch": 0.07808492447990881, "grad_norm": 2.543775028519797, "learning_rate": 7.792022792022793e-06, "loss": 0.6903, "step": 548 }, { "epoch": 0.07822741521801083, "grad_norm": 2.978302146288927, "learning_rate": 7.806267806267806e-06, "loss": 0.7964, "step": 549 }, { "epoch": 0.07836990595611286, "grad_norm": 2.852551745830911, "learning_rate": 7.820512820512822e-06, "loss": 0.7534, "step": 550 }, { "epoch": 0.07851239669421488, "grad_norm": 2.927764055654255, "learning_rate": 7.834757834757836e-06, "loss": 0.7125, "step": 551 }, { "epoch": 0.0786548874323169, "grad_norm": 3.186419845480123, "learning_rate": 7.849002849002849e-06, "loss": 0.8385, "step": 552 }, { "epoch": 0.07879737817041892, "grad_norm": 3.0016987731272495, "learning_rate": 7.863247863247863e-06, "loss": 0.7432, "step": 553 }, { "epoch": 0.07893986890852095, "grad_norm": 2.62628030339659, "learning_rate": 7.877492877492879e-06, "loss": 0.6902, "step": 554 }, { "epoch": 0.07908235964662297, "grad_norm": 3.000441845047228, "learning_rate": 7.891737891737893e-06, "loss": 0.7556, "step": 555 }, { "epoch": 0.07922485038472499, "grad_norm": 2.462355232532047, "learning_rate": 7.905982905982906e-06, "loss": 0.7661, "step": 556 }, { "epoch": 0.07936734112282702, "grad_norm": 2.4037623835622566, "learning_rate": 7.92022792022792e-06, "loss": 0.6648, "step": 557 }, { "epoch": 0.07950983186092904, "grad_norm": 3.2139784444401136, "learning_rate": 7.934472934472936e-06, "loss": 0.7026, "step": 558 }, { "epoch": 0.07965232259903106, "grad_norm": 2.7751450470621166, "learning_rate": 7.948717948717949e-06, "loss": 0.8677, "step": 559 }, { "epoch": 0.07979481333713309, "grad_norm": 3.0455344862996503, "learning_rate": 7.962962962962963e-06, "loss": 0.6981, "step": 560 }, { "epoch": 0.07993730407523511, "grad_norm": 2.746550138953799, "learning_rate": 7.977207977207979e-06, "loss": 0.7014, "step": 561 }, { "epoch": 0.08007979481333713, "grad_norm": 3.0456037171791976, "learning_rate": 7.991452991452993e-06, "loss": 0.7234, "step": 562 }, { "epoch": 0.08022228555143916, "grad_norm": 2.751388045377254, "learning_rate": 8.005698005698006e-06, "loss": 0.7292, "step": 563 }, { "epoch": 0.08036477628954118, "grad_norm": 3.2558053382316756, "learning_rate": 8.01994301994302e-06, "loss": 0.7365, "step": 564 }, { "epoch": 0.0805072670276432, "grad_norm": 2.8116397477579897, "learning_rate": 8.034188034188036e-06, "loss": 0.7806, "step": 565 }, { "epoch": 0.08064975776574522, "grad_norm": 3.422610175566564, "learning_rate": 8.048433048433048e-06, "loss": 0.7151, "step": 566 }, { "epoch": 0.08079224850384725, "grad_norm": 6.301567945365353, "learning_rate": 8.062678062678063e-06, "loss": 0.6777, "step": 567 }, { "epoch": 0.08093473924194927, "grad_norm": 3.385708722651322, "learning_rate": 8.076923076923077e-06, "loss": 0.6869, "step": 568 }, { "epoch": 0.08107722998005129, "grad_norm": 3.4836661937292415, "learning_rate": 8.091168091168093e-06, "loss": 0.6967, "step": 569 }, { "epoch": 0.08121972071815332, "grad_norm": 3.0709972564503234, "learning_rate": 8.105413105413106e-06, "loss": 0.7826, "step": 570 }, { "epoch": 0.08136221145625534, "grad_norm": 3.1075561338035804, "learning_rate": 8.11965811965812e-06, "loss": 0.756, "step": 571 }, { "epoch": 0.08150470219435736, "grad_norm": 3.1940969303149838, "learning_rate": 8.133903133903136e-06, "loss": 0.7236, "step": 572 }, { "epoch": 0.0816471929324594, "grad_norm": 3.282650883020139, "learning_rate": 8.148148148148148e-06, "loss": 0.778, "step": 573 }, { "epoch": 0.08178968367056141, "grad_norm": 3.4121805064288036, "learning_rate": 8.162393162393163e-06, "loss": 0.6878, "step": 574 }, { "epoch": 0.08193217440866343, "grad_norm": 2.9410962739353868, "learning_rate": 8.176638176638177e-06, "loss": 0.7442, "step": 575 }, { "epoch": 0.08207466514676547, "grad_norm": 3.665750120768833, "learning_rate": 8.190883190883193e-06, "loss": 0.8031, "step": 576 }, { "epoch": 0.08221715588486748, "grad_norm": 3.34806048888675, "learning_rate": 8.205128205128205e-06, "loss": 0.7368, "step": 577 }, { "epoch": 0.0823596466229695, "grad_norm": 3.3057914010505827, "learning_rate": 8.21937321937322e-06, "loss": 0.7162, "step": 578 }, { "epoch": 0.08250213736107154, "grad_norm": 4.057203254930591, "learning_rate": 8.233618233618234e-06, "loss": 0.6932, "step": 579 }, { "epoch": 0.08264462809917356, "grad_norm": 3.337578403596187, "learning_rate": 8.247863247863248e-06, "loss": 0.6739, "step": 580 }, { "epoch": 0.08278711883727558, "grad_norm": 3.2028901135605534, "learning_rate": 8.262108262108262e-06, "loss": 0.6721, "step": 581 }, { "epoch": 0.0829296095753776, "grad_norm": 3.8777681688664525, "learning_rate": 8.276353276353277e-06, "loss": 0.7642, "step": 582 }, { "epoch": 0.08307210031347963, "grad_norm": 3.4584471423898995, "learning_rate": 8.290598290598293e-06, "loss": 0.6719, "step": 583 }, { "epoch": 0.08321459105158165, "grad_norm": 3.2387719546418463, "learning_rate": 8.304843304843305e-06, "loss": 0.7135, "step": 584 }, { "epoch": 0.08335708178968367, "grad_norm": 3.3990028193776225, "learning_rate": 8.31908831908832e-06, "loss": 0.7791, "step": 585 }, { "epoch": 0.0834995725277857, "grad_norm": 3.8728809600596974, "learning_rate": 8.333333333333334e-06, "loss": 0.7082, "step": 586 }, { "epoch": 0.08364206326588772, "grad_norm": 4.906094572426612, "learning_rate": 8.347578347578348e-06, "loss": 0.7367, "step": 587 }, { "epoch": 0.08378455400398974, "grad_norm": 5.20238986451433, "learning_rate": 8.361823361823362e-06, "loss": 0.6636, "step": 588 }, { "epoch": 0.08392704474209177, "grad_norm": 3.201859604594211, "learning_rate": 8.376068376068377e-06, "loss": 0.7233, "step": 589 }, { "epoch": 0.08406953548019379, "grad_norm": 3.6613172322708722, "learning_rate": 8.39031339031339e-06, "loss": 0.7152, "step": 590 }, { "epoch": 0.08421202621829581, "grad_norm": 4.070581725213476, "learning_rate": 8.404558404558405e-06, "loss": 0.6841, "step": 591 }, { "epoch": 0.08435451695639784, "grad_norm": 2.97502616009444, "learning_rate": 8.41880341880342e-06, "loss": 0.6554, "step": 592 }, { "epoch": 0.08449700769449986, "grad_norm": 14.650891117584154, "learning_rate": 8.433048433048434e-06, "loss": 0.7749, "step": 593 }, { "epoch": 0.08463949843260188, "grad_norm": 2.991535752586272, "learning_rate": 8.447293447293448e-06, "loss": 0.6694, "step": 594 }, { "epoch": 0.0847819891707039, "grad_norm": 3.6579361011091382, "learning_rate": 8.461538461538462e-06, "loss": 0.7144, "step": 595 }, { "epoch": 0.08492447990880593, "grad_norm": 3.00862340488932, "learning_rate": 8.475783475783476e-06, "loss": 0.7669, "step": 596 }, { "epoch": 0.08506697064690795, "grad_norm": 3.0521045165049903, "learning_rate": 8.49002849002849e-06, "loss": 0.6926, "step": 597 }, { "epoch": 0.08520946138500997, "grad_norm": 3.446430107388002, "learning_rate": 8.504273504273505e-06, "loss": 0.7647, "step": 598 }, { "epoch": 0.085351952123112, "grad_norm": 3.9931441199018987, "learning_rate": 8.518518518518519e-06, "loss": 0.7281, "step": 599 }, { "epoch": 0.08549444286121402, "grad_norm": 8.238197500053474, "learning_rate": 8.532763532763533e-06, "loss": 0.7368, "step": 600 }, { "epoch": 0.08563693359931604, "grad_norm": 3.416802538683161, "learning_rate": 8.547008547008548e-06, "loss": 0.7852, "step": 601 }, { "epoch": 0.08577942433741807, "grad_norm": 3.4565121451147887, "learning_rate": 8.561253561253562e-06, "loss": 0.7739, "step": 602 }, { "epoch": 0.08592191507552009, "grad_norm": 2.9804709579222943, "learning_rate": 8.575498575498576e-06, "loss": 0.6448, "step": 603 }, { "epoch": 0.08606440581362211, "grad_norm": 3.2386958591852615, "learning_rate": 8.58974358974359e-06, "loss": 0.7613, "step": 604 }, { "epoch": 0.08620689655172414, "grad_norm": 6.161775244934307, "learning_rate": 8.603988603988605e-06, "loss": 0.6306, "step": 605 }, { "epoch": 0.08634938728982616, "grad_norm": 3.068044620826644, "learning_rate": 8.618233618233619e-06, "loss": 0.7424, "step": 606 }, { "epoch": 0.08649187802792818, "grad_norm": 3.6136310121803374, "learning_rate": 8.632478632478633e-06, "loss": 0.7136, "step": 607 }, { "epoch": 0.08663436876603021, "grad_norm": 2.877422371887224, "learning_rate": 8.646723646723648e-06, "loss": 0.7615, "step": 608 }, { "epoch": 0.08677685950413223, "grad_norm": 2.768932354931829, "learning_rate": 8.660968660968662e-06, "loss": 0.7152, "step": 609 }, { "epoch": 0.08691935024223425, "grad_norm": 8.949952480523399, "learning_rate": 8.675213675213676e-06, "loss": 0.7085, "step": 610 }, { "epoch": 0.08706184098033627, "grad_norm": 2.864393885282655, "learning_rate": 8.68945868945869e-06, "loss": 0.628, "step": 611 }, { "epoch": 0.0872043317184383, "grad_norm": 3.6033249678366728, "learning_rate": 8.703703703703705e-06, "loss": 0.6646, "step": 612 }, { "epoch": 0.08734682245654032, "grad_norm": 5.786845289281627, "learning_rate": 8.717948717948719e-06, "loss": 0.7174, "step": 613 }, { "epoch": 0.08748931319464234, "grad_norm": 3.886681432465251, "learning_rate": 8.732193732193733e-06, "loss": 0.7463, "step": 614 }, { "epoch": 0.08763180393274438, "grad_norm": 3.1420194679323314, "learning_rate": 8.746438746438747e-06, "loss": 0.7113, "step": 615 }, { "epoch": 0.0877742946708464, "grad_norm": 3.14094693914133, "learning_rate": 8.760683760683762e-06, "loss": 0.721, "step": 616 }, { "epoch": 0.08791678540894841, "grad_norm": 3.8898941616826312, "learning_rate": 8.774928774928776e-06, "loss": 0.6173, "step": 617 }, { "epoch": 0.08805927614705045, "grad_norm": 4.002451744513297, "learning_rate": 8.78917378917379e-06, "loss": 0.6733, "step": 618 }, { "epoch": 0.08820176688515247, "grad_norm": 3.8267401342856044, "learning_rate": 8.803418803418804e-06, "loss": 0.6864, "step": 619 }, { "epoch": 0.08834425762325449, "grad_norm": 6.037590941973323, "learning_rate": 8.817663817663819e-06, "loss": 0.6714, "step": 620 }, { "epoch": 0.08848674836135652, "grad_norm": 6.184056779313908, "learning_rate": 8.831908831908833e-06, "loss": 0.7196, "step": 621 }, { "epoch": 0.08862923909945854, "grad_norm": 5.71101350715979, "learning_rate": 8.846153846153847e-06, "loss": 0.7056, "step": 622 }, { "epoch": 0.08877172983756056, "grad_norm": 3.1782997789583227, "learning_rate": 8.860398860398861e-06, "loss": 0.7042, "step": 623 }, { "epoch": 0.08891422057566258, "grad_norm": 3.231728848972741, "learning_rate": 8.874643874643876e-06, "loss": 0.6715, "step": 624 }, { "epoch": 0.08905671131376461, "grad_norm": 4.609708658349013, "learning_rate": 8.888888888888888e-06, "loss": 0.7711, "step": 625 }, { "epoch": 0.08919920205186663, "grad_norm": 3.148785084635564, "learning_rate": 8.903133903133904e-06, "loss": 0.7045, "step": 626 }, { "epoch": 0.08934169278996865, "grad_norm": 6.374837601024855, "learning_rate": 8.917378917378919e-06, "loss": 0.755, "step": 627 }, { "epoch": 0.08948418352807068, "grad_norm": 2.9002325594730833, "learning_rate": 8.931623931623933e-06, "loss": 0.7692, "step": 628 }, { "epoch": 0.0896266742661727, "grad_norm": 3.7366743029710325, "learning_rate": 8.945868945868947e-06, "loss": 0.7299, "step": 629 }, { "epoch": 0.08976916500427472, "grad_norm": 3.5786002454582553, "learning_rate": 8.960113960113961e-06, "loss": 0.7492, "step": 630 }, { "epoch": 0.08991165574237675, "grad_norm": 3.0057446589799475, "learning_rate": 8.974358974358976e-06, "loss": 0.6599, "step": 631 }, { "epoch": 0.09005414648047877, "grad_norm": 6.19502888369817, "learning_rate": 8.988603988603988e-06, "loss": 0.6822, "step": 632 }, { "epoch": 0.09019663721858079, "grad_norm": 3.0793017844312076, "learning_rate": 9.002849002849004e-06, "loss": 0.6198, "step": 633 }, { "epoch": 0.09033912795668282, "grad_norm": 3.567836015072068, "learning_rate": 9.017094017094018e-06, "loss": 0.6977, "step": 634 }, { "epoch": 0.09048161869478484, "grad_norm": 2.895052396122222, "learning_rate": 9.031339031339033e-06, "loss": 0.7105, "step": 635 }, { "epoch": 0.09062410943288686, "grad_norm": 2.715001534589034, "learning_rate": 9.045584045584045e-06, "loss": 0.7089, "step": 636 }, { "epoch": 0.09076660017098889, "grad_norm": 2.9712749222164563, "learning_rate": 9.059829059829061e-06, "loss": 0.7426, "step": 637 }, { "epoch": 0.09090909090909091, "grad_norm": 2.919455205292661, "learning_rate": 9.074074074074075e-06, "loss": 0.7272, "step": 638 }, { "epoch": 0.09105158164719293, "grad_norm": 3.1702146015898123, "learning_rate": 9.088319088319088e-06, "loss": 0.6716, "step": 639 }, { "epoch": 0.09119407238529495, "grad_norm": 4.1755731049859035, "learning_rate": 9.102564102564104e-06, "loss": 0.7559, "step": 640 }, { "epoch": 0.09133656312339698, "grad_norm": 3.2282591359789565, "learning_rate": 9.116809116809118e-06, "loss": 0.7491, "step": 641 }, { "epoch": 0.091479053861499, "grad_norm": 2.611297699310979, "learning_rate": 9.131054131054132e-06, "loss": 0.798, "step": 642 }, { "epoch": 0.09162154459960102, "grad_norm": 3.3620806392526905, "learning_rate": 9.145299145299145e-06, "loss": 0.6832, "step": 643 }, { "epoch": 0.09176403533770305, "grad_norm": 2.967981269779073, "learning_rate": 9.159544159544161e-06, "loss": 0.7499, "step": 644 }, { "epoch": 0.09190652607580507, "grad_norm": 2.9855331429456036, "learning_rate": 9.173789173789175e-06, "loss": 0.6626, "step": 645 }, { "epoch": 0.09204901681390709, "grad_norm": 2.9689903390064236, "learning_rate": 9.188034188034188e-06, "loss": 0.7303, "step": 646 }, { "epoch": 0.09219150755200912, "grad_norm": 2.6149739699538865, "learning_rate": 9.202279202279202e-06, "loss": 0.7351, "step": 647 }, { "epoch": 0.09233399829011114, "grad_norm": 4.261976586368771, "learning_rate": 9.216524216524218e-06, "loss": 0.7268, "step": 648 }, { "epoch": 0.09247648902821316, "grad_norm": 2.8635601053465582, "learning_rate": 9.230769230769232e-06, "loss": 0.6947, "step": 649 }, { "epoch": 0.0926189797663152, "grad_norm": 3.028230432623032, "learning_rate": 9.245014245014245e-06, "loss": 0.8141, "step": 650 }, { "epoch": 0.09276147050441721, "grad_norm": 2.9701259668043694, "learning_rate": 9.25925925925926e-06, "loss": 0.7141, "step": 651 }, { "epoch": 0.09290396124251923, "grad_norm": 2.817321387128402, "learning_rate": 9.273504273504275e-06, "loss": 0.6616, "step": 652 }, { "epoch": 0.09304645198062125, "grad_norm": 3.7519917616958645, "learning_rate": 9.287749287749288e-06, "loss": 0.8485, "step": 653 }, { "epoch": 0.09318894271872329, "grad_norm": 2.997425224871847, "learning_rate": 9.301994301994302e-06, "loss": 0.6976, "step": 654 }, { "epoch": 0.0933314334568253, "grad_norm": 3.1588356999117795, "learning_rate": 9.316239316239318e-06, "loss": 0.8159, "step": 655 }, { "epoch": 0.09347392419492732, "grad_norm": 3.5716469145806253, "learning_rate": 9.330484330484332e-06, "loss": 0.7509, "step": 656 }, { "epoch": 0.09361641493302936, "grad_norm": 2.3584769700451385, "learning_rate": 9.344729344729345e-06, "loss": 0.6808, "step": 657 }, { "epoch": 0.09375890567113138, "grad_norm": 2.7096951844921193, "learning_rate": 9.358974358974359e-06, "loss": 0.6969, "step": 658 }, { "epoch": 0.0939013964092334, "grad_norm": 2.7781342421689685, "learning_rate": 9.373219373219375e-06, "loss": 0.6973, "step": 659 }, { "epoch": 0.09404388714733543, "grad_norm": 2.5599086915860547, "learning_rate": 9.387464387464388e-06, "loss": 0.6745, "step": 660 }, { "epoch": 0.09418637788543745, "grad_norm": 2.836982969721825, "learning_rate": 9.401709401709402e-06, "loss": 0.6852, "step": 661 }, { "epoch": 0.09432886862353947, "grad_norm": 2.7687226164814875, "learning_rate": 9.415954415954418e-06, "loss": 0.6693, "step": 662 }, { "epoch": 0.0944713593616415, "grad_norm": 2.4612822220286867, "learning_rate": 9.430199430199432e-06, "loss": 0.703, "step": 663 }, { "epoch": 0.09461385009974352, "grad_norm": 3.150210698393842, "learning_rate": 9.444444444444445e-06, "loss": 0.7857, "step": 664 }, { "epoch": 0.09475634083784554, "grad_norm": 2.840846097752243, "learning_rate": 9.458689458689459e-06, "loss": 0.6682, "step": 665 }, { "epoch": 0.09489883157594756, "grad_norm": 2.9353805578312233, "learning_rate": 9.472934472934475e-06, "loss": 0.727, "step": 666 }, { "epoch": 0.09504132231404959, "grad_norm": 3.1374185243380177, "learning_rate": 9.487179487179487e-06, "loss": 0.7474, "step": 667 }, { "epoch": 0.09518381305215161, "grad_norm": 3.1426681645290904, "learning_rate": 9.501424501424502e-06, "loss": 0.7025, "step": 668 }, { "epoch": 0.09532630379025363, "grad_norm": 2.6094016073644815, "learning_rate": 9.515669515669516e-06, "loss": 0.6841, "step": 669 }, { "epoch": 0.09546879452835566, "grad_norm": 2.451417250669974, "learning_rate": 9.52991452991453e-06, "loss": 0.7311, "step": 670 }, { "epoch": 0.09561128526645768, "grad_norm": 2.908766210197043, "learning_rate": 9.544159544159544e-06, "loss": 0.6768, "step": 671 }, { "epoch": 0.0957537760045597, "grad_norm": 2.846489046639633, "learning_rate": 9.558404558404559e-06, "loss": 0.7896, "step": 672 }, { "epoch": 0.09589626674266173, "grad_norm": 2.6580793352135825, "learning_rate": 9.572649572649575e-06, "loss": 0.7026, "step": 673 }, { "epoch": 0.09603875748076375, "grad_norm": 2.6927639401941406, "learning_rate": 9.586894586894587e-06, "loss": 0.8065, "step": 674 }, { "epoch": 0.09618124821886577, "grad_norm": 2.536030313037459, "learning_rate": 9.601139601139601e-06, "loss": 0.8258, "step": 675 }, { "epoch": 0.0963237389569678, "grad_norm": 2.6593292341068127, "learning_rate": 9.615384615384616e-06, "loss": 0.7356, "step": 676 }, { "epoch": 0.09646622969506982, "grad_norm": 2.7898831027011046, "learning_rate": 9.62962962962963e-06, "loss": 0.6859, "step": 677 }, { "epoch": 0.09660872043317184, "grad_norm": 2.8024570198994887, "learning_rate": 9.643874643874644e-06, "loss": 0.689, "step": 678 }, { "epoch": 0.09675121117127387, "grad_norm": 3.104425271241125, "learning_rate": 9.658119658119659e-06, "loss": 0.7807, "step": 679 }, { "epoch": 0.09689370190937589, "grad_norm": 4.018225619415269, "learning_rate": 9.672364672364673e-06, "loss": 0.7924, "step": 680 }, { "epoch": 0.09703619264747791, "grad_norm": 2.606774109778729, "learning_rate": 9.686609686609687e-06, "loss": 0.7359, "step": 681 }, { "epoch": 0.09717868338557993, "grad_norm": 2.7768823361115897, "learning_rate": 9.700854700854701e-06, "loss": 0.6734, "step": 682 }, { "epoch": 0.09732117412368196, "grad_norm": 2.576938300844271, "learning_rate": 9.715099715099716e-06, "loss": 0.7733, "step": 683 }, { "epoch": 0.09746366486178398, "grad_norm": 2.608220937618869, "learning_rate": 9.72934472934473e-06, "loss": 0.6901, "step": 684 }, { "epoch": 0.097606155599886, "grad_norm": 2.9033020918905335, "learning_rate": 9.743589743589744e-06, "loss": 0.7066, "step": 685 }, { "epoch": 0.09774864633798803, "grad_norm": 2.718238215659437, "learning_rate": 9.757834757834758e-06, "loss": 0.7102, "step": 686 }, { "epoch": 0.09789113707609005, "grad_norm": 2.635044895785049, "learning_rate": 9.772079772079773e-06, "loss": 0.6945, "step": 687 }, { "epoch": 0.09803362781419207, "grad_norm": 2.5520800374095587, "learning_rate": 9.786324786324787e-06, "loss": 0.6984, "step": 688 }, { "epoch": 0.0981761185522941, "grad_norm": 8.689099541516363, "learning_rate": 9.800569800569801e-06, "loss": 0.7321, "step": 689 }, { "epoch": 0.09831860929039613, "grad_norm": 2.881972083437522, "learning_rate": 9.814814814814815e-06, "loss": 0.7388, "step": 690 }, { "epoch": 0.09846110002849814, "grad_norm": 2.83290807768665, "learning_rate": 9.82905982905983e-06, "loss": 0.6848, "step": 691 }, { "epoch": 0.09860359076660018, "grad_norm": 2.6023868019003187, "learning_rate": 9.843304843304844e-06, "loss": 0.6503, "step": 692 }, { "epoch": 0.0987460815047022, "grad_norm": 2.654472031677163, "learning_rate": 9.857549857549858e-06, "loss": 0.763, "step": 693 }, { "epoch": 0.09888857224280422, "grad_norm": 3.0567497601410647, "learning_rate": 9.871794871794872e-06, "loss": 0.6891, "step": 694 }, { "epoch": 0.09903106298090623, "grad_norm": 2.450250151327045, "learning_rate": 9.886039886039887e-06, "loss": 0.7072, "step": 695 }, { "epoch": 0.09917355371900827, "grad_norm": 3.0745344302094133, "learning_rate": 9.900284900284901e-06, "loss": 0.6319, "step": 696 }, { "epoch": 0.09931604445711029, "grad_norm": 2.6672069425895115, "learning_rate": 9.914529914529915e-06, "loss": 0.8212, "step": 697 }, { "epoch": 0.0994585351952123, "grad_norm": 2.6441341341298408, "learning_rate": 9.92877492877493e-06, "loss": 0.7379, "step": 698 }, { "epoch": 0.09960102593331434, "grad_norm": 2.63393822499731, "learning_rate": 9.943019943019944e-06, "loss": 0.7381, "step": 699 }, { "epoch": 0.09974351667141636, "grad_norm": 2.85840156231467, "learning_rate": 9.957264957264958e-06, "loss": 0.7921, "step": 700 }, { "epoch": 0.09988600740951838, "grad_norm": 2.6571727837766144, "learning_rate": 9.971509971509972e-06, "loss": 0.7431, "step": 701 }, { "epoch": 0.10002849814762041, "grad_norm": 2.4437469979507216, "learning_rate": 9.985754985754987e-06, "loss": 0.637, "step": 702 }, { "epoch": 0.10017098888572243, "grad_norm": 6.047607800658882, "learning_rate": 1e-05, "loss": 0.7796, "step": 703 }, { "epoch": 0.10031347962382445, "grad_norm": 2.4854521149278797, "learning_rate": 1.0014245014245015e-05, "loss": 0.6857, "step": 704 }, { "epoch": 0.10045597036192648, "grad_norm": 2.6636652844258997, "learning_rate": 1.002849002849003e-05, "loss": 0.7188, "step": 705 }, { "epoch": 0.1005984611000285, "grad_norm": 2.607860130737216, "learning_rate": 1.0042735042735044e-05, "loss": 0.6578, "step": 706 }, { "epoch": 0.10074095183813052, "grad_norm": 2.7925259609906403, "learning_rate": 1.0056980056980056e-05, "loss": 0.7117, "step": 707 }, { "epoch": 0.10088344257623255, "grad_norm": 2.7282249859671612, "learning_rate": 1.0071225071225072e-05, "loss": 0.7146, "step": 708 }, { "epoch": 0.10102593331433457, "grad_norm": 2.8192956059136227, "learning_rate": 1.0085470085470086e-05, "loss": 0.7334, "step": 709 }, { "epoch": 0.10116842405243659, "grad_norm": 2.612805645734694, "learning_rate": 1.0099715099715099e-05, "loss": 0.7271, "step": 710 }, { "epoch": 0.10131091479053861, "grad_norm": 2.8779267385740073, "learning_rate": 1.0113960113960115e-05, "loss": 0.7931, "step": 711 }, { "epoch": 0.10145340552864064, "grad_norm": 11.531278511460556, "learning_rate": 1.012820512820513e-05, "loss": 0.7147, "step": 712 }, { "epoch": 0.10159589626674266, "grad_norm": 2.560721346256074, "learning_rate": 1.0142450142450143e-05, "loss": 0.6997, "step": 713 }, { "epoch": 0.10173838700484468, "grad_norm": 2.957189777690281, "learning_rate": 1.0156695156695158e-05, "loss": 0.7834, "step": 714 }, { "epoch": 0.10188087774294671, "grad_norm": 3.0023380659013115, "learning_rate": 1.0170940170940172e-05, "loss": 0.8013, "step": 715 }, { "epoch": 0.10202336848104873, "grad_norm": 2.86238475780529, "learning_rate": 1.0185185185185186e-05, "loss": 0.7352, "step": 716 }, { "epoch": 0.10216585921915075, "grad_norm": 3.0047347755103977, "learning_rate": 1.01994301994302e-05, "loss": 0.7302, "step": 717 }, { "epoch": 0.10230834995725278, "grad_norm": 2.7565963456027167, "learning_rate": 1.0213675213675213e-05, "loss": 0.7263, "step": 718 }, { "epoch": 0.1024508406953548, "grad_norm": 3.2075191110118935, "learning_rate": 1.0227920227920229e-05, "loss": 0.6642, "step": 719 }, { "epoch": 0.10259333143345682, "grad_norm": 2.9182935570311446, "learning_rate": 1.0242165242165243e-05, "loss": 0.7047, "step": 720 }, { "epoch": 0.10273582217155885, "grad_norm": 2.6087430703612706, "learning_rate": 1.0256410256410256e-05, "loss": 0.6586, "step": 721 }, { "epoch": 0.10287831290966087, "grad_norm": 2.8792023021760698, "learning_rate": 1.0270655270655272e-05, "loss": 0.716, "step": 722 }, { "epoch": 0.10302080364776289, "grad_norm": 2.619542676971604, "learning_rate": 1.0284900284900286e-05, "loss": 0.8032, "step": 723 }, { "epoch": 0.10316329438586491, "grad_norm": 2.469842768094263, "learning_rate": 1.0299145299145299e-05, "loss": 0.6815, "step": 724 }, { "epoch": 0.10330578512396695, "grad_norm": 3.353401976784867, "learning_rate": 1.0313390313390315e-05, "loss": 0.6629, "step": 725 }, { "epoch": 0.10344827586206896, "grad_norm": 2.78202190164797, "learning_rate": 1.0327635327635329e-05, "loss": 0.6282, "step": 726 }, { "epoch": 0.10359076660017098, "grad_norm": 2.6896516549789826, "learning_rate": 1.0341880341880343e-05, "loss": 0.7272, "step": 727 }, { "epoch": 0.10373325733827302, "grad_norm": 2.6088050282609734, "learning_rate": 1.0356125356125357e-05, "loss": 0.7177, "step": 728 }, { "epoch": 0.10387574807637504, "grad_norm": 2.711587296148255, "learning_rate": 1.037037037037037e-05, "loss": 0.7776, "step": 729 }, { "epoch": 0.10401823881447705, "grad_norm": 2.4300742924069887, "learning_rate": 1.0384615384615386e-05, "loss": 0.6347, "step": 730 }, { "epoch": 0.10416072955257909, "grad_norm": 2.9943407140009985, "learning_rate": 1.03988603988604e-05, "loss": 0.6854, "step": 731 }, { "epoch": 0.1043032202906811, "grad_norm": 3.167142377746204, "learning_rate": 1.0413105413105413e-05, "loss": 0.7794, "step": 732 }, { "epoch": 0.10444571102878313, "grad_norm": 2.4512270877331233, "learning_rate": 1.0427350427350429e-05, "loss": 0.6539, "step": 733 }, { "epoch": 0.10458820176688516, "grad_norm": 2.8654878797550873, "learning_rate": 1.0441595441595443e-05, "loss": 0.7633, "step": 734 }, { "epoch": 0.10473069250498718, "grad_norm": 2.4379847951367997, "learning_rate": 1.0455840455840456e-05, "loss": 0.7876, "step": 735 }, { "epoch": 0.1048731832430892, "grad_norm": 2.7704587604107354, "learning_rate": 1.0470085470085471e-05, "loss": 0.7569, "step": 736 }, { "epoch": 0.10501567398119123, "grad_norm": 2.517072854436532, "learning_rate": 1.0484330484330486e-05, "loss": 0.6586, "step": 737 }, { "epoch": 0.10515816471929325, "grad_norm": 2.293164603566482, "learning_rate": 1.0498575498575498e-05, "loss": 0.7069, "step": 738 }, { "epoch": 0.10530065545739527, "grad_norm": 2.682764331313133, "learning_rate": 1.0512820512820514e-05, "loss": 0.6585, "step": 739 }, { "epoch": 0.10544314619549729, "grad_norm": 2.647309340131497, "learning_rate": 1.0527065527065527e-05, "loss": 0.8162, "step": 740 }, { "epoch": 0.10558563693359932, "grad_norm": 2.2717503411936324, "learning_rate": 1.0541310541310543e-05, "loss": 0.6744, "step": 741 }, { "epoch": 0.10572812767170134, "grad_norm": 2.514534569076235, "learning_rate": 1.0555555555555557e-05, "loss": 0.7262, "step": 742 }, { "epoch": 0.10587061840980336, "grad_norm": 3.0048862709250517, "learning_rate": 1.056980056980057e-05, "loss": 0.7628, "step": 743 }, { "epoch": 0.10601310914790539, "grad_norm": 2.6958867260957677, "learning_rate": 1.0584045584045586e-05, "loss": 0.66, "step": 744 }, { "epoch": 0.10615559988600741, "grad_norm": 2.5915951706559768, "learning_rate": 1.05982905982906e-05, "loss": 0.7841, "step": 745 }, { "epoch": 0.10629809062410943, "grad_norm": 2.5828445693462614, "learning_rate": 1.0612535612535612e-05, "loss": 0.7124, "step": 746 }, { "epoch": 0.10644058136221146, "grad_norm": 2.464210904369053, "learning_rate": 1.0626780626780628e-05, "loss": 0.6155, "step": 747 }, { "epoch": 0.10658307210031348, "grad_norm": 2.7428670071129613, "learning_rate": 1.0641025641025643e-05, "loss": 0.651, "step": 748 }, { "epoch": 0.1067255628384155, "grad_norm": 9.457934765191311, "learning_rate": 1.0655270655270655e-05, "loss": 0.7459, "step": 749 }, { "epoch": 0.10686805357651753, "grad_norm": 2.5450678548913195, "learning_rate": 1.0669515669515671e-05, "loss": 0.7119, "step": 750 }, { "epoch": 0.10701054431461955, "grad_norm": 2.3554954066526483, "learning_rate": 1.0683760683760684e-05, "loss": 0.7528, "step": 751 }, { "epoch": 0.10715303505272157, "grad_norm": 2.6584129619447827, "learning_rate": 1.0698005698005698e-05, "loss": 0.7788, "step": 752 }, { "epoch": 0.10729552579082359, "grad_norm": 2.2053895223674598, "learning_rate": 1.0712250712250714e-05, "loss": 0.6702, "step": 753 }, { "epoch": 0.10743801652892562, "grad_norm": 4.480333235532683, "learning_rate": 1.0726495726495727e-05, "loss": 0.7204, "step": 754 }, { "epoch": 0.10758050726702764, "grad_norm": 2.583032743862882, "learning_rate": 1.0740740740740742e-05, "loss": 0.7231, "step": 755 }, { "epoch": 0.10772299800512966, "grad_norm": 2.4735458015591822, "learning_rate": 1.0754985754985757e-05, "loss": 0.7499, "step": 756 }, { "epoch": 0.1078654887432317, "grad_norm": 2.4724723841907985, "learning_rate": 1.076923076923077e-05, "loss": 0.7529, "step": 757 }, { "epoch": 0.10800797948133371, "grad_norm": 2.997680020310761, "learning_rate": 1.0783475783475785e-05, "loss": 0.7334, "step": 758 }, { "epoch": 0.10815047021943573, "grad_norm": 2.6227394012026712, "learning_rate": 1.07977207977208e-05, "loss": 0.7387, "step": 759 }, { "epoch": 0.10829296095753776, "grad_norm": 2.5017457128574323, "learning_rate": 1.0811965811965812e-05, "loss": 0.7842, "step": 760 }, { "epoch": 0.10843545169563978, "grad_norm": 2.6196675434374646, "learning_rate": 1.0826210826210828e-05, "loss": 0.811, "step": 761 }, { "epoch": 0.1085779424337418, "grad_norm": 3.0807897984257577, "learning_rate": 1.084045584045584e-05, "loss": 0.7499, "step": 762 }, { "epoch": 0.10872043317184384, "grad_norm": 2.7044174897558, "learning_rate": 1.0854700854700855e-05, "loss": 0.7317, "step": 763 }, { "epoch": 0.10886292390994586, "grad_norm": 2.661743181257005, "learning_rate": 1.0868945868945871e-05, "loss": 0.6892, "step": 764 }, { "epoch": 0.10900541464804787, "grad_norm": 2.3595754159396827, "learning_rate": 1.0883190883190883e-05, "loss": 0.7411, "step": 765 }, { "epoch": 0.10914790538614991, "grad_norm": 2.467140506610029, "learning_rate": 1.0897435897435898e-05, "loss": 0.6678, "step": 766 }, { "epoch": 0.10929039612425193, "grad_norm": 2.621974628344758, "learning_rate": 1.0911680911680914e-05, "loss": 0.661, "step": 767 }, { "epoch": 0.10943288686235395, "grad_norm": 2.811464633071028, "learning_rate": 1.0925925925925926e-05, "loss": 0.6552, "step": 768 }, { "epoch": 0.10957537760045596, "grad_norm": 2.184071520958789, "learning_rate": 1.0940170940170942e-05, "loss": 0.6276, "step": 769 }, { "epoch": 0.109717868338558, "grad_norm": 2.3280097677386014, "learning_rate": 1.0954415954415956e-05, "loss": 0.8029, "step": 770 }, { "epoch": 0.10986035907666002, "grad_norm": 2.451096680831099, "learning_rate": 1.0968660968660969e-05, "loss": 0.6694, "step": 771 }, { "epoch": 0.11000284981476204, "grad_norm": 2.536112089621767, "learning_rate": 1.0982905982905985e-05, "loss": 0.663, "step": 772 }, { "epoch": 0.11014534055286407, "grad_norm": 2.337033825533037, "learning_rate": 1.0997150997150998e-05, "loss": 0.7308, "step": 773 }, { "epoch": 0.11028783129096609, "grad_norm": 2.687474955625553, "learning_rate": 1.1011396011396012e-05, "loss": 0.6952, "step": 774 }, { "epoch": 0.1104303220290681, "grad_norm": 3.107142893396033, "learning_rate": 1.1025641025641028e-05, "loss": 0.7378, "step": 775 }, { "epoch": 0.11057281276717014, "grad_norm": 2.5429863546565765, "learning_rate": 1.103988603988604e-05, "loss": 0.6964, "step": 776 }, { "epoch": 0.11071530350527216, "grad_norm": 2.6147887465740087, "learning_rate": 1.1054131054131055e-05, "loss": 0.7638, "step": 777 }, { "epoch": 0.11085779424337418, "grad_norm": 2.7830350251124334, "learning_rate": 1.106837606837607e-05, "loss": 0.6941, "step": 778 }, { "epoch": 0.11100028498147621, "grad_norm": 2.42446407841906, "learning_rate": 1.1082621082621083e-05, "loss": 0.6832, "step": 779 }, { "epoch": 0.11114277571957823, "grad_norm": 2.5723597407639667, "learning_rate": 1.1096866096866097e-05, "loss": 0.822, "step": 780 }, { "epoch": 0.11128526645768025, "grad_norm": 2.6619111898738117, "learning_rate": 1.1111111111111113e-05, "loss": 0.7803, "step": 781 }, { "epoch": 0.11142775719578227, "grad_norm": 2.6148805403990973, "learning_rate": 1.1125356125356126e-05, "loss": 0.7077, "step": 782 }, { "epoch": 0.1115702479338843, "grad_norm": 2.5378604523596837, "learning_rate": 1.113960113960114e-05, "loss": 0.6882, "step": 783 }, { "epoch": 0.11171273867198632, "grad_norm": 2.7953469148664105, "learning_rate": 1.1153846153846154e-05, "loss": 0.6604, "step": 784 }, { "epoch": 0.11185522941008834, "grad_norm": 2.8819039906052097, "learning_rate": 1.1168091168091169e-05, "loss": 0.7256, "step": 785 }, { "epoch": 0.11199772014819037, "grad_norm": 3.9109328639170293, "learning_rate": 1.1182336182336185e-05, "loss": 0.755, "step": 786 }, { "epoch": 0.11214021088629239, "grad_norm": 2.442891486656236, "learning_rate": 1.1196581196581197e-05, "loss": 0.653, "step": 787 }, { "epoch": 0.11228270162439441, "grad_norm": 2.3705998453045534, "learning_rate": 1.1210826210826211e-05, "loss": 0.712, "step": 788 }, { "epoch": 0.11242519236249644, "grad_norm": 2.7386007484780666, "learning_rate": 1.1225071225071227e-05, "loss": 0.7538, "step": 789 }, { "epoch": 0.11256768310059846, "grad_norm": 2.693480476289502, "learning_rate": 1.123931623931624e-05, "loss": 0.7426, "step": 790 }, { "epoch": 0.11271017383870048, "grad_norm": 2.363829712059324, "learning_rate": 1.1253561253561254e-05, "loss": 0.711, "step": 791 }, { "epoch": 0.11285266457680251, "grad_norm": 2.4633615528929083, "learning_rate": 1.126780626780627e-05, "loss": 0.681, "step": 792 }, { "epoch": 0.11299515531490453, "grad_norm": 2.3475101129806704, "learning_rate": 1.1282051282051283e-05, "loss": 0.721, "step": 793 }, { "epoch": 0.11313764605300655, "grad_norm": 2.327180813884799, "learning_rate": 1.1296296296296297e-05, "loss": 0.744, "step": 794 }, { "epoch": 0.11328013679110857, "grad_norm": 2.8192718309898877, "learning_rate": 1.1310541310541311e-05, "loss": 0.6448, "step": 795 }, { "epoch": 0.1134226275292106, "grad_norm": 2.3834702228779343, "learning_rate": 1.1324786324786326e-05, "loss": 0.7781, "step": 796 }, { "epoch": 0.11356511826731262, "grad_norm": 3.2002361768622114, "learning_rate": 1.1339031339031338e-05, "loss": 0.738, "step": 797 }, { "epoch": 0.11370760900541464, "grad_norm": 2.6383977901305995, "learning_rate": 1.1353276353276354e-05, "loss": 0.7146, "step": 798 }, { "epoch": 0.11385009974351668, "grad_norm": 2.4707320938678397, "learning_rate": 1.1367521367521368e-05, "loss": 0.7235, "step": 799 }, { "epoch": 0.1139925904816187, "grad_norm": 2.4260613700899327, "learning_rate": 1.1381766381766384e-05, "loss": 0.7236, "step": 800 }, { "epoch": 0.11413508121972071, "grad_norm": 2.469630587237684, "learning_rate": 1.1396011396011397e-05, "loss": 0.6607, "step": 801 }, { "epoch": 0.11427757195782275, "grad_norm": 2.2309357046996556, "learning_rate": 1.1410256410256411e-05, "loss": 0.7822, "step": 802 }, { "epoch": 0.11442006269592477, "grad_norm": 2.435358768204438, "learning_rate": 1.1424501424501427e-05, "loss": 0.7101, "step": 803 }, { "epoch": 0.11456255343402678, "grad_norm": 2.4793998822095307, "learning_rate": 1.143874643874644e-05, "loss": 0.7343, "step": 804 }, { "epoch": 0.11470504417212882, "grad_norm": 2.238924392352516, "learning_rate": 1.1452991452991454e-05, "loss": 0.6623, "step": 805 }, { "epoch": 0.11484753491023084, "grad_norm": 2.9696355824422787, "learning_rate": 1.1467236467236468e-05, "loss": 0.7112, "step": 806 }, { "epoch": 0.11499002564833286, "grad_norm": 2.450809685723743, "learning_rate": 1.1481481481481482e-05, "loss": 0.6593, "step": 807 }, { "epoch": 0.11513251638643489, "grad_norm": 2.466904538308367, "learning_rate": 1.1495726495726495e-05, "loss": 0.6171, "step": 808 }, { "epoch": 0.11527500712453691, "grad_norm": 2.408814245095538, "learning_rate": 1.1509971509971511e-05, "loss": 0.6875, "step": 809 }, { "epoch": 0.11541749786263893, "grad_norm": 3.4208554751156126, "learning_rate": 1.1524216524216525e-05, "loss": 0.8094, "step": 810 }, { "epoch": 0.11555998860074095, "grad_norm": 2.629121919351048, "learning_rate": 1.1538461538461538e-05, "loss": 0.707, "step": 811 }, { "epoch": 0.11570247933884298, "grad_norm": 2.9076386561956262, "learning_rate": 1.1552706552706554e-05, "loss": 0.7416, "step": 812 }, { "epoch": 0.115844970076945, "grad_norm": 2.4222844820500256, "learning_rate": 1.1566951566951568e-05, "loss": 0.7743, "step": 813 }, { "epoch": 0.11598746081504702, "grad_norm": 2.480230141458872, "learning_rate": 1.1581196581196584e-05, "loss": 0.7051, "step": 814 }, { "epoch": 0.11612995155314905, "grad_norm": 2.324212391899294, "learning_rate": 1.1595441595441597e-05, "loss": 0.7419, "step": 815 }, { "epoch": 0.11627244229125107, "grad_norm": 2.309936215821381, "learning_rate": 1.1609686609686611e-05, "loss": 0.7478, "step": 816 }, { "epoch": 0.11641493302935309, "grad_norm": 2.27571620400798, "learning_rate": 1.1623931623931625e-05, "loss": 0.7078, "step": 817 }, { "epoch": 0.11655742376745512, "grad_norm": 2.4516242622517885, "learning_rate": 1.163817663817664e-05, "loss": 0.6869, "step": 818 }, { "epoch": 0.11669991450555714, "grad_norm": 2.4628133504828282, "learning_rate": 1.1652421652421652e-05, "loss": 0.7327, "step": 819 }, { "epoch": 0.11684240524365916, "grad_norm": 2.5823445321512866, "learning_rate": 1.1666666666666668e-05, "loss": 0.7119, "step": 820 }, { "epoch": 0.11698489598176119, "grad_norm": 2.804185125397984, "learning_rate": 1.1680911680911682e-05, "loss": 0.6709, "step": 821 }, { "epoch": 0.11712738671986321, "grad_norm": 2.2413440991533635, "learning_rate": 1.1695156695156695e-05, "loss": 0.7641, "step": 822 }, { "epoch": 0.11726987745796523, "grad_norm": 2.3988272104781125, "learning_rate": 1.170940170940171e-05, "loss": 0.7222, "step": 823 }, { "epoch": 0.11741236819606725, "grad_norm": 2.0942193972031697, "learning_rate": 1.1723646723646725e-05, "loss": 0.6983, "step": 824 }, { "epoch": 0.11755485893416928, "grad_norm": 2.687827503793233, "learning_rate": 1.1737891737891738e-05, "loss": 0.7051, "step": 825 }, { "epoch": 0.1176973496722713, "grad_norm": 2.8569084173690107, "learning_rate": 1.1752136752136753e-05, "loss": 0.7688, "step": 826 }, { "epoch": 0.11783984041037332, "grad_norm": 2.4120830610326367, "learning_rate": 1.1766381766381768e-05, "loss": 0.7844, "step": 827 }, { "epoch": 0.11798233114847535, "grad_norm": 2.191573555800474, "learning_rate": 1.1780626780626782e-05, "loss": 0.7302, "step": 828 }, { "epoch": 0.11812482188657737, "grad_norm": 2.2088331644196315, "learning_rate": 1.1794871794871796e-05, "loss": 0.706, "step": 829 }, { "epoch": 0.11826731262467939, "grad_norm": 2.5336934134681908, "learning_rate": 1.1809116809116809e-05, "loss": 0.6787, "step": 830 }, { "epoch": 0.11840980336278142, "grad_norm": 2.2541336064582254, "learning_rate": 1.1823361823361825e-05, "loss": 0.6812, "step": 831 }, { "epoch": 0.11855229410088344, "grad_norm": 2.188398960132035, "learning_rate": 1.1837606837606839e-05, "loss": 0.7467, "step": 832 }, { "epoch": 0.11869478483898546, "grad_norm": 2.40107508588818, "learning_rate": 1.1851851851851852e-05, "loss": 0.8359, "step": 833 }, { "epoch": 0.1188372755770875, "grad_norm": 2.353936457009128, "learning_rate": 1.1866096866096868e-05, "loss": 0.7168, "step": 834 }, { "epoch": 0.11897976631518951, "grad_norm": 2.571745773534694, "learning_rate": 1.1880341880341882e-05, "loss": 0.7257, "step": 835 }, { "epoch": 0.11912225705329153, "grad_norm": 2.1700067466978696, "learning_rate": 1.1894586894586894e-05, "loss": 0.7467, "step": 836 }, { "epoch": 0.11926474779139357, "grad_norm": 2.3588047885518644, "learning_rate": 1.190883190883191e-05, "loss": 0.6581, "step": 837 }, { "epoch": 0.11940723852949559, "grad_norm": 2.0446877529328136, "learning_rate": 1.1923076923076925e-05, "loss": 0.784, "step": 838 }, { "epoch": 0.1195497292675976, "grad_norm": 2.235362349284705, "learning_rate": 1.1937321937321937e-05, "loss": 0.795, "step": 839 }, { "epoch": 0.11969222000569962, "grad_norm": 2.2378198176292905, "learning_rate": 1.1951566951566953e-05, "loss": 0.7037, "step": 840 }, { "epoch": 0.11983471074380166, "grad_norm": 2.296851899304347, "learning_rate": 1.1965811965811966e-05, "loss": 0.7187, "step": 841 }, { "epoch": 0.11997720148190368, "grad_norm": 2.4447717297426705, "learning_rate": 1.1980056980056982e-05, "loss": 0.7741, "step": 842 }, { "epoch": 0.1201196922200057, "grad_norm": 2.4249658418750135, "learning_rate": 1.1994301994301996e-05, "loss": 0.7588, "step": 843 }, { "epoch": 0.12026218295810773, "grad_norm": 2.329900773519719, "learning_rate": 1.2008547008547009e-05, "loss": 0.6947, "step": 844 }, { "epoch": 0.12040467369620975, "grad_norm": 2.944995789251212, "learning_rate": 1.2022792022792024e-05, "loss": 0.7852, "step": 845 }, { "epoch": 0.12054716443431177, "grad_norm": 2.3835451671819237, "learning_rate": 1.2037037037037039e-05, "loss": 0.6391, "step": 846 }, { "epoch": 0.1206896551724138, "grad_norm": 2.299389293871591, "learning_rate": 1.2051282051282051e-05, "loss": 0.7244, "step": 847 }, { "epoch": 0.12083214591051582, "grad_norm": 2.305984275039815, "learning_rate": 1.2065527065527067e-05, "loss": 0.7374, "step": 848 }, { "epoch": 0.12097463664861784, "grad_norm": 2.360007102620898, "learning_rate": 1.2079772079772082e-05, "loss": 0.7043, "step": 849 }, { "epoch": 0.12111712738671987, "grad_norm": 2.1409722022187765, "learning_rate": 1.2094017094017094e-05, "loss": 0.7662, "step": 850 }, { "epoch": 0.12125961812482189, "grad_norm": 2.4890346228743936, "learning_rate": 1.210826210826211e-05, "loss": 0.6807, "step": 851 }, { "epoch": 0.12140210886292391, "grad_norm": 2.262519443213501, "learning_rate": 1.2122507122507123e-05, "loss": 0.7112, "step": 852 }, { "epoch": 0.12154459960102593, "grad_norm": 2.3403164228968505, "learning_rate": 1.2136752136752137e-05, "loss": 0.6981, "step": 853 }, { "epoch": 0.12168709033912796, "grad_norm": 2.2835869435474487, "learning_rate": 1.2150997150997153e-05, "loss": 0.647, "step": 854 }, { "epoch": 0.12182958107722998, "grad_norm": 2.5064520883974772, "learning_rate": 1.2165242165242165e-05, "loss": 0.765, "step": 855 }, { "epoch": 0.121972071815332, "grad_norm": 2.2579157226427173, "learning_rate": 1.217948717948718e-05, "loss": 0.6416, "step": 856 }, { "epoch": 0.12211456255343403, "grad_norm": 2.324019810045693, "learning_rate": 1.2193732193732196e-05, "loss": 0.6829, "step": 857 }, { "epoch": 0.12225705329153605, "grad_norm": 2.4119825780417767, "learning_rate": 1.2207977207977208e-05, "loss": 0.7083, "step": 858 }, { "epoch": 0.12239954402963807, "grad_norm": 2.4409031034200606, "learning_rate": 1.2222222222222224e-05, "loss": 0.6761, "step": 859 }, { "epoch": 0.1225420347677401, "grad_norm": 2.395185993003522, "learning_rate": 1.2236467236467238e-05, "loss": 0.6818, "step": 860 }, { "epoch": 0.12268452550584212, "grad_norm": 2.4138871294195847, "learning_rate": 1.2250712250712251e-05, "loss": 0.7017, "step": 861 }, { "epoch": 0.12282701624394414, "grad_norm": 2.12283093440646, "learning_rate": 1.2264957264957267e-05, "loss": 0.777, "step": 862 }, { "epoch": 0.12296950698204617, "grad_norm": 2.204847581359517, "learning_rate": 1.227920227920228e-05, "loss": 0.7117, "step": 863 }, { "epoch": 0.12311199772014819, "grad_norm": 3.574655582235353, "learning_rate": 1.2293447293447294e-05, "loss": 0.6842, "step": 864 }, { "epoch": 0.12325448845825021, "grad_norm": 2.18183780948886, "learning_rate": 1.230769230769231e-05, "loss": 0.7657, "step": 865 }, { "epoch": 0.12339697919635224, "grad_norm": 2.153696460569497, "learning_rate": 1.2321937321937322e-05, "loss": 0.7315, "step": 866 }, { "epoch": 0.12353946993445426, "grad_norm": 2.1543188355554865, "learning_rate": 1.2336182336182337e-05, "loss": 0.6831, "step": 867 }, { "epoch": 0.12368196067255628, "grad_norm": 2.383158099899854, "learning_rate": 1.2350427350427353e-05, "loss": 0.7504, "step": 868 }, { "epoch": 0.1238244514106583, "grad_norm": 2.070582261705173, "learning_rate": 1.2364672364672365e-05, "loss": 0.6529, "step": 869 }, { "epoch": 0.12396694214876033, "grad_norm": 3.596411999213913, "learning_rate": 1.237891737891738e-05, "loss": 0.7037, "step": 870 }, { "epoch": 0.12410943288686235, "grad_norm": 2.362389723014982, "learning_rate": 1.2393162393162395e-05, "loss": 0.6562, "step": 871 }, { "epoch": 0.12425192362496437, "grad_norm": 2.2906351744936173, "learning_rate": 1.2407407407407408e-05, "loss": 0.7989, "step": 872 }, { "epoch": 0.1243944143630664, "grad_norm": 2.3881131172289045, "learning_rate": 1.2421652421652424e-05, "loss": 0.7032, "step": 873 }, { "epoch": 0.12453690510116842, "grad_norm": 2.314731114171514, "learning_rate": 1.2435897435897436e-05, "loss": 0.7067, "step": 874 }, { "epoch": 0.12467939583927044, "grad_norm": 2.232439932853171, "learning_rate": 1.245014245014245e-05, "loss": 0.7588, "step": 875 }, { "epoch": 0.12482188657737248, "grad_norm": 2.0818974158033163, "learning_rate": 1.2464387464387467e-05, "loss": 0.7675, "step": 876 }, { "epoch": 0.1249643773154745, "grad_norm": 2.393604658772147, "learning_rate": 1.247863247863248e-05, "loss": 0.7088, "step": 877 }, { "epoch": 0.12510686805357651, "grad_norm": 2.392397539279162, "learning_rate": 1.2492877492877493e-05, "loss": 0.7062, "step": 878 }, { "epoch": 0.12524935879167853, "grad_norm": 2.238164105139647, "learning_rate": 1.250712250712251e-05, "loss": 0.7499, "step": 879 }, { "epoch": 0.12539184952978055, "grad_norm": 2.462768291650496, "learning_rate": 1.2521367521367522e-05, "loss": 0.7286, "step": 880 }, { "epoch": 0.1255343402678826, "grad_norm": 2.364729499092006, "learning_rate": 1.2535612535612536e-05, "loss": 0.7622, "step": 881 }, { "epoch": 0.12567683100598462, "grad_norm": 2.5084092646348606, "learning_rate": 1.2549857549857552e-05, "loss": 0.6537, "step": 882 }, { "epoch": 0.12581932174408664, "grad_norm": 2.1852343620940275, "learning_rate": 1.2564102564102565e-05, "loss": 0.7179, "step": 883 }, { "epoch": 0.12596181248218866, "grad_norm": 2.352724649245028, "learning_rate": 1.2578347578347579e-05, "loss": 0.6625, "step": 884 }, { "epoch": 0.12610430322029068, "grad_norm": 2.789061531916665, "learning_rate": 1.2592592592592593e-05, "loss": 0.7604, "step": 885 }, { "epoch": 0.1262467939583927, "grad_norm": 2.402862805080463, "learning_rate": 1.2606837606837608e-05, "loss": 0.8098, "step": 886 }, { "epoch": 0.12638928469649474, "grad_norm": 2.1926825651553274, "learning_rate": 1.2621082621082624e-05, "loss": 0.7061, "step": 887 }, { "epoch": 0.12653177543459676, "grad_norm": 4.386257489817343, "learning_rate": 1.2635327635327636e-05, "loss": 0.6703, "step": 888 }, { "epoch": 0.12667426617269878, "grad_norm": 2.7941974759607517, "learning_rate": 1.264957264957265e-05, "loss": 0.6971, "step": 889 }, { "epoch": 0.1268167569108008, "grad_norm": 2.120163872769933, "learning_rate": 1.2663817663817666e-05, "loss": 0.6572, "step": 890 }, { "epoch": 0.12695924764890282, "grad_norm": 3.021420675116011, "learning_rate": 1.2678062678062679e-05, "loss": 0.7805, "step": 891 }, { "epoch": 0.12710173838700484, "grad_norm": 2.49336352461088, "learning_rate": 1.2692307692307693e-05, "loss": 0.7749, "step": 892 }, { "epoch": 0.12724422912510686, "grad_norm": 2.682224521767773, "learning_rate": 1.2706552706552709e-05, "loss": 0.6865, "step": 893 }, { "epoch": 0.1273867198632089, "grad_norm": 2.6210247414585948, "learning_rate": 1.2720797720797722e-05, "loss": 0.7294, "step": 894 }, { "epoch": 0.12752921060131092, "grad_norm": 2.3217494729041195, "learning_rate": 1.2735042735042736e-05, "loss": 0.7278, "step": 895 }, { "epoch": 0.12767170133941294, "grad_norm": 2.2380216747982535, "learning_rate": 1.274928774928775e-05, "loss": 0.711, "step": 896 }, { "epoch": 0.12781419207751496, "grad_norm": 2.223693450692765, "learning_rate": 1.2763532763532764e-05, "loss": 0.6851, "step": 897 }, { "epoch": 0.12795668281561698, "grad_norm": 2.291343976214482, "learning_rate": 1.2777777777777777e-05, "loss": 0.7181, "step": 898 }, { "epoch": 0.128099173553719, "grad_norm": 2.074401841835119, "learning_rate": 1.2792022792022793e-05, "loss": 0.7217, "step": 899 }, { "epoch": 0.12824166429182104, "grad_norm": 2.4204565018883235, "learning_rate": 1.2806267806267807e-05, "loss": 0.7774, "step": 900 }, { "epoch": 0.12838415502992306, "grad_norm": 2.318774762268189, "learning_rate": 1.2820512820512823e-05, "loss": 0.715, "step": 901 }, { "epoch": 0.12852664576802508, "grad_norm": 2.2840556226192064, "learning_rate": 1.2834757834757836e-05, "loss": 0.7339, "step": 902 }, { "epoch": 0.1286691365061271, "grad_norm": 2.4790024612102073, "learning_rate": 1.284900284900285e-05, "loss": 0.7137, "step": 903 }, { "epoch": 0.12881162724422912, "grad_norm": 2.246266469996866, "learning_rate": 1.2863247863247866e-05, "loss": 0.746, "step": 904 }, { "epoch": 0.12895411798233114, "grad_norm": 2.350691077668257, "learning_rate": 1.2877492877492879e-05, "loss": 0.7227, "step": 905 }, { "epoch": 0.12909660872043316, "grad_norm": 2.238415658978706, "learning_rate": 1.2891737891737893e-05, "loss": 0.7227, "step": 906 }, { "epoch": 0.1292390994585352, "grad_norm": 2.259811269109293, "learning_rate": 1.2905982905982907e-05, "loss": 0.8201, "step": 907 }, { "epoch": 0.12938159019663723, "grad_norm": 2.0353157725756783, "learning_rate": 1.2920227920227921e-05, "loss": 0.7256, "step": 908 }, { "epoch": 0.12952408093473924, "grad_norm": 2.4998359024925048, "learning_rate": 1.2934472934472934e-05, "loss": 0.6347, "step": 909 }, { "epoch": 0.12966657167284126, "grad_norm": 2.379566405335619, "learning_rate": 1.294871794871795e-05, "loss": 0.7361, "step": 910 }, { "epoch": 0.12980906241094328, "grad_norm": 2.33665091873729, "learning_rate": 1.2962962962962964e-05, "loss": 0.7118, "step": 911 }, { "epoch": 0.1299515531490453, "grad_norm": 2.4136850020731506, "learning_rate": 1.2977207977207977e-05, "loss": 0.7298, "step": 912 }, { "epoch": 0.13009404388714735, "grad_norm": 2.2405991664639004, "learning_rate": 1.2991452991452993e-05, "loss": 0.7253, "step": 913 }, { "epoch": 0.13023653462524937, "grad_norm": 2.3359276614486117, "learning_rate": 1.3005698005698007e-05, "loss": 0.6907, "step": 914 }, { "epoch": 0.1303790253633514, "grad_norm": 1.9941111888500678, "learning_rate": 1.301994301994302e-05, "loss": 0.6482, "step": 915 }, { "epoch": 0.1305215161014534, "grad_norm": 2.0851390895809603, "learning_rate": 1.3034188034188035e-05, "loss": 0.6832, "step": 916 }, { "epoch": 0.13066400683955542, "grad_norm": 2.241326193150199, "learning_rate": 1.304843304843305e-05, "loss": 0.7104, "step": 917 }, { "epoch": 0.13080649757765744, "grad_norm": 2.434100319204837, "learning_rate": 1.3062678062678064e-05, "loss": 0.7232, "step": 918 }, { "epoch": 0.13094898831575946, "grad_norm": 2.655159274742201, "learning_rate": 1.3076923076923078e-05, "loss": 0.8556, "step": 919 }, { "epoch": 0.1310914790538615, "grad_norm": 2.1717684996918516, "learning_rate": 1.309116809116809e-05, "loss": 0.8114, "step": 920 }, { "epoch": 0.13123396979196353, "grad_norm": 2.345270571944277, "learning_rate": 1.3105413105413107e-05, "loss": 0.6701, "step": 921 }, { "epoch": 0.13137646053006555, "grad_norm": 3.227618682153418, "learning_rate": 1.3119658119658121e-05, "loss": 0.6824, "step": 922 }, { "epoch": 0.13151895126816757, "grad_norm": 2.443290790976878, "learning_rate": 1.3133903133903134e-05, "loss": 0.6709, "step": 923 }, { "epoch": 0.13166144200626959, "grad_norm": 2.197778416389414, "learning_rate": 1.314814814814815e-05, "loss": 0.7664, "step": 924 }, { "epoch": 0.1318039327443716, "grad_norm": 2.4417846214158025, "learning_rate": 1.3162393162393164e-05, "loss": 0.7139, "step": 925 }, { "epoch": 0.13194642348247365, "grad_norm": 5.958514129204709, "learning_rate": 1.3176638176638176e-05, "loss": 0.753, "step": 926 }, { "epoch": 0.13208891422057567, "grad_norm": 2.346835138494498, "learning_rate": 1.3190883190883192e-05, "loss": 0.7378, "step": 927 }, { "epoch": 0.1322314049586777, "grad_norm": 1.9554575578217706, "learning_rate": 1.3205128205128207e-05, "loss": 0.6527, "step": 928 }, { "epoch": 0.1323738956967797, "grad_norm": 2.154814954977004, "learning_rate": 1.321937321937322e-05, "loss": 0.768, "step": 929 }, { "epoch": 0.13251638643488173, "grad_norm": 2.2300529438489773, "learning_rate": 1.3233618233618235e-05, "loss": 0.729, "step": 930 }, { "epoch": 0.13265887717298375, "grad_norm": 2.3371688833142654, "learning_rate": 1.3247863247863248e-05, "loss": 0.706, "step": 931 }, { "epoch": 0.13280136791108577, "grad_norm": 2.3120334899742505, "learning_rate": 1.3262108262108264e-05, "loss": 0.7593, "step": 932 }, { "epoch": 0.1329438586491878, "grad_norm": 2.487218839581616, "learning_rate": 1.3276353276353278e-05, "loss": 0.7718, "step": 933 }, { "epoch": 0.13308634938728983, "grad_norm": 2.7967194503517323, "learning_rate": 1.329059829059829e-05, "loss": 0.655, "step": 934 }, { "epoch": 0.13322884012539185, "grad_norm": 1.8902364382098606, "learning_rate": 1.3304843304843306e-05, "loss": 0.7221, "step": 935 }, { "epoch": 0.13337133086349387, "grad_norm": 2.5503576404451676, "learning_rate": 1.331908831908832e-05, "loss": 0.7082, "step": 936 }, { "epoch": 0.1335138216015959, "grad_norm": 2.117531076120699, "learning_rate": 1.3333333333333333e-05, "loss": 0.7309, "step": 937 }, { "epoch": 0.1336563123396979, "grad_norm": 2.173108273783242, "learning_rate": 1.334757834757835e-05, "loss": 0.6672, "step": 938 }, { "epoch": 0.13379880307779995, "grad_norm": 2.5470865743854225, "learning_rate": 1.3361823361823364e-05, "loss": 0.7666, "step": 939 }, { "epoch": 0.13394129381590197, "grad_norm": 2.3481086167451823, "learning_rate": 1.3376068376068376e-05, "loss": 0.7807, "step": 940 }, { "epoch": 0.134083784554004, "grad_norm": 2.1814419805145167, "learning_rate": 1.3390313390313392e-05, "loss": 0.755, "step": 941 }, { "epoch": 0.134226275292106, "grad_norm": 2.094429121354249, "learning_rate": 1.3404558404558405e-05, "loss": 0.7247, "step": 942 }, { "epoch": 0.13436876603020803, "grad_norm": 2.4367005293622435, "learning_rate": 1.3418803418803419e-05, "loss": 0.6727, "step": 943 }, { "epoch": 0.13451125676831005, "grad_norm": 2.229570299719127, "learning_rate": 1.3433048433048435e-05, "loss": 0.7181, "step": 944 }, { "epoch": 0.1346537475064121, "grad_norm": 2.1988666317878076, "learning_rate": 1.3447293447293447e-05, "loss": 0.7227, "step": 945 }, { "epoch": 0.13479623824451412, "grad_norm": 2.458098934112646, "learning_rate": 1.3461538461538463e-05, "loss": 0.6604, "step": 946 }, { "epoch": 0.13493872898261614, "grad_norm": 2.3761665001611285, "learning_rate": 1.3475783475783478e-05, "loss": 0.6772, "step": 947 }, { "epoch": 0.13508121972071815, "grad_norm": 2.166947418366502, "learning_rate": 1.349002849002849e-05, "loss": 0.7599, "step": 948 }, { "epoch": 0.13522371045882017, "grad_norm": 2.2314701688900938, "learning_rate": 1.3504273504273506e-05, "loss": 0.6737, "step": 949 }, { "epoch": 0.1353662011969222, "grad_norm": 2.524746684813866, "learning_rate": 1.351851851851852e-05, "loss": 0.7347, "step": 950 }, { "epoch": 0.1355086919350242, "grad_norm": 2.4495331981261197, "learning_rate": 1.3532763532763533e-05, "loss": 0.7019, "step": 951 }, { "epoch": 0.13565118267312626, "grad_norm": 2.7446538110910588, "learning_rate": 1.3547008547008549e-05, "loss": 0.7515, "step": 952 }, { "epoch": 0.13579367341122828, "grad_norm": 2.7272346534779808, "learning_rate": 1.3561253561253562e-05, "loss": 0.792, "step": 953 }, { "epoch": 0.1359361641493303, "grad_norm": 2.233968530416295, "learning_rate": 1.3575498575498576e-05, "loss": 0.7083, "step": 954 }, { "epoch": 0.13607865488743232, "grad_norm": 2.2899535728972062, "learning_rate": 1.3589743589743592e-05, "loss": 0.6676, "step": 955 }, { "epoch": 0.13622114562553433, "grad_norm": 2.3222792460235246, "learning_rate": 1.3603988603988604e-05, "loss": 0.6864, "step": 956 }, { "epoch": 0.13636363636363635, "grad_norm": 2.077280650278391, "learning_rate": 1.3618233618233619e-05, "loss": 0.6977, "step": 957 }, { "epoch": 0.1365061271017384, "grad_norm": 2.054748491993581, "learning_rate": 1.3632478632478635e-05, "loss": 0.6906, "step": 958 }, { "epoch": 0.13664861783984042, "grad_norm": 2.495462379150057, "learning_rate": 1.3646723646723647e-05, "loss": 0.7139, "step": 959 }, { "epoch": 0.13679110857794244, "grad_norm": 2.2427085205975335, "learning_rate": 1.3660968660968663e-05, "loss": 0.7158, "step": 960 }, { "epoch": 0.13693359931604446, "grad_norm": 2.139049821764379, "learning_rate": 1.3675213675213677e-05, "loss": 0.7529, "step": 961 }, { "epoch": 0.13707609005414648, "grad_norm": 2.4301821022228594, "learning_rate": 1.368945868945869e-05, "loss": 0.6813, "step": 962 }, { "epoch": 0.1372185807922485, "grad_norm": 2.3755998216463676, "learning_rate": 1.3703703703703706e-05, "loss": 0.7084, "step": 963 }, { "epoch": 0.13736107153035051, "grad_norm": 3.262981664531705, "learning_rate": 1.3717948717948718e-05, "loss": 0.7183, "step": 964 }, { "epoch": 0.13750356226845256, "grad_norm": 2.079345850998463, "learning_rate": 1.3732193732193733e-05, "loss": 0.647, "step": 965 }, { "epoch": 0.13764605300655458, "grad_norm": 2.062967775920567, "learning_rate": 1.3746438746438749e-05, "loss": 0.7206, "step": 966 }, { "epoch": 0.1377885437446566, "grad_norm": 2.114778009081934, "learning_rate": 1.3760683760683761e-05, "loss": 0.7355, "step": 967 }, { "epoch": 0.13793103448275862, "grad_norm": 4.249148681872953, "learning_rate": 1.3774928774928775e-05, "loss": 0.7796, "step": 968 }, { "epoch": 0.13807352522086064, "grad_norm": 2.5362185117366605, "learning_rate": 1.3789173789173791e-05, "loss": 0.8017, "step": 969 }, { "epoch": 0.13821601595896266, "grad_norm": 2.431590459860959, "learning_rate": 1.3803418803418804e-05, "loss": 0.715, "step": 970 }, { "epoch": 0.1383585066970647, "grad_norm": 2.3730968460594317, "learning_rate": 1.3817663817663818e-05, "loss": 0.6619, "step": 971 }, { "epoch": 0.13850099743516672, "grad_norm": 2.4505750152601062, "learning_rate": 1.3831908831908834e-05, "loss": 0.7872, "step": 972 }, { "epoch": 0.13864348817326874, "grad_norm": 2.304719006815688, "learning_rate": 1.3846153846153847e-05, "loss": 0.721, "step": 973 }, { "epoch": 0.13878597891137076, "grad_norm": 2.2678939172492956, "learning_rate": 1.3860398860398863e-05, "loss": 0.7001, "step": 974 }, { "epoch": 0.13892846964947278, "grad_norm": 2.393388606802591, "learning_rate": 1.3874643874643875e-05, "loss": 0.7698, "step": 975 }, { "epoch": 0.1390709603875748, "grad_norm": 2.1292997568349255, "learning_rate": 1.388888888888889e-05, "loss": 0.6908, "step": 976 }, { "epoch": 0.13921345112567682, "grad_norm": 2.0992627495050495, "learning_rate": 1.3903133903133906e-05, "loss": 0.7287, "step": 977 }, { "epoch": 0.13935594186377886, "grad_norm": 2.4405537270674182, "learning_rate": 1.3917378917378918e-05, "loss": 0.7056, "step": 978 }, { "epoch": 0.13949843260188088, "grad_norm": 2.100484790997443, "learning_rate": 1.3931623931623932e-05, "loss": 0.7678, "step": 979 }, { "epoch": 0.1396409233399829, "grad_norm": 2.0263904244594935, "learning_rate": 1.3945868945868948e-05, "loss": 0.7294, "step": 980 }, { "epoch": 0.13978341407808492, "grad_norm": 2.187928504595227, "learning_rate": 1.3960113960113961e-05, "loss": 0.698, "step": 981 }, { "epoch": 0.13992590481618694, "grad_norm": 1.8958757956778458, "learning_rate": 1.3974358974358975e-05, "loss": 0.589, "step": 982 }, { "epoch": 0.14006839555428896, "grad_norm": 2.016159749756106, "learning_rate": 1.3988603988603991e-05, "loss": 0.6823, "step": 983 }, { "epoch": 0.140210886292391, "grad_norm": 2.990953442804765, "learning_rate": 1.4002849002849004e-05, "loss": 0.7748, "step": 984 }, { "epoch": 0.14035337703049303, "grad_norm": 2.445752637520358, "learning_rate": 1.4017094017094018e-05, "loss": 0.7429, "step": 985 }, { "epoch": 0.14049586776859505, "grad_norm": 2.856182598313438, "learning_rate": 1.4031339031339032e-05, "loss": 0.6897, "step": 986 }, { "epoch": 0.14063835850669706, "grad_norm": 2.2840348970404474, "learning_rate": 1.4045584045584046e-05, "loss": 0.7322, "step": 987 }, { "epoch": 0.14078084924479908, "grad_norm": 2.2404914790792545, "learning_rate": 1.405982905982906e-05, "loss": 0.7005, "step": 988 }, { "epoch": 0.1409233399829011, "grad_norm": 2.150568670450307, "learning_rate": 1.4074074074074075e-05, "loss": 0.7412, "step": 989 }, { "epoch": 0.14106583072100312, "grad_norm": 2.2360657039151564, "learning_rate": 1.408831908831909e-05, "loss": 0.7951, "step": 990 }, { "epoch": 0.14120832145910517, "grad_norm": 2.034323805361754, "learning_rate": 1.4102564102564105e-05, "loss": 0.7388, "step": 991 }, { "epoch": 0.1413508121972072, "grad_norm": 2.1362391665329232, "learning_rate": 1.4116809116809118e-05, "loss": 0.7489, "step": 992 }, { "epoch": 0.1414933029353092, "grad_norm": 2.2552907217145446, "learning_rate": 1.4131054131054132e-05, "loss": 0.7348, "step": 993 }, { "epoch": 0.14163579367341123, "grad_norm": 2.2190677371993845, "learning_rate": 1.4145299145299148e-05, "loss": 0.7627, "step": 994 }, { "epoch": 0.14177828441151324, "grad_norm": 2.115352618156418, "learning_rate": 1.415954415954416e-05, "loss": 0.7153, "step": 995 }, { "epoch": 0.14192077514961526, "grad_norm": 2.5166462611683142, "learning_rate": 1.4173789173789175e-05, "loss": 0.7415, "step": 996 }, { "epoch": 0.1420632658877173, "grad_norm": 2.1356187307481105, "learning_rate": 1.4188034188034189e-05, "loss": 0.8288, "step": 997 }, { "epoch": 0.14220575662581933, "grad_norm": 2.6885361560150827, "learning_rate": 1.4202279202279203e-05, "loss": 0.7302, "step": 998 }, { "epoch": 0.14234824736392135, "grad_norm": 2.0700348911031554, "learning_rate": 1.4216524216524218e-05, "loss": 0.719, "step": 999 }, { "epoch": 0.14249073810202337, "grad_norm": 2.1985249203629866, "learning_rate": 1.4230769230769232e-05, "loss": 0.7007, "step": 1000 }, { "epoch": 0.1426332288401254, "grad_norm": 2.1782820794383877, "learning_rate": 1.4245014245014246e-05, "loss": 0.731, "step": 1001 }, { "epoch": 0.1427757195782274, "grad_norm": 2.271947119959784, "learning_rate": 1.4259259259259259e-05, "loss": 0.774, "step": 1002 }, { "epoch": 0.14291821031632942, "grad_norm": 2.1484630488126104, "learning_rate": 1.4273504273504275e-05, "loss": 0.7355, "step": 1003 }, { "epoch": 0.14306070105443147, "grad_norm": 2.1678339981055443, "learning_rate": 1.4287749287749289e-05, "loss": 0.7164, "step": 1004 }, { "epoch": 0.1432031917925335, "grad_norm": 2.052046821762136, "learning_rate": 1.4301994301994305e-05, "loss": 0.7434, "step": 1005 }, { "epoch": 0.1433456825306355, "grad_norm": 2.0008562760772715, "learning_rate": 1.4316239316239317e-05, "loss": 0.6341, "step": 1006 }, { "epoch": 0.14348817326873753, "grad_norm": 2.0180903659899827, "learning_rate": 1.4330484330484332e-05, "loss": 0.7646, "step": 1007 }, { "epoch": 0.14363066400683955, "grad_norm": 2.17189599109155, "learning_rate": 1.4344729344729346e-05, "loss": 0.7338, "step": 1008 }, { "epoch": 0.14377315474494157, "grad_norm": 2.6225708318788428, "learning_rate": 1.435897435897436e-05, "loss": 0.8341, "step": 1009 }, { "epoch": 0.1439156454830436, "grad_norm": 2.2413733458791443, "learning_rate": 1.4373219373219374e-05, "loss": 0.6906, "step": 1010 }, { "epoch": 0.14405813622114563, "grad_norm": 2.3372020657333477, "learning_rate": 1.4387464387464389e-05, "loss": 0.7002, "step": 1011 }, { "epoch": 0.14420062695924765, "grad_norm": 2.098138747489516, "learning_rate": 1.4401709401709403e-05, "loss": 0.7054, "step": 1012 }, { "epoch": 0.14434311769734967, "grad_norm": 2.1002598139628916, "learning_rate": 1.4415954415954416e-05, "loss": 0.6213, "step": 1013 }, { "epoch": 0.1444856084354517, "grad_norm": 2.1556683373987746, "learning_rate": 1.4430199430199432e-05, "loss": 0.7252, "step": 1014 }, { "epoch": 0.1446280991735537, "grad_norm": 1.9937619218460434, "learning_rate": 1.4444444444444446e-05, "loss": 0.7584, "step": 1015 }, { "epoch": 0.14477058991165576, "grad_norm": 2.3326161024814778, "learning_rate": 1.4458689458689458e-05, "loss": 0.6635, "step": 1016 }, { "epoch": 0.14491308064975778, "grad_norm": 2.0949428508203702, "learning_rate": 1.4472934472934474e-05, "loss": 0.6649, "step": 1017 }, { "epoch": 0.1450555713878598, "grad_norm": 2.298456800603174, "learning_rate": 1.4487179487179489e-05, "loss": 0.7496, "step": 1018 }, { "epoch": 0.1451980621259618, "grad_norm": 2.138790162097024, "learning_rate": 1.4501424501424503e-05, "loss": 0.7506, "step": 1019 }, { "epoch": 0.14534055286406383, "grad_norm": 2.4083589726363757, "learning_rate": 1.4515669515669517e-05, "loss": 0.7158, "step": 1020 }, { "epoch": 0.14548304360216585, "grad_norm": 2.6021595398239894, "learning_rate": 1.4529914529914531e-05, "loss": 0.7911, "step": 1021 }, { "epoch": 0.14562553434026787, "grad_norm": 2.5201552054824026, "learning_rate": 1.4544159544159546e-05, "loss": 0.6845, "step": 1022 }, { "epoch": 0.14576802507836992, "grad_norm": 2.317021443532357, "learning_rate": 1.455840455840456e-05, "loss": 0.7265, "step": 1023 }, { "epoch": 0.14591051581647194, "grad_norm": 2.550414120156965, "learning_rate": 1.4572649572649572e-05, "loss": 0.7562, "step": 1024 }, { "epoch": 0.14605300655457396, "grad_norm": 2.0211200890002354, "learning_rate": 1.4586894586894588e-05, "loss": 0.7752, "step": 1025 }, { "epoch": 0.14619549729267597, "grad_norm": 2.162873196165332, "learning_rate": 1.4601139601139603e-05, "loss": 0.7021, "step": 1026 }, { "epoch": 0.146337988030778, "grad_norm": 3.6079531559746845, "learning_rate": 1.4615384615384615e-05, "loss": 0.6893, "step": 1027 }, { "epoch": 0.14648047876888, "grad_norm": 2.1659853764134973, "learning_rate": 1.4629629629629631e-05, "loss": 0.7911, "step": 1028 }, { "epoch": 0.14662296950698206, "grad_norm": 2.286622135920582, "learning_rate": 1.4643874643874645e-05, "loss": 0.7683, "step": 1029 }, { "epoch": 0.14676546024508408, "grad_norm": 2.5727744011260016, "learning_rate": 1.4658119658119658e-05, "loss": 0.6736, "step": 1030 }, { "epoch": 0.1469079509831861, "grad_norm": 2.2231842239883344, "learning_rate": 1.4672364672364674e-05, "loss": 0.7574, "step": 1031 }, { "epoch": 0.14705044172128812, "grad_norm": 2.4109946555498527, "learning_rate": 1.4686609686609688e-05, "loss": 0.7305, "step": 1032 }, { "epoch": 0.14719293245939014, "grad_norm": 2.2488423054274627, "learning_rate": 1.4700854700854703e-05, "loss": 0.7409, "step": 1033 }, { "epoch": 0.14733542319749215, "grad_norm": 2.0816278375298984, "learning_rate": 1.4715099715099717e-05, "loss": 0.7472, "step": 1034 }, { "epoch": 0.14747791393559417, "grad_norm": 2.290855537709416, "learning_rate": 1.472934472934473e-05, "loss": 0.6982, "step": 1035 }, { "epoch": 0.14762040467369622, "grad_norm": 2.3504203477394165, "learning_rate": 1.4743589743589745e-05, "loss": 0.7624, "step": 1036 }, { "epoch": 0.14776289541179824, "grad_norm": 2.0266191648346616, "learning_rate": 1.475783475783476e-05, "loss": 0.7713, "step": 1037 }, { "epoch": 0.14790538614990026, "grad_norm": 2.029362503703009, "learning_rate": 1.4772079772079772e-05, "loss": 0.7928, "step": 1038 }, { "epoch": 0.14804787688800228, "grad_norm": 2.0947081813778787, "learning_rate": 1.4786324786324788e-05, "loss": 0.7475, "step": 1039 }, { "epoch": 0.1481903676261043, "grad_norm": 2.10277766842947, "learning_rate": 1.4800569800569802e-05, "loss": 0.7878, "step": 1040 }, { "epoch": 0.14833285836420632, "grad_norm": 2.267035839027494, "learning_rate": 1.4814814814814815e-05, "loss": 0.697, "step": 1041 }, { "epoch": 0.14847534910230836, "grad_norm": 2.3981405680024914, "learning_rate": 1.4829059829059831e-05, "loss": 0.8156, "step": 1042 }, { "epoch": 0.14861783984041038, "grad_norm": 2.543822209451259, "learning_rate": 1.4843304843304845e-05, "loss": 0.7165, "step": 1043 }, { "epoch": 0.1487603305785124, "grad_norm": 2.4140436322995997, "learning_rate": 1.4857549857549858e-05, "loss": 0.778, "step": 1044 }, { "epoch": 0.14890282131661442, "grad_norm": 2.405960841560958, "learning_rate": 1.4871794871794874e-05, "loss": 0.7374, "step": 1045 }, { "epoch": 0.14904531205471644, "grad_norm": 2.1949528577686546, "learning_rate": 1.4886039886039886e-05, "loss": 0.6848, "step": 1046 }, { "epoch": 0.14918780279281846, "grad_norm": 2.1200929947260296, "learning_rate": 1.4900284900284902e-05, "loss": 0.7745, "step": 1047 }, { "epoch": 0.14933029353092048, "grad_norm": 2.279326846273459, "learning_rate": 1.4914529914529916e-05, "loss": 0.6981, "step": 1048 }, { "epoch": 0.14947278426902252, "grad_norm": 2.219838804595608, "learning_rate": 1.4928774928774929e-05, "loss": 0.8007, "step": 1049 }, { "epoch": 0.14961527500712454, "grad_norm": 1.842128799425866, "learning_rate": 1.4943019943019945e-05, "loss": 0.6779, "step": 1050 }, { "epoch": 0.14975776574522656, "grad_norm": 2.2284684333565195, "learning_rate": 1.495726495726496e-05, "loss": 0.7109, "step": 1051 }, { "epoch": 0.14990025648332858, "grad_norm": 1.9920200630057634, "learning_rate": 1.4971509971509972e-05, "loss": 0.7531, "step": 1052 }, { "epoch": 0.1500427472214306, "grad_norm": 2.1751510493791124, "learning_rate": 1.4985754985754988e-05, "loss": 0.6743, "step": 1053 }, { "epoch": 0.15018523795953262, "grad_norm": 1.9896999446825412, "learning_rate": 1.5000000000000002e-05, "loss": 0.7184, "step": 1054 }, { "epoch": 0.15032772869763467, "grad_norm": 2.183639886495196, "learning_rate": 1.5014245014245015e-05, "loss": 0.7395, "step": 1055 }, { "epoch": 0.15047021943573669, "grad_norm": 2.10147953599293, "learning_rate": 1.502849002849003e-05, "loss": 0.7226, "step": 1056 }, { "epoch": 0.1506127101738387, "grad_norm": 2.187908901287462, "learning_rate": 1.5042735042735043e-05, "loss": 0.6886, "step": 1057 }, { "epoch": 0.15075520091194072, "grad_norm": 2.998693734170363, "learning_rate": 1.5056980056980057e-05, "loss": 0.7413, "step": 1058 }, { "epoch": 0.15089769165004274, "grad_norm": 2.0746605211975813, "learning_rate": 1.5071225071225073e-05, "loss": 0.6816, "step": 1059 }, { "epoch": 0.15104018238814476, "grad_norm": 2.0598082593438547, "learning_rate": 1.5085470085470086e-05, "loss": 0.7157, "step": 1060 }, { "epoch": 0.15118267312624678, "grad_norm": 2.4510204591968026, "learning_rate": 1.50997150997151e-05, "loss": 0.677, "step": 1061 }, { "epoch": 0.15132516386434883, "grad_norm": 3.4598088930990105, "learning_rate": 1.5113960113960116e-05, "loss": 0.6639, "step": 1062 }, { "epoch": 0.15146765460245085, "grad_norm": 3.5526220952876186, "learning_rate": 1.5128205128205129e-05, "loss": 0.7054, "step": 1063 }, { "epoch": 0.15161014534055287, "grad_norm": 2.5992532509556177, "learning_rate": 1.5142450142450145e-05, "loss": 0.7109, "step": 1064 }, { "epoch": 0.15175263607865488, "grad_norm": 2.8666419947457076, "learning_rate": 1.5156695156695157e-05, "loss": 0.7196, "step": 1065 }, { "epoch": 0.1518951268167569, "grad_norm": 2.2355614070525585, "learning_rate": 1.5170940170940172e-05, "loss": 0.7559, "step": 1066 }, { "epoch": 0.15203761755485892, "grad_norm": 2.549743218651969, "learning_rate": 1.5185185185185187e-05, "loss": 0.6893, "step": 1067 }, { "epoch": 0.15218010829296097, "grad_norm": 2.215886486677687, "learning_rate": 1.51994301994302e-05, "loss": 0.6924, "step": 1068 }, { "epoch": 0.152322599031063, "grad_norm": 2.376023829700661, "learning_rate": 1.5213675213675214e-05, "loss": 0.715, "step": 1069 }, { "epoch": 0.152465089769165, "grad_norm": 2.2594617298640465, "learning_rate": 1.522792022792023e-05, "loss": 0.6907, "step": 1070 }, { "epoch": 0.15260758050726703, "grad_norm": 2.081914632747052, "learning_rate": 1.5242165242165243e-05, "loss": 0.7275, "step": 1071 }, { "epoch": 0.15275007124536905, "grad_norm": 2.2619006983166154, "learning_rate": 1.5256410256410257e-05, "loss": 0.7211, "step": 1072 }, { "epoch": 0.15289256198347106, "grad_norm": 11.564431509977181, "learning_rate": 1.5270655270655273e-05, "loss": 0.7637, "step": 1073 }, { "epoch": 0.1530350527215731, "grad_norm": 1.9625653524340951, "learning_rate": 1.5284900284900287e-05, "loss": 0.7728, "step": 1074 }, { "epoch": 0.15317754345967513, "grad_norm": 2.2040444413296583, "learning_rate": 1.5299145299145298e-05, "loss": 0.7392, "step": 1075 }, { "epoch": 0.15332003419777715, "grad_norm": 3.7207663929723376, "learning_rate": 1.5313390313390316e-05, "loss": 0.7516, "step": 1076 }, { "epoch": 0.15346252493587917, "grad_norm": 6.215879178953843, "learning_rate": 1.532763532763533e-05, "loss": 0.7924, "step": 1077 }, { "epoch": 0.1536050156739812, "grad_norm": 1.9786758627346286, "learning_rate": 1.5341880341880344e-05, "loss": 0.7032, "step": 1078 }, { "epoch": 0.1537475064120832, "grad_norm": 3.9889150891096494, "learning_rate": 1.535612535612536e-05, "loss": 0.8677, "step": 1079 }, { "epoch": 0.15388999715018523, "grad_norm": 2.0968195665024325, "learning_rate": 1.537037037037037e-05, "loss": 0.6502, "step": 1080 }, { "epoch": 0.15403248788828727, "grad_norm": 2.1320497973796737, "learning_rate": 1.5384615384615387e-05, "loss": 0.6236, "step": 1081 }, { "epoch": 0.1541749786263893, "grad_norm": 2.1028835416693092, "learning_rate": 1.53988603988604e-05, "loss": 0.7099, "step": 1082 }, { "epoch": 0.1543174693644913, "grad_norm": 2.3229442918938443, "learning_rate": 1.5413105413105412e-05, "loss": 0.6985, "step": 1083 }, { "epoch": 0.15445996010259333, "grad_norm": 2.4347656145159293, "learning_rate": 1.542735042735043e-05, "loss": 0.6654, "step": 1084 }, { "epoch": 0.15460245084069535, "grad_norm": 2.151667781601657, "learning_rate": 1.5441595441595444e-05, "loss": 0.7278, "step": 1085 }, { "epoch": 0.15474494157879737, "grad_norm": 3.5629948567373706, "learning_rate": 1.5455840455840455e-05, "loss": 0.7044, "step": 1086 }, { "epoch": 0.15488743231689941, "grad_norm": 2.2205878737687974, "learning_rate": 1.5470085470085473e-05, "loss": 0.7151, "step": 1087 }, { "epoch": 0.15502992305500143, "grad_norm": 3.7075991364504373, "learning_rate": 1.5484330484330487e-05, "loss": 0.8865, "step": 1088 }, { "epoch": 0.15517241379310345, "grad_norm": 2.434464682287812, "learning_rate": 1.5498575498575498e-05, "loss": 0.7973, "step": 1089 }, { "epoch": 0.15531490453120547, "grad_norm": 2.610508253647487, "learning_rate": 1.5512820512820516e-05, "loss": 0.6899, "step": 1090 }, { "epoch": 0.1554573952693075, "grad_norm": 2.166122221543333, "learning_rate": 1.5527065527065526e-05, "loss": 0.6084, "step": 1091 }, { "epoch": 0.1555998860074095, "grad_norm": 2.574516305153674, "learning_rate": 1.5541310541310544e-05, "loss": 0.8123, "step": 1092 }, { "epoch": 0.15574237674551153, "grad_norm": 2.4291561452821755, "learning_rate": 1.555555555555556e-05, "loss": 0.6885, "step": 1093 }, { "epoch": 0.15588486748361358, "grad_norm": 5.671405889318018, "learning_rate": 1.556980056980057e-05, "loss": 0.6748, "step": 1094 }, { "epoch": 0.1560273582217156, "grad_norm": 2.6282679545082286, "learning_rate": 1.5584045584045587e-05, "loss": 0.7612, "step": 1095 }, { "epoch": 0.15616984895981761, "grad_norm": 2.935650604227789, "learning_rate": 1.55982905982906e-05, "loss": 0.7258, "step": 1096 }, { "epoch": 0.15631233969791963, "grad_norm": 2.627207581631878, "learning_rate": 1.5612535612535612e-05, "loss": 0.6934, "step": 1097 }, { "epoch": 0.15645483043602165, "grad_norm": 2.3167064374383237, "learning_rate": 1.562678062678063e-05, "loss": 0.6984, "step": 1098 }, { "epoch": 0.15659732117412367, "grad_norm": 2.6776971849590554, "learning_rate": 1.5641025641025644e-05, "loss": 0.6983, "step": 1099 }, { "epoch": 0.15673981191222572, "grad_norm": 2.1794216819974017, "learning_rate": 1.5655270655270655e-05, "loss": 0.7451, "step": 1100 }, { "epoch": 0.15688230265032774, "grad_norm": 6.682956519803405, "learning_rate": 1.5669515669515672e-05, "loss": 0.7294, "step": 1101 }, { "epoch": 0.15702479338842976, "grad_norm": 2.2233022212235323, "learning_rate": 1.5683760683760683e-05, "loss": 0.7366, "step": 1102 }, { "epoch": 0.15716728412653178, "grad_norm": 5.444923909263716, "learning_rate": 1.5698005698005698e-05, "loss": 0.7509, "step": 1103 }, { "epoch": 0.1573097748646338, "grad_norm": 2.0593576932967546, "learning_rate": 1.5712250712250715e-05, "loss": 0.7108, "step": 1104 }, { "epoch": 0.1574522656027358, "grad_norm": 2.51227268379393, "learning_rate": 1.5726495726495726e-05, "loss": 0.7488, "step": 1105 }, { "epoch": 0.15759475634083783, "grad_norm": 2.3053483218781534, "learning_rate": 1.5740740740740744e-05, "loss": 0.6897, "step": 1106 }, { "epoch": 0.15773724707893988, "grad_norm": 2.1115423502825674, "learning_rate": 1.5754985754985758e-05, "loss": 0.6755, "step": 1107 }, { "epoch": 0.1578797378170419, "grad_norm": 2.8151036742413673, "learning_rate": 1.576923076923077e-05, "loss": 0.7344, "step": 1108 }, { "epoch": 0.15802222855514392, "grad_norm": 2.0027966567362756, "learning_rate": 1.5783475783475787e-05, "loss": 0.8055, "step": 1109 }, { "epoch": 0.15816471929324594, "grad_norm": 2.7342209036357588, "learning_rate": 1.57977207977208e-05, "loss": 0.6663, "step": 1110 }, { "epoch": 0.15830721003134796, "grad_norm": 1.9877387395732244, "learning_rate": 1.581196581196581e-05, "loss": 0.7275, "step": 1111 }, { "epoch": 0.15844970076944997, "grad_norm": 1.9472607878655912, "learning_rate": 1.582621082621083e-05, "loss": 0.7301, "step": 1112 }, { "epoch": 0.15859219150755202, "grad_norm": 2.3226904971100675, "learning_rate": 1.584045584045584e-05, "loss": 0.806, "step": 1113 }, { "epoch": 0.15873468224565404, "grad_norm": 2.6127414957442032, "learning_rate": 1.5854700854700854e-05, "loss": 0.7504, "step": 1114 }, { "epoch": 0.15887717298375606, "grad_norm": 1.9915058530855492, "learning_rate": 1.5868945868945872e-05, "loss": 0.7003, "step": 1115 }, { "epoch": 0.15901966372185808, "grad_norm": 2.266673881562569, "learning_rate": 1.5883190883190883e-05, "loss": 0.6759, "step": 1116 }, { "epoch": 0.1591621544599601, "grad_norm": 1.9411996719472142, "learning_rate": 1.5897435897435897e-05, "loss": 0.7191, "step": 1117 }, { "epoch": 0.15930464519806212, "grad_norm": 2.0934006865661026, "learning_rate": 1.5911680911680915e-05, "loss": 0.6518, "step": 1118 }, { "epoch": 0.15944713593616414, "grad_norm": 2.0001623867026486, "learning_rate": 1.5925925925925926e-05, "loss": 0.6988, "step": 1119 }, { "epoch": 0.15958962667426618, "grad_norm": 2.0505930293145833, "learning_rate": 1.5940170940170943e-05, "loss": 0.6572, "step": 1120 }, { "epoch": 0.1597321174123682, "grad_norm": 2.0737410916036527, "learning_rate": 1.5954415954415958e-05, "loss": 0.7476, "step": 1121 }, { "epoch": 0.15987460815047022, "grad_norm": 2.3582295648312592, "learning_rate": 1.596866096866097e-05, "loss": 0.7718, "step": 1122 }, { "epoch": 0.16001709888857224, "grad_norm": 2.106428392301396, "learning_rate": 1.5982905982905986e-05, "loss": 0.7728, "step": 1123 }, { "epoch": 0.16015958962667426, "grad_norm": 2.236930084315839, "learning_rate": 1.5997150997150997e-05, "loss": 0.7644, "step": 1124 }, { "epoch": 0.16030208036477628, "grad_norm": 2.2011257792845407, "learning_rate": 1.601139601139601e-05, "loss": 0.7322, "step": 1125 }, { "epoch": 0.16044457110287833, "grad_norm": 2.0718698893965497, "learning_rate": 1.602564102564103e-05, "loss": 0.7004, "step": 1126 }, { "epoch": 0.16058706184098034, "grad_norm": 1.831480663816359, "learning_rate": 1.603988603988604e-05, "loss": 0.8092, "step": 1127 }, { "epoch": 0.16072955257908236, "grad_norm": 2.0741091614739697, "learning_rate": 1.6054131054131054e-05, "loss": 0.6705, "step": 1128 }, { "epoch": 0.16087204331718438, "grad_norm": 2.095604575679234, "learning_rate": 1.6068376068376072e-05, "loss": 0.7066, "step": 1129 }, { "epoch": 0.1610145340552864, "grad_norm": 2.1589581040881227, "learning_rate": 1.6082621082621083e-05, "loss": 0.7471, "step": 1130 }, { "epoch": 0.16115702479338842, "grad_norm": 1.9427006199446137, "learning_rate": 1.6096866096866097e-05, "loss": 0.7433, "step": 1131 }, { "epoch": 0.16129951553149044, "grad_norm": 1.8283928861158492, "learning_rate": 1.6111111111111115e-05, "loss": 0.667, "step": 1132 }, { "epoch": 0.1614420062695925, "grad_norm": 2.0155015197819934, "learning_rate": 1.6125356125356125e-05, "loss": 0.6923, "step": 1133 }, { "epoch": 0.1615844970076945, "grad_norm": 1.9535732050753254, "learning_rate": 1.613960113960114e-05, "loss": 0.6324, "step": 1134 }, { "epoch": 0.16172698774579652, "grad_norm": 1.8931686513409436, "learning_rate": 1.6153846153846154e-05, "loss": 0.6982, "step": 1135 }, { "epoch": 0.16186947848389854, "grad_norm": 1.9779895669134244, "learning_rate": 1.6168091168091168e-05, "loss": 0.6642, "step": 1136 }, { "epoch": 0.16201196922200056, "grad_norm": 3.7706979211276757, "learning_rate": 1.6182336182336186e-05, "loss": 0.7915, "step": 1137 }, { "epoch": 0.16215445996010258, "grad_norm": 2.0851029583272034, "learning_rate": 1.6196581196581197e-05, "loss": 0.7549, "step": 1138 }, { "epoch": 0.16229695069820463, "grad_norm": 2.0998073821328886, "learning_rate": 1.621082621082621e-05, "loss": 0.7187, "step": 1139 }, { "epoch": 0.16243944143630665, "grad_norm": 2.0333503758529075, "learning_rate": 1.622507122507123e-05, "loss": 0.8043, "step": 1140 }, { "epoch": 0.16258193217440867, "grad_norm": 2.1426062378060715, "learning_rate": 1.623931623931624e-05, "loss": 0.6853, "step": 1141 }, { "epoch": 0.16272442291251069, "grad_norm": 2.1452078032431756, "learning_rate": 1.6253561253561254e-05, "loss": 0.7134, "step": 1142 }, { "epoch": 0.1628669136506127, "grad_norm": 1.92026334162723, "learning_rate": 1.626780626780627e-05, "loss": 0.7919, "step": 1143 }, { "epoch": 0.16300940438871472, "grad_norm": 1.9404912156437133, "learning_rate": 1.6282051282051282e-05, "loss": 0.6666, "step": 1144 }, { "epoch": 0.16315189512681677, "grad_norm": 2.618265349480139, "learning_rate": 1.6296296296296297e-05, "loss": 0.7527, "step": 1145 }, { "epoch": 0.1632943858649188, "grad_norm": 1.935297698893794, "learning_rate": 1.631054131054131e-05, "loss": 0.713, "step": 1146 }, { "epoch": 0.1634368766030208, "grad_norm": 2.262370582187225, "learning_rate": 1.6324786324786325e-05, "loss": 0.7491, "step": 1147 }, { "epoch": 0.16357936734112283, "grad_norm": 2.02131872421439, "learning_rate": 1.633903133903134e-05, "loss": 0.8115, "step": 1148 }, { "epoch": 0.16372185807922485, "grad_norm": 2.4224273746486724, "learning_rate": 1.6353276353276354e-05, "loss": 0.7754, "step": 1149 }, { "epoch": 0.16386434881732687, "grad_norm": 2.232918650460155, "learning_rate": 1.6367521367521368e-05, "loss": 0.837, "step": 1150 }, { "epoch": 0.16400683955542888, "grad_norm": 2.0469641697542196, "learning_rate": 1.6381766381766386e-05, "loss": 0.7165, "step": 1151 }, { "epoch": 0.16414933029353093, "grad_norm": 2.186465545632489, "learning_rate": 1.6396011396011396e-05, "loss": 0.7336, "step": 1152 }, { "epoch": 0.16429182103163295, "grad_norm": 1.9453460450867206, "learning_rate": 1.641025641025641e-05, "loss": 0.7547, "step": 1153 }, { "epoch": 0.16443431176973497, "grad_norm": 1.9645329443409585, "learning_rate": 1.642450142450143e-05, "loss": 0.7394, "step": 1154 }, { "epoch": 0.164576802507837, "grad_norm": 2.317976376419249, "learning_rate": 1.643874643874644e-05, "loss": 0.7251, "step": 1155 }, { "epoch": 0.164719293245939, "grad_norm": 2.3526405191386015, "learning_rate": 1.6452991452991454e-05, "loss": 0.7646, "step": 1156 }, { "epoch": 0.16486178398404103, "grad_norm": 1.949690844833117, "learning_rate": 1.6467236467236468e-05, "loss": 0.6908, "step": 1157 }, { "epoch": 0.16500427472214307, "grad_norm": 1.918679929851058, "learning_rate": 1.6481481481481482e-05, "loss": 0.6877, "step": 1158 }, { "epoch": 0.1651467654602451, "grad_norm": 2.053255086421929, "learning_rate": 1.6495726495726496e-05, "loss": 0.8024, "step": 1159 }, { "epoch": 0.1652892561983471, "grad_norm": 1.9145382979621965, "learning_rate": 1.650997150997151e-05, "loss": 0.7587, "step": 1160 }, { "epoch": 0.16543174693644913, "grad_norm": 2.324540921735072, "learning_rate": 1.6524216524216525e-05, "loss": 0.7378, "step": 1161 }, { "epoch": 0.16557423767455115, "grad_norm": 1.882878707594356, "learning_rate": 1.653846153846154e-05, "loss": 0.6877, "step": 1162 }, { "epoch": 0.16571672841265317, "grad_norm": 2.065804119244766, "learning_rate": 1.6552706552706553e-05, "loss": 0.7407, "step": 1163 }, { "epoch": 0.1658592191507552, "grad_norm": 2.119962019367717, "learning_rate": 1.6566951566951568e-05, "loss": 0.7528, "step": 1164 }, { "epoch": 0.16600170988885724, "grad_norm": 1.8576863260404246, "learning_rate": 1.6581196581196585e-05, "loss": 0.6646, "step": 1165 }, { "epoch": 0.16614420062695925, "grad_norm": 1.931119322939089, "learning_rate": 1.6595441595441596e-05, "loss": 0.6881, "step": 1166 }, { "epoch": 0.16628669136506127, "grad_norm": 1.8219922875648278, "learning_rate": 1.660968660968661e-05, "loss": 0.7371, "step": 1167 }, { "epoch": 0.1664291821031633, "grad_norm": 1.8487486786338054, "learning_rate": 1.6623931623931625e-05, "loss": 0.7044, "step": 1168 }, { "epoch": 0.1665716728412653, "grad_norm": 1.9549975765376637, "learning_rate": 1.663817663817664e-05, "loss": 0.744, "step": 1169 }, { "epoch": 0.16671416357936733, "grad_norm": 1.9332746721759715, "learning_rate": 1.6652421652421653e-05, "loss": 0.8197, "step": 1170 }, { "epoch": 0.16685665431746938, "grad_norm": 2.1011406895279032, "learning_rate": 1.6666666666666667e-05, "loss": 0.7074, "step": 1171 }, { "epoch": 0.1669991450555714, "grad_norm": 2.0356556075316594, "learning_rate": 1.6680911680911682e-05, "loss": 0.7703, "step": 1172 }, { "epoch": 0.16714163579367342, "grad_norm": 2.5114648335256904, "learning_rate": 1.6695156695156696e-05, "loss": 0.7524, "step": 1173 }, { "epoch": 0.16728412653177543, "grad_norm": 2.128936732989411, "learning_rate": 1.670940170940171e-05, "loss": 0.7081, "step": 1174 }, { "epoch": 0.16742661726987745, "grad_norm": 2.31220151494731, "learning_rate": 1.6723646723646725e-05, "loss": 0.7757, "step": 1175 }, { "epoch": 0.16756910800797947, "grad_norm": 1.9514801452990251, "learning_rate": 1.673789173789174e-05, "loss": 0.7438, "step": 1176 }, { "epoch": 0.1677115987460815, "grad_norm": 2.2721685176213406, "learning_rate": 1.6752136752136753e-05, "loss": 0.7184, "step": 1177 }, { "epoch": 0.16785408948418354, "grad_norm": 2.0137369192774957, "learning_rate": 1.6766381766381767e-05, "loss": 0.7735, "step": 1178 }, { "epoch": 0.16799658022228556, "grad_norm": 2.057546677717578, "learning_rate": 1.678062678062678e-05, "loss": 0.6923, "step": 1179 }, { "epoch": 0.16813907096038758, "grad_norm": 2.0732881586898624, "learning_rate": 1.6794871794871796e-05, "loss": 0.7001, "step": 1180 }, { "epoch": 0.1682815616984896, "grad_norm": 1.989510812384022, "learning_rate": 1.680911680911681e-05, "loss": 0.6828, "step": 1181 }, { "epoch": 0.16842405243659161, "grad_norm": 2.042662656398888, "learning_rate": 1.6823361823361824e-05, "loss": 0.801, "step": 1182 }, { "epoch": 0.16856654317469363, "grad_norm": 1.885692382323822, "learning_rate": 1.683760683760684e-05, "loss": 0.7148, "step": 1183 }, { "epoch": 0.16870903391279568, "grad_norm": 2.351979723236823, "learning_rate": 1.6851851851851853e-05, "loss": 0.7453, "step": 1184 }, { "epoch": 0.1688515246508977, "grad_norm": 1.7854249821280956, "learning_rate": 1.6866096866096867e-05, "loss": 0.678, "step": 1185 }, { "epoch": 0.16899401538899972, "grad_norm": 1.9079406975860604, "learning_rate": 1.688034188034188e-05, "loss": 0.723, "step": 1186 }, { "epoch": 0.16913650612710174, "grad_norm": 2.0792084339226387, "learning_rate": 1.6894586894586896e-05, "loss": 0.7189, "step": 1187 }, { "epoch": 0.16927899686520376, "grad_norm": 2.0072554903246917, "learning_rate": 1.690883190883191e-05, "loss": 0.7406, "step": 1188 }, { "epoch": 0.16942148760330578, "grad_norm": 2.056358779791694, "learning_rate": 1.6923076923076924e-05, "loss": 0.7203, "step": 1189 }, { "epoch": 0.1695639783414078, "grad_norm": 2.2178585949956924, "learning_rate": 1.693732193732194e-05, "loss": 0.6985, "step": 1190 }, { "epoch": 0.16970646907950984, "grad_norm": 1.863528603957546, "learning_rate": 1.6951566951566953e-05, "loss": 0.7742, "step": 1191 }, { "epoch": 0.16984895981761186, "grad_norm": 2.1231672018826604, "learning_rate": 1.6965811965811967e-05, "loss": 0.7219, "step": 1192 }, { "epoch": 0.16999145055571388, "grad_norm": 2.060788326814687, "learning_rate": 1.698005698005698e-05, "loss": 0.6765, "step": 1193 }, { "epoch": 0.1701339412938159, "grad_norm": 2.0278685165400057, "learning_rate": 1.6994301994301996e-05, "loss": 0.7179, "step": 1194 }, { "epoch": 0.17027643203191792, "grad_norm": 1.795794657624847, "learning_rate": 1.700854700854701e-05, "loss": 0.6902, "step": 1195 }, { "epoch": 0.17041892277001994, "grad_norm": 1.8720462900056651, "learning_rate": 1.7022792022792024e-05, "loss": 0.7198, "step": 1196 }, { "epoch": 0.17056141350812198, "grad_norm": 2.5162044662361414, "learning_rate": 1.7037037037037038e-05, "loss": 0.7839, "step": 1197 }, { "epoch": 0.170703904246224, "grad_norm": 1.9870675629949668, "learning_rate": 1.7051282051282053e-05, "loss": 0.7904, "step": 1198 }, { "epoch": 0.17084639498432602, "grad_norm": 2.0681072698035083, "learning_rate": 1.7065527065527067e-05, "loss": 0.7499, "step": 1199 }, { "epoch": 0.17098888572242804, "grad_norm": 2.6135807606360446, "learning_rate": 1.707977207977208e-05, "loss": 0.7887, "step": 1200 }, { "epoch": 0.17113137646053006, "grad_norm": 2.0073012264135373, "learning_rate": 1.7094017094017095e-05, "loss": 0.8342, "step": 1201 }, { "epoch": 0.17127386719863208, "grad_norm": 1.9566019459342918, "learning_rate": 1.710826210826211e-05, "loss": 0.7144, "step": 1202 }, { "epoch": 0.17141635793673413, "grad_norm": 2.0747731498446953, "learning_rate": 1.7122507122507124e-05, "loss": 0.7429, "step": 1203 }, { "epoch": 0.17155884867483615, "grad_norm": 2.060019366060231, "learning_rate": 1.7136752136752138e-05, "loss": 0.7094, "step": 1204 }, { "epoch": 0.17170133941293816, "grad_norm": 1.8130019212154338, "learning_rate": 1.7150997150997152e-05, "loss": 0.6038, "step": 1205 }, { "epoch": 0.17184383015104018, "grad_norm": 2.109652306568383, "learning_rate": 1.7165242165242167e-05, "loss": 0.7633, "step": 1206 }, { "epoch": 0.1719863208891422, "grad_norm": 2.266256106644944, "learning_rate": 1.717948717948718e-05, "loss": 0.7505, "step": 1207 }, { "epoch": 0.17212881162724422, "grad_norm": 2.1132550733456883, "learning_rate": 1.7193732193732195e-05, "loss": 0.7572, "step": 1208 }, { "epoch": 0.17227130236534624, "grad_norm": 1.9983661314473553, "learning_rate": 1.720797720797721e-05, "loss": 0.7047, "step": 1209 }, { "epoch": 0.1724137931034483, "grad_norm": 1.970449678346438, "learning_rate": 1.7222222222222224e-05, "loss": 0.6971, "step": 1210 }, { "epoch": 0.1725562838415503, "grad_norm": 1.990857723453259, "learning_rate": 1.7236467236467238e-05, "loss": 0.7054, "step": 1211 }, { "epoch": 0.17269877457965233, "grad_norm": 1.9318695199044649, "learning_rate": 1.7250712250712252e-05, "loss": 0.713, "step": 1212 }, { "epoch": 0.17284126531775434, "grad_norm": 1.966982411594655, "learning_rate": 1.7264957264957267e-05, "loss": 0.7383, "step": 1213 }, { "epoch": 0.17298375605585636, "grad_norm": 1.9680024554521762, "learning_rate": 1.727920227920228e-05, "loss": 0.7393, "step": 1214 }, { "epoch": 0.17312624679395838, "grad_norm": 1.812371215900176, "learning_rate": 1.7293447293447295e-05, "loss": 0.7186, "step": 1215 }, { "epoch": 0.17326873753206043, "grad_norm": 2.0302379825841452, "learning_rate": 1.730769230769231e-05, "loss": 0.6895, "step": 1216 }, { "epoch": 0.17341122827016245, "grad_norm": 1.8501826993362516, "learning_rate": 1.7321937321937324e-05, "loss": 0.7979, "step": 1217 }, { "epoch": 0.17355371900826447, "grad_norm": 2.4382046027485136, "learning_rate": 1.7336182336182338e-05, "loss": 0.699, "step": 1218 }, { "epoch": 0.1736962097463665, "grad_norm": 1.9401902856630224, "learning_rate": 1.7350427350427352e-05, "loss": 0.7184, "step": 1219 }, { "epoch": 0.1738387004844685, "grad_norm": 2.27742604878823, "learning_rate": 1.7364672364672366e-05, "loss": 0.7298, "step": 1220 }, { "epoch": 0.17398119122257052, "grad_norm": 1.7939192101334853, "learning_rate": 1.737891737891738e-05, "loss": 0.787, "step": 1221 }, { "epoch": 0.17412368196067254, "grad_norm": 1.9507727394872616, "learning_rate": 1.7393162393162395e-05, "loss": 0.6739, "step": 1222 }, { "epoch": 0.1742661726987746, "grad_norm": 1.9109744334336867, "learning_rate": 1.740740740740741e-05, "loss": 0.7843, "step": 1223 }, { "epoch": 0.1744086634368766, "grad_norm": 1.8503444999775887, "learning_rate": 1.7421652421652423e-05, "loss": 0.7326, "step": 1224 }, { "epoch": 0.17455115417497863, "grad_norm": 1.915587655075608, "learning_rate": 1.7435897435897438e-05, "loss": 0.7614, "step": 1225 }, { "epoch": 0.17469364491308065, "grad_norm": 2.7038550452496355, "learning_rate": 1.7450142450142452e-05, "loss": 0.7243, "step": 1226 }, { "epoch": 0.17483613565118267, "grad_norm": 2.050345562321276, "learning_rate": 1.7464387464387466e-05, "loss": 0.6646, "step": 1227 }, { "epoch": 0.17497862638928469, "grad_norm": 2.0624168251560073, "learning_rate": 1.747863247863248e-05, "loss": 0.684, "step": 1228 }, { "epoch": 0.17512111712738673, "grad_norm": 1.926259859691737, "learning_rate": 1.7492877492877495e-05, "loss": 0.803, "step": 1229 }, { "epoch": 0.17526360786548875, "grad_norm": 1.7620005639547018, "learning_rate": 1.750712250712251e-05, "loss": 0.7212, "step": 1230 }, { "epoch": 0.17540609860359077, "grad_norm": 1.9418765397652575, "learning_rate": 1.7521367521367523e-05, "loss": 0.7985, "step": 1231 }, { "epoch": 0.1755485893416928, "grad_norm": 1.8888020515484396, "learning_rate": 1.7535612535612538e-05, "loss": 0.733, "step": 1232 }, { "epoch": 0.1756910800797948, "grad_norm": 1.8219451604517591, "learning_rate": 1.7549857549857552e-05, "loss": 0.7249, "step": 1233 }, { "epoch": 0.17583357081789683, "grad_norm": 1.7538739119389652, "learning_rate": 1.7564102564102566e-05, "loss": 0.7781, "step": 1234 }, { "epoch": 0.17597606155599885, "grad_norm": 1.965337834613923, "learning_rate": 1.757834757834758e-05, "loss": 0.7614, "step": 1235 }, { "epoch": 0.1761185522941009, "grad_norm": 2.1037343935490225, "learning_rate": 1.7592592592592595e-05, "loss": 0.7161, "step": 1236 }, { "epoch": 0.1762610430322029, "grad_norm": 1.7385444018148764, "learning_rate": 1.760683760683761e-05, "loss": 0.6429, "step": 1237 }, { "epoch": 0.17640353377030493, "grad_norm": 1.8365247279763626, "learning_rate": 1.7621082621082623e-05, "loss": 0.7307, "step": 1238 }, { "epoch": 0.17654602450840695, "grad_norm": 1.939312406531483, "learning_rate": 1.7635327635327637e-05, "loss": 0.7396, "step": 1239 }, { "epoch": 0.17668851524650897, "grad_norm": 1.9265936983236915, "learning_rate": 1.764957264957265e-05, "loss": 0.7179, "step": 1240 }, { "epoch": 0.176831005984611, "grad_norm": 1.758585148334662, "learning_rate": 1.7663817663817666e-05, "loss": 0.6488, "step": 1241 }, { "epoch": 0.17697349672271304, "grad_norm": 1.835606020727021, "learning_rate": 1.767806267806268e-05, "loss": 0.7414, "step": 1242 }, { "epoch": 0.17711598746081506, "grad_norm": 1.7778396710461044, "learning_rate": 1.7692307692307694e-05, "loss": 0.6724, "step": 1243 }, { "epoch": 0.17725847819891707, "grad_norm": 2.019850212364493, "learning_rate": 1.770655270655271e-05, "loss": 0.7711, "step": 1244 }, { "epoch": 0.1774009689370191, "grad_norm": 1.743159816239985, "learning_rate": 1.7720797720797723e-05, "loss": 0.6844, "step": 1245 }, { "epoch": 0.1775434596751211, "grad_norm": 1.8003991926761003, "learning_rate": 1.7735042735042737e-05, "loss": 0.7728, "step": 1246 }, { "epoch": 0.17768595041322313, "grad_norm": 4.68627134593653, "learning_rate": 1.774928774928775e-05, "loss": 0.7955, "step": 1247 }, { "epoch": 0.17782844115132515, "grad_norm": 1.891938116189708, "learning_rate": 1.7763532763532766e-05, "loss": 0.7174, "step": 1248 }, { "epoch": 0.1779709318894272, "grad_norm": 1.8742542660367045, "learning_rate": 1.7777777777777777e-05, "loss": 0.713, "step": 1249 }, { "epoch": 0.17811342262752922, "grad_norm": 1.998943862636205, "learning_rate": 1.7792022792022794e-05, "loss": 0.7445, "step": 1250 }, { "epoch": 0.17825591336563124, "grad_norm": 1.7124057437248743, "learning_rate": 1.780626780626781e-05, "loss": 0.6226, "step": 1251 }, { "epoch": 0.17839840410373325, "grad_norm": 1.787047786997833, "learning_rate": 1.7820512820512823e-05, "loss": 0.7013, "step": 1252 }, { "epoch": 0.17854089484183527, "grad_norm": 1.7352911850134731, "learning_rate": 1.7834757834757837e-05, "loss": 0.6907, "step": 1253 }, { "epoch": 0.1786833855799373, "grad_norm": 1.6836722420927435, "learning_rate": 1.784900284900285e-05, "loss": 0.6589, "step": 1254 }, { "epoch": 0.17882587631803934, "grad_norm": 2.113238828949684, "learning_rate": 1.7863247863247866e-05, "loss": 0.7134, "step": 1255 }, { "epoch": 0.17896836705614136, "grad_norm": 2.059889397616747, "learning_rate": 1.787749287749288e-05, "loss": 0.7213, "step": 1256 }, { "epoch": 0.17911085779424338, "grad_norm": 1.9069703985513016, "learning_rate": 1.7891737891737894e-05, "loss": 0.7055, "step": 1257 }, { "epoch": 0.1792533485323454, "grad_norm": 1.8470613116587005, "learning_rate": 1.790598290598291e-05, "loss": 0.7072, "step": 1258 }, { "epoch": 0.17939583927044742, "grad_norm": 1.9203606138080647, "learning_rate": 1.7920227920227923e-05, "loss": 0.7067, "step": 1259 }, { "epoch": 0.17953833000854943, "grad_norm": 1.999078576481495, "learning_rate": 1.7934472934472933e-05, "loss": 0.7494, "step": 1260 }, { "epoch": 0.17968082074665145, "grad_norm": 1.886102397117621, "learning_rate": 1.794871794871795e-05, "loss": 0.7925, "step": 1261 }, { "epoch": 0.1798233114847535, "grad_norm": 1.7045461454050073, "learning_rate": 1.7962962962962965e-05, "loss": 0.6999, "step": 1262 }, { "epoch": 0.17996580222285552, "grad_norm": 1.9640810420413175, "learning_rate": 1.7977207977207976e-05, "loss": 0.7661, "step": 1263 }, { "epoch": 0.18010829296095754, "grad_norm": 2.034189438546153, "learning_rate": 1.7991452991452994e-05, "loss": 0.8005, "step": 1264 }, { "epoch": 0.18025078369905956, "grad_norm": 1.7846359974576906, "learning_rate": 1.8005698005698008e-05, "loss": 0.6612, "step": 1265 }, { "epoch": 0.18039327443716158, "grad_norm": 2.0796660459459204, "learning_rate": 1.801994301994302e-05, "loss": 0.7923, "step": 1266 }, { "epoch": 0.1805357651752636, "grad_norm": 1.933651273810028, "learning_rate": 1.8034188034188037e-05, "loss": 0.7052, "step": 1267 }, { "epoch": 0.18067825591336564, "grad_norm": 2.764650552106445, "learning_rate": 1.804843304843305e-05, "loss": 0.8007, "step": 1268 }, { "epoch": 0.18082074665146766, "grad_norm": 2.000804997401568, "learning_rate": 1.8062678062678065e-05, "loss": 0.7511, "step": 1269 }, { "epoch": 0.18096323738956968, "grad_norm": 1.9249993845941082, "learning_rate": 1.807692307692308e-05, "loss": 0.7693, "step": 1270 }, { "epoch": 0.1811057281276717, "grad_norm": 1.87802046850679, "learning_rate": 1.809116809116809e-05, "loss": 0.8067, "step": 1271 }, { "epoch": 0.18124821886577372, "grad_norm": 1.8102139361167975, "learning_rate": 1.8105413105413108e-05, "loss": 0.6143, "step": 1272 }, { "epoch": 0.18139070960387574, "grad_norm": 2.021511789734023, "learning_rate": 1.8119658119658122e-05, "loss": 0.7119, "step": 1273 }, { "epoch": 0.18153320034197779, "grad_norm": 1.8436737991843457, "learning_rate": 1.8133903133903133e-05, "loss": 0.6706, "step": 1274 }, { "epoch": 0.1816756910800798, "grad_norm": 1.769826360993228, "learning_rate": 1.814814814814815e-05, "loss": 0.6862, "step": 1275 }, { "epoch": 0.18181818181818182, "grad_norm": 1.8742383356983428, "learning_rate": 1.8162393162393165e-05, "loss": 0.7293, "step": 1276 }, { "epoch": 0.18196067255628384, "grad_norm": 1.7790711382358055, "learning_rate": 1.8176638176638176e-05, "loss": 0.7984, "step": 1277 }, { "epoch": 0.18210316329438586, "grad_norm": 1.9324815467060543, "learning_rate": 1.8190883190883194e-05, "loss": 0.6622, "step": 1278 }, { "epoch": 0.18224565403248788, "grad_norm": 1.8637595148362363, "learning_rate": 1.8205128205128208e-05, "loss": 0.6936, "step": 1279 }, { "epoch": 0.1823881447705899, "grad_norm": 2.0206004582621135, "learning_rate": 1.821937321937322e-05, "loss": 0.7979, "step": 1280 }, { "epoch": 0.18253063550869195, "grad_norm": 1.8081947766879207, "learning_rate": 1.8233618233618236e-05, "loss": 0.6523, "step": 1281 }, { "epoch": 0.18267312624679397, "grad_norm": 1.8953583407396755, "learning_rate": 1.8247863247863247e-05, "loss": 0.7926, "step": 1282 }, { "epoch": 0.18281561698489598, "grad_norm": 1.943262712677195, "learning_rate": 1.8262108262108265e-05, "loss": 0.7324, "step": 1283 }, { "epoch": 0.182958107722998, "grad_norm": 1.7968352076036314, "learning_rate": 1.827635327635328e-05, "loss": 0.7233, "step": 1284 }, { "epoch": 0.18310059846110002, "grad_norm": 1.7693499684098928, "learning_rate": 1.829059829059829e-05, "loss": 0.7749, "step": 1285 }, { "epoch": 0.18324308919920204, "grad_norm": 2.055207891874279, "learning_rate": 1.8304843304843308e-05, "loss": 0.7426, "step": 1286 }, { "epoch": 0.1833855799373041, "grad_norm": 2.03355710547735, "learning_rate": 1.8319088319088322e-05, "loss": 0.8098, "step": 1287 }, { "epoch": 0.1835280706754061, "grad_norm": 1.8449267289933142, "learning_rate": 1.8333333333333333e-05, "loss": 0.7181, "step": 1288 }, { "epoch": 0.18367056141350813, "grad_norm": 1.7774541935235002, "learning_rate": 1.834757834757835e-05, "loss": 0.7852, "step": 1289 }, { "epoch": 0.18381305215161015, "grad_norm": 1.7111588183993807, "learning_rate": 1.8361823361823365e-05, "loss": 0.7177, "step": 1290 }, { "epoch": 0.18395554288971216, "grad_norm": 2.2845446565444623, "learning_rate": 1.8376068376068376e-05, "loss": 0.7482, "step": 1291 }, { "epoch": 0.18409803362781418, "grad_norm": 2.046045754722287, "learning_rate": 1.8390313390313393e-05, "loss": 0.7433, "step": 1292 }, { "epoch": 0.1842405243659162, "grad_norm": 1.8783338908437168, "learning_rate": 1.8404558404558404e-05, "loss": 0.7374, "step": 1293 }, { "epoch": 0.18438301510401825, "grad_norm": 1.9604829819773903, "learning_rate": 1.841880341880342e-05, "loss": 0.8531, "step": 1294 }, { "epoch": 0.18452550584212027, "grad_norm": 1.6942022690160943, "learning_rate": 1.8433048433048436e-05, "loss": 0.7117, "step": 1295 }, { "epoch": 0.1846679965802223, "grad_norm": 1.8937193287525886, "learning_rate": 1.8447293447293447e-05, "loss": 0.707, "step": 1296 }, { "epoch": 0.1848104873183243, "grad_norm": 1.8628313682551116, "learning_rate": 1.8461538461538465e-05, "loss": 0.7658, "step": 1297 }, { "epoch": 0.18495297805642633, "grad_norm": 1.800943765897416, "learning_rate": 1.847578347578348e-05, "loss": 0.6818, "step": 1298 }, { "epoch": 0.18509546879452835, "grad_norm": 1.7848717221629193, "learning_rate": 1.849002849002849e-05, "loss": 0.7225, "step": 1299 }, { "epoch": 0.1852379595326304, "grad_norm": 1.7620426352132652, "learning_rate": 1.8504273504273507e-05, "loss": 0.6398, "step": 1300 }, { "epoch": 0.1853804502707324, "grad_norm": 1.8383319530576576, "learning_rate": 1.851851851851852e-05, "loss": 0.7085, "step": 1301 }, { "epoch": 0.18552294100883443, "grad_norm": 1.7499606113178394, "learning_rate": 1.8532763532763533e-05, "loss": 0.7601, "step": 1302 }, { "epoch": 0.18566543174693645, "grad_norm": 2.2521386750789545, "learning_rate": 1.854700854700855e-05, "loss": 0.7049, "step": 1303 }, { "epoch": 0.18580792248503847, "grad_norm": 1.628281654432605, "learning_rate": 1.856125356125356e-05, "loss": 0.6858, "step": 1304 }, { "epoch": 0.1859504132231405, "grad_norm": 1.9066187949577924, "learning_rate": 1.8575498575498575e-05, "loss": 0.7599, "step": 1305 }, { "epoch": 0.1860929039612425, "grad_norm": 1.7578422713453006, "learning_rate": 1.8589743589743593e-05, "loss": 0.665, "step": 1306 }, { "epoch": 0.18623539469934455, "grad_norm": 1.9476513640337223, "learning_rate": 1.8603988603988604e-05, "loss": 0.7214, "step": 1307 }, { "epoch": 0.18637788543744657, "grad_norm": 1.7447753710437852, "learning_rate": 1.8618233618233618e-05, "loss": 0.6982, "step": 1308 }, { "epoch": 0.1865203761755486, "grad_norm": 1.9280050234467279, "learning_rate": 1.8632478632478636e-05, "loss": 0.7447, "step": 1309 }, { "epoch": 0.1866628669136506, "grad_norm": 1.8802844782014645, "learning_rate": 1.8646723646723647e-05, "loss": 0.8158, "step": 1310 }, { "epoch": 0.18680535765175263, "grad_norm": 2.069228245740747, "learning_rate": 1.8660968660968664e-05, "loss": 0.6567, "step": 1311 }, { "epoch": 0.18694784838985465, "grad_norm": 1.7671718653098445, "learning_rate": 1.867521367521368e-05, "loss": 0.7161, "step": 1312 }, { "epoch": 0.1870903391279567, "grad_norm": 1.994123378258098, "learning_rate": 1.868945868945869e-05, "loss": 0.8427, "step": 1313 }, { "epoch": 0.18723282986605871, "grad_norm": 1.9831938514448737, "learning_rate": 1.8703703703703707e-05, "loss": 0.7874, "step": 1314 }, { "epoch": 0.18737532060416073, "grad_norm": 1.9014864161504097, "learning_rate": 1.8717948717948718e-05, "loss": 0.6827, "step": 1315 }, { "epoch": 0.18751781134226275, "grad_norm": 1.8728513228007557, "learning_rate": 1.8732193732193732e-05, "loss": 0.7209, "step": 1316 }, { "epoch": 0.18766030208036477, "grad_norm": 1.7540524298259665, "learning_rate": 1.874643874643875e-05, "loss": 0.7172, "step": 1317 }, { "epoch": 0.1878027928184668, "grad_norm": 5.04526252138005, "learning_rate": 1.876068376068376e-05, "loss": 0.7385, "step": 1318 }, { "epoch": 0.1879452835565688, "grad_norm": 1.8203567625001367, "learning_rate": 1.8774928774928775e-05, "loss": 0.7085, "step": 1319 }, { "epoch": 0.18808777429467086, "grad_norm": 1.8274778582864957, "learning_rate": 1.8789173789173793e-05, "loss": 0.7978, "step": 1320 }, { "epoch": 0.18823026503277288, "grad_norm": 1.927039281764623, "learning_rate": 1.8803418803418804e-05, "loss": 0.743, "step": 1321 }, { "epoch": 0.1883727557708749, "grad_norm": 1.848349207537631, "learning_rate": 1.8817663817663818e-05, "loss": 0.7829, "step": 1322 }, { "epoch": 0.1885152465089769, "grad_norm": 2.1328890714569426, "learning_rate": 1.8831908831908835e-05, "loss": 0.5847, "step": 1323 }, { "epoch": 0.18865773724707893, "grad_norm": 1.8332710041328162, "learning_rate": 1.8846153846153846e-05, "loss": 0.7271, "step": 1324 }, { "epoch": 0.18880022798518095, "grad_norm": 1.9043725517811465, "learning_rate": 1.8860398860398864e-05, "loss": 0.7978, "step": 1325 }, { "epoch": 0.188942718723283, "grad_norm": 1.8675560994617968, "learning_rate": 1.8874643874643875e-05, "loss": 0.7817, "step": 1326 }, { "epoch": 0.18908520946138502, "grad_norm": 1.7779205376439555, "learning_rate": 1.888888888888889e-05, "loss": 0.738, "step": 1327 }, { "epoch": 0.18922770019948704, "grad_norm": 2.143079074145782, "learning_rate": 1.8903133903133907e-05, "loss": 0.7333, "step": 1328 }, { "epoch": 0.18937019093758906, "grad_norm": 2.064468861256688, "learning_rate": 1.8917378917378918e-05, "loss": 0.7466, "step": 1329 }, { "epoch": 0.18951268167569107, "grad_norm": 1.8187019304809144, "learning_rate": 1.8931623931623932e-05, "loss": 0.6994, "step": 1330 }, { "epoch": 0.1896551724137931, "grad_norm": 1.8818762826957147, "learning_rate": 1.894586894586895e-05, "loss": 0.6821, "step": 1331 }, { "epoch": 0.1897976631518951, "grad_norm": 1.8854037344656986, "learning_rate": 1.896011396011396e-05, "loss": 0.7386, "step": 1332 }, { "epoch": 0.18994015388999716, "grad_norm": 2.390552670324625, "learning_rate": 1.8974358974358975e-05, "loss": 0.6883, "step": 1333 }, { "epoch": 0.19008264462809918, "grad_norm": 1.8435744183230134, "learning_rate": 1.8988603988603992e-05, "loss": 0.7499, "step": 1334 }, { "epoch": 0.1902251353662012, "grad_norm": 1.7908689318786872, "learning_rate": 1.9002849002849003e-05, "loss": 0.7566, "step": 1335 }, { "epoch": 0.19036762610430322, "grad_norm": 1.9761764427113802, "learning_rate": 1.9017094017094017e-05, "loss": 0.7859, "step": 1336 }, { "epoch": 0.19051011684240524, "grad_norm": 2.075575532962882, "learning_rate": 1.9031339031339032e-05, "loss": 0.7114, "step": 1337 }, { "epoch": 0.19065260758050726, "grad_norm": 1.9246562319762164, "learning_rate": 1.9045584045584046e-05, "loss": 0.7064, "step": 1338 }, { "epoch": 0.1907950983186093, "grad_norm": 1.9260740194060866, "learning_rate": 1.905982905982906e-05, "loss": 0.7955, "step": 1339 }, { "epoch": 0.19093758905671132, "grad_norm": 2.1826496992123885, "learning_rate": 1.9074074074074075e-05, "loss": 0.7708, "step": 1340 }, { "epoch": 0.19108007979481334, "grad_norm": 1.7929512630260978, "learning_rate": 1.908831908831909e-05, "loss": 0.7203, "step": 1341 }, { "epoch": 0.19122257053291536, "grad_norm": 1.8115153458782418, "learning_rate": 1.9102564102564106e-05, "loss": 0.6974, "step": 1342 }, { "epoch": 0.19136506127101738, "grad_norm": 1.702667032231572, "learning_rate": 1.9116809116809117e-05, "loss": 0.7803, "step": 1343 }, { "epoch": 0.1915075520091194, "grad_norm": 1.901691404127334, "learning_rate": 1.913105413105413e-05, "loss": 0.702, "step": 1344 }, { "epoch": 0.19165004274722144, "grad_norm": 4.422013949019032, "learning_rate": 1.914529914529915e-05, "loss": 0.7364, "step": 1345 }, { "epoch": 0.19179253348532346, "grad_norm": 2.786703714165945, "learning_rate": 1.915954415954416e-05, "loss": 0.7633, "step": 1346 }, { "epoch": 0.19193502422342548, "grad_norm": 1.9109185847902752, "learning_rate": 1.9173789173789174e-05, "loss": 0.8082, "step": 1347 }, { "epoch": 0.1920775149615275, "grad_norm": 1.9737545720201175, "learning_rate": 1.918803418803419e-05, "loss": 0.7893, "step": 1348 }, { "epoch": 0.19222000569962952, "grad_norm": 2.0749120611503047, "learning_rate": 1.9202279202279203e-05, "loss": 0.7635, "step": 1349 }, { "epoch": 0.19236249643773154, "grad_norm": 1.8128307969113608, "learning_rate": 1.9216524216524217e-05, "loss": 0.6914, "step": 1350 }, { "epoch": 0.19250498717583356, "grad_norm": 2.1152936000501685, "learning_rate": 1.923076923076923e-05, "loss": 0.7379, "step": 1351 }, { "epoch": 0.1926474779139356, "grad_norm": 1.9490501046727005, "learning_rate": 1.9245014245014246e-05, "loss": 0.787, "step": 1352 }, { "epoch": 0.19278996865203762, "grad_norm": 1.8134360458950303, "learning_rate": 1.925925925925926e-05, "loss": 0.7325, "step": 1353 }, { "epoch": 0.19293245939013964, "grad_norm": 2.0263142394009277, "learning_rate": 1.9273504273504274e-05, "loss": 0.7984, "step": 1354 }, { "epoch": 0.19307495012824166, "grad_norm": 1.980537508823723, "learning_rate": 1.928774928774929e-05, "loss": 0.7945, "step": 1355 }, { "epoch": 0.19321744086634368, "grad_norm": 2.1084807709209623, "learning_rate": 1.9301994301994306e-05, "loss": 0.7896, "step": 1356 }, { "epoch": 0.1933599316044457, "grad_norm": 2.0263686210640466, "learning_rate": 1.9316239316239317e-05, "loss": 0.7236, "step": 1357 }, { "epoch": 0.19350242234254775, "grad_norm": 1.913366306702751, "learning_rate": 1.933048433048433e-05, "loss": 0.7384, "step": 1358 }, { "epoch": 0.19364491308064977, "grad_norm": 2.151462097718851, "learning_rate": 1.9344729344729346e-05, "loss": 0.722, "step": 1359 }, { "epoch": 0.19378740381875179, "grad_norm": 2.618706737215807, "learning_rate": 1.935897435897436e-05, "loss": 0.7083, "step": 1360 }, { "epoch": 0.1939298945568538, "grad_norm": 2.0153140188717584, "learning_rate": 1.9373219373219374e-05, "loss": 0.7042, "step": 1361 }, { "epoch": 0.19407238529495582, "grad_norm": 1.7355487305412562, "learning_rate": 1.938746438746439e-05, "loss": 0.7106, "step": 1362 }, { "epoch": 0.19421487603305784, "grad_norm": 1.8596546853451341, "learning_rate": 1.9401709401709403e-05, "loss": 0.6842, "step": 1363 }, { "epoch": 0.19435736677115986, "grad_norm": 2.1088910609161915, "learning_rate": 1.9415954415954417e-05, "loss": 0.7652, "step": 1364 }, { "epoch": 0.1944998575092619, "grad_norm": 2.1938082612780225, "learning_rate": 1.943019943019943e-05, "loss": 0.718, "step": 1365 }, { "epoch": 0.19464234824736393, "grad_norm": 2.1620379764058537, "learning_rate": 1.9444444444444445e-05, "loss": 0.7507, "step": 1366 }, { "epoch": 0.19478483898546595, "grad_norm": 1.8283480962163046, "learning_rate": 1.945868945868946e-05, "loss": 0.7454, "step": 1367 }, { "epoch": 0.19492732972356797, "grad_norm": 1.750699691302766, "learning_rate": 1.9472934472934474e-05, "loss": 0.6748, "step": 1368 }, { "epoch": 0.19506982046166998, "grad_norm": 1.8715495295999618, "learning_rate": 1.9487179487179488e-05, "loss": 0.742, "step": 1369 }, { "epoch": 0.195212311199772, "grad_norm": 4.420523057667719, "learning_rate": 1.9501424501424502e-05, "loss": 0.6803, "step": 1370 }, { "epoch": 0.19535480193787405, "grad_norm": 1.8159760419433129, "learning_rate": 1.9515669515669517e-05, "loss": 0.8069, "step": 1371 }, { "epoch": 0.19549729267597607, "grad_norm": 1.5894019131042423, "learning_rate": 1.952991452991453e-05, "loss": 0.6891, "step": 1372 }, { "epoch": 0.1956397834140781, "grad_norm": 2.0675472726879596, "learning_rate": 1.9544159544159545e-05, "loss": 0.7252, "step": 1373 }, { "epoch": 0.1957822741521801, "grad_norm": 1.692729141697765, "learning_rate": 1.955840455840456e-05, "loss": 0.7315, "step": 1374 }, { "epoch": 0.19592476489028213, "grad_norm": 1.764336987289969, "learning_rate": 1.9572649572649574e-05, "loss": 0.6961, "step": 1375 }, { "epoch": 0.19606725562838415, "grad_norm": 1.9669216672772574, "learning_rate": 1.9586894586894588e-05, "loss": 0.7176, "step": 1376 }, { "epoch": 0.19620974636648617, "grad_norm": 1.832679969060842, "learning_rate": 1.9601139601139602e-05, "loss": 0.6397, "step": 1377 }, { "epoch": 0.1963522371045882, "grad_norm": 1.9564432733796644, "learning_rate": 1.9615384615384617e-05, "loss": 0.6898, "step": 1378 }, { "epoch": 0.19649472784269023, "grad_norm": 8.04287734876561, "learning_rate": 1.962962962962963e-05, "loss": 0.7192, "step": 1379 }, { "epoch": 0.19663721858079225, "grad_norm": 1.9000554631810052, "learning_rate": 1.9643874643874645e-05, "loss": 0.7201, "step": 1380 }, { "epoch": 0.19677970931889427, "grad_norm": 2.2517841665185596, "learning_rate": 1.965811965811966e-05, "loss": 0.7756, "step": 1381 }, { "epoch": 0.1969222000569963, "grad_norm": 1.7986317734142465, "learning_rate": 1.9672364672364674e-05, "loss": 0.7168, "step": 1382 }, { "epoch": 0.1970646907950983, "grad_norm": 2.0288324074401616, "learning_rate": 1.9686609686609688e-05, "loss": 0.7574, "step": 1383 }, { "epoch": 0.19720718153320035, "grad_norm": 1.8084458657889826, "learning_rate": 1.9700854700854702e-05, "loss": 0.6971, "step": 1384 }, { "epoch": 0.19734967227130237, "grad_norm": 1.903969116515712, "learning_rate": 1.9715099715099716e-05, "loss": 0.7653, "step": 1385 }, { "epoch": 0.1974921630094044, "grad_norm": 1.9668643791231686, "learning_rate": 1.972934472934473e-05, "loss": 0.824, "step": 1386 }, { "epoch": 0.1976346537475064, "grad_norm": 1.8235532896329851, "learning_rate": 1.9743589743589745e-05, "loss": 0.7623, "step": 1387 }, { "epoch": 0.19777714448560843, "grad_norm": 1.8165518753448067, "learning_rate": 1.975783475783476e-05, "loss": 0.6943, "step": 1388 }, { "epoch": 0.19791963522371045, "grad_norm": 1.651726269772696, "learning_rate": 1.9772079772079773e-05, "loss": 0.6974, "step": 1389 }, { "epoch": 0.19806212596181247, "grad_norm": 1.7555529396867313, "learning_rate": 1.9786324786324788e-05, "loss": 0.7541, "step": 1390 }, { "epoch": 0.19820461669991452, "grad_norm": 1.847788148228548, "learning_rate": 1.9800569800569802e-05, "loss": 0.698, "step": 1391 }, { "epoch": 0.19834710743801653, "grad_norm": 2.0327467269733552, "learning_rate": 1.9814814814814816e-05, "loss": 0.6711, "step": 1392 }, { "epoch": 0.19848959817611855, "grad_norm": 2.1338446581887713, "learning_rate": 1.982905982905983e-05, "loss": 0.7422, "step": 1393 }, { "epoch": 0.19863208891422057, "grad_norm": 2.125176620005485, "learning_rate": 1.9843304843304845e-05, "loss": 0.799, "step": 1394 }, { "epoch": 0.1987745796523226, "grad_norm": 1.675774504616298, "learning_rate": 1.985754985754986e-05, "loss": 0.6044, "step": 1395 }, { "epoch": 0.1989170703904246, "grad_norm": 1.8228002225379485, "learning_rate": 1.9871794871794873e-05, "loss": 0.6767, "step": 1396 }, { "epoch": 0.19905956112852666, "grad_norm": 1.9079219311864197, "learning_rate": 1.9886039886039888e-05, "loss": 0.7736, "step": 1397 }, { "epoch": 0.19920205186662868, "grad_norm": 1.8844325988191448, "learning_rate": 1.9900284900284902e-05, "loss": 0.712, "step": 1398 }, { "epoch": 0.1993445426047307, "grad_norm": 1.9743623078220738, "learning_rate": 1.9914529914529916e-05, "loss": 0.7853, "step": 1399 }, { "epoch": 0.19948703334283271, "grad_norm": 1.9647152365518747, "learning_rate": 1.992877492877493e-05, "loss": 0.7373, "step": 1400 }, { "epoch": 0.19962952408093473, "grad_norm": 1.98611002061421, "learning_rate": 1.9943019943019945e-05, "loss": 0.7352, "step": 1401 }, { "epoch": 0.19977201481903675, "grad_norm": 5.171925711493958, "learning_rate": 1.995726495726496e-05, "loss": 0.7985, "step": 1402 }, { "epoch": 0.1999145055571388, "grad_norm": 1.7062702261179639, "learning_rate": 1.9971509971509973e-05, "loss": 0.6403, "step": 1403 }, { "epoch": 0.20005699629524082, "grad_norm": 1.9967314585633538, "learning_rate": 1.9985754985754987e-05, "loss": 0.7384, "step": 1404 }, { "epoch": 0.20019948703334284, "grad_norm": 1.965428656696459, "learning_rate": 2e-05, "loss": 0.746, "step": 1405 }, { "epoch": 0.20034197777144486, "grad_norm": 1.8439148212785232, "learning_rate": 1.999999969073875e-05, "loss": 0.7416, "step": 1406 }, { "epoch": 0.20048446850954688, "grad_norm": 1.8441831898156482, "learning_rate": 1.9999998762955003e-05, "loss": 0.7089, "step": 1407 }, { "epoch": 0.2006269592476489, "grad_norm": 2.808811509305925, "learning_rate": 1.9999997216648826e-05, "loss": 0.7918, "step": 1408 }, { "epoch": 0.20076944998575091, "grad_norm": 2.0361705043247205, "learning_rate": 1.9999995051820308e-05, "loss": 0.7585, "step": 1409 }, { "epoch": 0.20091194072385296, "grad_norm": 1.7773745083660437, "learning_rate": 1.999999226846959e-05, "loss": 0.7272, "step": 1410 }, { "epoch": 0.20105443146195498, "grad_norm": 1.8452266564477542, "learning_rate": 1.9999988866596842e-05, "loss": 0.7477, "step": 1411 }, { "epoch": 0.201196922200057, "grad_norm": 1.8648706351836517, "learning_rate": 1.999998484620227e-05, "loss": 0.8447, "step": 1412 }, { "epoch": 0.20133941293815902, "grad_norm": 1.8875440137897308, "learning_rate": 1.999998020728613e-05, "loss": 0.764, "step": 1413 }, { "epoch": 0.20148190367626104, "grad_norm": 1.8486685438103723, "learning_rate": 1.99999749498487e-05, "loss": 0.7236, "step": 1414 }, { "epoch": 0.20162439441436306, "grad_norm": 1.9140257863926908, "learning_rate": 1.9999969073890316e-05, "loss": 0.8695, "step": 1415 }, { "epoch": 0.2017668851524651, "grad_norm": 1.7643965948721565, "learning_rate": 1.999996257941133e-05, "loss": 0.761, "step": 1416 }, { "epoch": 0.20190937589056712, "grad_norm": 1.8407653891015328, "learning_rate": 1.9999955466412152e-05, "loss": 0.6887, "step": 1417 }, { "epoch": 0.20205186662866914, "grad_norm": 1.613211467942385, "learning_rate": 1.9999947734893222e-05, "loss": 0.7244, "step": 1418 }, { "epoch": 0.20219435736677116, "grad_norm": 1.8052365604922194, "learning_rate": 1.9999939384855008e-05, "loss": 0.7688, "step": 1419 }, { "epoch": 0.20233684810487318, "grad_norm": 1.739026016179099, "learning_rate": 1.9999930416298042e-05, "loss": 0.7224, "step": 1420 }, { "epoch": 0.2024793388429752, "grad_norm": 1.6985146483229212, "learning_rate": 1.9999920829222863e-05, "loss": 0.7555, "step": 1421 }, { "epoch": 0.20262182958107722, "grad_norm": 1.90947647743732, "learning_rate": 1.9999910623630076e-05, "loss": 0.7387, "step": 1422 }, { "epoch": 0.20276432031917926, "grad_norm": 2.423152950796157, "learning_rate": 1.9999899799520306e-05, "loss": 0.7767, "step": 1423 }, { "epoch": 0.20290681105728128, "grad_norm": 1.9207071138000362, "learning_rate": 1.9999888356894227e-05, "loss": 0.7606, "step": 1424 }, { "epoch": 0.2030493017953833, "grad_norm": 1.6979862597796052, "learning_rate": 1.9999876295752544e-05, "loss": 0.7487, "step": 1425 }, { "epoch": 0.20319179253348532, "grad_norm": 1.9480905955754388, "learning_rate": 1.9999863616096e-05, "loss": 0.8123, "step": 1426 }, { "epoch": 0.20333428327158734, "grad_norm": 1.697085700878988, "learning_rate": 1.999985031792538e-05, "loss": 0.6859, "step": 1427 }, { "epoch": 0.20347677400968936, "grad_norm": 1.8379740076659845, "learning_rate": 1.9999836401241516e-05, "loss": 0.8478, "step": 1428 }, { "epoch": 0.2036192647477914, "grad_norm": 1.8227772207933286, "learning_rate": 1.9999821866045254e-05, "loss": 0.819, "step": 1429 }, { "epoch": 0.20376175548589343, "grad_norm": 1.877317633920065, "learning_rate": 1.9999806712337508e-05, "loss": 0.851, "step": 1430 }, { "epoch": 0.20390424622399544, "grad_norm": 1.8481996730756007, "learning_rate": 1.9999790940119202e-05, "loss": 0.8357, "step": 1431 }, { "epoch": 0.20404673696209746, "grad_norm": 1.8895469393550406, "learning_rate": 1.9999774549391323e-05, "loss": 0.7272, "step": 1432 }, { "epoch": 0.20418922770019948, "grad_norm": 3.721901415534161, "learning_rate": 1.9999757540154876e-05, "loss": 0.6467, "step": 1433 }, { "epoch": 0.2043317184383015, "grad_norm": 1.6507038205271733, "learning_rate": 1.9999739912410915e-05, "loss": 0.8003, "step": 1434 }, { "epoch": 0.20447420917640352, "grad_norm": 1.9278032892451842, "learning_rate": 1.9999721666160532e-05, "loss": 0.7067, "step": 1435 }, { "epoch": 0.20461669991450557, "grad_norm": 2.079598109597224, "learning_rate": 1.9999702801404858e-05, "loss": 0.7338, "step": 1436 }, { "epoch": 0.2047591906526076, "grad_norm": 1.8577809187298693, "learning_rate": 1.9999683318145054e-05, "loss": 0.7718, "step": 1437 }, { "epoch": 0.2049016813907096, "grad_norm": 1.8206169789934585, "learning_rate": 1.9999663216382332e-05, "loss": 0.7665, "step": 1438 }, { "epoch": 0.20504417212881162, "grad_norm": 2.147996904156347, "learning_rate": 1.999964249611793e-05, "loss": 0.7136, "step": 1439 }, { "epoch": 0.20518666286691364, "grad_norm": 1.6799784115081124, "learning_rate": 1.999962115735313e-05, "loss": 0.6998, "step": 1440 }, { "epoch": 0.20532915360501566, "grad_norm": 1.9395510237651665, "learning_rate": 1.999959920008925e-05, "loss": 0.7846, "step": 1441 }, { "epoch": 0.2054716443431177, "grad_norm": 1.9452380742357958, "learning_rate": 1.9999576624327655e-05, "loss": 0.7907, "step": 1442 }, { "epoch": 0.20561413508121973, "grad_norm": 2.0140187404847345, "learning_rate": 1.9999553430069736e-05, "loss": 0.7971, "step": 1443 }, { "epoch": 0.20575662581932175, "grad_norm": 1.8112147094982076, "learning_rate": 1.999952961731693e-05, "loss": 0.6974, "step": 1444 }, { "epoch": 0.20589911655742377, "grad_norm": 2.081477364056666, "learning_rate": 1.999950518607071e-05, "loss": 0.7523, "step": 1445 }, { "epoch": 0.20604160729552579, "grad_norm": 1.741410621619049, "learning_rate": 1.9999480136332585e-05, "loss": 0.7489, "step": 1446 }, { "epoch": 0.2061840980336278, "grad_norm": 1.6691535611203276, "learning_rate": 1.9999454468104106e-05, "loss": 0.7152, "step": 1447 }, { "epoch": 0.20632658877172982, "grad_norm": 1.7387423666662656, "learning_rate": 1.9999428181386858e-05, "loss": 0.7605, "step": 1448 }, { "epoch": 0.20646907950983187, "grad_norm": 1.8076603181722346, "learning_rate": 1.9999401276182468e-05, "loss": 0.7714, "step": 1449 }, { "epoch": 0.2066115702479339, "grad_norm": 1.6163379964685707, "learning_rate": 1.9999373752492605e-05, "loss": 0.7395, "step": 1450 }, { "epoch": 0.2067540609860359, "grad_norm": 1.7027623412622834, "learning_rate": 1.9999345610318965e-05, "loss": 0.7181, "step": 1451 }, { "epoch": 0.20689655172413793, "grad_norm": 2.2377411345830307, "learning_rate": 1.999931684966329e-05, "loss": 0.7421, "step": 1452 }, { "epoch": 0.20703904246223995, "grad_norm": 1.7265739268134217, "learning_rate": 1.9999287470527362e-05, "loss": 0.7047, "step": 1453 }, { "epoch": 0.20718153320034197, "grad_norm": 1.7768681407201936, "learning_rate": 1.9999257472912995e-05, "loss": 0.7214, "step": 1454 }, { "epoch": 0.207324023938444, "grad_norm": 3.00353840446928, "learning_rate": 1.9999226856822047e-05, "loss": 0.7174, "step": 1455 }, { "epoch": 0.20746651467654603, "grad_norm": 2.0218635486299554, "learning_rate": 1.999919562225641e-05, "loss": 0.7943, "step": 1456 }, { "epoch": 0.20760900541464805, "grad_norm": 1.6521982810665345, "learning_rate": 1.9999163769218014e-05, "loss": 0.6741, "step": 1457 }, { "epoch": 0.20775149615275007, "grad_norm": 1.641285887757032, "learning_rate": 1.9999131297708833e-05, "loss": 0.7459, "step": 1458 }, { "epoch": 0.2078939868908521, "grad_norm": 2.0611736417455058, "learning_rate": 1.9999098207730877e-05, "loss": 0.7507, "step": 1459 }, { "epoch": 0.2080364776289541, "grad_norm": 1.6541538102086997, "learning_rate": 1.9999064499286188e-05, "loss": 0.7316, "step": 1460 }, { "epoch": 0.20817896836705613, "grad_norm": 1.691762174193164, "learning_rate": 1.999903017237685e-05, "loss": 0.7766, "step": 1461 }, { "epoch": 0.20832145910515817, "grad_norm": 1.7833396917218172, "learning_rate": 1.9998995227004988e-05, "loss": 0.6639, "step": 1462 }, { "epoch": 0.2084639498432602, "grad_norm": 2.0921848860148695, "learning_rate": 1.9998959663172764e-05, "loss": 0.7384, "step": 1463 }, { "epoch": 0.2086064405813622, "grad_norm": 2.5843730171365635, "learning_rate": 1.9998923480882385e-05, "loss": 0.794, "step": 1464 }, { "epoch": 0.20874893131946423, "grad_norm": 1.7388175760167177, "learning_rate": 1.9998886680136077e-05, "loss": 0.6757, "step": 1465 }, { "epoch": 0.20889142205756625, "grad_norm": 2.029672418585896, "learning_rate": 1.9998849260936116e-05, "loss": 0.8043, "step": 1466 }, { "epoch": 0.20903391279566827, "grad_norm": 1.6376008448590846, "learning_rate": 1.999881122328483e-05, "loss": 0.7707, "step": 1467 }, { "epoch": 0.20917640353377032, "grad_norm": 2.0080249683885696, "learning_rate": 1.9998772567184557e-05, "loss": 0.8094, "step": 1468 }, { "epoch": 0.20931889427187234, "grad_norm": 1.7111844510813108, "learning_rate": 1.99987332926377e-05, "loss": 0.6964, "step": 1469 }, { "epoch": 0.20946138500997435, "grad_norm": 1.7936345648381702, "learning_rate": 1.9998693399646675e-05, "loss": 0.792, "step": 1470 }, { "epoch": 0.20960387574807637, "grad_norm": 1.7118212509945467, "learning_rate": 1.9998652888213962e-05, "loss": 0.6798, "step": 1471 }, { "epoch": 0.2097463664861784, "grad_norm": 1.904043061915581, "learning_rate": 1.999861175834206e-05, "loss": 0.8414, "step": 1472 }, { "epoch": 0.2098888572242804, "grad_norm": 1.6898489590405539, "learning_rate": 1.9998570010033515e-05, "loss": 0.7027, "step": 1473 }, { "epoch": 0.21003134796238246, "grad_norm": 1.7660011767813626, "learning_rate": 1.9998527643290907e-05, "loss": 0.7238, "step": 1474 }, { "epoch": 0.21017383870048448, "grad_norm": 1.8822177690618846, "learning_rate": 1.999848465811686e-05, "loss": 0.7824, "step": 1475 }, { "epoch": 0.2103163294385865, "grad_norm": 1.8279652786312892, "learning_rate": 1.9998441054514028e-05, "loss": 0.6436, "step": 1476 }, { "epoch": 0.21045882017668852, "grad_norm": 1.9853720756045061, "learning_rate": 1.9998396832485113e-05, "loss": 0.6892, "step": 1477 }, { "epoch": 0.21060131091479053, "grad_norm": 1.8289305299072502, "learning_rate": 1.9998351992032852e-05, "loss": 0.7763, "step": 1478 }, { "epoch": 0.21074380165289255, "grad_norm": 2.027856497815801, "learning_rate": 1.999830653316001e-05, "loss": 0.6397, "step": 1479 }, { "epoch": 0.21088629239099457, "grad_norm": 2.0151885316067886, "learning_rate": 1.9998260455869404e-05, "loss": 0.7271, "step": 1480 }, { "epoch": 0.21102878312909662, "grad_norm": 1.6985172166090172, "learning_rate": 1.9998213760163887e-05, "loss": 0.6757, "step": 1481 }, { "epoch": 0.21117127386719864, "grad_norm": 1.929998917612393, "learning_rate": 1.999816644604634e-05, "loss": 0.7404, "step": 1482 }, { "epoch": 0.21131376460530066, "grad_norm": 1.6987896147830341, "learning_rate": 1.9998118513519694e-05, "loss": 0.664, "step": 1483 }, { "epoch": 0.21145625534340268, "grad_norm": 1.8081396098603684, "learning_rate": 1.9998069962586913e-05, "loss": 0.7236, "step": 1484 }, { "epoch": 0.2115987460815047, "grad_norm": 1.630022215527111, "learning_rate": 1.9998020793251e-05, "loss": 0.6503, "step": 1485 }, { "epoch": 0.21174123681960672, "grad_norm": 1.8468359346450096, "learning_rate": 1.9997971005514992e-05, "loss": 0.6385, "step": 1486 }, { "epoch": 0.21188372755770876, "grad_norm": 1.8691398518479148, "learning_rate": 1.999792059938198e-05, "loss": 0.777, "step": 1487 }, { "epoch": 0.21202621829581078, "grad_norm": 2.021063764714194, "learning_rate": 1.999786957485507e-05, "loss": 0.7743, "step": 1488 }, { "epoch": 0.2121687090339128, "grad_norm": 1.8604127208727255, "learning_rate": 1.999781793193742e-05, "loss": 0.7026, "step": 1489 }, { "epoch": 0.21231119977201482, "grad_norm": 1.518317854709355, "learning_rate": 1.999776567063223e-05, "loss": 0.6734, "step": 1490 }, { "epoch": 0.21245369051011684, "grad_norm": 1.882685942180601, "learning_rate": 1.9997712790942726e-05, "loss": 0.7424, "step": 1491 }, { "epoch": 0.21259618124821886, "grad_norm": 2.7127289069729956, "learning_rate": 1.9997659292872183e-05, "loss": 0.6402, "step": 1492 }, { "epoch": 0.21273867198632088, "grad_norm": 1.7850991917120491, "learning_rate": 1.9997605176423912e-05, "loss": 0.6898, "step": 1493 }, { "epoch": 0.21288116272442292, "grad_norm": 1.8588279046547842, "learning_rate": 1.9997550441601254e-05, "loss": 0.6887, "step": 1494 }, { "epoch": 0.21302365346252494, "grad_norm": 1.855382836255114, "learning_rate": 1.9997495088407596e-05, "loss": 0.6742, "step": 1495 }, { "epoch": 0.21316614420062696, "grad_norm": 1.7184785785216103, "learning_rate": 1.9997439116846365e-05, "loss": 0.79, "step": 1496 }, { "epoch": 0.21330863493872898, "grad_norm": 1.7227797133730776, "learning_rate": 1.9997382526921023e-05, "loss": 0.7206, "step": 1497 }, { "epoch": 0.213451125676831, "grad_norm": 1.8085989018990016, "learning_rate": 1.9997325318635066e-05, "loss": 0.7197, "step": 1498 }, { "epoch": 0.21359361641493302, "grad_norm": 1.991536874664436, "learning_rate": 1.9997267491992032e-05, "loss": 0.8401, "step": 1499 }, { "epoch": 0.21373610715303507, "grad_norm": 1.7693918456065008, "learning_rate": 1.9997209046995506e-05, "loss": 0.7183, "step": 1500 }, { "epoch": 0.21387859789113708, "grad_norm": 1.826415018142786, "learning_rate": 1.999714998364909e-05, "loss": 0.7307, "step": 1501 }, { "epoch": 0.2140210886292391, "grad_norm": 1.9922874571725093, "learning_rate": 1.9997090301956452e-05, "loss": 0.8332, "step": 1502 }, { "epoch": 0.21416357936734112, "grad_norm": 1.7452216802430354, "learning_rate": 1.999703000192127e-05, "loss": 0.7274, "step": 1503 }, { "epoch": 0.21430607010544314, "grad_norm": 1.86175967590612, "learning_rate": 1.9996969083547285e-05, "loss": 0.8131, "step": 1504 }, { "epoch": 0.21444856084354516, "grad_norm": 1.7032094118727987, "learning_rate": 1.9996907546838258e-05, "loss": 0.7392, "step": 1505 }, { "epoch": 0.21459105158164718, "grad_norm": 1.7358132650950753, "learning_rate": 1.9996845391797998e-05, "loss": 0.7097, "step": 1506 }, { "epoch": 0.21473354231974923, "grad_norm": 1.6794402870872438, "learning_rate": 1.9996782618430344e-05, "loss": 0.7769, "step": 1507 }, { "epoch": 0.21487603305785125, "grad_norm": 1.633326448970263, "learning_rate": 1.9996719226739187e-05, "loss": 0.6827, "step": 1508 }, { "epoch": 0.21501852379595326, "grad_norm": 1.6790168579967395, "learning_rate": 1.999665521672844e-05, "loss": 0.7775, "step": 1509 }, { "epoch": 0.21516101453405528, "grad_norm": 1.883061857895782, "learning_rate": 1.999659058840207e-05, "loss": 0.748, "step": 1510 }, { "epoch": 0.2153035052721573, "grad_norm": 1.7393158053310696, "learning_rate": 1.999652534176407e-05, "loss": 0.6814, "step": 1511 }, { "epoch": 0.21544599601025932, "grad_norm": 1.7243417978078297, "learning_rate": 1.9996459476818473e-05, "loss": 0.7589, "step": 1512 }, { "epoch": 0.21558848674836137, "grad_norm": 1.9040111959647221, "learning_rate": 1.999639299356936e-05, "loss": 0.8753, "step": 1513 }, { "epoch": 0.2157309774864634, "grad_norm": 3.2123539398708134, "learning_rate": 1.9996325892020834e-05, "loss": 0.7123, "step": 1514 }, { "epoch": 0.2158734682245654, "grad_norm": 1.764129283463376, "learning_rate": 1.9996258172177057e-05, "loss": 0.6745, "step": 1515 }, { "epoch": 0.21601595896266743, "grad_norm": 1.717682221231401, "learning_rate": 1.9996189834042206e-05, "loss": 0.8233, "step": 1516 }, { "epoch": 0.21615844970076944, "grad_norm": 1.6797178514976487, "learning_rate": 1.9996120877620514e-05, "loss": 0.7239, "step": 1517 }, { "epoch": 0.21630094043887146, "grad_norm": 1.7490421576588688, "learning_rate": 1.9996051302916247e-05, "loss": 0.7349, "step": 1518 }, { "epoch": 0.21644343117697348, "grad_norm": 1.6998413209318763, "learning_rate": 1.9995981109933704e-05, "loss": 0.7776, "step": 1519 }, { "epoch": 0.21658592191507553, "grad_norm": 1.7111222055462156, "learning_rate": 1.999591029867723e-05, "loss": 0.6709, "step": 1520 }, { "epoch": 0.21672841265317755, "grad_norm": 1.7627170401770915, "learning_rate": 1.9995838869151207e-05, "loss": 0.7786, "step": 1521 }, { "epoch": 0.21687090339127957, "grad_norm": 1.5491019893649063, "learning_rate": 1.9995766821360046e-05, "loss": 0.7063, "step": 1522 }, { "epoch": 0.2170133941293816, "grad_norm": 1.7656372689010955, "learning_rate": 1.9995694155308206e-05, "loss": 0.6636, "step": 1523 }, { "epoch": 0.2171558848674836, "grad_norm": 1.6553221957070856, "learning_rate": 1.999562087100019e-05, "loss": 0.7302, "step": 1524 }, { "epoch": 0.21729837560558563, "grad_norm": 1.6319683528772828, "learning_rate": 1.9995546968440515e-05, "loss": 0.6595, "step": 1525 }, { "epoch": 0.21744086634368767, "grad_norm": 1.5923346426681038, "learning_rate": 1.9995472447633767e-05, "loss": 0.7378, "step": 1526 }, { "epoch": 0.2175833570817897, "grad_norm": 1.8498002808897696, "learning_rate": 1.9995397308584545e-05, "loss": 0.6918, "step": 1527 }, { "epoch": 0.2177258478198917, "grad_norm": 1.745979490340252, "learning_rate": 1.99953215512975e-05, "loss": 0.7619, "step": 1528 }, { "epoch": 0.21786833855799373, "grad_norm": 1.9144000495275184, "learning_rate": 1.9995245175777322e-05, "loss": 0.74, "step": 1529 }, { "epoch": 0.21801082929609575, "grad_norm": 1.6648725552218742, "learning_rate": 1.999516818202873e-05, "loss": 0.7243, "step": 1530 }, { "epoch": 0.21815332003419777, "grad_norm": 1.8144853178817981, "learning_rate": 1.9995090570056484e-05, "loss": 0.76, "step": 1531 }, { "epoch": 0.21829581077229981, "grad_norm": 1.6011928614581141, "learning_rate": 1.9995012339865394e-05, "loss": 0.7597, "step": 1532 }, { "epoch": 0.21843830151040183, "grad_norm": 1.7163965635116791, "learning_rate": 1.9994933491460287e-05, "loss": 0.6806, "step": 1533 }, { "epoch": 0.21858079224850385, "grad_norm": 1.5134780738033444, "learning_rate": 1.999485402484605e-05, "loss": 0.7387, "step": 1534 }, { "epoch": 0.21872328298660587, "grad_norm": 1.822951384061366, "learning_rate": 1.9994773940027593e-05, "loss": 0.7985, "step": 1535 }, { "epoch": 0.2188657737247079, "grad_norm": 1.722113247443824, "learning_rate": 1.999469323700987e-05, "loss": 0.7446, "step": 1536 }, { "epoch": 0.2190082644628099, "grad_norm": 1.7190066853722161, "learning_rate": 1.999461191579787e-05, "loss": 0.7641, "step": 1537 }, { "epoch": 0.21915075520091193, "grad_norm": 1.812300868397123, "learning_rate": 1.999452997639663e-05, "loss": 0.7749, "step": 1538 }, { "epoch": 0.21929324593901398, "grad_norm": 2.079079889934768, "learning_rate": 1.999444741881121e-05, "loss": 0.7324, "step": 1539 }, { "epoch": 0.219435736677116, "grad_norm": 1.8317990621281577, "learning_rate": 1.9994364243046724e-05, "loss": 0.7752, "step": 1540 }, { "epoch": 0.219578227415218, "grad_norm": 1.6774990381599242, "learning_rate": 1.9994280449108308e-05, "loss": 0.7798, "step": 1541 }, { "epoch": 0.21972071815332003, "grad_norm": 1.904766782568683, "learning_rate": 1.9994196037001155e-05, "loss": 0.7342, "step": 1542 }, { "epoch": 0.21986320889142205, "grad_norm": 1.7470755833555038, "learning_rate": 1.999411100673048e-05, "loss": 0.635, "step": 1543 }, { "epoch": 0.22000569962952407, "grad_norm": 1.721616527574478, "learning_rate": 1.999402535830154e-05, "loss": 0.693, "step": 1544 }, { "epoch": 0.22014819036762612, "grad_norm": 1.769537805369906, "learning_rate": 1.9993939091719636e-05, "loss": 0.7341, "step": 1545 }, { "epoch": 0.22029068110572814, "grad_norm": 2.2081520669917953, "learning_rate": 1.9993852206990106e-05, "loss": 0.7133, "step": 1546 }, { "epoch": 0.22043317184383016, "grad_norm": 1.9355069591799292, "learning_rate": 1.9993764704118323e-05, "loss": 0.7479, "step": 1547 }, { "epoch": 0.22057566258193217, "grad_norm": 1.6216026994369532, "learning_rate": 1.9993676583109694e-05, "loss": 0.75, "step": 1548 }, { "epoch": 0.2207181533200342, "grad_norm": 1.8964655797785077, "learning_rate": 1.9993587843969675e-05, "loss": 0.7976, "step": 1549 }, { "epoch": 0.2208606440581362, "grad_norm": 1.7566381073397448, "learning_rate": 1.999349848670375e-05, "loss": 0.8226, "step": 1550 }, { "epoch": 0.22100313479623823, "grad_norm": 1.6349032528679652, "learning_rate": 1.9993408511317455e-05, "loss": 0.7943, "step": 1551 }, { "epoch": 0.22114562553434028, "grad_norm": 1.6409737174467294, "learning_rate": 1.9993317917816343e-05, "loss": 0.6998, "step": 1552 }, { "epoch": 0.2212881162724423, "grad_norm": 1.783872013449325, "learning_rate": 1.9993226706206027e-05, "loss": 0.7487, "step": 1553 }, { "epoch": 0.22143060701054432, "grad_norm": 1.7899529016355904, "learning_rate": 1.9993134876492143e-05, "loss": 0.7583, "step": 1554 }, { "epoch": 0.22157309774864634, "grad_norm": 1.69734792558044, "learning_rate": 1.9993042428680374e-05, "loss": 0.6952, "step": 1555 }, { "epoch": 0.22171558848674836, "grad_norm": 1.9542589652281213, "learning_rate": 1.9992949362776436e-05, "loss": 0.6487, "step": 1556 }, { "epoch": 0.22185807922485037, "grad_norm": 1.7595765268887666, "learning_rate": 1.9992855678786088e-05, "loss": 0.774, "step": 1557 }, { "epoch": 0.22200056996295242, "grad_norm": 3.261118234545809, "learning_rate": 1.999276137671512e-05, "loss": 0.7516, "step": 1558 }, { "epoch": 0.22214306070105444, "grad_norm": 1.9408570485916168, "learning_rate": 1.9992666456569372e-05, "loss": 0.7853, "step": 1559 }, { "epoch": 0.22228555143915646, "grad_norm": 2.1327558945693457, "learning_rate": 1.999257091835471e-05, "loss": 0.7204, "step": 1560 }, { "epoch": 0.22242804217725848, "grad_norm": 1.6844698120670116, "learning_rate": 1.999247476207704e-05, "loss": 0.7712, "step": 1561 }, { "epoch": 0.2225705329153605, "grad_norm": 2.075277331063413, "learning_rate": 1.9992377987742317e-05, "loss": 0.7949, "step": 1562 }, { "epoch": 0.22271302365346252, "grad_norm": 1.5768595397348608, "learning_rate": 1.9992280595356525e-05, "loss": 0.7333, "step": 1563 }, { "epoch": 0.22285551439156454, "grad_norm": 1.6451067671534203, "learning_rate": 1.9992182584925682e-05, "loss": 0.7342, "step": 1564 }, { "epoch": 0.22299800512966658, "grad_norm": 1.7225146990104387, "learning_rate": 1.999208395645586e-05, "loss": 0.678, "step": 1565 }, { "epoch": 0.2231404958677686, "grad_norm": 1.5956527427383265, "learning_rate": 1.9991984709953147e-05, "loss": 0.7301, "step": 1566 }, { "epoch": 0.22328298660587062, "grad_norm": 1.7466481423827456, "learning_rate": 1.9991884845423693e-05, "loss": 0.7381, "step": 1567 }, { "epoch": 0.22342547734397264, "grad_norm": 1.6474983561678072, "learning_rate": 1.999178436287367e-05, "loss": 0.6435, "step": 1568 }, { "epoch": 0.22356796808207466, "grad_norm": 1.7025329138826375, "learning_rate": 1.9991683262309292e-05, "loss": 0.6715, "step": 1569 }, { "epoch": 0.22371045882017668, "grad_norm": 1.7807240843871748, "learning_rate": 1.9991581543736813e-05, "loss": 0.7284, "step": 1570 }, { "epoch": 0.22385294955827872, "grad_norm": 2.449219565338302, "learning_rate": 1.9991479207162527e-05, "loss": 0.7408, "step": 1571 }, { "epoch": 0.22399544029638074, "grad_norm": 1.7026749665324405, "learning_rate": 1.999137625259276e-05, "loss": 0.6671, "step": 1572 }, { "epoch": 0.22413793103448276, "grad_norm": 1.7730918109969291, "learning_rate": 1.9991272680033883e-05, "loss": 0.7502, "step": 1573 }, { "epoch": 0.22428042177258478, "grad_norm": 1.804095855602118, "learning_rate": 1.9991168489492302e-05, "loss": 0.7178, "step": 1574 }, { "epoch": 0.2244229125106868, "grad_norm": 1.6858315345888402, "learning_rate": 1.999106368097446e-05, "loss": 0.7303, "step": 1575 }, { "epoch": 0.22456540324878882, "grad_norm": 1.7456070415521152, "learning_rate": 1.9990958254486838e-05, "loss": 0.7616, "step": 1576 }, { "epoch": 0.22470789398689084, "grad_norm": 1.6237318730420842, "learning_rate": 1.9990852210035962e-05, "loss": 0.8072, "step": 1577 }, { "epoch": 0.22485038472499289, "grad_norm": 1.611980862438539, "learning_rate": 1.9990745547628384e-05, "loss": 0.6244, "step": 1578 }, { "epoch": 0.2249928754630949, "grad_norm": 1.587562662772652, "learning_rate": 1.9990638267270708e-05, "loss": 0.6335, "step": 1579 }, { "epoch": 0.22513536620119692, "grad_norm": 1.9381990722925062, "learning_rate": 1.9990530368969568e-05, "loss": 0.8855, "step": 1580 }, { "epoch": 0.22527785693929894, "grad_norm": 1.858449909119512, "learning_rate": 1.9990421852731634e-05, "loss": 0.7308, "step": 1581 }, { "epoch": 0.22542034767740096, "grad_norm": 1.8750850089592306, "learning_rate": 1.999031271856362e-05, "loss": 0.6991, "step": 1582 }, { "epoch": 0.22556283841550298, "grad_norm": 1.8402748625632992, "learning_rate": 1.999020296647228e-05, "loss": 0.7532, "step": 1583 }, { "epoch": 0.22570532915360503, "grad_norm": 1.6262308550604956, "learning_rate": 1.9990092596464398e-05, "loss": 0.7187, "step": 1584 }, { "epoch": 0.22584781989170705, "grad_norm": 1.744530713852818, "learning_rate": 1.9989981608546804e-05, "loss": 0.8107, "step": 1585 }, { "epoch": 0.22599031062980907, "grad_norm": 1.7096503782035664, "learning_rate": 1.9989870002726356e-05, "loss": 0.7444, "step": 1586 }, { "epoch": 0.22613280136791108, "grad_norm": 4.455618177168295, "learning_rate": 1.9989757779009963e-05, "loss": 0.6575, "step": 1587 }, { "epoch": 0.2262752921060131, "grad_norm": 1.9023631495651945, "learning_rate": 1.9989644937404566e-05, "loss": 0.7497, "step": 1588 }, { "epoch": 0.22641778284411512, "grad_norm": 3.418084882610644, "learning_rate": 1.9989531477917145e-05, "loss": 0.7943, "step": 1589 }, { "epoch": 0.22656027358221714, "grad_norm": 2.4360968568036427, "learning_rate": 1.9989417400554717e-05, "loss": 0.7373, "step": 1590 }, { "epoch": 0.2267027643203192, "grad_norm": 1.8807831532444133, "learning_rate": 1.9989302705324332e-05, "loss": 0.7444, "step": 1591 }, { "epoch": 0.2268452550584212, "grad_norm": 1.5416412774004362, "learning_rate": 1.9989187392233097e-05, "loss": 0.6719, "step": 1592 }, { "epoch": 0.22698774579652323, "grad_norm": 1.896931435443659, "learning_rate": 1.998907146128813e-05, "loss": 0.7554, "step": 1593 }, { "epoch": 0.22713023653462525, "grad_norm": 1.7093902988322278, "learning_rate": 1.9988954912496612e-05, "loss": 0.78, "step": 1594 }, { "epoch": 0.22727272727272727, "grad_norm": 1.7658565252813359, "learning_rate": 1.9988837745865746e-05, "loss": 0.6817, "step": 1595 }, { "epoch": 0.22741521801082928, "grad_norm": 2.0370018848756843, "learning_rate": 1.9988719961402784e-05, "loss": 0.7205, "step": 1596 }, { "epoch": 0.22755770874893133, "grad_norm": 2.4631973754654672, "learning_rate": 1.9988601559115007e-05, "loss": 0.7486, "step": 1597 }, { "epoch": 0.22770019948703335, "grad_norm": 1.6013374206648772, "learning_rate": 1.998848253900974e-05, "loss": 0.7118, "step": 1598 }, { "epoch": 0.22784269022513537, "grad_norm": 1.6668712256288074, "learning_rate": 1.9988362901094343e-05, "loss": 0.7305, "step": 1599 }, { "epoch": 0.2279851809632374, "grad_norm": 2.3209816603491467, "learning_rate": 1.998824264537622e-05, "loss": 0.6788, "step": 1600 }, { "epoch": 0.2281276717013394, "grad_norm": 1.891986345916166, "learning_rate": 1.9988121771862805e-05, "loss": 0.8401, "step": 1601 }, { "epoch": 0.22827016243944143, "grad_norm": 1.6136005980263841, "learning_rate": 1.9988000280561574e-05, "loss": 0.7115, "step": 1602 }, { "epoch": 0.22841265317754347, "grad_norm": 1.9843459997311927, "learning_rate": 1.9987878171480047e-05, "loss": 0.8013, "step": 1603 }, { "epoch": 0.2285551439156455, "grad_norm": 1.6293715492767724, "learning_rate": 1.998775544462577e-05, "loss": 0.721, "step": 1604 }, { "epoch": 0.2286976346537475, "grad_norm": 1.7294843128077797, "learning_rate": 1.9987632100006336e-05, "loss": 0.8278, "step": 1605 }, { "epoch": 0.22884012539184953, "grad_norm": 1.6601821152896372, "learning_rate": 1.998750813762938e-05, "loss": 0.7671, "step": 1606 }, { "epoch": 0.22898261612995155, "grad_norm": 1.6199569376474934, "learning_rate": 1.9987383557502562e-05, "loss": 0.7149, "step": 1607 }, { "epoch": 0.22912510686805357, "grad_norm": 1.7236373790659112, "learning_rate": 1.998725835963359e-05, "loss": 0.7198, "step": 1608 }, { "epoch": 0.2292675976061556, "grad_norm": 2.059424805538835, "learning_rate": 1.998713254403021e-05, "loss": 0.6917, "step": 1609 }, { "epoch": 0.22941008834425763, "grad_norm": 1.8518823218128568, "learning_rate": 1.9987006110700196e-05, "loss": 0.7927, "step": 1610 }, { "epoch": 0.22955257908235965, "grad_norm": 2.546529654585229, "learning_rate": 1.998687905965138e-05, "loss": 0.6936, "step": 1611 }, { "epoch": 0.22969506982046167, "grad_norm": 1.611761232629285, "learning_rate": 1.998675139089161e-05, "loss": 0.7151, "step": 1612 }, { "epoch": 0.2298375605585637, "grad_norm": 1.7832963036335223, "learning_rate": 1.998662310442879e-05, "loss": 0.7888, "step": 1613 }, { "epoch": 0.2299800512966657, "grad_norm": 1.4692511400303787, "learning_rate": 1.998649420027085e-05, "loss": 0.7379, "step": 1614 }, { "epoch": 0.23012254203476773, "grad_norm": 1.7945999027228132, "learning_rate": 1.9986364678425764e-05, "loss": 0.7402, "step": 1615 }, { "epoch": 0.23026503277286978, "grad_norm": 1.9381387690688654, "learning_rate": 1.9986234538901546e-05, "loss": 0.7593, "step": 1616 }, { "epoch": 0.2304075235109718, "grad_norm": 1.6421697126444224, "learning_rate": 1.9986103781706243e-05, "loss": 0.7077, "step": 1617 }, { "epoch": 0.23055001424907381, "grad_norm": 1.6704938063286612, "learning_rate": 1.998597240684794e-05, "loss": 0.7756, "step": 1618 }, { "epoch": 0.23069250498717583, "grad_norm": 1.6150162147005713, "learning_rate": 1.998584041433477e-05, "loss": 0.6766, "step": 1619 }, { "epoch": 0.23083499572527785, "grad_norm": 1.7055773009722168, "learning_rate": 1.9985707804174893e-05, "loss": 0.7483, "step": 1620 }, { "epoch": 0.23097748646337987, "grad_norm": 1.8634302439420194, "learning_rate": 1.998557457637651e-05, "loss": 0.8151, "step": 1621 }, { "epoch": 0.2311199772014819, "grad_norm": 2.0246126954782047, "learning_rate": 1.9985440730947864e-05, "loss": 0.6677, "step": 1622 }, { "epoch": 0.23126246793958394, "grad_norm": 1.6400840758077462, "learning_rate": 1.9985306267897225e-05, "loss": 0.7215, "step": 1623 }, { "epoch": 0.23140495867768596, "grad_norm": 2.149301241607555, "learning_rate": 1.9985171187232923e-05, "loss": 0.7695, "step": 1624 }, { "epoch": 0.23154744941578798, "grad_norm": 1.523262322247495, "learning_rate": 1.9985035488963306e-05, "loss": 0.6375, "step": 1625 }, { "epoch": 0.23168994015389, "grad_norm": 1.8381046222415547, "learning_rate": 1.998489917309677e-05, "loss": 0.6459, "step": 1626 }, { "epoch": 0.23183243089199201, "grad_norm": 1.6901968315021232, "learning_rate": 1.9984762239641746e-05, "loss": 0.7562, "step": 1627 }, { "epoch": 0.23197492163009403, "grad_norm": 1.8226041169567408, "learning_rate": 1.99846246886067e-05, "loss": 0.7852, "step": 1628 }, { "epoch": 0.23211741236819608, "grad_norm": 1.671934864550909, "learning_rate": 1.998448652000014e-05, "loss": 0.8307, "step": 1629 }, { "epoch": 0.2322599031062981, "grad_norm": 1.6909088225745306, "learning_rate": 1.998434773383062e-05, "loss": 0.6726, "step": 1630 }, { "epoch": 0.23240239384440012, "grad_norm": 1.6986309001790192, "learning_rate": 1.9984208330106713e-05, "loss": 0.775, "step": 1631 }, { "epoch": 0.23254488458250214, "grad_norm": 2.1954886907968407, "learning_rate": 1.998406830883705e-05, "loss": 0.7392, "step": 1632 }, { "epoch": 0.23268737532060416, "grad_norm": 1.6374378136795584, "learning_rate": 1.998392767003029e-05, "loss": 0.7577, "step": 1633 }, { "epoch": 0.23282986605870618, "grad_norm": 1.8294588980124955, "learning_rate": 1.9983786413695125e-05, "loss": 0.769, "step": 1634 }, { "epoch": 0.2329723567968082, "grad_norm": 1.6280774582087951, "learning_rate": 1.99836445398403e-05, "loss": 0.7056, "step": 1635 }, { "epoch": 0.23311484753491024, "grad_norm": 1.6051628423869098, "learning_rate": 1.998350204847459e-05, "loss": 0.7247, "step": 1636 }, { "epoch": 0.23325733827301226, "grad_norm": 1.7058962368742214, "learning_rate": 1.9983358939606805e-05, "loss": 0.8046, "step": 1637 }, { "epoch": 0.23339982901111428, "grad_norm": 1.9883362890272196, "learning_rate": 1.9983215213245796e-05, "loss": 0.7859, "step": 1638 }, { "epoch": 0.2335423197492163, "grad_norm": 1.586380432708615, "learning_rate": 1.9983070869400455e-05, "loss": 0.7596, "step": 1639 }, { "epoch": 0.23368481048731832, "grad_norm": 1.4713408791920555, "learning_rate": 1.9982925908079713e-05, "loss": 0.7437, "step": 1640 }, { "epoch": 0.23382730122542034, "grad_norm": 1.5635269353685695, "learning_rate": 1.998278032929253e-05, "loss": 0.7328, "step": 1641 }, { "epoch": 0.23396979196352238, "grad_norm": 1.6727557114836207, "learning_rate": 1.998263413304791e-05, "loss": 0.7143, "step": 1642 }, { "epoch": 0.2341122827016244, "grad_norm": 4.073683742176659, "learning_rate": 1.9982487319354903e-05, "loss": 0.697, "step": 1643 }, { "epoch": 0.23425477343972642, "grad_norm": 1.5495818025631838, "learning_rate": 1.9982339888222584e-05, "loss": 0.6609, "step": 1644 }, { "epoch": 0.23439726417782844, "grad_norm": 1.7293677566272463, "learning_rate": 1.9982191839660073e-05, "loss": 0.7243, "step": 1645 }, { "epoch": 0.23453975491593046, "grad_norm": 1.7810338473628573, "learning_rate": 1.9982043173676527e-05, "loss": 0.8588, "step": 1646 }, { "epoch": 0.23468224565403248, "grad_norm": 1.671244568406347, "learning_rate": 1.9981893890281142e-05, "loss": 0.7253, "step": 1647 }, { "epoch": 0.2348247363921345, "grad_norm": 1.633681303882972, "learning_rate": 1.9981743989483153e-05, "loss": 0.7423, "step": 1648 }, { "epoch": 0.23496722713023654, "grad_norm": 1.7437876187377954, "learning_rate": 1.9981593471291828e-05, "loss": 0.746, "step": 1649 }, { "epoch": 0.23510971786833856, "grad_norm": 1.8102736455783601, "learning_rate": 1.998144233571648e-05, "loss": 0.7603, "step": 1650 }, { "epoch": 0.23525220860644058, "grad_norm": 1.724786001016473, "learning_rate": 1.9981290582766454e-05, "loss": 0.6584, "step": 1651 }, { "epoch": 0.2353946993445426, "grad_norm": 1.689705391279843, "learning_rate": 1.9981138212451142e-05, "loss": 0.791, "step": 1652 }, { "epoch": 0.23553719008264462, "grad_norm": 1.6076318198728479, "learning_rate": 1.9980985224779962e-05, "loss": 0.6586, "step": 1653 }, { "epoch": 0.23567968082074664, "grad_norm": 1.6068638597102858, "learning_rate": 1.998083161976238e-05, "loss": 0.7629, "step": 1654 }, { "epoch": 0.2358221715588487, "grad_norm": 1.5893826052575473, "learning_rate": 1.9980677397407896e-05, "loss": 0.689, "step": 1655 }, { "epoch": 0.2359646622969507, "grad_norm": 1.6008515987828358, "learning_rate": 1.998052255772605e-05, "loss": 0.7413, "step": 1656 }, { "epoch": 0.23610715303505272, "grad_norm": 1.4957964822163234, "learning_rate": 1.9980367100726416e-05, "loss": 0.6656, "step": 1657 }, { "epoch": 0.23624964377315474, "grad_norm": 1.646814447143146, "learning_rate": 1.9980211026418614e-05, "loss": 0.7654, "step": 1658 }, { "epoch": 0.23639213451125676, "grad_norm": 1.7303601367435668, "learning_rate": 1.9980054334812293e-05, "loss": 0.7291, "step": 1659 }, { "epoch": 0.23653462524935878, "grad_norm": 1.7329196865345788, "learning_rate": 1.9979897025917148e-05, "loss": 0.6877, "step": 1660 }, { "epoch": 0.23667711598746083, "grad_norm": 1.5719594265610923, "learning_rate": 1.997973909974291e-05, "loss": 0.7103, "step": 1661 }, { "epoch": 0.23681960672556285, "grad_norm": 1.5651339821112538, "learning_rate": 1.9979580556299343e-05, "loss": 0.6676, "step": 1662 }, { "epoch": 0.23696209746366487, "grad_norm": 1.645900972835166, "learning_rate": 1.9979421395596253e-05, "loss": 0.7222, "step": 1663 }, { "epoch": 0.23710458820176689, "grad_norm": 1.745342781772256, "learning_rate": 1.997926161764349e-05, "loss": 0.7845, "step": 1664 }, { "epoch": 0.2372470789398689, "grad_norm": 1.55882001930003, "learning_rate": 1.9979101222450933e-05, "loss": 0.6969, "step": 1665 }, { "epoch": 0.23738956967797092, "grad_norm": 1.6080307556460878, "learning_rate": 1.9978940210028503e-05, "loss": 0.7067, "step": 1666 }, { "epoch": 0.23753206041607294, "grad_norm": 2.356399158488286, "learning_rate": 1.9978778580386158e-05, "loss": 0.6793, "step": 1667 }, { "epoch": 0.237674551154175, "grad_norm": 1.5081546740707636, "learning_rate": 1.9978616333533896e-05, "loss": 0.7707, "step": 1668 }, { "epoch": 0.237817041892277, "grad_norm": 1.7489187912446624, "learning_rate": 1.9978453469481753e-05, "loss": 0.774, "step": 1669 }, { "epoch": 0.23795953263037903, "grad_norm": 1.729019711434604, "learning_rate": 1.9978289988239802e-05, "loss": 0.8042, "step": 1670 }, { "epoch": 0.23810202336848105, "grad_norm": 1.9708021035668077, "learning_rate": 1.9978125889818156e-05, "loss": 0.7617, "step": 1671 }, { "epoch": 0.23824451410658307, "grad_norm": 1.506573989692652, "learning_rate": 1.9977961174226963e-05, "loss": 0.6785, "step": 1672 }, { "epoch": 0.23838700484468509, "grad_norm": 3.904971839317497, "learning_rate": 1.997779584147641e-05, "loss": 0.7578, "step": 1673 }, { "epoch": 0.23852949558278713, "grad_norm": 1.6516947897537693, "learning_rate": 1.9977629891576725e-05, "loss": 0.7615, "step": 1674 }, { "epoch": 0.23867198632088915, "grad_norm": 1.5697194573334576, "learning_rate": 1.9977463324538172e-05, "loss": 0.7549, "step": 1675 }, { "epoch": 0.23881447705899117, "grad_norm": 1.5861893748086913, "learning_rate": 1.9977296140371057e-05, "loss": 0.7919, "step": 1676 }, { "epoch": 0.2389569677970932, "grad_norm": 1.7264754752341593, "learning_rate": 1.9977128339085716e-05, "loss": 0.7728, "step": 1677 }, { "epoch": 0.2390994585351952, "grad_norm": 1.700930947217247, "learning_rate": 1.9976959920692528e-05, "loss": 0.7031, "step": 1678 }, { "epoch": 0.23924194927329723, "grad_norm": 1.4865988632998992, "learning_rate": 1.997679088520191e-05, "loss": 0.7055, "step": 1679 }, { "epoch": 0.23938444001139925, "grad_norm": 1.6446419026474226, "learning_rate": 1.9976621232624326e-05, "loss": 0.7855, "step": 1680 }, { "epoch": 0.2395269307495013, "grad_norm": 1.6614839292597061, "learning_rate": 1.9976450962970254e-05, "loss": 0.6394, "step": 1681 }, { "epoch": 0.2396694214876033, "grad_norm": 1.5631871928283574, "learning_rate": 1.9976280076250237e-05, "loss": 0.7323, "step": 1682 }, { "epoch": 0.23981191222570533, "grad_norm": 2.0960173314136417, "learning_rate": 1.9976108572474843e-05, "loss": 0.693, "step": 1683 }, { "epoch": 0.23995440296380735, "grad_norm": 1.9426539535317966, "learning_rate": 1.9975936451654672e-05, "loss": 0.6655, "step": 1684 }, { "epoch": 0.24009689370190937, "grad_norm": 5.522646545364979, "learning_rate": 1.9975763713800382e-05, "loss": 0.7448, "step": 1685 }, { "epoch": 0.2402393844400114, "grad_norm": 1.8244373757672, "learning_rate": 1.997559035892265e-05, "loss": 0.7546, "step": 1686 }, { "epoch": 0.24038187517811344, "grad_norm": 1.7809531522905462, "learning_rate": 1.99754163870322e-05, "loss": 0.7878, "step": 1687 }, { "epoch": 0.24052436591621545, "grad_norm": 1.9763495275597254, "learning_rate": 1.9975241798139793e-05, "loss": 0.7454, "step": 1688 }, { "epoch": 0.24066685665431747, "grad_norm": 1.581664555074483, "learning_rate": 1.9975066592256226e-05, "loss": 0.65, "step": 1689 }, { "epoch": 0.2408093473924195, "grad_norm": 1.6005686229152674, "learning_rate": 1.9974890769392335e-05, "loss": 0.7257, "step": 1690 }, { "epoch": 0.2409518381305215, "grad_norm": 1.400309716667802, "learning_rate": 1.9974714329559e-05, "loss": 0.6634, "step": 1691 }, { "epoch": 0.24109432886862353, "grad_norm": 1.6326422857235956, "learning_rate": 1.997453727276713e-05, "loss": 0.8011, "step": 1692 }, { "epoch": 0.24123681960672555, "grad_norm": 1.6901053371684898, "learning_rate": 1.9974359599027678e-05, "loss": 0.7075, "step": 1693 }, { "epoch": 0.2413793103448276, "grad_norm": 1.7469708091611054, "learning_rate": 1.9974181308351635e-05, "loss": 0.7772, "step": 1694 }, { "epoch": 0.24152180108292962, "grad_norm": 1.5428015552858063, "learning_rate": 1.9974002400750025e-05, "loss": 0.7364, "step": 1695 }, { "epoch": 0.24166429182103163, "grad_norm": 1.6535601668703421, "learning_rate": 1.997382287623392e-05, "loss": 0.7984, "step": 1696 }, { "epoch": 0.24180678255913365, "grad_norm": 1.546574031632103, "learning_rate": 1.9973642734814414e-05, "loss": 0.7406, "step": 1697 }, { "epoch": 0.24194927329723567, "grad_norm": 1.755761132479787, "learning_rate": 1.9973461976502656e-05, "loss": 0.721, "step": 1698 }, { "epoch": 0.2420917640353377, "grad_norm": 1.6637969387529497, "learning_rate": 1.9973280601309827e-05, "loss": 0.8246, "step": 1699 }, { "epoch": 0.24223425477343974, "grad_norm": 1.610181261986304, "learning_rate": 1.997309860924714e-05, "loss": 0.6987, "step": 1700 }, { "epoch": 0.24237674551154176, "grad_norm": 1.6408319234011157, "learning_rate": 1.997291600032586e-05, "loss": 0.6586, "step": 1701 }, { "epoch": 0.24251923624964378, "grad_norm": 1.7651454828959732, "learning_rate": 1.997273277455727e-05, "loss": 0.701, "step": 1702 }, { "epoch": 0.2426617269877458, "grad_norm": 1.6016142981041444, "learning_rate": 1.997254893195272e-05, "loss": 0.8154, "step": 1703 }, { "epoch": 0.24280421772584782, "grad_norm": 1.7250946109183403, "learning_rate": 1.9972364472523564e-05, "loss": 0.7515, "step": 1704 }, { "epoch": 0.24294670846394983, "grad_norm": 1.8726335323059347, "learning_rate": 1.997217939628122e-05, "loss": 0.8122, "step": 1705 }, { "epoch": 0.24308919920205185, "grad_norm": 1.7361160719755806, "learning_rate": 1.9971993703237133e-05, "loss": 0.6983, "step": 1706 }, { "epoch": 0.2432316899401539, "grad_norm": 1.5989874218974682, "learning_rate": 1.9971807393402792e-05, "loss": 0.7344, "step": 1707 }, { "epoch": 0.24337418067825592, "grad_norm": 1.6476605849460082, "learning_rate": 1.9971620466789715e-05, "loss": 0.7712, "step": 1708 }, { "epoch": 0.24351667141635794, "grad_norm": 1.6797356849676908, "learning_rate": 1.9971432923409465e-05, "loss": 0.7824, "step": 1709 }, { "epoch": 0.24365916215445996, "grad_norm": 1.7671439908536735, "learning_rate": 1.9971244763273647e-05, "loss": 0.8816, "step": 1710 }, { "epoch": 0.24380165289256198, "grad_norm": 1.9982787980320564, "learning_rate": 1.9971055986393892e-05, "loss": 0.6742, "step": 1711 }, { "epoch": 0.243944143630664, "grad_norm": 1.5840380797324196, "learning_rate": 1.9970866592781886e-05, "loss": 0.6936, "step": 1712 }, { "epoch": 0.24408663436876604, "grad_norm": 1.6415648220061498, "learning_rate": 1.9970676582449334e-05, "loss": 0.72, "step": 1713 }, { "epoch": 0.24422912510686806, "grad_norm": 1.7940537438580961, "learning_rate": 1.997048595540799e-05, "loss": 0.7842, "step": 1714 }, { "epoch": 0.24437161584497008, "grad_norm": 1.6382211003039195, "learning_rate": 1.997029471166965e-05, "loss": 0.8041, "step": 1715 }, { "epoch": 0.2445141065830721, "grad_norm": 1.490425155525085, "learning_rate": 1.997010285124614e-05, "loss": 0.7171, "step": 1716 }, { "epoch": 0.24465659732117412, "grad_norm": 1.583656877459623, "learning_rate": 1.996991037414932e-05, "loss": 0.7969, "step": 1717 }, { "epoch": 0.24479908805927614, "grad_norm": 1.4657321975427604, "learning_rate": 1.996971728039111e-05, "loss": 0.6918, "step": 1718 }, { "epoch": 0.24494157879737816, "grad_norm": 1.860467473524755, "learning_rate": 1.996952356998344e-05, "loss": 0.7485, "step": 1719 }, { "epoch": 0.2450840695354802, "grad_norm": 1.7087159403884555, "learning_rate": 1.99693292429383e-05, "loss": 0.7638, "step": 1720 }, { "epoch": 0.24522656027358222, "grad_norm": 1.5383632258689106, "learning_rate": 1.9969134299267706e-05, "loss": 0.7188, "step": 1721 }, { "epoch": 0.24536905101168424, "grad_norm": 1.6939390133005179, "learning_rate": 1.9968938738983712e-05, "loss": 0.7069, "step": 1722 }, { "epoch": 0.24551154174978626, "grad_norm": 1.569977242541434, "learning_rate": 1.996874256209842e-05, "loss": 0.7758, "step": 1723 }, { "epoch": 0.24565403248788828, "grad_norm": 1.6691619104769628, "learning_rate": 1.996854576862396e-05, "loss": 0.7151, "step": 1724 }, { "epoch": 0.2457965232259903, "grad_norm": 1.796378797510128, "learning_rate": 1.996834835857251e-05, "loss": 0.8182, "step": 1725 }, { "epoch": 0.24593901396409235, "grad_norm": 1.5902939623587207, "learning_rate": 1.996815033195627e-05, "loss": 0.7189, "step": 1726 }, { "epoch": 0.24608150470219436, "grad_norm": 1.6612778506764991, "learning_rate": 1.9967951688787496e-05, "loss": 0.7529, "step": 1727 }, { "epoch": 0.24622399544029638, "grad_norm": 1.6270722364472425, "learning_rate": 1.9967752429078476e-05, "loss": 0.7061, "step": 1728 }, { "epoch": 0.2463664861783984, "grad_norm": 1.5302348075923204, "learning_rate": 1.996755255284153e-05, "loss": 0.6595, "step": 1729 }, { "epoch": 0.24650897691650042, "grad_norm": 1.491266909514839, "learning_rate": 1.996735206008902e-05, "loss": 0.735, "step": 1730 }, { "epoch": 0.24665146765460244, "grad_norm": 1.8871592416577092, "learning_rate": 1.9967150950833353e-05, "loss": 0.8331, "step": 1731 }, { "epoch": 0.2467939583927045, "grad_norm": 1.5537143902331123, "learning_rate": 1.996694922508696e-05, "loss": 0.6831, "step": 1732 }, { "epoch": 0.2469364491308065, "grad_norm": 1.711684796411792, "learning_rate": 1.9966746882862325e-05, "loss": 0.7114, "step": 1733 }, { "epoch": 0.24707893986890853, "grad_norm": 1.5380460228225934, "learning_rate": 1.996654392417196e-05, "loss": 0.7493, "step": 1734 }, { "epoch": 0.24722143060701054, "grad_norm": 1.5711208571999573, "learning_rate": 1.9966340349028418e-05, "loss": 0.765, "step": 1735 }, { "epoch": 0.24736392134511256, "grad_norm": 1.6444096779305926, "learning_rate": 1.9966136157444296e-05, "loss": 0.7056, "step": 1736 }, { "epoch": 0.24750641208321458, "grad_norm": 1.5233714151937734, "learning_rate": 1.9965931349432217e-05, "loss": 0.7018, "step": 1737 }, { "epoch": 0.2476489028213166, "grad_norm": 1.5120259424215616, "learning_rate": 1.996572592500485e-05, "loss": 0.7868, "step": 1738 }, { "epoch": 0.24779139355941865, "grad_norm": 1.580775070735178, "learning_rate": 1.9965519884174904e-05, "loss": 0.7879, "step": 1739 }, { "epoch": 0.24793388429752067, "grad_norm": 1.8053011426142926, "learning_rate": 1.996531322695512e-05, "loss": 0.7353, "step": 1740 }, { "epoch": 0.2480763750356227, "grad_norm": 1.6269464247076886, "learning_rate": 1.9965105953358286e-05, "loss": 0.7752, "step": 1741 }, { "epoch": 0.2482188657737247, "grad_norm": 1.6676517461980311, "learning_rate": 1.9964898063397215e-05, "loss": 0.7516, "step": 1742 }, { "epoch": 0.24836135651182673, "grad_norm": 1.6578681899660386, "learning_rate": 1.9964689557084766e-05, "loss": 0.7165, "step": 1743 }, { "epoch": 0.24850384724992874, "grad_norm": 1.6301435886155795, "learning_rate": 1.996448043443384e-05, "loss": 0.7677, "step": 1744 }, { "epoch": 0.2486463379880308, "grad_norm": 1.6570053995293244, "learning_rate": 1.996427069545737e-05, "loss": 0.7203, "step": 1745 }, { "epoch": 0.2487888287261328, "grad_norm": 1.751189593771428, "learning_rate": 1.996406034016833e-05, "loss": 0.7019, "step": 1746 }, { "epoch": 0.24893131946423483, "grad_norm": 1.6731181187010735, "learning_rate": 1.996384936857973e-05, "loss": 0.7264, "step": 1747 }, { "epoch": 0.24907381020233685, "grad_norm": 1.4994076081403278, "learning_rate": 1.9963637780704617e-05, "loss": 0.618, "step": 1748 }, { "epoch": 0.24921630094043887, "grad_norm": 1.7217753455224927, "learning_rate": 1.996342557655608e-05, "loss": 0.8333, "step": 1749 }, { "epoch": 0.2493587916785409, "grad_norm": 1.8287619838832065, "learning_rate": 1.9963212756147242e-05, "loss": 0.7429, "step": 1750 }, { "epoch": 0.2495012824166429, "grad_norm": 1.8056015889309507, "learning_rate": 1.996299931949127e-05, "loss": 0.7779, "step": 1751 }, { "epoch": 0.24964377315474495, "grad_norm": 1.5821892854480188, "learning_rate": 1.9962785266601364e-05, "loss": 0.7205, "step": 1752 }, { "epoch": 0.24978626389284697, "grad_norm": 1.7716597350227454, "learning_rate": 1.9962570597490765e-05, "loss": 0.7, "step": 1753 }, { "epoch": 0.249928754630949, "grad_norm": 1.5934163866029813, "learning_rate": 1.9962355312172747e-05, "loss": 0.7041, "step": 1754 }, { "epoch": 0.250071245369051, "grad_norm": 1.808559456169955, "learning_rate": 1.996213941066063e-05, "loss": 0.8461, "step": 1755 }, { "epoch": 0.25021373610715303, "grad_norm": 1.8344044678358913, "learning_rate": 1.9961922892967764e-05, "loss": 0.7402, "step": 1756 }, { "epoch": 0.25035622684525505, "grad_norm": 1.927995278237701, "learning_rate": 1.9961705759107545e-05, "loss": 0.7157, "step": 1757 }, { "epoch": 0.25049871758335707, "grad_norm": 1.596467147559579, "learning_rate": 1.9961488009093403e-05, "loss": 0.7376, "step": 1758 }, { "epoch": 0.2506412083214591, "grad_norm": 1.6203073105148698, "learning_rate": 1.9961269642938803e-05, "loss": 0.6835, "step": 1759 }, { "epoch": 0.2507836990595611, "grad_norm": 2.884185191327913, "learning_rate": 1.9961050660657256e-05, "loss": 0.688, "step": 1760 }, { "epoch": 0.2509261897976632, "grad_norm": 1.6425904066811234, "learning_rate": 1.9960831062262304e-05, "loss": 0.7899, "step": 1761 }, { "epoch": 0.2510686805357652, "grad_norm": 1.837001782648401, "learning_rate": 1.9960610847767525e-05, "loss": 0.6823, "step": 1762 }, { "epoch": 0.2512111712738672, "grad_norm": 1.553700352519499, "learning_rate": 1.9960390017186548e-05, "loss": 0.6507, "step": 1763 }, { "epoch": 0.25135366201196924, "grad_norm": 2.8054045680337216, "learning_rate": 1.9960168570533026e-05, "loss": 0.756, "step": 1764 }, { "epoch": 0.25149615275007126, "grad_norm": 2.1772837538423584, "learning_rate": 1.995994650782066e-05, "loss": 0.8032, "step": 1765 }, { "epoch": 0.2516386434881733, "grad_norm": 1.7430329985822117, "learning_rate": 1.9959723829063185e-05, "loss": 0.7181, "step": 1766 }, { "epoch": 0.2517811342262753, "grad_norm": 1.5941242849864703, "learning_rate": 1.995950053427437e-05, "loss": 0.6645, "step": 1767 }, { "epoch": 0.2519236249643773, "grad_norm": 1.7557876488027073, "learning_rate": 1.9959276623468028e-05, "loss": 0.637, "step": 1768 }, { "epoch": 0.25206611570247933, "grad_norm": 1.599205121058913, "learning_rate": 1.9959052096658015e-05, "loss": 0.6574, "step": 1769 }, { "epoch": 0.25220860644058135, "grad_norm": 1.712478875487827, "learning_rate": 1.9958826953858205e-05, "loss": 0.7078, "step": 1770 }, { "epoch": 0.25235109717868337, "grad_norm": 1.6474920600519842, "learning_rate": 1.9958601195082535e-05, "loss": 0.6998, "step": 1771 }, { "epoch": 0.2524935879167854, "grad_norm": 1.7730184421764752, "learning_rate": 1.9958374820344963e-05, "loss": 0.7251, "step": 1772 }, { "epoch": 0.2526360786548874, "grad_norm": 1.8414051998973275, "learning_rate": 1.9958147829659495e-05, "loss": 0.7738, "step": 1773 }, { "epoch": 0.2527785693929895, "grad_norm": 1.456653731454631, "learning_rate": 1.995792022304017e-05, "loss": 0.6917, "step": 1774 }, { "epoch": 0.2529210601310915, "grad_norm": 1.5652604687656362, "learning_rate": 1.9957692000501062e-05, "loss": 0.7371, "step": 1775 }, { "epoch": 0.2530635508691935, "grad_norm": 1.7569589256059297, "learning_rate": 1.995746316205629e-05, "loss": 0.6983, "step": 1776 }, { "epoch": 0.25320604160729554, "grad_norm": 1.5880709886776356, "learning_rate": 1.9957233707720008e-05, "loss": 0.6378, "step": 1777 }, { "epoch": 0.25334853234539756, "grad_norm": 1.469556091351508, "learning_rate": 1.9957003637506405e-05, "loss": 0.7007, "step": 1778 }, { "epoch": 0.2534910230834996, "grad_norm": 1.93797728371894, "learning_rate": 1.9956772951429716e-05, "loss": 0.7369, "step": 1779 }, { "epoch": 0.2536335138216016, "grad_norm": 1.544821829125824, "learning_rate": 1.995654164950421e-05, "loss": 0.6784, "step": 1780 }, { "epoch": 0.2537760045597036, "grad_norm": 1.6507544673197703, "learning_rate": 1.9956309731744193e-05, "loss": 0.7237, "step": 1781 }, { "epoch": 0.25391849529780564, "grad_norm": 1.713877861297826, "learning_rate": 1.9956077198164006e-05, "loss": 0.6276, "step": 1782 }, { "epoch": 0.25406098603590765, "grad_norm": 1.7829221766624561, "learning_rate": 1.9955844048778032e-05, "loss": 0.7846, "step": 1783 }, { "epoch": 0.2542034767740097, "grad_norm": 1.5055011437999528, "learning_rate": 1.9955610283600695e-05, "loss": 0.659, "step": 1784 }, { "epoch": 0.2543459675121117, "grad_norm": 1.836255888746528, "learning_rate": 1.9955375902646454e-05, "loss": 0.6702, "step": 1785 }, { "epoch": 0.2544884582502137, "grad_norm": 2.4016101777288115, "learning_rate": 1.9955140905929802e-05, "loss": 0.7008, "step": 1786 }, { "epoch": 0.2546309489883158, "grad_norm": 1.6631482282692593, "learning_rate": 1.995490529346528e-05, "loss": 0.5961, "step": 1787 }, { "epoch": 0.2547734397264178, "grad_norm": 1.5101101150281029, "learning_rate": 1.9954669065267452e-05, "loss": 0.7261, "step": 1788 }, { "epoch": 0.2549159304645198, "grad_norm": 2.09634808955255, "learning_rate": 1.995443222135094e-05, "loss": 0.6856, "step": 1789 }, { "epoch": 0.25505842120262184, "grad_norm": 1.6378790842666542, "learning_rate": 1.9954194761730387e-05, "loss": 0.6757, "step": 1790 }, { "epoch": 0.25520091194072386, "grad_norm": 1.9870583840964402, "learning_rate": 1.9953956686420483e-05, "loss": 0.7712, "step": 1791 }, { "epoch": 0.2553434026788259, "grad_norm": 1.6849453220483868, "learning_rate": 1.995371799543595e-05, "loss": 0.6766, "step": 1792 }, { "epoch": 0.2554858934169279, "grad_norm": 1.5637396140944506, "learning_rate": 1.9953478688791554e-05, "loss": 0.7248, "step": 1793 }, { "epoch": 0.2556283841550299, "grad_norm": 1.524332017359176, "learning_rate": 1.9953238766502097e-05, "loss": 0.732, "step": 1794 }, { "epoch": 0.25577087489313194, "grad_norm": 1.644388885644922, "learning_rate": 1.995299822858242e-05, "loss": 0.7901, "step": 1795 }, { "epoch": 0.25591336563123396, "grad_norm": 1.8178295988673427, "learning_rate": 1.99527570750474e-05, "loss": 0.7776, "step": 1796 }, { "epoch": 0.256055856369336, "grad_norm": 1.6446053060468142, "learning_rate": 1.9952515305911946e-05, "loss": 0.6427, "step": 1797 }, { "epoch": 0.256198347107438, "grad_norm": 1.5456890160954968, "learning_rate": 1.9952272921191023e-05, "loss": 0.6939, "step": 1798 }, { "epoch": 0.25634083784554, "grad_norm": 1.7704073745311386, "learning_rate": 1.9952029920899615e-05, "loss": 0.791, "step": 1799 }, { "epoch": 0.2564833285836421, "grad_norm": 1.5541248156461136, "learning_rate": 1.9951786305052756e-05, "loss": 0.7311, "step": 1800 }, { "epoch": 0.2566258193217441, "grad_norm": 1.7574235243339578, "learning_rate": 1.9951542073665512e-05, "loss": 0.7633, "step": 1801 }, { "epoch": 0.2567683100598461, "grad_norm": 1.6069359026745893, "learning_rate": 1.9951297226752992e-05, "loss": 0.7583, "step": 1802 }, { "epoch": 0.25691080079794815, "grad_norm": 1.4951265983521143, "learning_rate": 1.995105176433034e-05, "loss": 0.6745, "step": 1803 }, { "epoch": 0.25705329153605017, "grad_norm": 1.5407970579683392, "learning_rate": 1.9950805686412735e-05, "loss": 0.7173, "step": 1804 }, { "epoch": 0.2571957822741522, "grad_norm": 1.602713582120181, "learning_rate": 1.99505589930154e-05, "loss": 0.7883, "step": 1805 }, { "epoch": 0.2573382730122542, "grad_norm": 1.5048962988297883, "learning_rate": 1.9950311684153595e-05, "loss": 0.6812, "step": 1806 }, { "epoch": 0.2574807637503562, "grad_norm": 1.5815811200061094, "learning_rate": 1.9950063759842614e-05, "loss": 0.7125, "step": 1807 }, { "epoch": 0.25762325448845824, "grad_norm": 1.8792241771628295, "learning_rate": 1.9949815220097792e-05, "loss": 0.7177, "step": 1808 }, { "epoch": 0.25776574522656026, "grad_norm": 2.067551185015945, "learning_rate": 1.99495660649345e-05, "loss": 0.72, "step": 1809 }, { "epoch": 0.2579082359646623, "grad_norm": 1.734690486673409, "learning_rate": 1.9949316294368157e-05, "loss": 0.7734, "step": 1810 }, { "epoch": 0.2580507267027643, "grad_norm": 1.9038639090168803, "learning_rate": 1.99490659084142e-05, "loss": 0.7326, "step": 1811 }, { "epoch": 0.2581932174408663, "grad_norm": 1.9357219639341814, "learning_rate": 1.9948814907088125e-05, "loss": 0.7458, "step": 1812 }, { "epoch": 0.2583357081789684, "grad_norm": 1.7229157403851063, "learning_rate": 1.9948563290405452e-05, "loss": 0.7132, "step": 1813 }, { "epoch": 0.2584781989170704, "grad_norm": 1.914682069529257, "learning_rate": 1.994831105838175e-05, "loss": 0.8174, "step": 1814 }, { "epoch": 0.25862068965517243, "grad_norm": 1.7113473295784534, "learning_rate": 1.994805821103261e-05, "loss": 0.7297, "step": 1815 }, { "epoch": 0.25876318039327445, "grad_norm": 1.6889119937010755, "learning_rate": 1.9947804748373684e-05, "loss": 0.7183, "step": 1816 }, { "epoch": 0.25890567113137647, "grad_norm": 1.7194083560000082, "learning_rate": 1.9947550670420637e-05, "loss": 0.7207, "step": 1817 }, { "epoch": 0.2590481618694785, "grad_norm": 2.293571031090919, "learning_rate": 1.994729597718919e-05, "loss": 0.6992, "step": 1818 }, { "epoch": 0.2591906526075805, "grad_norm": 1.6405668507604054, "learning_rate": 1.9947040668695097e-05, "loss": 0.673, "step": 1819 }, { "epoch": 0.2593331433456825, "grad_norm": 2.1180997169011917, "learning_rate": 1.994678474495415e-05, "loss": 0.6766, "step": 1820 }, { "epoch": 0.25947563408378455, "grad_norm": 1.6133778215023609, "learning_rate": 1.9946528205982176e-05, "loss": 0.7382, "step": 1821 }, { "epoch": 0.25961812482188656, "grad_norm": 1.6659365772588643, "learning_rate": 1.9946271051795045e-05, "loss": 0.7191, "step": 1822 }, { "epoch": 0.2597606155599886, "grad_norm": 1.6151739296402194, "learning_rate": 1.994601328240866e-05, "loss": 0.6924, "step": 1823 }, { "epoch": 0.2599031062980906, "grad_norm": 1.5740790982312007, "learning_rate": 1.9945754897838965e-05, "loss": 0.6827, "step": 1824 }, { "epoch": 0.2600455970361926, "grad_norm": 1.5393376037654296, "learning_rate": 1.994549589810194e-05, "loss": 0.8147, "step": 1825 }, { "epoch": 0.2601880877742947, "grad_norm": 1.682314984051498, "learning_rate": 1.994523628321361e-05, "loss": 0.787, "step": 1826 }, { "epoch": 0.2603305785123967, "grad_norm": 1.6023701571023583, "learning_rate": 1.994497605319003e-05, "loss": 0.6938, "step": 1827 }, { "epoch": 0.26047306925049873, "grad_norm": 1.6192349928254923, "learning_rate": 1.9944715208047297e-05, "loss": 0.7275, "step": 1828 }, { "epoch": 0.26061555998860075, "grad_norm": 1.6147723451321947, "learning_rate": 1.994445374780154e-05, "loss": 0.8037, "step": 1829 }, { "epoch": 0.2607580507267028, "grad_norm": 1.6603310935208158, "learning_rate": 1.9944191672468937e-05, "loss": 0.8373, "step": 1830 }, { "epoch": 0.2609005414648048, "grad_norm": 1.7663201697353357, "learning_rate": 1.9943928982065693e-05, "loss": 0.8212, "step": 1831 }, { "epoch": 0.2610430322029068, "grad_norm": 1.6749008046036737, "learning_rate": 1.994366567660806e-05, "loss": 0.7307, "step": 1832 }, { "epoch": 0.26118552294100883, "grad_norm": 1.82097216147817, "learning_rate": 1.994340175611232e-05, "loss": 0.7096, "step": 1833 }, { "epoch": 0.26132801367911085, "grad_norm": 1.5766648788840527, "learning_rate": 1.9943137220594803e-05, "loss": 0.8202, "step": 1834 }, { "epoch": 0.26147050441721287, "grad_norm": 1.5738616783512853, "learning_rate": 1.9942872070071866e-05, "loss": 0.7975, "step": 1835 }, { "epoch": 0.2616129951553149, "grad_norm": 1.6636852365337722, "learning_rate": 1.994260630455991e-05, "loss": 0.7404, "step": 1836 }, { "epoch": 0.2617554858934169, "grad_norm": 1.6131191375014884, "learning_rate": 1.9942339924075375e-05, "loss": 0.7317, "step": 1837 }, { "epoch": 0.2618979766315189, "grad_norm": 1.9374009417039093, "learning_rate": 1.9942072928634736e-05, "loss": 0.6657, "step": 1838 }, { "epoch": 0.262040467369621, "grad_norm": 1.6034478474175107, "learning_rate": 1.9941805318254507e-05, "loss": 0.7823, "step": 1839 }, { "epoch": 0.262182958107723, "grad_norm": 1.7174102272707823, "learning_rate": 1.994153709295124e-05, "loss": 0.7375, "step": 1840 }, { "epoch": 0.26232544884582504, "grad_norm": 1.8468924164480285, "learning_rate": 1.9941268252741527e-05, "loss": 0.7345, "step": 1841 }, { "epoch": 0.26246793958392706, "grad_norm": 1.6136813514809352, "learning_rate": 1.9940998797641994e-05, "loss": 0.7961, "step": 1842 }, { "epoch": 0.2626104303220291, "grad_norm": 1.5130117699460615, "learning_rate": 1.994072872766931e-05, "loss": 0.7306, "step": 1843 }, { "epoch": 0.2627529210601311, "grad_norm": 1.4822365191200815, "learning_rate": 1.994045804284018e-05, "loss": 0.6888, "step": 1844 }, { "epoch": 0.2628954117982331, "grad_norm": 1.7777644312907226, "learning_rate": 1.9940186743171344e-05, "loss": 0.6673, "step": 1845 }, { "epoch": 0.26303790253633513, "grad_norm": 1.5479853269097557, "learning_rate": 1.993991482867958e-05, "loss": 0.771, "step": 1846 }, { "epoch": 0.26318039327443715, "grad_norm": 2.057396545337801, "learning_rate": 1.9939642299381714e-05, "loss": 0.7425, "step": 1847 }, { "epoch": 0.26332288401253917, "grad_norm": 1.5525718331961313, "learning_rate": 1.9939369155294596e-05, "loss": 0.699, "step": 1848 }, { "epoch": 0.2634653747506412, "grad_norm": 1.676110382305203, "learning_rate": 1.9939095396435123e-05, "loss": 0.7899, "step": 1849 }, { "epoch": 0.2636078654887432, "grad_norm": 1.875892318964881, "learning_rate": 1.9938821022820227e-05, "loss": 0.7231, "step": 1850 }, { "epoch": 0.26375035622684523, "grad_norm": 3.6444450423123977, "learning_rate": 1.993854603446688e-05, "loss": 0.6709, "step": 1851 }, { "epoch": 0.2638928469649473, "grad_norm": 1.6595607425059866, "learning_rate": 1.9938270431392087e-05, "loss": 0.7165, "step": 1852 }, { "epoch": 0.2640353377030493, "grad_norm": 1.6980235869276257, "learning_rate": 1.99379942136129e-05, "loss": 0.7094, "step": 1853 }, { "epoch": 0.26417782844115134, "grad_norm": 1.7431318500042297, "learning_rate": 1.9937717381146405e-05, "loss": 0.7428, "step": 1854 }, { "epoch": 0.26432031917925336, "grad_norm": 1.6363692172431632, "learning_rate": 1.9937439934009716e-05, "loss": 0.7653, "step": 1855 }, { "epoch": 0.2644628099173554, "grad_norm": 1.5504738427787783, "learning_rate": 1.993716187222e-05, "loss": 0.6968, "step": 1856 }, { "epoch": 0.2646053006554574, "grad_norm": 1.6023109922643848, "learning_rate": 1.9936883195794453e-05, "loss": 0.7835, "step": 1857 }, { "epoch": 0.2647477913935594, "grad_norm": 1.6426460533572855, "learning_rate": 1.9936603904750314e-05, "loss": 0.7383, "step": 1858 }, { "epoch": 0.26489028213166144, "grad_norm": 1.622398587694187, "learning_rate": 1.9936323999104855e-05, "loss": 0.7352, "step": 1859 }, { "epoch": 0.26503277286976346, "grad_norm": 1.766027070649789, "learning_rate": 1.9936043478875394e-05, "loss": 0.7105, "step": 1860 }, { "epoch": 0.2651752636078655, "grad_norm": 1.8101854606592223, "learning_rate": 1.9935762344079277e-05, "loss": 0.7129, "step": 1861 }, { "epoch": 0.2653177543459675, "grad_norm": 1.7785727089728212, "learning_rate": 1.9935480594733895e-05, "loss": 0.7549, "step": 1862 }, { "epoch": 0.2654602450840695, "grad_norm": 1.482047382179094, "learning_rate": 1.993519823085667e-05, "loss": 0.7508, "step": 1863 }, { "epoch": 0.26560273582217153, "grad_norm": 2.048464969999955, "learning_rate": 1.9934915252465074e-05, "loss": 0.7919, "step": 1864 }, { "epoch": 0.2657452265602736, "grad_norm": 1.5925130098279148, "learning_rate": 1.993463165957661e-05, "loss": 0.6845, "step": 1865 }, { "epoch": 0.2658877172983756, "grad_norm": 1.8298793165554164, "learning_rate": 1.9934347452208812e-05, "loss": 0.8137, "step": 1866 }, { "epoch": 0.26603020803647764, "grad_norm": 1.5922029972264051, "learning_rate": 1.9934062630379262e-05, "loss": 0.677, "step": 1867 }, { "epoch": 0.26617269877457966, "grad_norm": 1.4995477862218043, "learning_rate": 1.9933777194105578e-05, "loss": 0.7254, "step": 1868 }, { "epoch": 0.2663151895126817, "grad_norm": 1.7120833276356868, "learning_rate": 1.9933491143405416e-05, "loss": 0.7758, "step": 1869 }, { "epoch": 0.2664576802507837, "grad_norm": 1.5092699072446334, "learning_rate": 1.9933204478296468e-05, "loss": 0.7085, "step": 1870 }, { "epoch": 0.2666001709888857, "grad_norm": 1.524664825280455, "learning_rate": 1.993291719879646e-05, "loss": 0.7227, "step": 1871 }, { "epoch": 0.26674266172698774, "grad_norm": 1.5690590438726535, "learning_rate": 1.993262930492317e-05, "loss": 0.7207, "step": 1872 }, { "epoch": 0.26688515246508976, "grad_norm": 1.5120175229130106, "learning_rate": 1.9932340796694394e-05, "loss": 0.6811, "step": 1873 }, { "epoch": 0.2670276432031918, "grad_norm": 1.6951968583392947, "learning_rate": 1.9932051674127984e-05, "loss": 0.8352, "step": 1874 }, { "epoch": 0.2671701339412938, "grad_norm": 1.5210840094263656, "learning_rate": 1.9931761937241822e-05, "loss": 0.7277, "step": 1875 }, { "epoch": 0.2673126246793958, "grad_norm": 1.5392545536467432, "learning_rate": 1.993147158605383e-05, "loss": 0.7127, "step": 1876 }, { "epoch": 0.26745511541749784, "grad_norm": 1.442480826687424, "learning_rate": 1.9931180620581964e-05, "loss": 0.7806, "step": 1877 }, { "epoch": 0.2675976061555999, "grad_norm": 1.6322288884979284, "learning_rate": 1.9930889040844223e-05, "loss": 0.7538, "step": 1878 }, { "epoch": 0.26774009689370193, "grad_norm": 1.652706097948067, "learning_rate": 1.9930596846858642e-05, "loss": 0.7951, "step": 1879 }, { "epoch": 0.26788258763180395, "grad_norm": 1.599484328480133, "learning_rate": 1.9930304038643292e-05, "loss": 0.6977, "step": 1880 }, { "epoch": 0.26802507836990597, "grad_norm": 1.633349347097137, "learning_rate": 1.9930010616216284e-05, "loss": 0.7383, "step": 1881 }, { "epoch": 0.268167569108008, "grad_norm": 1.555713429106605, "learning_rate": 1.9929716579595766e-05, "loss": 0.7088, "step": 1882 }, { "epoch": 0.26831005984611, "grad_norm": 1.613270092595079, "learning_rate": 1.992942192879993e-05, "loss": 0.7821, "step": 1883 }, { "epoch": 0.268452550584212, "grad_norm": 1.4919491387778825, "learning_rate": 1.9929126663846995e-05, "loss": 0.7581, "step": 1884 }, { "epoch": 0.26859504132231404, "grad_norm": 1.5669337356568291, "learning_rate": 1.9928830784755226e-05, "loss": 0.7947, "step": 1885 }, { "epoch": 0.26873753206041606, "grad_norm": 1.5067194604313794, "learning_rate": 1.9928534291542923e-05, "loss": 0.633, "step": 1886 }, { "epoch": 0.2688800227985181, "grad_norm": 1.7319765051109042, "learning_rate": 1.992823718422843e-05, "loss": 0.7147, "step": 1887 }, { "epoch": 0.2690225135366201, "grad_norm": 2.3284777942767008, "learning_rate": 1.9927939462830115e-05, "loss": 0.7306, "step": 1888 }, { "epoch": 0.2691650042747221, "grad_norm": 1.64275859043405, "learning_rate": 1.99276411273664e-05, "loss": 0.6931, "step": 1889 }, { "epoch": 0.2693074950128242, "grad_norm": 1.5725356587632384, "learning_rate": 1.9927342177855733e-05, "loss": 0.6856, "step": 1890 }, { "epoch": 0.2694499857509262, "grad_norm": 1.597817119266163, "learning_rate": 1.9927042614316607e-05, "loss": 0.7758, "step": 1891 }, { "epoch": 0.26959247648902823, "grad_norm": 1.5711078300800994, "learning_rate": 1.992674243676755e-05, "loss": 0.7922, "step": 1892 }, { "epoch": 0.26973496722713025, "grad_norm": 1.598307576839387, "learning_rate": 1.992644164522713e-05, "loss": 0.6476, "step": 1893 }, { "epoch": 0.26987745796523227, "grad_norm": 1.6771458173378582, "learning_rate": 1.9926140239713948e-05, "loss": 0.8035, "step": 1894 }, { "epoch": 0.2700199487033343, "grad_norm": 1.4804521399331827, "learning_rate": 1.992583822024665e-05, "loss": 0.6823, "step": 1895 }, { "epoch": 0.2701624394414363, "grad_norm": 1.5132258695569514, "learning_rate": 1.9925535586843914e-05, "loss": 0.6233, "step": 1896 }, { "epoch": 0.2703049301795383, "grad_norm": 1.5006305503277313, "learning_rate": 1.9925232339524464e-05, "loss": 0.7757, "step": 1897 }, { "epoch": 0.27044742091764035, "grad_norm": 1.58036640664394, "learning_rate": 1.9924928478307053e-05, "loss": 0.7394, "step": 1898 }, { "epoch": 0.27058991165574237, "grad_norm": 1.5263596690694314, "learning_rate": 1.9924624003210473e-05, "loss": 0.7088, "step": 1899 }, { "epoch": 0.2707324023938444, "grad_norm": 1.5031893463705155, "learning_rate": 1.9924318914253557e-05, "loss": 0.7912, "step": 1900 }, { "epoch": 0.2708748931319464, "grad_norm": 1.7652664188577463, "learning_rate": 1.992401321145518e-05, "loss": 0.7433, "step": 1901 }, { "epoch": 0.2710173838700484, "grad_norm": 1.537191330200844, "learning_rate": 1.9923706894834245e-05, "loss": 0.7671, "step": 1902 }, { "epoch": 0.2711598746081505, "grad_norm": 1.5432112124283557, "learning_rate": 1.9923399964409705e-05, "loss": 0.7095, "step": 1903 }, { "epoch": 0.2713023653462525, "grad_norm": 1.5093747558454327, "learning_rate": 1.9923092420200537e-05, "loss": 0.6203, "step": 1904 }, { "epoch": 0.27144485608435454, "grad_norm": 1.4585362070543328, "learning_rate": 1.9922784262225766e-05, "loss": 0.6935, "step": 1905 }, { "epoch": 0.27158734682245655, "grad_norm": 1.6869100714597096, "learning_rate": 1.9922475490504456e-05, "loss": 0.7447, "step": 1906 }, { "epoch": 0.2717298375605586, "grad_norm": 1.4881044305005826, "learning_rate": 1.99221661050557e-05, "loss": 0.6727, "step": 1907 }, { "epoch": 0.2718723282986606, "grad_norm": 1.5458451526035306, "learning_rate": 1.9921856105898637e-05, "loss": 0.7169, "step": 1908 }, { "epoch": 0.2720148190367626, "grad_norm": 1.9883422049171737, "learning_rate": 1.992154549305244e-05, "loss": 0.6895, "step": 1909 }, { "epoch": 0.27215730977486463, "grad_norm": 1.6931903871181069, "learning_rate": 1.9921234266536323e-05, "loss": 0.7862, "step": 1910 }, { "epoch": 0.27229980051296665, "grad_norm": 1.4421934978737396, "learning_rate": 1.9920922426369532e-05, "loss": 0.6667, "step": 1911 }, { "epoch": 0.27244229125106867, "grad_norm": 1.5443855082918734, "learning_rate": 1.992060997257136e-05, "loss": 0.6596, "step": 1912 }, { "epoch": 0.2725847819891707, "grad_norm": 1.6617061436512688, "learning_rate": 1.992029690516113e-05, "loss": 0.7043, "step": 1913 }, { "epoch": 0.2727272727272727, "grad_norm": 1.5781065416354367, "learning_rate": 1.9919983224158205e-05, "loss": 0.7212, "step": 1914 }, { "epoch": 0.2728697634653747, "grad_norm": 1.6017716739637105, "learning_rate": 1.9919668929581987e-05, "loss": 0.7307, "step": 1915 }, { "epoch": 0.2730122542034768, "grad_norm": 1.508096764878737, "learning_rate": 1.991935402145192e-05, "loss": 0.6868, "step": 1916 }, { "epoch": 0.2731547449415788, "grad_norm": 1.6473446339664009, "learning_rate": 1.9919038499787478e-05, "loss": 0.7921, "step": 1917 }, { "epoch": 0.27329723567968084, "grad_norm": 1.631805232266441, "learning_rate": 1.991872236460818e-05, "loss": 0.7113, "step": 1918 }, { "epoch": 0.27343972641778286, "grad_norm": 1.6454365580097101, "learning_rate": 1.9918405615933576e-05, "loss": 0.7096, "step": 1919 }, { "epoch": 0.2735822171558849, "grad_norm": 1.7044352543274086, "learning_rate": 1.9918088253783257e-05, "loss": 0.7198, "step": 1920 }, { "epoch": 0.2737247078939869, "grad_norm": 1.6363265954783175, "learning_rate": 1.9917770278176857e-05, "loss": 0.7878, "step": 1921 }, { "epoch": 0.2738671986320889, "grad_norm": 1.5019141205747877, "learning_rate": 1.991745168913404e-05, "loss": 0.6993, "step": 1922 }, { "epoch": 0.27400968937019093, "grad_norm": 1.3855738300046991, "learning_rate": 1.991713248667451e-05, "loss": 0.7222, "step": 1923 }, { "epoch": 0.27415218010829295, "grad_norm": 1.4769274424356822, "learning_rate": 1.9916812670818017e-05, "loss": 0.6427, "step": 1924 }, { "epoch": 0.274294670846395, "grad_norm": 1.5637772207968572, "learning_rate": 1.9916492241584337e-05, "loss": 0.6764, "step": 1925 }, { "epoch": 0.274437161584497, "grad_norm": 1.7838410807718859, "learning_rate": 1.991617119899329e-05, "loss": 0.6612, "step": 1926 }, { "epoch": 0.274579652322599, "grad_norm": 1.5677682452921005, "learning_rate": 1.9915849543064733e-05, "loss": 0.7823, "step": 1927 }, { "epoch": 0.27472214306070103, "grad_norm": 1.58262273275042, "learning_rate": 1.9915527273818562e-05, "loss": 0.673, "step": 1928 }, { "epoch": 0.2748646337988031, "grad_norm": 1.573960453148321, "learning_rate": 1.991520439127471e-05, "loss": 0.7127, "step": 1929 }, { "epoch": 0.2750071245369051, "grad_norm": 1.550551402846043, "learning_rate": 1.991488089545315e-05, "loss": 0.7627, "step": 1930 }, { "epoch": 0.27514961527500714, "grad_norm": 1.9427134640688593, "learning_rate": 1.9914556786373886e-05, "loss": 0.7447, "step": 1931 }, { "epoch": 0.27529210601310916, "grad_norm": 1.621747271843799, "learning_rate": 1.991423206405697e-05, "loss": 0.8044, "step": 1932 }, { "epoch": 0.2754345967512112, "grad_norm": 1.5397057810211516, "learning_rate": 1.9913906728522483e-05, "loss": 0.7205, "step": 1933 }, { "epoch": 0.2755770874893132, "grad_norm": 1.5473637966919425, "learning_rate": 1.991358077979055e-05, "loss": 0.6548, "step": 1934 }, { "epoch": 0.2757195782274152, "grad_norm": 1.5500251801664189, "learning_rate": 1.9913254217881328e-05, "loss": 0.7097, "step": 1935 }, { "epoch": 0.27586206896551724, "grad_norm": 1.6270168547764718, "learning_rate": 1.9912927042815023e-05, "loss": 0.779, "step": 1936 }, { "epoch": 0.27600455970361926, "grad_norm": 3.320347430815088, "learning_rate": 1.9912599254611863e-05, "loss": 0.5904, "step": 1937 }, { "epoch": 0.2761470504417213, "grad_norm": 1.7585546914793035, "learning_rate": 1.991227085329213e-05, "loss": 0.6298, "step": 1938 }, { "epoch": 0.2762895411798233, "grad_norm": 1.6301176880203745, "learning_rate": 1.9911941838876132e-05, "loss": 0.7212, "step": 1939 }, { "epoch": 0.2764320319179253, "grad_norm": 1.5754657267926107, "learning_rate": 1.9911612211384218e-05, "loss": 0.7779, "step": 1940 }, { "epoch": 0.27657452265602733, "grad_norm": 1.6965868014300924, "learning_rate": 1.9911281970836782e-05, "loss": 0.7738, "step": 1941 }, { "epoch": 0.2767170133941294, "grad_norm": 1.647221979324511, "learning_rate": 1.9910951117254245e-05, "loss": 0.6629, "step": 1942 }, { "epoch": 0.2768595041322314, "grad_norm": 1.578754829568695, "learning_rate": 1.9910619650657073e-05, "loss": 0.7394, "step": 1943 }, { "epoch": 0.27700199487033345, "grad_norm": 1.5157912506262807, "learning_rate": 1.9910287571065767e-05, "loss": 0.6425, "step": 1944 }, { "epoch": 0.27714448560843546, "grad_norm": 2.4482129711409155, "learning_rate": 1.9909954878500867e-05, "loss": 0.7466, "step": 1945 }, { "epoch": 0.2772869763465375, "grad_norm": 1.746657966626277, "learning_rate": 1.990962157298295e-05, "loss": 0.7138, "step": 1946 }, { "epoch": 0.2774294670846395, "grad_norm": 1.6019728009901777, "learning_rate": 1.9909287654532635e-05, "loss": 0.7158, "step": 1947 }, { "epoch": 0.2775719578227415, "grad_norm": 1.6956337786349964, "learning_rate": 1.9908953123170568e-05, "loss": 0.7191, "step": 1948 }, { "epoch": 0.27771444856084354, "grad_norm": 1.5670257293096592, "learning_rate": 1.9908617978917452e-05, "loss": 0.7391, "step": 1949 }, { "epoch": 0.27785693929894556, "grad_norm": 1.6364935867051353, "learning_rate": 1.990828222179401e-05, "loss": 0.6471, "step": 1950 }, { "epoch": 0.2779994300370476, "grad_norm": 1.5929539391830596, "learning_rate": 1.9907945851821007e-05, "loss": 0.737, "step": 1951 }, { "epoch": 0.2781419207751496, "grad_norm": 1.686340310613284, "learning_rate": 1.9907608869019254e-05, "loss": 0.8734, "step": 1952 }, { "epoch": 0.2782844115132516, "grad_norm": 1.5000746957530604, "learning_rate": 1.9907271273409586e-05, "loss": 0.6885, "step": 1953 }, { "epoch": 0.27842690225135364, "grad_norm": 2.055746301910388, "learning_rate": 1.9906933065012893e-05, "loss": 0.6683, "step": 1954 }, { "epoch": 0.2785693929894557, "grad_norm": 1.4960490083458193, "learning_rate": 1.990659424385009e-05, "loss": 0.7434, "step": 1955 }, { "epoch": 0.27871188372755773, "grad_norm": 1.644217504872015, "learning_rate": 1.990625480994213e-05, "loss": 0.7183, "step": 1956 }, { "epoch": 0.27885437446565975, "grad_norm": 1.9096335255309058, "learning_rate": 1.9905914763310015e-05, "loss": 0.746, "step": 1957 }, { "epoch": 0.27899686520376177, "grad_norm": 1.4961273452906345, "learning_rate": 1.9905574103974775e-05, "loss": 0.7409, "step": 1958 }, { "epoch": 0.2791393559418638, "grad_norm": 1.7304276604717599, "learning_rate": 1.990523283195748e-05, "loss": 0.8011, "step": 1959 }, { "epoch": 0.2792818466799658, "grad_norm": 1.6327353294012146, "learning_rate": 1.9904890947279238e-05, "loss": 0.6342, "step": 1960 }, { "epoch": 0.2794243374180678, "grad_norm": 1.6496374320456386, "learning_rate": 1.9904548449961195e-05, "loss": 0.7654, "step": 1961 }, { "epoch": 0.27956682815616984, "grad_norm": 1.5500381337207938, "learning_rate": 1.9904205340024536e-05, "loss": 0.7841, "step": 1962 }, { "epoch": 0.27970931889427186, "grad_norm": 1.8958113191909174, "learning_rate": 1.9903861617490482e-05, "loss": 0.7574, "step": 1963 }, { "epoch": 0.2798518096323739, "grad_norm": 2.0130935159165384, "learning_rate": 1.9903517282380297e-05, "loss": 0.6826, "step": 1964 }, { "epoch": 0.2799943003704759, "grad_norm": 1.7732408925631071, "learning_rate": 1.9903172334715274e-05, "loss": 0.6694, "step": 1965 }, { "epoch": 0.2801367911085779, "grad_norm": 2.052145332160167, "learning_rate": 1.990282677451675e-05, "loss": 0.7296, "step": 1966 }, { "epoch": 0.28027928184667994, "grad_norm": 1.662069558900818, "learning_rate": 1.99024806018061e-05, "loss": 0.6948, "step": 1967 }, { "epoch": 0.280421772584782, "grad_norm": 1.643216600443593, "learning_rate": 1.9902133816604733e-05, "loss": 0.6551, "step": 1968 }, { "epoch": 0.28056426332288403, "grad_norm": 1.5764855214364488, "learning_rate": 1.9901786418934105e-05, "loss": 0.6988, "step": 1969 }, { "epoch": 0.28070675406098605, "grad_norm": 1.5779784621884476, "learning_rate": 1.9901438408815698e-05, "loss": 0.709, "step": 1970 }, { "epoch": 0.28084924479908807, "grad_norm": 1.6956395974172183, "learning_rate": 1.9901089786271034e-05, "loss": 0.7803, "step": 1971 }, { "epoch": 0.2809917355371901, "grad_norm": 1.7079836232026524, "learning_rate": 1.9900740551321684e-05, "loss": 0.666, "step": 1972 }, { "epoch": 0.2811342262752921, "grad_norm": 1.6829612398338665, "learning_rate": 1.990039070398924e-05, "loss": 0.7578, "step": 1973 }, { "epoch": 0.28127671701339413, "grad_norm": 2.104131357475444, "learning_rate": 1.990004024429535e-05, "loss": 0.7144, "step": 1974 }, { "epoch": 0.28141920775149615, "grad_norm": 1.635377399570385, "learning_rate": 1.9899689172261682e-05, "loss": 0.7054, "step": 1975 }, { "epoch": 0.28156169848959817, "grad_norm": 1.7449261376811256, "learning_rate": 1.989933748790996e-05, "loss": 0.8111, "step": 1976 }, { "epoch": 0.2817041892277002, "grad_norm": 1.7847254762321019, "learning_rate": 1.989898519126193e-05, "loss": 0.7429, "step": 1977 }, { "epoch": 0.2818466799658022, "grad_norm": 1.640276745633719, "learning_rate": 1.9898632282339382e-05, "loss": 0.7113, "step": 1978 }, { "epoch": 0.2819891707039042, "grad_norm": 2.1133799040197596, "learning_rate": 1.989827876116415e-05, "loss": 0.7099, "step": 1979 }, { "epoch": 0.28213166144200624, "grad_norm": 1.705196497731305, "learning_rate": 1.9897924627758093e-05, "loss": 0.7848, "step": 1980 }, { "epoch": 0.2822741521801083, "grad_norm": 1.5750568759447743, "learning_rate": 1.9897569882143123e-05, "loss": 0.7243, "step": 1981 }, { "epoch": 0.28241664291821034, "grad_norm": 2.0117393900909217, "learning_rate": 1.9897214524341172e-05, "loss": 0.7317, "step": 1982 }, { "epoch": 0.28255913365631236, "grad_norm": 1.5831222760661714, "learning_rate": 1.9896858554374225e-05, "loss": 0.6349, "step": 1983 }, { "epoch": 0.2827016243944144, "grad_norm": 1.6537316403308695, "learning_rate": 1.9896501972264303e-05, "loss": 0.6768, "step": 1984 }, { "epoch": 0.2828441151325164, "grad_norm": 1.6924291092033046, "learning_rate": 1.9896144778033455e-05, "loss": 0.7055, "step": 1985 }, { "epoch": 0.2829866058706184, "grad_norm": 1.6551296545219947, "learning_rate": 1.9895786971703778e-05, "loss": 0.7114, "step": 1986 }, { "epoch": 0.28312909660872043, "grad_norm": 1.7887475427165453, "learning_rate": 1.98954285532974e-05, "loss": 0.6831, "step": 1987 }, { "epoch": 0.28327158734682245, "grad_norm": 1.486048414103483, "learning_rate": 1.9895069522836495e-05, "loss": 0.6758, "step": 1988 }, { "epoch": 0.28341407808492447, "grad_norm": 1.6127884329531519, "learning_rate": 1.9894709880343262e-05, "loss": 0.7176, "step": 1989 }, { "epoch": 0.2835565688230265, "grad_norm": 1.5585638812750773, "learning_rate": 1.9894349625839954e-05, "loss": 0.6955, "step": 1990 }, { "epoch": 0.2836990595611285, "grad_norm": 1.6194467257411398, "learning_rate": 1.989398875934885e-05, "loss": 0.6617, "step": 1991 }, { "epoch": 0.2838415502992305, "grad_norm": 1.6907635700131407, "learning_rate": 1.9893627280892272e-05, "loss": 0.6592, "step": 1992 }, { "epoch": 0.28398404103733255, "grad_norm": 1.5545387654019889, "learning_rate": 1.9893265190492572e-05, "loss": 0.6421, "step": 1993 }, { "epoch": 0.2841265317754346, "grad_norm": 1.6007648636815561, "learning_rate": 1.9892902488172155e-05, "loss": 0.7565, "step": 1994 }, { "epoch": 0.28426902251353664, "grad_norm": 1.691951495589253, "learning_rate": 1.989253917395345e-05, "loss": 0.8092, "step": 1995 }, { "epoch": 0.28441151325163866, "grad_norm": 1.516283598801646, "learning_rate": 1.989217524785893e-05, "loss": 0.6531, "step": 1996 }, { "epoch": 0.2845540039897407, "grad_norm": 1.5425660651832713, "learning_rate": 1.9891810709911102e-05, "loss": 0.6569, "step": 1997 }, { "epoch": 0.2846964947278427, "grad_norm": 1.7473660996605285, "learning_rate": 1.9891445560132517e-05, "loss": 0.6148, "step": 1998 }, { "epoch": 0.2848389854659447, "grad_norm": 1.631105172485887, "learning_rate": 1.9891079798545762e-05, "loss": 0.7071, "step": 1999 }, { "epoch": 0.28498147620404674, "grad_norm": 1.8236375289304398, "learning_rate": 1.9890713425173454e-05, "loss": 0.6939, "step": 2000 }, { "epoch": 0.28512396694214875, "grad_norm": 1.6209600694706665, "learning_rate": 1.989034644003826e-05, "loss": 0.7247, "step": 2001 }, { "epoch": 0.2852664576802508, "grad_norm": 1.508518501074265, "learning_rate": 1.988997884316287e-05, "loss": 0.6984, "step": 2002 }, { "epoch": 0.2854089484183528, "grad_norm": 1.6981066741076256, "learning_rate": 1.988961063457003e-05, "loss": 0.6596, "step": 2003 }, { "epoch": 0.2855514391564548, "grad_norm": 1.5342300265053759, "learning_rate": 1.9889241814282515e-05, "loss": 0.7173, "step": 2004 }, { "epoch": 0.28569392989455683, "grad_norm": 1.6787106724339178, "learning_rate": 1.9888872382323132e-05, "loss": 0.6071, "step": 2005 }, { "epoch": 0.28583642063265885, "grad_norm": 1.6980358354378573, "learning_rate": 1.9888502338714733e-05, "loss": 0.6839, "step": 2006 }, { "epoch": 0.2859789113707609, "grad_norm": 1.5447450669959217, "learning_rate": 1.9888131683480204e-05, "loss": 0.6483, "step": 2007 }, { "epoch": 0.28612140210886294, "grad_norm": 1.7013649003400737, "learning_rate": 1.9887760416642473e-05, "loss": 0.7243, "step": 2008 }, { "epoch": 0.28626389284696496, "grad_norm": 1.8873970673293974, "learning_rate": 1.9887388538224504e-05, "loss": 0.6789, "step": 2009 }, { "epoch": 0.286406383585067, "grad_norm": 1.7473310914561195, "learning_rate": 1.9887016048249302e-05, "loss": 0.6031, "step": 2010 }, { "epoch": 0.286548874323169, "grad_norm": 1.5591631750461816, "learning_rate": 1.9886642946739898e-05, "loss": 0.7428, "step": 2011 }, { "epoch": 0.286691365061271, "grad_norm": 1.752979314661445, "learning_rate": 1.9886269233719373e-05, "loss": 0.7225, "step": 2012 }, { "epoch": 0.28683385579937304, "grad_norm": 1.7090420564400954, "learning_rate": 1.9885894909210847e-05, "loss": 0.8129, "step": 2013 }, { "epoch": 0.28697634653747506, "grad_norm": 1.6004838870678053, "learning_rate": 1.988551997323746e-05, "loss": 0.674, "step": 2014 }, { "epoch": 0.2871188372755771, "grad_norm": 1.5778589545841013, "learning_rate": 1.988514442582242e-05, "loss": 0.7324, "step": 2015 }, { "epoch": 0.2872613280136791, "grad_norm": 1.6158794982277234, "learning_rate": 1.9884768266988944e-05, "loss": 0.8182, "step": 2016 }, { "epoch": 0.2874038187517811, "grad_norm": 2.0044174468648515, "learning_rate": 1.9884391496760298e-05, "loss": 0.7204, "step": 2017 }, { "epoch": 0.28754630948988313, "grad_norm": 1.597593296621382, "learning_rate": 1.988401411515979e-05, "loss": 0.7154, "step": 2018 }, { "epoch": 0.2876888002279852, "grad_norm": 1.771099719809576, "learning_rate": 1.988363612221076e-05, "loss": 0.7744, "step": 2019 }, { "epoch": 0.2878312909660872, "grad_norm": 1.6340359665932267, "learning_rate": 1.988325751793659e-05, "loss": 0.6145, "step": 2020 }, { "epoch": 0.28797378170418925, "grad_norm": 1.6536697699030587, "learning_rate": 1.9882878302360695e-05, "loss": 0.6524, "step": 2021 }, { "epoch": 0.28811627244229127, "grad_norm": 1.516326829826821, "learning_rate": 1.9882498475506532e-05, "loss": 0.7549, "step": 2022 }, { "epoch": 0.2882587631803933, "grad_norm": 1.61362957869837, "learning_rate": 1.9882118037397595e-05, "loss": 0.7173, "step": 2023 }, { "epoch": 0.2884012539184953, "grad_norm": 1.719357893298084, "learning_rate": 1.9881736988057412e-05, "loss": 0.7557, "step": 2024 }, { "epoch": 0.2885437446565973, "grad_norm": 1.5127589768931193, "learning_rate": 1.9881355327509554e-05, "loss": 0.686, "step": 2025 }, { "epoch": 0.28868623539469934, "grad_norm": 1.635404192845437, "learning_rate": 1.9880973055777622e-05, "loss": 0.7009, "step": 2026 }, { "epoch": 0.28882872613280136, "grad_norm": 1.8174367872570334, "learning_rate": 1.988059017288527e-05, "loss": 0.704, "step": 2027 }, { "epoch": 0.2889712168709034, "grad_norm": 1.6505935053821428, "learning_rate": 1.9880206678856175e-05, "loss": 0.7493, "step": 2028 }, { "epoch": 0.2891137076090054, "grad_norm": 1.53938480598139, "learning_rate": 1.9879822573714052e-05, "loss": 0.7202, "step": 2029 }, { "epoch": 0.2892561983471074, "grad_norm": 1.9696233777531693, "learning_rate": 1.987943785748267e-05, "loss": 0.6804, "step": 2030 }, { "epoch": 0.28939868908520944, "grad_norm": 1.7764049122391417, "learning_rate": 1.9879052530185816e-05, "loss": 0.6958, "step": 2031 }, { "epoch": 0.2895411798233115, "grad_norm": 1.5619308213614231, "learning_rate": 1.9878666591847328e-05, "loss": 0.7591, "step": 2032 }, { "epoch": 0.28968367056141353, "grad_norm": 2.4788423793561503, "learning_rate": 1.9878280042491073e-05, "loss": 0.7936, "step": 2033 }, { "epoch": 0.28982616129951555, "grad_norm": 1.9654877037812728, "learning_rate": 1.987789288214096e-05, "loss": 0.7576, "step": 2034 }, { "epoch": 0.28996865203761757, "grad_norm": 1.7778392761244632, "learning_rate": 1.9877505110820943e-05, "loss": 0.7208, "step": 2035 }, { "epoch": 0.2901111427757196, "grad_norm": 2.2023321234985356, "learning_rate": 1.9877116728555e-05, "loss": 0.7003, "step": 2036 }, { "epoch": 0.2902536335138216, "grad_norm": 1.7180472002265326, "learning_rate": 1.9876727735367153e-05, "loss": 0.6841, "step": 2037 }, { "epoch": 0.2903961242519236, "grad_norm": 1.7849413555086011, "learning_rate": 1.9876338131281462e-05, "loss": 0.7718, "step": 2038 }, { "epoch": 0.29053861499002565, "grad_norm": 1.8635028015361983, "learning_rate": 1.9875947916322027e-05, "loss": 0.6699, "step": 2039 }, { "epoch": 0.29068110572812766, "grad_norm": 2.031564558530629, "learning_rate": 1.9875557090512988e-05, "loss": 0.7584, "step": 2040 }, { "epoch": 0.2908235964662297, "grad_norm": 1.950762412970083, "learning_rate": 1.987516565387851e-05, "loss": 0.7288, "step": 2041 }, { "epoch": 0.2909660872043317, "grad_norm": 2.18131109915844, "learning_rate": 1.9874773606442804e-05, "loss": 0.5692, "step": 2042 }, { "epoch": 0.2911085779424337, "grad_norm": 1.7167569140568828, "learning_rate": 1.987438094823013e-05, "loss": 0.7334, "step": 2043 }, { "epoch": 0.29125106868053574, "grad_norm": 2.104908266965351, "learning_rate": 1.9873987679264764e-05, "loss": 0.7781, "step": 2044 }, { "epoch": 0.2913935594186378, "grad_norm": 1.6247896354414102, "learning_rate": 1.9873593799571035e-05, "loss": 0.7889, "step": 2045 }, { "epoch": 0.29153605015673983, "grad_norm": 1.7704848390679981, "learning_rate": 1.987319930917331e-05, "loss": 0.6855, "step": 2046 }, { "epoch": 0.29167854089484185, "grad_norm": 1.686626054472164, "learning_rate": 1.9872804208095976e-05, "loss": 0.7167, "step": 2047 }, { "epoch": 0.2918210316329439, "grad_norm": 1.6610724218710538, "learning_rate": 1.987240849636348e-05, "loss": 0.5884, "step": 2048 }, { "epoch": 0.2919635223710459, "grad_norm": 1.6403583131695232, "learning_rate": 1.9872012174000298e-05, "loss": 0.7119, "step": 2049 }, { "epoch": 0.2921060131091479, "grad_norm": 2.6354462682547135, "learning_rate": 1.9871615241030942e-05, "loss": 0.7347, "step": 2050 }, { "epoch": 0.29224850384724993, "grad_norm": 1.7731412463685379, "learning_rate": 1.9871217697479963e-05, "loss": 0.7921, "step": 2051 }, { "epoch": 0.29239099458535195, "grad_norm": 1.4856286834027632, "learning_rate": 1.9870819543371952e-05, "loss": 0.6711, "step": 2052 }, { "epoch": 0.29253348532345397, "grad_norm": 2.0864021807671405, "learning_rate": 1.987042077873153e-05, "loss": 0.714, "step": 2053 }, { "epoch": 0.292675976061556, "grad_norm": 1.607797452082196, "learning_rate": 1.9870021403583364e-05, "loss": 0.6703, "step": 2054 }, { "epoch": 0.292818466799658, "grad_norm": 1.628851472584853, "learning_rate": 1.9869621417952163e-05, "loss": 0.7238, "step": 2055 }, { "epoch": 0.29296095753776, "grad_norm": 1.973588901969622, "learning_rate": 1.986922082186266e-05, "loss": 0.7488, "step": 2056 }, { "epoch": 0.29310344827586204, "grad_norm": 1.4849197643894263, "learning_rate": 1.9868819615339628e-05, "loss": 0.6861, "step": 2057 }, { "epoch": 0.2932459390139641, "grad_norm": 1.7418510413534962, "learning_rate": 1.9868417798407894e-05, "loss": 0.7239, "step": 2058 }, { "epoch": 0.29338842975206614, "grad_norm": 1.631315156807748, "learning_rate": 1.9868015371092305e-05, "loss": 0.6268, "step": 2059 }, { "epoch": 0.29353092049016816, "grad_norm": 1.6825407767081197, "learning_rate": 1.9867612333417754e-05, "loss": 0.6815, "step": 2060 }, { "epoch": 0.2936734112282702, "grad_norm": 1.9615097947037718, "learning_rate": 1.9867208685409168e-05, "loss": 0.7276, "step": 2061 }, { "epoch": 0.2938159019663722, "grad_norm": 1.6559431487527603, "learning_rate": 1.9866804427091514e-05, "loss": 0.7017, "step": 2062 }, { "epoch": 0.2939583927044742, "grad_norm": 1.5856080000363342, "learning_rate": 1.98663995584898e-05, "loss": 0.6722, "step": 2063 }, { "epoch": 0.29410088344257623, "grad_norm": 1.6880280063218442, "learning_rate": 1.9865994079629062e-05, "loss": 0.7267, "step": 2064 }, { "epoch": 0.29424337418067825, "grad_norm": 1.528954735016033, "learning_rate": 1.9865587990534382e-05, "loss": 0.6502, "step": 2065 }, { "epoch": 0.29438586491878027, "grad_norm": 1.8307191360740926, "learning_rate": 1.9865181291230878e-05, "loss": 0.703, "step": 2066 }, { "epoch": 0.2945283556568823, "grad_norm": 1.6204457023513663, "learning_rate": 1.9864773981743705e-05, "loss": 0.648, "step": 2067 }, { "epoch": 0.2946708463949843, "grad_norm": 1.6984947461109414, "learning_rate": 1.9864366062098058e-05, "loss": 0.6797, "step": 2068 }, { "epoch": 0.29481333713308633, "grad_norm": 1.6582373013002047, "learning_rate": 1.9863957532319164e-05, "loss": 0.6554, "step": 2069 }, { "epoch": 0.29495582787118835, "grad_norm": 1.6769453483249221, "learning_rate": 1.9863548392432294e-05, "loss": 0.7419, "step": 2070 }, { "epoch": 0.2950983186092904, "grad_norm": 1.8715720102007245, "learning_rate": 1.9863138642462754e-05, "loss": 0.7405, "step": 2071 }, { "epoch": 0.29524080934739244, "grad_norm": 1.5948964369282526, "learning_rate": 1.9862728282435888e-05, "loss": 0.6907, "step": 2072 }, { "epoch": 0.29538330008549446, "grad_norm": 1.8785232920213295, "learning_rate": 1.986231731237708e-05, "loss": 0.7469, "step": 2073 }, { "epoch": 0.2955257908235965, "grad_norm": 5.028816152170076, "learning_rate": 1.986190573231174e-05, "loss": 0.7674, "step": 2074 }, { "epoch": 0.2956682815616985, "grad_norm": 1.8943369866671276, "learning_rate": 1.9861493542265336e-05, "loss": 0.6444, "step": 2075 }, { "epoch": 0.2958107722998005, "grad_norm": 1.8623338218838317, "learning_rate": 1.986108074226336e-05, "loss": 0.6639, "step": 2076 }, { "epoch": 0.29595326303790254, "grad_norm": 2.758186763572398, "learning_rate": 1.986066733233134e-05, "loss": 0.8067, "step": 2077 }, { "epoch": 0.29609575377600456, "grad_norm": 3.0510596972074704, "learning_rate": 1.9860253312494854e-05, "loss": 0.6957, "step": 2078 }, { "epoch": 0.2962382445141066, "grad_norm": 2.783934792330616, "learning_rate": 1.9859838682779503e-05, "loss": 0.6828, "step": 2079 }, { "epoch": 0.2963807352522086, "grad_norm": 1.8005930198783264, "learning_rate": 1.9859423443210936e-05, "loss": 0.7966, "step": 2080 }, { "epoch": 0.2965232259903106, "grad_norm": 1.8996692175401708, "learning_rate": 1.9859007593814836e-05, "loss": 0.7275, "step": 2081 }, { "epoch": 0.29666571672841263, "grad_norm": 2.8168668960640844, "learning_rate": 1.9858591134616926e-05, "loss": 0.7212, "step": 2082 }, { "epoch": 0.29680820746651465, "grad_norm": 1.6955614249994793, "learning_rate": 1.9858174065642964e-05, "loss": 0.6982, "step": 2083 }, { "epoch": 0.2969506982046167, "grad_norm": 1.494700699426692, "learning_rate": 1.9857756386918743e-05, "loss": 0.6806, "step": 2084 }, { "epoch": 0.29709318894271874, "grad_norm": 1.5985384739493047, "learning_rate": 1.9857338098470102e-05, "loss": 0.6946, "step": 2085 }, { "epoch": 0.29723567968082076, "grad_norm": 2.686445003949331, "learning_rate": 1.985691920032291e-05, "loss": 0.6421, "step": 2086 }, { "epoch": 0.2973781704189228, "grad_norm": 1.841873709856621, "learning_rate": 1.9856499692503078e-05, "loss": 0.6881, "step": 2087 }, { "epoch": 0.2975206611570248, "grad_norm": 1.7857954610530256, "learning_rate": 1.9856079575036557e-05, "loss": 0.7609, "step": 2088 }, { "epoch": 0.2976631518951268, "grad_norm": 1.6615134527625388, "learning_rate": 1.9855658847949324e-05, "loss": 0.6599, "step": 2089 }, { "epoch": 0.29780564263322884, "grad_norm": 1.5419691690070123, "learning_rate": 1.985523751126741e-05, "loss": 0.6623, "step": 2090 }, { "epoch": 0.29794813337133086, "grad_norm": 1.476934172402756, "learning_rate": 1.985481556501687e-05, "loss": 0.7116, "step": 2091 }, { "epoch": 0.2980906241094329, "grad_norm": 1.5820568688182302, "learning_rate": 1.9854393009223808e-05, "loss": 0.7334, "step": 2092 }, { "epoch": 0.2982331148475349, "grad_norm": 1.4459975636405566, "learning_rate": 1.9853969843914357e-05, "loss": 0.6712, "step": 2093 }, { "epoch": 0.2983756055856369, "grad_norm": 1.664437691105221, "learning_rate": 1.9853546069114688e-05, "loss": 0.7743, "step": 2094 }, { "epoch": 0.29851809632373894, "grad_norm": 1.7599765376572067, "learning_rate": 1.9853121684851016e-05, "loss": 0.7568, "step": 2095 }, { "epoch": 0.29866058706184095, "grad_norm": 1.6085954630959842, "learning_rate": 1.9852696691149587e-05, "loss": 0.7798, "step": 2096 }, { "epoch": 0.29880307779994303, "grad_norm": 1.6569345262257713, "learning_rate": 1.9852271088036695e-05, "loss": 0.747, "step": 2097 }, { "epoch": 0.29894556853804505, "grad_norm": 1.4882215704710873, "learning_rate": 1.9851844875538654e-05, "loss": 0.7099, "step": 2098 }, { "epoch": 0.29908805927614707, "grad_norm": 1.6893264587125494, "learning_rate": 1.9851418053681835e-05, "loss": 0.8052, "step": 2099 }, { "epoch": 0.2992305500142491, "grad_norm": 1.6864318609851154, "learning_rate": 1.985099062249263e-05, "loss": 0.6911, "step": 2100 }, { "epoch": 0.2993730407523511, "grad_norm": 1.4585104666290114, "learning_rate": 1.985056258199749e-05, "loss": 0.6512, "step": 2101 }, { "epoch": 0.2995155314904531, "grad_norm": 1.6473835147783593, "learning_rate": 1.985013393222287e-05, "loss": 0.7976, "step": 2102 }, { "epoch": 0.29965802222855514, "grad_norm": 2.229548601754316, "learning_rate": 1.9849704673195303e-05, "loss": 0.7747, "step": 2103 }, { "epoch": 0.29980051296665716, "grad_norm": 1.682480644607222, "learning_rate": 1.9849274804941328e-05, "loss": 0.8033, "step": 2104 }, { "epoch": 0.2999430037047592, "grad_norm": 1.6125734111965857, "learning_rate": 1.9848844327487534e-05, "loss": 0.7467, "step": 2105 }, { "epoch": 0.3000854944428612, "grad_norm": 1.584142312426728, "learning_rate": 1.9848413240860554e-05, "loss": 0.6885, "step": 2106 }, { "epoch": 0.3002279851809632, "grad_norm": 1.5622133709868087, "learning_rate": 1.9847981545087042e-05, "loss": 0.7367, "step": 2107 }, { "epoch": 0.30037047591906524, "grad_norm": 1.5564115636486633, "learning_rate": 1.9847549240193705e-05, "loss": 0.696, "step": 2108 }, { "epoch": 0.30051296665716726, "grad_norm": 1.841754883058733, "learning_rate": 1.9847116326207284e-05, "loss": 0.7802, "step": 2109 }, { "epoch": 0.30065545739526933, "grad_norm": 1.873526476705807, "learning_rate": 1.9846682803154552e-05, "loss": 0.7271, "step": 2110 }, { "epoch": 0.30079794813337135, "grad_norm": 1.725953156340755, "learning_rate": 1.9846248671062325e-05, "loss": 0.777, "step": 2111 }, { "epoch": 0.30094043887147337, "grad_norm": 1.7204581318342207, "learning_rate": 1.9845813929957454e-05, "loss": 0.7303, "step": 2112 }, { "epoch": 0.3010829296095754, "grad_norm": 1.7620079418330634, "learning_rate": 1.9845378579866827e-05, "loss": 0.6108, "step": 2113 }, { "epoch": 0.3012254203476774, "grad_norm": 1.6222327284452533, "learning_rate": 1.9844942620817378e-05, "loss": 0.6334, "step": 2114 }, { "epoch": 0.3013679110857794, "grad_norm": 1.6941641914469607, "learning_rate": 1.9844506052836065e-05, "loss": 0.7218, "step": 2115 }, { "epoch": 0.30151040182388145, "grad_norm": 1.8771970187425224, "learning_rate": 1.984406887594989e-05, "loss": 0.7059, "step": 2116 }, { "epoch": 0.30165289256198347, "grad_norm": 1.8587992258733532, "learning_rate": 1.98436310901859e-05, "loss": 0.7454, "step": 2117 }, { "epoch": 0.3017953833000855, "grad_norm": 1.5091342114320858, "learning_rate": 1.9843192695571172e-05, "loss": 0.6536, "step": 2118 }, { "epoch": 0.3019378740381875, "grad_norm": 1.4898551843835839, "learning_rate": 1.9842753692132817e-05, "loss": 0.7273, "step": 2119 }, { "epoch": 0.3020803647762895, "grad_norm": 1.6131032972365595, "learning_rate": 1.9842314079897992e-05, "loss": 0.6716, "step": 2120 }, { "epoch": 0.30222285551439154, "grad_norm": 1.7157506389874606, "learning_rate": 1.9841873858893885e-05, "loss": 0.6884, "step": 2121 }, { "epoch": 0.30236534625249356, "grad_norm": 1.5844473597776796, "learning_rate": 1.9841433029147725e-05, "loss": 0.6514, "step": 2122 }, { "epoch": 0.30250783699059564, "grad_norm": 1.7013943299198335, "learning_rate": 1.984099159068678e-05, "loss": 0.7209, "step": 2123 }, { "epoch": 0.30265032772869765, "grad_norm": 1.5285079856174586, "learning_rate": 1.9840549543538357e-05, "loss": 0.5997, "step": 2124 }, { "epoch": 0.3027928184667997, "grad_norm": 1.6290457185884741, "learning_rate": 1.9840106887729794e-05, "loss": 0.7202, "step": 2125 }, { "epoch": 0.3029353092049017, "grad_norm": 1.557034802381495, "learning_rate": 1.9839663623288467e-05, "loss": 0.7219, "step": 2126 }, { "epoch": 0.3030777999430037, "grad_norm": 1.6352569093677694, "learning_rate": 1.98392197502418e-05, "loss": 0.6909, "step": 2127 }, { "epoch": 0.30322029068110573, "grad_norm": 1.520518182360501, "learning_rate": 1.9838775268617243e-05, "loss": 0.7258, "step": 2128 }, { "epoch": 0.30336278141920775, "grad_norm": 1.6339941872583421, "learning_rate": 1.9838330178442288e-05, "loss": 0.78, "step": 2129 }, { "epoch": 0.30350527215730977, "grad_norm": 1.6239713937047404, "learning_rate": 1.9837884479744467e-05, "loss": 0.7082, "step": 2130 }, { "epoch": 0.3036477628954118, "grad_norm": 1.621018385944167, "learning_rate": 1.9837438172551346e-05, "loss": 0.6716, "step": 2131 }, { "epoch": 0.3037902536335138, "grad_norm": 2.3364942871924903, "learning_rate": 1.9836991256890533e-05, "loss": 0.7543, "step": 2132 }, { "epoch": 0.3039327443716158, "grad_norm": 1.656041589113924, "learning_rate": 1.9836543732789666e-05, "loss": 0.744, "step": 2133 }, { "epoch": 0.30407523510971785, "grad_norm": 1.7343382924125068, "learning_rate": 1.9836095600276425e-05, "loss": 0.7733, "step": 2134 }, { "epoch": 0.30421772584781986, "grad_norm": 1.7254642734455008, "learning_rate": 1.9835646859378537e-05, "loss": 0.6906, "step": 2135 }, { "epoch": 0.30436021658592194, "grad_norm": 1.7954945021474318, "learning_rate": 1.9835197510123747e-05, "loss": 0.6832, "step": 2136 }, { "epoch": 0.30450270732402396, "grad_norm": 1.5997688206559153, "learning_rate": 1.9834747552539856e-05, "loss": 0.7241, "step": 2137 }, { "epoch": 0.304645198062126, "grad_norm": 1.531033011472386, "learning_rate": 1.9834296986654687e-05, "loss": 0.6966, "step": 2138 }, { "epoch": 0.304787688800228, "grad_norm": 1.642008116285032, "learning_rate": 1.9833845812496117e-05, "loss": 0.6356, "step": 2139 }, { "epoch": 0.30493017953833, "grad_norm": 1.6328686355236188, "learning_rate": 1.9833394030092044e-05, "loss": 0.7538, "step": 2140 }, { "epoch": 0.30507267027643203, "grad_norm": 1.6494408562850769, "learning_rate": 1.9832941639470417e-05, "loss": 0.7399, "step": 2141 }, { "epoch": 0.30521516101453405, "grad_norm": 1.6413647936554785, "learning_rate": 1.983248864065922e-05, "loss": 0.5854, "step": 2142 }, { "epoch": 0.3053576517526361, "grad_norm": 1.6255551097481244, "learning_rate": 1.9832035033686465e-05, "loss": 0.7848, "step": 2143 }, { "epoch": 0.3055001424907381, "grad_norm": 1.5740381159957852, "learning_rate": 1.9831580818580213e-05, "loss": 0.7561, "step": 2144 }, { "epoch": 0.3056426332288401, "grad_norm": 1.9187282697761403, "learning_rate": 1.9831125995368558e-05, "loss": 0.7071, "step": 2145 }, { "epoch": 0.30578512396694213, "grad_norm": 1.5558868140037991, "learning_rate": 1.9830670564079627e-05, "loss": 0.6531, "step": 2146 }, { "epoch": 0.30592761470504415, "grad_norm": 1.642363060036023, "learning_rate": 1.9830214524741597e-05, "loss": 0.6988, "step": 2147 }, { "epoch": 0.3060701054431462, "grad_norm": 1.8041359846470137, "learning_rate": 1.9829757877382673e-05, "loss": 0.7192, "step": 2148 }, { "epoch": 0.30621259618124824, "grad_norm": 1.4841419165792173, "learning_rate": 1.9829300622031096e-05, "loss": 0.5902, "step": 2149 }, { "epoch": 0.30635508691935026, "grad_norm": 1.84013316984809, "learning_rate": 1.982884275871515e-05, "loss": 0.7443, "step": 2150 }, { "epoch": 0.3064975776574523, "grad_norm": 1.585113898759697, "learning_rate": 1.9828384287463153e-05, "loss": 0.8135, "step": 2151 }, { "epoch": 0.3066400683955543, "grad_norm": 1.7226808768278088, "learning_rate": 1.982792520830347e-05, "loss": 0.7323, "step": 2152 }, { "epoch": 0.3067825591336563, "grad_norm": 2.2777325307643763, "learning_rate": 1.9827465521264486e-05, "loss": 0.6298, "step": 2153 }, { "epoch": 0.30692504987175834, "grad_norm": 1.5402925615925696, "learning_rate": 1.982700522637464e-05, "loss": 0.6592, "step": 2154 }, { "epoch": 0.30706754060986036, "grad_norm": 1.5307677537807565, "learning_rate": 1.9826544323662403e-05, "loss": 0.6816, "step": 2155 }, { "epoch": 0.3072100313479624, "grad_norm": 1.8132734538058766, "learning_rate": 1.982608281315628e-05, "loss": 0.7078, "step": 2156 }, { "epoch": 0.3073525220860644, "grad_norm": 1.797140412931178, "learning_rate": 1.9825620694884813e-05, "loss": 0.7525, "step": 2157 }, { "epoch": 0.3074950128241664, "grad_norm": 1.5170094105786545, "learning_rate": 1.9825157968876594e-05, "loss": 0.6914, "step": 2158 }, { "epoch": 0.30763750356226843, "grad_norm": 1.940103537625316, "learning_rate": 1.982469463516024e-05, "loss": 0.7876, "step": 2159 }, { "epoch": 0.30777999430037045, "grad_norm": 1.7393114371236482, "learning_rate": 1.9824230693764403e-05, "loss": 0.7608, "step": 2160 }, { "epoch": 0.3079224850384725, "grad_norm": 1.7183942434817867, "learning_rate": 1.982376614471779e-05, "loss": 0.7883, "step": 2161 }, { "epoch": 0.30806497577657455, "grad_norm": 1.547209467667134, "learning_rate": 1.982330098804912e-05, "loss": 0.7128, "step": 2162 }, { "epoch": 0.30820746651467656, "grad_norm": 1.673472935543426, "learning_rate": 1.982283522378718e-05, "loss": 0.6599, "step": 2163 }, { "epoch": 0.3083499572527786, "grad_norm": 1.5194255440679114, "learning_rate": 1.9822368851960766e-05, "loss": 0.7445, "step": 2164 }, { "epoch": 0.3084924479908806, "grad_norm": 1.63338604084467, "learning_rate": 1.9821901872598733e-05, "loss": 0.6919, "step": 2165 }, { "epoch": 0.3086349387289826, "grad_norm": 1.500506250934481, "learning_rate": 1.9821434285729955e-05, "loss": 0.7453, "step": 2166 }, { "epoch": 0.30877742946708464, "grad_norm": 1.6500460494494205, "learning_rate": 1.9820966091383365e-05, "loss": 0.6262, "step": 2167 }, { "epoch": 0.30891992020518666, "grad_norm": 1.6580772522786602, "learning_rate": 1.9820497289587913e-05, "loss": 0.7685, "step": 2168 }, { "epoch": 0.3090624109432887, "grad_norm": 1.5683904671255189, "learning_rate": 1.9820027880372598e-05, "loss": 0.7026, "step": 2169 }, { "epoch": 0.3092049016813907, "grad_norm": 1.640982374012761, "learning_rate": 1.9819557863766454e-05, "loss": 0.7394, "step": 2170 }, { "epoch": 0.3093473924194927, "grad_norm": 1.5323979887519, "learning_rate": 1.9819087239798557e-05, "loss": 0.7385, "step": 2171 }, { "epoch": 0.30948988315759474, "grad_norm": 1.4764810600854705, "learning_rate": 1.9818616008498004e-05, "loss": 0.6393, "step": 2172 }, { "epoch": 0.30963237389569676, "grad_norm": 1.570550743348623, "learning_rate": 1.9818144169893958e-05, "loss": 0.7593, "step": 2173 }, { "epoch": 0.30977486463379883, "grad_norm": 1.4960010638209162, "learning_rate": 1.9817671724015593e-05, "loss": 0.658, "step": 2174 }, { "epoch": 0.30991735537190085, "grad_norm": 1.5115960005809979, "learning_rate": 1.981719867089213e-05, "loss": 0.7854, "step": 2175 }, { "epoch": 0.31005984611000287, "grad_norm": 1.4779679572153341, "learning_rate": 1.9816725010552836e-05, "loss": 0.7513, "step": 2176 }, { "epoch": 0.3102023368481049, "grad_norm": 1.448604178372223, "learning_rate": 1.9816250743027e-05, "loss": 0.7318, "step": 2177 }, { "epoch": 0.3103448275862069, "grad_norm": 1.5806219729542643, "learning_rate": 1.981577586834396e-05, "loss": 0.6826, "step": 2178 }, { "epoch": 0.3104873183243089, "grad_norm": 1.6351200029203248, "learning_rate": 1.981530038653309e-05, "loss": 0.7358, "step": 2179 }, { "epoch": 0.31062980906241094, "grad_norm": 1.7884152313326231, "learning_rate": 1.9814824297623794e-05, "loss": 0.7163, "step": 2180 }, { "epoch": 0.31077229980051296, "grad_norm": 1.6742481618908716, "learning_rate": 1.9814347601645523e-05, "loss": 0.6832, "step": 2181 }, { "epoch": 0.310914790538615, "grad_norm": 1.6901352469077893, "learning_rate": 1.9813870298627766e-05, "loss": 0.7061, "step": 2182 }, { "epoch": 0.311057281276717, "grad_norm": 1.4559231786526319, "learning_rate": 1.9813392388600038e-05, "loss": 0.6839, "step": 2183 }, { "epoch": 0.311199772014819, "grad_norm": 2.1455471391885315, "learning_rate": 1.98129138715919e-05, "loss": 0.779, "step": 2184 }, { "epoch": 0.31134226275292104, "grad_norm": 1.601086979802511, "learning_rate": 1.9812434747632953e-05, "loss": 0.7, "step": 2185 }, { "epoch": 0.31148475349102306, "grad_norm": 1.3615565176726028, "learning_rate": 1.9811955016752827e-05, "loss": 0.6691, "step": 2186 }, { "epoch": 0.31162724422912513, "grad_norm": 1.3596888430084688, "learning_rate": 1.9811474678981198e-05, "loss": 0.6523, "step": 2187 }, { "epoch": 0.31176973496722715, "grad_norm": 1.6288177475254229, "learning_rate": 1.9810993734347775e-05, "loss": 0.7119, "step": 2188 }, { "epoch": 0.31191222570532917, "grad_norm": 1.6365503590160322, "learning_rate": 1.9810512182882307e-05, "loss": 0.7068, "step": 2189 }, { "epoch": 0.3120547164434312, "grad_norm": 1.6340909938156933, "learning_rate": 1.9810030024614578e-05, "loss": 0.7183, "step": 2190 }, { "epoch": 0.3121972071815332, "grad_norm": 1.6386705402685067, "learning_rate": 1.9809547259574408e-05, "loss": 0.7861, "step": 2191 }, { "epoch": 0.31233969791963523, "grad_norm": 1.456874056717009, "learning_rate": 1.980906388779166e-05, "loss": 0.7386, "step": 2192 }, { "epoch": 0.31248218865773725, "grad_norm": 1.7640935731158363, "learning_rate": 1.9808579909296233e-05, "loss": 0.6802, "step": 2193 }, { "epoch": 0.31262467939583927, "grad_norm": 1.6058924632707698, "learning_rate": 1.9808095324118056e-05, "loss": 0.7291, "step": 2194 }, { "epoch": 0.3127671701339413, "grad_norm": 2.1238407765712437, "learning_rate": 1.980761013228711e-05, "loss": 0.6723, "step": 2195 }, { "epoch": 0.3129096608720433, "grad_norm": 1.5606142213037155, "learning_rate": 1.9807124333833402e-05, "loss": 0.6958, "step": 2196 }, { "epoch": 0.3130521516101453, "grad_norm": 1.3917580487525922, "learning_rate": 1.9806637928786974e-05, "loss": 0.6698, "step": 2197 }, { "epoch": 0.31319464234824734, "grad_norm": 1.5664351322407026, "learning_rate": 1.980615091717792e-05, "loss": 0.7073, "step": 2198 }, { "epoch": 0.31333713308634936, "grad_norm": 1.620999126152012, "learning_rate": 1.9805663299036357e-05, "loss": 0.7744, "step": 2199 }, { "epoch": 0.31347962382445144, "grad_norm": 1.5028503546005783, "learning_rate": 1.9805175074392447e-05, "loss": 0.7642, "step": 2200 }, { "epoch": 0.31362211456255346, "grad_norm": 1.5801719559412268, "learning_rate": 1.980468624327639e-05, "loss": 0.7762, "step": 2201 }, { "epoch": 0.3137646053006555, "grad_norm": 1.5957027257161205, "learning_rate": 1.9804196805718415e-05, "loss": 0.788, "step": 2202 }, { "epoch": 0.3139070960387575, "grad_norm": 1.7772663849885335, "learning_rate": 1.98037067617488e-05, "loss": 0.8082, "step": 2203 }, { "epoch": 0.3140495867768595, "grad_norm": 1.7256595609587508, "learning_rate": 1.9803216111397857e-05, "loss": 0.7035, "step": 2204 }, { "epoch": 0.31419207751496153, "grad_norm": 1.56085225322876, "learning_rate": 1.980272485469593e-05, "loss": 0.6647, "step": 2205 }, { "epoch": 0.31433456825306355, "grad_norm": 1.5729867107175328, "learning_rate": 1.9802232991673404e-05, "loss": 0.6501, "step": 2206 }, { "epoch": 0.31447705899116557, "grad_norm": 1.7017437520069583, "learning_rate": 1.9801740522360705e-05, "loss": 0.6828, "step": 2207 }, { "epoch": 0.3146195497292676, "grad_norm": 1.4090552974683304, "learning_rate": 1.980124744678829e-05, "loss": 0.6641, "step": 2208 }, { "epoch": 0.3147620404673696, "grad_norm": 1.4491626835915206, "learning_rate": 1.980075376498666e-05, "loss": 0.6801, "step": 2209 }, { "epoch": 0.3149045312054716, "grad_norm": 1.6527968651031881, "learning_rate": 1.980025947698635e-05, "loss": 0.6337, "step": 2210 }, { "epoch": 0.31504702194357365, "grad_norm": 1.5406355036944788, "learning_rate": 1.9799764582817927e-05, "loss": 0.6635, "step": 2211 }, { "epoch": 0.31518951268167567, "grad_norm": 1.4216024757056867, "learning_rate": 1.979926908251201e-05, "loss": 0.7439, "step": 2212 }, { "epoch": 0.31533200341977774, "grad_norm": 1.9790041885292693, "learning_rate": 1.979877297609924e-05, "loss": 0.7096, "step": 2213 }, { "epoch": 0.31547449415787976, "grad_norm": 1.4281147579627758, "learning_rate": 1.9798276263610305e-05, "loss": 0.6441, "step": 2214 }, { "epoch": 0.3156169848959818, "grad_norm": 1.5306421771553431, "learning_rate": 1.979777894507593e-05, "loss": 0.7667, "step": 2215 }, { "epoch": 0.3157594756340838, "grad_norm": 1.6493979990898628, "learning_rate": 1.9797281020526873e-05, "loss": 0.7169, "step": 2216 }, { "epoch": 0.3159019663721858, "grad_norm": 1.8233698094005863, "learning_rate": 1.979678248999393e-05, "loss": 0.7754, "step": 2217 }, { "epoch": 0.31604445711028784, "grad_norm": 1.5415397336990455, "learning_rate": 1.979628335350794e-05, "loss": 0.6529, "step": 2218 }, { "epoch": 0.31618694784838985, "grad_norm": 2.0572031661571115, "learning_rate": 1.979578361109977e-05, "loss": 0.6835, "step": 2219 }, { "epoch": 0.3163294385864919, "grad_norm": 1.4954805662927815, "learning_rate": 1.979528326280034e-05, "loss": 0.7519, "step": 2220 }, { "epoch": 0.3164719293245939, "grad_norm": 1.5791430979856795, "learning_rate": 1.979478230864059e-05, "loss": 0.7208, "step": 2221 }, { "epoch": 0.3166144200626959, "grad_norm": 1.6576506236548374, "learning_rate": 1.9794280748651503e-05, "loss": 0.6731, "step": 2222 }, { "epoch": 0.31675691080079793, "grad_norm": 1.84124428906306, "learning_rate": 1.979377858286411e-05, "loss": 0.7593, "step": 2223 }, { "epoch": 0.31689940153889995, "grad_norm": 1.6987992913238086, "learning_rate": 1.9793275811309462e-05, "loss": 0.7491, "step": 2224 }, { "epoch": 0.31704189227700197, "grad_norm": 2.053273339632608, "learning_rate": 1.9792772434018667e-05, "loss": 0.8013, "step": 2225 }, { "epoch": 0.31718438301510404, "grad_norm": 1.4306717518844765, "learning_rate": 1.9792268451022848e-05, "loss": 0.6694, "step": 2226 }, { "epoch": 0.31732687375320606, "grad_norm": 1.589468913593666, "learning_rate": 1.9791763862353186e-05, "loss": 0.7153, "step": 2227 }, { "epoch": 0.3174693644913081, "grad_norm": 1.4934682618255088, "learning_rate": 1.979125866804089e-05, "loss": 0.6756, "step": 2228 }, { "epoch": 0.3176118552294101, "grad_norm": 1.4392794483095601, "learning_rate": 1.9790752868117202e-05, "loss": 0.8217, "step": 2229 }, { "epoch": 0.3177543459675121, "grad_norm": 1.5884260142096056, "learning_rate": 1.9790246462613415e-05, "loss": 0.7277, "step": 2230 }, { "epoch": 0.31789683670561414, "grad_norm": 1.4584434652531002, "learning_rate": 1.9789739451560845e-05, "loss": 0.6727, "step": 2231 }, { "epoch": 0.31803932744371616, "grad_norm": 1.4871385796510757, "learning_rate": 1.9789231834990854e-05, "loss": 0.694, "step": 2232 }, { "epoch": 0.3181818181818182, "grad_norm": 1.600073157705383, "learning_rate": 1.978872361293484e-05, "loss": 0.7235, "step": 2233 }, { "epoch": 0.3183243089199202, "grad_norm": 1.5736953083414635, "learning_rate": 1.9788214785424236e-05, "loss": 0.8263, "step": 2234 }, { "epoch": 0.3184667996580222, "grad_norm": 1.7683799789409782, "learning_rate": 1.9787705352490515e-05, "loss": 0.7958, "step": 2235 }, { "epoch": 0.31860929039612423, "grad_norm": 1.582487275821147, "learning_rate": 1.9787195314165183e-05, "loss": 0.8099, "step": 2236 }, { "epoch": 0.31875178113422625, "grad_norm": 1.6334380262596755, "learning_rate": 1.9786684670479793e-05, "loss": 0.7424, "step": 2237 }, { "epoch": 0.31889427187232827, "grad_norm": 1.6144930054498987, "learning_rate": 1.9786173421465932e-05, "loss": 0.6658, "step": 2238 }, { "epoch": 0.31903676261043035, "grad_norm": 1.4670136576222297, "learning_rate": 1.978566156715521e-05, "loss": 0.6413, "step": 2239 }, { "epoch": 0.31917925334853237, "grad_norm": 1.5509452373077852, "learning_rate": 1.97851491075793e-05, "loss": 0.6356, "step": 2240 }, { "epoch": 0.3193217440866344, "grad_norm": 2.347009364658814, "learning_rate": 1.9784636042769884e-05, "loss": 0.7698, "step": 2241 }, { "epoch": 0.3194642348247364, "grad_norm": 1.4525654626672946, "learning_rate": 1.9784122372758708e-05, "loss": 0.7017, "step": 2242 }, { "epoch": 0.3196067255628384, "grad_norm": 1.6389604654668914, "learning_rate": 1.978360809757754e-05, "loss": 0.7088, "step": 2243 }, { "epoch": 0.31974921630094044, "grad_norm": 1.6128060234769812, "learning_rate": 1.978309321725819e-05, "loss": 0.7538, "step": 2244 }, { "epoch": 0.31989170703904246, "grad_norm": 1.3783863983846703, "learning_rate": 1.9782577731832502e-05, "loss": 0.7446, "step": 2245 }, { "epoch": 0.3200341977771445, "grad_norm": 1.7646292346481607, "learning_rate": 1.9782061641332363e-05, "loss": 0.698, "step": 2246 }, { "epoch": 0.3201766885152465, "grad_norm": 1.5631021848960087, "learning_rate": 1.978154494578969e-05, "loss": 0.7286, "step": 2247 }, { "epoch": 0.3203191792533485, "grad_norm": 1.417990390023718, "learning_rate": 1.9781027645236444e-05, "loss": 0.6439, "step": 2248 }, { "epoch": 0.32046166999145054, "grad_norm": 1.5412907061354957, "learning_rate": 1.9780509739704623e-05, "loss": 0.7246, "step": 2249 }, { "epoch": 0.32060416072955256, "grad_norm": 1.6114834126972455, "learning_rate": 1.977999122922626e-05, "loss": 0.7354, "step": 2250 }, { "epoch": 0.3207466514676546, "grad_norm": 1.5082102028660191, "learning_rate": 1.9779472113833425e-05, "loss": 0.6417, "step": 2251 }, { "epoch": 0.32088914220575665, "grad_norm": 1.653640881766318, "learning_rate": 1.9778952393558226e-05, "loss": 0.7107, "step": 2252 }, { "epoch": 0.32103163294385867, "grad_norm": 1.4139789686579778, "learning_rate": 1.9778432068432813e-05, "loss": 0.655, "step": 2253 }, { "epoch": 0.3211741236819607, "grad_norm": 1.58923492095961, "learning_rate": 1.977791113848936e-05, "loss": 0.7354, "step": 2254 }, { "epoch": 0.3213166144200627, "grad_norm": 1.5474941204588062, "learning_rate": 1.97773896037601e-05, "loss": 0.7043, "step": 2255 }, { "epoch": 0.3214591051581647, "grad_norm": 1.588937403219152, "learning_rate": 1.977686746427728e-05, "loss": 0.7643, "step": 2256 }, { "epoch": 0.32160159589626675, "grad_norm": 3.117237703777907, "learning_rate": 1.97763447200732e-05, "loss": 0.7583, "step": 2257 }, { "epoch": 0.32174408663436876, "grad_norm": 1.49508496620301, "learning_rate": 1.9775821371180197e-05, "loss": 0.7521, "step": 2258 }, { "epoch": 0.3218865773724708, "grad_norm": 1.52963402342109, "learning_rate": 1.9775297417630637e-05, "loss": 0.7403, "step": 2259 }, { "epoch": 0.3220290681105728, "grad_norm": 1.4980067682647416, "learning_rate": 1.9774772859456924e-05, "loss": 0.7416, "step": 2260 }, { "epoch": 0.3221715588486748, "grad_norm": 1.9817899630414935, "learning_rate": 1.9774247696691514e-05, "loss": 0.8132, "step": 2261 }, { "epoch": 0.32231404958677684, "grad_norm": 1.4919514788130601, "learning_rate": 1.9773721929366878e-05, "loss": 0.7596, "step": 2262 }, { "epoch": 0.32245654032487886, "grad_norm": 1.8443699191764915, "learning_rate": 1.977319555751554e-05, "loss": 0.7664, "step": 2263 }, { "epoch": 0.3225990310629809, "grad_norm": 1.5778857760624523, "learning_rate": 1.977266858117006e-05, "loss": 0.7638, "step": 2264 }, { "epoch": 0.32274152180108295, "grad_norm": 1.5710139216984849, "learning_rate": 1.977214100036303e-05, "loss": 0.7942, "step": 2265 }, { "epoch": 0.322884012539185, "grad_norm": 1.4669786685044945, "learning_rate": 1.9771612815127085e-05, "loss": 0.6688, "step": 2266 }, { "epoch": 0.323026503277287, "grad_norm": 1.5328518732057708, "learning_rate": 1.977108402549489e-05, "loss": 0.6938, "step": 2267 }, { "epoch": 0.323168994015389, "grad_norm": 1.642336357644016, "learning_rate": 1.9770554631499153e-05, "loss": 0.7042, "step": 2268 }, { "epoch": 0.32331148475349103, "grad_norm": 1.430261249567122, "learning_rate": 1.977002463317262e-05, "loss": 0.7129, "step": 2269 }, { "epoch": 0.32345397549159305, "grad_norm": 1.60488918621839, "learning_rate": 1.9769494030548072e-05, "loss": 0.7175, "step": 2270 }, { "epoch": 0.32359646622969507, "grad_norm": 1.5831288150915286, "learning_rate": 1.9768962823658327e-05, "loss": 0.6612, "step": 2271 }, { "epoch": 0.3237389569677971, "grad_norm": 1.7011966922892001, "learning_rate": 1.9768431012536244e-05, "loss": 0.649, "step": 2272 }, { "epoch": 0.3238814477058991, "grad_norm": 2.30631507028136, "learning_rate": 1.9767898597214714e-05, "loss": 0.7472, "step": 2273 }, { "epoch": 0.3240239384440011, "grad_norm": 1.4100431234890285, "learning_rate": 1.9767365577726666e-05, "loss": 0.6624, "step": 2274 }, { "epoch": 0.32416642918210314, "grad_norm": 1.5950191213948661, "learning_rate": 1.9766831954105074e-05, "loss": 0.7077, "step": 2275 }, { "epoch": 0.32430891992020516, "grad_norm": 1.634791181289844, "learning_rate": 1.976629772638294e-05, "loss": 0.6105, "step": 2276 }, { "epoch": 0.32445141065830724, "grad_norm": 1.5354244220188864, "learning_rate": 1.976576289459331e-05, "loss": 0.7015, "step": 2277 }, { "epoch": 0.32459390139640926, "grad_norm": 1.5055738453606624, "learning_rate": 1.9765227458769262e-05, "loss": 0.6517, "step": 2278 }, { "epoch": 0.3247363921345113, "grad_norm": 1.5560285119725878, "learning_rate": 1.9764691418943915e-05, "loss": 0.6285, "step": 2279 }, { "epoch": 0.3248788828726133, "grad_norm": 1.4851877953752997, "learning_rate": 1.976415477515042e-05, "loss": 0.7176, "step": 2280 }, { "epoch": 0.3250213736107153, "grad_norm": 1.6282579721368204, "learning_rate": 1.976361752742198e-05, "loss": 0.7048, "step": 2281 }, { "epoch": 0.32516386434881733, "grad_norm": 1.3717813943520896, "learning_rate": 1.9763079675791816e-05, "loss": 0.7349, "step": 2282 }, { "epoch": 0.32530635508691935, "grad_norm": 1.6994617923260773, "learning_rate": 1.9762541220293196e-05, "loss": 0.7689, "step": 2283 }, { "epoch": 0.32544884582502137, "grad_norm": 1.6665157918828017, "learning_rate": 1.9762002160959432e-05, "loss": 0.7655, "step": 2284 }, { "epoch": 0.3255913365631234, "grad_norm": 1.644203614710537, "learning_rate": 1.9761462497823855e-05, "loss": 0.7147, "step": 2285 }, { "epoch": 0.3257338273012254, "grad_norm": 1.6444197852890388, "learning_rate": 1.9760922230919856e-05, "loss": 0.7034, "step": 2286 }, { "epoch": 0.32587631803932743, "grad_norm": 1.5151760922561945, "learning_rate": 1.976038136028084e-05, "loss": 0.7471, "step": 2287 }, { "epoch": 0.32601880877742945, "grad_norm": 1.4177727604625352, "learning_rate": 1.9759839885940267e-05, "loss": 0.7159, "step": 2288 }, { "epoch": 0.32616129951553147, "grad_norm": 1.5910475188395294, "learning_rate": 1.9759297807931634e-05, "loss": 0.7823, "step": 2289 }, { "epoch": 0.32630379025363354, "grad_norm": 1.485472044115423, "learning_rate": 1.975875512628846e-05, "loss": 0.8095, "step": 2290 }, { "epoch": 0.32644628099173556, "grad_norm": 1.5879547692333926, "learning_rate": 1.9758211841044316e-05, "loss": 0.7385, "step": 2291 }, { "epoch": 0.3265887717298376, "grad_norm": 1.6318807128556483, "learning_rate": 1.9757667952232805e-05, "loss": 0.7745, "step": 2292 }, { "epoch": 0.3267312624679396, "grad_norm": 2.126853797843133, "learning_rate": 1.9757123459887564e-05, "loss": 0.7486, "step": 2293 }, { "epoch": 0.3268737532060416, "grad_norm": 1.5810831935742171, "learning_rate": 1.975657836404228e-05, "loss": 0.6846, "step": 2294 }, { "epoch": 0.32701624394414364, "grad_norm": 1.6639170960926146, "learning_rate": 1.9756032664730657e-05, "loss": 0.7022, "step": 2295 }, { "epoch": 0.32715873468224566, "grad_norm": 1.7514940560056353, "learning_rate": 1.9755486361986455e-05, "loss": 0.6957, "step": 2296 }, { "epoch": 0.3273012254203477, "grad_norm": 1.5346970164729392, "learning_rate": 1.9754939455843465e-05, "loss": 0.6946, "step": 2297 }, { "epoch": 0.3274437161584497, "grad_norm": 1.507347711664199, "learning_rate": 1.975439194633551e-05, "loss": 0.7559, "step": 2298 }, { "epoch": 0.3275862068965517, "grad_norm": 1.5675528953284539, "learning_rate": 1.9753843833496458e-05, "loss": 0.6748, "step": 2299 }, { "epoch": 0.32772869763465373, "grad_norm": 1.5447688339685801, "learning_rate": 1.975329511736021e-05, "loss": 0.7168, "step": 2300 }, { "epoch": 0.32787118837275575, "grad_norm": 1.4926309636335486, "learning_rate": 1.97527457979607e-05, "loss": 0.6934, "step": 2301 }, { "epoch": 0.32801367911085777, "grad_norm": 1.6872280861025974, "learning_rate": 1.9752195875331915e-05, "loss": 0.7588, "step": 2302 }, { "epoch": 0.32815616984895984, "grad_norm": 1.4907055945593535, "learning_rate": 1.9751645349507863e-05, "loss": 0.7635, "step": 2303 }, { "epoch": 0.32829866058706186, "grad_norm": 1.4642370509463305, "learning_rate": 1.9751094220522593e-05, "loss": 0.8005, "step": 2304 }, { "epoch": 0.3284411513251639, "grad_norm": 1.4579807679640144, "learning_rate": 1.97505424884102e-05, "loss": 0.6054, "step": 2305 }, { "epoch": 0.3285836420632659, "grad_norm": 1.4577807608628794, "learning_rate": 1.9749990153204806e-05, "loss": 0.7248, "step": 2306 }, { "epoch": 0.3287261328013679, "grad_norm": 1.5277541446281193, "learning_rate": 1.9749437214940572e-05, "loss": 0.6467, "step": 2307 }, { "epoch": 0.32886862353946994, "grad_norm": 1.6206598140668482, "learning_rate": 1.97488836736517e-05, "loss": 0.7732, "step": 2308 }, { "epoch": 0.32901111427757196, "grad_norm": 1.5331367856383014, "learning_rate": 1.9748329529372432e-05, "loss": 0.762, "step": 2309 }, { "epoch": 0.329153605015674, "grad_norm": 1.3833225652154697, "learning_rate": 1.974777478213704e-05, "loss": 0.6797, "step": 2310 }, { "epoch": 0.329296095753776, "grad_norm": 1.5978129094462068, "learning_rate": 1.9747219431979832e-05, "loss": 0.7803, "step": 2311 }, { "epoch": 0.329438586491878, "grad_norm": 1.5876809167402899, "learning_rate": 1.9746663478935163e-05, "loss": 0.8236, "step": 2312 }, { "epoch": 0.32958107722998004, "grad_norm": 1.4358267499445188, "learning_rate": 1.9746106923037424e-05, "loss": 0.7764, "step": 2313 }, { "epoch": 0.32972356796808205, "grad_norm": 1.588110254925409, "learning_rate": 1.9745549764321027e-05, "loss": 0.7469, "step": 2314 }, { "epoch": 0.3298660587061841, "grad_norm": 1.5913959921060334, "learning_rate": 1.9744992002820443e-05, "loss": 0.6673, "step": 2315 }, { "epoch": 0.33000854944428615, "grad_norm": 2.05089002359395, "learning_rate": 1.9744433638570167e-05, "loss": 0.5949, "step": 2316 }, { "epoch": 0.33015104018238817, "grad_norm": 1.6635630279603344, "learning_rate": 1.974387467160474e-05, "loss": 0.7869, "step": 2317 }, { "epoch": 0.3302935309204902, "grad_norm": 1.6730500186221577, "learning_rate": 1.974331510195873e-05, "loss": 0.6572, "step": 2318 }, { "epoch": 0.3304360216585922, "grad_norm": 1.5220234585050052, "learning_rate": 1.974275492966675e-05, "loss": 0.7035, "step": 2319 }, { "epoch": 0.3305785123966942, "grad_norm": 1.4817524726012556, "learning_rate": 1.9742194154763445e-05, "loss": 0.7208, "step": 2320 }, { "epoch": 0.33072100313479624, "grad_norm": 1.5425601591050844, "learning_rate": 1.9741632777283503e-05, "loss": 0.7189, "step": 2321 }, { "epoch": 0.33086349387289826, "grad_norm": 1.5355697237952257, "learning_rate": 1.9741070797261648e-05, "loss": 0.7066, "step": 2322 }, { "epoch": 0.3310059846110003, "grad_norm": 1.8764695233739797, "learning_rate": 1.9740508214732637e-05, "loss": 0.6775, "step": 2323 }, { "epoch": 0.3311484753491023, "grad_norm": 1.4598051795186304, "learning_rate": 1.9739945029731267e-05, "loss": 0.7295, "step": 2324 }, { "epoch": 0.3312909660872043, "grad_norm": 1.4831211861094773, "learning_rate": 1.9739381242292373e-05, "loss": 0.729, "step": 2325 }, { "epoch": 0.33143345682530634, "grad_norm": 1.41471319307237, "learning_rate": 1.9738816852450826e-05, "loss": 0.6191, "step": 2326 }, { "epoch": 0.33157594756340836, "grad_norm": 1.4711072304247026, "learning_rate": 1.9738251860241538e-05, "loss": 0.6442, "step": 2327 }, { "epoch": 0.3317184383015104, "grad_norm": 1.6275267434298206, "learning_rate": 1.9737686265699447e-05, "loss": 0.6929, "step": 2328 }, { "epoch": 0.33186092903961245, "grad_norm": 1.5804669003539153, "learning_rate": 1.9737120068859546e-05, "loss": 0.7405, "step": 2329 }, { "epoch": 0.33200341977771447, "grad_norm": 1.5864224245104437, "learning_rate": 1.9736553269756847e-05, "loss": 0.727, "step": 2330 }, { "epoch": 0.3321459105158165, "grad_norm": 1.7026433461824224, "learning_rate": 1.973598586842642e-05, "loss": 0.7741, "step": 2331 }, { "epoch": 0.3322884012539185, "grad_norm": 1.7754763669406832, "learning_rate": 1.9735417864903344e-05, "loss": 0.7109, "step": 2332 }, { "epoch": 0.3324308919920205, "grad_norm": 1.8195802013380544, "learning_rate": 1.973484925922276e-05, "loss": 0.7098, "step": 2333 }, { "epoch": 0.33257338273012255, "grad_norm": 1.805814167902464, "learning_rate": 1.973428005141984e-05, "loss": 0.7162, "step": 2334 }, { "epoch": 0.33271587346822457, "grad_norm": 1.516171518849315, "learning_rate": 1.9733710241529786e-05, "loss": 0.8112, "step": 2335 }, { "epoch": 0.3328583642063266, "grad_norm": 1.4371420524667307, "learning_rate": 1.9733139829587845e-05, "loss": 0.6405, "step": 2336 }, { "epoch": 0.3330008549444286, "grad_norm": 1.5493181476457656, "learning_rate": 1.9732568815629296e-05, "loss": 0.7162, "step": 2337 }, { "epoch": 0.3331433456825306, "grad_norm": 1.5049812735720476, "learning_rate": 1.9731997199689456e-05, "loss": 0.7084, "step": 2338 }, { "epoch": 0.33328583642063264, "grad_norm": 1.6473837158658273, "learning_rate": 1.973142498180369e-05, "loss": 0.6728, "step": 2339 }, { "epoch": 0.33342832715873466, "grad_norm": 1.6288001236058174, "learning_rate": 1.9730852162007377e-05, "loss": 0.7125, "step": 2340 }, { "epoch": 0.3335708178968367, "grad_norm": 1.5579813634770312, "learning_rate": 1.9730278740335954e-05, "loss": 0.7728, "step": 2341 }, { "epoch": 0.33371330863493875, "grad_norm": 1.3985192197188523, "learning_rate": 1.9729704716824894e-05, "loss": 0.694, "step": 2342 }, { "epoch": 0.3338557993730408, "grad_norm": 1.531502625794464, "learning_rate": 1.972913009150969e-05, "loss": 0.69, "step": 2343 }, { "epoch": 0.3339982901111428, "grad_norm": 1.3359824182333773, "learning_rate": 1.97285548644259e-05, "loss": 0.6547, "step": 2344 }, { "epoch": 0.3341407808492448, "grad_norm": 2.5369160115838993, "learning_rate": 1.9727979035609083e-05, "loss": 0.6998, "step": 2345 }, { "epoch": 0.33428327158734683, "grad_norm": 1.6793972831595896, "learning_rate": 1.972740260509487e-05, "loss": 0.7299, "step": 2346 }, { "epoch": 0.33442576232544885, "grad_norm": 1.6529681210534144, "learning_rate": 1.972682557291891e-05, "loss": 0.7866, "step": 2347 }, { "epoch": 0.33456825306355087, "grad_norm": 1.5604305436260628, "learning_rate": 1.9726247939116897e-05, "loss": 0.7116, "step": 2348 }, { "epoch": 0.3347107438016529, "grad_norm": 1.4679209920117546, "learning_rate": 1.972566970372455e-05, "loss": 0.651, "step": 2349 }, { "epoch": 0.3348532345397549, "grad_norm": 1.526375322409733, "learning_rate": 1.9725090866777642e-05, "loss": 0.6436, "step": 2350 }, { "epoch": 0.3349957252778569, "grad_norm": 1.7444557862499646, "learning_rate": 1.9724511428311975e-05, "loss": 0.7675, "step": 2351 }, { "epoch": 0.33513821601595895, "grad_norm": 1.4216614737681925, "learning_rate": 1.9723931388363387e-05, "loss": 0.7008, "step": 2352 }, { "epoch": 0.33528070675406096, "grad_norm": 2.429812861725152, "learning_rate": 1.9723350746967753e-05, "loss": 0.6602, "step": 2353 }, { "epoch": 0.335423197492163, "grad_norm": 1.4819556186151632, "learning_rate": 1.972276950416099e-05, "loss": 0.6413, "step": 2354 }, { "epoch": 0.33556568823026506, "grad_norm": 8.414541608462324, "learning_rate": 1.9722187659979046e-05, "loss": 0.7762, "step": 2355 }, { "epoch": 0.3357081789683671, "grad_norm": 1.9959833172962056, "learning_rate": 1.9721605214457912e-05, "loss": 0.7045, "step": 2356 }, { "epoch": 0.3358506697064691, "grad_norm": 1.4913915426684432, "learning_rate": 1.9721022167633614e-05, "loss": 0.6998, "step": 2357 }, { "epoch": 0.3359931604445711, "grad_norm": 1.5418342946475772, "learning_rate": 1.9720438519542213e-05, "loss": 0.681, "step": 2358 }, { "epoch": 0.33613565118267313, "grad_norm": 1.4113955479770697, "learning_rate": 1.971985427021981e-05, "loss": 0.5784, "step": 2359 }, { "epoch": 0.33627814192077515, "grad_norm": 1.6194122915625144, "learning_rate": 1.971926941970254e-05, "loss": 0.8202, "step": 2360 }, { "epoch": 0.3364206326588772, "grad_norm": 1.8163648474089302, "learning_rate": 1.9718683968026577e-05, "loss": 0.8324, "step": 2361 }, { "epoch": 0.3365631233969792, "grad_norm": 1.3643332171273737, "learning_rate": 1.971809791522814e-05, "loss": 0.7369, "step": 2362 }, { "epoch": 0.3367056141350812, "grad_norm": 2.6896155471615324, "learning_rate": 1.971751126134347e-05, "loss": 0.6924, "step": 2363 }, { "epoch": 0.33684810487318323, "grad_norm": 1.5003078021073493, "learning_rate": 1.9716924006408854e-05, "loss": 0.7119, "step": 2364 }, { "epoch": 0.33699059561128525, "grad_norm": 1.5077429158760436, "learning_rate": 1.9716336150460615e-05, "loss": 0.7127, "step": 2365 }, { "epoch": 0.33713308634938727, "grad_norm": 1.4872590971588842, "learning_rate": 1.9715747693535117e-05, "loss": 0.6963, "step": 2366 }, { "epoch": 0.3372755770874893, "grad_norm": 1.4108861665533976, "learning_rate": 1.9715158635668753e-05, "loss": 0.6536, "step": 2367 }, { "epoch": 0.33741806782559136, "grad_norm": 1.632889777118395, "learning_rate": 1.971456897689796e-05, "loss": 0.7418, "step": 2368 }, { "epoch": 0.3375605585636934, "grad_norm": 1.5539860884737633, "learning_rate": 1.9713978717259207e-05, "loss": 0.7143, "step": 2369 }, { "epoch": 0.3377030493017954, "grad_norm": 1.7537678447860983, "learning_rate": 1.9713387856789006e-05, "loss": 0.7285, "step": 2370 }, { "epoch": 0.3378455400398974, "grad_norm": 1.5076911253445624, "learning_rate": 1.9712796395523903e-05, "loss": 0.7382, "step": 2371 }, { "epoch": 0.33798803077799944, "grad_norm": 1.4899863007624485, "learning_rate": 1.9712204333500478e-05, "loss": 0.7287, "step": 2372 }, { "epoch": 0.33813052151610146, "grad_norm": 1.5219777411621376, "learning_rate": 1.9711611670755355e-05, "loss": 0.7206, "step": 2373 }, { "epoch": 0.3382730122542035, "grad_norm": 1.482611937086099, "learning_rate": 1.971101840732519e-05, "loss": 0.659, "step": 2374 }, { "epoch": 0.3384155029923055, "grad_norm": 1.5487365045863668, "learning_rate": 1.9710424543246677e-05, "loss": 0.7879, "step": 2375 }, { "epoch": 0.3385579937304075, "grad_norm": 1.4923545450278808, "learning_rate": 1.970983007855655e-05, "loss": 0.6001, "step": 2376 }, { "epoch": 0.33870048446850953, "grad_norm": 1.6658080560071742, "learning_rate": 1.9709235013291573e-05, "loss": 0.7592, "step": 2377 }, { "epoch": 0.33884297520661155, "grad_norm": 1.5420745365591473, "learning_rate": 1.9708639347488558e-05, "loss": 0.6746, "step": 2378 }, { "epoch": 0.33898546594471357, "grad_norm": 1.5602475317087618, "learning_rate": 1.9708043081184346e-05, "loss": 0.7974, "step": 2379 }, { "epoch": 0.3391279566828156, "grad_norm": 1.508886317636785, "learning_rate": 1.9707446214415816e-05, "loss": 0.7174, "step": 2380 }, { "epoch": 0.33927044742091766, "grad_norm": 1.5617610453899209, "learning_rate": 1.9706848747219886e-05, "loss": 0.6413, "step": 2381 }, { "epoch": 0.3394129381590197, "grad_norm": 2.0549766628751183, "learning_rate": 1.9706250679633515e-05, "loss": 0.7749, "step": 2382 }, { "epoch": 0.3395554288971217, "grad_norm": 1.413828893291401, "learning_rate": 1.970565201169369e-05, "loss": 0.7707, "step": 2383 }, { "epoch": 0.3396979196352237, "grad_norm": 1.5001543343317056, "learning_rate": 1.970505274343744e-05, "loss": 0.7038, "step": 2384 }, { "epoch": 0.33984041037332574, "grad_norm": 1.4664353235289442, "learning_rate": 1.970445287490183e-05, "loss": 0.6545, "step": 2385 }, { "epoch": 0.33998290111142776, "grad_norm": 1.6390872666127922, "learning_rate": 1.970385240612397e-05, "loss": 0.7075, "step": 2386 }, { "epoch": 0.3401253918495298, "grad_norm": 1.4557500646248671, "learning_rate": 1.9703251337140998e-05, "loss": 0.7638, "step": 2387 }, { "epoch": 0.3402678825876318, "grad_norm": 1.967407974516004, "learning_rate": 1.9702649667990085e-05, "loss": 0.7495, "step": 2388 }, { "epoch": 0.3404103733257338, "grad_norm": 1.6946718305001114, "learning_rate": 1.970204739870845e-05, "loss": 0.6767, "step": 2389 }, { "epoch": 0.34055286406383584, "grad_norm": 1.602893623919932, "learning_rate": 1.9701444529333346e-05, "loss": 0.7412, "step": 2390 }, { "epoch": 0.34069535480193786, "grad_norm": 1.5262960407725232, "learning_rate": 1.970084105990206e-05, "loss": 0.6476, "step": 2391 }, { "epoch": 0.3408378455400399, "grad_norm": 1.674425565234027, "learning_rate": 1.970023699045192e-05, "loss": 0.7332, "step": 2392 }, { "epoch": 0.3409803362781419, "grad_norm": 1.6046435489760793, "learning_rate": 1.9699632321020284e-05, "loss": 0.6752, "step": 2393 }, { "epoch": 0.34112282701624397, "grad_norm": 1.9073602873842312, "learning_rate": 1.969902705164456e-05, "loss": 0.6966, "step": 2394 }, { "epoch": 0.341265317754346, "grad_norm": 1.7124755993268013, "learning_rate": 1.9698421182362177e-05, "loss": 0.6721, "step": 2395 }, { "epoch": 0.341407808492448, "grad_norm": 1.5769569763093465, "learning_rate": 1.9697814713210616e-05, "loss": 0.6851, "step": 2396 }, { "epoch": 0.34155029923055, "grad_norm": 1.4769712098854766, "learning_rate": 1.969720764422739e-05, "loss": 0.7681, "step": 2397 }, { "epoch": 0.34169278996865204, "grad_norm": 1.6107130712507756, "learning_rate": 1.9696599975450035e-05, "loss": 0.7418, "step": 2398 }, { "epoch": 0.34183528070675406, "grad_norm": 1.5615075754816796, "learning_rate": 1.969599170691615e-05, "loss": 0.6689, "step": 2399 }, { "epoch": 0.3419777714448561, "grad_norm": 1.588081815217033, "learning_rate": 1.969538283866335e-05, "loss": 0.8032, "step": 2400 }, { "epoch": 0.3421202621829581, "grad_norm": 1.7274185102315989, "learning_rate": 1.9694773370729302e-05, "loss": 0.6956, "step": 2401 }, { "epoch": 0.3422627529210601, "grad_norm": 1.5506079856679214, "learning_rate": 1.9694163303151693e-05, "loss": 0.7781, "step": 2402 }, { "epoch": 0.34240524365916214, "grad_norm": 2.0148632956496253, "learning_rate": 1.9693552635968267e-05, "loss": 0.7652, "step": 2403 }, { "epoch": 0.34254773439726416, "grad_norm": 1.4490076328750539, "learning_rate": 1.969294136921679e-05, "loss": 0.6799, "step": 2404 }, { "epoch": 0.3426902251353662, "grad_norm": 1.647153473587433, "learning_rate": 1.969232950293507e-05, "loss": 0.7448, "step": 2405 }, { "epoch": 0.34283271587346825, "grad_norm": 1.4057021893982589, "learning_rate": 1.9691717037160955e-05, "loss": 0.7181, "step": 2406 }, { "epoch": 0.34297520661157027, "grad_norm": 1.5904280515359195, "learning_rate": 1.9691103971932326e-05, "loss": 0.6787, "step": 2407 }, { "epoch": 0.3431176973496723, "grad_norm": 1.545256630260339, "learning_rate": 1.96904903072871e-05, "loss": 0.6636, "step": 2408 }, { "epoch": 0.3432601880877743, "grad_norm": 2.07986236848322, "learning_rate": 1.9689876043263238e-05, "loss": 0.7306, "step": 2409 }, { "epoch": 0.34340267882587633, "grad_norm": 1.4651725758907397, "learning_rate": 1.968926117989873e-05, "loss": 0.6429, "step": 2410 }, { "epoch": 0.34354516956397835, "grad_norm": 1.5766400353437815, "learning_rate": 1.968864571723161e-05, "loss": 0.6631, "step": 2411 }, { "epoch": 0.34368766030208037, "grad_norm": 1.4973705744912063, "learning_rate": 1.9688029655299943e-05, "loss": 0.6704, "step": 2412 }, { "epoch": 0.3438301510401824, "grad_norm": 1.4776936171454769, "learning_rate": 1.9687412994141835e-05, "loss": 0.6241, "step": 2413 }, { "epoch": 0.3439726417782844, "grad_norm": 1.9087258029895886, "learning_rate": 1.9686795733795426e-05, "loss": 0.6094, "step": 2414 }, { "epoch": 0.3441151325163864, "grad_norm": 1.4740254394796728, "learning_rate": 1.96861778742989e-05, "loss": 0.6895, "step": 2415 }, { "epoch": 0.34425762325448844, "grad_norm": 1.5438502671438072, "learning_rate": 1.9685559415690466e-05, "loss": 0.7874, "step": 2416 }, { "epoch": 0.34440011399259046, "grad_norm": 1.6040911977559797, "learning_rate": 1.9684940358008383e-05, "loss": 0.6407, "step": 2417 }, { "epoch": 0.3445426047306925, "grad_norm": 1.4093579000838814, "learning_rate": 1.9684320701290936e-05, "loss": 0.6635, "step": 2418 }, { "epoch": 0.34468509546879456, "grad_norm": 1.7112261768584356, "learning_rate": 1.9683700445576453e-05, "loss": 0.6946, "step": 2419 }, { "epoch": 0.3448275862068966, "grad_norm": 1.5089227666601632, "learning_rate": 1.9683079590903307e-05, "loss": 0.6863, "step": 2420 }, { "epoch": 0.3449700769449986, "grad_norm": 1.451636412684355, "learning_rate": 1.9682458137309887e-05, "loss": 0.7097, "step": 2421 }, { "epoch": 0.3451125676831006, "grad_norm": 1.5774749339842868, "learning_rate": 1.968183608483464e-05, "loss": 0.647, "step": 2422 }, { "epoch": 0.34525505842120263, "grad_norm": 1.6513399118192038, "learning_rate": 1.9681213433516036e-05, "loss": 0.7685, "step": 2423 }, { "epoch": 0.34539754915930465, "grad_norm": 1.4417498000363382, "learning_rate": 1.968059018339259e-05, "loss": 0.6855, "step": 2424 }, { "epoch": 0.34554003989740667, "grad_norm": 1.8360288636295807, "learning_rate": 1.967996633450285e-05, "loss": 0.8039, "step": 2425 }, { "epoch": 0.3456825306355087, "grad_norm": 1.7680414870401167, "learning_rate": 1.9679341886885402e-05, "loss": 0.6716, "step": 2426 }, { "epoch": 0.3458250213736107, "grad_norm": 1.4443402664478853, "learning_rate": 1.9678716840578877e-05, "loss": 0.6422, "step": 2427 }, { "epoch": 0.3459675121117127, "grad_norm": 1.5657701446438261, "learning_rate": 1.9678091195621923e-05, "loss": 0.7136, "step": 2428 }, { "epoch": 0.34611000284981475, "grad_norm": 1.4774646180544764, "learning_rate": 1.9677464952053246e-05, "loss": 0.6997, "step": 2429 }, { "epoch": 0.34625249358791677, "grad_norm": 1.438938933706258, "learning_rate": 1.9676838109911576e-05, "loss": 0.7035, "step": 2430 }, { "epoch": 0.3463949843260188, "grad_norm": 1.511905394825986, "learning_rate": 1.967621066923569e-05, "loss": 0.6516, "step": 2431 }, { "epoch": 0.34653747506412086, "grad_norm": 1.6583883207197383, "learning_rate": 1.967558263006439e-05, "loss": 0.712, "step": 2432 }, { "epoch": 0.3466799658022229, "grad_norm": 1.3555947982883207, "learning_rate": 1.967495399243653e-05, "loss": 0.6605, "step": 2433 }, { "epoch": 0.3468224565403249, "grad_norm": 1.4398940025619658, "learning_rate": 1.9674324756390984e-05, "loss": 0.6348, "step": 2434 }, { "epoch": 0.3469649472784269, "grad_norm": 1.448440540332313, "learning_rate": 1.9673694921966677e-05, "loss": 0.7435, "step": 2435 }, { "epoch": 0.34710743801652894, "grad_norm": 1.5754633240169842, "learning_rate": 1.9673064489202565e-05, "loss": 0.6998, "step": 2436 }, { "epoch": 0.34724992875463095, "grad_norm": 1.5830437944863291, "learning_rate": 1.967243345813764e-05, "loss": 0.6955, "step": 2437 }, { "epoch": 0.347392419492733, "grad_norm": 1.4364539671414072, "learning_rate": 1.9671801828810934e-05, "loss": 0.666, "step": 2438 }, { "epoch": 0.347534910230835, "grad_norm": 1.4518118747706514, "learning_rate": 1.9671169601261514e-05, "loss": 0.749, "step": 2439 }, { "epoch": 0.347677400968937, "grad_norm": 1.3668038315856867, "learning_rate": 1.9670536775528485e-05, "loss": 0.7571, "step": 2440 }, { "epoch": 0.34781989170703903, "grad_norm": 1.3685293348406187, "learning_rate": 1.9669903351650987e-05, "loss": 0.6868, "step": 2441 }, { "epoch": 0.34796238244514105, "grad_norm": 1.4106627694521783, "learning_rate": 1.9669269329668205e-05, "loss": 0.7117, "step": 2442 }, { "epoch": 0.34810487318324307, "grad_norm": 5.773614360168657, "learning_rate": 1.9668634709619344e-05, "loss": 0.8837, "step": 2443 }, { "epoch": 0.3482473639213451, "grad_norm": 1.5335903272834195, "learning_rate": 1.9667999491543668e-05, "loss": 0.7242, "step": 2444 }, { "epoch": 0.34838985465944716, "grad_norm": 1.564818009561052, "learning_rate": 1.966736367548046e-05, "loss": 0.6889, "step": 2445 }, { "epoch": 0.3485323453975492, "grad_norm": 1.407642369549205, "learning_rate": 1.9666727261469045e-05, "loss": 0.6599, "step": 2446 }, { "epoch": 0.3486748361356512, "grad_norm": 1.570801726775953, "learning_rate": 1.9666090249548792e-05, "loss": 0.7361, "step": 2447 }, { "epoch": 0.3488173268737532, "grad_norm": 1.4441576171801833, "learning_rate": 1.96654526397591e-05, "loss": 0.7121, "step": 2448 }, { "epoch": 0.34895981761185524, "grad_norm": 1.4926908469769582, "learning_rate": 1.9664814432139408e-05, "loss": 0.713, "step": 2449 }, { "epoch": 0.34910230834995726, "grad_norm": 1.8016867510731027, "learning_rate": 1.9664175626729184e-05, "loss": 0.7445, "step": 2450 }, { "epoch": 0.3492447990880593, "grad_norm": 1.7296297702775703, "learning_rate": 1.9663536223567944e-05, "loss": 0.8093, "step": 2451 }, { "epoch": 0.3493872898261613, "grad_norm": 1.4070628714481916, "learning_rate": 1.966289622269524e-05, "loss": 0.6671, "step": 2452 }, { "epoch": 0.3495297805642633, "grad_norm": 1.6842909984201102, "learning_rate": 1.9662255624150654e-05, "loss": 0.679, "step": 2453 }, { "epoch": 0.34967227130236533, "grad_norm": 1.3529891592014682, "learning_rate": 1.9661614427973808e-05, "loss": 0.6616, "step": 2454 }, { "epoch": 0.34981476204046735, "grad_norm": 1.5029697706931497, "learning_rate": 1.966097263420436e-05, "loss": 0.774, "step": 2455 }, { "epoch": 0.34995725277856937, "grad_norm": 1.5070954775063505, "learning_rate": 1.966033024288201e-05, "loss": 0.6917, "step": 2456 }, { "epoch": 0.3500997435166714, "grad_norm": 1.5486655418905586, "learning_rate": 1.9659687254046487e-05, "loss": 0.7022, "step": 2457 }, { "epoch": 0.35024223425477347, "grad_norm": 1.4858799442346133, "learning_rate": 1.9659043667737567e-05, "loss": 0.6667, "step": 2458 }, { "epoch": 0.3503847249928755, "grad_norm": 1.518045249891935, "learning_rate": 1.9658399483995055e-05, "loss": 0.7345, "step": 2459 }, { "epoch": 0.3505272157309775, "grad_norm": 1.5136857841320726, "learning_rate": 1.9657754702858793e-05, "loss": 0.7859, "step": 2460 }, { "epoch": 0.3506697064690795, "grad_norm": 1.4093068372255075, "learning_rate": 1.965710932436866e-05, "loss": 0.7683, "step": 2461 }, { "epoch": 0.35081219720718154, "grad_norm": 1.3609570715490478, "learning_rate": 1.9656463348564584e-05, "loss": 0.6657, "step": 2462 }, { "epoch": 0.35095468794528356, "grad_norm": 1.694573926824382, "learning_rate": 1.965581677548651e-05, "loss": 0.7581, "step": 2463 }, { "epoch": 0.3510971786833856, "grad_norm": 1.5621168099235045, "learning_rate": 1.9655169605174435e-05, "loss": 0.6659, "step": 2464 }, { "epoch": 0.3512396694214876, "grad_norm": 1.5306814526551158, "learning_rate": 1.965452183766839e-05, "loss": 0.7045, "step": 2465 }, { "epoch": 0.3513821601595896, "grad_norm": 1.4395019062449004, "learning_rate": 1.965387347300843e-05, "loss": 0.6733, "step": 2466 }, { "epoch": 0.35152465089769164, "grad_norm": 1.5104399648250106, "learning_rate": 1.9653224511234673e-05, "loss": 0.6715, "step": 2467 }, { "epoch": 0.35166714163579366, "grad_norm": 1.6318830529228823, "learning_rate": 1.9652574952387245e-05, "loss": 0.7298, "step": 2468 }, { "epoch": 0.3518096323738957, "grad_norm": 1.3642703679591854, "learning_rate": 1.9651924796506334e-05, "loss": 0.6649, "step": 2469 }, { "epoch": 0.3519521231119977, "grad_norm": 1.6029794247490037, "learning_rate": 1.9651274043632146e-05, "loss": 0.7149, "step": 2470 }, { "epoch": 0.35209461385009977, "grad_norm": 1.5763614381093054, "learning_rate": 1.9650622693804936e-05, "loss": 0.7509, "step": 2471 }, { "epoch": 0.3522371045882018, "grad_norm": 1.8391758014926027, "learning_rate": 1.964997074706499e-05, "loss": 0.6713, "step": 2472 }, { "epoch": 0.3523795953263038, "grad_norm": 1.5271885183243497, "learning_rate": 1.964931820345263e-05, "loss": 0.7474, "step": 2473 }, { "epoch": 0.3525220860644058, "grad_norm": 1.7867819581162128, "learning_rate": 1.9648665063008218e-05, "loss": 0.6566, "step": 2474 }, { "epoch": 0.35266457680250785, "grad_norm": 1.5966964818950486, "learning_rate": 1.964801132577215e-05, "loss": 0.7106, "step": 2475 }, { "epoch": 0.35280706754060986, "grad_norm": 1.5525507883931369, "learning_rate": 1.964735699178487e-05, "loss": 0.7584, "step": 2476 }, { "epoch": 0.3529495582787119, "grad_norm": 1.4801618464411215, "learning_rate": 1.9646702061086845e-05, "loss": 0.6859, "step": 2477 }, { "epoch": 0.3530920490168139, "grad_norm": 1.5835523367197972, "learning_rate": 1.964604653371858e-05, "loss": 0.7144, "step": 2478 }, { "epoch": 0.3532345397549159, "grad_norm": 1.5102164262632847, "learning_rate": 1.9645390409720627e-05, "loss": 0.6874, "step": 2479 }, { "epoch": 0.35337703049301794, "grad_norm": 1.813114034262885, "learning_rate": 1.9644733689133563e-05, "loss": 0.675, "step": 2480 }, { "epoch": 0.35351952123111996, "grad_norm": 1.4626810675100501, "learning_rate": 1.9644076371998017e-05, "loss": 0.6852, "step": 2481 }, { "epoch": 0.353662011969222, "grad_norm": 1.4291125253279118, "learning_rate": 1.9643418458354632e-05, "loss": 0.6865, "step": 2482 }, { "epoch": 0.353804502707324, "grad_norm": 1.5708119233392612, "learning_rate": 1.9642759948244113e-05, "loss": 0.6473, "step": 2483 }, { "epoch": 0.3539469934454261, "grad_norm": 1.4909390315413813, "learning_rate": 1.9642100841707183e-05, "loss": 0.7189, "step": 2484 }, { "epoch": 0.3540894841835281, "grad_norm": 1.5750943049298844, "learning_rate": 1.9641441138784617e-05, "loss": 0.7093, "step": 2485 }, { "epoch": 0.3542319749216301, "grad_norm": 1.5612057798436216, "learning_rate": 1.964078083951721e-05, "loss": 0.7101, "step": 2486 }, { "epoch": 0.35437446565973213, "grad_norm": 1.6371044918293256, "learning_rate": 1.964011994394581e-05, "loss": 0.6957, "step": 2487 }, { "epoch": 0.35451695639783415, "grad_norm": 1.6416094711181646, "learning_rate": 1.9639458452111285e-05, "loss": 0.7313, "step": 2488 }, { "epoch": 0.35465944713593617, "grad_norm": 1.8710437333785344, "learning_rate": 1.9638796364054566e-05, "loss": 0.8058, "step": 2489 }, { "epoch": 0.3548019378740382, "grad_norm": 1.6927323279732798, "learning_rate": 1.963813367981659e-05, "loss": 0.6972, "step": 2490 }, { "epoch": 0.3549444286121402, "grad_norm": 1.7922916645893185, "learning_rate": 1.9637470399438353e-05, "loss": 0.7856, "step": 2491 }, { "epoch": 0.3550869193502422, "grad_norm": 1.419202305435863, "learning_rate": 1.963680652296088e-05, "loss": 0.7039, "step": 2492 }, { "epoch": 0.35522941008834424, "grad_norm": 1.586784235994445, "learning_rate": 1.9636142050425228e-05, "loss": 0.7255, "step": 2493 }, { "epoch": 0.35537190082644626, "grad_norm": 1.6487144970042982, "learning_rate": 1.9635476981872505e-05, "loss": 0.7351, "step": 2494 }, { "epoch": 0.3555143915645483, "grad_norm": 1.6266074740312593, "learning_rate": 1.963481131734384e-05, "loss": 0.7181, "step": 2495 }, { "epoch": 0.3556568823026503, "grad_norm": 1.764555042891001, "learning_rate": 1.9634145056880406e-05, "loss": 0.7022, "step": 2496 }, { "epoch": 0.3557993730407524, "grad_norm": 1.5365856686764927, "learning_rate": 1.9633478200523416e-05, "loss": 0.7284, "step": 2497 }, { "epoch": 0.3559418637788544, "grad_norm": 1.4812949485264344, "learning_rate": 1.9632810748314114e-05, "loss": 0.6756, "step": 2498 }, { "epoch": 0.3560843545169564, "grad_norm": 1.4975660299073534, "learning_rate": 1.9632142700293782e-05, "loss": 0.6671, "step": 2499 }, { "epoch": 0.35622684525505843, "grad_norm": 1.4018383941219934, "learning_rate": 1.9631474056503744e-05, "loss": 0.6451, "step": 2500 }, { "epoch": 0.35636933599316045, "grad_norm": 1.5524225206104107, "learning_rate": 1.9630804816985358e-05, "loss": 0.6153, "step": 2501 }, { "epoch": 0.35651182673126247, "grad_norm": 1.5461596597225125, "learning_rate": 1.9630134981780012e-05, "loss": 0.787, "step": 2502 }, { "epoch": 0.3566543174693645, "grad_norm": 1.4411133770666908, "learning_rate": 1.9629464550929145e-05, "loss": 0.5969, "step": 2503 }, { "epoch": 0.3567968082074665, "grad_norm": 1.6300786781713639, "learning_rate": 1.962879352447422e-05, "loss": 0.7034, "step": 2504 }, { "epoch": 0.35693929894556853, "grad_norm": 1.505381084673352, "learning_rate": 1.962812190245674e-05, "loss": 0.6397, "step": 2505 }, { "epoch": 0.35708178968367055, "grad_norm": 1.724464006415269, "learning_rate": 1.962744968491825e-05, "loss": 0.7869, "step": 2506 }, { "epoch": 0.35722428042177257, "grad_norm": 1.3264950499624302, "learning_rate": 1.9626776871900324e-05, "loss": 0.7169, "step": 2507 }, { "epoch": 0.3573667711598746, "grad_norm": 1.5781026136578955, "learning_rate": 1.962610346344458e-05, "loss": 0.7031, "step": 2508 }, { "epoch": 0.3575092618979766, "grad_norm": 1.588612664208357, "learning_rate": 1.9625429459592667e-05, "loss": 0.6704, "step": 2509 }, { "epoch": 0.3576517526360787, "grad_norm": 1.4409369783365917, "learning_rate": 1.9624754860386276e-05, "loss": 0.8299, "step": 2510 }, { "epoch": 0.3577942433741807, "grad_norm": 1.5475028591952789, "learning_rate": 1.9624079665867135e-05, "loss": 0.7266, "step": 2511 }, { "epoch": 0.3579367341122827, "grad_norm": 2.9547171171715525, "learning_rate": 1.9623403876077003e-05, "loss": 0.705, "step": 2512 }, { "epoch": 0.35807922485038474, "grad_norm": 1.3125623106065734, "learning_rate": 1.962272749105768e-05, "loss": 0.7038, "step": 2513 }, { "epoch": 0.35822171558848676, "grad_norm": 1.4596953655041782, "learning_rate": 1.9622050510850998e-05, "loss": 0.6953, "step": 2514 }, { "epoch": 0.3583642063265888, "grad_norm": 1.6014518671365403, "learning_rate": 1.962137293549884e-05, "loss": 0.6796, "step": 2515 }, { "epoch": 0.3585066970646908, "grad_norm": 1.646292122666491, "learning_rate": 1.96206947650431e-05, "loss": 0.7384, "step": 2516 }, { "epoch": 0.3586491878027928, "grad_norm": 1.415199504725961, "learning_rate": 1.962001599952574e-05, "loss": 0.8098, "step": 2517 }, { "epoch": 0.35879167854089483, "grad_norm": 1.478748086257963, "learning_rate": 1.9619336638988732e-05, "loss": 0.7326, "step": 2518 }, { "epoch": 0.35893416927899685, "grad_norm": 1.4384561080762839, "learning_rate": 1.9618656683474106e-05, "loss": 0.7324, "step": 2519 }, { "epoch": 0.35907666001709887, "grad_norm": 1.5066998377713254, "learning_rate": 1.9617976133023907e-05, "loss": 0.7629, "step": 2520 }, { "epoch": 0.3592191507552009, "grad_norm": 1.4252072456665836, "learning_rate": 1.9617294987680237e-05, "loss": 0.6483, "step": 2521 }, { "epoch": 0.3593616414933029, "grad_norm": 1.5123175767895025, "learning_rate": 1.9616613247485223e-05, "loss": 0.6513, "step": 2522 }, { "epoch": 0.359504132231405, "grad_norm": 1.4008671668194166, "learning_rate": 1.9615930912481037e-05, "loss": 0.6528, "step": 2523 }, { "epoch": 0.359646622969507, "grad_norm": 1.499785696159337, "learning_rate": 1.961524798270988e-05, "loss": 0.7771, "step": 2524 }, { "epoch": 0.359789113707609, "grad_norm": 1.5420903008887032, "learning_rate": 1.9614564458213987e-05, "loss": 0.7583, "step": 2525 }, { "epoch": 0.35993160444571104, "grad_norm": 1.5082561554291296, "learning_rate": 1.961388033903564e-05, "loss": 0.7101, "step": 2526 }, { "epoch": 0.36007409518381306, "grad_norm": 1.4576881657566272, "learning_rate": 1.9613195625217157e-05, "loss": 0.6949, "step": 2527 }, { "epoch": 0.3602165859219151, "grad_norm": 1.4628185141560104, "learning_rate": 1.9612510316800886e-05, "loss": 0.6793, "step": 2528 }, { "epoch": 0.3603590766600171, "grad_norm": 1.7079713882945757, "learning_rate": 1.9611824413829215e-05, "loss": 0.7589, "step": 2529 }, { "epoch": 0.3605015673981191, "grad_norm": 1.5900655532303527, "learning_rate": 1.9611137916344566e-05, "loss": 0.6878, "step": 2530 }, { "epoch": 0.36064405813622114, "grad_norm": 1.422451121919145, "learning_rate": 1.9610450824389403e-05, "loss": 0.7039, "step": 2531 }, { "epoch": 0.36078654887432315, "grad_norm": 1.5321171532487483, "learning_rate": 1.9609763138006226e-05, "loss": 0.6836, "step": 2532 }, { "epoch": 0.3609290396124252, "grad_norm": 1.5702490536700897, "learning_rate": 1.9609074857237567e-05, "loss": 0.6905, "step": 2533 }, { "epoch": 0.3610715303505272, "grad_norm": 1.7922905210553615, "learning_rate": 1.9608385982126e-05, "loss": 0.7194, "step": 2534 }, { "epoch": 0.36121402108862927, "grad_norm": 1.5417569753996079, "learning_rate": 1.9607696512714133e-05, "loss": 0.7087, "step": 2535 }, { "epoch": 0.3613565118267313, "grad_norm": 1.545160662021172, "learning_rate": 1.9607006449044607e-05, "loss": 0.7349, "step": 2536 }, { "epoch": 0.3614990025648333, "grad_norm": 1.3917219291534633, "learning_rate": 1.960631579116011e-05, "loss": 0.6348, "step": 2537 }, { "epoch": 0.3616414933029353, "grad_norm": 1.8041595501658105, "learning_rate": 1.9605624539103355e-05, "loss": 0.6461, "step": 2538 }, { "epoch": 0.36178398404103734, "grad_norm": 1.4298294374614973, "learning_rate": 1.9604932692917105e-05, "loss": 0.6684, "step": 2539 }, { "epoch": 0.36192647477913936, "grad_norm": 1.5402640038937825, "learning_rate": 1.9604240252644145e-05, "loss": 0.7751, "step": 2540 }, { "epoch": 0.3620689655172414, "grad_norm": 1.6590448302079257, "learning_rate": 1.9603547218327307e-05, "loss": 0.7284, "step": 2541 }, { "epoch": 0.3622114562553434, "grad_norm": 1.5325504084977024, "learning_rate": 1.9602853590009456e-05, "loss": 0.7387, "step": 2542 }, { "epoch": 0.3623539469934454, "grad_norm": 1.835548948253926, "learning_rate": 1.9602159367733494e-05, "loss": 0.7419, "step": 2543 }, { "epoch": 0.36249643773154744, "grad_norm": 1.4834170335897625, "learning_rate": 1.9601464551542366e-05, "loss": 0.7825, "step": 2544 }, { "epoch": 0.36263892846964946, "grad_norm": 1.508539367462075, "learning_rate": 1.960076914147904e-05, "loss": 0.6318, "step": 2545 }, { "epoch": 0.3627814192077515, "grad_norm": 1.4453329626566713, "learning_rate": 1.960007313758653e-05, "loss": 0.6939, "step": 2546 }, { "epoch": 0.3629239099458535, "grad_norm": 1.654320422810121, "learning_rate": 1.9599376539907893e-05, "loss": 0.778, "step": 2547 }, { "epoch": 0.36306640068395557, "grad_norm": 1.625537988010103, "learning_rate": 1.9598679348486206e-05, "loss": 0.7582, "step": 2548 }, { "epoch": 0.3632088914220576, "grad_norm": 1.5165811913945169, "learning_rate": 1.9597981563364594e-05, "loss": 0.6664, "step": 2549 }, { "epoch": 0.3633513821601596, "grad_norm": 1.499465407538274, "learning_rate": 1.959728318458622e-05, "loss": 0.701, "step": 2550 }, { "epoch": 0.3634938728982616, "grad_norm": 1.329590986223564, "learning_rate": 1.9596584212194277e-05, "loss": 0.6956, "step": 2551 }, { "epoch": 0.36363636363636365, "grad_norm": 1.6245379779656168, "learning_rate": 1.9595884646232e-05, "loss": 0.7019, "step": 2552 }, { "epoch": 0.36377885437446567, "grad_norm": 1.68938327215616, "learning_rate": 1.9595184486742656e-05, "loss": 0.6852, "step": 2553 }, { "epoch": 0.3639213451125677, "grad_norm": 1.6146618349461597, "learning_rate": 1.959448373376956e-05, "loss": 0.6736, "step": 2554 }, { "epoch": 0.3640638358506697, "grad_norm": 1.374621590108682, "learning_rate": 1.959378238735604e-05, "loss": 0.6635, "step": 2555 }, { "epoch": 0.3642063265887717, "grad_norm": 1.5341849732395836, "learning_rate": 1.9593080447545486e-05, "loss": 0.6852, "step": 2556 }, { "epoch": 0.36434881732687374, "grad_norm": 1.5397542696913211, "learning_rate": 1.9592377914381316e-05, "loss": 0.8277, "step": 2557 }, { "epoch": 0.36449130806497576, "grad_norm": 2.24468082606029, "learning_rate": 1.959167478790698e-05, "loss": 0.7024, "step": 2558 }, { "epoch": 0.3646337988030778, "grad_norm": 1.44453393236539, "learning_rate": 1.9590971068165966e-05, "loss": 0.7455, "step": 2559 }, { "epoch": 0.3647762895411798, "grad_norm": 1.4724528699880848, "learning_rate": 1.9590266755201804e-05, "loss": 0.6897, "step": 2560 }, { "epoch": 0.3649187802792819, "grad_norm": 1.481606363770471, "learning_rate": 1.9589561849058057e-05, "loss": 0.7331, "step": 2561 }, { "epoch": 0.3650612710173839, "grad_norm": 1.7872942816982824, "learning_rate": 1.9588856349778323e-05, "loss": 0.7215, "step": 2562 }, { "epoch": 0.3652037617554859, "grad_norm": 1.7407685795911323, "learning_rate": 1.958815025740624e-05, "loss": 0.778, "step": 2563 }, { "epoch": 0.36534625249358793, "grad_norm": 1.5812260528715998, "learning_rate": 1.9587443571985482e-05, "loss": 0.7457, "step": 2564 }, { "epoch": 0.36548874323168995, "grad_norm": 1.4836862628913152, "learning_rate": 1.9586736293559754e-05, "loss": 0.6403, "step": 2565 }, { "epoch": 0.36563123396979197, "grad_norm": 1.3989930627101543, "learning_rate": 1.9586028422172814e-05, "loss": 0.6998, "step": 2566 }, { "epoch": 0.365773724707894, "grad_norm": 1.422106681122611, "learning_rate": 1.9585319957868437e-05, "loss": 0.587, "step": 2567 }, { "epoch": 0.365916215445996, "grad_norm": 1.567660874007755, "learning_rate": 1.958461090069044e-05, "loss": 0.7484, "step": 2568 }, { "epoch": 0.366058706184098, "grad_norm": 1.4937641853900603, "learning_rate": 1.9583901250682687e-05, "loss": 0.6796, "step": 2569 }, { "epoch": 0.36620119692220005, "grad_norm": 1.490504725335314, "learning_rate": 1.958319100788907e-05, "loss": 0.6766, "step": 2570 }, { "epoch": 0.36634368766030206, "grad_norm": 1.6071138287704687, "learning_rate": 1.9582480172353518e-05, "loss": 0.6769, "step": 2571 }, { "epoch": 0.3664861783984041, "grad_norm": 1.4623010045708902, "learning_rate": 1.9581768744119998e-05, "loss": 0.6948, "step": 2572 }, { "epoch": 0.3666286691365061, "grad_norm": 2.4546556269167255, "learning_rate": 1.9581056723232513e-05, "loss": 0.6637, "step": 2573 }, { "epoch": 0.3667711598746082, "grad_norm": 1.5113235184322318, "learning_rate": 1.95803441097351e-05, "loss": 0.6805, "step": 2574 }, { "epoch": 0.3669136506127102, "grad_norm": 1.5719517830681782, "learning_rate": 1.9579630903671845e-05, "loss": 0.7351, "step": 2575 }, { "epoch": 0.3670561413508122, "grad_norm": 1.4101762682564658, "learning_rate": 1.957891710508685e-05, "loss": 0.7275, "step": 2576 }, { "epoch": 0.36719863208891423, "grad_norm": 1.7921618896219107, "learning_rate": 1.9578202714024275e-05, "loss": 0.7407, "step": 2577 }, { "epoch": 0.36734112282701625, "grad_norm": 1.4801114599497738, "learning_rate": 1.95774877305283e-05, "loss": 0.7637, "step": 2578 }, { "epoch": 0.3674836135651183, "grad_norm": 1.4902113405548925, "learning_rate": 1.957677215464315e-05, "loss": 0.7371, "step": 2579 }, { "epoch": 0.3676261043032203, "grad_norm": 1.405744855457891, "learning_rate": 1.9576055986413087e-05, "loss": 0.5984, "step": 2580 }, { "epoch": 0.3677685950413223, "grad_norm": 1.527509745314795, "learning_rate": 1.9575339225882405e-05, "loss": 0.6443, "step": 2581 }, { "epoch": 0.36791108577942433, "grad_norm": 1.5205175140201428, "learning_rate": 1.957462187309544e-05, "loss": 0.6849, "step": 2582 }, { "epoch": 0.36805357651752635, "grad_norm": 1.5148630272167372, "learning_rate": 1.957390392809656e-05, "loss": 0.6574, "step": 2583 }, { "epoch": 0.36819606725562837, "grad_norm": 1.410134374553916, "learning_rate": 1.957318539093017e-05, "loss": 0.5906, "step": 2584 }, { "epoch": 0.3683385579937304, "grad_norm": 1.7391767422648885, "learning_rate": 1.9572466261640715e-05, "loss": 0.8026, "step": 2585 }, { "epoch": 0.3684810487318324, "grad_norm": 1.3964457890278505, "learning_rate": 1.9571746540272674e-05, "loss": 0.6481, "step": 2586 }, { "epoch": 0.3686235394699345, "grad_norm": 1.4214047903754514, "learning_rate": 1.957102622687057e-05, "loss": 0.6746, "step": 2587 }, { "epoch": 0.3687660302080365, "grad_norm": 1.5370458365731154, "learning_rate": 1.9570305321478943e-05, "loss": 0.7621, "step": 2588 }, { "epoch": 0.3689085209461385, "grad_norm": 1.5395466433435987, "learning_rate": 1.9569583824142393e-05, "loss": 0.6933, "step": 2589 }, { "epoch": 0.36905101168424054, "grad_norm": 1.5664198501197881, "learning_rate": 1.9568861734905543e-05, "loss": 0.7233, "step": 2590 }, { "epoch": 0.36919350242234256, "grad_norm": 1.4629004400007064, "learning_rate": 1.9568139053813057e-05, "loss": 0.6777, "step": 2591 }, { "epoch": 0.3693359931604446, "grad_norm": 1.903012865324726, "learning_rate": 1.956741578090963e-05, "loss": 0.6105, "step": 2592 }, { "epoch": 0.3694784838985466, "grad_norm": 1.4169423005255743, "learning_rate": 1.9566691916240004e-05, "loss": 0.6635, "step": 2593 }, { "epoch": 0.3696209746366486, "grad_norm": 1.4977905928232866, "learning_rate": 1.9565967459848947e-05, "loss": 0.6558, "step": 2594 }, { "epoch": 0.36976346537475063, "grad_norm": 1.534749247751005, "learning_rate": 1.9565242411781274e-05, "loss": 0.7446, "step": 2595 }, { "epoch": 0.36990595611285265, "grad_norm": 1.4322564296068874, "learning_rate": 1.956451677208182e-05, "loss": 0.7978, "step": 2596 }, { "epoch": 0.37004844685095467, "grad_norm": 1.4887915237165594, "learning_rate": 1.9563790540795483e-05, "loss": 0.733, "step": 2597 }, { "epoch": 0.3701909375890567, "grad_norm": 1.715686320753472, "learning_rate": 1.9563063717967167e-05, "loss": 0.7415, "step": 2598 }, { "epoch": 0.3703334283271587, "grad_norm": 1.6222731490238538, "learning_rate": 1.956233630364184e-05, "loss": 0.7308, "step": 2599 }, { "epoch": 0.3704759190652608, "grad_norm": 1.5633956726747893, "learning_rate": 1.9561608297864483e-05, "loss": 0.7381, "step": 2600 }, { "epoch": 0.3706184098033628, "grad_norm": 1.5052008105360062, "learning_rate": 1.9560879700680132e-05, "loss": 0.7043, "step": 2601 }, { "epoch": 0.3707609005414648, "grad_norm": 1.5802308051344582, "learning_rate": 1.956015051213385e-05, "loss": 0.7264, "step": 2602 }, { "epoch": 0.37090339127956684, "grad_norm": 1.3446065724645564, "learning_rate": 1.9559420732270743e-05, "loss": 0.7051, "step": 2603 }, { "epoch": 0.37104588201766886, "grad_norm": 1.3985899692952808, "learning_rate": 1.9558690361135945e-05, "loss": 0.6637, "step": 2604 }, { "epoch": 0.3711883727557709, "grad_norm": 1.596124587707346, "learning_rate": 1.9557959398774627e-05, "loss": 0.7097, "step": 2605 }, { "epoch": 0.3713308634938729, "grad_norm": 1.6426774426395119, "learning_rate": 1.955722784523201e-05, "loss": 0.6718, "step": 2606 }, { "epoch": 0.3714733542319749, "grad_norm": 1.5473799853543566, "learning_rate": 1.955649570055334e-05, "loss": 0.6436, "step": 2607 }, { "epoch": 0.37161584497007694, "grad_norm": 1.4030151280364735, "learning_rate": 1.9555762964783896e-05, "loss": 0.6734, "step": 2608 }, { "epoch": 0.37175833570817896, "grad_norm": 1.4343456474338654, "learning_rate": 1.9555029637969005e-05, "loss": 0.7052, "step": 2609 }, { "epoch": 0.371900826446281, "grad_norm": 2.620852524936606, "learning_rate": 1.9554295720154022e-05, "loss": 0.7948, "step": 2610 }, { "epoch": 0.372043317184383, "grad_norm": 1.580171074309367, "learning_rate": 1.955356121138434e-05, "loss": 0.814, "step": 2611 }, { "epoch": 0.372185807922485, "grad_norm": 1.4427953477949906, "learning_rate": 1.9552826111705402e-05, "loss": 0.7867, "step": 2612 }, { "epoch": 0.3723282986605871, "grad_norm": 1.35915392391033, "learning_rate": 1.955209042116266e-05, "loss": 0.6478, "step": 2613 }, { "epoch": 0.3724707893986891, "grad_norm": 1.5344001782728913, "learning_rate": 1.955135413980162e-05, "loss": 0.5486, "step": 2614 }, { "epoch": 0.3726132801367911, "grad_norm": 1.7459180814709467, "learning_rate": 1.9550617267667834e-05, "loss": 0.74, "step": 2615 }, { "epoch": 0.37275577087489314, "grad_norm": 1.4189138463384878, "learning_rate": 1.954987980480687e-05, "loss": 0.6452, "step": 2616 }, { "epoch": 0.37289826161299516, "grad_norm": 2.029365961292181, "learning_rate": 1.9549141751264344e-05, "loss": 0.6972, "step": 2617 }, { "epoch": 0.3730407523510972, "grad_norm": 1.6909804868471217, "learning_rate": 1.9548403107085905e-05, "loss": 0.712, "step": 2618 }, { "epoch": 0.3731832430891992, "grad_norm": 1.935752574170134, "learning_rate": 1.9547663872317245e-05, "loss": 0.7898, "step": 2619 }, { "epoch": 0.3733257338273012, "grad_norm": 1.6753734301856151, "learning_rate": 1.9546924047004077e-05, "loss": 0.7099, "step": 2620 }, { "epoch": 0.37346822456540324, "grad_norm": 1.5768358617733673, "learning_rate": 1.9546183631192174e-05, "loss": 0.7103, "step": 2621 }, { "epoch": 0.37361071530350526, "grad_norm": 1.562773155573806, "learning_rate": 1.954544262492732e-05, "loss": 0.6637, "step": 2622 }, { "epoch": 0.3737532060416073, "grad_norm": 1.531126876951779, "learning_rate": 1.9544701028255354e-05, "loss": 0.7191, "step": 2623 }, { "epoch": 0.3738956967797093, "grad_norm": 1.5347715446316146, "learning_rate": 1.954395884122215e-05, "loss": 0.8189, "step": 2624 }, { "epoch": 0.3740381875178113, "grad_norm": 1.6554927958396353, "learning_rate": 1.9543216063873603e-05, "loss": 0.6419, "step": 2625 }, { "epoch": 0.3741806782559134, "grad_norm": 1.4803923454386656, "learning_rate": 1.9542472696255666e-05, "loss": 0.6307, "step": 2626 }, { "epoch": 0.3743231689940154, "grad_norm": 1.535697261762851, "learning_rate": 1.954172873841431e-05, "loss": 0.6787, "step": 2627 }, { "epoch": 0.37446565973211743, "grad_norm": 1.5022860547195531, "learning_rate": 1.9540984190395552e-05, "loss": 0.6692, "step": 2628 }, { "epoch": 0.37460815047021945, "grad_norm": 1.571090906968676, "learning_rate": 1.9540239052245453e-05, "loss": 0.7417, "step": 2629 }, { "epoch": 0.37475064120832147, "grad_norm": 1.4991150472836612, "learning_rate": 1.9539493324010088e-05, "loss": 0.6643, "step": 2630 }, { "epoch": 0.3748931319464235, "grad_norm": 1.619846185029918, "learning_rate": 1.9538747005735587e-05, "loss": 0.7041, "step": 2631 }, { "epoch": 0.3750356226845255, "grad_norm": 1.5850955474185318, "learning_rate": 1.9538000097468117e-05, "loss": 0.68, "step": 2632 }, { "epoch": 0.3751781134226275, "grad_norm": 1.4838162671807493, "learning_rate": 1.9537252599253867e-05, "loss": 0.662, "step": 2633 }, { "epoch": 0.37532060416072954, "grad_norm": 1.407722914830414, "learning_rate": 1.953650451113908e-05, "loss": 0.743, "step": 2634 }, { "epoch": 0.37546309489883156, "grad_norm": 1.6963593822720686, "learning_rate": 1.9535755833170024e-05, "loss": 0.6694, "step": 2635 }, { "epoch": 0.3756055856369336, "grad_norm": 1.4683658512815172, "learning_rate": 1.9535006565393003e-05, "loss": 0.7223, "step": 2636 }, { "epoch": 0.3757480763750356, "grad_norm": 1.4390104732341353, "learning_rate": 1.953425670785436e-05, "loss": 0.6849, "step": 2637 }, { "epoch": 0.3758905671131376, "grad_norm": 1.3322740661414372, "learning_rate": 1.9533506260600483e-05, "loss": 0.6955, "step": 2638 }, { "epoch": 0.3760330578512397, "grad_norm": 1.3593323672523971, "learning_rate": 1.9532755223677783e-05, "loss": 0.6964, "step": 2639 }, { "epoch": 0.3761755485893417, "grad_norm": 1.5892005259851083, "learning_rate": 1.9532003597132715e-05, "loss": 0.7445, "step": 2640 }, { "epoch": 0.37631803932744373, "grad_norm": 1.657360960252637, "learning_rate": 1.9531251381011767e-05, "loss": 0.7294, "step": 2641 }, { "epoch": 0.37646053006554575, "grad_norm": 1.6004484543828101, "learning_rate": 1.953049857536147e-05, "loss": 0.6817, "step": 2642 }, { "epoch": 0.37660302080364777, "grad_norm": 1.668080325318029, "learning_rate": 1.9529745180228384e-05, "loss": 0.7487, "step": 2643 }, { "epoch": 0.3767455115417498, "grad_norm": 1.5319685440851527, "learning_rate": 1.9528991195659106e-05, "loss": 0.6563, "step": 2644 }, { "epoch": 0.3768880022798518, "grad_norm": 1.5685118453065852, "learning_rate": 1.9528236621700275e-05, "loss": 0.6057, "step": 2645 }, { "epoch": 0.3770304930179538, "grad_norm": 1.477385578843823, "learning_rate": 1.9527481458398558e-05, "loss": 0.6976, "step": 2646 }, { "epoch": 0.37717298375605585, "grad_norm": 1.9054800617512075, "learning_rate": 1.952672570580067e-05, "loss": 0.6336, "step": 2647 }, { "epoch": 0.37731547449415787, "grad_norm": 1.478480215404995, "learning_rate": 1.952596936395335e-05, "loss": 0.69, "step": 2648 }, { "epoch": 0.3774579652322599, "grad_norm": 1.5811652494048904, "learning_rate": 1.9525212432903388e-05, "loss": 0.7435, "step": 2649 }, { "epoch": 0.3776004559703619, "grad_norm": 1.5602280505594184, "learning_rate": 1.952445491269759e-05, "loss": 0.674, "step": 2650 }, { "epoch": 0.3777429467084639, "grad_norm": 1.6658222463302086, "learning_rate": 1.9523696803382822e-05, "loss": 0.7708, "step": 2651 }, { "epoch": 0.377885437446566, "grad_norm": 1.5655739439917609, "learning_rate": 1.9522938105005966e-05, "loss": 0.7186, "step": 2652 }, { "epoch": 0.378027928184668, "grad_norm": 1.584751253140485, "learning_rate": 1.9522178817613955e-05, "loss": 0.6851, "step": 2653 }, { "epoch": 0.37817041892277004, "grad_norm": 1.3883318916474008, "learning_rate": 1.952141894125375e-05, "loss": 0.7033, "step": 2654 }, { "epoch": 0.37831290966087205, "grad_norm": 1.5106030604767713, "learning_rate": 1.952065847597235e-05, "loss": 0.6905, "step": 2655 }, { "epoch": 0.3784554003989741, "grad_norm": 1.5539608662328732, "learning_rate": 1.951989742181679e-05, "loss": 0.7202, "step": 2656 }, { "epoch": 0.3785978911370761, "grad_norm": 1.7099564902129483, "learning_rate": 1.9519135778834154e-05, "loss": 0.6809, "step": 2657 }, { "epoch": 0.3787403818751781, "grad_norm": 1.5154630651316046, "learning_rate": 1.9518373547071535e-05, "loss": 0.6865, "step": 2658 }, { "epoch": 0.37888287261328013, "grad_norm": 1.7604410102412358, "learning_rate": 1.9517610726576092e-05, "loss": 0.6282, "step": 2659 }, { "epoch": 0.37902536335138215, "grad_norm": 1.2987483937532196, "learning_rate": 1.9516847317395e-05, "loss": 0.6587, "step": 2660 }, { "epoch": 0.37916785408948417, "grad_norm": 1.3761487548623557, "learning_rate": 1.951608331957548e-05, "loss": 0.6477, "step": 2661 }, { "epoch": 0.3793103448275862, "grad_norm": 1.5580706388975425, "learning_rate": 1.9515318733164785e-05, "loss": 0.7117, "step": 2662 }, { "epoch": 0.3794528355656882, "grad_norm": 1.5185689281370502, "learning_rate": 1.951455355821021e-05, "loss": 0.7611, "step": 2663 }, { "epoch": 0.3795953263037902, "grad_norm": 1.4334367098614298, "learning_rate": 1.9513787794759082e-05, "loss": 0.6937, "step": 2664 }, { "epoch": 0.3797378170418923, "grad_norm": 1.5741549195363982, "learning_rate": 1.951302144285876e-05, "loss": 0.7744, "step": 2665 }, { "epoch": 0.3798803077799943, "grad_norm": 1.5921184611424715, "learning_rate": 1.9512254502556652e-05, "loss": 0.684, "step": 2666 }, { "epoch": 0.38002279851809634, "grad_norm": 5.595632646894878, "learning_rate": 1.951148697390019e-05, "loss": 0.748, "step": 2667 }, { "epoch": 0.38016528925619836, "grad_norm": 1.7429521351038193, "learning_rate": 1.951071885693685e-05, "loss": 0.6699, "step": 2668 }, { "epoch": 0.3803077799943004, "grad_norm": 1.5955770554180664, "learning_rate": 1.9509950151714142e-05, "loss": 0.7233, "step": 2669 }, { "epoch": 0.3804502707324024, "grad_norm": 1.5421461661901823, "learning_rate": 1.9509180858279608e-05, "loss": 0.7479, "step": 2670 }, { "epoch": 0.3805927614705044, "grad_norm": 1.390209696857184, "learning_rate": 1.9508410976680835e-05, "loss": 0.6687, "step": 2671 }, { "epoch": 0.38073525220860643, "grad_norm": 1.536326715195259, "learning_rate": 1.950764050696544e-05, "loss": 0.7706, "step": 2672 }, { "epoch": 0.38087774294670845, "grad_norm": 1.5941288390290034, "learning_rate": 1.9506869449181077e-05, "loss": 0.6471, "step": 2673 }, { "epoch": 0.38102023368481047, "grad_norm": 1.3834778730787802, "learning_rate": 1.950609780337544e-05, "loss": 0.6379, "step": 2674 }, { "epoch": 0.3811627244229125, "grad_norm": 1.6089386335711167, "learning_rate": 1.9505325569596256e-05, "loss": 0.7002, "step": 2675 }, { "epoch": 0.3813052151610145, "grad_norm": 1.5532382802624523, "learning_rate": 1.9504552747891293e-05, "loss": 0.7414, "step": 2676 }, { "epoch": 0.3814477058991166, "grad_norm": 1.53982579012125, "learning_rate": 1.9503779338308344e-05, "loss": 0.7924, "step": 2677 }, { "epoch": 0.3815901966372186, "grad_norm": 2.3055821853101572, "learning_rate": 1.950300534089525e-05, "loss": 0.6869, "step": 2678 }, { "epoch": 0.3817326873753206, "grad_norm": 2.0704620651324603, "learning_rate": 1.9502230755699888e-05, "loss": 0.7281, "step": 2679 }, { "epoch": 0.38187517811342264, "grad_norm": 1.564296831137049, "learning_rate": 1.9501455582770167e-05, "loss": 0.6232, "step": 2680 }, { "epoch": 0.38201766885152466, "grad_norm": 1.5221075698509312, "learning_rate": 1.9500679822154028e-05, "loss": 0.7543, "step": 2681 }, { "epoch": 0.3821601595896267, "grad_norm": 2.651473254896127, "learning_rate": 1.9499903473899455e-05, "loss": 0.6771, "step": 2682 }, { "epoch": 0.3823026503277287, "grad_norm": 1.6635453120551589, "learning_rate": 1.949912653805447e-05, "loss": 0.6689, "step": 2683 }, { "epoch": 0.3824451410658307, "grad_norm": 1.5311373391905985, "learning_rate": 1.9498349014667128e-05, "loss": 0.7072, "step": 2684 }, { "epoch": 0.38258763180393274, "grad_norm": 1.7773215979795467, "learning_rate": 1.949757090378552e-05, "loss": 0.6963, "step": 2685 }, { "epoch": 0.38273012254203476, "grad_norm": 1.4457761961005116, "learning_rate": 1.949679220545777e-05, "loss": 0.6252, "step": 2686 }, { "epoch": 0.3828726132801368, "grad_norm": 1.4963511697043128, "learning_rate": 1.9496012919732048e-05, "loss": 0.66, "step": 2687 }, { "epoch": 0.3830151040182388, "grad_norm": 1.3726714900523391, "learning_rate": 1.949523304665655e-05, "loss": 0.7701, "step": 2688 }, { "epoch": 0.3831575947563408, "grad_norm": 1.4547692634125027, "learning_rate": 1.9494452586279516e-05, "loss": 0.738, "step": 2689 }, { "epoch": 0.3833000854944429, "grad_norm": 1.4679634716820424, "learning_rate": 1.9493671538649217e-05, "loss": 0.6757, "step": 2690 }, { "epoch": 0.3834425762325449, "grad_norm": 1.4829868565221576, "learning_rate": 1.9492889903813964e-05, "loss": 0.7204, "step": 2691 }, { "epoch": 0.3835850669706469, "grad_norm": 1.4486364381104266, "learning_rate": 1.9492107681822103e-05, "loss": 0.6989, "step": 2692 }, { "epoch": 0.38372755770874895, "grad_norm": 1.629041688479375, "learning_rate": 1.9491324872722016e-05, "loss": 0.6899, "step": 2693 }, { "epoch": 0.38387004844685096, "grad_norm": 1.513240018835183, "learning_rate": 1.949054147656212e-05, "loss": 0.6567, "step": 2694 }, { "epoch": 0.384012539184953, "grad_norm": 1.5794499183147384, "learning_rate": 1.9489757493390874e-05, "loss": 0.7122, "step": 2695 }, { "epoch": 0.384155029923055, "grad_norm": 1.602880151994007, "learning_rate": 1.9488972923256764e-05, "loss": 0.7012, "step": 2696 }, { "epoch": 0.384297520661157, "grad_norm": 1.731821037259871, "learning_rate": 1.9488187766208323e-05, "loss": 0.7511, "step": 2697 }, { "epoch": 0.38444001139925904, "grad_norm": 1.5500974643164878, "learning_rate": 1.9487402022294105e-05, "loss": 0.6923, "step": 2698 }, { "epoch": 0.38458250213736106, "grad_norm": 1.7534317205722358, "learning_rate": 1.948661569156272e-05, "loss": 0.6179, "step": 2699 }, { "epoch": 0.3847249928754631, "grad_norm": 1.4202341551277142, "learning_rate": 1.9485828774062803e-05, "loss": 0.6737, "step": 2700 }, { "epoch": 0.3848674836135651, "grad_norm": 1.4034634082539168, "learning_rate": 1.9485041269843023e-05, "loss": 0.7522, "step": 2701 }, { "epoch": 0.3850099743516671, "grad_norm": 1.4258320167276224, "learning_rate": 1.948425317895209e-05, "loss": 0.6177, "step": 2702 }, { "epoch": 0.3851524650897692, "grad_norm": 3.384471922191862, "learning_rate": 1.9483464501438747e-05, "loss": 0.6359, "step": 2703 }, { "epoch": 0.3852949558278712, "grad_norm": 1.6077292732574426, "learning_rate": 1.9482675237351782e-05, "loss": 0.7066, "step": 2704 }, { "epoch": 0.38543744656597323, "grad_norm": 1.364145294126018, "learning_rate": 1.9481885386740003e-05, "loss": 0.6498, "step": 2705 }, { "epoch": 0.38557993730407525, "grad_norm": 1.5198087321884741, "learning_rate": 1.9481094949652272e-05, "loss": 0.8154, "step": 2706 }, { "epoch": 0.38572242804217727, "grad_norm": 1.5971853111056602, "learning_rate": 1.948030392613748e-05, "loss": 0.6981, "step": 2707 }, { "epoch": 0.3858649187802793, "grad_norm": 1.4645693486036453, "learning_rate": 1.947951231624455e-05, "loss": 0.7159, "step": 2708 }, { "epoch": 0.3860074095183813, "grad_norm": 1.6752818884340046, "learning_rate": 1.9478720120022443e-05, "loss": 0.6658, "step": 2709 }, { "epoch": 0.3861499002564833, "grad_norm": 1.380871816484121, "learning_rate": 1.9477927337520162e-05, "loss": 0.6438, "step": 2710 }, { "epoch": 0.38629239099458534, "grad_norm": 16.931343075550892, "learning_rate": 1.947713396878674e-05, "loss": 0.7041, "step": 2711 }, { "epoch": 0.38643488173268736, "grad_norm": 1.435879373248376, "learning_rate": 1.947634001387125e-05, "loss": 0.7444, "step": 2712 }, { "epoch": 0.3865773724707894, "grad_norm": 1.8911769663803888, "learning_rate": 1.94755454728228e-05, "loss": 0.6016, "step": 2713 }, { "epoch": 0.3867198632088914, "grad_norm": 1.852586599551298, "learning_rate": 1.9474750345690533e-05, "loss": 0.6727, "step": 2714 }, { "epoch": 0.3868623539469934, "grad_norm": 1.4589025892521998, "learning_rate": 1.9473954632523633e-05, "loss": 0.6709, "step": 2715 }, { "epoch": 0.3870048446850955, "grad_norm": 1.8459278401259784, "learning_rate": 1.947315833337131e-05, "loss": 0.7316, "step": 2716 }, { "epoch": 0.3871473354231975, "grad_norm": 1.4579660512430808, "learning_rate": 1.9472361448282823e-05, "loss": 0.6937, "step": 2717 }, { "epoch": 0.38728982616129953, "grad_norm": 1.4722437426483996, "learning_rate": 1.947156397730746e-05, "loss": 0.802, "step": 2718 }, { "epoch": 0.38743231689940155, "grad_norm": 1.4320755604138258, "learning_rate": 1.947076592049454e-05, "loss": 0.7022, "step": 2719 }, { "epoch": 0.38757480763750357, "grad_norm": 1.5909094792311786, "learning_rate": 1.9469967277893432e-05, "loss": 0.7002, "step": 2720 }, { "epoch": 0.3877172983756056, "grad_norm": 1.4186000637540404, "learning_rate": 1.9469168049553534e-05, "loss": 0.725, "step": 2721 }, { "epoch": 0.3878597891137076, "grad_norm": 1.4911658033985002, "learning_rate": 1.9468368235524274e-05, "loss": 0.7176, "step": 2722 }, { "epoch": 0.38800227985180963, "grad_norm": 1.4417908476577834, "learning_rate": 1.946756783585513e-05, "loss": 0.6656, "step": 2723 }, { "epoch": 0.38814477058991165, "grad_norm": 1.630607517252751, "learning_rate": 1.9466766850595603e-05, "loss": 0.8213, "step": 2724 }, { "epoch": 0.38828726132801367, "grad_norm": 1.50205253354154, "learning_rate": 1.9465965279795237e-05, "loss": 0.6212, "step": 2725 }, { "epoch": 0.3884297520661157, "grad_norm": 1.5054622146696732, "learning_rate": 1.946516312350361e-05, "loss": 0.6561, "step": 2726 }, { "epoch": 0.3885722428042177, "grad_norm": 1.6432199498623858, "learning_rate": 1.946436038177034e-05, "loss": 0.7504, "step": 2727 }, { "epoch": 0.3887147335423197, "grad_norm": 1.585128507567459, "learning_rate": 1.9463557054645074e-05, "loss": 0.7054, "step": 2728 }, { "epoch": 0.3888572242804218, "grad_norm": 1.5462532984429735, "learning_rate": 1.9462753142177507e-05, "loss": 0.6665, "step": 2729 }, { "epoch": 0.3889997150185238, "grad_norm": 1.4343807469420886, "learning_rate": 1.9461948644417356e-05, "loss": 0.6374, "step": 2730 }, { "epoch": 0.38914220575662584, "grad_norm": 1.3884860281217406, "learning_rate": 1.946114356141438e-05, "loss": 0.755, "step": 2731 }, { "epoch": 0.38928469649472786, "grad_norm": 1.49575506323643, "learning_rate": 1.9460337893218383e-05, "loss": 0.6732, "step": 2732 }, { "epoch": 0.3894271872328299, "grad_norm": 1.4836029629861291, "learning_rate": 1.945953163987919e-05, "loss": 0.6701, "step": 2733 }, { "epoch": 0.3895696779709319, "grad_norm": 1.6363507592589057, "learning_rate": 1.945872480144667e-05, "loss": 0.6579, "step": 2734 }, { "epoch": 0.3897121687090339, "grad_norm": 1.5779995550834034, "learning_rate": 1.945791737797073e-05, "loss": 0.7765, "step": 2735 }, { "epoch": 0.38985465944713593, "grad_norm": 1.5061137614039293, "learning_rate": 1.9457109369501316e-05, "loss": 0.6593, "step": 2736 }, { "epoch": 0.38999715018523795, "grad_norm": 1.9143224550051745, "learning_rate": 1.94563007760884e-05, "loss": 0.6985, "step": 2737 }, { "epoch": 0.39013964092333997, "grad_norm": 1.7632548121192084, "learning_rate": 1.9455491597781992e-05, "loss": 0.7334, "step": 2738 }, { "epoch": 0.390282131661442, "grad_norm": 2.0242650753198603, "learning_rate": 1.9454681834632148e-05, "loss": 0.6872, "step": 2739 }, { "epoch": 0.390424622399544, "grad_norm": 1.7359341272286601, "learning_rate": 1.9453871486688947e-05, "loss": 0.6978, "step": 2740 }, { "epoch": 0.390567113137646, "grad_norm": 1.5828898114055814, "learning_rate": 1.9453060554002515e-05, "loss": 0.7705, "step": 2741 }, { "epoch": 0.3907096038757481, "grad_norm": 1.527277879352676, "learning_rate": 1.9452249036623015e-05, "loss": 0.7288, "step": 2742 }, { "epoch": 0.3908520946138501, "grad_norm": 1.552700392281528, "learning_rate": 1.9451436934600633e-05, "loss": 0.6931, "step": 2743 }, { "epoch": 0.39099458535195214, "grad_norm": 1.5505119298398282, "learning_rate": 1.9450624247985598e-05, "loss": 0.7004, "step": 2744 }, { "epoch": 0.39113707609005416, "grad_norm": 1.326701747541429, "learning_rate": 1.9449810976828182e-05, "loss": 0.6307, "step": 2745 }, { "epoch": 0.3912795668281562, "grad_norm": 1.5912081468197705, "learning_rate": 1.944899712117869e-05, "loss": 0.7664, "step": 2746 }, { "epoch": 0.3914220575662582, "grad_norm": 1.5825649015676722, "learning_rate": 1.944818268108745e-05, "loss": 0.6836, "step": 2747 }, { "epoch": 0.3915645483043602, "grad_norm": 1.5206914569468244, "learning_rate": 1.9447367656604853e-05, "loss": 0.6112, "step": 2748 }, { "epoch": 0.39170703904246224, "grad_norm": 1.4265892620373588, "learning_rate": 1.9446552047781298e-05, "loss": 0.7378, "step": 2749 }, { "epoch": 0.39184952978056425, "grad_norm": 1.4245001189364388, "learning_rate": 1.9445735854667233e-05, "loss": 0.6704, "step": 2750 }, { "epoch": 0.3919920205186663, "grad_norm": 1.4844843823109353, "learning_rate": 1.9444919077313145e-05, "loss": 0.7352, "step": 2751 }, { "epoch": 0.3921345112567683, "grad_norm": 1.3833326930338836, "learning_rate": 1.944410171576955e-05, "loss": 0.7443, "step": 2752 }, { "epoch": 0.3922770019948703, "grad_norm": 1.4313247314363793, "learning_rate": 1.9443283770087008e-05, "loss": 0.6996, "step": 2753 }, { "epoch": 0.39241949273297233, "grad_norm": 1.633704602509172, "learning_rate": 1.944246524031611e-05, "loss": 0.6559, "step": 2754 }, { "epoch": 0.3925619834710744, "grad_norm": 1.3693550499178693, "learning_rate": 1.9441646126507477e-05, "loss": 0.7108, "step": 2755 }, { "epoch": 0.3927044742091764, "grad_norm": 1.7276326312320696, "learning_rate": 1.9440826428711784e-05, "loss": 0.7296, "step": 2756 }, { "epoch": 0.39284696494727844, "grad_norm": 1.7526276361855768, "learning_rate": 1.9440006146979722e-05, "loss": 0.6761, "step": 2757 }, { "epoch": 0.39298945568538046, "grad_norm": 1.4798203390817073, "learning_rate": 1.9439185281362035e-05, "loss": 0.7151, "step": 2758 }, { "epoch": 0.3931319464234825, "grad_norm": 1.6960222308584079, "learning_rate": 1.9438363831909488e-05, "loss": 0.7631, "step": 2759 }, { "epoch": 0.3932744371615845, "grad_norm": 1.4770281643746979, "learning_rate": 1.9437541798672896e-05, "loss": 0.6714, "step": 2760 }, { "epoch": 0.3934169278996865, "grad_norm": 2.329308633473721, "learning_rate": 1.9436719181703097e-05, "loss": 0.674, "step": 2761 }, { "epoch": 0.39355941863778854, "grad_norm": 1.3462708734391662, "learning_rate": 1.9435895981050976e-05, "loss": 0.6536, "step": 2762 }, { "epoch": 0.39370190937589056, "grad_norm": 1.568275669715446, "learning_rate": 1.9435072196767447e-05, "loss": 0.6836, "step": 2763 }, { "epoch": 0.3938444001139926, "grad_norm": 1.6635768945692393, "learning_rate": 1.943424782890347e-05, "loss": 0.6939, "step": 2764 }, { "epoch": 0.3939868908520946, "grad_norm": 1.523320827103164, "learning_rate": 1.9433422877510026e-05, "loss": 0.7167, "step": 2765 }, { "epoch": 0.3941293815901966, "grad_norm": 1.552407711442156, "learning_rate": 1.9432597342638142e-05, "loss": 0.7275, "step": 2766 }, { "epoch": 0.39427187232829863, "grad_norm": 8.825154613447753, "learning_rate": 1.9431771224338885e-05, "loss": 0.6469, "step": 2767 }, { "epoch": 0.3944143630664007, "grad_norm": 1.433689423181348, "learning_rate": 1.943094452266334e-05, "loss": 0.721, "step": 2768 }, { "epoch": 0.3945568538045027, "grad_norm": 1.5284539907003627, "learning_rate": 1.9430117237662654e-05, "loss": 0.7024, "step": 2769 }, { "epoch": 0.39469934454260475, "grad_norm": 1.6655583485463097, "learning_rate": 1.942928936938799e-05, "loss": 0.7297, "step": 2770 }, { "epoch": 0.39484183528070677, "grad_norm": 2.253369558353401, "learning_rate": 1.942846091789055e-05, "loss": 0.6812, "step": 2771 }, { "epoch": 0.3949843260188088, "grad_norm": 1.4061644177954222, "learning_rate": 1.942763188322158e-05, "loss": 0.6743, "step": 2772 }, { "epoch": 0.3951268167569108, "grad_norm": 1.9623875358203935, "learning_rate": 1.942680226543236e-05, "loss": 0.6289, "step": 2773 }, { "epoch": 0.3952693074950128, "grad_norm": 1.539791033614929, "learning_rate": 1.94259720645742e-05, "loss": 0.7191, "step": 2774 }, { "epoch": 0.39541179823311484, "grad_norm": 1.5307853848091872, "learning_rate": 1.942514128069845e-05, "loss": 0.7055, "step": 2775 }, { "epoch": 0.39555428897121686, "grad_norm": 1.5241495356404144, "learning_rate": 1.9424309913856496e-05, "loss": 0.7194, "step": 2776 }, { "epoch": 0.3956967797093189, "grad_norm": 1.5547866754675905, "learning_rate": 1.9423477964099763e-05, "loss": 0.7055, "step": 2777 }, { "epoch": 0.3958392704474209, "grad_norm": 1.2642957609625491, "learning_rate": 1.94226454314797e-05, "loss": 0.6822, "step": 2778 }, { "epoch": 0.3959817611855229, "grad_norm": 1.4782927591606043, "learning_rate": 1.9421812316047814e-05, "loss": 0.7397, "step": 2779 }, { "epoch": 0.39612425192362494, "grad_norm": 1.59822857873661, "learning_rate": 1.9420978617855623e-05, "loss": 0.6827, "step": 2780 }, { "epoch": 0.396266742661727, "grad_norm": 1.5704631055822067, "learning_rate": 1.94201443369547e-05, "loss": 0.7927, "step": 2781 }, { "epoch": 0.39640923339982903, "grad_norm": 1.815065077919652, "learning_rate": 1.9419309473396648e-05, "loss": 0.7352, "step": 2782 }, { "epoch": 0.39655172413793105, "grad_norm": 1.4948671896200552, "learning_rate": 1.94184740272331e-05, "loss": 0.7067, "step": 2783 }, { "epoch": 0.39669421487603307, "grad_norm": 1.7167999778342231, "learning_rate": 1.9417637998515733e-05, "loss": 0.7275, "step": 2784 }, { "epoch": 0.3968367056141351, "grad_norm": 1.4542356427353933, "learning_rate": 1.941680138729626e-05, "loss": 0.6289, "step": 2785 }, { "epoch": 0.3969791963522371, "grad_norm": 1.5363820501245238, "learning_rate": 1.9415964193626426e-05, "loss": 0.6235, "step": 2786 }, { "epoch": 0.3971216870903391, "grad_norm": 1.4495580641372792, "learning_rate": 1.9415126417558008e-05, "loss": 0.675, "step": 2787 }, { "epoch": 0.39726417782844115, "grad_norm": 1.4781731876589936, "learning_rate": 1.941428805914283e-05, "loss": 0.6995, "step": 2788 }, { "epoch": 0.39740666856654316, "grad_norm": 1.5834429896489228, "learning_rate": 1.9413449118432743e-05, "loss": 0.7219, "step": 2789 }, { "epoch": 0.3975491593046452, "grad_norm": 1.4195208382383737, "learning_rate": 1.941260959547964e-05, "loss": 0.6552, "step": 2790 }, { "epoch": 0.3976916500427472, "grad_norm": 1.3545798086113758, "learning_rate": 1.9411769490335448e-05, "loss": 0.6738, "step": 2791 }, { "epoch": 0.3978341407808492, "grad_norm": 2.2216878899116947, "learning_rate": 1.9410928803052124e-05, "loss": 0.6293, "step": 2792 }, { "epoch": 0.39797663151895124, "grad_norm": 1.4760357586000823, "learning_rate": 1.941008753368167e-05, "loss": 0.7579, "step": 2793 }, { "epoch": 0.3981191222570533, "grad_norm": 1.5109451809492602, "learning_rate": 1.9409245682276125e-05, "loss": 0.769, "step": 2794 }, { "epoch": 0.39826161299515533, "grad_norm": 1.5222733487950069, "learning_rate": 1.9408403248887554e-05, "loss": 0.6621, "step": 2795 }, { "epoch": 0.39840410373325735, "grad_norm": 1.327269823712257, "learning_rate": 1.9407560233568062e-05, "loss": 0.646, "step": 2796 }, { "epoch": 0.39854659447135937, "grad_norm": 1.653725860658987, "learning_rate": 1.9406716636369797e-05, "loss": 0.6891, "step": 2797 }, { "epoch": 0.3986890852094614, "grad_norm": 1.5516341032596246, "learning_rate": 1.9405872457344933e-05, "loss": 0.7115, "step": 2798 }, { "epoch": 0.3988315759475634, "grad_norm": 1.4116801576765499, "learning_rate": 1.940502769654568e-05, "loss": 0.8214, "step": 2799 }, { "epoch": 0.39897406668566543, "grad_norm": 1.6922743861339324, "learning_rate": 1.9404182354024302e-05, "loss": 0.735, "step": 2800 }, { "epoch": 0.39911655742376745, "grad_norm": 1.7488574005995774, "learning_rate": 1.9403336429833072e-05, "loss": 0.7508, "step": 2801 }, { "epoch": 0.39925904816186947, "grad_norm": 1.5188111107164521, "learning_rate": 1.9402489924024318e-05, "loss": 0.64, "step": 2802 }, { "epoch": 0.3994015388999715, "grad_norm": 1.403720804694437, "learning_rate": 1.94016428366504e-05, "loss": 0.7864, "step": 2803 }, { "epoch": 0.3995440296380735, "grad_norm": 1.5039471310281467, "learning_rate": 1.940079516776371e-05, "loss": 0.6557, "step": 2804 }, { "epoch": 0.3996865203761755, "grad_norm": 2.0125752167427744, "learning_rate": 1.9399946917416675e-05, "loss": 0.6574, "step": 2805 }, { "epoch": 0.3998290111142776, "grad_norm": 1.4388226639313717, "learning_rate": 1.939909808566177e-05, "loss": 0.6037, "step": 2806 }, { "epoch": 0.3999715018523796, "grad_norm": 1.5013805468492418, "learning_rate": 1.9398248672551487e-05, "loss": 0.8208, "step": 2807 }, { "epoch": 0.40011399259048164, "grad_norm": 1.7610441359057085, "learning_rate": 1.9397398678138372e-05, "loss": 0.6972, "step": 2808 }, { "epoch": 0.40025648332858366, "grad_norm": 1.6359041121151499, "learning_rate": 1.9396548102474992e-05, "loss": 0.6463, "step": 2809 }, { "epoch": 0.4003989740666857, "grad_norm": 1.4346746752073922, "learning_rate": 1.9395696945613966e-05, "loss": 0.6546, "step": 2810 }, { "epoch": 0.4005414648047877, "grad_norm": 1.422578081512465, "learning_rate": 1.939484520760793e-05, "loss": 0.6604, "step": 2811 }, { "epoch": 0.4006839555428897, "grad_norm": 1.5759240443061506, "learning_rate": 1.939399288850957e-05, "loss": 0.7892, "step": 2812 }, { "epoch": 0.40082644628099173, "grad_norm": 1.43594693439953, "learning_rate": 1.9393139988371608e-05, "loss": 0.6713, "step": 2813 }, { "epoch": 0.40096893701909375, "grad_norm": 1.654193591527076, "learning_rate": 1.9392286507246794e-05, "loss": 0.6654, "step": 2814 }, { "epoch": 0.40111142775719577, "grad_norm": 1.711230343058647, "learning_rate": 1.9391432445187916e-05, "loss": 0.7543, "step": 2815 }, { "epoch": 0.4012539184952978, "grad_norm": 1.4407521337741758, "learning_rate": 1.9390577802247805e-05, "loss": 0.7472, "step": 2816 }, { "epoch": 0.4013964092333998, "grad_norm": 1.5280854313747603, "learning_rate": 1.9389722578479317e-05, "loss": 0.7714, "step": 2817 }, { "epoch": 0.40153889997150183, "grad_norm": 1.4686467252509385, "learning_rate": 1.9388866773935353e-05, "loss": 0.6523, "step": 2818 }, { "epoch": 0.4016813907096039, "grad_norm": 1.7671476927060121, "learning_rate": 1.9388010388668846e-05, "loss": 0.7007, "step": 2819 }, { "epoch": 0.4018238814477059, "grad_norm": 1.8967596640747075, "learning_rate": 1.9387153422732763e-05, "loss": 0.7205, "step": 2820 }, { "epoch": 0.40196637218580794, "grad_norm": 1.663595028243928, "learning_rate": 1.938629587618011e-05, "loss": 0.6761, "step": 2821 }, { "epoch": 0.40210886292390996, "grad_norm": 1.557697468999058, "learning_rate": 1.938543774906393e-05, "loss": 0.6615, "step": 2822 }, { "epoch": 0.402251353662012, "grad_norm": 1.31008373953159, "learning_rate": 1.9384579041437302e-05, "loss": 0.6724, "step": 2823 }, { "epoch": 0.402393844400114, "grad_norm": 1.4182592018946305, "learning_rate": 1.9383719753353333e-05, "loss": 0.6449, "step": 2824 }, { "epoch": 0.402536335138216, "grad_norm": 1.2672326103052136, "learning_rate": 1.9382859884865177e-05, "loss": 0.708, "step": 2825 }, { "epoch": 0.40267882587631804, "grad_norm": 1.592559533057118, "learning_rate": 1.9381999436026014e-05, "loss": 0.7247, "step": 2826 }, { "epoch": 0.40282131661442006, "grad_norm": 1.5830114446590742, "learning_rate": 1.938113840688907e-05, "loss": 0.7152, "step": 2827 }, { "epoch": 0.4029638073525221, "grad_norm": 1.6374716696364902, "learning_rate": 1.93802767975076e-05, "loss": 0.769, "step": 2828 }, { "epoch": 0.4031062980906241, "grad_norm": 1.5246452796119088, "learning_rate": 1.9379414607934894e-05, "loss": 0.6554, "step": 2829 }, { "epoch": 0.4032487888287261, "grad_norm": 1.3239056712243134, "learning_rate": 1.9378551838224283e-05, "loss": 0.6738, "step": 2830 }, { "epoch": 0.40339127956682813, "grad_norm": 1.5496012762261249, "learning_rate": 1.937768848842913e-05, "loss": 0.7546, "step": 2831 }, { "epoch": 0.4035337703049302, "grad_norm": 1.6803527644484253, "learning_rate": 1.9376824558602836e-05, "loss": 0.6445, "step": 2832 }, { "epoch": 0.4036762610430322, "grad_norm": 2.657936537012122, "learning_rate": 1.9375960048798835e-05, "loss": 0.6819, "step": 2833 }, { "epoch": 0.40381875178113424, "grad_norm": 1.4744963237390556, "learning_rate": 1.93750949590706e-05, "loss": 0.704, "step": 2834 }, { "epoch": 0.40396124251923626, "grad_norm": 1.365000332367714, "learning_rate": 1.937422928947164e-05, "loss": 0.7284, "step": 2835 }, { "epoch": 0.4041037332573383, "grad_norm": 1.9506579641460244, "learning_rate": 1.93733630400555e-05, "loss": 0.6832, "step": 2836 }, { "epoch": 0.4042462239954403, "grad_norm": 1.4909255242081307, "learning_rate": 1.9372496210875754e-05, "loss": 0.668, "step": 2837 }, { "epoch": 0.4043887147335423, "grad_norm": 1.5239440498374797, "learning_rate": 1.937162880198602e-05, "loss": 0.7277, "step": 2838 }, { "epoch": 0.40453120547164434, "grad_norm": 1.9183466482421199, "learning_rate": 1.9370760813439954e-05, "loss": 0.6962, "step": 2839 }, { "epoch": 0.40467369620974636, "grad_norm": 1.4476843542721252, "learning_rate": 1.9369892245291235e-05, "loss": 0.607, "step": 2840 }, { "epoch": 0.4048161869478484, "grad_norm": 1.4171261416231813, "learning_rate": 1.936902309759359e-05, "loss": 0.658, "step": 2841 }, { "epoch": 0.4049586776859504, "grad_norm": 1.4766928445575735, "learning_rate": 1.9368153370400776e-05, "loss": 0.7145, "step": 2842 }, { "epoch": 0.4051011684240524, "grad_norm": 1.4763784784334026, "learning_rate": 1.9367283063766592e-05, "loss": 0.6828, "step": 2843 }, { "epoch": 0.40524365916215443, "grad_norm": 1.4144040077424846, "learning_rate": 1.9366412177744864e-05, "loss": 0.6587, "step": 2844 }, { "epoch": 0.4053861499002565, "grad_norm": 1.4424455801592175, "learning_rate": 1.936554071238946e-05, "loss": 0.7941, "step": 2845 }, { "epoch": 0.40552864063835853, "grad_norm": 1.4502149714291603, "learning_rate": 1.9364668667754284e-05, "loss": 0.7246, "step": 2846 }, { "epoch": 0.40567113137646055, "grad_norm": 1.3467700855624645, "learning_rate": 1.9363796043893266e-05, "loss": 0.6365, "step": 2847 }, { "epoch": 0.40581362211456257, "grad_norm": 1.689670333251665, "learning_rate": 1.936292284086039e-05, "loss": 0.7281, "step": 2848 }, { "epoch": 0.4059561128526646, "grad_norm": 1.5291910984815305, "learning_rate": 1.936204905870966e-05, "loss": 0.643, "step": 2849 }, { "epoch": 0.4060986035907666, "grad_norm": 1.4638297177037607, "learning_rate": 1.936117469749512e-05, "loss": 0.6962, "step": 2850 }, { "epoch": 0.4062410943288686, "grad_norm": 1.4611635626470547, "learning_rate": 1.9360299757270856e-05, "loss": 0.6437, "step": 2851 }, { "epoch": 0.40638358506697064, "grad_norm": 1.7770814782507118, "learning_rate": 1.935942423809098e-05, "loss": 0.7599, "step": 2852 }, { "epoch": 0.40652607580507266, "grad_norm": 1.8901702428440454, "learning_rate": 1.935854814000965e-05, "loss": 0.7158, "step": 2853 }, { "epoch": 0.4066685665431747, "grad_norm": 1.4345029106409324, "learning_rate": 1.935767146308105e-05, "loss": 0.7424, "step": 2854 }, { "epoch": 0.4068110572812767, "grad_norm": 1.6581249386194639, "learning_rate": 1.935679420735941e-05, "loss": 0.7399, "step": 2855 }, { "epoch": 0.4069535480193787, "grad_norm": 1.5769603754214794, "learning_rate": 1.9355916372898983e-05, "loss": 0.7026, "step": 2856 }, { "epoch": 0.40709603875748074, "grad_norm": 1.55987412438134, "learning_rate": 1.9355037959754074e-05, "loss": 0.7085, "step": 2857 }, { "epoch": 0.4072385294955828, "grad_norm": 1.9928197462729427, "learning_rate": 1.9354158967979003e-05, "loss": 0.6975, "step": 2858 }, { "epoch": 0.40738102023368483, "grad_norm": 1.6656129520256862, "learning_rate": 1.9353279397628147e-05, "loss": 0.5869, "step": 2859 }, { "epoch": 0.40752351097178685, "grad_norm": 1.5535087111998198, "learning_rate": 1.935239924875591e-05, "loss": 0.7339, "step": 2860 }, { "epoch": 0.40766600170988887, "grad_norm": 1.4535342069959978, "learning_rate": 1.9351518521416723e-05, "loss": 0.6114, "step": 2861 }, { "epoch": 0.4078084924479909, "grad_norm": 1.569411907203796, "learning_rate": 1.9350637215665066e-05, "loss": 0.7033, "step": 2862 }, { "epoch": 0.4079509831860929, "grad_norm": 1.5592704275728846, "learning_rate": 1.9349755331555454e-05, "loss": 0.6923, "step": 2863 }, { "epoch": 0.4080934739241949, "grad_norm": 1.5633273170616497, "learning_rate": 1.9348872869142425e-05, "loss": 0.7729, "step": 2864 }, { "epoch": 0.40823596466229695, "grad_norm": 1.5350591630758417, "learning_rate": 1.9347989828480566e-05, "loss": 0.7322, "step": 2865 }, { "epoch": 0.40837845540039897, "grad_norm": 1.537136736733423, "learning_rate": 1.9347106209624496e-05, "loss": 0.7259, "step": 2866 }, { "epoch": 0.408520946138501, "grad_norm": 1.9176548994078861, "learning_rate": 1.9346222012628866e-05, "loss": 0.7943, "step": 2867 }, { "epoch": 0.408663436876603, "grad_norm": 1.5506098571389078, "learning_rate": 1.9345337237548368e-05, "loss": 0.7326, "step": 2868 }, { "epoch": 0.408805927614705, "grad_norm": 1.4433225231899105, "learning_rate": 1.9344451884437722e-05, "loss": 0.6643, "step": 2869 }, { "epoch": 0.40894841835280704, "grad_norm": 1.5788557574617856, "learning_rate": 1.9343565953351696e-05, "loss": 0.6967, "step": 2870 }, { "epoch": 0.4090909090909091, "grad_norm": 1.5759085325431625, "learning_rate": 1.9342679444345088e-05, "loss": 0.6344, "step": 2871 }, { "epoch": 0.40923339982901114, "grad_norm": 1.473876287321162, "learning_rate": 1.9341792357472718e-05, "loss": 0.6603, "step": 2872 }, { "epoch": 0.40937589056711315, "grad_norm": 1.7443691431211268, "learning_rate": 1.934090469278947e-05, "loss": 0.7131, "step": 2873 }, { "epoch": 0.4095183813052152, "grad_norm": 1.6947252550043348, "learning_rate": 1.934001645035024e-05, "loss": 0.7204, "step": 2874 }, { "epoch": 0.4096608720433172, "grad_norm": 2.221512265754538, "learning_rate": 1.9339127630209965e-05, "loss": 0.6282, "step": 2875 }, { "epoch": 0.4098033627814192, "grad_norm": 1.4517580960067742, "learning_rate": 1.9338238232423626e-05, "loss": 0.757, "step": 2876 }, { "epoch": 0.40994585351952123, "grad_norm": 1.470125438896509, "learning_rate": 1.9337348257046236e-05, "loss": 0.7302, "step": 2877 }, { "epoch": 0.41008834425762325, "grad_norm": 1.4213610437937554, "learning_rate": 1.9336457704132837e-05, "loss": 0.6331, "step": 2878 }, { "epoch": 0.41023083499572527, "grad_norm": 1.6441037789670976, "learning_rate": 1.933556657373851e-05, "loss": 0.7486, "step": 2879 }, { "epoch": 0.4103733257338273, "grad_norm": 1.3825391173144626, "learning_rate": 1.933467486591838e-05, "loss": 0.6823, "step": 2880 }, { "epoch": 0.4105158164719293, "grad_norm": 1.6236353619884063, "learning_rate": 1.9333782580727596e-05, "loss": 0.6416, "step": 2881 }, { "epoch": 0.4106583072100313, "grad_norm": 1.3836892903787146, "learning_rate": 1.933288971822135e-05, "loss": 0.6675, "step": 2882 }, { "epoch": 0.41080079794813334, "grad_norm": 1.5884199709779083, "learning_rate": 1.933199627845487e-05, "loss": 0.7439, "step": 2883 }, { "epoch": 0.4109432886862354, "grad_norm": 1.4317008236299764, "learning_rate": 1.933110226148341e-05, "loss": 0.6351, "step": 2884 }, { "epoch": 0.41108577942433744, "grad_norm": 1.6523489304665075, "learning_rate": 1.9330207667362273e-05, "loss": 0.7046, "step": 2885 }, { "epoch": 0.41122827016243946, "grad_norm": 1.5154250037750445, "learning_rate": 1.9329312496146792e-05, "loss": 0.6702, "step": 2886 }, { "epoch": 0.4113707609005415, "grad_norm": 1.6146794133487754, "learning_rate": 1.932841674789233e-05, "loss": 0.834, "step": 2887 }, { "epoch": 0.4115132516386435, "grad_norm": 1.4118586428006406, "learning_rate": 1.9327520422654298e-05, "loss": 0.6339, "step": 2888 }, { "epoch": 0.4116557423767455, "grad_norm": 1.376255665474216, "learning_rate": 1.932662352048813e-05, "loss": 0.7484, "step": 2889 }, { "epoch": 0.41179823311484753, "grad_norm": 1.5270916725705124, "learning_rate": 1.9325726041449305e-05, "loss": 0.6826, "step": 2890 }, { "epoch": 0.41194072385294955, "grad_norm": 1.8941684807538932, "learning_rate": 1.9324827985593333e-05, "loss": 0.6847, "step": 2891 }, { "epoch": 0.41208321459105157, "grad_norm": 1.793020778560945, "learning_rate": 1.9323929352975755e-05, "loss": 0.6492, "step": 2892 }, { "epoch": 0.4122257053291536, "grad_norm": 1.4230537436476633, "learning_rate": 1.9323030143652166e-05, "loss": 0.7177, "step": 2893 }, { "epoch": 0.4123681960672556, "grad_norm": 1.567850589871709, "learning_rate": 1.9322130357678176e-05, "loss": 0.7496, "step": 2894 }, { "epoch": 0.41251068680535763, "grad_norm": 1.6738664479592151, "learning_rate": 1.9321229995109438e-05, "loss": 0.7277, "step": 2895 }, { "epoch": 0.41265317754345965, "grad_norm": 1.5255531610563449, "learning_rate": 1.9320329056001642e-05, "loss": 0.748, "step": 2896 }, { "epoch": 0.4127956682815617, "grad_norm": 1.383711926818311, "learning_rate": 1.9319427540410517e-05, "loss": 0.692, "step": 2897 }, { "epoch": 0.41293815901966374, "grad_norm": 1.5325962528658543, "learning_rate": 1.9318525448391822e-05, "loss": 0.7076, "step": 2898 }, { "epoch": 0.41308064975776576, "grad_norm": 1.3349125260523145, "learning_rate": 1.931762278000135e-05, "loss": 0.6681, "step": 2899 }, { "epoch": 0.4132231404958678, "grad_norm": 1.8240359105704516, "learning_rate": 1.9316719535294935e-05, "loss": 0.6804, "step": 2900 }, { "epoch": 0.4133656312339698, "grad_norm": 1.548747372873528, "learning_rate": 1.9315815714328448e-05, "loss": 0.6367, "step": 2901 }, { "epoch": 0.4135081219720718, "grad_norm": 1.333762025857469, "learning_rate": 1.931491131715779e-05, "loss": 0.6474, "step": 2902 }, { "epoch": 0.41365061271017384, "grad_norm": 1.4014408564296266, "learning_rate": 1.9314006343838898e-05, "loss": 0.6901, "step": 2903 }, { "epoch": 0.41379310344827586, "grad_norm": 1.316662689652931, "learning_rate": 1.931310079442775e-05, "loss": 0.7203, "step": 2904 }, { "epoch": 0.4139355941863779, "grad_norm": 1.5837779804856336, "learning_rate": 1.9312194668980352e-05, "loss": 0.6789, "step": 2905 }, { "epoch": 0.4140780849244799, "grad_norm": 1.4452977722334222, "learning_rate": 1.9311287967552753e-05, "loss": 0.7281, "step": 2906 }, { "epoch": 0.4142205756625819, "grad_norm": 1.4656498117556054, "learning_rate": 1.931038069020104e-05, "loss": 0.6995, "step": 2907 }, { "epoch": 0.41436306640068393, "grad_norm": 1.4751173730171603, "learning_rate": 1.9309472836981318e-05, "loss": 0.6822, "step": 2908 }, { "epoch": 0.41450555713878595, "grad_norm": 1.365207562526706, "learning_rate": 1.9308564407949748e-05, "loss": 0.6838, "step": 2909 }, { "epoch": 0.414648047876888, "grad_norm": 1.5401871784078984, "learning_rate": 1.9307655403162514e-05, "loss": 0.6607, "step": 2910 }, { "epoch": 0.41479053861499005, "grad_norm": 1.3482938598049568, "learning_rate": 1.9306745822675846e-05, "loss": 0.6955, "step": 2911 }, { "epoch": 0.41493302935309206, "grad_norm": 1.4843781942564118, "learning_rate": 1.9305835666545998e-05, "loss": 0.7459, "step": 2912 }, { "epoch": 0.4150755200911941, "grad_norm": 1.4478562049835328, "learning_rate": 1.930492493482927e-05, "loss": 0.6355, "step": 2913 }, { "epoch": 0.4152180108292961, "grad_norm": 1.5486845596168328, "learning_rate": 1.9304013627581987e-05, "loss": 0.6691, "step": 2914 }, { "epoch": 0.4153605015673981, "grad_norm": 1.5219996674005531, "learning_rate": 1.930310174486052e-05, "loss": 0.6461, "step": 2915 }, { "epoch": 0.41550299230550014, "grad_norm": 1.492421986772547, "learning_rate": 1.930218928672127e-05, "loss": 0.7388, "step": 2916 }, { "epoch": 0.41564548304360216, "grad_norm": 1.421439629173983, "learning_rate": 1.9301276253220668e-05, "loss": 0.6977, "step": 2917 }, { "epoch": 0.4157879737817042, "grad_norm": 1.4784817885015953, "learning_rate": 1.9300362644415197e-05, "loss": 0.7955, "step": 2918 }, { "epoch": 0.4159304645198062, "grad_norm": 1.4126252226276672, "learning_rate": 1.9299448460361365e-05, "loss": 0.6415, "step": 2919 }, { "epoch": 0.4160729552579082, "grad_norm": 1.5516258427563274, "learning_rate": 1.929853370111571e-05, "loss": 0.6515, "step": 2920 }, { "epoch": 0.41621544599601024, "grad_norm": 1.402390785206359, "learning_rate": 1.929761836673482e-05, "loss": 0.6944, "step": 2921 }, { "epoch": 0.41635793673411226, "grad_norm": 1.36798701974374, "learning_rate": 1.9296702457275297e-05, "loss": 0.7355, "step": 2922 }, { "epoch": 0.41650042747221433, "grad_norm": 1.4950854305701202, "learning_rate": 1.9295785972793807e-05, "loss": 0.6982, "step": 2923 }, { "epoch": 0.41664291821031635, "grad_norm": 1.4097400288358677, "learning_rate": 1.9294868913347028e-05, "loss": 0.776, "step": 2924 }, { "epoch": 0.41678540894841837, "grad_norm": 1.949336033860845, "learning_rate": 1.929395127899169e-05, "loss": 0.6642, "step": 2925 }, { "epoch": 0.4169278996865204, "grad_norm": 1.645469117685956, "learning_rate": 1.929303306978454e-05, "loss": 0.6981, "step": 2926 }, { "epoch": 0.4170703904246224, "grad_norm": 1.4563055882428204, "learning_rate": 1.9292114285782377e-05, "loss": 0.5976, "step": 2927 }, { "epoch": 0.4172128811627244, "grad_norm": 1.4260804920011767, "learning_rate": 1.929119492704203e-05, "loss": 0.6931, "step": 2928 }, { "epoch": 0.41735537190082644, "grad_norm": 1.4002535076366034, "learning_rate": 1.929027499362036e-05, "loss": 0.7042, "step": 2929 }, { "epoch": 0.41749786263892846, "grad_norm": 1.3860969322951657, "learning_rate": 1.9289354485574274e-05, "loss": 0.6466, "step": 2930 }, { "epoch": 0.4176403533770305, "grad_norm": 1.5466522667876692, "learning_rate": 1.9288433402960702e-05, "loss": 0.6838, "step": 2931 }, { "epoch": 0.4177828441151325, "grad_norm": 1.530794675120072, "learning_rate": 1.9287511745836615e-05, "loss": 0.7669, "step": 2932 }, { "epoch": 0.4179253348532345, "grad_norm": 1.4972308630027558, "learning_rate": 1.9286589514259024e-05, "loss": 0.6695, "step": 2933 }, { "epoch": 0.41806782559133654, "grad_norm": 1.50017694865799, "learning_rate": 1.9285666708284967e-05, "loss": 0.7473, "step": 2934 }, { "epoch": 0.4182103163294386, "grad_norm": 1.7048429857274194, "learning_rate": 1.9284743327971523e-05, "loss": 0.6604, "step": 2935 }, { "epoch": 0.41835280706754063, "grad_norm": 1.528400426704983, "learning_rate": 1.92838193733758e-05, "loss": 0.7098, "step": 2936 }, { "epoch": 0.41849529780564265, "grad_norm": 1.6937818551024002, "learning_rate": 1.9282894844554957e-05, "loss": 0.7827, "step": 2937 }, { "epoch": 0.41863778854374467, "grad_norm": 1.5942816636317692, "learning_rate": 1.9281969741566173e-05, "loss": 0.6548, "step": 2938 }, { "epoch": 0.4187802792818467, "grad_norm": 1.435698710520952, "learning_rate": 1.9281044064466665e-05, "loss": 0.7107, "step": 2939 }, { "epoch": 0.4189227700199487, "grad_norm": 1.4610135484833855, "learning_rate": 1.928011781331369e-05, "loss": 0.6302, "step": 2940 }, { "epoch": 0.41906526075805073, "grad_norm": 1.483112582940361, "learning_rate": 1.927919098816454e-05, "loss": 0.722, "step": 2941 }, { "epoch": 0.41920775149615275, "grad_norm": 1.515253903451657, "learning_rate": 1.927826358907654e-05, "loss": 0.6836, "step": 2942 }, { "epoch": 0.41935024223425477, "grad_norm": 1.5253196129586262, "learning_rate": 1.9277335616107054e-05, "loss": 0.7535, "step": 2943 }, { "epoch": 0.4194927329723568, "grad_norm": 1.5926453609438156, "learning_rate": 1.9276407069313475e-05, "loss": 0.7244, "step": 2944 }, { "epoch": 0.4196352237104588, "grad_norm": 1.399457308835034, "learning_rate": 1.927547794875324e-05, "loss": 0.6285, "step": 2945 }, { "epoch": 0.4197777144485608, "grad_norm": 1.4635478688068022, "learning_rate": 1.9274548254483817e-05, "loss": 0.7248, "step": 2946 }, { "epoch": 0.41992020518666284, "grad_norm": 1.5906877387707372, "learning_rate": 1.9273617986562704e-05, "loss": 0.7696, "step": 2947 }, { "epoch": 0.4200626959247649, "grad_norm": 1.4891021495925432, "learning_rate": 1.9272687145047447e-05, "loss": 0.6519, "step": 2948 }, { "epoch": 0.42020518666286694, "grad_norm": 1.366328220795296, "learning_rate": 1.9271755729995617e-05, "loss": 0.5889, "step": 2949 }, { "epoch": 0.42034767740096896, "grad_norm": 1.5955683183060938, "learning_rate": 1.9270823741464827e-05, "loss": 0.6464, "step": 2950 }, { "epoch": 0.420490168139071, "grad_norm": 1.4036660033546706, "learning_rate": 1.9269891179512718e-05, "loss": 0.6789, "step": 2951 }, { "epoch": 0.420632658877173, "grad_norm": 1.4304449680777813, "learning_rate": 1.9268958044196976e-05, "loss": 0.6415, "step": 2952 }, { "epoch": 0.420775149615275, "grad_norm": 1.4180847428040797, "learning_rate": 1.9268024335575312e-05, "loss": 0.7381, "step": 2953 }, { "epoch": 0.42091764035337703, "grad_norm": 1.6001738543922812, "learning_rate": 1.9267090053705484e-05, "loss": 0.706, "step": 2954 }, { "epoch": 0.42106013109147905, "grad_norm": 1.4648891341546308, "learning_rate": 1.9266155198645275e-05, "loss": 0.6965, "step": 2955 }, { "epoch": 0.42120262182958107, "grad_norm": 1.288708760962464, "learning_rate": 1.926521977045251e-05, "loss": 0.6557, "step": 2956 }, { "epoch": 0.4213451125676831, "grad_norm": 1.4977105638372186, "learning_rate": 1.9264283769185047e-05, "loss": 0.6747, "step": 2957 }, { "epoch": 0.4214876033057851, "grad_norm": 1.3973227666676598, "learning_rate": 1.9263347194900778e-05, "loss": 0.7731, "step": 2958 }, { "epoch": 0.4216300940438871, "grad_norm": 4.434577507425651, "learning_rate": 1.9262410047657636e-05, "loss": 0.7368, "step": 2959 }, { "epoch": 0.42177258478198915, "grad_norm": 1.5667344338327487, "learning_rate": 1.9261472327513582e-05, "loss": 0.6129, "step": 2960 }, { "epoch": 0.4219150755200912, "grad_norm": 1.3413904009056017, "learning_rate": 1.9260534034526617e-05, "loss": 0.7563, "step": 2961 }, { "epoch": 0.42205756625819324, "grad_norm": 1.3248547997652085, "learning_rate": 1.9259595168754778e-05, "loss": 0.8165, "step": 2962 }, { "epoch": 0.42220005699629526, "grad_norm": 1.3876579867824037, "learning_rate": 1.9258655730256136e-05, "loss": 0.6713, "step": 2963 }, { "epoch": 0.4223425477343973, "grad_norm": 1.4079956293862317, "learning_rate": 1.9257715719088798e-05, "loss": 0.6743, "step": 2964 }, { "epoch": 0.4224850384724993, "grad_norm": 1.4302188502308575, "learning_rate": 1.92567751353109e-05, "loss": 0.6894, "step": 2965 }, { "epoch": 0.4226275292106013, "grad_norm": 1.4220091700795163, "learning_rate": 1.9255833978980626e-05, "loss": 0.7898, "step": 2966 }, { "epoch": 0.42277001994870334, "grad_norm": 1.3130986326216687, "learning_rate": 1.9254892250156184e-05, "loss": 0.6323, "step": 2967 }, { "epoch": 0.42291251068680535, "grad_norm": 1.5456224512974137, "learning_rate": 1.9253949948895828e-05, "loss": 0.7249, "step": 2968 }, { "epoch": 0.4230550014249074, "grad_norm": 1.886334651199159, "learning_rate": 1.9253007075257833e-05, "loss": 0.6671, "step": 2969 }, { "epoch": 0.4231974921630094, "grad_norm": 1.469324695634031, "learning_rate": 1.9252063629300526e-05, "loss": 0.7196, "step": 2970 }, { "epoch": 0.4233399829011114, "grad_norm": 2.025922500229249, "learning_rate": 1.9251119611082255e-05, "loss": 0.6853, "step": 2971 }, { "epoch": 0.42348247363921343, "grad_norm": 1.4622059568694026, "learning_rate": 1.9250175020661416e-05, "loss": 0.6907, "step": 2972 }, { "epoch": 0.42362496437731545, "grad_norm": 1.3441167453021337, "learning_rate": 1.924922985809643e-05, "loss": 0.6154, "step": 2973 }, { "epoch": 0.4237674551154175, "grad_norm": 1.4581908311667064, "learning_rate": 1.9248284123445755e-05, "loss": 0.6922, "step": 2974 }, { "epoch": 0.42390994585351954, "grad_norm": 1.561368865282406, "learning_rate": 1.924733781676789e-05, "loss": 0.6186, "step": 2975 }, { "epoch": 0.42405243659162156, "grad_norm": 1.4402654556436767, "learning_rate": 1.9246390938121368e-05, "loss": 0.7381, "step": 2976 }, { "epoch": 0.4241949273297236, "grad_norm": 1.6056410347442567, "learning_rate": 1.924544348756475e-05, "loss": 0.704, "step": 2977 }, { "epoch": 0.4243374180678256, "grad_norm": 1.4092402903966477, "learning_rate": 1.9244495465156645e-05, "loss": 0.7391, "step": 2978 }, { "epoch": 0.4244799088059276, "grad_norm": 1.5032673014418176, "learning_rate": 1.9243546870955684e-05, "loss": 0.702, "step": 2979 }, { "epoch": 0.42462239954402964, "grad_norm": 1.317490413383949, "learning_rate": 1.9242597705020545e-05, "loss": 0.7012, "step": 2980 }, { "epoch": 0.42476489028213166, "grad_norm": 1.4507635940914747, "learning_rate": 1.924164796740993e-05, "loss": 0.6311, "step": 2981 }, { "epoch": 0.4249073810202337, "grad_norm": 1.48707434219198, "learning_rate": 1.924069765818259e-05, "loss": 0.7198, "step": 2982 }, { "epoch": 0.4250498717583357, "grad_norm": 1.69680212989863, "learning_rate": 1.9239746777397295e-05, "loss": 0.7474, "step": 2983 }, { "epoch": 0.4251923624964377, "grad_norm": 1.4642499679160323, "learning_rate": 1.9238795325112867e-05, "loss": 0.6791, "step": 2984 }, { "epoch": 0.42533485323453973, "grad_norm": 1.4832271380249593, "learning_rate": 1.9237843301388155e-05, "loss": 0.7321, "step": 2985 }, { "epoch": 0.42547734397264175, "grad_norm": 1.5045063230704847, "learning_rate": 1.9236890706282036e-05, "loss": 0.5912, "step": 2986 }, { "epoch": 0.4256198347107438, "grad_norm": 1.7319707906183217, "learning_rate": 1.9235937539853438e-05, "loss": 0.7477, "step": 2987 }, { "epoch": 0.42576232544884585, "grad_norm": 1.4439085558657045, "learning_rate": 1.923498380216131e-05, "loss": 0.7025, "step": 2988 }, { "epoch": 0.42590481618694787, "grad_norm": 1.5969183988443358, "learning_rate": 1.923402949326465e-05, "loss": 0.7161, "step": 2989 }, { "epoch": 0.4260473069250499, "grad_norm": 1.3666026423163062, "learning_rate": 1.923307461322248e-05, "loss": 0.6766, "step": 2990 }, { "epoch": 0.4261897976631519, "grad_norm": 1.5251893827223306, "learning_rate": 1.9232119162093863e-05, "loss": 0.7644, "step": 2991 }, { "epoch": 0.4263322884012539, "grad_norm": 1.540547029289854, "learning_rate": 1.9231163139937895e-05, "loss": 0.7261, "step": 2992 }, { "epoch": 0.42647477913935594, "grad_norm": 1.5804854194201259, "learning_rate": 1.9230206546813707e-05, "loss": 0.7925, "step": 2993 }, { "epoch": 0.42661726987745796, "grad_norm": 1.4874508254450427, "learning_rate": 1.9229249382780467e-05, "loss": 0.6022, "step": 2994 }, { "epoch": 0.42675976061556, "grad_norm": 1.3870669008017849, "learning_rate": 1.9228291647897377e-05, "loss": 0.6965, "step": 2995 }, { "epoch": 0.426902251353662, "grad_norm": 1.773997381344437, "learning_rate": 1.9227333342223677e-05, "loss": 0.6303, "step": 2996 }, { "epoch": 0.427044742091764, "grad_norm": 1.4328817873947, "learning_rate": 1.922637446581864e-05, "loss": 0.6319, "step": 2997 }, { "epoch": 0.42718723282986604, "grad_norm": 1.3687539796026706, "learning_rate": 1.9225415018741578e-05, "loss": 0.6248, "step": 2998 }, { "epoch": 0.42732972356796806, "grad_norm": 1.6227863988820423, "learning_rate": 1.9224455001051827e-05, "loss": 0.6577, "step": 2999 }, { "epoch": 0.42747221430607013, "grad_norm": 1.5177353892488068, "learning_rate": 1.922349441280877e-05, "loss": 0.7298, "step": 3000 }, { "epoch": 0.42761470504417215, "grad_norm": 1.6484163141478057, "learning_rate": 1.9222533254071827e-05, "loss": 0.7037, "step": 3001 }, { "epoch": 0.42775719578227417, "grad_norm": 1.3932003737402705, "learning_rate": 1.922157152490044e-05, "loss": 0.6608, "step": 3002 }, { "epoch": 0.4278996865203762, "grad_norm": 4.132259316780323, "learning_rate": 1.9220609225354093e-05, "loss": 0.7591, "step": 3003 }, { "epoch": 0.4280421772584782, "grad_norm": 1.9651272949151655, "learning_rate": 1.9219646355492315e-05, "loss": 0.6839, "step": 3004 }, { "epoch": 0.4281846679965802, "grad_norm": 1.5404935222551042, "learning_rate": 1.921868291537466e-05, "loss": 0.7439, "step": 3005 }, { "epoch": 0.42832715873468225, "grad_norm": 1.4583522467778998, "learning_rate": 1.9217718905060708e-05, "loss": 0.6618, "step": 3006 }, { "epoch": 0.42846964947278426, "grad_norm": 1.5169167141602928, "learning_rate": 1.92167543246101e-05, "loss": 0.6992, "step": 3007 }, { "epoch": 0.4286121402108863, "grad_norm": 1.488145232504805, "learning_rate": 1.921578917408249e-05, "loss": 0.6722, "step": 3008 }, { "epoch": 0.4287546309489883, "grad_norm": 1.4471404634499951, "learning_rate": 1.9214823453537568e-05, "loss": 0.6992, "step": 3009 }, { "epoch": 0.4288971216870903, "grad_norm": 1.931929857168607, "learning_rate": 1.921385716303508e-05, "loss": 0.7383, "step": 3010 }, { "epoch": 0.42903961242519234, "grad_norm": 1.6393700268072575, "learning_rate": 1.921289030263479e-05, "loss": 0.6361, "step": 3011 }, { "epoch": 0.42918210316329436, "grad_norm": 2.277170654685449, "learning_rate": 1.921192287239649e-05, "loss": 0.6914, "step": 3012 }, { "epoch": 0.42932459390139643, "grad_norm": 1.4110244115551567, "learning_rate": 1.921095487238003e-05, "loss": 0.7095, "step": 3013 }, { "epoch": 0.42946708463949845, "grad_norm": 1.4000205347509482, "learning_rate": 1.9209986302645274e-05, "loss": 0.6264, "step": 3014 }, { "epoch": 0.42960957537760047, "grad_norm": 1.5058380417245691, "learning_rate": 1.9209017163252138e-05, "loss": 0.6407, "step": 3015 }, { "epoch": 0.4297520661157025, "grad_norm": 1.5726573111356588, "learning_rate": 1.9208047454260556e-05, "loss": 0.7025, "step": 3016 }, { "epoch": 0.4298945568538045, "grad_norm": 1.6847301340870766, "learning_rate": 1.920707717573052e-05, "loss": 0.7282, "step": 3017 }, { "epoch": 0.43003704759190653, "grad_norm": 1.4763289835490234, "learning_rate": 1.920610632772203e-05, "loss": 0.7041, "step": 3018 }, { "epoch": 0.43017953833000855, "grad_norm": 1.5423667318895098, "learning_rate": 1.920513491029514e-05, "loss": 0.7936, "step": 3019 }, { "epoch": 0.43032202906811057, "grad_norm": 1.51739785395709, "learning_rate": 1.920416292350994e-05, "loss": 0.6251, "step": 3020 }, { "epoch": 0.4304645198062126, "grad_norm": 1.5522556897577509, "learning_rate": 1.9203190367426547e-05, "loss": 0.6359, "step": 3021 }, { "epoch": 0.4306070105443146, "grad_norm": 1.4560771723784884, "learning_rate": 1.920221724210511e-05, "loss": 0.7307, "step": 3022 }, { "epoch": 0.4307495012824166, "grad_norm": 2.0806343928922373, "learning_rate": 1.9201243547605824e-05, "loss": 0.6695, "step": 3023 }, { "epoch": 0.43089199202051864, "grad_norm": 1.6170834283825237, "learning_rate": 1.9200269283988912e-05, "loss": 0.675, "step": 3024 }, { "epoch": 0.43103448275862066, "grad_norm": 1.3440462419639119, "learning_rate": 1.9199294451314636e-05, "loss": 0.7201, "step": 3025 }, { "epoch": 0.43117697349672274, "grad_norm": 1.6476389687323842, "learning_rate": 1.9198319049643294e-05, "loss": 0.6963, "step": 3026 }, { "epoch": 0.43131946423482476, "grad_norm": 1.381459080191419, "learning_rate": 1.9197343079035212e-05, "loss": 0.6804, "step": 3027 }, { "epoch": 0.4314619549729268, "grad_norm": 1.4968445604825211, "learning_rate": 1.9196366539550756e-05, "loss": 0.6794, "step": 3028 }, { "epoch": 0.4316044457110288, "grad_norm": 1.587104277918951, "learning_rate": 1.919538943125033e-05, "loss": 0.6836, "step": 3029 }, { "epoch": 0.4317469364491308, "grad_norm": 1.3414028508294464, "learning_rate": 1.9194411754194373e-05, "loss": 0.6411, "step": 3030 }, { "epoch": 0.43188942718723283, "grad_norm": 1.5426581653355165, "learning_rate": 1.919343350844335e-05, "loss": 0.6879, "step": 3031 }, { "epoch": 0.43203191792533485, "grad_norm": 1.567747509943601, "learning_rate": 1.919245469405777e-05, "loss": 0.7022, "step": 3032 }, { "epoch": 0.43217440866343687, "grad_norm": 1.3092217956518302, "learning_rate": 1.919147531109818e-05, "loss": 0.7006, "step": 3033 }, { "epoch": 0.4323168994015389, "grad_norm": 1.447683258856694, "learning_rate": 1.9190495359625146e-05, "loss": 0.6797, "step": 3034 }, { "epoch": 0.4324593901396409, "grad_norm": 1.4498537637816538, "learning_rate": 1.918951483969929e-05, "loss": 0.7875, "step": 3035 }, { "epoch": 0.43260188087774293, "grad_norm": 1.596377895762053, "learning_rate": 1.9188533751381255e-05, "loss": 0.676, "step": 3036 }, { "epoch": 0.43274437161584495, "grad_norm": 1.6039861829862245, "learning_rate": 1.918755209473173e-05, "loss": 0.675, "step": 3037 }, { "epoch": 0.43288686235394697, "grad_norm": 1.4015648863240466, "learning_rate": 1.918656986981142e-05, "loss": 0.718, "step": 3038 }, { "epoch": 0.43302935309204904, "grad_norm": 1.486927759735442, "learning_rate": 1.9185587076681086e-05, "loss": 0.7201, "step": 3039 }, { "epoch": 0.43317184383015106, "grad_norm": 1.490218701472527, "learning_rate": 1.918460371540152e-05, "loss": 0.7237, "step": 3040 }, { "epoch": 0.4333143345682531, "grad_norm": 1.415572751836177, "learning_rate": 1.9183619786033537e-05, "loss": 0.7345, "step": 3041 }, { "epoch": 0.4334568253063551, "grad_norm": 1.377751521330666, "learning_rate": 1.9182635288638e-05, "loss": 0.696, "step": 3042 }, { "epoch": 0.4335993160444571, "grad_norm": 1.4504493783689478, "learning_rate": 1.91816502232758e-05, "loss": 0.6673, "step": 3043 }, { "epoch": 0.43374180678255914, "grad_norm": 1.407149315880607, "learning_rate": 1.9180664590007866e-05, "loss": 0.7303, "step": 3044 }, { "epoch": 0.43388429752066116, "grad_norm": 1.3233291685184152, "learning_rate": 1.9179678388895163e-05, "loss": 0.6722, "step": 3045 }, { "epoch": 0.4340267882587632, "grad_norm": 1.4014784210725244, "learning_rate": 1.917869161999869e-05, "loss": 0.6507, "step": 3046 }, { "epoch": 0.4341692789968652, "grad_norm": 1.3530913147332826, "learning_rate": 1.9177704283379476e-05, "loss": 0.6616, "step": 3047 }, { "epoch": 0.4343117697349672, "grad_norm": 1.585937726708585, "learning_rate": 1.9176716379098597e-05, "loss": 0.7306, "step": 3048 }, { "epoch": 0.43445426047306923, "grad_norm": 2.007917608726145, "learning_rate": 1.9175727907217153e-05, "loss": 0.7055, "step": 3049 }, { "epoch": 0.43459675121117125, "grad_norm": 1.896066489726512, "learning_rate": 1.9174738867796285e-05, "loss": 0.7122, "step": 3050 }, { "epoch": 0.43473924194927327, "grad_norm": 1.4442509599000848, "learning_rate": 1.9173749260897162e-05, "loss": 0.6447, "step": 3051 }, { "epoch": 0.43488173268737534, "grad_norm": 1.8670901827864106, "learning_rate": 1.9172759086581002e-05, "loss": 0.7967, "step": 3052 }, { "epoch": 0.43502422342547736, "grad_norm": 1.5419137754987704, "learning_rate": 1.9171768344909042e-05, "loss": 0.7258, "step": 3053 }, { "epoch": 0.4351667141635794, "grad_norm": 1.8700370105749482, "learning_rate": 1.9170777035942566e-05, "loss": 0.6242, "step": 3054 }, { "epoch": 0.4353092049016814, "grad_norm": 1.556403635762018, "learning_rate": 1.9169785159742892e-05, "loss": 0.6387, "step": 3055 }, { "epoch": 0.4354516956397834, "grad_norm": 1.5864072866461953, "learning_rate": 1.916879271637136e-05, "loss": 0.7844, "step": 3056 }, { "epoch": 0.43559418637788544, "grad_norm": 1.8267652538650312, "learning_rate": 1.916779970588936e-05, "loss": 0.7082, "step": 3057 }, { "epoch": 0.43573667711598746, "grad_norm": 1.5920616130036125, "learning_rate": 1.9166806128358316e-05, "loss": 0.649, "step": 3058 }, { "epoch": 0.4358791678540895, "grad_norm": 1.679137492780933, "learning_rate": 1.9165811983839673e-05, "loss": 0.6448, "step": 3059 }, { "epoch": 0.4360216585921915, "grad_norm": 1.4955001802685837, "learning_rate": 1.9164817272394933e-05, "loss": 0.6833, "step": 3060 }, { "epoch": 0.4361641493302935, "grad_norm": 1.5289409191380896, "learning_rate": 1.916382199408561e-05, "loss": 0.6887, "step": 3061 }, { "epoch": 0.43630664006839553, "grad_norm": 1.5052169915285125, "learning_rate": 1.9162826148973275e-05, "loss": 0.755, "step": 3062 }, { "epoch": 0.43644913080649755, "grad_norm": 2.762194449236582, "learning_rate": 1.9161829737119515e-05, "loss": 0.7054, "step": 3063 }, { "epoch": 0.43659162154459963, "grad_norm": 1.6335900271463308, "learning_rate": 1.9160832758585962e-05, "loss": 0.7499, "step": 3064 }, { "epoch": 0.43673411228270165, "grad_norm": 1.4255218985741136, "learning_rate": 1.9159835213434286e-05, "loss": 0.6135, "step": 3065 }, { "epoch": 0.43687660302080367, "grad_norm": 1.356228211086893, "learning_rate": 1.9158837101726182e-05, "loss": 0.6794, "step": 3066 }, { "epoch": 0.4370190937589057, "grad_norm": 1.4398697141745567, "learning_rate": 1.9157838423523384e-05, "loss": 0.7227, "step": 3067 }, { "epoch": 0.4371615844970077, "grad_norm": 1.4533353690943218, "learning_rate": 1.9156839178887672e-05, "loss": 0.6734, "step": 3068 }, { "epoch": 0.4373040752351097, "grad_norm": 1.3745957770551716, "learning_rate": 1.9155839367880843e-05, "loss": 0.6561, "step": 3069 }, { "epoch": 0.43744656597321174, "grad_norm": 1.9288972845777586, "learning_rate": 1.9154838990564736e-05, "loss": 0.8168, "step": 3070 }, { "epoch": 0.43758905671131376, "grad_norm": 1.4084408704687448, "learning_rate": 1.9153838047001235e-05, "loss": 0.635, "step": 3071 }, { "epoch": 0.4377315474494158, "grad_norm": 1.7139000549168557, "learning_rate": 1.9152836537252245e-05, "loss": 0.6676, "step": 3072 }, { "epoch": 0.4378740381875178, "grad_norm": 1.3743044331456433, "learning_rate": 1.9151834461379712e-05, "loss": 0.5844, "step": 3073 }, { "epoch": 0.4380165289256198, "grad_norm": 1.6611360385335874, "learning_rate": 1.9150831819445617e-05, "loss": 0.7456, "step": 3074 }, { "epoch": 0.43815901966372184, "grad_norm": 1.3147486212292276, "learning_rate": 1.9149828611511978e-05, "loss": 0.6501, "step": 3075 }, { "epoch": 0.43830151040182386, "grad_norm": 1.374725559523574, "learning_rate": 1.9148824837640844e-05, "loss": 0.6682, "step": 3076 }, { "epoch": 0.43844400113992593, "grad_norm": 1.6898976606918596, "learning_rate": 1.91478204978943e-05, "loss": 0.6766, "step": 3077 }, { "epoch": 0.43858649187802795, "grad_norm": 1.484746799965118, "learning_rate": 1.9146815592334462e-05, "loss": 0.5877, "step": 3078 }, { "epoch": 0.43872898261612997, "grad_norm": 1.4522598742014319, "learning_rate": 1.9145810121023494e-05, "loss": 0.6905, "step": 3079 }, { "epoch": 0.438871473354232, "grad_norm": 1.5613310797768556, "learning_rate": 1.9144804084023586e-05, "loss": 0.719, "step": 3080 }, { "epoch": 0.439013964092334, "grad_norm": 1.5370045753077066, "learning_rate": 1.914379748139696e-05, "loss": 0.7312, "step": 3081 }, { "epoch": 0.439156454830436, "grad_norm": 1.5566696676637997, "learning_rate": 1.9142790313205877e-05, "loss": 0.6782, "step": 3082 }, { "epoch": 0.43929894556853805, "grad_norm": 1.559065459300464, "learning_rate": 1.9141782579512632e-05, "loss": 0.765, "step": 3083 }, { "epoch": 0.43944143630664007, "grad_norm": 1.2718963581318476, "learning_rate": 1.9140774280379558e-05, "loss": 0.6072, "step": 3084 }, { "epoch": 0.4395839270447421, "grad_norm": 1.9995180697842738, "learning_rate": 1.913976541586902e-05, "loss": 0.6666, "step": 3085 }, { "epoch": 0.4397264177828441, "grad_norm": 1.4349903384391411, "learning_rate": 1.9138755986043418e-05, "loss": 0.6247, "step": 3086 }, { "epoch": 0.4398689085209461, "grad_norm": 1.5031267592639863, "learning_rate": 1.9137745990965188e-05, "loss": 0.655, "step": 3087 }, { "epoch": 0.44001139925904814, "grad_norm": 1.4956215022437678, "learning_rate": 1.9136735430696797e-05, "loss": 0.6948, "step": 3088 }, { "epoch": 0.44015388999715016, "grad_norm": 2.071505176069469, "learning_rate": 1.9135724305300757e-05, "loss": 0.6698, "step": 3089 }, { "epoch": 0.44029638073525224, "grad_norm": 1.840006885519034, "learning_rate": 1.9134712614839605e-05, "loss": 0.693, "step": 3090 }, { "epoch": 0.44043887147335425, "grad_norm": 1.9817621741270652, "learning_rate": 1.9133700359375913e-05, "loss": 0.6999, "step": 3091 }, { "epoch": 0.4405813622114563, "grad_norm": 1.4879108896537798, "learning_rate": 1.9132687538972297e-05, "loss": 0.7276, "step": 3092 }, { "epoch": 0.4407238529495583, "grad_norm": 1.5627659628180863, "learning_rate": 1.9131674153691398e-05, "loss": 0.7006, "step": 3093 }, { "epoch": 0.4408663436876603, "grad_norm": 1.8666617400325927, "learning_rate": 1.91306602035959e-05, "loss": 0.6214, "step": 3094 }, { "epoch": 0.44100883442576233, "grad_norm": 1.7866837167145908, "learning_rate": 1.912964568874851e-05, "loss": 0.7826, "step": 3095 }, { "epoch": 0.44115132516386435, "grad_norm": 1.6295263330712513, "learning_rate": 1.9128630609211988e-05, "loss": 0.7675, "step": 3096 }, { "epoch": 0.44129381590196637, "grad_norm": 1.562765946729033, "learning_rate": 1.9127614965049117e-05, "loss": 0.7113, "step": 3097 }, { "epoch": 0.4414363066400684, "grad_norm": 1.6735218312027682, "learning_rate": 1.912659875632271e-05, "loss": 0.728, "step": 3098 }, { "epoch": 0.4415787973781704, "grad_norm": 1.6630056599713061, "learning_rate": 1.912558198309563e-05, "loss": 0.6843, "step": 3099 }, { "epoch": 0.4417212881162724, "grad_norm": 1.3888278204826368, "learning_rate": 1.9124564645430762e-05, "loss": 0.6621, "step": 3100 }, { "epoch": 0.44186377885437444, "grad_norm": 1.5041274638768716, "learning_rate": 1.9123546743391036e-05, "loss": 0.6681, "step": 3101 }, { "epoch": 0.44200626959247646, "grad_norm": 1.5234787415445756, "learning_rate": 1.9122528277039403e-05, "loss": 0.6964, "step": 3102 }, { "epoch": 0.44214876033057854, "grad_norm": 1.3805708254069116, "learning_rate": 1.912150924643886e-05, "loss": 0.7325, "step": 3103 }, { "epoch": 0.44229125106868056, "grad_norm": 2.213880163611169, "learning_rate": 1.9120489651652442e-05, "loss": 0.7115, "step": 3104 }, { "epoch": 0.4424337418067826, "grad_norm": 1.3730106220396636, "learning_rate": 1.911946949274321e-05, "loss": 0.6151, "step": 3105 }, { "epoch": 0.4425762325448846, "grad_norm": 1.4390165632594711, "learning_rate": 1.9118448769774257e-05, "loss": 0.7442, "step": 3106 }, { "epoch": 0.4427187232829866, "grad_norm": 1.5561984144297927, "learning_rate": 1.9117427482808727e-05, "loss": 0.7399, "step": 3107 }, { "epoch": 0.44286121402108863, "grad_norm": 1.4920773767108422, "learning_rate": 1.9116405631909786e-05, "loss": 0.6654, "step": 3108 }, { "epoch": 0.44300370475919065, "grad_norm": 1.5754847373215835, "learning_rate": 1.9115383217140633e-05, "loss": 0.7511, "step": 3109 }, { "epoch": 0.44314619549729267, "grad_norm": 1.3722314575544063, "learning_rate": 1.9114360238564514e-05, "loss": 0.7038, "step": 3110 }, { "epoch": 0.4432886862353947, "grad_norm": 1.5767677005479697, "learning_rate": 1.911333669624469e-05, "loss": 0.6792, "step": 3111 }, { "epoch": 0.4434311769734967, "grad_norm": 1.4533548960285345, "learning_rate": 1.9112312590244487e-05, "loss": 0.772, "step": 3112 }, { "epoch": 0.44357366771159873, "grad_norm": 1.3001801043074706, "learning_rate": 1.9111287920627234e-05, "loss": 0.572, "step": 3113 }, { "epoch": 0.44371615844970075, "grad_norm": 1.3975111030185576, "learning_rate": 1.9110262687456316e-05, "loss": 0.6402, "step": 3114 }, { "epoch": 0.44385864918780277, "grad_norm": 1.4263688079721126, "learning_rate": 1.9109236890795143e-05, "loss": 0.6846, "step": 3115 }, { "epoch": 0.44400113992590484, "grad_norm": 1.6565389245436517, "learning_rate": 1.9108210530707167e-05, "loss": 0.7377, "step": 3116 }, { "epoch": 0.44414363066400686, "grad_norm": 1.4885981974044162, "learning_rate": 1.9107183607255863e-05, "loss": 0.6866, "step": 3117 }, { "epoch": 0.4442861214021089, "grad_norm": 1.3024498408465286, "learning_rate": 1.9106156120504758e-05, "loss": 0.6608, "step": 3118 }, { "epoch": 0.4444286121402109, "grad_norm": 1.4824690870306196, "learning_rate": 1.9105128070517395e-05, "loss": 0.7002, "step": 3119 }, { "epoch": 0.4445711028783129, "grad_norm": 1.9309171473410318, "learning_rate": 1.910409945735737e-05, "loss": 0.7236, "step": 3120 }, { "epoch": 0.44471359361641494, "grad_norm": 1.5224654474015407, "learning_rate": 1.9103070281088295e-05, "loss": 0.7237, "step": 3121 }, { "epoch": 0.44485608435451696, "grad_norm": 1.4982741804520512, "learning_rate": 1.9102040541773837e-05, "loss": 0.7627, "step": 3122 }, { "epoch": 0.444998575092619, "grad_norm": 1.5389213445421357, "learning_rate": 1.9101010239477684e-05, "loss": 0.7562, "step": 3123 }, { "epoch": 0.445141065830721, "grad_norm": 1.4178410731052062, "learning_rate": 1.9099979374263564e-05, "loss": 0.7985, "step": 3124 }, { "epoch": 0.445283556568823, "grad_norm": 1.419566134431229, "learning_rate": 1.909894794619523e-05, "loss": 0.6256, "step": 3125 }, { "epoch": 0.44542604730692503, "grad_norm": 1.5290178544137818, "learning_rate": 1.9097915955336487e-05, "loss": 0.6669, "step": 3126 }, { "epoch": 0.44556853804502705, "grad_norm": 1.4444733944878707, "learning_rate": 1.9096883401751166e-05, "loss": 0.6725, "step": 3127 }, { "epoch": 0.44571102878312907, "grad_norm": 1.6013414930048429, "learning_rate": 1.9095850285503125e-05, "loss": 0.7711, "step": 3128 }, { "epoch": 0.44585351952123115, "grad_norm": 1.4879364277013414, "learning_rate": 1.9094816606656272e-05, "loss": 0.6856, "step": 3129 }, { "epoch": 0.44599601025933316, "grad_norm": 1.3370534570566261, "learning_rate": 1.9093782365274543e-05, "loss": 0.6581, "step": 3130 }, { "epoch": 0.4461385009974352, "grad_norm": 1.39068549051544, "learning_rate": 1.9092747561421904e-05, "loss": 0.7111, "step": 3131 }, { "epoch": 0.4462809917355372, "grad_norm": 1.457229008636813, "learning_rate": 1.9091712195162356e-05, "loss": 0.6483, "step": 3132 }, { "epoch": 0.4464234824736392, "grad_norm": 2.404552293369324, "learning_rate": 1.909067626655995e-05, "loss": 0.8067, "step": 3133 }, { "epoch": 0.44656597321174124, "grad_norm": 1.3103686144033277, "learning_rate": 1.908963977567875e-05, "loss": 0.6822, "step": 3134 }, { "epoch": 0.44670846394984326, "grad_norm": 1.5083967765811284, "learning_rate": 1.9088602722582873e-05, "loss": 0.6608, "step": 3135 }, { "epoch": 0.4468509546879453, "grad_norm": 1.5561565262142392, "learning_rate": 1.908756510733646e-05, "loss": 0.6682, "step": 3136 }, { "epoch": 0.4469934454260473, "grad_norm": 1.4369935635681126, "learning_rate": 1.908652693000369e-05, "loss": 0.667, "step": 3137 }, { "epoch": 0.4471359361641493, "grad_norm": 1.2913458201572057, "learning_rate": 1.9085488190648772e-05, "loss": 0.6661, "step": 3138 }, { "epoch": 0.44727842690225134, "grad_norm": 1.4263245084789598, "learning_rate": 1.908444888933596e-05, "loss": 0.6983, "step": 3139 }, { "epoch": 0.44742091764035335, "grad_norm": 1.6146163423830338, "learning_rate": 1.908340902612954e-05, "loss": 0.7161, "step": 3140 }, { "epoch": 0.4475634083784554, "grad_norm": 1.376790084134014, "learning_rate": 1.9082368601093822e-05, "loss": 0.6603, "step": 3141 }, { "epoch": 0.44770589911655745, "grad_norm": 1.350038240257107, "learning_rate": 1.9081327614293163e-05, "loss": 0.6977, "step": 3142 }, { "epoch": 0.44784838985465947, "grad_norm": 1.4711431886740491, "learning_rate": 1.908028606579195e-05, "loss": 0.6518, "step": 3143 }, { "epoch": 0.4479908805927615, "grad_norm": 1.5054238455812794, "learning_rate": 1.9079243955654602e-05, "loss": 0.7427, "step": 3144 }, { "epoch": 0.4481333713308635, "grad_norm": 1.388085778482063, "learning_rate": 1.907820128394558e-05, "loss": 0.6641, "step": 3145 }, { "epoch": 0.4482758620689655, "grad_norm": 1.4546822354857383, "learning_rate": 1.9077158050729375e-05, "loss": 0.6385, "step": 3146 }, { "epoch": 0.44841835280706754, "grad_norm": 1.2697909708036115, "learning_rate": 1.907611425607051e-05, "loss": 0.6841, "step": 3147 }, { "epoch": 0.44856084354516956, "grad_norm": 1.4545889660107927, "learning_rate": 1.9075069900033552e-05, "loss": 0.6344, "step": 3148 }, { "epoch": 0.4487033342832716, "grad_norm": 1.4311206003937318, "learning_rate": 1.907402498268309e-05, "loss": 0.7226, "step": 3149 }, { "epoch": 0.4488458250213736, "grad_norm": 1.4473109837005735, "learning_rate": 1.907297950408376e-05, "loss": 0.714, "step": 3150 }, { "epoch": 0.4489883157594756, "grad_norm": 1.352080632740925, "learning_rate": 1.9071933464300225e-05, "loss": 0.6273, "step": 3151 }, { "epoch": 0.44913080649757764, "grad_norm": 1.4320627691113508, "learning_rate": 1.9070886863397186e-05, "loss": 0.6651, "step": 3152 }, { "epoch": 0.44927329723567966, "grad_norm": 1.4148083026699843, "learning_rate": 1.9069839701439373e-05, "loss": 0.7134, "step": 3153 }, { "epoch": 0.4494157879737817, "grad_norm": 1.5451701168586458, "learning_rate": 1.9068791978491564e-05, "loss": 0.7163, "step": 3154 }, { "epoch": 0.44955827871188375, "grad_norm": 1.5147258294955155, "learning_rate": 1.906774369461855e-05, "loss": 0.6842, "step": 3155 }, { "epoch": 0.44970076944998577, "grad_norm": 1.5813245058005143, "learning_rate": 1.9066694849885183e-05, "loss": 0.718, "step": 3156 }, { "epoch": 0.4498432601880878, "grad_norm": 1.4247062679556017, "learning_rate": 1.9065645444356333e-05, "loss": 0.7424, "step": 3157 }, { "epoch": 0.4499857509261898, "grad_norm": 1.6822676741514966, "learning_rate": 1.9064595478096902e-05, "loss": 0.7527, "step": 3158 }, { "epoch": 0.45012824166429183, "grad_norm": 1.4764462525948572, "learning_rate": 1.9063544951171838e-05, "loss": 0.732, "step": 3159 }, { "epoch": 0.45027073240239385, "grad_norm": 1.347093301262203, "learning_rate": 1.906249386364612e-05, "loss": 0.6614, "step": 3160 }, { "epoch": 0.45041322314049587, "grad_norm": 1.436738710047843, "learning_rate": 1.9061442215584754e-05, "loss": 0.6357, "step": 3161 }, { "epoch": 0.4505557138785979, "grad_norm": 1.517561635006035, "learning_rate": 1.906039000705279e-05, "loss": 0.6621, "step": 3162 }, { "epoch": 0.4506982046166999, "grad_norm": 1.348517142447908, "learning_rate": 1.905933723811531e-05, "loss": 0.6576, "step": 3163 }, { "epoch": 0.4508406953548019, "grad_norm": 1.5968012039596158, "learning_rate": 1.9058283908837435e-05, "loss": 0.7207, "step": 3164 }, { "epoch": 0.45098318609290394, "grad_norm": 1.5368890338676764, "learning_rate": 1.9057230019284304e-05, "loss": 0.7017, "step": 3165 }, { "epoch": 0.45112567683100596, "grad_norm": 1.3126763673274968, "learning_rate": 1.9056175569521112e-05, "loss": 0.5774, "step": 3166 }, { "epoch": 0.451268167569108, "grad_norm": 1.470356684796301, "learning_rate": 1.9055120559613077e-05, "loss": 0.6977, "step": 3167 }, { "epoch": 0.45141065830721006, "grad_norm": 1.6162955443001936, "learning_rate": 1.9054064989625448e-05, "loss": 0.7337, "step": 3168 }, { "epoch": 0.4515531490453121, "grad_norm": 1.4237653473534584, "learning_rate": 1.9053008859623527e-05, "loss": 0.7011, "step": 3169 }, { "epoch": 0.4516956397834141, "grad_norm": 1.564288013954672, "learning_rate": 1.9051952169672624e-05, "loss": 0.6998, "step": 3170 }, { "epoch": 0.4518381305215161, "grad_norm": 1.6393300260093302, "learning_rate": 1.9050894919838107e-05, "loss": 0.6589, "step": 3171 }, { "epoch": 0.45198062125961813, "grad_norm": 1.3474195556355444, "learning_rate": 1.9049837110185366e-05, "loss": 0.7188, "step": 3172 }, { "epoch": 0.45212311199772015, "grad_norm": 1.5599865580989016, "learning_rate": 1.9048778740779826e-05, "loss": 0.7956, "step": 3173 }, { "epoch": 0.45226560273582217, "grad_norm": 1.7238005446103049, "learning_rate": 1.9047719811686956e-05, "loss": 0.6505, "step": 3174 }, { "epoch": 0.4524080934739242, "grad_norm": 1.378787275571688, "learning_rate": 1.904666032297225e-05, "loss": 0.6919, "step": 3175 }, { "epoch": 0.4525505842120262, "grad_norm": 1.4448542998226113, "learning_rate": 1.9045600274701238e-05, "loss": 0.6719, "step": 3176 }, { "epoch": 0.4526930749501282, "grad_norm": 1.5407803036233918, "learning_rate": 1.904453966693949e-05, "loss": 0.7561, "step": 3177 }, { "epoch": 0.45283556568823025, "grad_norm": 1.37703806962685, "learning_rate": 1.90434784997526e-05, "loss": 0.7126, "step": 3178 }, { "epoch": 0.45297805642633227, "grad_norm": 1.417590552989998, "learning_rate": 1.9042416773206212e-05, "loss": 0.7033, "step": 3179 }, { "epoch": 0.4531205471644343, "grad_norm": 1.3770646140838017, "learning_rate": 1.9041354487365995e-05, "loss": 0.6071, "step": 3180 }, { "epoch": 0.45326303790253636, "grad_norm": 1.9560417444644853, "learning_rate": 1.904029164229765e-05, "loss": 0.7584, "step": 3181 }, { "epoch": 0.4534055286406384, "grad_norm": 1.4414255109794647, "learning_rate": 1.9039228238066916e-05, "loss": 0.6575, "step": 3182 }, { "epoch": 0.4535480193787404, "grad_norm": 1.4718814290200557, "learning_rate": 1.903816427473957e-05, "loss": 0.7102, "step": 3183 }, { "epoch": 0.4536905101168424, "grad_norm": 1.736322026968161, "learning_rate": 1.903709975238142e-05, "loss": 0.7276, "step": 3184 }, { "epoch": 0.45383300085494443, "grad_norm": 1.4958713399414572, "learning_rate": 1.9036034671058307e-05, "loss": 0.6561, "step": 3185 }, { "epoch": 0.45397549159304645, "grad_norm": 1.2783139704958792, "learning_rate": 1.903496903083611e-05, "loss": 0.673, "step": 3186 }, { "epoch": 0.4541179823311485, "grad_norm": 1.6768590913858503, "learning_rate": 1.9033902831780743e-05, "loss": 0.729, "step": 3187 }, { "epoch": 0.4542604730692505, "grad_norm": 1.4880996835472535, "learning_rate": 1.903283607395815e-05, "loss": 0.6821, "step": 3188 }, { "epoch": 0.4544029638073525, "grad_norm": 1.328407160826805, "learning_rate": 1.9031768757434316e-05, "loss": 0.7156, "step": 3189 }, { "epoch": 0.45454545454545453, "grad_norm": 1.500510349028525, "learning_rate": 1.9030700882275248e-05, "loss": 0.6702, "step": 3190 }, { "epoch": 0.45468794528355655, "grad_norm": 1.4591210459214934, "learning_rate": 1.9029632448547008e-05, "loss": 0.7285, "step": 3191 }, { "epoch": 0.45483043602165857, "grad_norm": 1.4292822724382028, "learning_rate": 1.9028563456315675e-05, "loss": 0.6615, "step": 3192 }, { "epoch": 0.45497292675976064, "grad_norm": 1.4896304510700822, "learning_rate": 1.902749390564737e-05, "loss": 0.7178, "step": 3193 }, { "epoch": 0.45511541749786266, "grad_norm": 1.5840310549773977, "learning_rate": 1.9026423796608243e-05, "loss": 0.6991, "step": 3194 }, { "epoch": 0.4552579082359647, "grad_norm": 1.9650382724567237, "learning_rate": 1.9025353129264493e-05, "loss": 0.7288, "step": 3195 }, { "epoch": 0.4554003989740667, "grad_norm": 1.3164577455315105, "learning_rate": 1.9024281903682333e-05, "loss": 0.702, "step": 3196 }, { "epoch": 0.4555428897121687, "grad_norm": 1.52280928217962, "learning_rate": 1.9023210119928022e-05, "loss": 0.6966, "step": 3197 }, { "epoch": 0.45568538045027074, "grad_norm": 4.219763313548664, "learning_rate": 1.9022137778067857e-05, "loss": 0.7285, "step": 3198 }, { "epoch": 0.45582787118837276, "grad_norm": 1.5368259727784552, "learning_rate": 1.9021064878168162e-05, "loss": 0.688, "step": 3199 }, { "epoch": 0.4559703619264748, "grad_norm": 1.26192234442109, "learning_rate": 1.9019991420295295e-05, "loss": 0.6256, "step": 3200 }, { "epoch": 0.4561128526645768, "grad_norm": 1.4420677272735918, "learning_rate": 1.901891740451566e-05, "loss": 0.6261, "step": 3201 }, { "epoch": 0.4562553434026788, "grad_norm": 1.4778313602543087, "learning_rate": 1.901784283089568e-05, "loss": 0.696, "step": 3202 }, { "epoch": 0.45639783414078083, "grad_norm": 1.6869651952752496, "learning_rate": 1.9016767699501824e-05, "loss": 0.6806, "step": 3203 }, { "epoch": 0.45654032487888285, "grad_norm": 1.5129789501225288, "learning_rate": 1.901569201040059e-05, "loss": 0.6855, "step": 3204 }, { "epoch": 0.45668281561698487, "grad_norm": 1.4402003845624882, "learning_rate": 1.901461576365851e-05, "loss": 0.7593, "step": 3205 }, { "epoch": 0.45682530635508695, "grad_norm": 1.4620000393098762, "learning_rate": 1.901353895934215e-05, "loss": 0.7268, "step": 3206 }, { "epoch": 0.45696779709318897, "grad_norm": 1.4974297384894795, "learning_rate": 1.9012461597518123e-05, "loss": 0.7325, "step": 3207 }, { "epoch": 0.457110287831291, "grad_norm": 1.3984091492252293, "learning_rate": 1.9011383678253056e-05, "loss": 0.7379, "step": 3208 }, { "epoch": 0.457252778569393, "grad_norm": 1.4428935547986417, "learning_rate": 1.9010305201613625e-05, "loss": 0.7018, "step": 3209 }, { "epoch": 0.457395269307495, "grad_norm": 1.7069605441313576, "learning_rate": 1.900922616766654e-05, "loss": 0.6688, "step": 3210 }, { "epoch": 0.45753776004559704, "grad_norm": 1.423631458554949, "learning_rate": 1.9008146576478533e-05, "loss": 0.6288, "step": 3211 }, { "epoch": 0.45768025078369906, "grad_norm": 1.3983500543391334, "learning_rate": 1.9007066428116384e-05, "loss": 0.7316, "step": 3212 }, { "epoch": 0.4578227415218011, "grad_norm": 1.6466351650722484, "learning_rate": 1.90059857226469e-05, "loss": 0.6975, "step": 3213 }, { "epoch": 0.4579652322599031, "grad_norm": 1.4715138980873557, "learning_rate": 1.900490446013693e-05, "loss": 0.7356, "step": 3214 }, { "epoch": 0.4581077229980051, "grad_norm": 1.3865492694543382, "learning_rate": 1.900382264065335e-05, "loss": 0.6939, "step": 3215 }, { "epoch": 0.45825021373610714, "grad_norm": 2.8966561201669645, "learning_rate": 1.900274026426307e-05, "loss": 0.7264, "step": 3216 }, { "epoch": 0.45839270447420916, "grad_norm": 1.568794972932564, "learning_rate": 1.9001657331033043e-05, "loss": 0.7206, "step": 3217 }, { "epoch": 0.4585351952123112, "grad_norm": 1.512240040133903, "learning_rate": 1.9000573841030247e-05, "loss": 0.7153, "step": 3218 }, { "epoch": 0.45867768595041325, "grad_norm": 1.3742001585555483, "learning_rate": 1.89994897943217e-05, "loss": 0.6036, "step": 3219 }, { "epoch": 0.45882017668851527, "grad_norm": 1.568999274714739, "learning_rate": 1.899840519097445e-05, "loss": 0.7216, "step": 3220 }, { "epoch": 0.4589626674266173, "grad_norm": 1.543406240683442, "learning_rate": 1.8997320031055585e-05, "loss": 0.8062, "step": 3221 }, { "epoch": 0.4591051581647193, "grad_norm": 1.5002092509056597, "learning_rate": 1.8996234314632224e-05, "loss": 0.6599, "step": 3222 }, { "epoch": 0.4592476489028213, "grad_norm": 1.3755153961208968, "learning_rate": 1.899514804177152e-05, "loss": 0.5901, "step": 3223 }, { "epoch": 0.45939013964092335, "grad_norm": 1.5020840346905908, "learning_rate": 1.8994061212540663e-05, "loss": 0.6902, "step": 3224 }, { "epoch": 0.45953263037902536, "grad_norm": 1.58906445777954, "learning_rate": 1.8992973827006875e-05, "loss": 0.7437, "step": 3225 }, { "epoch": 0.4596751211171274, "grad_norm": 1.6676410398469446, "learning_rate": 1.8991885885237412e-05, "loss": 0.7302, "step": 3226 }, { "epoch": 0.4598176118552294, "grad_norm": 1.7675761168361086, "learning_rate": 1.8990797387299567e-05, "loss": 0.6269, "step": 3227 }, { "epoch": 0.4599601025933314, "grad_norm": 1.5552145368457182, "learning_rate": 1.8989708333260665e-05, "loss": 0.6936, "step": 3228 }, { "epoch": 0.46010259333143344, "grad_norm": 1.5703778655157181, "learning_rate": 1.898861872318807e-05, "loss": 0.6945, "step": 3229 }, { "epoch": 0.46024508406953546, "grad_norm": 1.557890258109125, "learning_rate": 1.8987528557149173e-05, "loss": 0.7208, "step": 3230 }, { "epoch": 0.4603875748076375, "grad_norm": 1.4249344409609666, "learning_rate": 1.8986437835211403e-05, "loss": 0.6721, "step": 3231 }, { "epoch": 0.46053006554573955, "grad_norm": 1.5461061704382812, "learning_rate": 1.8985346557442227e-05, "loss": 0.7242, "step": 3232 }, { "epoch": 0.46067255628384157, "grad_norm": 1.4530924141658488, "learning_rate": 1.898425472390914e-05, "loss": 0.6998, "step": 3233 }, { "epoch": 0.4608150470219436, "grad_norm": 1.6307051896485754, "learning_rate": 1.8983162334679676e-05, "loss": 0.7113, "step": 3234 }, { "epoch": 0.4609575377600456, "grad_norm": 1.3749286526238036, "learning_rate": 1.8982069389821402e-05, "loss": 0.6221, "step": 3235 }, { "epoch": 0.46110002849814763, "grad_norm": 1.4212007908730901, "learning_rate": 1.8980975889401916e-05, "loss": 0.6978, "step": 3236 }, { "epoch": 0.46124251923624965, "grad_norm": 1.4142194304327436, "learning_rate": 1.897988183348886e-05, "loss": 0.7027, "step": 3237 }, { "epoch": 0.46138500997435167, "grad_norm": 1.387628159772053, "learning_rate": 1.8978787222149894e-05, "loss": 0.7074, "step": 3238 }, { "epoch": 0.4615275007124537, "grad_norm": 1.3413551374768737, "learning_rate": 1.897769205545273e-05, "loss": 0.6504, "step": 3239 }, { "epoch": 0.4616699914505557, "grad_norm": 1.3663720018795757, "learning_rate": 1.8976596333465104e-05, "loss": 0.6615, "step": 3240 }, { "epoch": 0.4618124821886577, "grad_norm": 1.3197460420645444, "learning_rate": 1.8975500056254787e-05, "loss": 0.665, "step": 3241 }, { "epoch": 0.46195497292675974, "grad_norm": 1.4076559188434628, "learning_rate": 1.8974403223889592e-05, "loss": 0.6322, "step": 3242 }, { "epoch": 0.46209746366486176, "grad_norm": 1.4435666459671948, "learning_rate": 1.8973305836437355e-05, "loss": 0.7076, "step": 3243 }, { "epoch": 0.4622399544029638, "grad_norm": 1.4039551960451777, "learning_rate": 1.8972207893965952e-05, "loss": 0.621, "step": 3244 }, { "epoch": 0.46238244514106586, "grad_norm": 1.4252594233568225, "learning_rate": 1.89711093965433e-05, "loss": 0.6656, "step": 3245 }, { "epoch": 0.4625249358791679, "grad_norm": 1.5715837108931223, "learning_rate": 1.8970010344237334e-05, "loss": 0.7589, "step": 3246 }, { "epoch": 0.4626674266172699, "grad_norm": 1.4885977389860738, "learning_rate": 1.8968910737116038e-05, "loss": 0.8271, "step": 3247 }, { "epoch": 0.4628099173553719, "grad_norm": 1.4831591389813463, "learning_rate": 1.8967810575247426e-05, "loss": 0.7143, "step": 3248 }, { "epoch": 0.46295240809347393, "grad_norm": 1.3601090560665665, "learning_rate": 1.8966709858699542e-05, "loss": 0.6675, "step": 3249 }, { "epoch": 0.46309489883157595, "grad_norm": 1.4507196413047407, "learning_rate": 1.8965608587540472e-05, "loss": 0.6939, "step": 3250 }, { "epoch": 0.46323738956967797, "grad_norm": 1.2744876228055613, "learning_rate": 1.8964506761838327e-05, "loss": 0.6287, "step": 3251 }, { "epoch": 0.46337988030778, "grad_norm": 1.359041380697093, "learning_rate": 1.8963404381661262e-05, "loss": 0.7715, "step": 3252 }, { "epoch": 0.463522371045882, "grad_norm": 1.43228466033265, "learning_rate": 1.896230144707746e-05, "loss": 0.6943, "step": 3253 }, { "epoch": 0.46366486178398403, "grad_norm": 1.4139548790633425, "learning_rate": 1.896119795815514e-05, "loss": 0.6006, "step": 3254 }, { "epoch": 0.46380735252208605, "grad_norm": 1.5756044452043036, "learning_rate": 1.8960093914962553e-05, "loss": 0.7239, "step": 3255 }, { "epoch": 0.46394984326018807, "grad_norm": 1.9575291873329095, "learning_rate": 1.8958989317567993e-05, "loss": 0.6444, "step": 3256 }, { "epoch": 0.4640923339982901, "grad_norm": 1.3735840250026148, "learning_rate": 1.8957884166039772e-05, "loss": 0.7008, "step": 3257 }, { "epoch": 0.46423482473639216, "grad_norm": 1.4221637408858205, "learning_rate": 1.8956778460446257e-05, "loss": 0.6717, "step": 3258 }, { "epoch": 0.4643773154744942, "grad_norm": 1.577800994061318, "learning_rate": 1.895567220085583e-05, "loss": 0.7104, "step": 3259 }, { "epoch": 0.4645198062125962, "grad_norm": 1.6209782641683852, "learning_rate": 1.8954565387336922e-05, "loss": 0.6455, "step": 3260 }, { "epoch": 0.4646622969506982, "grad_norm": 1.3720128129064413, "learning_rate": 1.8953458019957986e-05, "loss": 0.6733, "step": 3261 }, { "epoch": 0.46480478768880024, "grad_norm": 1.486845485193613, "learning_rate": 1.8952350098787516e-05, "loss": 0.6608, "step": 3262 }, { "epoch": 0.46494727842690226, "grad_norm": 1.4228732910318846, "learning_rate": 1.8951241623894045e-05, "loss": 0.6948, "step": 3263 }, { "epoch": 0.4650897691650043, "grad_norm": 1.3740348859834204, "learning_rate": 1.895013259534613e-05, "loss": 0.7223, "step": 3264 }, { "epoch": 0.4652322599031063, "grad_norm": 1.4197494853273573, "learning_rate": 1.8949023013212366e-05, "loss": 0.7553, "step": 3265 }, { "epoch": 0.4653747506412083, "grad_norm": 1.3828561577410172, "learning_rate": 1.894791287756139e-05, "loss": 0.6573, "step": 3266 }, { "epoch": 0.46551724137931033, "grad_norm": 1.3201298134867898, "learning_rate": 1.8946802188461854e-05, "loss": 0.6216, "step": 3267 }, { "epoch": 0.46565973211741235, "grad_norm": 1.3518658544703237, "learning_rate": 1.894569094598247e-05, "loss": 0.6183, "step": 3268 }, { "epoch": 0.46580222285551437, "grad_norm": 1.566038319602457, "learning_rate": 1.8944579150191963e-05, "loss": 0.7253, "step": 3269 }, { "epoch": 0.4659447135936164, "grad_norm": 4.9163621148034515, "learning_rate": 1.89434668011591e-05, "loss": 0.6509, "step": 3270 }, { "epoch": 0.46608720433171846, "grad_norm": 1.537754092634252, "learning_rate": 1.8942353898952687e-05, "loss": 0.717, "step": 3271 }, { "epoch": 0.4662296950698205, "grad_norm": 1.5431595668522633, "learning_rate": 1.8941240443641553e-05, "loss": 0.6918, "step": 3272 }, { "epoch": 0.4663721858079225, "grad_norm": 1.3094348744965072, "learning_rate": 1.8940126435294575e-05, "loss": 0.633, "step": 3273 }, { "epoch": 0.4665146765460245, "grad_norm": 1.5215132078282998, "learning_rate": 1.893901187398065e-05, "loss": 0.6592, "step": 3274 }, { "epoch": 0.46665716728412654, "grad_norm": 1.4199817913424881, "learning_rate": 1.8937896759768722e-05, "loss": 0.7186, "step": 3275 }, { "epoch": 0.46679965802222856, "grad_norm": 5.06620845088033, "learning_rate": 1.893678109272776e-05, "loss": 0.7175, "step": 3276 }, { "epoch": 0.4669421487603306, "grad_norm": 1.3817687361743725, "learning_rate": 1.8935664872926772e-05, "loss": 0.6853, "step": 3277 }, { "epoch": 0.4670846394984326, "grad_norm": 1.4595663080499237, "learning_rate": 1.8934548100434798e-05, "loss": 0.6888, "step": 3278 }, { "epoch": 0.4672271302365346, "grad_norm": 2.3204201017433457, "learning_rate": 1.8933430775320915e-05, "loss": 0.7693, "step": 3279 }, { "epoch": 0.46736962097463663, "grad_norm": 1.3991437973367336, "learning_rate": 1.8932312897654226e-05, "loss": 0.5487, "step": 3280 }, { "epoch": 0.46751211171273865, "grad_norm": 1.6610695371394133, "learning_rate": 1.893119446750388e-05, "loss": 0.7077, "step": 3281 }, { "epoch": 0.4676546024508407, "grad_norm": 1.635492758544539, "learning_rate": 1.893007548493905e-05, "loss": 0.7497, "step": 3282 }, { "epoch": 0.4677970931889427, "grad_norm": 1.5397432835266056, "learning_rate": 1.8928955950028953e-05, "loss": 0.6811, "step": 3283 }, { "epoch": 0.46793958392704477, "grad_norm": 1.5904150550770453, "learning_rate": 1.8927835862842832e-05, "loss": 0.7391, "step": 3284 }, { "epoch": 0.4680820746651468, "grad_norm": 1.2750995977513853, "learning_rate": 1.892671522344997e-05, "loss": 0.6591, "step": 3285 }, { "epoch": 0.4682245654032488, "grad_norm": 1.4799294125263889, "learning_rate": 1.892559403191967e-05, "loss": 0.6884, "step": 3286 }, { "epoch": 0.4683670561413508, "grad_norm": 1.5612391923417595, "learning_rate": 1.8924472288321292e-05, "loss": 0.6759, "step": 3287 }, { "epoch": 0.46850954687945284, "grad_norm": 1.5216477352168611, "learning_rate": 1.8923349992724216e-05, "loss": 0.7865, "step": 3288 }, { "epoch": 0.46865203761755486, "grad_norm": 2.1397979867871526, "learning_rate": 1.8922227145197856e-05, "loss": 0.7129, "step": 3289 }, { "epoch": 0.4687945283556569, "grad_norm": 1.3200525177265667, "learning_rate": 1.8921103745811665e-05, "loss": 0.649, "step": 3290 }, { "epoch": 0.4689370190937589, "grad_norm": 1.3631169149922011, "learning_rate": 1.8919979794635128e-05, "loss": 0.6583, "step": 3291 }, { "epoch": 0.4690795098318609, "grad_norm": 1.6100783783236712, "learning_rate": 1.8918855291737757e-05, "loss": 0.7156, "step": 3292 }, { "epoch": 0.46922200056996294, "grad_norm": 1.5923188824096874, "learning_rate": 1.8917730237189112e-05, "loss": 0.6971, "step": 3293 }, { "epoch": 0.46936449130806496, "grad_norm": 1.451001132615866, "learning_rate": 1.8916604631058782e-05, "loss": 0.6861, "step": 3294 }, { "epoch": 0.469506982046167, "grad_norm": 1.4322620254303293, "learning_rate": 1.8915478473416382e-05, "loss": 0.7207, "step": 3295 }, { "epoch": 0.469649472784269, "grad_norm": 1.3556796127899329, "learning_rate": 1.891435176433157e-05, "loss": 0.6607, "step": 3296 }, { "epoch": 0.46979196352237107, "grad_norm": 1.6764325388453607, "learning_rate": 1.8913224503874038e-05, "loss": 0.712, "step": 3297 }, { "epoch": 0.4699344542604731, "grad_norm": 1.52096129073847, "learning_rate": 1.8912096692113505e-05, "loss": 0.6863, "step": 3298 }, { "epoch": 0.4700769449985751, "grad_norm": 1.3527602302680724, "learning_rate": 1.8910968329119735e-05, "loss": 0.7249, "step": 3299 }, { "epoch": 0.4702194357366771, "grad_norm": 1.372430202931312, "learning_rate": 1.890983941496251e-05, "loss": 0.6061, "step": 3300 }, { "epoch": 0.47036192647477915, "grad_norm": 1.3730746939472476, "learning_rate": 1.8908709949711666e-05, "loss": 0.6869, "step": 3301 }, { "epoch": 0.47050441721288117, "grad_norm": 1.5335979175202332, "learning_rate": 1.8907579933437058e-05, "loss": 0.7306, "step": 3302 }, { "epoch": 0.4706469079509832, "grad_norm": 1.428695007631841, "learning_rate": 1.890644936620858e-05, "loss": 0.7188, "step": 3303 }, { "epoch": 0.4707893986890852, "grad_norm": 1.6642000102133483, "learning_rate": 1.890531824809616e-05, "loss": 0.6934, "step": 3304 }, { "epoch": 0.4709318894271872, "grad_norm": 1.6437767387523834, "learning_rate": 1.8904186579169765e-05, "loss": 0.6807, "step": 3305 }, { "epoch": 0.47107438016528924, "grad_norm": 1.421229421983261, "learning_rate": 1.8903054359499383e-05, "loss": 0.6934, "step": 3306 }, { "epoch": 0.47121687090339126, "grad_norm": 1.4761156214114795, "learning_rate": 1.8901921589155047e-05, "loss": 0.6322, "step": 3307 }, { "epoch": 0.4713593616414933, "grad_norm": 1.607317655867124, "learning_rate": 1.8900788268206827e-05, "loss": 0.7587, "step": 3308 }, { "epoch": 0.4715018523795953, "grad_norm": 1.5446703802672817, "learning_rate": 1.8899654396724817e-05, "loss": 0.7037, "step": 3309 }, { "epoch": 0.4716443431176974, "grad_norm": 1.3185913432459302, "learning_rate": 1.8898519974779154e-05, "loss": 0.6839, "step": 3310 }, { "epoch": 0.4717868338557994, "grad_norm": 1.494547788712245, "learning_rate": 1.8897385002439992e-05, "loss": 0.6739, "step": 3311 }, { "epoch": 0.4719293245939014, "grad_norm": 1.5978105729307779, "learning_rate": 1.8896249479777545e-05, "loss": 0.7408, "step": 3312 }, { "epoch": 0.47207181533200343, "grad_norm": 1.433280902356771, "learning_rate": 1.8895113406862044e-05, "loss": 0.6387, "step": 3313 }, { "epoch": 0.47221430607010545, "grad_norm": 1.5437116673769238, "learning_rate": 1.8893976783763754e-05, "loss": 0.5878, "step": 3314 }, { "epoch": 0.47235679680820747, "grad_norm": 1.6687605027552201, "learning_rate": 1.889283961055298e-05, "loss": 0.7586, "step": 3315 }, { "epoch": 0.4724992875463095, "grad_norm": 1.5521641115196891, "learning_rate": 1.889170188730006e-05, "loss": 0.6965, "step": 3316 }, { "epoch": 0.4726417782844115, "grad_norm": 1.6137450312969202, "learning_rate": 1.8890563614075367e-05, "loss": 0.7165, "step": 3317 }, { "epoch": 0.4727842690225135, "grad_norm": 1.7998112727524749, "learning_rate": 1.8889424790949298e-05, "loss": 0.6858, "step": 3318 }, { "epoch": 0.47292675976061554, "grad_norm": 1.7615309643061041, "learning_rate": 1.8888285417992293e-05, "loss": 0.6853, "step": 3319 }, { "epoch": 0.47306925049871756, "grad_norm": 1.7896551733637773, "learning_rate": 1.8887145495274835e-05, "loss": 0.6871, "step": 3320 }, { "epoch": 0.4732117412368196, "grad_norm": 1.5770600820572434, "learning_rate": 1.888600502286742e-05, "loss": 0.6319, "step": 3321 }, { "epoch": 0.47335423197492166, "grad_norm": 1.334893070984889, "learning_rate": 1.8884864000840593e-05, "loss": 0.7293, "step": 3322 }, { "epoch": 0.4734967227130237, "grad_norm": 1.6755164785995482, "learning_rate": 1.8883722429264927e-05, "loss": 0.6091, "step": 3323 }, { "epoch": 0.4736392134511257, "grad_norm": 1.650229194398824, "learning_rate": 1.8882580308211037e-05, "loss": 0.6166, "step": 3324 }, { "epoch": 0.4737817041892277, "grad_norm": 1.732760845344237, "learning_rate": 1.8881437637749554e-05, "loss": 0.6933, "step": 3325 }, { "epoch": 0.47392419492732973, "grad_norm": 1.446359978836375, "learning_rate": 1.8880294417951165e-05, "loss": 0.6603, "step": 3326 }, { "epoch": 0.47406668566543175, "grad_norm": 1.6365865113149447, "learning_rate": 1.887915064888658e-05, "loss": 0.7028, "step": 3327 }, { "epoch": 0.47420917640353377, "grad_norm": 1.5531275198588887, "learning_rate": 1.887800633062654e-05, "loss": 0.6987, "step": 3328 }, { "epoch": 0.4743516671416358, "grad_norm": 1.6614835580723177, "learning_rate": 1.887686146324182e-05, "loss": 0.7078, "step": 3329 }, { "epoch": 0.4744941578797378, "grad_norm": 1.8923210727283897, "learning_rate": 1.887571604680324e-05, "loss": 0.6505, "step": 3330 }, { "epoch": 0.47463664861783983, "grad_norm": 3.782971634787104, "learning_rate": 1.8874570081381643e-05, "loss": 0.7947, "step": 3331 }, { "epoch": 0.47477913935594185, "grad_norm": 1.7274510976588602, "learning_rate": 1.887342356704791e-05, "loss": 0.7331, "step": 3332 }, { "epoch": 0.47492163009404387, "grad_norm": 1.4674824823402102, "learning_rate": 1.8872276503872958e-05, "loss": 0.7025, "step": 3333 }, { "epoch": 0.4750641208321459, "grad_norm": 1.376534964471543, "learning_rate": 1.8871128891927736e-05, "loss": 0.6502, "step": 3334 }, { "epoch": 0.47520661157024796, "grad_norm": 1.6107093643788999, "learning_rate": 1.886998073128322e-05, "loss": 0.729, "step": 3335 }, { "epoch": 0.47534910230835, "grad_norm": 1.4001551608034144, "learning_rate": 1.8868832022010428e-05, "loss": 0.7707, "step": 3336 }, { "epoch": 0.475491593046452, "grad_norm": 1.372148283513131, "learning_rate": 1.8867682764180416e-05, "loss": 0.6628, "step": 3337 }, { "epoch": 0.475634083784554, "grad_norm": 1.6206934247278018, "learning_rate": 1.8866532957864265e-05, "loss": 0.6562, "step": 3338 }, { "epoch": 0.47577657452265604, "grad_norm": 1.5472494209806191, "learning_rate": 1.8865382603133088e-05, "loss": 0.723, "step": 3339 }, { "epoch": 0.47591906526075806, "grad_norm": 1.451213538376622, "learning_rate": 1.8864231700058043e-05, "loss": 0.7197, "step": 3340 }, { "epoch": 0.4760615559988601, "grad_norm": 1.5961289148148257, "learning_rate": 1.8863080248710318e-05, "loss": 0.7088, "step": 3341 }, { "epoch": 0.4762040467369621, "grad_norm": 1.416723452025796, "learning_rate": 1.8861928249161128e-05, "loss": 0.6918, "step": 3342 }, { "epoch": 0.4763465374750641, "grad_norm": 1.4078058263726274, "learning_rate": 1.8860775701481725e-05, "loss": 0.5982, "step": 3343 }, { "epoch": 0.47648902821316613, "grad_norm": 1.6180811174595595, "learning_rate": 1.8859622605743403e-05, "loss": 0.6823, "step": 3344 }, { "epoch": 0.47663151895126815, "grad_norm": 1.7549213348865689, "learning_rate": 1.885846896201748e-05, "loss": 0.7635, "step": 3345 }, { "epoch": 0.47677400968937017, "grad_norm": 1.38569086519877, "learning_rate": 1.885731477037531e-05, "loss": 0.7707, "step": 3346 }, { "epoch": 0.4769165004274722, "grad_norm": 2.2682300557960544, "learning_rate": 1.8856160030888288e-05, "loss": 0.6557, "step": 3347 }, { "epoch": 0.47705899116557426, "grad_norm": 1.503200950891152, "learning_rate": 1.8855004743627828e-05, "loss": 0.7587, "step": 3348 }, { "epoch": 0.4772014819036763, "grad_norm": 1.5338504420049393, "learning_rate": 1.88538489086654e-05, "loss": 0.7324, "step": 3349 }, { "epoch": 0.4773439726417783, "grad_norm": 1.5545870726478188, "learning_rate": 1.8852692526072483e-05, "loss": 0.6766, "step": 3350 }, { "epoch": 0.4774864633798803, "grad_norm": 1.5383241677885204, "learning_rate": 1.8851535595920604e-05, "loss": 0.652, "step": 3351 }, { "epoch": 0.47762895411798234, "grad_norm": 1.7935380120784858, "learning_rate": 1.885037811828133e-05, "loss": 0.7942, "step": 3352 }, { "epoch": 0.47777144485608436, "grad_norm": 1.3583427178965455, "learning_rate": 1.8849220093226242e-05, "loss": 0.6701, "step": 3353 }, { "epoch": 0.4779139355941864, "grad_norm": 1.4500532825379155, "learning_rate": 1.8848061520826976e-05, "loss": 0.6853, "step": 3354 }, { "epoch": 0.4780564263322884, "grad_norm": 1.4161022449510443, "learning_rate": 1.8846902401155186e-05, "loss": 0.6589, "step": 3355 }, { "epoch": 0.4781989170703904, "grad_norm": 1.3818930819812139, "learning_rate": 1.8845742734282572e-05, "loss": 0.6914, "step": 3356 }, { "epoch": 0.47834140780849244, "grad_norm": 1.473892553397908, "learning_rate": 1.8844582520280857e-05, "loss": 0.7249, "step": 3357 }, { "epoch": 0.47848389854659445, "grad_norm": 1.2853298228970893, "learning_rate": 1.88434217592218e-05, "loss": 0.6773, "step": 3358 }, { "epoch": 0.4786263892846965, "grad_norm": 1.4732825209993825, "learning_rate": 1.8842260451177207e-05, "loss": 0.6654, "step": 3359 }, { "epoch": 0.4787688800227985, "grad_norm": 1.4750714389484652, "learning_rate": 1.88410985962189e-05, "loss": 0.6864, "step": 3360 }, { "epoch": 0.47891137076090057, "grad_norm": 1.4856477503684222, "learning_rate": 1.8839936194418745e-05, "loss": 0.606, "step": 3361 }, { "epoch": 0.4790538614990026, "grad_norm": 1.4773798187441645, "learning_rate": 1.883877324584864e-05, "loss": 0.7667, "step": 3362 }, { "epoch": 0.4791963522371046, "grad_norm": 1.4692648082676136, "learning_rate": 1.883760975058051e-05, "loss": 0.6806, "step": 3363 }, { "epoch": 0.4793388429752066, "grad_norm": 1.4402043423920514, "learning_rate": 1.883644570868633e-05, "loss": 0.7696, "step": 3364 }, { "epoch": 0.47948133371330864, "grad_norm": 1.4043584533507472, "learning_rate": 1.8835281120238086e-05, "loss": 0.6729, "step": 3365 }, { "epoch": 0.47962382445141066, "grad_norm": 1.5465467612263786, "learning_rate": 1.883411598530782e-05, "loss": 0.705, "step": 3366 }, { "epoch": 0.4797663151895127, "grad_norm": 1.4433519131536179, "learning_rate": 1.8832950303967593e-05, "loss": 0.5986, "step": 3367 }, { "epoch": 0.4799088059276147, "grad_norm": 1.6708296533537665, "learning_rate": 1.883178407628951e-05, "loss": 0.6344, "step": 3368 }, { "epoch": 0.4800512966657167, "grad_norm": 1.594247712004892, "learning_rate": 1.8830617302345706e-05, "loss": 0.6275, "step": 3369 }, { "epoch": 0.48019378740381874, "grad_norm": 1.7680733068557324, "learning_rate": 1.8829449982208337e-05, "loss": 0.7508, "step": 3370 }, { "epoch": 0.48033627814192076, "grad_norm": 1.6338579741575163, "learning_rate": 1.8828282115949613e-05, "loss": 0.7378, "step": 3371 }, { "epoch": 0.4804787688800228, "grad_norm": 1.4179799990798836, "learning_rate": 1.8827113703641772e-05, "loss": 0.7091, "step": 3372 }, { "epoch": 0.4806212596181248, "grad_norm": 1.382264435685238, "learning_rate": 1.882594474535708e-05, "loss": 0.684, "step": 3373 }, { "epoch": 0.48076375035622687, "grad_norm": 1.552643403600251, "learning_rate": 1.8824775241167835e-05, "loss": 0.7061, "step": 3374 }, { "epoch": 0.4809062410943289, "grad_norm": 1.6163689854401024, "learning_rate": 1.882360519114638e-05, "loss": 0.5908, "step": 3375 }, { "epoch": 0.4810487318324309, "grad_norm": 1.5102486888016529, "learning_rate": 1.882243459536508e-05, "loss": 0.6353, "step": 3376 }, { "epoch": 0.48119122257053293, "grad_norm": 1.799285943173197, "learning_rate": 1.8821263453896345e-05, "loss": 0.7374, "step": 3377 }, { "epoch": 0.48133371330863495, "grad_norm": 1.5432993896811156, "learning_rate": 1.8820091766812603e-05, "loss": 0.7553, "step": 3378 }, { "epoch": 0.48147620404673697, "grad_norm": 1.407315089191444, "learning_rate": 1.8818919534186338e-05, "loss": 0.6595, "step": 3379 }, { "epoch": 0.481618694784839, "grad_norm": 1.6002086057338971, "learning_rate": 1.8817746756090046e-05, "loss": 0.7234, "step": 3380 }, { "epoch": 0.481761185522941, "grad_norm": 1.4025018130225657, "learning_rate": 1.881657343259627e-05, "loss": 0.7349, "step": 3381 }, { "epoch": 0.481903676261043, "grad_norm": 1.451197863485125, "learning_rate": 1.881539956377758e-05, "loss": 0.6943, "step": 3382 }, { "epoch": 0.48204616699914504, "grad_norm": 1.519255981937566, "learning_rate": 1.8814225149706587e-05, "loss": 0.6387, "step": 3383 }, { "epoch": 0.48218865773724706, "grad_norm": 1.5288676657229947, "learning_rate": 1.881305019045593e-05, "loss": 0.6359, "step": 3384 }, { "epoch": 0.4823311484753491, "grad_norm": 3.623655580033636, "learning_rate": 1.8811874686098277e-05, "loss": 0.664, "step": 3385 }, { "epoch": 0.4824736392134511, "grad_norm": 3.8037825992538314, "learning_rate": 1.881069863670634e-05, "loss": 0.7238, "step": 3386 }, { "epoch": 0.4826161299515532, "grad_norm": 1.5377823727319253, "learning_rate": 1.880952204235286e-05, "loss": 0.6903, "step": 3387 }, { "epoch": 0.4827586206896552, "grad_norm": 1.6237417693027796, "learning_rate": 1.8808344903110612e-05, "loss": 0.6334, "step": 3388 }, { "epoch": 0.4829011114277572, "grad_norm": 1.5119535152239794, "learning_rate": 1.880716721905241e-05, "loss": 0.6356, "step": 3389 }, { "epoch": 0.48304360216585923, "grad_norm": 1.6968137176403042, "learning_rate": 1.8805988990251084e-05, "loss": 0.6887, "step": 3390 }, { "epoch": 0.48318609290396125, "grad_norm": 1.3688100527512208, "learning_rate": 1.880481021677952e-05, "loss": 0.7436, "step": 3391 }, { "epoch": 0.48332858364206327, "grad_norm": 1.5926754328287123, "learning_rate": 1.8803630898710627e-05, "loss": 0.6739, "step": 3392 }, { "epoch": 0.4834710743801653, "grad_norm": 1.5416677553165863, "learning_rate": 1.8802451036117344e-05, "loss": 0.6386, "step": 3393 }, { "epoch": 0.4836135651182673, "grad_norm": 1.5572848163248993, "learning_rate": 1.880127062907265e-05, "loss": 0.6418, "step": 3394 }, { "epoch": 0.4837560558563693, "grad_norm": 1.4574605818502508, "learning_rate": 1.880008967764956e-05, "loss": 0.7446, "step": 3395 }, { "epoch": 0.48389854659447135, "grad_norm": 1.894154662882583, "learning_rate": 1.879890818192111e-05, "loss": 0.8278, "step": 3396 }, { "epoch": 0.48404103733257337, "grad_norm": 1.391388407080926, "learning_rate": 1.8797726141960387e-05, "loss": 0.7869, "step": 3397 }, { "epoch": 0.4841835280706754, "grad_norm": 1.3342866185677142, "learning_rate": 1.87965435578405e-05, "loss": 0.6038, "step": 3398 }, { "epoch": 0.4843260188087774, "grad_norm": 1.5242867110534708, "learning_rate": 1.879536042963459e-05, "loss": 0.6676, "step": 3399 }, { "epoch": 0.4844685095468795, "grad_norm": 1.4551881684967256, "learning_rate": 1.879417675741584e-05, "loss": 0.7385, "step": 3400 }, { "epoch": 0.4846110002849815, "grad_norm": 1.4146803984582808, "learning_rate": 1.8792992541257464e-05, "loss": 0.6972, "step": 3401 }, { "epoch": 0.4847534910230835, "grad_norm": 1.4254462681043996, "learning_rate": 1.8791807781232708e-05, "loss": 0.6606, "step": 3402 }, { "epoch": 0.48489598176118553, "grad_norm": 1.3874484030320493, "learning_rate": 1.8790622477414846e-05, "loss": 0.6206, "step": 3403 }, { "epoch": 0.48503847249928755, "grad_norm": 1.662737758320832, "learning_rate": 1.87894366298772e-05, "loss": 0.708, "step": 3404 }, { "epoch": 0.4851809632373896, "grad_norm": 1.4686310133744054, "learning_rate": 1.8788250238693116e-05, "loss": 0.7416, "step": 3405 }, { "epoch": 0.4853234539754916, "grad_norm": 1.5571678034215348, "learning_rate": 1.8787063303935968e-05, "loss": 0.72, "step": 3406 }, { "epoch": 0.4854659447135936, "grad_norm": 2.211123163934995, "learning_rate": 1.878587582567918e-05, "loss": 0.6623, "step": 3407 }, { "epoch": 0.48560843545169563, "grad_norm": 1.4807980528147369, "learning_rate": 1.8784687803996197e-05, "loss": 0.611, "step": 3408 }, { "epoch": 0.48575092618979765, "grad_norm": 1.357966155600607, "learning_rate": 1.8783499238960495e-05, "loss": 0.5804, "step": 3409 }, { "epoch": 0.48589341692789967, "grad_norm": 1.4485748356293247, "learning_rate": 1.8782310130645595e-05, "loss": 0.7821, "step": 3410 }, { "epoch": 0.4860359076660017, "grad_norm": 1.5695086587643627, "learning_rate": 1.8781120479125044e-05, "loss": 0.6622, "step": 3411 }, { "epoch": 0.4861783984041037, "grad_norm": 2.516325486495844, "learning_rate": 1.877993028447243e-05, "loss": 0.6004, "step": 3412 }, { "epoch": 0.4863208891422058, "grad_norm": 1.4482592289432747, "learning_rate": 1.8778739546761364e-05, "loss": 0.6941, "step": 3413 }, { "epoch": 0.4864633798803078, "grad_norm": 1.5003593536746216, "learning_rate": 1.8777548266065492e-05, "loss": 0.71, "step": 3414 }, { "epoch": 0.4866058706184098, "grad_norm": 3.9509630207989166, "learning_rate": 1.8776356442458507e-05, "loss": 0.7494, "step": 3415 }, { "epoch": 0.48674836135651184, "grad_norm": 1.376844330770375, "learning_rate": 1.877516407601412e-05, "loss": 0.7007, "step": 3416 }, { "epoch": 0.48689085209461386, "grad_norm": 4.35564259490371, "learning_rate": 1.877397116680608e-05, "loss": 0.6759, "step": 3417 }, { "epoch": 0.4870333428327159, "grad_norm": 1.4099215554091828, "learning_rate": 1.8772777714908176e-05, "loss": 0.6593, "step": 3418 }, { "epoch": 0.4871758335708179, "grad_norm": 1.4438124126017218, "learning_rate": 1.8771583720394222e-05, "loss": 0.7669, "step": 3419 }, { "epoch": 0.4873183243089199, "grad_norm": 1.672995430056239, "learning_rate": 1.877038918333807e-05, "loss": 0.6778, "step": 3420 }, { "epoch": 0.48746081504702193, "grad_norm": 1.9363715460930475, "learning_rate": 1.8769194103813608e-05, "loss": 0.6801, "step": 3421 }, { "epoch": 0.48760330578512395, "grad_norm": 1.8839779122511513, "learning_rate": 1.8767998481894752e-05, "loss": 0.68, "step": 3422 }, { "epoch": 0.48774579652322597, "grad_norm": 1.633901317403819, "learning_rate": 1.876680231765545e-05, "loss": 0.7854, "step": 3423 }, { "epoch": 0.487888287261328, "grad_norm": 1.4311114869472006, "learning_rate": 1.8765605611169693e-05, "loss": 0.6353, "step": 3424 }, { "epoch": 0.48803077799943, "grad_norm": 1.5108861050572853, "learning_rate": 1.87644083625115e-05, "loss": 0.7496, "step": 3425 }, { "epoch": 0.4881732687375321, "grad_norm": 1.3914119000636673, "learning_rate": 1.876321057175492e-05, "loss": 0.6519, "step": 3426 }, { "epoch": 0.4883157594756341, "grad_norm": 1.5138636042421658, "learning_rate": 1.876201223897404e-05, "loss": 0.7694, "step": 3427 }, { "epoch": 0.4884582502137361, "grad_norm": 1.632040364295811, "learning_rate": 1.8760813364242986e-05, "loss": 0.6976, "step": 3428 }, { "epoch": 0.48860074095183814, "grad_norm": 1.4964818392089216, "learning_rate": 1.87596139476359e-05, "loss": 0.6179, "step": 3429 }, { "epoch": 0.48874323168994016, "grad_norm": 1.5329029806743515, "learning_rate": 1.8758413989226972e-05, "loss": 0.6347, "step": 3430 }, { "epoch": 0.4888857224280422, "grad_norm": 1.3740705534719568, "learning_rate": 1.8757213489090427e-05, "loss": 0.6405, "step": 3431 }, { "epoch": 0.4890282131661442, "grad_norm": 1.3447059697883323, "learning_rate": 1.8756012447300516e-05, "loss": 0.7159, "step": 3432 }, { "epoch": 0.4891707039042462, "grad_norm": 4.844114788146657, "learning_rate": 1.8754810863931525e-05, "loss": 0.6809, "step": 3433 }, { "epoch": 0.48931319464234824, "grad_norm": 1.432324773603976, "learning_rate": 1.875360873905778e-05, "loss": 0.6358, "step": 3434 }, { "epoch": 0.48945568538045026, "grad_norm": 1.6044957236876956, "learning_rate": 1.8752406072753625e-05, "loss": 0.6676, "step": 3435 }, { "epoch": 0.4895981761185523, "grad_norm": 1.6930540536655596, "learning_rate": 1.8751202865093455e-05, "loss": 0.7159, "step": 3436 }, { "epoch": 0.4897406668566543, "grad_norm": 1.5071645568327514, "learning_rate": 1.8749999116151686e-05, "loss": 0.6697, "step": 3437 }, { "epoch": 0.4898831575947563, "grad_norm": 1.4560214775052778, "learning_rate": 1.8748794826002782e-05, "loss": 0.6972, "step": 3438 }, { "epoch": 0.4900256483328584, "grad_norm": 1.4615711372990934, "learning_rate": 1.8747589994721222e-05, "loss": 0.7033, "step": 3439 }, { "epoch": 0.4901681390709604, "grad_norm": 1.6711520107750204, "learning_rate": 1.8746384622381534e-05, "loss": 0.7181, "step": 3440 }, { "epoch": 0.4903106298090624, "grad_norm": 1.4624731944285136, "learning_rate": 1.8745178709058264e-05, "loss": 0.639, "step": 3441 }, { "epoch": 0.49045312054716445, "grad_norm": 1.5551089631119288, "learning_rate": 1.874397225482601e-05, "loss": 0.7289, "step": 3442 }, { "epoch": 0.49059561128526646, "grad_norm": 1.327692195613377, "learning_rate": 1.8742765259759388e-05, "loss": 0.658, "step": 3443 }, { "epoch": 0.4907381020233685, "grad_norm": 1.3612952775980693, "learning_rate": 1.8741557723933055e-05, "loss": 0.7053, "step": 3444 }, { "epoch": 0.4908805927614705, "grad_norm": 1.7979243805740377, "learning_rate": 1.8740349647421703e-05, "loss": 0.6546, "step": 3445 }, { "epoch": 0.4910230834995725, "grad_norm": 1.9782004023025928, "learning_rate": 1.8739141030300046e-05, "loss": 0.6304, "step": 3446 }, { "epoch": 0.49116557423767454, "grad_norm": 1.5469566488207056, "learning_rate": 1.8737931872642853e-05, "loss": 0.6182, "step": 3447 }, { "epoch": 0.49130806497577656, "grad_norm": 1.7468462469678991, "learning_rate": 1.87367221745249e-05, "loss": 0.5965, "step": 3448 }, { "epoch": 0.4914505557138786, "grad_norm": 1.5292525137406054, "learning_rate": 1.8735511936021016e-05, "loss": 0.6928, "step": 3449 }, { "epoch": 0.4915930464519806, "grad_norm": 1.3529419946299408, "learning_rate": 1.8734301157206053e-05, "loss": 0.6469, "step": 3450 }, { "epoch": 0.49173553719008267, "grad_norm": 1.3869200183975192, "learning_rate": 1.8733089838154905e-05, "loss": 0.661, "step": 3451 }, { "epoch": 0.4918780279281847, "grad_norm": 1.4733077659413027, "learning_rate": 1.8731877978942492e-05, "loss": 0.6469, "step": 3452 }, { "epoch": 0.4920205186662867, "grad_norm": 1.3598175644204664, "learning_rate": 1.8730665579643773e-05, "loss": 0.648, "step": 3453 }, { "epoch": 0.49216300940438873, "grad_norm": 1.4736965336934496, "learning_rate": 1.8729452640333736e-05, "loss": 0.7115, "step": 3454 }, { "epoch": 0.49230550014249075, "grad_norm": 1.6289641907026968, "learning_rate": 1.8728239161087403e-05, "loss": 0.6453, "step": 3455 }, { "epoch": 0.49244799088059277, "grad_norm": 1.416061964855922, "learning_rate": 1.872702514197983e-05, "loss": 0.6605, "step": 3456 }, { "epoch": 0.4925904816186948, "grad_norm": 1.5099141015380115, "learning_rate": 1.8725810583086107e-05, "loss": 0.7436, "step": 3457 }, { "epoch": 0.4927329723567968, "grad_norm": 1.4123415480064383, "learning_rate": 1.872459548448136e-05, "loss": 0.7277, "step": 3458 }, { "epoch": 0.4928754630948988, "grad_norm": 1.511521866286356, "learning_rate": 1.8723379846240745e-05, "loss": 0.6714, "step": 3459 }, { "epoch": 0.49301795383300084, "grad_norm": 1.8460084461268644, "learning_rate": 1.872216366843945e-05, "loss": 0.6141, "step": 3460 }, { "epoch": 0.49316044457110286, "grad_norm": 1.4643480006143683, "learning_rate": 1.8720946951152702e-05, "loss": 0.6117, "step": 3461 }, { "epoch": 0.4933029353092049, "grad_norm": 1.4484340831491824, "learning_rate": 1.871972969445575e-05, "loss": 0.7525, "step": 3462 }, { "epoch": 0.4934454260473069, "grad_norm": 1.5110629253579988, "learning_rate": 1.871851189842389e-05, "loss": 0.7793, "step": 3463 }, { "epoch": 0.493587916785409, "grad_norm": 1.8526572751298729, "learning_rate": 1.8717293563132442e-05, "loss": 0.6587, "step": 3464 }, { "epoch": 0.493730407523511, "grad_norm": 1.3471590654042294, "learning_rate": 1.871607468865677e-05, "loss": 0.7358, "step": 3465 }, { "epoch": 0.493872898261613, "grad_norm": 1.5006393174930073, "learning_rate": 1.8714855275072255e-05, "loss": 0.698, "step": 3466 }, { "epoch": 0.49401538899971503, "grad_norm": 1.3518130378401951, "learning_rate": 1.871363532245433e-05, "loss": 0.7013, "step": 3467 }, { "epoch": 0.49415787973781705, "grad_norm": 1.336724103191479, "learning_rate": 1.871241483087844e-05, "loss": 0.7009, "step": 3468 }, { "epoch": 0.49430037047591907, "grad_norm": 1.6228985654012438, "learning_rate": 1.8711193800420086e-05, "loss": 0.7679, "step": 3469 }, { "epoch": 0.4944428612140211, "grad_norm": 1.4771264882244044, "learning_rate": 1.8709972231154785e-05, "loss": 0.7245, "step": 3470 }, { "epoch": 0.4945853519521231, "grad_norm": 1.438094965428327, "learning_rate": 1.87087501231581e-05, "loss": 0.679, "step": 3471 }, { "epoch": 0.49472784269022513, "grad_norm": 1.3952045611796537, "learning_rate": 1.8707527476505612e-05, "loss": 0.7092, "step": 3472 }, { "epoch": 0.49487033342832715, "grad_norm": 1.5336759241382205, "learning_rate": 1.8706304291272948e-05, "loss": 0.7167, "step": 3473 }, { "epoch": 0.49501282416642917, "grad_norm": 1.2501227875762893, "learning_rate": 1.870508056753577e-05, "loss": 0.611, "step": 3474 }, { "epoch": 0.4951553149045312, "grad_norm": 1.444939151656985, "learning_rate": 1.870385630536977e-05, "loss": 0.713, "step": 3475 }, { "epoch": 0.4952978056426332, "grad_norm": 1.8469215417004397, "learning_rate": 1.8702631504850655e-05, "loss": 0.6829, "step": 3476 }, { "epoch": 0.4954402963807353, "grad_norm": 1.6482461524147098, "learning_rate": 1.87014061660542e-05, "loss": 0.6611, "step": 3477 }, { "epoch": 0.4955827871188373, "grad_norm": 1.388780118146737, "learning_rate": 1.8700180289056183e-05, "loss": 0.6327, "step": 3478 }, { "epoch": 0.4957252778569393, "grad_norm": 1.5372030679854098, "learning_rate": 1.869895387393243e-05, "loss": 0.657, "step": 3479 }, { "epoch": 0.49586776859504134, "grad_norm": 1.381940606737592, "learning_rate": 1.8697726920758807e-05, "loss": 0.6813, "step": 3480 }, { "epoch": 0.49601025933314336, "grad_norm": 1.4053066309949749, "learning_rate": 1.8696499429611188e-05, "loss": 0.7248, "step": 3481 }, { "epoch": 0.4961527500712454, "grad_norm": 1.4477207078310377, "learning_rate": 1.8695271400565507e-05, "loss": 0.7018, "step": 3482 }, { "epoch": 0.4962952408093474, "grad_norm": 1.4604179557399901, "learning_rate": 1.8694042833697717e-05, "loss": 0.7304, "step": 3483 }, { "epoch": 0.4964377315474494, "grad_norm": 1.460272257130122, "learning_rate": 1.8692813729083806e-05, "loss": 0.6431, "step": 3484 }, { "epoch": 0.49658022228555143, "grad_norm": 1.358577358628463, "learning_rate": 1.8691584086799805e-05, "loss": 0.7582, "step": 3485 }, { "epoch": 0.49672271302365345, "grad_norm": 1.441956176171953, "learning_rate": 1.869035390692176e-05, "loss": 0.7162, "step": 3486 }, { "epoch": 0.49686520376175547, "grad_norm": 1.3895583396965978, "learning_rate": 1.8689123189525763e-05, "loss": 0.6651, "step": 3487 }, { "epoch": 0.4970076944998575, "grad_norm": 1.4716898464653714, "learning_rate": 1.868789193468794e-05, "loss": 0.6178, "step": 3488 }, { "epoch": 0.4971501852379595, "grad_norm": 1.3509753257295045, "learning_rate": 1.8686660142484446e-05, "loss": 0.5831, "step": 3489 }, { "epoch": 0.4972926759760616, "grad_norm": 1.466808286545598, "learning_rate": 1.868542781299147e-05, "loss": 0.6687, "step": 3490 }, { "epoch": 0.4974351667141636, "grad_norm": 1.4231445826569689, "learning_rate": 1.868419494628523e-05, "loss": 0.6465, "step": 3491 }, { "epoch": 0.4975776574522656, "grad_norm": 4.2811236204040055, "learning_rate": 1.8682961542441984e-05, "loss": 0.6144, "step": 3492 }, { "epoch": 0.49772014819036764, "grad_norm": 1.5369503932920117, "learning_rate": 1.8681727601538027e-05, "loss": 0.7445, "step": 3493 }, { "epoch": 0.49786263892846966, "grad_norm": 1.4822408574493158, "learning_rate": 1.868049312364967e-05, "loss": 0.6909, "step": 3494 }, { "epoch": 0.4980051296665717, "grad_norm": 1.3017135808286757, "learning_rate": 1.867925810885328e-05, "loss": 0.6134, "step": 3495 }, { "epoch": 0.4981476204046737, "grad_norm": 1.552651265326009, "learning_rate": 1.8678022557225236e-05, "loss": 0.7196, "step": 3496 }, { "epoch": 0.4982901111427757, "grad_norm": 1.6266012942460322, "learning_rate": 1.8676786468841964e-05, "loss": 0.7747, "step": 3497 }, { "epoch": 0.49843260188087773, "grad_norm": 1.4801825133069422, "learning_rate": 1.8675549843779916e-05, "loss": 0.6658, "step": 3498 }, { "epoch": 0.49857509261897975, "grad_norm": 1.7391409028966072, "learning_rate": 1.8674312682115583e-05, "loss": 0.6305, "step": 3499 }, { "epoch": 0.4987175833570818, "grad_norm": 1.865159511546938, "learning_rate": 1.8673074983925487e-05, "loss": 0.7395, "step": 3500 }, { "epoch": 0.4988600740951838, "grad_norm": 1.4636866474269516, "learning_rate": 1.867183674928618e-05, "loss": 0.7095, "step": 3501 }, { "epoch": 0.4990025648332858, "grad_norm": 1.5053534512245792, "learning_rate": 1.867059797827425e-05, "loss": 0.6522, "step": 3502 }, { "epoch": 0.4991450555713879, "grad_norm": 1.3616200890885357, "learning_rate": 1.8669358670966317e-05, "loss": 0.5825, "step": 3503 }, { "epoch": 0.4992875463094899, "grad_norm": 1.3738355923531245, "learning_rate": 1.866811882743904e-05, "loss": 0.7323, "step": 3504 }, { "epoch": 0.4994300370475919, "grad_norm": 1.375179493946672, "learning_rate": 1.86668784477691e-05, "loss": 0.7134, "step": 3505 }, { "epoch": 0.49957252778569394, "grad_norm": 1.5304729303089062, "learning_rate": 1.866563753203322e-05, "loss": 0.753, "step": 3506 }, { "epoch": 0.49971501852379596, "grad_norm": 1.7172614246861937, "learning_rate": 1.866439608030815e-05, "loss": 0.7087, "step": 3507 }, { "epoch": 0.499857509261898, "grad_norm": 1.4703773839995367, "learning_rate": 1.8663154092670682e-05, "loss": 0.6037, "step": 3508 }, { "epoch": 0.5, "grad_norm": 1.38755192253141, "learning_rate": 1.866191156919763e-05, "loss": 0.7026, "step": 3509 }, { "epoch": 0.500142490738102, "grad_norm": 1.432482918523011, "learning_rate": 1.8660668509965854e-05, "loss": 0.6981, "step": 3510 }, { "epoch": 0.500284981476204, "grad_norm": 1.3841932684371296, "learning_rate": 1.8659424915052233e-05, "loss": 0.7266, "step": 3511 }, { "epoch": 0.5004274722143061, "grad_norm": 1.5475047905207617, "learning_rate": 1.8658180784533692e-05, "loss": 0.7717, "step": 3512 }, { "epoch": 0.5005699629524081, "grad_norm": 3.4948071134884735, "learning_rate": 1.865693611848718e-05, "loss": 0.7117, "step": 3513 }, { "epoch": 0.5007124536905101, "grad_norm": 1.411664547095398, "learning_rate": 1.865569091698968e-05, "loss": 0.6944, "step": 3514 }, { "epoch": 0.5008549444286121, "grad_norm": 1.5543943564916376, "learning_rate": 1.8654445180118217e-05, "loss": 0.7013, "step": 3515 }, { "epoch": 0.5009974351667141, "grad_norm": 1.3929441171829071, "learning_rate": 1.8653198907949836e-05, "loss": 0.752, "step": 3516 }, { "epoch": 0.5011399259048162, "grad_norm": 1.7110910310723333, "learning_rate": 1.8651952100561628e-05, "loss": 0.6929, "step": 3517 }, { "epoch": 0.5012824166429182, "grad_norm": 1.4395520495287988, "learning_rate": 1.8650704758030708e-05, "loss": 0.7684, "step": 3518 }, { "epoch": 0.5014249073810202, "grad_norm": 1.5872618934414293, "learning_rate": 1.8649456880434222e-05, "loss": 0.6509, "step": 3519 }, { "epoch": 0.5015673981191222, "grad_norm": 1.5979017352196698, "learning_rate": 1.864820846784936e-05, "loss": 0.7407, "step": 3520 }, { "epoch": 0.5017098888572242, "grad_norm": 1.4345193218408754, "learning_rate": 1.864695952035334e-05, "loss": 0.6628, "step": 3521 }, { "epoch": 0.5018523795953264, "grad_norm": 1.3628263736038753, "learning_rate": 1.864571003802341e-05, "loss": 0.6412, "step": 3522 }, { "epoch": 0.5019948703334284, "grad_norm": 1.6177068485512074, "learning_rate": 1.864446002093685e-05, "loss": 0.6145, "step": 3523 }, { "epoch": 0.5021373610715304, "grad_norm": 1.4843192294715797, "learning_rate": 1.8643209469170983e-05, "loss": 0.6699, "step": 3524 }, { "epoch": 0.5022798518096324, "grad_norm": 1.3505405423070835, "learning_rate": 1.864195838280315e-05, "loss": 0.6121, "step": 3525 }, { "epoch": 0.5024223425477344, "grad_norm": 1.374474470857058, "learning_rate": 1.8640706761910746e-05, "loss": 0.6556, "step": 3526 }, { "epoch": 0.5025648332858365, "grad_norm": 1.3851514875529205, "learning_rate": 1.8639454606571174e-05, "loss": 0.6925, "step": 3527 }, { "epoch": 0.5027073240239385, "grad_norm": 1.4470628921527642, "learning_rate": 1.863820191686189e-05, "loss": 0.6375, "step": 3528 }, { "epoch": 0.5028498147620405, "grad_norm": 1.4218079998458022, "learning_rate": 1.8636948692860373e-05, "loss": 0.7014, "step": 3529 }, { "epoch": 0.5029923055001425, "grad_norm": 1.4345531821956448, "learning_rate": 1.8635694934644135e-05, "loss": 0.7446, "step": 3530 }, { "epoch": 0.5031347962382445, "grad_norm": 1.4570339673966195, "learning_rate": 1.8634440642290734e-05, "loss": 0.632, "step": 3531 }, { "epoch": 0.5032772869763465, "grad_norm": 2.215023333506568, "learning_rate": 1.8633185815877736e-05, "loss": 0.7743, "step": 3532 }, { "epoch": 0.5034197777144486, "grad_norm": 1.2497405344074004, "learning_rate": 1.8631930455482764e-05, "loss": 0.6608, "step": 3533 }, { "epoch": 0.5035622684525506, "grad_norm": 1.3261194130990468, "learning_rate": 1.8630674561183465e-05, "loss": 0.6121, "step": 3534 }, { "epoch": 0.5037047591906526, "grad_norm": 1.5356514882959387, "learning_rate": 1.862941813305752e-05, "loss": 0.6646, "step": 3535 }, { "epoch": 0.5038472499287546, "grad_norm": 1.409181568430904, "learning_rate": 1.8628161171182634e-05, "loss": 0.6723, "step": 3536 }, { "epoch": 0.5039897406668566, "grad_norm": 2.5956571326787565, "learning_rate": 1.8626903675636563e-05, "loss": 0.6899, "step": 3537 }, { "epoch": 0.5041322314049587, "grad_norm": 1.4461668327750525, "learning_rate": 1.862564564649708e-05, "loss": 0.7523, "step": 3538 }, { "epoch": 0.5042747221430607, "grad_norm": 1.7065963318359787, "learning_rate": 1.8624387083841996e-05, "loss": 0.6203, "step": 3539 }, { "epoch": 0.5044172128811627, "grad_norm": 1.5506330460248856, "learning_rate": 1.8623127987749157e-05, "loss": 0.6302, "step": 3540 }, { "epoch": 0.5045597036192647, "grad_norm": 1.682659971724037, "learning_rate": 1.8621868358296446e-05, "loss": 0.7025, "step": 3541 }, { "epoch": 0.5047021943573667, "grad_norm": 1.3778555066287164, "learning_rate": 1.8620608195561765e-05, "loss": 0.6686, "step": 3542 }, { "epoch": 0.5048446850954688, "grad_norm": 1.499372480283992, "learning_rate": 1.8619347499623063e-05, "loss": 0.6854, "step": 3543 }, { "epoch": 0.5049871758335708, "grad_norm": 1.326367296825186, "learning_rate": 1.861808627055832e-05, "loss": 0.684, "step": 3544 }, { "epoch": 0.5051296665716728, "grad_norm": 1.3994786548581322, "learning_rate": 1.861682450844554e-05, "loss": 0.7087, "step": 3545 }, { "epoch": 0.5052721573097748, "grad_norm": 1.4399649620601958, "learning_rate": 1.8615562213362773e-05, "loss": 0.6313, "step": 3546 }, { "epoch": 0.5054146480478768, "grad_norm": 1.5955982681132095, "learning_rate": 1.8614299385388085e-05, "loss": 0.7297, "step": 3547 }, { "epoch": 0.505557138785979, "grad_norm": 1.6141690894506735, "learning_rate": 1.861303602459959e-05, "loss": 0.7132, "step": 3548 }, { "epoch": 0.505699629524081, "grad_norm": 1.4268009460502606, "learning_rate": 1.861177213107543e-05, "loss": 0.6172, "step": 3549 }, { "epoch": 0.505842120262183, "grad_norm": 1.585330422751513, "learning_rate": 1.8610507704893778e-05, "loss": 0.6863, "step": 3550 }, { "epoch": 0.505984611000285, "grad_norm": 1.3901144770416543, "learning_rate": 1.8609242746132847e-05, "loss": 0.7054, "step": 3551 }, { "epoch": 0.506127101738387, "grad_norm": 1.465436141260383, "learning_rate": 1.860797725487087e-05, "loss": 0.7519, "step": 3552 }, { "epoch": 0.5062695924764891, "grad_norm": 1.5964759102442736, "learning_rate": 1.8606711231186126e-05, "loss": 0.6928, "step": 3553 }, { "epoch": 0.5064120832145911, "grad_norm": 1.4591641644603086, "learning_rate": 1.8605444675156915e-05, "loss": 0.701, "step": 3554 }, { "epoch": 0.5065545739526931, "grad_norm": 1.3823074185442221, "learning_rate": 1.8604177586861584e-05, "loss": 0.5979, "step": 3555 }, { "epoch": 0.5066970646907951, "grad_norm": 1.4970813536967909, "learning_rate": 1.8602909966378503e-05, "loss": 0.7026, "step": 3556 }, { "epoch": 0.5068395554288971, "grad_norm": 1.4032877553298595, "learning_rate": 1.8601641813786074e-05, "loss": 0.6138, "step": 3557 }, { "epoch": 0.5069820461669992, "grad_norm": 1.858446386911231, "learning_rate": 1.8600373129162738e-05, "loss": 0.6367, "step": 3558 }, { "epoch": 0.5071245369051012, "grad_norm": 1.6612023179134974, "learning_rate": 1.8599103912586966e-05, "loss": 0.6438, "step": 3559 }, { "epoch": 0.5072670276432032, "grad_norm": 1.3046755038240667, "learning_rate": 1.8597834164137255e-05, "loss": 0.665, "step": 3560 }, { "epoch": 0.5074095183813052, "grad_norm": 1.3879621442489611, "learning_rate": 1.8596563883892155e-05, "loss": 0.6998, "step": 3561 }, { "epoch": 0.5075520091194072, "grad_norm": 1.568891660764245, "learning_rate": 1.8595293071930226e-05, "loss": 0.7341, "step": 3562 }, { "epoch": 0.5076944998575093, "grad_norm": 1.6947136041713062, "learning_rate": 1.8594021728330068e-05, "loss": 0.632, "step": 3563 }, { "epoch": 0.5078369905956113, "grad_norm": 1.342850955824569, "learning_rate": 1.859274985317033e-05, "loss": 0.6433, "step": 3564 }, { "epoch": 0.5079794813337133, "grad_norm": 1.3544087725660343, "learning_rate": 1.8591477446529668e-05, "loss": 0.6806, "step": 3565 }, { "epoch": 0.5081219720718153, "grad_norm": 1.4263998186493236, "learning_rate": 1.8590204508486785e-05, "loss": 0.6926, "step": 3566 }, { "epoch": 0.5082644628099173, "grad_norm": 1.6013643811792306, "learning_rate": 1.8588931039120422e-05, "loss": 0.6404, "step": 3567 }, { "epoch": 0.5084069535480193, "grad_norm": 1.395761666374753, "learning_rate": 1.8587657038509337e-05, "loss": 0.6205, "step": 3568 }, { "epoch": 0.5085494442861214, "grad_norm": 1.468830666121999, "learning_rate": 1.8586382506732334e-05, "loss": 0.6633, "step": 3569 }, { "epoch": 0.5086919350242234, "grad_norm": 1.322362743310685, "learning_rate": 1.8585107443868248e-05, "loss": 0.6975, "step": 3570 }, { "epoch": 0.5088344257623254, "grad_norm": 1.4257511001109875, "learning_rate": 1.858383184999594e-05, "loss": 0.6873, "step": 3571 }, { "epoch": 0.5089769165004274, "grad_norm": 1.5082967056634768, "learning_rate": 1.8582555725194313e-05, "loss": 0.6858, "step": 3572 }, { "epoch": 0.5091194072385294, "grad_norm": 1.4839111520760737, "learning_rate": 1.8581279069542293e-05, "loss": 0.639, "step": 3573 }, { "epoch": 0.5092618979766316, "grad_norm": 1.3640549584791128, "learning_rate": 1.858000188311885e-05, "loss": 0.6701, "step": 3574 }, { "epoch": 0.5094043887147336, "grad_norm": 1.4904519491244097, "learning_rate": 1.8578724166002975e-05, "loss": 0.7325, "step": 3575 }, { "epoch": 0.5095468794528356, "grad_norm": 1.409765878317187, "learning_rate": 1.85774459182737e-05, "loss": 0.6464, "step": 3576 }, { "epoch": 0.5096893701909376, "grad_norm": 1.3030090653397328, "learning_rate": 1.8576167140010087e-05, "loss": 0.5809, "step": 3577 }, { "epoch": 0.5098318609290396, "grad_norm": 1.5169417773154048, "learning_rate": 1.857488783129123e-05, "loss": 0.6264, "step": 3578 }, { "epoch": 0.5099743516671417, "grad_norm": 1.4086329305213103, "learning_rate": 1.8573607992196265e-05, "loss": 0.682, "step": 3579 }, { "epoch": 0.5101168424052437, "grad_norm": 1.4896555545553847, "learning_rate": 1.8572327622804345e-05, "loss": 0.7373, "step": 3580 }, { "epoch": 0.5102593331433457, "grad_norm": 1.4352850000108446, "learning_rate": 1.8571046723194665e-05, "loss": 0.642, "step": 3581 }, { "epoch": 0.5104018238814477, "grad_norm": 1.4384833492204587, "learning_rate": 1.856976529344645e-05, "loss": 0.6242, "step": 3582 }, { "epoch": 0.5105443146195497, "grad_norm": 1.477122379829481, "learning_rate": 1.8568483333638963e-05, "loss": 0.6438, "step": 3583 }, { "epoch": 0.5106868053576518, "grad_norm": 1.49934734183515, "learning_rate": 1.85672008438515e-05, "loss": 0.6434, "step": 3584 }, { "epoch": 0.5108292960957538, "grad_norm": 1.3151643645954914, "learning_rate": 1.8565917824163374e-05, "loss": 0.6328, "step": 3585 }, { "epoch": 0.5109717868338558, "grad_norm": 1.4385155050109488, "learning_rate": 1.856463427465395e-05, "loss": 0.7168, "step": 3586 }, { "epoch": 0.5111142775719578, "grad_norm": 1.4956052323118834, "learning_rate": 1.856335019540262e-05, "loss": 0.6915, "step": 3587 }, { "epoch": 0.5112567683100598, "grad_norm": 1.3689153066376878, "learning_rate": 1.8562065586488805e-05, "loss": 0.8015, "step": 3588 }, { "epoch": 0.5113992590481619, "grad_norm": 1.5097839028766649, "learning_rate": 1.856078044799196e-05, "loss": 0.6434, "step": 3589 }, { "epoch": 0.5115417497862639, "grad_norm": 1.2801870073272479, "learning_rate": 1.8559494779991575e-05, "loss": 0.6396, "step": 3590 }, { "epoch": 0.5116842405243659, "grad_norm": 1.7213981086344647, "learning_rate": 1.855820858256717e-05, "loss": 0.6213, "step": 3591 }, { "epoch": 0.5118267312624679, "grad_norm": 1.4293967753328378, "learning_rate": 1.85569218557983e-05, "loss": 0.7737, "step": 3592 }, { "epoch": 0.5119692220005699, "grad_norm": 1.563106711762378, "learning_rate": 1.8555634599764554e-05, "loss": 0.6716, "step": 3593 }, { "epoch": 0.512111712738672, "grad_norm": 1.5586420879818328, "learning_rate": 1.855434681454555e-05, "loss": 0.6552, "step": 3594 }, { "epoch": 0.512254203476774, "grad_norm": 2.4389239899098363, "learning_rate": 1.8553058500220937e-05, "loss": 0.75, "step": 3595 }, { "epoch": 0.512396694214876, "grad_norm": 1.4202104317192281, "learning_rate": 1.8551769656870404e-05, "loss": 0.7569, "step": 3596 }, { "epoch": 0.512539184952978, "grad_norm": 1.3657594738330416, "learning_rate": 1.855048028457367e-05, "loss": 0.707, "step": 3597 }, { "epoch": 0.51268167569108, "grad_norm": 1.4888823129765425, "learning_rate": 1.8549190383410485e-05, "loss": 0.7511, "step": 3598 }, { "epoch": 0.512824166429182, "grad_norm": 1.9081136880682912, "learning_rate": 1.8547899953460628e-05, "loss": 0.7461, "step": 3599 }, { "epoch": 0.5129666571672842, "grad_norm": 1.4872216507685898, "learning_rate": 1.854660899480392e-05, "loss": 0.7899, "step": 3600 }, { "epoch": 0.5131091479053862, "grad_norm": 1.5880428829810063, "learning_rate": 1.8545317507520207e-05, "loss": 0.7528, "step": 3601 }, { "epoch": 0.5132516386434882, "grad_norm": 1.537513763593412, "learning_rate": 1.854402549168937e-05, "loss": 0.6966, "step": 3602 }, { "epoch": 0.5133941293815902, "grad_norm": 1.5752079441036957, "learning_rate": 1.8542732947391327e-05, "loss": 0.722, "step": 3603 }, { "epoch": 0.5135366201196923, "grad_norm": 1.4298747403494645, "learning_rate": 1.8541439874706024e-05, "loss": 0.6415, "step": 3604 }, { "epoch": 0.5136791108577943, "grad_norm": 1.292246921506194, "learning_rate": 1.8540146273713433e-05, "loss": 0.6894, "step": 3605 }, { "epoch": 0.5138216015958963, "grad_norm": 1.4402979279313202, "learning_rate": 1.8538852144493577e-05, "loss": 0.6816, "step": 3606 }, { "epoch": 0.5139640923339983, "grad_norm": 1.6507938131093793, "learning_rate": 1.853755748712649e-05, "loss": 0.6689, "step": 3607 }, { "epoch": 0.5141065830721003, "grad_norm": 1.4808619447759659, "learning_rate": 1.8536262301692258e-05, "loss": 0.7333, "step": 3608 }, { "epoch": 0.5142490738102024, "grad_norm": 1.336217098638979, "learning_rate": 1.8534966588270987e-05, "loss": 0.6648, "step": 3609 }, { "epoch": 0.5143915645483044, "grad_norm": 1.3903282662934746, "learning_rate": 1.853367034694282e-05, "loss": 0.6754, "step": 3610 }, { "epoch": 0.5145340552864064, "grad_norm": 1.5408139514711898, "learning_rate": 1.8532373577787938e-05, "loss": 0.6855, "step": 3611 }, { "epoch": 0.5146765460245084, "grad_norm": 1.6397353562590586, "learning_rate": 1.853107628088654e-05, "loss": 0.7347, "step": 3612 }, { "epoch": 0.5148190367626104, "grad_norm": 1.4637825698367504, "learning_rate": 1.852977845631887e-05, "loss": 0.761, "step": 3613 }, { "epoch": 0.5149615275007124, "grad_norm": 1.4644032251390662, "learning_rate": 1.8528480104165207e-05, "loss": 0.688, "step": 3614 }, { "epoch": 0.5151040182388145, "grad_norm": 1.4609982548803546, "learning_rate": 1.852718122450585e-05, "loss": 0.6127, "step": 3615 }, { "epoch": 0.5152465089769165, "grad_norm": 1.516191767114245, "learning_rate": 1.852588181742114e-05, "loss": 0.631, "step": 3616 }, { "epoch": 0.5153889997150185, "grad_norm": 1.4168333344725157, "learning_rate": 1.852458188299145e-05, "loss": 0.6798, "step": 3617 }, { "epoch": 0.5155314904531205, "grad_norm": 1.8130261826809013, "learning_rate": 1.852328142129718e-05, "loss": 0.6302, "step": 3618 }, { "epoch": 0.5156739811912225, "grad_norm": 1.3749164825551348, "learning_rate": 1.8521980432418768e-05, "loss": 0.6252, "step": 3619 }, { "epoch": 0.5158164719293246, "grad_norm": 1.8080643869025443, "learning_rate": 1.8520678916436686e-05, "loss": 0.6639, "step": 3620 }, { "epoch": 0.5159589626674266, "grad_norm": 1.409388216960681, "learning_rate": 1.8519376873431436e-05, "loss": 0.6711, "step": 3621 }, { "epoch": 0.5161014534055286, "grad_norm": 1.3892557786998039, "learning_rate": 1.8518074303483547e-05, "loss": 0.6637, "step": 3622 }, { "epoch": 0.5162439441436306, "grad_norm": 1.4920189479098085, "learning_rate": 1.851677120667359e-05, "loss": 0.6625, "step": 3623 }, { "epoch": 0.5163864348817326, "grad_norm": 1.6490578778035425, "learning_rate": 1.851546758308216e-05, "loss": 0.6018, "step": 3624 }, { "epoch": 0.5165289256198347, "grad_norm": 1.6169327618222271, "learning_rate": 1.8514163432789894e-05, "loss": 0.721, "step": 3625 }, { "epoch": 0.5166714163579368, "grad_norm": 1.5128738381825952, "learning_rate": 1.8512858755877456e-05, "loss": 0.7024, "step": 3626 }, { "epoch": 0.5168139070960388, "grad_norm": 1.4757058865363075, "learning_rate": 1.851155355242554e-05, "loss": 0.6666, "step": 3627 }, { "epoch": 0.5169563978341408, "grad_norm": 1.4567265926232433, "learning_rate": 1.851024782251488e-05, "loss": 0.6792, "step": 3628 }, { "epoch": 0.5170988885722428, "grad_norm": 1.3654807393635622, "learning_rate": 1.8508941566226235e-05, "loss": 0.5151, "step": 3629 }, { "epoch": 0.5172413793103449, "grad_norm": 1.4942870873511582, "learning_rate": 1.85076347836404e-05, "loss": 0.7071, "step": 3630 }, { "epoch": 0.5173838700484469, "grad_norm": 1.9639253111495638, "learning_rate": 1.8506327474838203e-05, "loss": 0.7459, "step": 3631 }, { "epoch": 0.5175263607865489, "grad_norm": 1.4545546595705545, "learning_rate": 1.850501963990051e-05, "loss": 0.6864, "step": 3632 }, { "epoch": 0.5176688515246509, "grad_norm": 1.5241216340385064, "learning_rate": 1.8503711278908204e-05, "loss": 0.6248, "step": 3633 }, { "epoch": 0.5178113422627529, "grad_norm": 1.7989655616934042, "learning_rate": 1.8502402391942212e-05, "loss": 0.7086, "step": 3634 }, { "epoch": 0.517953833000855, "grad_norm": 1.3313971750916278, "learning_rate": 1.8501092979083496e-05, "loss": 0.6713, "step": 3635 }, { "epoch": 0.518096323738957, "grad_norm": 1.336851606089795, "learning_rate": 1.8499783040413045e-05, "loss": 0.6921, "step": 3636 }, { "epoch": 0.518238814477059, "grad_norm": 1.3174168078245057, "learning_rate": 1.849847257601188e-05, "loss": 0.6369, "step": 3637 }, { "epoch": 0.518381305215161, "grad_norm": 1.5581940986232043, "learning_rate": 1.8497161585961055e-05, "loss": 0.7625, "step": 3638 }, { "epoch": 0.518523795953263, "grad_norm": 1.514198955033618, "learning_rate": 1.849585007034166e-05, "loss": 0.7472, "step": 3639 }, { "epoch": 0.518666286691365, "grad_norm": 1.4693092883841208, "learning_rate": 1.8494538029234815e-05, "loss": 0.7642, "step": 3640 }, { "epoch": 0.5188087774294671, "grad_norm": 1.5034252662020517, "learning_rate": 1.849322546272167e-05, "loss": 0.7007, "step": 3641 }, { "epoch": 0.5189512681675691, "grad_norm": 1.3654160963046587, "learning_rate": 1.849191237088342e-05, "loss": 0.7023, "step": 3642 }, { "epoch": 0.5190937589056711, "grad_norm": 1.5993117733367916, "learning_rate": 1.8490598753801267e-05, "loss": 0.7158, "step": 3643 }, { "epoch": 0.5192362496437731, "grad_norm": 1.2464761801909097, "learning_rate": 1.8489284611556472e-05, "loss": 0.6723, "step": 3644 }, { "epoch": 0.5193787403818751, "grad_norm": 1.489130903865015, "learning_rate": 1.8487969944230312e-05, "loss": 0.6501, "step": 3645 }, { "epoch": 0.5195212311199772, "grad_norm": 1.566453504749771, "learning_rate": 1.848665475190411e-05, "loss": 0.7101, "step": 3646 }, { "epoch": 0.5196637218580792, "grad_norm": 1.4239515438702757, "learning_rate": 1.8485339034659207e-05, "loss": 0.6384, "step": 3647 }, { "epoch": 0.5198062125961812, "grad_norm": 1.449633171191572, "learning_rate": 1.8484022792576987e-05, "loss": 0.6038, "step": 3648 }, { "epoch": 0.5199487033342832, "grad_norm": 1.5272551933884335, "learning_rate": 1.8482706025738856e-05, "loss": 0.7187, "step": 3649 }, { "epoch": 0.5200911940723852, "grad_norm": 1.5766080674307923, "learning_rate": 1.8481388734226264e-05, "loss": 0.7836, "step": 3650 }, { "epoch": 0.5202336848104874, "grad_norm": 1.4510814220789732, "learning_rate": 1.848007091812069e-05, "loss": 0.7679, "step": 3651 }, { "epoch": 0.5203761755485894, "grad_norm": 1.6647755461766969, "learning_rate": 1.847875257750364e-05, "loss": 0.6638, "step": 3652 }, { "epoch": 0.5205186662866914, "grad_norm": 1.4354517989847082, "learning_rate": 1.8477433712456658e-05, "loss": 0.7377, "step": 3653 }, { "epoch": 0.5206611570247934, "grad_norm": 1.43701023714647, "learning_rate": 1.847611432306132e-05, "loss": 0.6495, "step": 3654 }, { "epoch": 0.5208036477628954, "grad_norm": 1.642638797223943, "learning_rate": 1.847479440939923e-05, "loss": 0.7514, "step": 3655 }, { "epoch": 0.5209461385009975, "grad_norm": 2.3688638877778514, "learning_rate": 1.8473473971552033e-05, "loss": 0.6547, "step": 3656 }, { "epoch": 0.5210886292390995, "grad_norm": 1.4939051752202972, "learning_rate": 1.8472153009601393e-05, "loss": 0.5857, "step": 3657 }, { "epoch": 0.5212311199772015, "grad_norm": 1.405198916714052, "learning_rate": 1.847083152362902e-05, "loss": 0.7359, "step": 3658 }, { "epoch": 0.5213736107153035, "grad_norm": 1.5071208685723227, "learning_rate": 1.846950951371665e-05, "loss": 0.7386, "step": 3659 }, { "epoch": 0.5215161014534055, "grad_norm": 1.3687693318519438, "learning_rate": 1.8468186979946056e-05, "loss": 0.6384, "step": 3660 }, { "epoch": 0.5216585921915076, "grad_norm": 1.7561421657168008, "learning_rate": 1.8466863922399035e-05, "loss": 0.6896, "step": 3661 }, { "epoch": 0.5218010829296096, "grad_norm": 1.394818561985747, "learning_rate": 1.846554034115742e-05, "loss": 0.6544, "step": 3662 }, { "epoch": 0.5219435736677116, "grad_norm": 1.4658562773408639, "learning_rate": 1.846421623630308e-05, "loss": 0.6705, "step": 3663 }, { "epoch": 0.5220860644058136, "grad_norm": 1.3452415155885529, "learning_rate": 1.8462891607917912e-05, "loss": 0.6442, "step": 3664 }, { "epoch": 0.5222285551439156, "grad_norm": 1.4314027001491703, "learning_rate": 1.8461566456083854e-05, "loss": 0.7695, "step": 3665 }, { "epoch": 0.5223710458820177, "grad_norm": 1.4219972526130369, "learning_rate": 1.8460240780882858e-05, "loss": 0.6947, "step": 3666 }, { "epoch": 0.5225135366201197, "grad_norm": 1.2646913960447772, "learning_rate": 1.845891458239693e-05, "loss": 0.6713, "step": 3667 }, { "epoch": 0.5226560273582217, "grad_norm": 1.3388184620312855, "learning_rate": 1.845758786070809e-05, "loss": 0.6995, "step": 3668 }, { "epoch": 0.5227985180963237, "grad_norm": 1.5303437984903983, "learning_rate": 1.8456260615898407e-05, "loss": 0.6392, "step": 3669 }, { "epoch": 0.5229410088344257, "grad_norm": 1.4918092384495423, "learning_rate": 1.8454932848049972e-05, "loss": 0.7486, "step": 3670 }, { "epoch": 0.5230834995725278, "grad_norm": 1.2498717530126884, "learning_rate": 1.8453604557244907e-05, "loss": 0.6792, "step": 3671 }, { "epoch": 0.5232259903106298, "grad_norm": 1.5516113633271313, "learning_rate": 1.845227574356537e-05, "loss": 0.7452, "step": 3672 }, { "epoch": 0.5233684810487318, "grad_norm": 1.401869210191626, "learning_rate": 1.8450946407093554e-05, "loss": 0.6826, "step": 3673 }, { "epoch": 0.5235109717868338, "grad_norm": 1.4354652157285057, "learning_rate": 1.8449616547911682e-05, "loss": 0.7186, "step": 3674 }, { "epoch": 0.5236534625249358, "grad_norm": 1.4029856752320282, "learning_rate": 1.8448286166102005e-05, "loss": 0.6177, "step": 3675 }, { "epoch": 0.5237959532630379, "grad_norm": 1.2722482731485512, "learning_rate": 1.844695526174681e-05, "loss": 0.6157, "step": 3676 }, { "epoch": 0.52393844400114, "grad_norm": 2.018974482523924, "learning_rate": 1.8445623834928424e-05, "loss": 0.6764, "step": 3677 }, { "epoch": 0.524080934739242, "grad_norm": 1.4359698439824937, "learning_rate": 1.844429188572919e-05, "loss": 0.6684, "step": 3678 }, { "epoch": 0.524223425477344, "grad_norm": 1.5693497010257194, "learning_rate": 1.8442959414231496e-05, "loss": 0.7195, "step": 3679 }, { "epoch": 0.524365916215446, "grad_norm": 1.4974613840910689, "learning_rate": 1.8441626420517758e-05, "loss": 0.7088, "step": 3680 }, { "epoch": 0.5245084069535481, "grad_norm": 1.4800722502640238, "learning_rate": 1.844029290467042e-05, "loss": 0.7207, "step": 3681 }, { "epoch": 0.5246508976916501, "grad_norm": 1.3724167129672689, "learning_rate": 1.8438958866771975e-05, "loss": 0.7157, "step": 3682 }, { "epoch": 0.5247933884297521, "grad_norm": 1.4311039668930996, "learning_rate": 1.8437624306904923e-05, "loss": 0.6526, "step": 3683 }, { "epoch": 0.5249358791678541, "grad_norm": 1.8653435453992055, "learning_rate": 1.8436289225151815e-05, "loss": 0.7436, "step": 3684 }, { "epoch": 0.5250783699059561, "grad_norm": 1.3743079442755992, "learning_rate": 1.843495362159523e-05, "loss": 0.5716, "step": 3685 }, { "epoch": 0.5252208606440582, "grad_norm": 1.4995476554420082, "learning_rate": 1.843361749631778e-05, "loss": 0.6706, "step": 3686 }, { "epoch": 0.5253633513821602, "grad_norm": 1.4018732009540418, "learning_rate": 1.84322808494021e-05, "loss": 0.6853, "step": 3687 }, { "epoch": 0.5255058421202622, "grad_norm": 1.3865866319151476, "learning_rate": 1.843094368093087e-05, "loss": 0.6114, "step": 3688 }, { "epoch": 0.5256483328583642, "grad_norm": 1.3836823187567833, "learning_rate": 1.8429605990986797e-05, "loss": 0.6789, "step": 3689 }, { "epoch": 0.5257908235964662, "grad_norm": 1.5827133330620518, "learning_rate": 1.842826777965262e-05, "loss": 0.6906, "step": 3690 }, { "epoch": 0.5259333143345682, "grad_norm": 1.384891196321941, "learning_rate": 1.8426929047011105e-05, "loss": 0.6491, "step": 3691 }, { "epoch": 0.5260758050726703, "grad_norm": 1.4636708876597122, "learning_rate": 1.8425589793145065e-05, "loss": 0.6124, "step": 3692 }, { "epoch": 0.5262182958107723, "grad_norm": 1.6535708078775326, "learning_rate": 1.842425001813733e-05, "loss": 0.6812, "step": 3693 }, { "epoch": 0.5263607865488743, "grad_norm": 1.3332073427233888, "learning_rate": 1.8422909722070767e-05, "loss": 0.6414, "step": 3694 }, { "epoch": 0.5265032772869763, "grad_norm": 1.4941517967867963, "learning_rate": 1.842156890502828e-05, "loss": 0.6285, "step": 3695 }, { "epoch": 0.5266457680250783, "grad_norm": 1.387279764910489, "learning_rate": 1.8420227567092798e-05, "loss": 0.7097, "step": 3696 }, { "epoch": 0.5267882587631804, "grad_norm": 1.4733877269476519, "learning_rate": 1.8418885708347287e-05, "loss": 0.6563, "step": 3697 }, { "epoch": 0.5269307495012824, "grad_norm": 1.5229263286854833, "learning_rate": 1.8417543328874744e-05, "loss": 0.7583, "step": 3698 }, { "epoch": 0.5270732402393844, "grad_norm": 1.5093933878434826, "learning_rate": 1.8416200428758203e-05, "loss": 0.6139, "step": 3699 }, { "epoch": 0.5272157309774864, "grad_norm": 1.4055867343373707, "learning_rate": 1.841485700808072e-05, "loss": 0.6808, "step": 3700 }, { "epoch": 0.5273582217155884, "grad_norm": 1.4013505253753902, "learning_rate": 1.841351306692539e-05, "loss": 0.7568, "step": 3701 }, { "epoch": 0.5275007124536905, "grad_norm": 1.3303412226223332, "learning_rate": 1.8412168605375337e-05, "loss": 0.6368, "step": 3702 }, { "epoch": 0.5276432031917926, "grad_norm": 1.7891926940690759, "learning_rate": 1.841082362351372e-05, "loss": 0.6946, "step": 3703 }, { "epoch": 0.5277856939298946, "grad_norm": 1.7207856074892622, "learning_rate": 1.840947812142373e-05, "loss": 0.6173, "step": 3704 }, { "epoch": 0.5279281846679966, "grad_norm": 1.6398306779670428, "learning_rate": 1.8408132099188586e-05, "loss": 0.6284, "step": 3705 }, { "epoch": 0.5280706754060986, "grad_norm": 1.5113420972177898, "learning_rate": 1.8406785556891552e-05, "loss": 0.6688, "step": 3706 }, { "epoch": 0.5282131661442007, "grad_norm": 1.4023596670127318, "learning_rate": 1.8405438494615903e-05, "loss": 0.6946, "step": 3707 }, { "epoch": 0.5283556568823027, "grad_norm": 1.6331486483467432, "learning_rate": 1.8404090912444966e-05, "loss": 0.7194, "step": 3708 }, { "epoch": 0.5284981476204047, "grad_norm": 1.6497908639058043, "learning_rate": 1.8402742810462087e-05, "loss": 0.6989, "step": 3709 }, { "epoch": 0.5286406383585067, "grad_norm": 1.3911156164031924, "learning_rate": 1.8401394188750654e-05, "loss": 0.6947, "step": 3710 }, { "epoch": 0.5287831290966087, "grad_norm": 1.3168841101970066, "learning_rate": 1.840004504739408e-05, "loss": 0.6455, "step": 3711 }, { "epoch": 0.5289256198347108, "grad_norm": 1.5456322923382935, "learning_rate": 1.8398695386475808e-05, "loss": 0.658, "step": 3712 }, { "epoch": 0.5290681105728128, "grad_norm": 1.432382259177841, "learning_rate": 1.839734520607932e-05, "loss": 0.6903, "step": 3713 }, { "epoch": 0.5292106013109148, "grad_norm": 1.6634542708267848, "learning_rate": 1.8395994506288132e-05, "loss": 0.8222, "step": 3714 }, { "epoch": 0.5293530920490168, "grad_norm": 1.439161895481017, "learning_rate": 1.8394643287185788e-05, "loss": 0.6339, "step": 3715 }, { "epoch": 0.5294955827871188, "grad_norm": 1.5066104318040188, "learning_rate": 1.8393291548855856e-05, "loss": 0.768, "step": 3716 }, { "epoch": 0.5296380735252209, "grad_norm": 1.2555357820452628, "learning_rate": 1.8391939291381952e-05, "loss": 0.5999, "step": 3717 }, { "epoch": 0.5297805642633229, "grad_norm": 1.5009733754820413, "learning_rate": 1.839058651484771e-05, "loss": 0.6436, "step": 3718 }, { "epoch": 0.5299230550014249, "grad_norm": 1.5890480582973046, "learning_rate": 1.8389233219336807e-05, "loss": 0.7119, "step": 3719 }, { "epoch": 0.5300655457395269, "grad_norm": 1.5345961143188396, "learning_rate": 1.838787940493295e-05, "loss": 0.7539, "step": 3720 }, { "epoch": 0.5302080364776289, "grad_norm": 1.486151669595198, "learning_rate": 1.8386525071719865e-05, "loss": 0.6325, "step": 3721 }, { "epoch": 0.530350527215731, "grad_norm": 1.4723130415615597, "learning_rate": 1.838517021978133e-05, "loss": 0.619, "step": 3722 }, { "epoch": 0.530493017953833, "grad_norm": 1.4903888587540872, "learning_rate": 1.838381484920114e-05, "loss": 0.6927, "step": 3723 }, { "epoch": 0.530635508691935, "grad_norm": 1.4896828115316945, "learning_rate": 1.8382458960063132e-05, "loss": 0.65, "step": 3724 }, { "epoch": 0.530777999430037, "grad_norm": 1.6599544154429298, "learning_rate": 1.838110255245117e-05, "loss": 0.635, "step": 3725 }, { "epoch": 0.530920490168139, "grad_norm": 1.483033596254292, "learning_rate": 1.8379745626449148e-05, "loss": 0.7116, "step": 3726 }, { "epoch": 0.531062980906241, "grad_norm": 1.3596708454154478, "learning_rate": 1.8378388182141e-05, "loss": 0.6195, "step": 3727 }, { "epoch": 0.5312054716443431, "grad_norm": 1.2899168926772557, "learning_rate": 1.8377030219610675e-05, "loss": 0.6372, "step": 3728 }, { "epoch": 0.5313479623824452, "grad_norm": 1.2713129685879738, "learning_rate": 1.8375671738942183e-05, "loss": 0.613, "step": 3729 }, { "epoch": 0.5314904531205472, "grad_norm": 1.3749884431580557, "learning_rate": 1.837431274021954e-05, "loss": 0.6334, "step": 3730 }, { "epoch": 0.5316329438586492, "grad_norm": 1.3267485441137448, "learning_rate": 1.8372953223526804e-05, "loss": 0.6496, "step": 3731 }, { "epoch": 0.5317754345967513, "grad_norm": 1.3031055611174154, "learning_rate": 1.837159318894806e-05, "loss": 0.7642, "step": 3732 }, { "epoch": 0.5319179253348533, "grad_norm": 1.2890693461555287, "learning_rate": 1.8370232636567435e-05, "loss": 0.6875, "step": 3733 }, { "epoch": 0.5320604160729553, "grad_norm": 1.4972132178219637, "learning_rate": 1.8368871566469083e-05, "loss": 0.6903, "step": 3734 }, { "epoch": 0.5322029068110573, "grad_norm": 1.5262476105348615, "learning_rate": 1.8367509978737187e-05, "loss": 0.6989, "step": 3735 }, { "epoch": 0.5323453975491593, "grad_norm": 1.4015737308076825, "learning_rate": 1.8366147873455963e-05, "loss": 0.6973, "step": 3736 }, { "epoch": 0.5324878882872613, "grad_norm": 1.3362050163311157, "learning_rate": 1.836478525070966e-05, "loss": 0.7013, "step": 3737 }, { "epoch": 0.5326303790253634, "grad_norm": 1.377671586358271, "learning_rate": 1.836342211058256e-05, "loss": 0.6122, "step": 3738 }, { "epoch": 0.5327728697634654, "grad_norm": 1.408342112100154, "learning_rate": 1.836205845315898e-05, "loss": 0.6581, "step": 3739 }, { "epoch": 0.5329153605015674, "grad_norm": 1.4377170466387301, "learning_rate": 1.836069427852326e-05, "loss": 0.6293, "step": 3740 }, { "epoch": 0.5330578512396694, "grad_norm": 1.5090039931691384, "learning_rate": 1.8359329586759782e-05, "loss": 0.6758, "step": 3741 }, { "epoch": 0.5332003419777714, "grad_norm": 1.3459406466175718, "learning_rate": 1.835796437795295e-05, "loss": 0.5791, "step": 3742 }, { "epoch": 0.5333428327158735, "grad_norm": 1.7786557957258253, "learning_rate": 1.8356598652187208e-05, "loss": 0.7472, "step": 3743 }, { "epoch": 0.5334853234539755, "grad_norm": 1.4929636297707656, "learning_rate": 1.835523240954703e-05, "loss": 0.7873, "step": 3744 }, { "epoch": 0.5336278141920775, "grad_norm": 1.537199271242338, "learning_rate": 1.8353865650116925e-05, "loss": 0.798, "step": 3745 }, { "epoch": 0.5337703049301795, "grad_norm": 1.3461804880061587, "learning_rate": 1.835249837398142e-05, "loss": 0.6464, "step": 3746 }, { "epoch": 0.5339127956682815, "grad_norm": 1.6546727077422758, "learning_rate": 1.835113058122509e-05, "loss": 0.7113, "step": 3747 }, { "epoch": 0.5340552864063836, "grad_norm": 1.6836807286056428, "learning_rate": 1.8349762271932536e-05, "loss": 0.6829, "step": 3748 }, { "epoch": 0.5341977771444856, "grad_norm": 1.4202157292878155, "learning_rate": 1.8348393446188394e-05, "loss": 0.6083, "step": 3749 }, { "epoch": 0.5343402678825876, "grad_norm": 1.455791400603499, "learning_rate": 1.834702410407732e-05, "loss": 0.7134, "step": 3750 }, { "epoch": 0.5344827586206896, "grad_norm": 1.4870123649484914, "learning_rate": 1.8345654245684018e-05, "loss": 0.7125, "step": 3751 }, { "epoch": 0.5346252493587916, "grad_norm": 1.524605388951589, "learning_rate": 1.834428387109322e-05, "loss": 0.7271, "step": 3752 }, { "epoch": 0.5347677400968937, "grad_norm": 1.3266937799773393, "learning_rate": 1.834291298038968e-05, "loss": 0.6969, "step": 3753 }, { "epoch": 0.5349102308349957, "grad_norm": 1.4215478711502854, "learning_rate": 1.834154157365819e-05, "loss": 0.6233, "step": 3754 }, { "epoch": 0.5350527215730978, "grad_norm": 1.6629714892852472, "learning_rate": 1.834016965098358e-05, "loss": 0.6771, "step": 3755 }, { "epoch": 0.5351952123111998, "grad_norm": 1.38406744634318, "learning_rate": 1.8338797212450703e-05, "loss": 0.8033, "step": 3756 }, { "epoch": 0.5353377030493018, "grad_norm": 1.764922072075166, "learning_rate": 1.833742425814445e-05, "loss": 0.6864, "step": 3757 }, { "epoch": 0.5354801937874039, "grad_norm": 1.3963601966489156, "learning_rate": 1.8336050788149736e-05, "loss": 0.7364, "step": 3758 }, { "epoch": 0.5356226845255059, "grad_norm": 1.4910611353642858, "learning_rate": 1.833467680255152e-05, "loss": 0.6439, "step": 3759 }, { "epoch": 0.5357651752636079, "grad_norm": 1.4656064620337341, "learning_rate": 1.8333302301434782e-05, "loss": 0.7759, "step": 3760 }, { "epoch": 0.5359076660017099, "grad_norm": 1.352652713957299, "learning_rate": 1.833192728488454e-05, "loss": 0.745, "step": 3761 }, { "epoch": 0.5360501567398119, "grad_norm": 1.3716092896689673, "learning_rate": 1.8330551752985835e-05, "loss": 0.6994, "step": 3762 }, { "epoch": 0.536192647477914, "grad_norm": 1.367001037813085, "learning_rate": 1.832917570582376e-05, "loss": 0.6532, "step": 3763 }, { "epoch": 0.536335138216016, "grad_norm": 1.3342860918656503, "learning_rate": 1.8327799143483415e-05, "loss": 0.6219, "step": 3764 }, { "epoch": 0.536477628954118, "grad_norm": 1.3302744180766446, "learning_rate": 1.832642206604995e-05, "loss": 0.6929, "step": 3765 }, { "epoch": 0.53662011969222, "grad_norm": 1.4459311495041836, "learning_rate": 1.832504447360854e-05, "loss": 0.7425, "step": 3766 }, { "epoch": 0.536762610430322, "grad_norm": 1.3193303425469634, "learning_rate": 1.8323666366244387e-05, "loss": 0.6552, "step": 3767 }, { "epoch": 0.536905101168424, "grad_norm": 1.5140228614664504, "learning_rate": 1.832228774404273e-05, "loss": 0.693, "step": 3768 }, { "epoch": 0.5370475919065261, "grad_norm": 1.4084739709382903, "learning_rate": 1.8320908607088847e-05, "loss": 0.6976, "step": 3769 }, { "epoch": 0.5371900826446281, "grad_norm": 1.3727948304698094, "learning_rate": 1.8319528955468038e-05, "loss": 0.5715, "step": 3770 }, { "epoch": 0.5373325733827301, "grad_norm": 1.402805122324526, "learning_rate": 1.8318148789265634e-05, "loss": 0.7216, "step": 3771 }, { "epoch": 0.5374750641208321, "grad_norm": 1.4708437402343988, "learning_rate": 1.8316768108567004e-05, "loss": 0.7576, "step": 3772 }, { "epoch": 0.5376175548589341, "grad_norm": 1.5066940845235197, "learning_rate": 1.8315386913457548e-05, "loss": 0.696, "step": 3773 }, { "epoch": 0.5377600455970362, "grad_norm": 1.6575291638936631, "learning_rate": 1.8314005204022693e-05, "loss": 0.7025, "step": 3774 }, { "epoch": 0.5379025363351382, "grad_norm": 1.7006757849917515, "learning_rate": 1.83126229803479e-05, "loss": 0.7967, "step": 3775 }, { "epoch": 0.5380450270732402, "grad_norm": 1.3647856404554566, "learning_rate": 1.8311240242518666e-05, "loss": 0.6814, "step": 3776 }, { "epoch": 0.5381875178113422, "grad_norm": 1.465231370935322, "learning_rate": 1.8309856990620518e-05, "loss": 0.644, "step": 3777 }, { "epoch": 0.5383300085494442, "grad_norm": 1.4060997628493643, "learning_rate": 1.8308473224739005e-05, "loss": 0.7009, "step": 3778 }, { "epoch": 0.5384724992875463, "grad_norm": 1.5314674499467549, "learning_rate": 1.830708894495972e-05, "loss": 0.6557, "step": 3779 }, { "epoch": 0.5386149900256484, "grad_norm": 1.960216970780895, "learning_rate": 1.8305704151368292e-05, "loss": 0.6936, "step": 3780 }, { "epoch": 0.5387574807637504, "grad_norm": 1.276426828369844, "learning_rate": 1.830431884405036e-05, "loss": 0.5904, "step": 3781 }, { "epoch": 0.5388999715018524, "grad_norm": 1.4610178264071008, "learning_rate": 1.830293302309162e-05, "loss": 0.6284, "step": 3782 }, { "epoch": 0.5390424622399544, "grad_norm": 1.5192875824417216, "learning_rate": 1.830154668857778e-05, "loss": 0.6854, "step": 3783 }, { "epoch": 0.5391849529780565, "grad_norm": 1.3858109007426405, "learning_rate": 1.8300159840594595e-05, "loss": 0.6635, "step": 3784 }, { "epoch": 0.5393274437161585, "grad_norm": 1.2512829584751133, "learning_rate": 1.8298772479227835e-05, "loss": 0.6772, "step": 3785 }, { "epoch": 0.5394699344542605, "grad_norm": 1.4732850888124238, "learning_rate": 1.8297384604563323e-05, "loss": 0.6845, "step": 3786 }, { "epoch": 0.5396124251923625, "grad_norm": 1.2824389890538022, "learning_rate": 1.8295996216686893e-05, "loss": 0.6781, "step": 3787 }, { "epoch": 0.5397549159304645, "grad_norm": 1.3858447685190103, "learning_rate": 1.829460731568442e-05, "loss": 0.6144, "step": 3788 }, { "epoch": 0.5398974066685666, "grad_norm": 1.3474745313493977, "learning_rate": 1.829321790164182e-05, "loss": 0.6225, "step": 3789 }, { "epoch": 0.5400398974066686, "grad_norm": 1.4040481456402651, "learning_rate": 1.829182797464502e-05, "loss": 0.7467, "step": 3790 }, { "epoch": 0.5401823881447706, "grad_norm": 1.5075823530390988, "learning_rate": 1.8290437534780002e-05, "loss": 0.7023, "step": 3791 }, { "epoch": 0.5403248788828726, "grad_norm": 1.932576050556033, "learning_rate": 1.8289046582132758e-05, "loss": 0.7697, "step": 3792 }, { "epoch": 0.5404673696209746, "grad_norm": 1.374578131370925, "learning_rate": 1.828765511678932e-05, "loss": 0.7014, "step": 3793 }, { "epoch": 0.5406098603590767, "grad_norm": 1.4491762058934305, "learning_rate": 1.8286263138835765e-05, "loss": 0.5999, "step": 3794 }, { "epoch": 0.5407523510971787, "grad_norm": 1.3325745193831144, "learning_rate": 1.828487064835818e-05, "loss": 0.6496, "step": 3795 }, { "epoch": 0.5408948418352807, "grad_norm": 1.3800948758425748, "learning_rate": 1.8283477645442696e-05, "loss": 0.6913, "step": 3796 }, { "epoch": 0.5410373325733827, "grad_norm": 1.5362115860272678, "learning_rate": 1.8282084130175478e-05, "loss": 0.8131, "step": 3797 }, { "epoch": 0.5411798233114847, "grad_norm": 1.3251317205869722, "learning_rate": 1.828069010264271e-05, "loss": 0.7027, "step": 3798 }, { "epoch": 0.5413223140495868, "grad_norm": 2.0223313510803047, "learning_rate": 1.8279295562930622e-05, "loss": 0.7524, "step": 3799 }, { "epoch": 0.5414648047876888, "grad_norm": 1.3220665091611756, "learning_rate": 1.8277900511125467e-05, "loss": 0.6209, "step": 3800 }, { "epoch": 0.5416072955257908, "grad_norm": 1.5465732305742006, "learning_rate": 1.827650494731353e-05, "loss": 0.6718, "step": 3801 }, { "epoch": 0.5417497862638928, "grad_norm": 1.4223998022553408, "learning_rate": 1.8275108871581137e-05, "loss": 0.6342, "step": 3802 }, { "epoch": 0.5418922770019948, "grad_norm": 1.4079893702367277, "learning_rate": 1.8273712284014627e-05, "loss": 0.6773, "step": 3803 }, { "epoch": 0.5420347677400968, "grad_norm": 1.630501078377699, "learning_rate": 1.827231518470039e-05, "loss": 0.7941, "step": 3804 }, { "epoch": 0.5421772584781989, "grad_norm": 1.6181767678861152, "learning_rate": 1.8270917573724842e-05, "loss": 0.7758, "step": 3805 }, { "epoch": 0.542319749216301, "grad_norm": 1.5224059577017117, "learning_rate": 1.8269519451174424e-05, "loss": 0.7943, "step": 3806 }, { "epoch": 0.542462239954403, "grad_norm": 1.4327793981096133, "learning_rate": 1.8268120817135612e-05, "loss": 0.7341, "step": 3807 }, { "epoch": 0.542604730692505, "grad_norm": 1.3930204523962544, "learning_rate": 1.826672167169492e-05, "loss": 0.6847, "step": 3808 }, { "epoch": 0.542747221430607, "grad_norm": 1.4358059110746089, "learning_rate": 1.8265322014938883e-05, "loss": 0.6808, "step": 3809 }, { "epoch": 0.5428897121687091, "grad_norm": 1.331680348458745, "learning_rate": 1.8263921846954072e-05, "loss": 0.7803, "step": 3810 }, { "epoch": 0.5430322029068111, "grad_norm": 1.3303528595390905, "learning_rate": 1.8262521167827097e-05, "loss": 0.6987, "step": 3811 }, { "epoch": 0.5431746936449131, "grad_norm": 1.3965126737447355, "learning_rate": 1.8261119977644586e-05, "loss": 0.7083, "step": 3812 }, { "epoch": 0.5433171843830151, "grad_norm": 1.4850482355358385, "learning_rate": 1.825971827649321e-05, "loss": 0.6919, "step": 3813 }, { "epoch": 0.5434596751211171, "grad_norm": 1.385114489066073, "learning_rate": 1.825831606445967e-05, "loss": 0.6017, "step": 3814 }, { "epoch": 0.5436021658592192, "grad_norm": 1.3870812622937703, "learning_rate": 1.825691334163069e-05, "loss": 0.6832, "step": 3815 }, { "epoch": 0.5437446565973212, "grad_norm": 1.5869949591468324, "learning_rate": 1.8255510108093034e-05, "loss": 0.7352, "step": 3816 }, { "epoch": 0.5438871473354232, "grad_norm": 1.5787375078214658, "learning_rate": 1.825410636393349e-05, "loss": 0.725, "step": 3817 }, { "epoch": 0.5440296380735252, "grad_norm": 1.430295341673362, "learning_rate": 1.82527021092389e-05, "loss": 0.7339, "step": 3818 }, { "epoch": 0.5441721288116272, "grad_norm": 1.3567517908173388, "learning_rate": 1.8251297344096097e-05, "loss": 0.7227, "step": 3819 }, { "epoch": 0.5443146195497293, "grad_norm": 1.4148569947623826, "learning_rate": 1.8249892068591984e-05, "loss": 0.6595, "step": 3820 }, { "epoch": 0.5444571102878313, "grad_norm": 1.2853953148621826, "learning_rate": 1.8248486282813478e-05, "loss": 0.6082, "step": 3821 }, { "epoch": 0.5445996010259333, "grad_norm": 1.3088213612403812, "learning_rate": 1.824707998684753e-05, "loss": 0.7121, "step": 3822 }, { "epoch": 0.5447420917640353, "grad_norm": 1.3802692983555251, "learning_rate": 1.8245673180781117e-05, "loss": 0.7417, "step": 3823 }, { "epoch": 0.5448845825021373, "grad_norm": 1.4004722083064727, "learning_rate": 1.8244265864701257e-05, "loss": 0.6835, "step": 3824 }, { "epoch": 0.5450270732402394, "grad_norm": 1.4428794230513147, "learning_rate": 1.8242858038695e-05, "loss": 0.6363, "step": 3825 }, { "epoch": 0.5451695639783414, "grad_norm": 1.4375142735195694, "learning_rate": 1.8241449702849415e-05, "loss": 0.7183, "step": 3826 }, { "epoch": 0.5453120547164434, "grad_norm": 1.345000123231434, "learning_rate": 1.8240040857251618e-05, "loss": 0.7622, "step": 3827 }, { "epoch": 0.5454545454545454, "grad_norm": 1.3924801103247284, "learning_rate": 1.8238631501988747e-05, "loss": 0.6717, "step": 3828 }, { "epoch": 0.5455970361926474, "grad_norm": 1.3171990441809207, "learning_rate": 1.823722163714797e-05, "loss": 0.658, "step": 3829 }, { "epoch": 0.5457395269307495, "grad_norm": 1.40471786583595, "learning_rate": 1.8235811262816494e-05, "loss": 0.6669, "step": 3830 }, { "epoch": 0.5458820176688515, "grad_norm": 1.3818403585922137, "learning_rate": 1.8234400379081555e-05, "loss": 0.6387, "step": 3831 }, { "epoch": 0.5460245084069536, "grad_norm": 1.6537416557548976, "learning_rate": 1.8232988986030414e-05, "loss": 0.721, "step": 3832 }, { "epoch": 0.5461669991450556, "grad_norm": 1.3880218996451696, "learning_rate": 1.8231577083750376e-05, "loss": 0.6953, "step": 3833 }, { "epoch": 0.5463094898831576, "grad_norm": 1.3402500648873086, "learning_rate": 1.8230164672328765e-05, "loss": 0.6352, "step": 3834 }, { "epoch": 0.5464519806212597, "grad_norm": 1.3909474206802952, "learning_rate": 1.8228751751852943e-05, "loss": 0.6474, "step": 3835 }, { "epoch": 0.5465944713593617, "grad_norm": 1.449585878632828, "learning_rate": 1.8227338322410303e-05, "loss": 0.6431, "step": 3836 }, { "epoch": 0.5467369620974637, "grad_norm": 1.3315662682313576, "learning_rate": 1.822592438408827e-05, "loss": 0.6239, "step": 3837 }, { "epoch": 0.5468794528355657, "grad_norm": 1.5262764889985774, "learning_rate": 1.8224509936974296e-05, "loss": 0.6995, "step": 3838 }, { "epoch": 0.5470219435736677, "grad_norm": 1.4169560997540258, "learning_rate": 1.822309498115587e-05, "loss": 0.6809, "step": 3839 }, { "epoch": 0.5471644343117698, "grad_norm": 1.4768109444832511, "learning_rate": 1.822167951672051e-05, "loss": 0.6304, "step": 3840 }, { "epoch": 0.5473069250498718, "grad_norm": 1.2713409765748658, "learning_rate": 1.8220263543755766e-05, "loss": 0.6482, "step": 3841 }, { "epoch": 0.5474494157879738, "grad_norm": 1.395711788706277, "learning_rate": 1.8218847062349215e-05, "loss": 0.7095, "step": 3842 }, { "epoch": 0.5475919065260758, "grad_norm": 1.3235515954249333, "learning_rate": 1.821743007258848e-05, "loss": 0.6793, "step": 3843 }, { "epoch": 0.5477343972641778, "grad_norm": 1.3821752019408646, "learning_rate": 1.8216012574561194e-05, "loss": 0.7315, "step": 3844 }, { "epoch": 0.5478768880022798, "grad_norm": 1.2539419513129095, "learning_rate": 1.8214594568355035e-05, "loss": 0.6538, "step": 3845 }, { "epoch": 0.5480193787403819, "grad_norm": 1.4381871666516062, "learning_rate": 1.8213176054057712e-05, "loss": 0.6976, "step": 3846 }, { "epoch": 0.5481618694784839, "grad_norm": 1.3887647003234875, "learning_rate": 1.8211757031756966e-05, "loss": 0.7571, "step": 3847 }, { "epoch": 0.5483043602165859, "grad_norm": 1.321844946625298, "learning_rate": 1.821033750154056e-05, "loss": 0.6743, "step": 3848 }, { "epoch": 0.5484468509546879, "grad_norm": 1.2512463378869314, "learning_rate": 1.82089174634963e-05, "loss": 0.6437, "step": 3849 }, { "epoch": 0.54858934169279, "grad_norm": 1.2243541965854003, "learning_rate": 1.8207496917712016e-05, "loss": 0.6887, "step": 3850 }, { "epoch": 0.548731832430892, "grad_norm": 1.3090804884685598, "learning_rate": 1.8206075864275577e-05, "loss": 0.6524, "step": 3851 }, { "epoch": 0.548874323168994, "grad_norm": 1.3955909483293476, "learning_rate": 1.820465430327487e-05, "loss": 0.5924, "step": 3852 }, { "epoch": 0.549016813907096, "grad_norm": 1.4749090585602327, "learning_rate": 1.820323223479783e-05, "loss": 0.7227, "step": 3853 }, { "epoch": 0.549159304645198, "grad_norm": 1.360502805510824, "learning_rate": 1.820180965893241e-05, "loss": 0.6533, "step": 3854 }, { "epoch": 0.5493017953833, "grad_norm": 1.3536428586944353, "learning_rate": 1.8200386575766598e-05, "loss": 0.7165, "step": 3855 }, { "epoch": 0.5494442861214021, "grad_norm": 1.4068926195783678, "learning_rate": 1.819896298538842e-05, "loss": 0.667, "step": 3856 }, { "epoch": 0.5495867768595041, "grad_norm": 1.435227987543345, "learning_rate": 1.8197538887885926e-05, "loss": 0.7209, "step": 3857 }, { "epoch": 0.5497292675976062, "grad_norm": 1.4335446007040087, "learning_rate": 1.81961142833472e-05, "loss": 0.6401, "step": 3858 }, { "epoch": 0.5498717583357082, "grad_norm": 1.3702022810193022, "learning_rate": 1.8194689171860353e-05, "loss": 0.6469, "step": 3859 }, { "epoch": 0.5500142490738102, "grad_norm": 1.481262874685561, "learning_rate": 1.819326355351354e-05, "loss": 0.7322, "step": 3860 }, { "epoch": 0.5501567398119123, "grad_norm": 1.438260630402604, "learning_rate": 1.819183742839493e-05, "loss": 0.6107, "step": 3861 }, { "epoch": 0.5502992305500143, "grad_norm": 1.407228426868584, "learning_rate": 1.819041079659274e-05, "loss": 0.7786, "step": 3862 }, { "epoch": 0.5504417212881163, "grad_norm": 1.3469874745587174, "learning_rate": 1.8188983658195203e-05, "loss": 0.8083, "step": 3863 }, { "epoch": 0.5505842120262183, "grad_norm": 1.5679266437632287, "learning_rate": 1.8187556013290596e-05, "loss": 0.7162, "step": 3864 }, { "epoch": 0.5507267027643203, "grad_norm": 1.3191951536175492, "learning_rate": 1.8186127861967218e-05, "loss": 0.6394, "step": 3865 }, { "epoch": 0.5508691935024224, "grad_norm": 1.3523004498723874, "learning_rate": 1.8184699204313406e-05, "loss": 0.7463, "step": 3866 }, { "epoch": 0.5510116842405244, "grad_norm": 1.3431104357257113, "learning_rate": 1.8183270040417526e-05, "loss": 0.5865, "step": 3867 }, { "epoch": 0.5511541749786264, "grad_norm": 1.3570767259081085, "learning_rate": 1.818184037036797e-05, "loss": 0.6388, "step": 3868 }, { "epoch": 0.5512966657167284, "grad_norm": 1.4016355236626397, "learning_rate": 1.8180410194253176e-05, "loss": 0.6706, "step": 3869 }, { "epoch": 0.5514391564548304, "grad_norm": 1.8765904391195654, "learning_rate": 1.817897951216159e-05, "loss": 0.6977, "step": 3870 }, { "epoch": 0.5515816471929325, "grad_norm": 1.4611841724396772, "learning_rate": 1.817754832418172e-05, "loss": 0.7126, "step": 3871 }, { "epoch": 0.5517241379310345, "grad_norm": 1.3636828193016737, "learning_rate": 1.8176116630402073e-05, "loss": 0.6872, "step": 3872 }, { "epoch": 0.5518666286691365, "grad_norm": 1.3299681740632192, "learning_rate": 1.817468443091121e-05, "loss": 0.6305, "step": 3873 }, { "epoch": 0.5520091194072385, "grad_norm": 1.27915480404696, "learning_rate": 1.8173251725797715e-05, "loss": 0.6324, "step": 3874 }, { "epoch": 0.5521516101453405, "grad_norm": 1.4513281081544829, "learning_rate": 1.8171818515150206e-05, "loss": 0.6787, "step": 3875 }, { "epoch": 0.5522941008834426, "grad_norm": 1.3491733121790763, "learning_rate": 1.8170384799057324e-05, "loss": 0.6572, "step": 3876 }, { "epoch": 0.5524365916215446, "grad_norm": 1.3302537824685219, "learning_rate": 1.816895057760775e-05, "loss": 0.6061, "step": 3877 }, { "epoch": 0.5525790823596466, "grad_norm": 1.3106643577937749, "learning_rate": 1.8167515850890196e-05, "loss": 0.6882, "step": 3878 }, { "epoch": 0.5527215730977486, "grad_norm": 1.3640778592997653, "learning_rate": 1.8166080618993403e-05, "loss": 0.6247, "step": 3879 }, { "epoch": 0.5528640638358506, "grad_norm": 1.4093812559351286, "learning_rate": 1.8164644882006144e-05, "loss": 0.7471, "step": 3880 }, { "epoch": 0.5530065545739526, "grad_norm": 1.2740221244056502, "learning_rate": 1.8163208640017222e-05, "loss": 0.6726, "step": 3881 }, { "epoch": 0.5531490453120547, "grad_norm": 1.5687727750625973, "learning_rate": 1.8161771893115467e-05, "loss": 0.6556, "step": 3882 }, { "epoch": 0.5532915360501567, "grad_norm": 1.5128175823367886, "learning_rate": 1.816033464138975e-05, "loss": 0.6829, "step": 3883 }, { "epoch": 0.5534340267882588, "grad_norm": 1.4919722989925823, "learning_rate": 1.8158896884928966e-05, "loss": 0.6996, "step": 3884 }, { "epoch": 0.5535765175263608, "grad_norm": 1.327957721245703, "learning_rate": 1.8157458623822044e-05, "loss": 0.6494, "step": 3885 }, { "epoch": 0.5537190082644629, "grad_norm": 1.3499333077537112, "learning_rate": 1.8156019858157945e-05, "loss": 0.7581, "step": 3886 }, { "epoch": 0.5538614990025649, "grad_norm": 1.3713896572466542, "learning_rate": 1.815458058802566e-05, "loss": 0.6888, "step": 3887 }, { "epoch": 0.5540039897406669, "grad_norm": 1.3404100216251462, "learning_rate": 1.815314081351421e-05, "loss": 0.7152, "step": 3888 }, { "epoch": 0.5541464804787689, "grad_norm": 1.3434996158072599, "learning_rate": 1.815170053471265e-05, "loss": 0.6895, "step": 3889 }, { "epoch": 0.5542889712168709, "grad_norm": 1.5551190816982274, "learning_rate": 1.815025975171006e-05, "loss": 0.7593, "step": 3890 }, { "epoch": 0.554431461954973, "grad_norm": 1.3084867430375742, "learning_rate": 1.814881846459556e-05, "loss": 0.6805, "step": 3891 }, { "epoch": 0.554573952693075, "grad_norm": 1.3591763766692067, "learning_rate": 1.8147376673458294e-05, "loss": 0.6738, "step": 3892 }, { "epoch": 0.554716443431177, "grad_norm": 1.3903653988881843, "learning_rate": 1.8145934378387444e-05, "loss": 0.6752, "step": 3893 }, { "epoch": 0.554858934169279, "grad_norm": 1.588757715806165, "learning_rate": 1.8144491579472218e-05, "loss": 0.7007, "step": 3894 }, { "epoch": 0.555001424907381, "grad_norm": 2.9305762370632604, "learning_rate": 1.8143048276801853e-05, "loss": 0.643, "step": 3895 }, { "epoch": 0.555143915645483, "grad_norm": 1.3885792940352883, "learning_rate": 1.8141604470465623e-05, "loss": 0.6665, "step": 3896 }, { "epoch": 0.5552864063835851, "grad_norm": 1.3288595723735157, "learning_rate": 1.814016016055283e-05, "loss": 0.6327, "step": 3897 }, { "epoch": 0.5554288971216871, "grad_norm": 1.481514187214165, "learning_rate": 1.8138715347152805e-05, "loss": 0.7181, "step": 3898 }, { "epoch": 0.5555713878597891, "grad_norm": 1.2737571851927707, "learning_rate": 1.813727003035492e-05, "loss": 0.5663, "step": 3899 }, { "epoch": 0.5557138785978911, "grad_norm": 1.3488335084908072, "learning_rate": 1.8135824210248566e-05, "loss": 0.6835, "step": 3900 }, { "epoch": 0.5558563693359931, "grad_norm": 1.3020861468518636, "learning_rate": 1.8134377886923172e-05, "loss": 0.6366, "step": 3901 }, { "epoch": 0.5559988600740952, "grad_norm": 1.3701623962530598, "learning_rate": 1.8132931060468197e-05, "loss": 0.723, "step": 3902 }, { "epoch": 0.5561413508121972, "grad_norm": 1.4544878157098087, "learning_rate": 1.8131483730973127e-05, "loss": 0.658, "step": 3903 }, { "epoch": 0.5562838415502992, "grad_norm": 1.2929187948427199, "learning_rate": 1.8130035898527482e-05, "loss": 0.6743, "step": 3904 }, { "epoch": 0.5564263322884012, "grad_norm": 1.4124958877351963, "learning_rate": 1.8128587563220822e-05, "loss": 0.6331, "step": 3905 }, { "epoch": 0.5565688230265032, "grad_norm": 1.50422100174117, "learning_rate": 1.8127138725142723e-05, "loss": 0.5969, "step": 3906 }, { "epoch": 0.5567113137646053, "grad_norm": 1.4496276146672407, "learning_rate": 1.8125689384382797e-05, "loss": 0.5983, "step": 3907 }, { "epoch": 0.5568538045027073, "grad_norm": 1.3485037299171656, "learning_rate": 1.8124239541030696e-05, "loss": 0.6733, "step": 3908 }, { "epoch": 0.5569962952408094, "grad_norm": 2.105307708843631, "learning_rate": 1.8122789195176088e-05, "loss": 0.672, "step": 3909 }, { "epoch": 0.5571387859789114, "grad_norm": 2.1793489950830987, "learning_rate": 1.812133834690869e-05, "loss": 0.739, "step": 3910 }, { "epoch": 0.5572812767170134, "grad_norm": 1.4507662835603952, "learning_rate": 1.8119886996318233e-05, "loss": 0.6871, "step": 3911 }, { "epoch": 0.5574237674551155, "grad_norm": 1.3730822688262283, "learning_rate": 1.8118435143494484e-05, "loss": 0.6771, "step": 3912 }, { "epoch": 0.5575662581932175, "grad_norm": 1.4997546078115456, "learning_rate": 1.8116982788527254e-05, "loss": 0.7505, "step": 3913 }, { "epoch": 0.5577087489313195, "grad_norm": 1.4225451411977355, "learning_rate": 1.8115529931506363e-05, "loss": 0.6085, "step": 3914 }, { "epoch": 0.5578512396694215, "grad_norm": 1.8934386724547143, "learning_rate": 1.8114076572521676e-05, "loss": 0.6361, "step": 3915 }, { "epoch": 0.5579937304075235, "grad_norm": 1.7207631263955023, "learning_rate": 1.8112622711663093e-05, "loss": 0.8096, "step": 3916 }, { "epoch": 0.5581362211456256, "grad_norm": 1.401767587421078, "learning_rate": 1.8111168349020532e-05, "loss": 0.7334, "step": 3917 }, { "epoch": 0.5582787118837276, "grad_norm": 1.391474319360391, "learning_rate": 1.8109713484683954e-05, "loss": 0.6948, "step": 3918 }, { "epoch": 0.5584212026218296, "grad_norm": 1.3385658598848191, "learning_rate": 1.810825811874334e-05, "loss": 0.668, "step": 3919 }, { "epoch": 0.5585636933599316, "grad_norm": 1.56577505180146, "learning_rate": 1.810680225128871e-05, "loss": 0.6189, "step": 3920 }, { "epoch": 0.5587061840980336, "grad_norm": 1.5047838782439702, "learning_rate": 1.8105345882410112e-05, "loss": 0.7267, "step": 3921 }, { "epoch": 0.5588486748361357, "grad_norm": 1.5158172903896665, "learning_rate": 1.810388901219763e-05, "loss": 0.6359, "step": 3922 }, { "epoch": 0.5589911655742377, "grad_norm": 1.4010033384336318, "learning_rate": 1.810243164074137e-05, "loss": 0.6757, "step": 3923 }, { "epoch": 0.5591336563123397, "grad_norm": 1.435112079653595, "learning_rate": 1.8100973768131474e-05, "loss": 0.6287, "step": 3924 }, { "epoch": 0.5592761470504417, "grad_norm": 1.309855825903542, "learning_rate": 1.8099515394458117e-05, "loss": 0.6864, "step": 3925 }, { "epoch": 0.5594186377885437, "grad_norm": 1.4359908079551402, "learning_rate": 1.80980565198115e-05, "loss": 0.6657, "step": 3926 }, { "epoch": 0.5595611285266457, "grad_norm": 1.5269199916861966, "learning_rate": 1.809659714428186e-05, "loss": 0.7009, "step": 3927 }, { "epoch": 0.5597036192647478, "grad_norm": 1.4662675851563671, "learning_rate": 1.809513726795946e-05, "loss": 0.7178, "step": 3928 }, { "epoch": 0.5598461100028498, "grad_norm": 1.407705228753132, "learning_rate": 1.80936768909346e-05, "loss": 0.7304, "step": 3929 }, { "epoch": 0.5599886007409518, "grad_norm": 1.372215767376189, "learning_rate": 1.8092216013297604e-05, "loss": 0.6124, "step": 3930 }, { "epoch": 0.5601310914790538, "grad_norm": 1.3329166495990623, "learning_rate": 1.8090754635138833e-05, "loss": 0.6475, "step": 3931 }, { "epoch": 0.5602735822171558, "grad_norm": 1.7068101121092338, "learning_rate": 1.808929275654868e-05, "loss": 0.6323, "step": 3932 }, { "epoch": 0.5604160729552579, "grad_norm": 1.474450860203948, "learning_rate": 1.8087830377617556e-05, "loss": 0.7131, "step": 3933 }, { "epoch": 0.5605585636933599, "grad_norm": 1.3508117141834965, "learning_rate": 1.808636749843592e-05, "loss": 0.6813, "step": 3934 }, { "epoch": 0.560701054431462, "grad_norm": 1.421809098404743, "learning_rate": 1.8084904119094257e-05, "loss": 0.6055, "step": 3935 }, { "epoch": 0.560843545169564, "grad_norm": 1.3139357881172484, "learning_rate": 1.808344023968307e-05, "loss": 0.6292, "step": 3936 }, { "epoch": 0.560986035907666, "grad_norm": 1.4121395757827786, "learning_rate": 1.8081975860292908e-05, "loss": 0.6083, "step": 3937 }, { "epoch": 0.5611285266457681, "grad_norm": 1.5633730067340852, "learning_rate": 1.808051098101435e-05, "loss": 0.7155, "step": 3938 }, { "epoch": 0.5612710173838701, "grad_norm": 1.6168987576997216, "learning_rate": 1.8079045601938e-05, "loss": 0.7271, "step": 3939 }, { "epoch": 0.5614135081219721, "grad_norm": 1.4726321528852813, "learning_rate": 1.807757972315449e-05, "loss": 0.6844, "step": 3940 }, { "epoch": 0.5615559988600741, "grad_norm": 1.2835257063197123, "learning_rate": 1.80761133447545e-05, "loss": 0.5965, "step": 3941 }, { "epoch": 0.5616984895981761, "grad_norm": 1.5207981310005159, "learning_rate": 1.8074646466828715e-05, "loss": 0.7026, "step": 3942 }, { "epoch": 0.5618409803362782, "grad_norm": 1.4184996015489855, "learning_rate": 1.807317908946787e-05, "loss": 0.6886, "step": 3943 }, { "epoch": 0.5619834710743802, "grad_norm": 1.506014307583328, "learning_rate": 1.8071711212762725e-05, "loss": 0.7695, "step": 3944 }, { "epoch": 0.5621259618124822, "grad_norm": 1.5406168574048842, "learning_rate": 1.8070242836804076e-05, "loss": 0.7382, "step": 3945 }, { "epoch": 0.5622684525505842, "grad_norm": 1.329469774459305, "learning_rate": 1.806877396168274e-05, "loss": 0.691, "step": 3946 }, { "epoch": 0.5624109432886862, "grad_norm": 1.4188334328518233, "learning_rate": 1.8067304587489577e-05, "loss": 0.6897, "step": 3947 }, { "epoch": 0.5625534340267883, "grad_norm": 1.3637934688066342, "learning_rate": 1.8065834714315456e-05, "loss": 0.6234, "step": 3948 }, { "epoch": 0.5626959247648903, "grad_norm": 1.3870240160947518, "learning_rate": 1.8064364342251314e-05, "loss": 0.6874, "step": 3949 }, { "epoch": 0.5628384155029923, "grad_norm": 2.347910804253095, "learning_rate": 1.8062893471388076e-05, "loss": 0.7517, "step": 3950 }, { "epoch": 0.5629809062410943, "grad_norm": 1.6081823800863442, "learning_rate": 1.8061422101816735e-05, "loss": 0.6482, "step": 3951 }, { "epoch": 0.5631233969791963, "grad_norm": 1.3442802318464981, "learning_rate": 1.8059950233628285e-05, "loss": 0.6747, "step": 3952 }, { "epoch": 0.5632658877172984, "grad_norm": 1.5048251888799369, "learning_rate": 1.8058477866913777e-05, "loss": 0.6625, "step": 3953 }, { "epoch": 0.5634083784554004, "grad_norm": 1.33926095997619, "learning_rate": 1.8057005001764265e-05, "loss": 0.6786, "step": 3954 }, { "epoch": 0.5635508691935024, "grad_norm": 1.3107078377117125, "learning_rate": 1.8055531638270864e-05, "loss": 0.6345, "step": 3955 }, { "epoch": 0.5636933599316044, "grad_norm": 1.3387441339387534, "learning_rate": 1.8054057776524698e-05, "loss": 0.6808, "step": 3956 }, { "epoch": 0.5638358506697064, "grad_norm": 1.360796291503977, "learning_rate": 1.805258341661693e-05, "loss": 0.6884, "step": 3957 }, { "epoch": 0.5639783414078084, "grad_norm": 1.3075409309619004, "learning_rate": 1.805110855863875e-05, "loss": 0.723, "step": 3958 }, { "epoch": 0.5641208321459105, "grad_norm": 1.9212211276534263, "learning_rate": 1.8049633202681385e-05, "loss": 0.636, "step": 3959 }, { "epoch": 0.5642633228840125, "grad_norm": 1.4404074097346378, "learning_rate": 1.8048157348836086e-05, "loss": 0.6476, "step": 3960 }, { "epoch": 0.5644058136221146, "grad_norm": 1.3234173382769128, "learning_rate": 1.8046680997194138e-05, "loss": 0.7299, "step": 3961 }, { "epoch": 0.5645483043602166, "grad_norm": 1.4919877270510526, "learning_rate": 1.804520414784686e-05, "loss": 0.6128, "step": 3962 }, { "epoch": 0.5646907950983187, "grad_norm": 1.5132163208892562, "learning_rate": 1.8043726800885595e-05, "loss": 0.6834, "step": 3963 }, { "epoch": 0.5648332858364207, "grad_norm": 1.372849211307047, "learning_rate": 1.8042248956401722e-05, "loss": 0.7047, "step": 3964 }, { "epoch": 0.5649757765745227, "grad_norm": 1.5237425581638084, "learning_rate": 1.8040770614486648e-05, "loss": 0.7468, "step": 3965 }, { "epoch": 0.5651182673126247, "grad_norm": 1.9658274746435085, "learning_rate": 1.803929177523181e-05, "loss": 0.7094, "step": 3966 }, { "epoch": 0.5652607580507267, "grad_norm": 1.3974891380595635, "learning_rate": 1.8037812438728685e-05, "loss": 0.6408, "step": 3967 }, { "epoch": 0.5654032487888287, "grad_norm": 1.425242525301147, "learning_rate": 1.8036332605068766e-05, "loss": 0.7106, "step": 3968 }, { "epoch": 0.5655457395269308, "grad_norm": 1.4928890128395176, "learning_rate": 1.8034852274343585e-05, "loss": 0.6502, "step": 3969 }, { "epoch": 0.5656882302650328, "grad_norm": 1.4249610872969356, "learning_rate": 1.8033371446644705e-05, "loss": 0.6794, "step": 3970 }, { "epoch": 0.5658307210031348, "grad_norm": 1.3295604281099747, "learning_rate": 1.8031890122063718e-05, "loss": 0.6384, "step": 3971 }, { "epoch": 0.5659732117412368, "grad_norm": 1.272484866078396, "learning_rate": 1.803040830069225e-05, "loss": 0.6804, "step": 3972 }, { "epoch": 0.5661157024793388, "grad_norm": 1.3097798459513272, "learning_rate": 1.802892598262195e-05, "loss": 0.7014, "step": 3973 }, { "epoch": 0.5662581932174409, "grad_norm": 1.7324805196776638, "learning_rate": 1.8027443167944506e-05, "loss": 0.7179, "step": 3974 }, { "epoch": 0.5664006839555429, "grad_norm": 1.5336131960519441, "learning_rate": 1.8025959856751635e-05, "loss": 0.6838, "step": 3975 }, { "epoch": 0.5665431746936449, "grad_norm": 1.4326342395856475, "learning_rate": 1.8024476049135078e-05, "loss": 0.6957, "step": 3976 }, { "epoch": 0.5666856654317469, "grad_norm": 1.404646558967613, "learning_rate": 1.8022991745186616e-05, "loss": 0.6492, "step": 3977 }, { "epoch": 0.5668281561698489, "grad_norm": 1.4874365148636959, "learning_rate": 1.8021506944998054e-05, "loss": 0.7469, "step": 3978 }, { "epoch": 0.566970646907951, "grad_norm": 1.4100144615284036, "learning_rate": 1.8020021648661234e-05, "loss": 0.6783, "step": 3979 }, { "epoch": 0.567113137646053, "grad_norm": 1.5663077777902108, "learning_rate": 1.801853585626802e-05, "loss": 0.7103, "step": 3980 }, { "epoch": 0.567255628384155, "grad_norm": 1.806226274171027, "learning_rate": 1.801704956791032e-05, "loss": 0.6659, "step": 3981 }, { "epoch": 0.567398119122257, "grad_norm": 2.0123917012280703, "learning_rate": 1.8015562783680053e-05, "loss": 0.6772, "step": 3982 }, { "epoch": 0.567540609860359, "grad_norm": 1.3680700020968743, "learning_rate": 1.8014075503669185e-05, "loss": 0.6233, "step": 3983 }, { "epoch": 0.567683100598461, "grad_norm": 1.4654772837468386, "learning_rate": 1.801258772796971e-05, "loss": 0.7379, "step": 3984 }, { "epoch": 0.5678255913365631, "grad_norm": 1.4817043408974901, "learning_rate": 1.8011099456673648e-05, "loss": 0.6605, "step": 3985 }, { "epoch": 0.5679680820746651, "grad_norm": 1.3999107557649781, "learning_rate": 1.800961068987305e-05, "loss": 0.6369, "step": 3986 }, { "epoch": 0.5681105728127672, "grad_norm": 1.3260626297366096, "learning_rate": 1.8008121427660005e-05, "loss": 0.6504, "step": 3987 }, { "epoch": 0.5682530635508692, "grad_norm": 1.3058838509016986, "learning_rate": 1.8006631670126623e-05, "loss": 0.6722, "step": 3988 }, { "epoch": 0.5683955542889713, "grad_norm": 1.4810224185211456, "learning_rate": 1.8005141417365046e-05, "loss": 0.7182, "step": 3989 }, { "epoch": 0.5685380450270733, "grad_norm": 1.5744097440765636, "learning_rate": 1.8003650669467457e-05, "loss": 0.7686, "step": 3990 }, { "epoch": 0.5686805357651753, "grad_norm": 1.4629164156926056, "learning_rate": 1.800215942652606e-05, "loss": 0.7156, "step": 3991 }, { "epoch": 0.5688230265032773, "grad_norm": 1.4148460936282983, "learning_rate": 1.8000667688633085e-05, "loss": 0.6802, "step": 3992 }, { "epoch": 0.5689655172413793, "grad_norm": 1.4139259588291564, "learning_rate": 1.799917545588081e-05, "loss": 0.6257, "step": 3993 }, { "epoch": 0.5691080079794814, "grad_norm": 1.509798525297103, "learning_rate": 1.7997682728361524e-05, "loss": 0.7166, "step": 3994 }, { "epoch": 0.5692504987175834, "grad_norm": 1.4573919624268663, "learning_rate": 1.799618950616756e-05, "loss": 0.7541, "step": 3995 }, { "epoch": 0.5693929894556854, "grad_norm": 1.4114603239597463, "learning_rate": 1.7994695789391273e-05, "loss": 0.7871, "step": 3996 }, { "epoch": 0.5695354801937874, "grad_norm": 1.6652274625803827, "learning_rate": 1.799320157812506e-05, "loss": 0.7462, "step": 3997 }, { "epoch": 0.5696779709318894, "grad_norm": 2.424125312410407, "learning_rate": 1.7991706872461336e-05, "loss": 0.6744, "step": 3998 }, { "epoch": 0.5698204616699915, "grad_norm": 1.4748168194260856, "learning_rate": 1.799021167249255e-05, "loss": 0.6607, "step": 3999 }, { "epoch": 0.5699629524080935, "grad_norm": 1.43263419387371, "learning_rate": 1.7988715978311193e-05, "loss": 0.7439, "step": 4000 }, { "epoch": 0.5701054431461955, "grad_norm": 1.589558173833731, "learning_rate": 1.798721979000977e-05, "loss": 0.716, "step": 4001 }, { "epoch": 0.5702479338842975, "grad_norm": 1.3311797295268912, "learning_rate": 1.7985723107680818e-05, "loss": 0.6838, "step": 4002 }, { "epoch": 0.5703904246223995, "grad_norm": 1.4877309368515468, "learning_rate": 1.7984225931416922e-05, "loss": 0.7056, "step": 4003 }, { "epoch": 0.5705329153605015, "grad_norm": 1.3823286204841392, "learning_rate": 1.7982728261310677e-05, "loss": 0.6259, "step": 4004 }, { "epoch": 0.5706754060986036, "grad_norm": 1.4978290065596886, "learning_rate": 1.798123009745472e-05, "loss": 0.6909, "step": 4005 }, { "epoch": 0.5708178968367056, "grad_norm": 1.4143488046413226, "learning_rate": 1.797973143994172e-05, "loss": 0.7002, "step": 4006 }, { "epoch": 0.5709603875748076, "grad_norm": 1.2783956433907115, "learning_rate": 1.797823228886437e-05, "loss": 0.7005, "step": 4007 }, { "epoch": 0.5711028783129096, "grad_norm": 1.4056631073960566, "learning_rate": 1.7976732644315386e-05, "loss": 0.5881, "step": 4008 }, { "epoch": 0.5712453690510116, "grad_norm": 1.4089011311275779, "learning_rate": 1.797523250638754e-05, "loss": 0.6579, "step": 4009 }, { "epoch": 0.5713878597891137, "grad_norm": 1.5440887626621782, "learning_rate": 1.797373187517361e-05, "loss": 0.7329, "step": 4010 }, { "epoch": 0.5715303505272157, "grad_norm": 1.431499537264619, "learning_rate": 1.7972230750766412e-05, "loss": 0.6968, "step": 4011 }, { "epoch": 0.5716728412653177, "grad_norm": 1.4607403019425866, "learning_rate": 1.79707291332588e-05, "loss": 0.6609, "step": 4012 }, { "epoch": 0.5718153320034198, "grad_norm": 1.4280254473502403, "learning_rate": 1.7969227022743652e-05, "loss": 0.7376, "step": 4013 }, { "epoch": 0.5719578227415218, "grad_norm": 1.4043296407211454, "learning_rate": 1.796772441931387e-05, "loss": 0.6576, "step": 4014 }, { "epoch": 0.5721003134796239, "grad_norm": 1.3488539329764646, "learning_rate": 1.79662213230624e-05, "loss": 0.6776, "step": 4015 }, { "epoch": 0.5722428042177259, "grad_norm": 1.3978295531708862, "learning_rate": 1.7964717734082212e-05, "loss": 0.721, "step": 4016 }, { "epoch": 0.5723852949558279, "grad_norm": 1.5855144456492463, "learning_rate": 1.7963213652466298e-05, "loss": 0.6597, "step": 4017 }, { "epoch": 0.5725277856939299, "grad_norm": 1.4019157084121336, "learning_rate": 1.79617090783077e-05, "loss": 0.7076, "step": 4018 }, { "epoch": 0.5726702764320319, "grad_norm": 1.4073985724738776, "learning_rate": 1.7960204011699472e-05, "loss": 0.7073, "step": 4019 }, { "epoch": 0.572812767170134, "grad_norm": 1.3800204691488358, "learning_rate": 1.7958698452734712e-05, "loss": 0.6576, "step": 4020 }, { "epoch": 0.572955257908236, "grad_norm": 1.4452196025911113, "learning_rate": 1.7957192401506532e-05, "loss": 0.7273, "step": 4021 }, { "epoch": 0.573097748646338, "grad_norm": 1.3378009270737445, "learning_rate": 1.7955685858108093e-05, "loss": 0.6307, "step": 4022 }, { "epoch": 0.57324023938444, "grad_norm": 1.3551452139769644, "learning_rate": 1.795417882263258e-05, "loss": 0.6267, "step": 4023 }, { "epoch": 0.573382730122542, "grad_norm": 1.3370323314186272, "learning_rate": 1.7952671295173197e-05, "loss": 0.6826, "step": 4024 }, { "epoch": 0.5735252208606441, "grad_norm": 1.5339734254375557, "learning_rate": 1.7951163275823195e-05, "loss": 0.7103, "step": 4025 }, { "epoch": 0.5736677115987461, "grad_norm": 1.409641455947857, "learning_rate": 1.794965476467585e-05, "loss": 0.7454, "step": 4026 }, { "epoch": 0.5738102023368481, "grad_norm": 1.701985190689812, "learning_rate": 1.794814576182446e-05, "loss": 0.69, "step": 4027 }, { "epoch": 0.5739526930749501, "grad_norm": 1.3446878189340743, "learning_rate": 1.7946636267362362e-05, "loss": 0.6275, "step": 4028 }, { "epoch": 0.5740951838130521, "grad_norm": 1.5495594070517051, "learning_rate": 1.794512628138293e-05, "loss": 0.7981, "step": 4029 }, { "epoch": 0.5742376745511542, "grad_norm": 1.3786739413217004, "learning_rate": 1.794361580397955e-05, "loss": 0.645, "step": 4030 }, { "epoch": 0.5743801652892562, "grad_norm": 1.3759183522607243, "learning_rate": 1.794210483524565e-05, "loss": 0.7287, "step": 4031 }, { "epoch": 0.5745226560273582, "grad_norm": 1.3457937659589685, "learning_rate": 1.794059337527469e-05, "loss": 0.6178, "step": 4032 }, { "epoch": 0.5746651467654602, "grad_norm": 1.3682639913537809, "learning_rate": 1.7939081424160158e-05, "loss": 0.6304, "step": 4033 }, { "epoch": 0.5748076375035622, "grad_norm": 1.6630504422070616, "learning_rate": 1.7937568981995567e-05, "loss": 0.6653, "step": 4034 }, { "epoch": 0.5749501282416642, "grad_norm": 1.4811432314434303, "learning_rate": 1.7936056048874467e-05, "loss": 0.6892, "step": 4035 }, { "epoch": 0.5750926189797663, "grad_norm": 1.4510275916958246, "learning_rate": 1.793454262489044e-05, "loss": 0.6651, "step": 4036 }, { "epoch": 0.5752351097178683, "grad_norm": 1.399830460101253, "learning_rate": 1.793302871013709e-05, "loss": 0.6141, "step": 4037 }, { "epoch": 0.5753776004559704, "grad_norm": 1.3488785829290657, "learning_rate": 1.793151430470806e-05, "loss": 0.5875, "step": 4038 }, { "epoch": 0.5755200911940724, "grad_norm": 2.2891923879822285, "learning_rate": 1.7929999408697016e-05, "loss": 0.7597, "step": 4039 }, { "epoch": 0.5756625819321745, "grad_norm": 1.345536936456943, "learning_rate": 1.7928484022197653e-05, "loss": 0.7005, "step": 4040 }, { "epoch": 0.5758050726702765, "grad_norm": 1.295418673457462, "learning_rate": 1.792696814530371e-05, "loss": 0.5758, "step": 4041 }, { "epoch": 0.5759475634083785, "grad_norm": 1.377671541099267, "learning_rate": 1.792545177810895e-05, "loss": 0.7004, "step": 4042 }, { "epoch": 0.5760900541464805, "grad_norm": 1.540484392829847, "learning_rate": 1.792393492070715e-05, "loss": 0.6688, "step": 4043 }, { "epoch": 0.5762325448845825, "grad_norm": 1.318675213836102, "learning_rate": 1.7922417573192145e-05, "loss": 0.6487, "step": 4044 }, { "epoch": 0.5763750356226846, "grad_norm": 1.5429364147378049, "learning_rate": 1.7920899735657775e-05, "loss": 0.662, "step": 4045 }, { "epoch": 0.5765175263607866, "grad_norm": 1.3760127907257698, "learning_rate": 1.7919381408197928e-05, "loss": 0.7139, "step": 4046 }, { "epoch": 0.5766600170988886, "grad_norm": 1.3042195583763345, "learning_rate": 1.7917862590906518e-05, "loss": 0.6777, "step": 4047 }, { "epoch": 0.5768025078369906, "grad_norm": 1.6983512507691547, "learning_rate": 1.7916343283877482e-05, "loss": 0.7747, "step": 4048 }, { "epoch": 0.5769449985750926, "grad_norm": 1.4328934881887887, "learning_rate": 1.7914823487204796e-05, "loss": 0.6982, "step": 4049 }, { "epoch": 0.5770874893131946, "grad_norm": 1.3175847665811686, "learning_rate": 1.7913303200982458e-05, "loss": 0.6947, "step": 4050 }, { "epoch": 0.5772299800512967, "grad_norm": 1.3729198866585284, "learning_rate": 1.791178242530451e-05, "loss": 0.7016, "step": 4051 }, { "epoch": 0.5773724707893987, "grad_norm": 1.1954398976725498, "learning_rate": 1.7910261160265007e-05, "loss": 0.6862, "step": 4052 }, { "epoch": 0.5775149615275007, "grad_norm": 1.3721163933073417, "learning_rate": 1.7908739405958043e-05, "loss": 0.6322, "step": 4053 }, { "epoch": 0.5776574522656027, "grad_norm": 1.3636376817928266, "learning_rate": 1.7907217162477748e-05, "loss": 0.7154, "step": 4054 }, { "epoch": 0.5777999430037047, "grad_norm": 1.393431009576423, "learning_rate": 1.7905694429918275e-05, "loss": 0.6634, "step": 4055 }, { "epoch": 0.5779424337418068, "grad_norm": 1.728376913645334, "learning_rate": 1.7904171208373803e-05, "loss": 0.6384, "step": 4056 }, { "epoch": 0.5780849244799088, "grad_norm": 1.3477922335407246, "learning_rate": 1.790264749793855e-05, "loss": 0.6615, "step": 4057 }, { "epoch": 0.5782274152180108, "grad_norm": 1.4019174783261878, "learning_rate": 1.7901123298706762e-05, "loss": 0.7, "step": 4058 }, { "epoch": 0.5783699059561128, "grad_norm": 1.5849067432114046, "learning_rate": 1.7899598610772712e-05, "loss": 0.7853, "step": 4059 }, { "epoch": 0.5785123966942148, "grad_norm": 1.3500821902659814, "learning_rate": 1.789807343423071e-05, "loss": 0.7082, "step": 4060 }, { "epoch": 0.5786548874323169, "grad_norm": 1.7920820086850686, "learning_rate": 1.7896547769175084e-05, "loss": 0.6666, "step": 4061 }, { "epoch": 0.5787973781704189, "grad_norm": 1.4007265598308642, "learning_rate": 1.7895021615700204e-05, "loss": 0.7078, "step": 4062 }, { "epoch": 0.5789398689085209, "grad_norm": 1.4420324150808077, "learning_rate": 1.7893494973900466e-05, "loss": 0.6745, "step": 4063 }, { "epoch": 0.579082359646623, "grad_norm": 1.4628874855772254, "learning_rate": 1.7891967843870296e-05, "loss": 0.6401, "step": 4064 }, { "epoch": 0.579224850384725, "grad_norm": 1.454208107483349, "learning_rate": 1.7890440225704157e-05, "loss": 0.5916, "step": 4065 }, { "epoch": 0.5793673411228271, "grad_norm": 1.3322889911206466, "learning_rate": 1.7888912119496522e-05, "loss": 0.5852, "step": 4066 }, { "epoch": 0.5795098318609291, "grad_norm": 1.266188780597515, "learning_rate": 1.7887383525341914e-05, "loss": 0.6077, "step": 4067 }, { "epoch": 0.5796523225990311, "grad_norm": 1.5213306160396691, "learning_rate": 1.7885854443334888e-05, "loss": 0.6969, "step": 4068 }, { "epoch": 0.5797948133371331, "grad_norm": 1.384229427861406, "learning_rate": 1.7884324873570008e-05, "loss": 0.7191, "step": 4069 }, { "epoch": 0.5799373040752351, "grad_norm": 1.2761690729269135, "learning_rate": 1.7882794816141887e-05, "loss": 0.6665, "step": 4070 }, { "epoch": 0.5800797948133372, "grad_norm": 1.3984542041667725, "learning_rate": 1.788126427114517e-05, "loss": 0.7412, "step": 4071 }, { "epoch": 0.5802222855514392, "grad_norm": 1.2877171780052845, "learning_rate": 1.787973323867451e-05, "loss": 0.6657, "step": 4072 }, { "epoch": 0.5803647762895412, "grad_norm": 1.31914198124506, "learning_rate": 1.7878201718824618e-05, "loss": 0.6538, "step": 4073 }, { "epoch": 0.5805072670276432, "grad_norm": 1.3177524656160318, "learning_rate": 1.787666971169021e-05, "loss": 0.6702, "step": 4074 }, { "epoch": 0.5806497577657452, "grad_norm": 1.4699242022194392, "learning_rate": 1.7875137217366058e-05, "loss": 0.6683, "step": 4075 }, { "epoch": 0.5807922485038473, "grad_norm": 1.2453013547139946, "learning_rate": 1.787360423594694e-05, "loss": 0.5971, "step": 4076 }, { "epoch": 0.5809347392419493, "grad_norm": 1.290306101959749, "learning_rate": 1.7872070767527673e-05, "loss": 0.6403, "step": 4077 }, { "epoch": 0.5810772299800513, "grad_norm": 1.509192516438835, "learning_rate": 1.787053681220311e-05, "loss": 0.7186, "step": 4078 }, { "epoch": 0.5812197207181533, "grad_norm": 1.4575290277871575, "learning_rate": 1.7869002370068136e-05, "loss": 0.7026, "step": 4079 }, { "epoch": 0.5813622114562553, "grad_norm": 1.319724039101374, "learning_rate": 1.7867467441217647e-05, "loss": 0.6302, "step": 4080 }, { "epoch": 0.5815047021943573, "grad_norm": 1.7767058816536119, "learning_rate": 1.786593202574659e-05, "loss": 0.6526, "step": 4081 }, { "epoch": 0.5816471929324594, "grad_norm": 1.4153415902400837, "learning_rate": 1.7864396123749928e-05, "loss": 0.6373, "step": 4082 }, { "epoch": 0.5817896836705614, "grad_norm": 1.2888776837858473, "learning_rate": 1.7862859735322667e-05, "loss": 0.6781, "step": 4083 }, { "epoch": 0.5819321744086634, "grad_norm": 1.507232762291457, "learning_rate": 1.7861322860559834e-05, "loss": 0.6887, "step": 4084 }, { "epoch": 0.5820746651467654, "grad_norm": 1.513058187875095, "learning_rate": 1.7859785499556485e-05, "loss": 0.6591, "step": 4085 }, { "epoch": 0.5822171558848674, "grad_norm": 1.467746403838837, "learning_rate": 1.7858247652407707e-05, "loss": 0.7004, "step": 4086 }, { "epoch": 0.5823596466229695, "grad_norm": 1.3388451963782508, "learning_rate": 1.7856709319208628e-05, "loss": 0.7311, "step": 4087 }, { "epoch": 0.5825021373610715, "grad_norm": 1.300933755850911, "learning_rate": 1.785517050005439e-05, "loss": 0.6528, "step": 4088 }, { "epoch": 0.5826446280991735, "grad_norm": 1.5690855882464905, "learning_rate": 1.7853631195040178e-05, "loss": 0.676, "step": 4089 }, { "epoch": 0.5827871188372756, "grad_norm": 1.6811213737258808, "learning_rate": 1.78520914042612e-05, "loss": 0.7472, "step": 4090 }, { "epoch": 0.5829296095753776, "grad_norm": 1.3142852185638985, "learning_rate": 1.785055112781269e-05, "loss": 0.6594, "step": 4091 }, { "epoch": 0.5830721003134797, "grad_norm": 1.5870972807773804, "learning_rate": 1.784901036578992e-05, "loss": 0.7518, "step": 4092 }, { "epoch": 0.5832145910515817, "grad_norm": 1.3894425877373118, "learning_rate": 1.7847469118288195e-05, "loss": 0.6689, "step": 4093 }, { "epoch": 0.5833570817896837, "grad_norm": 1.3021507873783797, "learning_rate": 1.784592738540284e-05, "loss": 0.6142, "step": 4094 }, { "epoch": 0.5834995725277857, "grad_norm": 1.4144130706278208, "learning_rate": 1.7844385167229214e-05, "loss": 0.666, "step": 4095 }, { "epoch": 0.5836420632658877, "grad_norm": 1.3550083610701447, "learning_rate": 1.784284246386271e-05, "loss": 0.6667, "step": 4096 }, { "epoch": 0.5837845540039898, "grad_norm": 1.313616211486397, "learning_rate": 1.7841299275398748e-05, "loss": 0.6652, "step": 4097 }, { "epoch": 0.5839270447420918, "grad_norm": 1.614642976056736, "learning_rate": 1.783975560193277e-05, "loss": 0.7485, "step": 4098 }, { "epoch": 0.5840695354801938, "grad_norm": 1.3482898388821867, "learning_rate": 1.7838211443560266e-05, "loss": 0.6351, "step": 4099 }, { "epoch": 0.5842120262182958, "grad_norm": 1.382319906199378, "learning_rate": 1.783666680037674e-05, "loss": 0.6677, "step": 4100 }, { "epoch": 0.5843545169563978, "grad_norm": 1.2669319298168247, "learning_rate": 1.783512167247773e-05, "loss": 0.6426, "step": 4101 }, { "epoch": 0.5844970076944999, "grad_norm": 1.4874069519576092, "learning_rate": 1.7833576059958812e-05, "loss": 0.6052, "step": 4102 }, { "epoch": 0.5846394984326019, "grad_norm": 1.4643352766244548, "learning_rate": 1.783202996291558e-05, "loss": 0.6518, "step": 4103 }, { "epoch": 0.5847819891707039, "grad_norm": 1.5504470593344235, "learning_rate": 1.7830483381443664e-05, "loss": 0.6797, "step": 4104 }, { "epoch": 0.5849244799088059, "grad_norm": 1.5154962409807267, "learning_rate": 1.7828936315638727e-05, "loss": 0.6318, "step": 4105 }, { "epoch": 0.5850669706469079, "grad_norm": 1.6045124176608532, "learning_rate": 1.7827388765596457e-05, "loss": 0.6227, "step": 4106 }, { "epoch": 0.58520946138501, "grad_norm": 1.4355977029422475, "learning_rate": 1.782584073141257e-05, "loss": 0.7064, "step": 4107 }, { "epoch": 0.585351952123112, "grad_norm": 1.404775480175146, "learning_rate": 1.782429221318282e-05, "loss": 0.6449, "step": 4108 }, { "epoch": 0.585494442861214, "grad_norm": 1.3993037698016066, "learning_rate": 1.7822743211002987e-05, "loss": 0.6329, "step": 4109 }, { "epoch": 0.585636933599316, "grad_norm": 1.5029291994742866, "learning_rate": 1.7821193724968875e-05, "loss": 0.6854, "step": 4110 }, { "epoch": 0.585779424337418, "grad_norm": 1.2780942113445348, "learning_rate": 1.7819643755176326e-05, "loss": 0.6102, "step": 4111 }, { "epoch": 0.58592191507552, "grad_norm": 1.5439884704584859, "learning_rate": 1.781809330172121e-05, "loss": 0.6439, "step": 4112 }, { "epoch": 0.5860644058136221, "grad_norm": 1.3516738024072552, "learning_rate": 1.7816542364699423e-05, "loss": 0.6632, "step": 4113 }, { "epoch": 0.5862068965517241, "grad_norm": 1.4543762355823737, "learning_rate": 1.78149909442069e-05, "loss": 0.7033, "step": 4114 }, { "epoch": 0.5863493872898261, "grad_norm": 1.3122273964121196, "learning_rate": 1.7813439040339596e-05, "loss": 0.7304, "step": 4115 }, { "epoch": 0.5864918780279282, "grad_norm": 1.4475872666122935, "learning_rate": 1.78118866531935e-05, "loss": 0.6744, "step": 4116 }, { "epoch": 0.5866343687660303, "grad_norm": 1.3798046991341342, "learning_rate": 1.7810333782864626e-05, "loss": 0.7262, "step": 4117 }, { "epoch": 0.5867768595041323, "grad_norm": 1.3504049987065152, "learning_rate": 1.7808780429449028e-05, "loss": 0.6553, "step": 4118 }, { "epoch": 0.5869193502422343, "grad_norm": 1.3912692150573507, "learning_rate": 1.7807226593042785e-05, "loss": 0.7064, "step": 4119 }, { "epoch": 0.5870618409803363, "grad_norm": 1.3579639900839358, "learning_rate": 1.7805672273742005e-05, "loss": 0.6365, "step": 4120 }, { "epoch": 0.5872043317184383, "grad_norm": 1.364685003936383, "learning_rate": 1.7804117471642823e-05, "loss": 0.675, "step": 4121 }, { "epoch": 0.5873468224565404, "grad_norm": 1.3719741781085744, "learning_rate": 1.780256218684141e-05, "loss": 0.6186, "step": 4122 }, { "epoch": 0.5874893131946424, "grad_norm": 1.4427964874649193, "learning_rate": 1.7801006419433965e-05, "loss": 0.597, "step": 4123 }, { "epoch": 0.5876318039327444, "grad_norm": 1.5690364346852381, "learning_rate": 1.7799450169516708e-05, "loss": 0.7125, "step": 4124 }, { "epoch": 0.5877742946708464, "grad_norm": 1.332400512680763, "learning_rate": 1.7797893437185904e-05, "loss": 0.7123, "step": 4125 }, { "epoch": 0.5879167854089484, "grad_norm": 1.7456994359180016, "learning_rate": 1.779633622253784e-05, "loss": 0.6419, "step": 4126 }, { "epoch": 0.5880592761470504, "grad_norm": 1.3475571139933036, "learning_rate": 1.779477852566883e-05, "loss": 0.636, "step": 4127 }, { "epoch": 0.5882017668851525, "grad_norm": 1.512420083928768, "learning_rate": 1.7793220346675223e-05, "loss": 0.7237, "step": 4128 }, { "epoch": 0.5883442576232545, "grad_norm": 1.605584231983358, "learning_rate": 1.7791661685653395e-05, "loss": 0.6882, "step": 4129 }, { "epoch": 0.5884867483613565, "grad_norm": 1.6708962299162988, "learning_rate": 1.7790102542699755e-05, "loss": 0.6837, "step": 4130 }, { "epoch": 0.5886292390994585, "grad_norm": 1.4342564408039487, "learning_rate": 1.7788542917910735e-05, "loss": 0.7062, "step": 4131 }, { "epoch": 0.5887717298375605, "grad_norm": 1.4487224106334202, "learning_rate": 1.7786982811382806e-05, "loss": 0.7003, "step": 4132 }, { "epoch": 0.5889142205756626, "grad_norm": 1.3446676320421274, "learning_rate": 1.778542222321246e-05, "loss": 0.6144, "step": 4133 }, { "epoch": 0.5890567113137646, "grad_norm": 1.292480338499222, "learning_rate": 1.778386115349623e-05, "loss": 0.6471, "step": 4134 }, { "epoch": 0.5891992020518666, "grad_norm": 1.4003921984699559, "learning_rate": 1.7782299602330663e-05, "loss": 0.6328, "step": 4135 }, { "epoch": 0.5893416927899686, "grad_norm": 1.6043124930309387, "learning_rate": 1.7780737569812347e-05, "loss": 0.6661, "step": 4136 }, { "epoch": 0.5894841835280706, "grad_norm": 1.2806934534595096, "learning_rate": 1.77791750560379e-05, "loss": 0.6474, "step": 4137 }, { "epoch": 0.5896266742661727, "grad_norm": 1.5304971264641904, "learning_rate": 1.7777612061103968e-05, "loss": 0.7441, "step": 4138 }, { "epoch": 0.5897691650042747, "grad_norm": 1.278273091099926, "learning_rate": 1.7776048585107218e-05, "loss": 0.6519, "step": 4139 }, { "epoch": 0.5899116557423767, "grad_norm": 1.3551889998407882, "learning_rate": 1.777448462814436e-05, "loss": 0.6863, "step": 4140 }, { "epoch": 0.5900541464804787, "grad_norm": 1.4073802608367139, "learning_rate": 1.7772920190312134e-05, "loss": 0.6199, "step": 4141 }, { "epoch": 0.5901966372185808, "grad_norm": 1.1983080133128066, "learning_rate": 1.7771355271707293e-05, "loss": 0.5962, "step": 4142 }, { "epoch": 0.5903391279566829, "grad_norm": 1.976881162352497, "learning_rate": 1.7769789872426636e-05, "loss": 0.644, "step": 4143 }, { "epoch": 0.5904816186947849, "grad_norm": 1.3300317326603917, "learning_rate": 1.7768223992566987e-05, "loss": 0.7092, "step": 4144 }, { "epoch": 0.5906241094328869, "grad_norm": 1.4364987975424977, "learning_rate": 1.7766657632225195e-05, "loss": 0.603, "step": 4145 }, { "epoch": 0.5907666001709889, "grad_norm": 1.32782705222694, "learning_rate": 1.7765090791498153e-05, "loss": 0.6621, "step": 4146 }, { "epoch": 0.5909090909090909, "grad_norm": 1.3941622485428837, "learning_rate": 1.7763523470482763e-05, "loss": 0.6567, "step": 4147 }, { "epoch": 0.591051581647193, "grad_norm": 1.4436665155770465, "learning_rate": 1.776195566927597e-05, "loss": 0.6649, "step": 4148 }, { "epoch": 0.591194072385295, "grad_norm": 1.2325410713860578, "learning_rate": 1.7760387387974746e-05, "loss": 0.6733, "step": 4149 }, { "epoch": 0.591336563123397, "grad_norm": 1.5562891661962235, "learning_rate": 1.77588186266761e-05, "loss": 0.6046, "step": 4150 }, { "epoch": 0.591479053861499, "grad_norm": 1.433484807924974, "learning_rate": 1.775724938547705e-05, "loss": 0.7417, "step": 4151 }, { "epoch": 0.591621544599601, "grad_norm": 1.432941400487565, "learning_rate": 1.7755679664474666e-05, "loss": 0.7198, "step": 4152 }, { "epoch": 0.591764035337703, "grad_norm": 1.6116212101447729, "learning_rate": 1.7754109463766044e-05, "loss": 0.7402, "step": 4153 }, { "epoch": 0.5919065260758051, "grad_norm": 1.323473550482585, "learning_rate": 1.775253878344829e-05, "loss": 0.6623, "step": 4154 }, { "epoch": 0.5920490168139071, "grad_norm": 1.4317653937620693, "learning_rate": 1.7750967623618564e-05, "loss": 0.6456, "step": 4155 }, { "epoch": 0.5921915075520091, "grad_norm": 1.544475651698655, "learning_rate": 1.7749395984374043e-05, "loss": 0.736, "step": 4156 }, { "epoch": 0.5923339982901111, "grad_norm": 1.2593285813342567, "learning_rate": 1.774782386581194e-05, "loss": 0.6894, "step": 4157 }, { "epoch": 0.5924764890282131, "grad_norm": 1.4101276438703343, "learning_rate": 1.774625126802949e-05, "loss": 0.6316, "step": 4158 }, { "epoch": 0.5926189797663152, "grad_norm": 1.27562657373657, "learning_rate": 1.774467819112396e-05, "loss": 0.5427, "step": 4159 }, { "epoch": 0.5927614705044172, "grad_norm": 1.4396266660679957, "learning_rate": 1.7743104635192657e-05, "loss": 0.6585, "step": 4160 }, { "epoch": 0.5929039612425192, "grad_norm": 1.6555955354949128, "learning_rate": 1.7741530600332895e-05, "loss": 0.7146, "step": 4161 }, { "epoch": 0.5930464519806212, "grad_norm": 1.342943105782081, "learning_rate": 1.7739956086642047e-05, "loss": 0.6484, "step": 4162 }, { "epoch": 0.5931889427187232, "grad_norm": 1.4646111391412955, "learning_rate": 1.7738381094217488e-05, "loss": 0.6701, "step": 4163 }, { "epoch": 0.5933314334568253, "grad_norm": 1.4426988212155345, "learning_rate": 1.7736805623156647e-05, "loss": 0.6406, "step": 4164 }, { "epoch": 0.5934739241949273, "grad_norm": 1.238784196459851, "learning_rate": 1.7735229673556956e-05, "loss": 0.602, "step": 4165 }, { "epoch": 0.5936164149330293, "grad_norm": 1.3782843096496291, "learning_rate": 1.77336532455159e-05, "loss": 0.6903, "step": 4166 }, { "epoch": 0.5937589056711314, "grad_norm": 1.3951317778996413, "learning_rate": 1.773207633913098e-05, "loss": 0.7126, "step": 4167 }, { "epoch": 0.5939013964092335, "grad_norm": 1.506932424629193, "learning_rate": 1.7730498954499738e-05, "loss": 0.7197, "step": 4168 }, { "epoch": 0.5940438871473355, "grad_norm": 1.2721770421101835, "learning_rate": 1.7728921091719733e-05, "loss": 0.6786, "step": 4169 }, { "epoch": 0.5941863778854375, "grad_norm": 1.3366894067475932, "learning_rate": 1.7727342750888562e-05, "loss": 0.7141, "step": 4170 }, { "epoch": 0.5943288686235395, "grad_norm": 1.505336388851782, "learning_rate": 1.772576393210385e-05, "loss": 0.6671, "step": 4171 }, { "epoch": 0.5944713593616415, "grad_norm": 1.4933316555967164, "learning_rate": 1.7724184635463245e-05, "loss": 0.7176, "step": 4172 }, { "epoch": 0.5946138500997435, "grad_norm": 1.4676570136236546, "learning_rate": 1.7722604861064434e-05, "loss": 0.7434, "step": 4173 }, { "epoch": 0.5947563408378456, "grad_norm": 1.4193169632606186, "learning_rate": 1.7721024609005133e-05, "loss": 0.7651, "step": 4174 }, { "epoch": 0.5948988315759476, "grad_norm": 1.3526612233773079, "learning_rate": 1.771944387938308e-05, "loss": 0.6883, "step": 4175 }, { "epoch": 0.5950413223140496, "grad_norm": 1.4707012941872102, "learning_rate": 1.7717862672296042e-05, "loss": 0.7415, "step": 4176 }, { "epoch": 0.5951838130521516, "grad_norm": 1.2489627996104469, "learning_rate": 1.7716280987841828e-05, "loss": 0.6226, "step": 4177 }, { "epoch": 0.5953263037902536, "grad_norm": 1.416076812810451, "learning_rate": 1.7714698826118267e-05, "loss": 0.6639, "step": 4178 }, { "epoch": 0.5954687945283557, "grad_norm": 1.3225004393353008, "learning_rate": 1.7713116187223218e-05, "loss": 0.7337, "step": 4179 }, { "epoch": 0.5956112852664577, "grad_norm": 1.4615652543132838, "learning_rate": 1.7711533071254568e-05, "loss": 0.7301, "step": 4180 }, { "epoch": 0.5957537760045597, "grad_norm": 1.2438705809238795, "learning_rate": 1.7709949478310244e-05, "loss": 0.6364, "step": 4181 }, { "epoch": 0.5958962667426617, "grad_norm": 1.3434476973269176, "learning_rate": 1.7708365408488187e-05, "loss": 0.6614, "step": 4182 }, { "epoch": 0.5960387574807637, "grad_norm": 1.3295869623440086, "learning_rate": 1.7706780861886378e-05, "loss": 0.6295, "step": 4183 }, { "epoch": 0.5961812482188658, "grad_norm": 1.2376334898133843, "learning_rate": 1.7705195838602832e-05, "loss": 0.6586, "step": 4184 }, { "epoch": 0.5963237389569678, "grad_norm": 1.3086326991637705, "learning_rate": 1.7703610338735572e-05, "loss": 0.769, "step": 4185 }, { "epoch": 0.5964662296950698, "grad_norm": 1.3064030957682087, "learning_rate": 1.7702024362382674e-05, "loss": 0.6896, "step": 4186 }, { "epoch": 0.5966087204331718, "grad_norm": 1.2593665296596266, "learning_rate": 1.7700437909642233e-05, "loss": 0.677, "step": 4187 }, { "epoch": 0.5967512111712738, "grad_norm": 1.2979699149309762, "learning_rate": 1.7698850980612375e-05, "loss": 0.6585, "step": 4188 }, { "epoch": 0.5968937019093759, "grad_norm": 1.8367778394546161, "learning_rate": 1.7697263575391256e-05, "loss": 0.6613, "step": 4189 }, { "epoch": 0.5970361926474779, "grad_norm": 1.341880419322863, "learning_rate": 1.7695675694077055e-05, "loss": 0.7169, "step": 4190 }, { "epoch": 0.5971786833855799, "grad_norm": 1.3988243325188718, "learning_rate": 1.769408733676799e-05, "loss": 0.7011, "step": 4191 }, { "epoch": 0.5973211741236819, "grad_norm": 1.4275244157334879, "learning_rate": 1.769249850356231e-05, "loss": 0.6639, "step": 4192 }, { "epoch": 0.597463664861784, "grad_norm": 1.7680800300502661, "learning_rate": 1.7690909194558276e-05, "loss": 0.7443, "step": 4193 }, { "epoch": 0.5976061555998861, "grad_norm": 1.3681086642658262, "learning_rate": 1.7689319409854197e-05, "loss": 0.7105, "step": 4194 }, { "epoch": 0.5977486463379881, "grad_norm": 1.3617457413804819, "learning_rate": 1.7687729149548406e-05, "loss": 0.78, "step": 4195 }, { "epoch": 0.5978911370760901, "grad_norm": 1.4802953949801225, "learning_rate": 1.768613841373926e-05, "loss": 0.6955, "step": 4196 }, { "epoch": 0.5980336278141921, "grad_norm": 1.2968265231042473, "learning_rate": 1.7684547202525156e-05, "loss": 0.7314, "step": 4197 }, { "epoch": 0.5981761185522941, "grad_norm": 1.2948590512335254, "learning_rate": 1.7682955516004506e-05, "loss": 0.6556, "step": 4198 }, { "epoch": 0.5983186092903962, "grad_norm": 1.3277086989565428, "learning_rate": 1.7681363354275767e-05, "loss": 0.641, "step": 4199 }, { "epoch": 0.5984611000284982, "grad_norm": 1.2951828812387802, "learning_rate": 1.7679770717437416e-05, "loss": 0.5825, "step": 4200 }, { "epoch": 0.5986035907666002, "grad_norm": 3.3419207634332224, "learning_rate": 1.7678177605587957e-05, "loss": 0.6618, "step": 4201 }, { "epoch": 0.5987460815047022, "grad_norm": 1.2967566093384177, "learning_rate": 1.7676584018825926e-05, "loss": 0.647, "step": 4202 }, { "epoch": 0.5988885722428042, "grad_norm": 1.3160550527073815, "learning_rate": 1.76749899572499e-05, "loss": 0.6479, "step": 4203 }, { "epoch": 0.5990310629809062, "grad_norm": 1.3693296655136475, "learning_rate": 1.7673395420958467e-05, "loss": 0.6568, "step": 4204 }, { "epoch": 0.5991735537190083, "grad_norm": 1.442739614971439, "learning_rate": 1.7671800410050255e-05, "loss": 0.6277, "step": 4205 }, { "epoch": 0.5993160444571103, "grad_norm": 1.7732680081232115, "learning_rate": 1.767020492462392e-05, "loss": 0.6322, "step": 4206 }, { "epoch": 0.5994585351952123, "grad_norm": 1.4065965203577608, "learning_rate": 1.766860896477814e-05, "loss": 0.6601, "step": 4207 }, { "epoch": 0.5996010259333143, "grad_norm": 1.4645919527258184, "learning_rate": 1.766701253061164e-05, "loss": 0.7113, "step": 4208 }, { "epoch": 0.5997435166714163, "grad_norm": 1.3967415653207391, "learning_rate": 1.7665415622223155e-05, "loss": 0.6274, "step": 4209 }, { "epoch": 0.5998860074095184, "grad_norm": 1.5180818111552792, "learning_rate": 1.766381823971146e-05, "loss": 0.5894, "step": 4210 }, { "epoch": 0.6000284981476204, "grad_norm": 1.9232034178136348, "learning_rate": 1.7662220383175354e-05, "loss": 0.6721, "step": 4211 }, { "epoch": 0.6001709888857224, "grad_norm": 1.3753644757786652, "learning_rate": 1.7660622052713674e-05, "loss": 0.6545, "step": 4212 }, { "epoch": 0.6003134796238244, "grad_norm": 1.3758858448225184, "learning_rate": 1.7659023248425274e-05, "loss": 0.6622, "step": 4213 }, { "epoch": 0.6004559703619264, "grad_norm": 1.4582773490533252, "learning_rate": 1.7657423970409047e-05, "loss": 0.651, "step": 4214 }, { "epoch": 0.6005984611000285, "grad_norm": 1.3208898576094552, "learning_rate": 1.765582421876391e-05, "loss": 0.6816, "step": 4215 }, { "epoch": 0.6007409518381305, "grad_norm": 1.3625298212045727, "learning_rate": 1.765422399358881e-05, "loss": 0.6644, "step": 4216 }, { "epoch": 0.6008834425762325, "grad_norm": 1.574215638692513, "learning_rate": 1.765262329498273e-05, "loss": 0.671, "step": 4217 }, { "epoch": 0.6010259333143345, "grad_norm": 1.2812528464863417, "learning_rate": 1.7651022123044676e-05, "loss": 0.6286, "step": 4218 }, { "epoch": 0.6011684240524366, "grad_norm": 1.4284122439044922, "learning_rate": 1.7649420477873677e-05, "loss": 0.6591, "step": 4219 }, { "epoch": 0.6013109147905387, "grad_norm": 1.450394855743006, "learning_rate": 1.7647818359568803e-05, "loss": 0.624, "step": 4220 }, { "epoch": 0.6014534055286407, "grad_norm": 1.4588281026116046, "learning_rate": 1.7646215768229154e-05, "loss": 0.7712, "step": 4221 }, { "epoch": 0.6015958962667427, "grad_norm": 1.344828674763735, "learning_rate": 1.7644612703953846e-05, "loss": 0.6828, "step": 4222 }, { "epoch": 0.6017383870048447, "grad_norm": 1.5315970247924897, "learning_rate": 1.7643009166842033e-05, "loss": 0.6532, "step": 4223 }, { "epoch": 0.6018808777429467, "grad_norm": 1.3360150356575158, "learning_rate": 1.7641405156992902e-05, "loss": 0.6873, "step": 4224 }, { "epoch": 0.6020233684810488, "grad_norm": 1.4984871360986027, "learning_rate": 1.7639800674505658e-05, "loss": 0.6995, "step": 4225 }, { "epoch": 0.6021658592191508, "grad_norm": 1.585166408971606, "learning_rate": 1.7638195719479546e-05, "loss": 0.649, "step": 4226 }, { "epoch": 0.6023083499572528, "grad_norm": 1.399248673764771, "learning_rate": 1.763659029201384e-05, "loss": 0.6777, "step": 4227 }, { "epoch": 0.6024508406953548, "grad_norm": 1.3994013223979782, "learning_rate": 1.763498439220783e-05, "loss": 0.6904, "step": 4228 }, { "epoch": 0.6025933314334568, "grad_norm": 1.3522940607580314, "learning_rate": 1.7633378020160854e-05, "loss": 0.7465, "step": 4229 }, { "epoch": 0.6027358221715589, "grad_norm": 1.327231989605246, "learning_rate": 1.7631771175972264e-05, "loss": 0.6578, "step": 4230 }, { "epoch": 0.6028783129096609, "grad_norm": 1.3678333614909104, "learning_rate": 1.7630163859741448e-05, "loss": 0.6286, "step": 4231 }, { "epoch": 0.6030208036477629, "grad_norm": 1.3916952207234379, "learning_rate": 1.762855607156782e-05, "loss": 0.7196, "step": 4232 }, { "epoch": 0.6031632943858649, "grad_norm": 1.4968103205357313, "learning_rate": 1.7626947811550826e-05, "loss": 0.6374, "step": 4233 }, { "epoch": 0.6033057851239669, "grad_norm": 1.3452786611895498, "learning_rate": 1.7625339079789947e-05, "loss": 0.6781, "step": 4234 }, { "epoch": 0.603448275862069, "grad_norm": 1.5112183809149817, "learning_rate": 1.762372987638468e-05, "loss": 0.677, "step": 4235 }, { "epoch": 0.603590766600171, "grad_norm": 1.384618286288483, "learning_rate": 1.7622120201434562e-05, "loss": 0.5672, "step": 4236 }, { "epoch": 0.603733257338273, "grad_norm": 1.3548721120437943, "learning_rate": 1.762051005503915e-05, "loss": 0.6884, "step": 4237 }, { "epoch": 0.603875748076375, "grad_norm": 1.4950390520128434, "learning_rate": 1.7618899437298037e-05, "loss": 0.6432, "step": 4238 }, { "epoch": 0.604018238814477, "grad_norm": 1.4938700510371594, "learning_rate": 1.7617288348310843e-05, "loss": 0.6715, "step": 4239 }, { "epoch": 0.604160729552579, "grad_norm": 1.357055399547327, "learning_rate": 1.761567678817722e-05, "loss": 0.7232, "step": 4240 }, { "epoch": 0.6043032202906811, "grad_norm": 1.278866049008682, "learning_rate": 1.7614064756996848e-05, "loss": 0.6823, "step": 4241 }, { "epoch": 0.6044457110287831, "grad_norm": 1.819917003114964, "learning_rate": 1.761245225486943e-05, "loss": 0.6547, "step": 4242 }, { "epoch": 0.6045882017668851, "grad_norm": 1.2607799227227783, "learning_rate": 1.7610839281894704e-05, "loss": 0.6585, "step": 4243 }, { "epoch": 0.6047306925049871, "grad_norm": 1.3995746249448109, "learning_rate": 1.760922583817244e-05, "loss": 0.6933, "step": 4244 }, { "epoch": 0.6048731832430893, "grad_norm": 1.3603509296913832, "learning_rate": 1.7607611923802427e-05, "loss": 0.6321, "step": 4245 }, { "epoch": 0.6050156739811913, "grad_norm": 1.4162372316980492, "learning_rate": 1.760599753888449e-05, "loss": 0.6561, "step": 4246 }, { "epoch": 0.6051581647192933, "grad_norm": 1.288343334310386, "learning_rate": 1.760438268351849e-05, "loss": 0.6074, "step": 4247 }, { "epoch": 0.6053006554573953, "grad_norm": 1.5651666825951727, "learning_rate": 1.76027673578043e-05, "loss": 0.6593, "step": 4248 }, { "epoch": 0.6054431461954973, "grad_norm": 73.0095087712425, "learning_rate": 1.760115156184184e-05, "loss": 0.6314, "step": 4249 }, { "epoch": 0.6055856369335993, "grad_norm": 1.3467302181497216, "learning_rate": 1.7599535295731042e-05, "loss": 0.5387, "step": 4250 }, { "epoch": 0.6057281276717014, "grad_norm": 1.2833412204358847, "learning_rate": 1.759791855957188e-05, "loss": 0.6345, "step": 4251 }, { "epoch": 0.6058706184098034, "grad_norm": 1.4863461700803784, "learning_rate": 1.7596301353464354e-05, "loss": 0.7437, "step": 4252 }, { "epoch": 0.6060131091479054, "grad_norm": 1.4721074427315455, "learning_rate": 1.7594683677508494e-05, "loss": 0.6243, "step": 4253 }, { "epoch": 0.6061555998860074, "grad_norm": 1.376472090165389, "learning_rate": 1.759306553180435e-05, "loss": 0.6504, "step": 4254 }, { "epoch": 0.6062980906241094, "grad_norm": 1.2955813803078178, "learning_rate": 1.7591446916452012e-05, "loss": 0.7346, "step": 4255 }, { "epoch": 0.6064405813622115, "grad_norm": 1.2689884624147172, "learning_rate": 1.758982783155159e-05, "loss": 0.582, "step": 4256 }, { "epoch": 0.6065830721003135, "grad_norm": 1.3576721223256005, "learning_rate": 1.758820827720324e-05, "loss": 0.6028, "step": 4257 }, { "epoch": 0.6067255628384155, "grad_norm": 1.3749774763718599, "learning_rate": 1.7586588253507125e-05, "loss": 0.634, "step": 4258 }, { "epoch": 0.6068680535765175, "grad_norm": 1.447225968704567, "learning_rate": 1.7584967760563448e-05, "loss": 0.6284, "step": 4259 }, { "epoch": 0.6070105443146195, "grad_norm": 1.3192537120180095, "learning_rate": 1.758334679847244e-05, "loss": 0.6302, "step": 4260 }, { "epoch": 0.6071530350527216, "grad_norm": 1.449797021522763, "learning_rate": 1.7581725367334367e-05, "loss": 0.6992, "step": 4261 }, { "epoch": 0.6072955257908236, "grad_norm": 1.6153742136075562, "learning_rate": 1.7580103467249513e-05, "loss": 0.7004, "step": 4262 }, { "epoch": 0.6074380165289256, "grad_norm": 1.3354515095471495, "learning_rate": 1.7578481098318193e-05, "loss": 0.646, "step": 4263 }, { "epoch": 0.6075805072670276, "grad_norm": 1.8517433496966114, "learning_rate": 1.7576858260640762e-05, "loss": 0.6841, "step": 4264 }, { "epoch": 0.6077229980051296, "grad_norm": 1.3037033678258447, "learning_rate": 1.7575234954317592e-05, "loss": 0.7069, "step": 4265 }, { "epoch": 0.6078654887432317, "grad_norm": 1.429035700064622, "learning_rate": 1.757361117944909e-05, "loss": 0.6714, "step": 4266 }, { "epoch": 0.6080079794813337, "grad_norm": 1.4794351071634113, "learning_rate": 1.757198693613569e-05, "loss": 0.6379, "step": 4267 }, { "epoch": 0.6081504702194357, "grad_norm": 1.363650424017824, "learning_rate": 1.757036222447785e-05, "loss": 0.6615, "step": 4268 }, { "epoch": 0.6082929609575377, "grad_norm": 3.038838311099712, "learning_rate": 1.756873704457607e-05, "loss": 0.6919, "step": 4269 }, { "epoch": 0.6084354516956397, "grad_norm": 1.38143763658739, "learning_rate": 1.756711139653086e-05, "loss": 0.6935, "step": 4270 }, { "epoch": 0.6085779424337419, "grad_norm": 1.488906586654191, "learning_rate": 1.7565485280442785e-05, "loss": 0.5927, "step": 4271 }, { "epoch": 0.6087204331718439, "grad_norm": 1.6258557013115307, "learning_rate": 1.756385869641241e-05, "loss": 0.6206, "step": 4272 }, { "epoch": 0.6088629239099459, "grad_norm": 1.4943312642601263, "learning_rate": 1.7562231644540354e-05, "loss": 0.6318, "step": 4273 }, { "epoch": 0.6090054146480479, "grad_norm": 1.3330299814952113, "learning_rate": 1.7560604124927246e-05, "loss": 0.6367, "step": 4274 }, { "epoch": 0.6091479053861499, "grad_norm": 1.572802261953622, "learning_rate": 1.7558976137673757e-05, "loss": 0.7521, "step": 4275 }, { "epoch": 0.609290396124252, "grad_norm": 1.3484188105591752, "learning_rate": 1.7557347682880575e-05, "loss": 0.7679, "step": 4276 }, { "epoch": 0.609432886862354, "grad_norm": 1.3639090005353853, "learning_rate": 1.7555718760648432e-05, "loss": 0.5736, "step": 4277 }, { "epoch": 0.609575377600456, "grad_norm": 1.299738834693969, "learning_rate": 1.7554089371078072e-05, "loss": 0.6, "step": 4278 }, { "epoch": 0.609717868338558, "grad_norm": 1.6734911113863682, "learning_rate": 1.7552459514270284e-05, "loss": 0.7088, "step": 4279 }, { "epoch": 0.60986035907666, "grad_norm": 1.4105089352597657, "learning_rate": 1.7550829190325875e-05, "loss": 0.7259, "step": 4280 }, { "epoch": 0.610002849814762, "grad_norm": 1.3264495416420794, "learning_rate": 1.7549198399345683e-05, "loss": 0.6761, "step": 4281 }, { "epoch": 0.6101453405528641, "grad_norm": 1.2867922762598372, "learning_rate": 1.7547567141430576e-05, "loss": 0.7113, "step": 4282 }, { "epoch": 0.6102878312909661, "grad_norm": 1.4736398849073136, "learning_rate": 1.7545935416681453e-05, "loss": 0.6375, "step": 4283 }, { "epoch": 0.6104303220290681, "grad_norm": 1.3550121268635587, "learning_rate": 1.754430322519924e-05, "loss": 0.638, "step": 4284 }, { "epoch": 0.6105728127671701, "grad_norm": 1.5551196671537086, "learning_rate": 1.7542670567084887e-05, "loss": 0.6515, "step": 4285 }, { "epoch": 0.6107153035052721, "grad_norm": 1.4790214768038117, "learning_rate": 1.7541037442439388e-05, "loss": 0.6739, "step": 4286 }, { "epoch": 0.6108577942433742, "grad_norm": 1.287778479566183, "learning_rate": 1.7539403851363747e-05, "loss": 0.5962, "step": 4287 }, { "epoch": 0.6110002849814762, "grad_norm": 1.4764655433682352, "learning_rate": 1.7537769793959003e-05, "loss": 0.6455, "step": 4288 }, { "epoch": 0.6111427757195782, "grad_norm": 1.3227007628950014, "learning_rate": 1.753613527032623e-05, "loss": 0.648, "step": 4289 }, { "epoch": 0.6112852664576802, "grad_norm": 1.481756466425753, "learning_rate": 1.753450028056653e-05, "loss": 0.713, "step": 4290 }, { "epoch": 0.6114277571957822, "grad_norm": 1.3973917325749592, "learning_rate": 1.753286482478103e-05, "loss": 0.7141, "step": 4291 }, { "epoch": 0.6115702479338843, "grad_norm": 1.4118711570809657, "learning_rate": 1.753122890307088e-05, "loss": 0.6266, "step": 4292 }, { "epoch": 0.6117127386719863, "grad_norm": 1.2495109800496134, "learning_rate": 1.7529592515537276e-05, "loss": 0.6472, "step": 4293 }, { "epoch": 0.6118552294100883, "grad_norm": 1.569280285733317, "learning_rate": 1.7527955662281423e-05, "loss": 0.6966, "step": 4294 }, { "epoch": 0.6119977201481903, "grad_norm": 1.366140671056782, "learning_rate": 1.7526318343404566e-05, "loss": 0.6452, "step": 4295 }, { "epoch": 0.6121402108862924, "grad_norm": 1.3612423749939395, "learning_rate": 1.752468055900798e-05, "loss": 0.622, "step": 4296 }, { "epoch": 0.6122827016243945, "grad_norm": 1.3722634420742554, "learning_rate": 1.752304230919296e-05, "loss": 0.6845, "step": 4297 }, { "epoch": 0.6124251923624965, "grad_norm": 1.441778390137226, "learning_rate": 1.7521403594060845e-05, "loss": 0.6459, "step": 4298 }, { "epoch": 0.6125676831005985, "grad_norm": 1.6424703984194644, "learning_rate": 1.751976441371298e-05, "loss": 0.7544, "step": 4299 }, { "epoch": 0.6127101738387005, "grad_norm": 1.4461612610928596, "learning_rate": 1.751812476825077e-05, "loss": 0.732, "step": 4300 }, { "epoch": 0.6128526645768025, "grad_norm": 1.7496130773627716, "learning_rate": 1.7516484657775616e-05, "loss": 0.7346, "step": 4301 }, { "epoch": 0.6129951553149046, "grad_norm": 1.6030289918658756, "learning_rate": 1.751484408238896e-05, "loss": 0.8164, "step": 4302 }, { "epoch": 0.6131376460530066, "grad_norm": 1.5027873654669472, "learning_rate": 1.7513203042192292e-05, "loss": 0.6681, "step": 4303 }, { "epoch": 0.6132801367911086, "grad_norm": 1.3809973363375727, "learning_rate": 1.75115615372871e-05, "loss": 0.7116, "step": 4304 }, { "epoch": 0.6134226275292106, "grad_norm": 1.4819669938914888, "learning_rate": 1.7509919567774914e-05, "loss": 0.6553, "step": 4305 }, { "epoch": 0.6135651182673126, "grad_norm": 1.232568400700528, "learning_rate": 1.7508277133757304e-05, "loss": 0.4952, "step": 4306 }, { "epoch": 0.6137076090054147, "grad_norm": 1.3393405170101778, "learning_rate": 1.7506634235335852e-05, "loss": 0.6157, "step": 4307 }, { "epoch": 0.6138500997435167, "grad_norm": 2.001128542225861, "learning_rate": 1.7504990872612175e-05, "loss": 0.6583, "step": 4308 }, { "epoch": 0.6139925904816187, "grad_norm": 1.3745375766173311, "learning_rate": 1.750334704568792e-05, "loss": 0.6517, "step": 4309 }, { "epoch": 0.6141350812197207, "grad_norm": 1.2321604900066345, "learning_rate": 1.750170275466476e-05, "loss": 0.6349, "step": 4310 }, { "epoch": 0.6142775719578227, "grad_norm": 1.3342493916804974, "learning_rate": 1.75000579996444e-05, "loss": 0.6806, "step": 4311 }, { "epoch": 0.6144200626959248, "grad_norm": 1.5095040089267435, "learning_rate": 1.749841278072857e-05, "loss": 0.6859, "step": 4312 }, { "epoch": 0.6145625534340268, "grad_norm": 2.0586729237057644, "learning_rate": 1.7496767098019033e-05, "loss": 0.7715, "step": 4313 }, { "epoch": 0.6147050441721288, "grad_norm": 1.300084161997679, "learning_rate": 1.749512095161757e-05, "loss": 0.7122, "step": 4314 }, { "epoch": 0.6148475349102308, "grad_norm": 1.3223098563929265, "learning_rate": 1.7493474341626013e-05, "loss": 0.7318, "step": 4315 }, { "epoch": 0.6149900256483328, "grad_norm": 1.4755757373015637, "learning_rate": 1.7491827268146194e-05, "loss": 0.7775, "step": 4316 }, { "epoch": 0.6151325163864348, "grad_norm": 1.56783791228874, "learning_rate": 1.749017973128e-05, "loss": 0.6189, "step": 4317 }, { "epoch": 0.6152750071245369, "grad_norm": 1.4549918890189588, "learning_rate": 1.7488531731129325e-05, "loss": 0.6489, "step": 4318 }, { "epoch": 0.6154174978626389, "grad_norm": 1.2822429685243484, "learning_rate": 1.7486883267796107e-05, "loss": 0.7155, "step": 4319 }, { "epoch": 0.6155599886007409, "grad_norm": 1.3373246402707955, "learning_rate": 1.7485234341382307e-05, "loss": 0.6668, "step": 4320 }, { "epoch": 0.6157024793388429, "grad_norm": 1.383502765181604, "learning_rate": 1.7483584951989917e-05, "loss": 0.6465, "step": 4321 }, { "epoch": 0.615844970076945, "grad_norm": 1.342860555627244, "learning_rate": 1.748193509972095e-05, "loss": 0.6025, "step": 4322 }, { "epoch": 0.6159874608150471, "grad_norm": 2.2085675930967477, "learning_rate": 1.7480284784677457e-05, "loss": 0.658, "step": 4323 }, { "epoch": 0.6161299515531491, "grad_norm": 1.3714148212261155, "learning_rate": 1.7478634006961512e-05, "loss": 0.6928, "step": 4324 }, { "epoch": 0.6162724422912511, "grad_norm": 1.3484046127321134, "learning_rate": 1.7476982766675223e-05, "loss": 0.6812, "step": 4325 }, { "epoch": 0.6164149330293531, "grad_norm": 1.354325059447602, "learning_rate": 1.7475331063920715e-05, "loss": 0.5915, "step": 4326 }, { "epoch": 0.6165574237674551, "grad_norm": 1.6475028971670393, "learning_rate": 1.7473678898800153e-05, "loss": 0.6417, "step": 4327 }, { "epoch": 0.6166999145055572, "grad_norm": 1.3121498460164516, "learning_rate": 1.7472026271415732e-05, "loss": 0.6694, "step": 4328 }, { "epoch": 0.6168424052436592, "grad_norm": 1.5262675783309425, "learning_rate": 1.7470373181869667e-05, "loss": 0.6673, "step": 4329 }, { "epoch": 0.6169848959817612, "grad_norm": 1.3781358498109375, "learning_rate": 1.7468719630264205e-05, "loss": 0.7014, "step": 4330 }, { "epoch": 0.6171273867198632, "grad_norm": 1.9033846692602503, "learning_rate": 1.746706561670162e-05, "loss": 0.6731, "step": 4331 }, { "epoch": 0.6172698774579652, "grad_norm": 1.3353774673952832, "learning_rate": 1.7465411141284222e-05, "loss": 0.6893, "step": 4332 }, { "epoch": 0.6174123681960673, "grad_norm": 1.3553397266277256, "learning_rate": 1.746375620411434e-05, "loss": 0.6755, "step": 4333 }, { "epoch": 0.6175548589341693, "grad_norm": 1.239033574265305, "learning_rate": 1.7462100805294335e-05, "loss": 0.587, "step": 4334 }, { "epoch": 0.6176973496722713, "grad_norm": 1.3765292839592433, "learning_rate": 1.7460444944926598e-05, "loss": 0.6503, "step": 4335 }, { "epoch": 0.6178398404103733, "grad_norm": 1.427396117324422, "learning_rate": 1.745878862311355e-05, "loss": 0.7649, "step": 4336 }, { "epoch": 0.6179823311484753, "grad_norm": 2.4975613683041353, "learning_rate": 1.7457131839957634e-05, "loss": 0.7344, "step": 4337 }, { "epoch": 0.6181248218865774, "grad_norm": 1.490170341788953, "learning_rate": 1.745547459556133e-05, "loss": 0.6583, "step": 4338 }, { "epoch": 0.6182673126246794, "grad_norm": 1.297665209862424, "learning_rate": 1.7453816890027143e-05, "loss": 0.6606, "step": 4339 }, { "epoch": 0.6184098033627814, "grad_norm": 1.5136327718577423, "learning_rate": 1.7452158723457597e-05, "loss": 0.6535, "step": 4340 }, { "epoch": 0.6185522941008834, "grad_norm": 1.3789717438279703, "learning_rate": 1.7450500095955265e-05, "loss": 0.7627, "step": 4341 }, { "epoch": 0.6186947848389854, "grad_norm": 1.2909852286901156, "learning_rate": 1.744884100762273e-05, "loss": 0.5981, "step": 4342 }, { "epoch": 0.6188372755770875, "grad_norm": 1.3604243655249995, "learning_rate": 1.7447181458562614e-05, "loss": 0.7016, "step": 4343 }, { "epoch": 0.6189797663151895, "grad_norm": 1.3020428770511152, "learning_rate": 1.7445521448877557e-05, "loss": 0.7567, "step": 4344 }, { "epoch": 0.6191222570532915, "grad_norm": 1.4940536348363649, "learning_rate": 1.744386097867024e-05, "loss": 0.6524, "step": 4345 }, { "epoch": 0.6192647477913935, "grad_norm": 1.2135028553498992, "learning_rate": 1.7442200048043367e-05, "loss": 0.6506, "step": 4346 }, { "epoch": 0.6194072385294955, "grad_norm": 1.365230341028164, "learning_rate": 1.744053865709967e-05, "loss": 0.6252, "step": 4347 }, { "epoch": 0.6195497292675977, "grad_norm": 1.4275401378403072, "learning_rate": 1.743887680594191e-05, "loss": 0.6335, "step": 4348 }, { "epoch": 0.6196922200056997, "grad_norm": 1.5037023813259864, "learning_rate": 1.743721449467287e-05, "loss": 0.6314, "step": 4349 }, { "epoch": 0.6198347107438017, "grad_norm": 1.2256267627054116, "learning_rate": 1.7435551723395375e-05, "loss": 0.6007, "step": 4350 }, { "epoch": 0.6199772014819037, "grad_norm": 1.4861764308261787, "learning_rate": 1.7433888492212272e-05, "loss": 0.7207, "step": 4351 }, { "epoch": 0.6201196922200057, "grad_norm": 1.4975602973948734, "learning_rate": 1.743222480122643e-05, "loss": 0.71, "step": 4352 }, { "epoch": 0.6202621829581078, "grad_norm": 1.261924869736558, "learning_rate": 1.7430560650540754e-05, "loss": 0.5726, "step": 4353 }, { "epoch": 0.6204046736962098, "grad_norm": 1.312054070715891, "learning_rate": 1.742889604025818e-05, "loss": 0.6398, "step": 4354 }, { "epoch": 0.6205471644343118, "grad_norm": 1.4251003458895848, "learning_rate": 1.742723097048166e-05, "loss": 0.6521, "step": 4355 }, { "epoch": 0.6206896551724138, "grad_norm": 1.372219116161577, "learning_rate": 1.7425565441314187e-05, "loss": 0.6276, "step": 4356 }, { "epoch": 0.6208321459105158, "grad_norm": 1.3537536050038168, "learning_rate": 1.7423899452858777e-05, "loss": 0.6293, "step": 4357 }, { "epoch": 0.6209746366486179, "grad_norm": 1.4130800137436306, "learning_rate": 1.7422233005218476e-05, "loss": 0.7177, "step": 4358 }, { "epoch": 0.6211171273867199, "grad_norm": 1.369728526974741, "learning_rate": 1.7420566098496356e-05, "loss": 0.6928, "step": 4359 }, { "epoch": 0.6212596181248219, "grad_norm": 1.3735944538174445, "learning_rate": 1.741889873279552e-05, "loss": 0.6127, "step": 4360 }, { "epoch": 0.6214021088629239, "grad_norm": 1.5005894998263198, "learning_rate": 1.74172309082191e-05, "loss": 0.7226, "step": 4361 }, { "epoch": 0.6215445996010259, "grad_norm": 1.4307196752736155, "learning_rate": 1.7415562624870248e-05, "loss": 0.7523, "step": 4362 }, { "epoch": 0.621687090339128, "grad_norm": 1.5947120893076727, "learning_rate": 1.7413893882852158e-05, "loss": 0.7045, "step": 4363 }, { "epoch": 0.62182958107723, "grad_norm": 1.266900581806826, "learning_rate": 1.7412224682268042e-05, "loss": 0.5787, "step": 4364 }, { "epoch": 0.621972071815332, "grad_norm": 1.475478927031441, "learning_rate": 1.7410555023221147e-05, "loss": 0.7085, "step": 4365 }, { "epoch": 0.622114562553434, "grad_norm": 1.2421043540538594, "learning_rate": 1.740888490581474e-05, "loss": 0.7275, "step": 4366 }, { "epoch": 0.622257053291536, "grad_norm": 1.354716150595515, "learning_rate": 1.7407214330152128e-05, "loss": 0.6455, "step": 4367 }, { "epoch": 0.622399544029638, "grad_norm": 1.4026063446260943, "learning_rate": 1.7405543296336637e-05, "loss": 0.7721, "step": 4368 }, { "epoch": 0.6225420347677401, "grad_norm": 1.2920488779374601, "learning_rate": 1.740387180447162e-05, "loss": 0.6364, "step": 4369 }, { "epoch": 0.6226845255058421, "grad_norm": 1.326713629734156, "learning_rate": 1.740219985466047e-05, "loss": 0.6565, "step": 4370 }, { "epoch": 0.6228270162439441, "grad_norm": 1.4718182155363815, "learning_rate": 1.7400527447006596e-05, "loss": 0.6966, "step": 4371 }, { "epoch": 0.6229695069820461, "grad_norm": 1.296902648905414, "learning_rate": 1.739885458161344e-05, "loss": 0.6639, "step": 4372 }, { "epoch": 0.6231119977201481, "grad_norm": 1.2643569822605119, "learning_rate": 1.7397181258584476e-05, "loss": 0.6867, "step": 4373 }, { "epoch": 0.6232544884582503, "grad_norm": 1.3594229321025137, "learning_rate": 1.73955074780232e-05, "loss": 0.6454, "step": 4374 }, { "epoch": 0.6233969791963523, "grad_norm": 1.4474128266226054, "learning_rate": 1.7393833240033138e-05, "loss": 0.716, "step": 4375 }, { "epoch": 0.6235394699344543, "grad_norm": 1.2960168426496936, "learning_rate": 1.7392158544717847e-05, "loss": 0.6529, "step": 4376 }, { "epoch": 0.6236819606725563, "grad_norm": 1.3357692453087207, "learning_rate": 1.7390483392180912e-05, "loss": 0.6719, "step": 4377 }, { "epoch": 0.6238244514106583, "grad_norm": 1.39064503486669, "learning_rate": 1.7388807782525945e-05, "loss": 0.7157, "step": 4378 }, { "epoch": 0.6239669421487604, "grad_norm": 1.3084635828255449, "learning_rate": 1.7387131715856583e-05, "loss": 0.6024, "step": 4379 }, { "epoch": 0.6241094328868624, "grad_norm": 1.248071990403529, "learning_rate": 1.7385455192276498e-05, "loss": 0.7244, "step": 4380 }, { "epoch": 0.6242519236249644, "grad_norm": 1.445142301168579, "learning_rate": 1.7383778211889382e-05, "loss": 0.6861, "step": 4381 }, { "epoch": 0.6243944143630664, "grad_norm": 2.226683626751374, "learning_rate": 1.7382100774798964e-05, "loss": 0.6476, "step": 4382 }, { "epoch": 0.6245369051011684, "grad_norm": 1.4306279989248485, "learning_rate": 1.7380422881109e-05, "loss": 0.6731, "step": 4383 }, { "epoch": 0.6246793958392705, "grad_norm": 1.3625631197077266, "learning_rate": 1.7378744530923264e-05, "loss": 0.563, "step": 4384 }, { "epoch": 0.6248218865773725, "grad_norm": 1.4605519616074865, "learning_rate": 1.7377065724345572e-05, "loss": 0.6641, "step": 4385 }, { "epoch": 0.6249643773154745, "grad_norm": 1.4664273772614358, "learning_rate": 1.737538646147976e-05, "loss": 0.6229, "step": 4386 }, { "epoch": 0.6251068680535765, "grad_norm": 1.4101012982902548, "learning_rate": 1.737370674242969e-05, "loss": 0.6883, "step": 4387 }, { "epoch": 0.6252493587916785, "grad_norm": 1.4318961974124353, "learning_rate": 1.7372026567299266e-05, "loss": 0.6771, "step": 4388 }, { "epoch": 0.6253918495297806, "grad_norm": 1.443354258633824, "learning_rate": 1.73703459361924e-05, "loss": 0.6649, "step": 4389 }, { "epoch": 0.6255343402678826, "grad_norm": 1.5352724719068271, "learning_rate": 1.736866484921305e-05, "loss": 0.5921, "step": 4390 }, { "epoch": 0.6256768310059846, "grad_norm": 1.4559673388379097, "learning_rate": 1.7366983306465192e-05, "loss": 0.6508, "step": 4391 }, { "epoch": 0.6258193217440866, "grad_norm": 1.31952006238593, "learning_rate": 1.7365301308052832e-05, "loss": 0.6944, "step": 4392 }, { "epoch": 0.6259618124821886, "grad_norm": 1.3789284784289138, "learning_rate": 1.7363618854080014e-05, "loss": 0.6373, "step": 4393 }, { "epoch": 0.6261043032202906, "grad_norm": 1.4213684085102352, "learning_rate": 1.7361935944650787e-05, "loss": 0.7157, "step": 4394 }, { "epoch": 0.6262467939583927, "grad_norm": 1.3329118854135724, "learning_rate": 1.7360252579869255e-05, "loss": 0.597, "step": 4395 }, { "epoch": 0.6263892846964947, "grad_norm": 1.4692612989261251, "learning_rate": 1.735856875983953e-05, "loss": 0.7522, "step": 4396 }, { "epoch": 0.6265317754345967, "grad_norm": 1.5936661879109475, "learning_rate": 1.735688448466577e-05, "loss": 0.774, "step": 4397 }, { "epoch": 0.6266742661726987, "grad_norm": 1.346510799800693, "learning_rate": 1.7355199754452138e-05, "loss": 0.6655, "step": 4398 }, { "epoch": 0.6268167569108007, "grad_norm": 1.3571545469378588, "learning_rate": 1.735351456930285e-05, "loss": 0.6589, "step": 4399 }, { "epoch": 0.6269592476489029, "grad_norm": 1.393082215476329, "learning_rate": 1.7351828929322132e-05, "loss": 0.733, "step": 4400 }, { "epoch": 0.6271017383870049, "grad_norm": 1.3297774369692132, "learning_rate": 1.735014283461424e-05, "loss": 0.617, "step": 4401 }, { "epoch": 0.6272442291251069, "grad_norm": 1.3319968953766894, "learning_rate": 1.7348456285283476e-05, "loss": 0.627, "step": 4402 }, { "epoch": 0.6273867198632089, "grad_norm": 1.4564439226296393, "learning_rate": 1.734676928143415e-05, "loss": 0.7374, "step": 4403 }, { "epoch": 0.627529210601311, "grad_norm": 1.3985228990961716, "learning_rate": 1.7345081823170605e-05, "loss": 0.6464, "step": 4404 }, { "epoch": 0.627671701339413, "grad_norm": 1.4377392958775448, "learning_rate": 1.734339391059722e-05, "loss": 0.6463, "step": 4405 }, { "epoch": 0.627814192077515, "grad_norm": 1.5597338529699367, "learning_rate": 1.7341705543818385e-05, "loss": 0.6725, "step": 4406 }, { "epoch": 0.627956682815617, "grad_norm": 1.7790501090029962, "learning_rate": 1.734001672293854e-05, "loss": 0.6681, "step": 4407 }, { "epoch": 0.628099173553719, "grad_norm": 1.3484092119019577, "learning_rate": 1.733832744806214e-05, "loss": 0.7107, "step": 4408 }, { "epoch": 0.628241664291821, "grad_norm": 1.3491998611006586, "learning_rate": 1.7336637719293667e-05, "loss": 0.6022, "step": 4409 }, { "epoch": 0.6283841550299231, "grad_norm": 1.4275658044363726, "learning_rate": 1.7334947536737637e-05, "loss": 0.6964, "step": 4410 }, { "epoch": 0.6285266457680251, "grad_norm": 1.5756904741610618, "learning_rate": 1.7333256900498594e-05, "loss": 0.7191, "step": 4411 }, { "epoch": 0.6286691365061271, "grad_norm": 1.3739214225631178, "learning_rate": 1.7331565810681105e-05, "loss": 0.666, "step": 4412 }, { "epoch": 0.6288116272442291, "grad_norm": 1.3913826073963496, "learning_rate": 1.7329874267389762e-05, "loss": 0.7629, "step": 4413 }, { "epoch": 0.6289541179823311, "grad_norm": 1.3391737635106518, "learning_rate": 1.73281822707292e-05, "loss": 0.6341, "step": 4414 }, { "epoch": 0.6290966087204332, "grad_norm": 1.4027020686264162, "learning_rate": 1.732648982080407e-05, "loss": 0.6066, "step": 4415 }, { "epoch": 0.6292390994585352, "grad_norm": 1.3132213150661667, "learning_rate": 1.7324796917719052e-05, "loss": 0.7001, "step": 4416 }, { "epoch": 0.6293815901966372, "grad_norm": 1.4766190400041628, "learning_rate": 1.732310356157886e-05, "loss": 0.6704, "step": 4417 }, { "epoch": 0.6295240809347392, "grad_norm": 1.3780764881069199, "learning_rate": 1.7321409752488225e-05, "loss": 0.6342, "step": 4418 }, { "epoch": 0.6296665716728412, "grad_norm": 1.2730812645251017, "learning_rate": 1.731971549055192e-05, "loss": 0.7055, "step": 4419 }, { "epoch": 0.6298090624109433, "grad_norm": 1.3034542109526115, "learning_rate": 1.7318020775874733e-05, "loss": 0.6785, "step": 4420 }, { "epoch": 0.6299515531490453, "grad_norm": 1.4924990293108633, "learning_rate": 1.731632560856149e-05, "loss": 0.7028, "step": 4421 }, { "epoch": 0.6300940438871473, "grad_norm": 1.3777629101967044, "learning_rate": 1.731462998871704e-05, "loss": 0.7164, "step": 4422 }, { "epoch": 0.6302365346252493, "grad_norm": 1.4622489148877846, "learning_rate": 1.731293391644626e-05, "loss": 0.6698, "step": 4423 }, { "epoch": 0.6303790253633513, "grad_norm": 1.5286146339099196, "learning_rate": 1.7311237391854056e-05, "loss": 0.622, "step": 4424 }, { "epoch": 0.6305215161014535, "grad_norm": 1.5556904040489699, "learning_rate": 1.7309540415045362e-05, "loss": 0.6868, "step": 4425 }, { "epoch": 0.6306640068395555, "grad_norm": 1.4659106300846128, "learning_rate": 1.7307842986125138e-05, "loss": 0.6947, "step": 4426 }, { "epoch": 0.6308064975776575, "grad_norm": 1.3570571962670035, "learning_rate": 1.730614510519838e-05, "loss": 0.7291, "step": 4427 }, { "epoch": 0.6309489883157595, "grad_norm": 1.5249060166754578, "learning_rate": 1.73044467723701e-05, "loss": 0.7058, "step": 4428 }, { "epoch": 0.6310914790538615, "grad_norm": 1.422991282115767, "learning_rate": 1.7302747987745345e-05, "loss": 0.6433, "step": 4429 }, { "epoch": 0.6312339697919636, "grad_norm": 1.499043671191213, "learning_rate": 1.730104875142919e-05, "loss": 0.6759, "step": 4430 }, { "epoch": 0.6313764605300656, "grad_norm": 1.325526829168655, "learning_rate": 1.7299349063526732e-05, "loss": 0.675, "step": 4431 }, { "epoch": 0.6315189512681676, "grad_norm": 1.5155142922576523, "learning_rate": 1.729764892414311e-05, "loss": 0.756, "step": 4432 }, { "epoch": 0.6316614420062696, "grad_norm": 1.435139300414388, "learning_rate": 1.729594833338347e-05, "loss": 0.688, "step": 4433 }, { "epoch": 0.6318039327443716, "grad_norm": 1.2546858677674655, "learning_rate": 1.7294247291353004e-05, "loss": 0.7021, "step": 4434 }, { "epoch": 0.6319464234824737, "grad_norm": 1.4965712869409022, "learning_rate": 1.7292545798156924e-05, "loss": 0.7165, "step": 4435 }, { "epoch": 0.6320889142205757, "grad_norm": 1.3680332083788904, "learning_rate": 1.7290843853900475e-05, "loss": 0.6769, "step": 4436 }, { "epoch": 0.6322314049586777, "grad_norm": 1.4307483957554732, "learning_rate": 1.728914145868892e-05, "loss": 0.6893, "step": 4437 }, { "epoch": 0.6323738956967797, "grad_norm": 1.474426367016686, "learning_rate": 1.7287438612627557e-05, "loss": 0.6369, "step": 4438 }, { "epoch": 0.6325163864348817, "grad_norm": 1.6442160944049113, "learning_rate": 1.728573531582171e-05, "loss": 0.7328, "step": 4439 }, { "epoch": 0.6326588771729837, "grad_norm": 1.8737680413553908, "learning_rate": 1.7284031568376744e-05, "loss": 0.7651, "step": 4440 }, { "epoch": 0.6328013679110858, "grad_norm": 1.3056849306476874, "learning_rate": 1.728232737039802e-05, "loss": 0.6861, "step": 4441 }, { "epoch": 0.6329438586491878, "grad_norm": 1.2688422715949315, "learning_rate": 1.7280622721990957e-05, "loss": 0.5863, "step": 4442 }, { "epoch": 0.6330863493872898, "grad_norm": 1.5347330692721464, "learning_rate": 1.7278917623260996e-05, "loss": 0.6346, "step": 4443 }, { "epoch": 0.6332288401253918, "grad_norm": 1.4952379268548135, "learning_rate": 1.7277212074313593e-05, "loss": 0.6063, "step": 4444 }, { "epoch": 0.6333713308634938, "grad_norm": 1.4025744130196252, "learning_rate": 1.727550607525424e-05, "loss": 0.6465, "step": 4445 }, { "epoch": 0.6335138216015959, "grad_norm": 1.4002412950255212, "learning_rate": 1.727379962618846e-05, "loss": 0.7272, "step": 4446 }, { "epoch": 0.6336563123396979, "grad_norm": 1.4000112363494033, "learning_rate": 1.7272092727221802e-05, "loss": 0.7654, "step": 4447 }, { "epoch": 0.6337988030777999, "grad_norm": 1.3468753602493038, "learning_rate": 1.7270385378459842e-05, "loss": 0.6148, "step": 4448 }, { "epoch": 0.6339412938159019, "grad_norm": 1.4782517639264228, "learning_rate": 1.726867758000818e-05, "loss": 0.6701, "step": 4449 }, { "epoch": 0.6340837845540039, "grad_norm": 1.290916041552439, "learning_rate": 1.7266969331972444e-05, "loss": 0.6374, "step": 4450 }, { "epoch": 0.6342262752921061, "grad_norm": 1.5936808750365443, "learning_rate": 1.7265260634458302e-05, "loss": 0.6435, "step": 4451 }, { "epoch": 0.6343687660302081, "grad_norm": 1.4835242904940034, "learning_rate": 1.7263551487571434e-05, "loss": 0.7064, "step": 4452 }, { "epoch": 0.6345112567683101, "grad_norm": 1.435410419960175, "learning_rate": 1.7261841891417555e-05, "loss": 0.7129, "step": 4453 }, { "epoch": 0.6346537475064121, "grad_norm": 1.324732125304582, "learning_rate": 1.7260131846102416e-05, "loss": 0.6857, "step": 4454 }, { "epoch": 0.6347962382445141, "grad_norm": 1.3973276437871494, "learning_rate": 1.7258421351731774e-05, "loss": 0.6692, "step": 4455 }, { "epoch": 0.6349387289826162, "grad_norm": 1.416182821179824, "learning_rate": 1.7256710408411434e-05, "loss": 0.6486, "step": 4456 }, { "epoch": 0.6350812197207182, "grad_norm": 1.4980980594883382, "learning_rate": 1.7254999016247224e-05, "loss": 0.6626, "step": 4457 }, { "epoch": 0.6352237104588202, "grad_norm": 1.4547575489305296, "learning_rate": 1.725328717534499e-05, "loss": 0.67, "step": 4458 }, { "epoch": 0.6353662011969222, "grad_norm": 1.4130567241534433, "learning_rate": 1.7251574885810622e-05, "loss": 0.7263, "step": 4459 }, { "epoch": 0.6355086919350242, "grad_norm": 1.4118186392222494, "learning_rate": 1.724986214775002e-05, "loss": 0.6793, "step": 4460 }, { "epoch": 0.6356511826731263, "grad_norm": 1.348924183557145, "learning_rate": 1.7248148961269126e-05, "loss": 0.6374, "step": 4461 }, { "epoch": 0.6357936734112283, "grad_norm": 1.3286592619637565, "learning_rate": 1.724643532647391e-05, "loss": 0.5795, "step": 4462 }, { "epoch": 0.6359361641493303, "grad_norm": 1.471901801201864, "learning_rate": 1.724472124347035e-05, "loss": 0.826, "step": 4463 }, { "epoch": 0.6360786548874323, "grad_norm": 1.9733217980478264, "learning_rate": 1.7243006712364477e-05, "loss": 0.6697, "step": 4464 }, { "epoch": 0.6362211456255343, "grad_norm": 1.2948577201776634, "learning_rate": 1.7241291733262334e-05, "loss": 0.6541, "step": 4465 }, { "epoch": 0.6363636363636364, "grad_norm": 1.4446705936737334, "learning_rate": 1.7239576306269998e-05, "loss": 0.6769, "step": 4466 }, { "epoch": 0.6365061271017384, "grad_norm": 1.4148209611382883, "learning_rate": 1.7237860431493573e-05, "loss": 0.6986, "step": 4467 }, { "epoch": 0.6366486178398404, "grad_norm": 1.3299192563698348, "learning_rate": 1.7236144109039184e-05, "loss": 0.7198, "step": 4468 }, { "epoch": 0.6367911085779424, "grad_norm": 1.3166273022068262, "learning_rate": 1.7234427339012997e-05, "loss": 0.6336, "step": 4469 }, { "epoch": 0.6369335993160444, "grad_norm": 1.7998862076917501, "learning_rate": 1.72327101215212e-05, "loss": 0.6706, "step": 4470 }, { "epoch": 0.6370760900541464, "grad_norm": 1.5105184815158874, "learning_rate": 1.7230992456669993e-05, "loss": 0.7451, "step": 4471 }, { "epoch": 0.6372185807922485, "grad_norm": 1.7840160081261993, "learning_rate": 1.722927434456563e-05, "loss": 0.7116, "step": 4472 }, { "epoch": 0.6373610715303505, "grad_norm": 1.3687847054491762, "learning_rate": 1.7227555785314377e-05, "loss": 0.5729, "step": 4473 }, { "epoch": 0.6375035622684525, "grad_norm": 1.5443802176019774, "learning_rate": 1.722583677902253e-05, "loss": 0.7013, "step": 4474 }, { "epoch": 0.6376460530065545, "grad_norm": 1.2341297901684183, "learning_rate": 1.722411732579641e-05, "loss": 0.6632, "step": 4475 }, { "epoch": 0.6377885437446565, "grad_norm": 1.3708895184908263, "learning_rate": 1.7222397425742373e-05, "loss": 0.6904, "step": 4476 }, { "epoch": 0.6379310344827587, "grad_norm": 1.3045437502851476, "learning_rate": 1.72206770789668e-05, "loss": 0.6727, "step": 4477 }, { "epoch": 0.6380735252208607, "grad_norm": 1.4614527976985343, "learning_rate": 1.7218956285576096e-05, "loss": 0.6268, "step": 4478 }, { "epoch": 0.6382160159589627, "grad_norm": 1.5099784979651336, "learning_rate": 1.72172350456767e-05, "loss": 0.81, "step": 4479 }, { "epoch": 0.6383585066970647, "grad_norm": 1.4644186851372616, "learning_rate": 1.7215513359375063e-05, "loss": 0.6411, "step": 4480 }, { "epoch": 0.6385009974351668, "grad_norm": 1.262360033005731, "learning_rate": 1.721379122677769e-05, "loss": 0.6272, "step": 4481 }, { "epoch": 0.6386434881732688, "grad_norm": 1.3405745025615925, "learning_rate": 1.7212068647991087e-05, "loss": 0.6628, "step": 4482 }, { "epoch": 0.6387859789113708, "grad_norm": 1.2404804848654922, "learning_rate": 1.7210345623121807e-05, "loss": 0.6402, "step": 4483 }, { "epoch": 0.6389284696494728, "grad_norm": 1.4394971682038227, "learning_rate": 1.720862215227642e-05, "loss": 0.5975, "step": 4484 }, { "epoch": 0.6390709603875748, "grad_norm": 1.2781719229780182, "learning_rate": 1.7206898235561524e-05, "loss": 0.6972, "step": 4485 }, { "epoch": 0.6392134511256768, "grad_norm": 1.456637323421111, "learning_rate": 1.7205173873083753e-05, "loss": 0.7113, "step": 4486 }, { "epoch": 0.6393559418637789, "grad_norm": 1.3296516846493331, "learning_rate": 1.720344906494976e-05, "loss": 0.6686, "step": 4487 }, { "epoch": 0.6394984326018809, "grad_norm": 1.441427594936416, "learning_rate": 1.7201723811266227e-05, "loss": 0.6956, "step": 4488 }, { "epoch": 0.6396409233399829, "grad_norm": 1.414993436549734, "learning_rate": 1.7199998112139863e-05, "loss": 0.6579, "step": 4489 }, { "epoch": 0.6397834140780849, "grad_norm": 1.4177662671019422, "learning_rate": 1.7198271967677414e-05, "loss": 0.7552, "step": 4490 }, { "epoch": 0.6399259048161869, "grad_norm": 1.302468453811901, "learning_rate": 1.7196545377985637e-05, "loss": 0.6788, "step": 4491 }, { "epoch": 0.640068395554289, "grad_norm": 1.4644492768016044, "learning_rate": 1.7194818343171332e-05, "loss": 0.7175, "step": 4492 }, { "epoch": 0.640210886292391, "grad_norm": 1.4199357078698316, "learning_rate": 1.7193090863341315e-05, "loss": 0.6348, "step": 4493 }, { "epoch": 0.640353377030493, "grad_norm": 1.4896708605826583, "learning_rate": 1.719136293860244e-05, "loss": 0.6796, "step": 4494 }, { "epoch": 0.640495867768595, "grad_norm": 1.4527318896969803, "learning_rate": 1.7189634569061574e-05, "loss": 0.6858, "step": 4495 }, { "epoch": 0.640638358506697, "grad_norm": 1.418779797754465, "learning_rate": 1.7187905754825634e-05, "loss": 0.6738, "step": 4496 }, { "epoch": 0.6407808492447991, "grad_norm": 1.421867831433593, "learning_rate": 1.7186176496001538e-05, "loss": 0.6909, "step": 4497 }, { "epoch": 0.6409233399829011, "grad_norm": 1.363155378576041, "learning_rate": 1.718444679269625e-05, "loss": 0.7244, "step": 4498 }, { "epoch": 0.6410658307210031, "grad_norm": 1.565295176609698, "learning_rate": 1.7182716645016763e-05, "loss": 0.7489, "step": 4499 }, { "epoch": 0.6412083214591051, "grad_norm": 1.276715999708452, "learning_rate": 1.7180986053070075e-05, "loss": 0.5849, "step": 4500 }, { "epoch": 0.6413508121972071, "grad_norm": 1.4416898850189614, "learning_rate": 1.717925501696324e-05, "loss": 0.7631, "step": 4501 }, { "epoch": 0.6414933029353092, "grad_norm": 1.4392759245561288, "learning_rate": 1.717752353680332e-05, "loss": 0.6867, "step": 4502 }, { "epoch": 0.6416357936734113, "grad_norm": 1.4056099748973732, "learning_rate": 1.7175791612697418e-05, "loss": 0.7062, "step": 4503 }, { "epoch": 0.6417782844115133, "grad_norm": 1.4506781312393533, "learning_rate": 1.7174059244752647e-05, "loss": 0.7229, "step": 4504 }, { "epoch": 0.6419207751496153, "grad_norm": 1.3361106874194113, "learning_rate": 1.7172326433076168e-05, "loss": 0.6367, "step": 4505 }, { "epoch": 0.6420632658877173, "grad_norm": 1.3227446334885518, "learning_rate": 1.7170593177775155e-05, "loss": 0.6196, "step": 4506 }, { "epoch": 0.6422057566258194, "grad_norm": 1.3340675870442609, "learning_rate": 1.7168859478956808e-05, "loss": 0.645, "step": 4507 }, { "epoch": 0.6423482473639214, "grad_norm": 1.3741480653121902, "learning_rate": 1.716712533672837e-05, "loss": 0.645, "step": 4508 }, { "epoch": 0.6424907381020234, "grad_norm": 1.3147978913383749, "learning_rate": 1.7165390751197094e-05, "loss": 0.6956, "step": 4509 }, { "epoch": 0.6426332288401254, "grad_norm": 1.4732735204688114, "learning_rate": 1.7163655722470274e-05, "loss": 0.6045, "step": 4510 }, { "epoch": 0.6427757195782274, "grad_norm": 1.3691965122717982, "learning_rate": 1.716192025065522e-05, "loss": 0.6717, "step": 4511 }, { "epoch": 0.6429182103163295, "grad_norm": 1.3869962893525918, "learning_rate": 1.716018433585928e-05, "loss": 0.6734, "step": 4512 }, { "epoch": 0.6430607010544315, "grad_norm": 1.2751943593813169, "learning_rate": 1.7158447978189823e-05, "loss": 0.5541, "step": 4513 }, { "epoch": 0.6432031917925335, "grad_norm": 1.3902089324322466, "learning_rate": 1.7156711177754243e-05, "loss": 0.6184, "step": 4514 }, { "epoch": 0.6433456825306355, "grad_norm": 1.4345330908689136, "learning_rate": 1.7154973934659963e-05, "loss": 0.7677, "step": 4515 }, { "epoch": 0.6434881732687375, "grad_norm": 1.747963025849475, "learning_rate": 1.7153236249014448e-05, "loss": 0.6149, "step": 4516 }, { "epoch": 0.6436306640068395, "grad_norm": 1.4820194045916095, "learning_rate": 1.7151498120925166e-05, "loss": 0.7177, "step": 4517 }, { "epoch": 0.6437731547449416, "grad_norm": 1.4681396718723265, "learning_rate": 1.714975955049963e-05, "loss": 0.6233, "step": 4518 }, { "epoch": 0.6439156454830436, "grad_norm": 1.3949282273307178, "learning_rate": 1.7148020537845366e-05, "loss": 0.763, "step": 4519 }, { "epoch": 0.6440581362211456, "grad_norm": 1.427802533871147, "learning_rate": 1.7146281083069944e-05, "loss": 0.7318, "step": 4520 }, { "epoch": 0.6442006269592476, "grad_norm": 1.3644594012750173, "learning_rate": 1.7144541186280953e-05, "loss": 0.6571, "step": 4521 }, { "epoch": 0.6443431176973496, "grad_norm": 1.227191974549034, "learning_rate": 1.7142800847586007e-05, "loss": 0.7019, "step": 4522 }, { "epoch": 0.6444856084354517, "grad_norm": 1.180735971730343, "learning_rate": 1.7141060067092753e-05, "loss": 0.5152, "step": 4523 }, { "epoch": 0.6446280991735537, "grad_norm": 1.205623707416075, "learning_rate": 1.7139318844908856e-05, "loss": 0.6757, "step": 4524 }, { "epoch": 0.6447705899116557, "grad_norm": 1.3704073769475669, "learning_rate": 1.713757718114202e-05, "loss": 0.7034, "step": 4525 }, { "epoch": 0.6449130806497577, "grad_norm": 1.4255485356198643, "learning_rate": 1.713583507589997e-05, "loss": 0.7622, "step": 4526 }, { "epoch": 0.6450555713878597, "grad_norm": 1.4439581392162304, "learning_rate": 1.713409252929046e-05, "loss": 0.6152, "step": 4527 }, { "epoch": 0.6451980621259618, "grad_norm": 1.3095018411156543, "learning_rate": 1.7132349541421267e-05, "loss": 0.6454, "step": 4528 }, { "epoch": 0.6453405528640639, "grad_norm": 1.460553008439064, "learning_rate": 1.71306061124002e-05, "loss": 0.6319, "step": 4529 }, { "epoch": 0.6454830436021659, "grad_norm": 1.5109301443389866, "learning_rate": 1.7128862242335093e-05, "loss": 0.6872, "step": 4530 }, { "epoch": 0.6456255343402679, "grad_norm": 1.3339571453976449, "learning_rate": 1.712711793133381e-05, "loss": 0.6061, "step": 4531 }, { "epoch": 0.64576802507837, "grad_norm": 1.2938530566696596, "learning_rate": 1.7125373179504242e-05, "loss": 0.6457, "step": 4532 }, { "epoch": 0.645910515816472, "grad_norm": 1.2774802389814217, "learning_rate": 1.71236279869543e-05, "loss": 0.7206, "step": 4533 }, { "epoch": 0.646053006554574, "grad_norm": 1.3988555904285898, "learning_rate": 1.712188235379194e-05, "loss": 0.6434, "step": 4534 }, { "epoch": 0.646195497292676, "grad_norm": 1.6042189122986048, "learning_rate": 1.712013628012512e-05, "loss": 0.617, "step": 4535 }, { "epoch": 0.646337988030778, "grad_norm": 1.3573152344575337, "learning_rate": 1.7118389766061844e-05, "loss": 0.6455, "step": 4536 }, { "epoch": 0.64648047876888, "grad_norm": 1.372631564311044, "learning_rate": 1.711664281171014e-05, "loss": 0.6883, "step": 4537 }, { "epoch": 0.6466229695069821, "grad_norm": 1.4393347403540941, "learning_rate": 1.7114895417178056e-05, "loss": 0.6982, "step": 4538 }, { "epoch": 0.6467654602450841, "grad_norm": 1.3174735718630681, "learning_rate": 1.7113147582573678e-05, "loss": 0.6743, "step": 4539 }, { "epoch": 0.6469079509831861, "grad_norm": 1.7504959681241736, "learning_rate": 1.711139930800511e-05, "loss": 0.5472, "step": 4540 }, { "epoch": 0.6470504417212881, "grad_norm": 1.272309699910292, "learning_rate": 1.7109650593580486e-05, "loss": 0.6794, "step": 4541 }, { "epoch": 0.6471929324593901, "grad_norm": 1.312511369154274, "learning_rate": 1.7107901439407976e-05, "loss": 0.6236, "step": 4542 }, { "epoch": 0.6473354231974922, "grad_norm": 3.165011562762442, "learning_rate": 1.7106151845595754e-05, "loss": 0.6677, "step": 4543 }, { "epoch": 0.6474779139355942, "grad_norm": 1.4710911903185329, "learning_rate": 1.710440181225205e-05, "loss": 0.5922, "step": 4544 }, { "epoch": 0.6476204046736962, "grad_norm": 1.4265232981675098, "learning_rate": 1.71026513394851e-05, "loss": 0.6321, "step": 4545 }, { "epoch": 0.6477628954117982, "grad_norm": 1.6951003669484024, "learning_rate": 1.7100900427403177e-05, "loss": 0.7294, "step": 4546 }, { "epoch": 0.6479053861499002, "grad_norm": 1.5707096035879904, "learning_rate": 1.709914907611458e-05, "loss": 0.7373, "step": 4547 }, { "epoch": 0.6480478768880022, "grad_norm": 1.3153973431941026, "learning_rate": 1.7097397285727634e-05, "loss": 0.7258, "step": 4548 }, { "epoch": 0.6481903676261043, "grad_norm": 1.4440390226013085, "learning_rate": 1.7095645056350685e-05, "loss": 0.6265, "step": 4549 }, { "epoch": 0.6483328583642063, "grad_norm": 1.4187509395669227, "learning_rate": 1.7093892388092123e-05, "loss": 0.7195, "step": 4550 }, { "epoch": 0.6484753491023083, "grad_norm": 1.3309098575563534, "learning_rate": 1.709213928106035e-05, "loss": 0.7386, "step": 4551 }, { "epoch": 0.6486178398404103, "grad_norm": 1.310467104519707, "learning_rate": 1.7090385735363793e-05, "loss": 0.6352, "step": 4552 }, { "epoch": 0.6487603305785123, "grad_norm": 1.4208241489195221, "learning_rate": 1.7088631751110924e-05, "loss": 0.7318, "step": 4553 }, { "epoch": 0.6489028213166145, "grad_norm": 1.293844109836132, "learning_rate": 1.708687732841022e-05, "loss": 0.6846, "step": 4554 }, { "epoch": 0.6490453120547165, "grad_norm": 1.4819077771876414, "learning_rate": 1.7085122467370202e-05, "loss": 0.6701, "step": 4555 }, { "epoch": 0.6491878027928185, "grad_norm": 1.3380386476262989, "learning_rate": 1.7083367168099414e-05, "loss": 0.7672, "step": 4556 }, { "epoch": 0.6493302935309205, "grad_norm": 1.3742726682046702, "learning_rate": 1.708161143070642e-05, "loss": 0.6336, "step": 4557 }, { "epoch": 0.6494727842690226, "grad_norm": 1.3846392178751752, "learning_rate": 1.707985525529982e-05, "loss": 0.6336, "step": 4558 }, { "epoch": 0.6496152750071246, "grad_norm": 1.3824162907964934, "learning_rate": 1.7078098641988236e-05, "loss": 0.6289, "step": 4559 }, { "epoch": 0.6497577657452266, "grad_norm": 1.582263708855762, "learning_rate": 1.7076341590880318e-05, "loss": 0.6418, "step": 4560 }, { "epoch": 0.6499002564833286, "grad_norm": 1.3975512359672868, "learning_rate": 1.7074584102084747e-05, "loss": 0.6951, "step": 4561 }, { "epoch": 0.6500427472214306, "grad_norm": 1.4122293493897087, "learning_rate": 1.7072826175710224e-05, "loss": 0.7203, "step": 4562 }, { "epoch": 0.6501852379595326, "grad_norm": 1.459057863682554, "learning_rate": 1.7071067811865477e-05, "loss": 0.7013, "step": 4563 }, { "epoch": 0.6503277286976347, "grad_norm": 1.375092713541526, "learning_rate": 1.7069309010659273e-05, "loss": 0.686, "step": 4564 }, { "epoch": 0.6504702194357367, "grad_norm": 1.514760463265564, "learning_rate": 1.7067549772200395e-05, "loss": 0.6663, "step": 4565 }, { "epoch": 0.6506127101738387, "grad_norm": 1.336656075614309, "learning_rate": 1.706579009659765e-05, "loss": 0.6507, "step": 4566 }, { "epoch": 0.6507552009119407, "grad_norm": 1.36981833545864, "learning_rate": 1.706402998395989e-05, "loss": 0.6262, "step": 4567 }, { "epoch": 0.6508976916500427, "grad_norm": 1.2980949059347493, "learning_rate": 1.7062269434395968e-05, "loss": 0.6883, "step": 4568 }, { "epoch": 0.6510401823881448, "grad_norm": 1.3457140711671745, "learning_rate": 1.706050844801479e-05, "loss": 0.7066, "step": 4569 }, { "epoch": 0.6511826731262468, "grad_norm": 1.4370239836386436, "learning_rate": 1.705874702492527e-05, "loss": 0.7272, "step": 4570 }, { "epoch": 0.6513251638643488, "grad_norm": 1.3939405174263821, "learning_rate": 1.7056985165236357e-05, "loss": 0.6251, "step": 4571 }, { "epoch": 0.6514676546024508, "grad_norm": 1.494212427166024, "learning_rate": 1.7055222869057026e-05, "loss": 0.5924, "step": 4572 }, { "epoch": 0.6516101453405528, "grad_norm": 1.5646258412396028, "learning_rate": 1.7053460136496282e-05, "loss": 0.6218, "step": 4573 }, { "epoch": 0.6517526360786549, "grad_norm": 1.4002089627003995, "learning_rate": 1.705169696766315e-05, "loss": 0.7559, "step": 4574 }, { "epoch": 0.6518951268167569, "grad_norm": 1.4056577643140307, "learning_rate": 1.704993336266669e-05, "loss": 0.7223, "step": 4575 }, { "epoch": 0.6520376175548589, "grad_norm": 1.2982915280457177, "learning_rate": 1.704816932161598e-05, "loss": 0.6949, "step": 4576 }, { "epoch": 0.6521801082929609, "grad_norm": 1.3658652661868036, "learning_rate": 1.704640484462013e-05, "loss": 0.6481, "step": 4577 }, { "epoch": 0.6523225990310629, "grad_norm": 1.3213182911951817, "learning_rate": 1.7044639931788286e-05, "loss": 0.7331, "step": 4578 }, { "epoch": 0.652465089769165, "grad_norm": 1.442174037656731, "learning_rate": 1.7042874583229602e-05, "loss": 0.6674, "step": 4579 }, { "epoch": 0.6526075805072671, "grad_norm": 1.4855514749973537, "learning_rate": 1.7041108799053275e-05, "loss": 0.6668, "step": 4580 }, { "epoch": 0.6527500712453691, "grad_norm": 1.8130532239199055, "learning_rate": 1.7039342579368513e-05, "loss": 0.6798, "step": 4581 }, { "epoch": 0.6528925619834711, "grad_norm": 1.4821291145511066, "learning_rate": 1.703757592428457e-05, "loss": 0.712, "step": 4582 }, { "epoch": 0.6530350527215731, "grad_norm": 1.3483289985075022, "learning_rate": 1.7035808833910715e-05, "loss": 0.6341, "step": 4583 }, { "epoch": 0.6531775434596752, "grad_norm": 1.2646267837657612, "learning_rate": 1.703404130835625e-05, "loss": 0.5921, "step": 4584 }, { "epoch": 0.6533200341977772, "grad_norm": 1.5504145978608403, "learning_rate": 1.7032273347730493e-05, "loss": 0.7369, "step": 4585 }, { "epoch": 0.6534625249358792, "grad_norm": 1.3946398214375932, "learning_rate": 1.7030504952142804e-05, "loss": 0.7313, "step": 4586 }, { "epoch": 0.6536050156739812, "grad_norm": 1.364960907331122, "learning_rate": 1.7028736121702555e-05, "loss": 0.681, "step": 4587 }, { "epoch": 0.6537475064120832, "grad_norm": 1.385916802593418, "learning_rate": 1.702696685651916e-05, "loss": 0.6305, "step": 4588 }, { "epoch": 0.6538899971501853, "grad_norm": 1.6270673800059972, "learning_rate": 1.7025197156702043e-05, "loss": 0.7063, "step": 4589 }, { "epoch": 0.6540324878882873, "grad_norm": 1.2910006002162335, "learning_rate": 1.702342702236067e-05, "loss": 0.5698, "step": 4590 }, { "epoch": 0.6541749786263893, "grad_norm": 1.6484683785995358, "learning_rate": 1.7021656453604524e-05, "loss": 0.7172, "step": 4591 }, { "epoch": 0.6543174693644913, "grad_norm": 1.3704227853478665, "learning_rate": 1.7019885450543125e-05, "loss": 0.6622, "step": 4592 }, { "epoch": 0.6544599601025933, "grad_norm": 1.4167141179865743, "learning_rate": 1.701811401328601e-05, "loss": 0.6925, "step": 4593 }, { "epoch": 0.6546024508406953, "grad_norm": 1.4066727568733906, "learning_rate": 1.7016342141942742e-05, "loss": 0.6887, "step": 4594 }, { "epoch": 0.6547449415787974, "grad_norm": 1.378396915922988, "learning_rate": 1.701456983662292e-05, "loss": 0.5957, "step": 4595 }, { "epoch": 0.6548874323168994, "grad_norm": 1.5058570097201611, "learning_rate": 1.7012797097436164e-05, "loss": 0.7184, "step": 4596 }, { "epoch": 0.6550299230550014, "grad_norm": 1.3317792805953863, "learning_rate": 1.7011023924492125e-05, "loss": 0.6835, "step": 4597 }, { "epoch": 0.6551724137931034, "grad_norm": 1.4168148678404067, "learning_rate": 1.7009250317900474e-05, "loss": 0.643, "step": 4598 }, { "epoch": 0.6553149045312054, "grad_norm": 1.3598178833751204, "learning_rate": 1.7007476277770913e-05, "loss": 0.5811, "step": 4599 }, { "epoch": 0.6554573952693075, "grad_norm": 1.6027147514870828, "learning_rate": 1.700570180421317e-05, "loss": 0.7304, "step": 4600 }, { "epoch": 0.6555998860074095, "grad_norm": 1.4211175473452438, "learning_rate": 1.7003926897337003e-05, "loss": 0.6812, "step": 4601 }, { "epoch": 0.6557423767455115, "grad_norm": 1.3807695678850518, "learning_rate": 1.7002151557252192e-05, "loss": 0.6087, "step": 4602 }, { "epoch": 0.6558848674836135, "grad_norm": 1.4046196774967985, "learning_rate": 1.7000375784068545e-05, "loss": 0.5922, "step": 4603 }, { "epoch": 0.6560273582217155, "grad_norm": 1.4511736006524327, "learning_rate": 1.6998599577895896e-05, "loss": 0.6484, "step": 4604 }, { "epoch": 0.6561698489598176, "grad_norm": 1.4529683995383647, "learning_rate": 1.6996822938844112e-05, "loss": 0.6885, "step": 4605 }, { "epoch": 0.6563123396979197, "grad_norm": 1.4246551616870125, "learning_rate": 1.699504586702308e-05, "loss": 0.7022, "step": 4606 }, { "epoch": 0.6564548304360217, "grad_norm": 1.4400137835321578, "learning_rate": 1.699326836254272e-05, "loss": 0.6973, "step": 4607 }, { "epoch": 0.6565973211741237, "grad_norm": 1.2984175373085725, "learning_rate": 1.699149042551296e-05, "loss": 0.6271, "step": 4608 }, { "epoch": 0.6567398119122257, "grad_norm": 2.399735897262222, "learning_rate": 1.6989712056043786e-05, "loss": 0.6327, "step": 4609 }, { "epoch": 0.6568823026503278, "grad_norm": 1.5218745435380854, "learning_rate": 1.698793325424519e-05, "loss": 0.6968, "step": 4610 }, { "epoch": 0.6570247933884298, "grad_norm": 1.3908324766031128, "learning_rate": 1.6986154020227192e-05, "loss": 0.6401, "step": 4611 }, { "epoch": 0.6571672841265318, "grad_norm": 1.3734939298192894, "learning_rate": 1.698437435409984e-05, "loss": 0.6757, "step": 4612 }, { "epoch": 0.6573097748646338, "grad_norm": 1.2649657541613963, "learning_rate": 1.6982594255973214e-05, "loss": 0.6183, "step": 4613 }, { "epoch": 0.6574522656027358, "grad_norm": 1.7265079248763358, "learning_rate": 1.6980813725957415e-05, "loss": 0.6055, "step": 4614 }, { "epoch": 0.6575947563408379, "grad_norm": 1.237557637151426, "learning_rate": 1.6979032764162573e-05, "loss": 0.5943, "step": 4615 }, { "epoch": 0.6577372470789399, "grad_norm": 1.3103611167634788, "learning_rate": 1.6977251370698847e-05, "loss": 0.6329, "step": 4616 }, { "epoch": 0.6578797378170419, "grad_norm": 1.6500282167984366, "learning_rate": 1.6975469545676418e-05, "loss": 0.618, "step": 4617 }, { "epoch": 0.6580222285551439, "grad_norm": 1.4749026939434506, "learning_rate": 1.6973687289205496e-05, "loss": 0.7098, "step": 4618 }, { "epoch": 0.6581647192932459, "grad_norm": 1.3281141014545006, "learning_rate": 1.697190460139632e-05, "loss": 0.7412, "step": 4619 }, { "epoch": 0.658307210031348, "grad_norm": 1.5635905555771024, "learning_rate": 1.6970121482359147e-05, "loss": 0.6897, "step": 4620 }, { "epoch": 0.65844970076945, "grad_norm": 1.4315838486292511, "learning_rate": 1.6968337932204274e-05, "loss": 0.693, "step": 4621 }, { "epoch": 0.658592191507552, "grad_norm": 1.2906725844044022, "learning_rate": 1.6966553951042013e-05, "loss": 0.6341, "step": 4622 }, { "epoch": 0.658734682245654, "grad_norm": 1.3293184724839462, "learning_rate": 1.696476953898271e-05, "loss": 0.7097, "step": 4623 }, { "epoch": 0.658877172983756, "grad_norm": 1.4919734585889501, "learning_rate": 1.6962984696136734e-05, "loss": 0.7863, "step": 4624 }, { "epoch": 0.659019663721858, "grad_norm": 1.3251708192259066, "learning_rate": 1.6961199422614482e-05, "loss": 0.6165, "step": 4625 }, { "epoch": 0.6591621544599601, "grad_norm": 1.4819340458062262, "learning_rate": 1.695941371852637e-05, "loss": 0.7382, "step": 4626 }, { "epoch": 0.6593046451980621, "grad_norm": 1.3312482154150558, "learning_rate": 1.6957627583982863e-05, "loss": 0.6077, "step": 4627 }, { "epoch": 0.6594471359361641, "grad_norm": 1.4830279902541423, "learning_rate": 1.6955841019094427e-05, "loss": 0.6446, "step": 4628 }, { "epoch": 0.6595896266742661, "grad_norm": 1.3444020181994532, "learning_rate": 1.6954054023971566e-05, "loss": 0.6777, "step": 4629 }, { "epoch": 0.6597321174123681, "grad_norm": 1.3733153011595995, "learning_rate": 1.6952266598724806e-05, "loss": 0.7287, "step": 4630 }, { "epoch": 0.6598746081504702, "grad_norm": 1.5408573375087788, "learning_rate": 1.6950478743464714e-05, "loss": 0.6368, "step": 4631 }, { "epoch": 0.6600170988885723, "grad_norm": 1.4083576826890296, "learning_rate": 1.6948690458301866e-05, "loss": 0.7087, "step": 4632 }, { "epoch": 0.6601595896266743, "grad_norm": 2.587125473858425, "learning_rate": 1.6946901743346866e-05, "loss": 0.6296, "step": 4633 }, { "epoch": 0.6603020803647763, "grad_norm": 1.520019956543214, "learning_rate": 1.694511259871036e-05, "loss": 0.6954, "step": 4634 }, { "epoch": 0.6604445711028784, "grad_norm": 1.3549388835068705, "learning_rate": 1.694332302450301e-05, "loss": 0.6835, "step": 4635 }, { "epoch": 0.6605870618409804, "grad_norm": 1.2705565856261332, "learning_rate": 1.69415330208355e-05, "loss": 0.651, "step": 4636 }, { "epoch": 0.6607295525790824, "grad_norm": 1.3633415598878114, "learning_rate": 1.6939742587818546e-05, "loss": 0.7235, "step": 4637 }, { "epoch": 0.6608720433171844, "grad_norm": 1.252348946409836, "learning_rate": 1.6937951725562892e-05, "loss": 0.6601, "step": 4638 }, { "epoch": 0.6610145340552864, "grad_norm": 1.5067760605421658, "learning_rate": 1.6936160434179307e-05, "loss": 0.6766, "step": 4639 }, { "epoch": 0.6611570247933884, "grad_norm": 1.3660195290714228, "learning_rate": 1.6934368713778585e-05, "loss": 0.5974, "step": 4640 }, { "epoch": 0.6612995155314905, "grad_norm": 1.3918423967591684, "learning_rate": 1.6932576564471554e-05, "loss": 0.6284, "step": 4641 }, { "epoch": 0.6614420062695925, "grad_norm": 1.3385868997950612, "learning_rate": 1.6930783986369055e-05, "loss": 0.629, "step": 4642 }, { "epoch": 0.6615844970076945, "grad_norm": 1.8677820959687503, "learning_rate": 1.6928990979581965e-05, "loss": 0.6148, "step": 4643 }, { "epoch": 0.6617269877457965, "grad_norm": 1.2926266436852654, "learning_rate": 1.6927197544221187e-05, "loss": 0.6308, "step": 4644 }, { "epoch": 0.6618694784838985, "grad_norm": 1.30144722301389, "learning_rate": 1.6925403680397647e-05, "loss": 0.6393, "step": 4645 }, { "epoch": 0.6620119692220006, "grad_norm": 1.4824996223793907, "learning_rate": 1.6923609388222304e-05, "loss": 0.7143, "step": 4646 }, { "epoch": 0.6621544599601026, "grad_norm": 1.4031573172304082, "learning_rate": 1.6921814667806132e-05, "loss": 0.6932, "step": 4647 }, { "epoch": 0.6622969506982046, "grad_norm": 1.2808610950048473, "learning_rate": 1.6920019519260144e-05, "loss": 0.5886, "step": 4648 }, { "epoch": 0.6624394414363066, "grad_norm": 1.6039610444773245, "learning_rate": 1.6918223942695374e-05, "loss": 0.6711, "step": 4649 }, { "epoch": 0.6625819321744086, "grad_norm": 1.5274622844459582, "learning_rate": 1.6916427938222878e-05, "loss": 0.6041, "step": 4650 }, { "epoch": 0.6627244229125107, "grad_norm": 1.5721232774082936, "learning_rate": 1.6914631505953746e-05, "loss": 0.6682, "step": 4651 }, { "epoch": 0.6628669136506127, "grad_norm": 1.3044410602493692, "learning_rate": 1.691283464599909e-05, "loss": 0.7011, "step": 4652 }, { "epoch": 0.6630094043887147, "grad_norm": 1.3350512843047997, "learning_rate": 1.691103735847005e-05, "loss": 0.5913, "step": 4653 }, { "epoch": 0.6631518951268167, "grad_norm": 1.4436954355787752, "learning_rate": 1.69092396434778e-05, "loss": 0.7573, "step": 4654 }, { "epoch": 0.6632943858649187, "grad_norm": 1.607878859837937, "learning_rate": 1.690744150113352e-05, "loss": 0.6547, "step": 4655 }, { "epoch": 0.6634368766030208, "grad_norm": 1.3311285552118324, "learning_rate": 1.6905642931548432e-05, "loss": 0.6248, "step": 4656 }, { "epoch": 0.6635793673411228, "grad_norm": 1.3929365993975995, "learning_rate": 1.6903843934833794e-05, "loss": 0.6915, "step": 4657 }, { "epoch": 0.6637218580792249, "grad_norm": 1.4559169832541328, "learning_rate": 1.690204451110086e-05, "loss": 0.6382, "step": 4658 }, { "epoch": 0.6638643488173269, "grad_norm": 1.4281241358551815, "learning_rate": 1.6900244660460942e-05, "loss": 0.6958, "step": 4659 }, { "epoch": 0.6640068395554289, "grad_norm": 1.3782674860367035, "learning_rate": 1.6898444383025356e-05, "loss": 0.6606, "step": 4660 }, { "epoch": 0.664149330293531, "grad_norm": 1.41727609499786, "learning_rate": 1.6896643678905463e-05, "loss": 0.6844, "step": 4661 }, { "epoch": 0.664291821031633, "grad_norm": 1.2924201703514548, "learning_rate": 1.6894842548212627e-05, "loss": 0.6263, "step": 4662 }, { "epoch": 0.664434311769735, "grad_norm": 1.2853016524939156, "learning_rate": 1.6893040991058264e-05, "loss": 0.5843, "step": 4663 }, { "epoch": 0.664576802507837, "grad_norm": 1.3361527962028004, "learning_rate": 1.6891239007553798e-05, "loss": 0.661, "step": 4664 }, { "epoch": 0.664719293245939, "grad_norm": 1.3432606297962824, "learning_rate": 1.6889436597810687e-05, "loss": 0.5655, "step": 4665 }, { "epoch": 0.664861783984041, "grad_norm": 1.316346352248457, "learning_rate": 1.6887633761940415e-05, "loss": 0.6806, "step": 4666 }, { "epoch": 0.6650042747221431, "grad_norm": 1.3676012744450337, "learning_rate": 1.6885830500054495e-05, "loss": 0.6472, "step": 4667 }, { "epoch": 0.6651467654602451, "grad_norm": 1.4901554623412558, "learning_rate": 1.6884026812264455e-05, "loss": 0.7425, "step": 4668 }, { "epoch": 0.6652892561983471, "grad_norm": 1.3946617303515845, "learning_rate": 1.688222269868186e-05, "loss": 0.7157, "step": 4669 }, { "epoch": 0.6654317469364491, "grad_norm": 1.4933623783755183, "learning_rate": 1.6880418159418307e-05, "loss": 0.7824, "step": 4670 }, { "epoch": 0.6655742376745512, "grad_norm": 1.3665329948110982, "learning_rate": 1.6878613194585396e-05, "loss": 0.6696, "step": 4671 }, { "epoch": 0.6657167284126532, "grad_norm": 1.5666432252086484, "learning_rate": 1.687680780429478e-05, "loss": 0.6458, "step": 4672 }, { "epoch": 0.6658592191507552, "grad_norm": 1.4007383269978615, "learning_rate": 1.687500198865812e-05, "loss": 0.6232, "step": 4673 }, { "epoch": 0.6660017098888572, "grad_norm": 1.5340234877027321, "learning_rate": 1.6873195747787116e-05, "loss": 0.653, "step": 4674 }, { "epoch": 0.6661442006269592, "grad_norm": 1.4135078316414222, "learning_rate": 1.6871389081793478e-05, "loss": 0.6608, "step": 4675 }, { "epoch": 0.6662866913650612, "grad_norm": 1.2624878020604464, "learning_rate": 1.686958199078896e-05, "loss": 0.5488, "step": 4676 }, { "epoch": 0.6664291821031633, "grad_norm": 1.2536703928982575, "learning_rate": 1.6867774474885332e-05, "loss": 0.632, "step": 4677 }, { "epoch": 0.6665716728412653, "grad_norm": 1.399344674141871, "learning_rate": 1.6865966534194394e-05, "loss": 0.6998, "step": 4678 }, { "epoch": 0.6667141635793673, "grad_norm": 1.3860977417864713, "learning_rate": 1.6864158168827973e-05, "loss": 0.7414, "step": 4679 }, { "epoch": 0.6668566543174693, "grad_norm": 1.297400743473116, "learning_rate": 1.686234937889792e-05, "loss": 0.6385, "step": 4680 }, { "epoch": 0.6669991450555713, "grad_norm": 1.276954215734523, "learning_rate": 1.6860540164516108e-05, "loss": 0.6963, "step": 4681 }, { "epoch": 0.6671416357936734, "grad_norm": 1.398815332327808, "learning_rate": 1.6858730525794445e-05, "loss": 0.6414, "step": 4682 }, { "epoch": 0.6672841265317755, "grad_norm": 2.0032287510255844, "learning_rate": 1.685692046284486e-05, "loss": 0.6816, "step": 4683 }, { "epoch": 0.6674266172698775, "grad_norm": 1.3628550371185493, "learning_rate": 1.6855109975779308e-05, "loss": 0.6983, "step": 4684 }, { "epoch": 0.6675691080079795, "grad_norm": 1.3946496721934125, "learning_rate": 1.6853299064709777e-05, "loss": 0.6795, "step": 4685 }, { "epoch": 0.6677115987460815, "grad_norm": 1.4908640808503608, "learning_rate": 1.685148772974827e-05, "loss": 0.6647, "step": 4686 }, { "epoch": 0.6678540894841836, "grad_norm": 1.4798679329933486, "learning_rate": 1.6849675971006828e-05, "loss": 0.5971, "step": 4687 }, { "epoch": 0.6679965802222856, "grad_norm": 1.383780443856161, "learning_rate": 1.6847863788597507e-05, "loss": 0.6673, "step": 4688 }, { "epoch": 0.6681390709603876, "grad_norm": 1.5236343465928335, "learning_rate": 1.6846051182632396e-05, "loss": 0.6642, "step": 4689 }, { "epoch": 0.6682815616984896, "grad_norm": 1.5621735962305752, "learning_rate": 1.684423815322361e-05, "loss": 0.7014, "step": 4690 }, { "epoch": 0.6684240524365916, "grad_norm": 1.265889317980942, "learning_rate": 1.6842424700483287e-05, "loss": 0.637, "step": 4691 }, { "epoch": 0.6685665431746937, "grad_norm": 1.3847294421508871, "learning_rate": 1.6840610824523596e-05, "loss": 0.6314, "step": 4692 }, { "epoch": 0.6687090339127957, "grad_norm": 1.3569337814065814, "learning_rate": 1.6838796525456727e-05, "loss": 0.6781, "step": 4693 }, { "epoch": 0.6688515246508977, "grad_norm": 1.4464614239702573, "learning_rate": 1.68369818033949e-05, "loss": 0.6885, "step": 4694 }, { "epoch": 0.6689940153889997, "grad_norm": 1.3932954133175435, "learning_rate": 1.683516665845036e-05, "loss": 0.6585, "step": 4695 }, { "epoch": 0.6691365061271017, "grad_norm": 1.5532193296253927, "learning_rate": 1.6833351090735375e-05, "loss": 0.6563, "step": 4696 }, { "epoch": 0.6692789968652038, "grad_norm": 1.4350262608164932, "learning_rate": 1.6831535100362243e-05, "loss": 0.6473, "step": 4697 }, { "epoch": 0.6694214876033058, "grad_norm": 1.469786538226251, "learning_rate": 1.682971868744329e-05, "loss": 0.7776, "step": 4698 }, { "epoch": 0.6695639783414078, "grad_norm": 1.333949424816067, "learning_rate": 1.682790185209086e-05, "loss": 0.6403, "step": 4699 }, { "epoch": 0.6697064690795098, "grad_norm": 1.3908126019176408, "learning_rate": 1.6826084594417332e-05, "loss": 0.7017, "step": 4700 }, { "epoch": 0.6698489598176118, "grad_norm": 1.4130849180098006, "learning_rate": 1.6824266914535108e-05, "loss": 0.6474, "step": 4701 }, { "epoch": 0.6699914505557139, "grad_norm": 1.4818453487937535, "learning_rate": 1.6822448812556614e-05, "loss": 0.6895, "step": 4702 }, { "epoch": 0.6701339412938159, "grad_norm": 1.317469241130591, "learning_rate": 1.6820630288594305e-05, "loss": 0.6348, "step": 4703 }, { "epoch": 0.6702764320319179, "grad_norm": 1.3744712762841989, "learning_rate": 1.6818811342760656e-05, "loss": 0.7201, "step": 4704 }, { "epoch": 0.6704189227700199, "grad_norm": 1.581097520107455, "learning_rate": 1.6816991975168182e-05, "loss": 0.6896, "step": 4705 }, { "epoch": 0.6705614135081219, "grad_norm": 1.3901569035375863, "learning_rate": 1.681517218592941e-05, "loss": 0.6226, "step": 4706 }, { "epoch": 0.670703904246224, "grad_norm": 1.4286081537106916, "learning_rate": 1.6813351975156892e-05, "loss": 0.6928, "step": 4707 }, { "epoch": 0.670846394984326, "grad_norm": 1.3967475751380911, "learning_rate": 1.6811531342963218e-05, "loss": 0.6717, "step": 4708 }, { "epoch": 0.6709888857224281, "grad_norm": 1.5752333794262943, "learning_rate": 1.6809710289461004e-05, "loss": 0.6864, "step": 4709 }, { "epoch": 0.6711313764605301, "grad_norm": 1.3239220456483893, "learning_rate": 1.680788881476288e-05, "loss": 0.682, "step": 4710 }, { "epoch": 0.6712738671986321, "grad_norm": 1.4301742713453807, "learning_rate": 1.6806066918981507e-05, "loss": 0.6775, "step": 4711 }, { "epoch": 0.6714163579367342, "grad_norm": 1.3552807967674332, "learning_rate": 1.680424460222957e-05, "loss": 0.6847, "step": 4712 }, { "epoch": 0.6715588486748362, "grad_norm": 1.3901912580072573, "learning_rate": 1.6802421864619792e-05, "loss": 0.7164, "step": 4713 }, { "epoch": 0.6717013394129382, "grad_norm": 1.3624833202479303, "learning_rate": 1.6800598706264912e-05, "loss": 0.7206, "step": 4714 }, { "epoch": 0.6718438301510402, "grad_norm": 1.2942810266218974, "learning_rate": 1.6798775127277692e-05, "loss": 0.6902, "step": 4715 }, { "epoch": 0.6719863208891422, "grad_norm": 1.3440886529140077, "learning_rate": 1.679695112777093e-05, "loss": 0.6526, "step": 4716 }, { "epoch": 0.6721288116272442, "grad_norm": 1.4188109481430464, "learning_rate": 1.679512670785744e-05, "loss": 0.7134, "step": 4717 }, { "epoch": 0.6722713023653463, "grad_norm": 1.458741342046202, "learning_rate": 1.6793301867650065e-05, "loss": 0.6464, "step": 4718 }, { "epoch": 0.6724137931034483, "grad_norm": 1.4004514049953911, "learning_rate": 1.6791476607261682e-05, "loss": 0.6599, "step": 4719 }, { "epoch": 0.6725562838415503, "grad_norm": 1.4869787782628963, "learning_rate": 1.6789650926805178e-05, "loss": 0.6525, "step": 4720 }, { "epoch": 0.6726987745796523, "grad_norm": 1.3831189354884177, "learning_rate": 1.6787824826393483e-05, "loss": 0.6265, "step": 4721 }, { "epoch": 0.6728412653177543, "grad_norm": 1.3214238865316208, "learning_rate": 1.678599830613955e-05, "loss": 0.6148, "step": 4722 }, { "epoch": 0.6729837560558564, "grad_norm": 1.4219281005447155, "learning_rate": 1.678417136615634e-05, "loss": 0.6774, "step": 4723 }, { "epoch": 0.6731262467939584, "grad_norm": 1.3660004817491491, "learning_rate": 1.6782344006556862e-05, "loss": 0.6871, "step": 4724 }, { "epoch": 0.6732687375320604, "grad_norm": 1.2776711613198106, "learning_rate": 1.678051622745414e-05, "loss": 0.7121, "step": 4725 }, { "epoch": 0.6734112282701624, "grad_norm": 1.3160023951771638, "learning_rate": 1.677868802896123e-05, "loss": 0.6693, "step": 4726 }, { "epoch": 0.6735537190082644, "grad_norm": 1.3100956259468826, "learning_rate": 1.6776859411191205e-05, "loss": 0.6533, "step": 4727 }, { "epoch": 0.6736962097463665, "grad_norm": 1.309819547541102, "learning_rate": 1.6775030374257167e-05, "loss": 0.6606, "step": 4728 }, { "epoch": 0.6738387004844685, "grad_norm": 1.4033836626304037, "learning_rate": 1.6773200918272257e-05, "loss": 0.6411, "step": 4729 }, { "epoch": 0.6739811912225705, "grad_norm": 1.2801823758869604, "learning_rate": 1.677137104334962e-05, "loss": 0.6639, "step": 4730 }, { "epoch": 0.6741236819606725, "grad_norm": 1.9626340091527996, "learning_rate": 1.6769540749602446e-05, "loss": 0.7425, "step": 4731 }, { "epoch": 0.6742661726987745, "grad_norm": 1.3323670613481575, "learning_rate": 1.6767710037143932e-05, "loss": 0.6484, "step": 4732 }, { "epoch": 0.6744086634368766, "grad_norm": 1.2849186926861846, "learning_rate": 1.6765878906087327e-05, "loss": 0.5809, "step": 4733 }, { "epoch": 0.6745511541749786, "grad_norm": 1.262482022460576, "learning_rate": 1.6764047356545874e-05, "loss": 0.6421, "step": 4734 }, { "epoch": 0.6746936449130807, "grad_norm": 1.2797536514604713, "learning_rate": 1.6762215388632873e-05, "loss": 0.6002, "step": 4735 }, { "epoch": 0.6748361356511827, "grad_norm": 1.4145070613860062, "learning_rate": 1.6760383002461623e-05, "loss": 0.6815, "step": 4736 }, { "epoch": 0.6749786263892847, "grad_norm": 1.5565104950478494, "learning_rate": 1.6758550198145474e-05, "loss": 0.7105, "step": 4737 }, { "epoch": 0.6751211171273868, "grad_norm": 1.181866559789049, "learning_rate": 1.6756716975797777e-05, "loss": 0.5468, "step": 4738 }, { "epoch": 0.6752636078654888, "grad_norm": 1.4669202187343615, "learning_rate": 1.6754883335531927e-05, "loss": 0.6925, "step": 4739 }, { "epoch": 0.6754060986035908, "grad_norm": 1.3631005422374174, "learning_rate": 1.675304927746134e-05, "loss": 0.6414, "step": 4740 }, { "epoch": 0.6755485893416928, "grad_norm": 1.400599411838558, "learning_rate": 1.6751214801699454e-05, "loss": 0.6773, "step": 4741 }, { "epoch": 0.6756910800797948, "grad_norm": 1.378810842667633, "learning_rate": 1.6749379908359734e-05, "loss": 0.6939, "step": 4742 }, { "epoch": 0.6758335708178969, "grad_norm": 1.4745977710579143, "learning_rate": 1.6747544597555675e-05, "loss": 0.7048, "step": 4743 }, { "epoch": 0.6759760615559989, "grad_norm": 1.3471841199780579, "learning_rate": 1.6745708869400793e-05, "loss": 0.6671, "step": 4744 }, { "epoch": 0.6761185522941009, "grad_norm": 1.3815958554690266, "learning_rate": 1.6743872724008636e-05, "loss": 0.6649, "step": 4745 }, { "epoch": 0.6762610430322029, "grad_norm": 1.4834989033068988, "learning_rate": 1.6742036161492773e-05, "loss": 0.6277, "step": 4746 }, { "epoch": 0.6764035337703049, "grad_norm": 1.9391685402855685, "learning_rate": 1.674019918196679e-05, "loss": 0.6163, "step": 4747 }, { "epoch": 0.676546024508407, "grad_norm": 1.3682286036670275, "learning_rate": 1.6738361785544324e-05, "loss": 0.5955, "step": 4748 }, { "epoch": 0.676688515246509, "grad_norm": 1.3005906107832368, "learning_rate": 1.673652397233901e-05, "loss": 0.7674, "step": 4749 }, { "epoch": 0.676831005984611, "grad_norm": 1.4384429884845682, "learning_rate": 1.6734685742464524e-05, "loss": 0.6727, "step": 4750 }, { "epoch": 0.676973496722713, "grad_norm": 1.3835207550017519, "learning_rate": 1.6732847096034568e-05, "loss": 0.6965, "step": 4751 }, { "epoch": 0.677115987460815, "grad_norm": 1.2843254749362303, "learning_rate": 1.6731008033162863e-05, "loss": 0.6086, "step": 4752 }, { "epoch": 0.677258478198917, "grad_norm": 1.481869228964184, "learning_rate": 1.672916855396316e-05, "loss": 0.609, "step": 4753 }, { "epoch": 0.6774009689370191, "grad_norm": 1.2155378126695444, "learning_rate": 1.6727328658549233e-05, "loss": 0.5877, "step": 4754 }, { "epoch": 0.6775434596751211, "grad_norm": 1.4031222607087626, "learning_rate": 1.672548834703489e-05, "loss": 0.6557, "step": 4755 }, { "epoch": 0.6776859504132231, "grad_norm": 1.3615803257123966, "learning_rate": 1.672364761953395e-05, "loss": 0.6239, "step": 4756 }, { "epoch": 0.6778284411513251, "grad_norm": 1.4914049824979774, "learning_rate": 1.6721806476160272e-05, "loss": 0.6115, "step": 4757 }, { "epoch": 0.6779709318894271, "grad_norm": 1.342173483591209, "learning_rate": 1.6719964917027732e-05, "loss": 0.6673, "step": 4758 }, { "epoch": 0.6781134226275292, "grad_norm": 1.3247166002485737, "learning_rate": 1.6718122942250237e-05, "loss": 0.6319, "step": 4759 }, { "epoch": 0.6782559133656312, "grad_norm": 1.2862594850002123, "learning_rate": 1.671628055194172e-05, "loss": 0.6706, "step": 4760 }, { "epoch": 0.6783984041037333, "grad_norm": 1.4307598736620324, "learning_rate": 1.6714437746216123e-05, "loss": 0.6453, "step": 4761 }, { "epoch": 0.6785408948418353, "grad_norm": 1.6287076901935809, "learning_rate": 1.6712594525187444e-05, "loss": 0.6933, "step": 4762 }, { "epoch": 0.6786833855799373, "grad_norm": 1.3918604129593577, "learning_rate": 1.6710750888969683e-05, "loss": 0.5971, "step": 4763 }, { "epoch": 0.6788258763180394, "grad_norm": 1.4952759291249262, "learning_rate": 1.6708906837676874e-05, "loss": 0.7591, "step": 4764 }, { "epoch": 0.6789683670561414, "grad_norm": 1.3250593935855646, "learning_rate": 1.6707062371423077e-05, "loss": 0.5964, "step": 4765 }, { "epoch": 0.6791108577942434, "grad_norm": 1.313393468148577, "learning_rate": 1.6705217490322373e-05, "loss": 0.6394, "step": 4766 }, { "epoch": 0.6792533485323454, "grad_norm": 1.383668272703651, "learning_rate": 1.6703372194488875e-05, "loss": 0.6293, "step": 4767 }, { "epoch": 0.6793958392704474, "grad_norm": 1.2993705785650198, "learning_rate": 1.670152648403672e-05, "loss": 0.5884, "step": 4768 }, { "epoch": 0.6795383300085495, "grad_norm": 1.4822813088819007, "learning_rate": 1.6699680359080066e-05, "loss": 0.6627, "step": 4769 }, { "epoch": 0.6796808207466515, "grad_norm": 1.3596065935940482, "learning_rate": 1.6697833819733104e-05, "loss": 0.699, "step": 4770 }, { "epoch": 0.6798233114847535, "grad_norm": 1.6063516146103194, "learning_rate": 1.6695986866110036e-05, "loss": 0.6263, "step": 4771 }, { "epoch": 0.6799658022228555, "grad_norm": 1.378911819992472, "learning_rate": 1.6694139498325116e-05, "loss": 0.6699, "step": 4772 }, { "epoch": 0.6801082929609575, "grad_norm": 1.2726105578399411, "learning_rate": 1.6692291716492595e-05, "loss": 0.6432, "step": 4773 }, { "epoch": 0.6802507836990596, "grad_norm": 1.626237863731344, "learning_rate": 1.669044352072677e-05, "loss": 0.5837, "step": 4774 }, { "epoch": 0.6803932744371616, "grad_norm": 1.4700626296078931, "learning_rate": 1.6688594911141952e-05, "loss": 0.6742, "step": 4775 }, { "epoch": 0.6805357651752636, "grad_norm": 1.4544714134220311, "learning_rate": 1.6686745887852485e-05, "loss": 0.7541, "step": 4776 }, { "epoch": 0.6806782559133656, "grad_norm": 1.4106091209713996, "learning_rate": 1.668489645097273e-05, "loss": 0.6367, "step": 4777 }, { "epoch": 0.6808207466514676, "grad_norm": 1.3964663810226778, "learning_rate": 1.6683046600617082e-05, "loss": 0.7102, "step": 4778 }, { "epoch": 0.6809632373895697, "grad_norm": 1.3193120297120609, "learning_rate": 1.6681196336899963e-05, "loss": 0.6802, "step": 4779 }, { "epoch": 0.6811057281276717, "grad_norm": 1.2766789126409408, "learning_rate": 1.6679345659935808e-05, "loss": 0.6721, "step": 4780 }, { "epoch": 0.6812482188657737, "grad_norm": 1.2924135163330335, "learning_rate": 1.6677494569839092e-05, "loss": 0.6047, "step": 4781 }, { "epoch": 0.6813907096038757, "grad_norm": 1.1327055491390343, "learning_rate": 1.6675643066724307e-05, "loss": 0.6276, "step": 4782 }, { "epoch": 0.6815332003419777, "grad_norm": 1.2565095206544035, "learning_rate": 1.667379115070597e-05, "loss": 0.5346, "step": 4783 }, { "epoch": 0.6816756910800797, "grad_norm": 1.5124025916891397, "learning_rate": 1.6671938821898626e-05, "loss": 0.7039, "step": 4784 }, { "epoch": 0.6818181818181818, "grad_norm": 1.2756807098071636, "learning_rate": 1.667008608041685e-05, "loss": 0.6189, "step": 4785 }, { "epoch": 0.6819606725562838, "grad_norm": 1.3601684557438816, "learning_rate": 1.6668232926375237e-05, "loss": 0.7312, "step": 4786 }, { "epoch": 0.6821031632943859, "grad_norm": 1.5170320019388572, "learning_rate": 1.6666379359888405e-05, "loss": 0.6655, "step": 4787 }, { "epoch": 0.6822456540324879, "grad_norm": 1.5169237330076943, "learning_rate": 1.6664525381071007e-05, "loss": 0.6919, "step": 4788 }, { "epoch": 0.68238814477059, "grad_norm": 1.408542359490696, "learning_rate": 1.666267099003771e-05, "loss": 0.6965, "step": 4789 }, { "epoch": 0.682530635508692, "grad_norm": 1.3389797237041634, "learning_rate": 1.666081618690322e-05, "loss": 0.6278, "step": 4790 }, { "epoch": 0.682673126246794, "grad_norm": 1.3256010388917918, "learning_rate": 1.6658960971782254e-05, "loss": 0.691, "step": 4791 }, { "epoch": 0.682815616984896, "grad_norm": 1.374967746360574, "learning_rate": 1.6657105344789556e-05, "loss": 0.6994, "step": 4792 }, { "epoch": 0.682958107722998, "grad_norm": 1.3753522922794095, "learning_rate": 1.6655249306039912e-05, "loss": 0.6732, "step": 4793 }, { "epoch": 0.6831005984611, "grad_norm": 1.2899220047235909, "learning_rate": 1.6653392855648123e-05, "loss": 0.6637, "step": 4794 }, { "epoch": 0.6832430891992021, "grad_norm": 1.3678655177414578, "learning_rate": 1.6651535993729005e-05, "loss": 0.6451, "step": 4795 }, { "epoch": 0.6833855799373041, "grad_norm": 1.37809021181442, "learning_rate": 1.6649678720397413e-05, "loss": 0.6857, "step": 4796 }, { "epoch": 0.6835280706754061, "grad_norm": 1.3911358611880096, "learning_rate": 1.6647821035768227e-05, "loss": 0.6785, "step": 4797 }, { "epoch": 0.6836705614135081, "grad_norm": 1.587448884931292, "learning_rate": 1.6645962939956343e-05, "loss": 0.6911, "step": 4798 }, { "epoch": 0.6838130521516101, "grad_norm": 1.4557386647001773, "learning_rate": 1.664410443307669e-05, "loss": 0.6726, "step": 4799 }, { "epoch": 0.6839555428897122, "grad_norm": 1.333914407676437, "learning_rate": 1.6642245515244227e-05, "loss": 0.6302, "step": 4800 }, { "epoch": 0.6840980336278142, "grad_norm": 1.2715419453768744, "learning_rate": 1.6640386186573927e-05, "loss": 0.7055, "step": 4801 }, { "epoch": 0.6842405243659162, "grad_norm": 1.348215529301649, "learning_rate": 1.6638526447180793e-05, "loss": 0.6561, "step": 4802 }, { "epoch": 0.6843830151040182, "grad_norm": 1.3696336334912467, "learning_rate": 1.6636666297179856e-05, "loss": 0.7059, "step": 4803 }, { "epoch": 0.6845255058421202, "grad_norm": 1.969804160205727, "learning_rate": 1.6634805736686166e-05, "loss": 0.6845, "step": 4804 }, { "epoch": 0.6846679965802223, "grad_norm": 1.2998131152924242, "learning_rate": 1.6632944765814812e-05, "loss": 0.7775, "step": 4805 }, { "epoch": 0.6848104873183243, "grad_norm": 1.3220364499119117, "learning_rate": 1.663108338468089e-05, "loss": 0.5848, "step": 4806 }, { "epoch": 0.6849529780564263, "grad_norm": 1.4383268570550076, "learning_rate": 1.6629221593399537e-05, "loss": 0.6548, "step": 4807 }, { "epoch": 0.6850954687945283, "grad_norm": 1.3356773995061642, "learning_rate": 1.6627359392085907e-05, "loss": 0.6962, "step": 4808 }, { "epoch": 0.6852379595326303, "grad_norm": 1.2823946321050603, "learning_rate": 1.662549678085518e-05, "loss": 0.669, "step": 4809 }, { "epoch": 0.6853804502707324, "grad_norm": 1.6927984962199296, "learning_rate": 1.6623633759822562e-05, "loss": 0.6004, "step": 4810 }, { "epoch": 0.6855229410088344, "grad_norm": 1.3994839096605152, "learning_rate": 1.662177032910329e-05, "loss": 0.7105, "step": 4811 }, { "epoch": 0.6856654317469365, "grad_norm": 1.3422145013214444, "learning_rate": 1.6619906488812613e-05, "loss": 0.7015, "step": 4812 }, { "epoch": 0.6858079224850385, "grad_norm": 1.3747870719954067, "learning_rate": 1.6618042239065824e-05, "loss": 0.6067, "step": 4813 }, { "epoch": 0.6859504132231405, "grad_norm": 1.4539002775700975, "learning_rate": 1.661617757997822e-05, "loss": 0.7029, "step": 4814 }, { "epoch": 0.6860929039612426, "grad_norm": 4.469111370956145, "learning_rate": 1.6614312511665143e-05, "loss": 0.6015, "step": 4815 }, { "epoch": 0.6862353946993446, "grad_norm": 1.3421162064036927, "learning_rate": 1.661244703424195e-05, "loss": 0.7058, "step": 4816 }, { "epoch": 0.6863778854374466, "grad_norm": 1.4673120155466914, "learning_rate": 1.6610581147824022e-05, "loss": 0.6555, "step": 4817 }, { "epoch": 0.6865203761755486, "grad_norm": 1.4201836933935685, "learning_rate": 1.6608714852526773e-05, "loss": 0.6927, "step": 4818 }, { "epoch": 0.6866628669136506, "grad_norm": 1.3645226005294386, "learning_rate": 1.660684814846563e-05, "loss": 0.7058, "step": 4819 }, { "epoch": 0.6868053576517527, "grad_norm": 1.500940602031204, "learning_rate": 1.6604981035756062e-05, "loss": 0.6406, "step": 4820 }, { "epoch": 0.6869478483898547, "grad_norm": 1.4401504800556062, "learning_rate": 1.6603113514513548e-05, "loss": 0.6999, "step": 4821 }, { "epoch": 0.6870903391279567, "grad_norm": 1.9766862778129395, "learning_rate": 1.66012455848536e-05, "loss": 0.6733, "step": 4822 }, { "epoch": 0.6872328298660587, "grad_norm": 1.230430037415352, "learning_rate": 1.6599377246891753e-05, "loss": 0.6383, "step": 4823 }, { "epoch": 0.6873753206041607, "grad_norm": 1.6357352742660858, "learning_rate": 1.6597508500743568e-05, "loss": 0.7354, "step": 4824 }, { "epoch": 0.6875178113422628, "grad_norm": 1.6809167778279546, "learning_rate": 1.659563934652463e-05, "loss": 0.6969, "step": 4825 }, { "epoch": 0.6876603020803648, "grad_norm": 1.4426859665549867, "learning_rate": 1.6593769784350556e-05, "loss": 0.6633, "step": 4826 }, { "epoch": 0.6878027928184668, "grad_norm": 1.6449077612478882, "learning_rate": 1.6591899814336974e-05, "loss": 0.6522, "step": 4827 }, { "epoch": 0.6879452835565688, "grad_norm": 1.4172563889658225, "learning_rate": 1.6590029436599556e-05, "loss": 0.6401, "step": 4828 }, { "epoch": 0.6880877742946708, "grad_norm": 1.5235669662677611, "learning_rate": 1.658815865125398e-05, "loss": 0.6352, "step": 4829 }, { "epoch": 0.6882302650327728, "grad_norm": 1.2631733521138093, "learning_rate": 1.6586287458415964e-05, "loss": 0.5534, "step": 4830 }, { "epoch": 0.6883727557708749, "grad_norm": 1.6436902082456997, "learning_rate": 1.6584415858201244e-05, "loss": 0.6488, "step": 4831 }, { "epoch": 0.6885152465089769, "grad_norm": 1.507679236604413, "learning_rate": 1.6582543850725577e-05, "loss": 0.7425, "step": 4832 }, { "epoch": 0.6886577372470789, "grad_norm": 1.5038763752590392, "learning_rate": 1.658067143610476e-05, "loss": 0.7671, "step": 4833 }, { "epoch": 0.6888002279851809, "grad_norm": 1.750762609073602, "learning_rate": 1.6578798614454602e-05, "loss": 0.6607, "step": 4834 }, { "epoch": 0.6889427187232829, "grad_norm": 1.3920716245898592, "learning_rate": 1.6576925385890944e-05, "loss": 0.6605, "step": 4835 }, { "epoch": 0.689085209461385, "grad_norm": 1.3969441094725468, "learning_rate": 1.657505175052964e-05, "loss": 0.6627, "step": 4836 }, { "epoch": 0.689227700199487, "grad_norm": 1.417639813821646, "learning_rate": 1.657317770848659e-05, "loss": 0.6491, "step": 4837 }, { "epoch": 0.6893701909375891, "grad_norm": 1.3981057192377477, "learning_rate": 1.65713032598777e-05, "loss": 0.6055, "step": 4838 }, { "epoch": 0.6895126816756911, "grad_norm": 1.3049674544799224, "learning_rate": 1.6569428404818913e-05, "loss": 0.6162, "step": 4839 }, { "epoch": 0.6896551724137931, "grad_norm": 1.4429172538175226, "learning_rate": 1.6567553143426193e-05, "loss": 0.633, "step": 4840 }, { "epoch": 0.6897976631518952, "grad_norm": 2.443990981350267, "learning_rate": 1.6565677475815527e-05, "loss": 0.6864, "step": 4841 }, { "epoch": 0.6899401538899972, "grad_norm": 1.526433347829762, "learning_rate": 1.6563801402102933e-05, "loss": 0.6884, "step": 4842 }, { "epoch": 0.6900826446280992, "grad_norm": 1.4304264104608584, "learning_rate": 1.6561924922404443e-05, "loss": 0.5901, "step": 4843 }, { "epoch": 0.6902251353662012, "grad_norm": 1.315787691353109, "learning_rate": 1.6560048036836127e-05, "loss": 0.6724, "step": 4844 }, { "epoch": 0.6903676261043032, "grad_norm": 1.460240635944478, "learning_rate": 1.6558170745514075e-05, "loss": 0.7601, "step": 4845 }, { "epoch": 0.6905101168424053, "grad_norm": 1.3467565669622783, "learning_rate": 1.65562930485544e-05, "loss": 0.6608, "step": 4846 }, { "epoch": 0.6906526075805073, "grad_norm": 1.4661714367017302, "learning_rate": 1.6554414946073244e-05, "loss": 0.7323, "step": 4847 }, { "epoch": 0.6907950983186093, "grad_norm": 1.4833672992748501, "learning_rate": 1.655253643818677e-05, "loss": 0.6903, "step": 4848 }, { "epoch": 0.6909375890567113, "grad_norm": 1.4770990819774958, "learning_rate": 1.6550657525011163e-05, "loss": 0.703, "step": 4849 }, { "epoch": 0.6910800797948133, "grad_norm": 1.485864913316588, "learning_rate": 1.654877820666265e-05, "loss": 0.7942, "step": 4850 }, { "epoch": 0.6912225705329154, "grad_norm": 2.5734375804016167, "learning_rate": 1.6546898483257457e-05, "loss": 0.7003, "step": 4851 }, { "epoch": 0.6913650612710174, "grad_norm": 1.263321088119382, "learning_rate": 1.654501835491186e-05, "loss": 0.6514, "step": 4852 }, { "epoch": 0.6915075520091194, "grad_norm": 1.3793486605451046, "learning_rate": 1.6543137821742145e-05, "loss": 0.69, "step": 4853 }, { "epoch": 0.6916500427472214, "grad_norm": 1.3679808283693744, "learning_rate": 1.6541256883864627e-05, "loss": 0.7119, "step": 4854 }, { "epoch": 0.6917925334853234, "grad_norm": 1.3308419563838427, "learning_rate": 1.6539375541395645e-05, "loss": 0.6732, "step": 4855 }, { "epoch": 0.6919350242234255, "grad_norm": 1.3750476451500033, "learning_rate": 1.653749379445157e-05, "loss": 0.6627, "step": 4856 }, { "epoch": 0.6920775149615275, "grad_norm": 1.3624018527055677, "learning_rate": 1.6535611643148784e-05, "loss": 0.7048, "step": 4857 }, { "epoch": 0.6922200056996295, "grad_norm": 1.2959837654938804, "learning_rate": 1.6533729087603708e-05, "loss": 0.6238, "step": 4858 }, { "epoch": 0.6923624964377315, "grad_norm": 1.5443567209639526, "learning_rate": 1.6531846127932786e-05, "loss": 0.6549, "step": 4859 }, { "epoch": 0.6925049871758335, "grad_norm": 1.582452750653485, "learning_rate": 1.652996276425247e-05, "loss": 0.6532, "step": 4860 }, { "epoch": 0.6926474779139355, "grad_norm": 2.3252186368850123, "learning_rate": 1.6528078996679266e-05, "loss": 0.7434, "step": 4861 }, { "epoch": 0.6927899686520376, "grad_norm": 1.6409183214997556, "learning_rate": 1.6526194825329678e-05, "loss": 0.6933, "step": 4862 }, { "epoch": 0.6929324593901396, "grad_norm": 1.2688756122246017, "learning_rate": 1.652431025032025e-05, "loss": 0.6897, "step": 4863 }, { "epoch": 0.6930749501282417, "grad_norm": 1.5907030659253036, "learning_rate": 1.652242527176755e-05, "loss": 0.6574, "step": 4864 }, { "epoch": 0.6932174408663437, "grad_norm": 1.3056612688103688, "learning_rate": 1.652053988978816e-05, "loss": 0.6534, "step": 4865 }, { "epoch": 0.6933599316044458, "grad_norm": 1.4925006960050151, "learning_rate": 1.6518654104498704e-05, "loss": 0.6155, "step": 4866 }, { "epoch": 0.6935024223425478, "grad_norm": 1.6931910427798276, "learning_rate": 1.651676791601582e-05, "loss": 0.7004, "step": 4867 }, { "epoch": 0.6936449130806498, "grad_norm": 1.5158600741929371, "learning_rate": 1.651488132445617e-05, "loss": 0.7083, "step": 4868 }, { "epoch": 0.6937874038187518, "grad_norm": 1.3890890463849292, "learning_rate": 1.6512994329936446e-05, "loss": 0.5787, "step": 4869 }, { "epoch": 0.6939298945568538, "grad_norm": 1.3930776071709567, "learning_rate": 1.6511106932573363e-05, "loss": 0.6994, "step": 4870 }, { "epoch": 0.6940723852949559, "grad_norm": 1.3203276896521108, "learning_rate": 1.6509219132483657e-05, "loss": 0.6741, "step": 4871 }, { "epoch": 0.6942148760330579, "grad_norm": 1.4213856599342605, "learning_rate": 1.6507330929784098e-05, "loss": 0.6285, "step": 4872 }, { "epoch": 0.6943573667711599, "grad_norm": 1.2877056227784685, "learning_rate": 1.6505442324591473e-05, "loss": 0.6828, "step": 4873 }, { "epoch": 0.6944998575092619, "grad_norm": 1.3790581199085126, "learning_rate": 1.6503553317022596e-05, "loss": 0.6384, "step": 4874 }, { "epoch": 0.6946423482473639, "grad_norm": 1.4896172017436236, "learning_rate": 1.6501663907194306e-05, "loss": 0.6341, "step": 4875 }, { "epoch": 0.694784838985466, "grad_norm": 1.5276335627521282, "learning_rate": 1.6499774095223474e-05, "loss": 0.8203, "step": 4876 }, { "epoch": 0.694927329723568, "grad_norm": 1.4214495455444682, "learning_rate": 1.6497883881226983e-05, "loss": 0.63, "step": 4877 }, { "epoch": 0.69506982046167, "grad_norm": 1.4531631524089916, "learning_rate": 1.649599326532174e-05, "loss": 0.7401, "step": 4878 }, { "epoch": 0.695212311199772, "grad_norm": 1.4424640663594945, "learning_rate": 1.64941022476247e-05, "loss": 0.7231, "step": 4879 }, { "epoch": 0.695354801937874, "grad_norm": 1.3337042504514145, "learning_rate": 1.6492210828252812e-05, "loss": 0.7236, "step": 4880 }, { "epoch": 0.695497292675976, "grad_norm": 1.6975321414748996, "learning_rate": 1.6490319007323073e-05, "loss": 0.6771, "step": 4881 }, { "epoch": 0.6956397834140781, "grad_norm": 1.4745446132420519, "learning_rate": 1.6488426784952497e-05, "loss": 0.6718, "step": 4882 }, { "epoch": 0.6957822741521801, "grad_norm": 1.3329637844260844, "learning_rate": 1.6486534161258117e-05, "loss": 0.7278, "step": 4883 }, { "epoch": 0.6959247648902821, "grad_norm": 1.5656743950893406, "learning_rate": 1.6484641136356997e-05, "loss": 0.6463, "step": 4884 }, { "epoch": 0.6960672556283841, "grad_norm": 1.627786199233927, "learning_rate": 1.648274771036623e-05, "loss": 0.661, "step": 4885 }, { "epoch": 0.6962097463664861, "grad_norm": 1.2916115143687519, "learning_rate": 1.648085388340292e-05, "loss": 0.632, "step": 4886 }, { "epoch": 0.6963522371045882, "grad_norm": 1.286445580401991, "learning_rate": 1.6478959655584213e-05, "loss": 0.6487, "step": 4887 }, { "epoch": 0.6964947278426902, "grad_norm": 1.3984686925159382, "learning_rate": 1.6477065027027266e-05, "loss": 0.6389, "step": 4888 }, { "epoch": 0.6966372185807922, "grad_norm": 1.5644460200114958, "learning_rate": 1.6475169997849267e-05, "loss": 0.6734, "step": 4889 }, { "epoch": 0.6967797093188943, "grad_norm": 1.5157763140046234, "learning_rate": 1.647327456816743e-05, "loss": 0.5764, "step": 4890 }, { "epoch": 0.6969222000569963, "grad_norm": 1.6426660853948871, "learning_rate": 1.647137873809899e-05, "loss": 0.7098, "step": 4891 }, { "epoch": 0.6970646907950984, "grad_norm": 1.4542403033295972, "learning_rate": 1.6469482507761208e-05, "loss": 0.6571, "step": 4892 }, { "epoch": 0.6972071815332004, "grad_norm": 1.2785531561999546, "learning_rate": 1.646758587727137e-05, "loss": 0.664, "step": 4893 }, { "epoch": 0.6973496722713024, "grad_norm": 1.5120521957004711, "learning_rate": 1.6465688846746787e-05, "loss": 0.7288, "step": 4894 }, { "epoch": 0.6974921630094044, "grad_norm": 1.4884721677918222, "learning_rate": 1.6463791416304796e-05, "loss": 0.6887, "step": 4895 }, { "epoch": 0.6976346537475064, "grad_norm": 1.3546952969350095, "learning_rate": 1.6461893586062757e-05, "loss": 0.6507, "step": 4896 }, { "epoch": 0.6977771444856085, "grad_norm": 1.3840947633669254, "learning_rate": 1.6459995356138053e-05, "loss": 0.7362, "step": 4897 }, { "epoch": 0.6979196352237105, "grad_norm": 1.4610488222529636, "learning_rate": 1.6458096726648095e-05, "loss": 0.5944, "step": 4898 }, { "epoch": 0.6980621259618125, "grad_norm": 1.443702606709668, "learning_rate": 1.6456197697710317e-05, "loss": 0.7035, "step": 4899 }, { "epoch": 0.6982046166999145, "grad_norm": 1.301420762951501, "learning_rate": 1.645429826944218e-05, "loss": 0.6845, "step": 4900 }, { "epoch": 0.6983471074380165, "grad_norm": 1.300792162847853, "learning_rate": 1.6452398441961168e-05, "loss": 0.6595, "step": 4901 }, { "epoch": 0.6984895981761186, "grad_norm": 1.3404067317907724, "learning_rate": 1.645049821538479e-05, "loss": 0.5946, "step": 4902 }, { "epoch": 0.6986320889142206, "grad_norm": 1.4633661377765665, "learning_rate": 1.6448597589830572e-05, "loss": 0.674, "step": 4903 }, { "epoch": 0.6987745796523226, "grad_norm": 1.5428876021951805, "learning_rate": 1.6446696565416083e-05, "loss": 0.6522, "step": 4904 }, { "epoch": 0.6989170703904246, "grad_norm": 1.4103786026769314, "learning_rate": 1.6444795142258897e-05, "loss": 0.6211, "step": 4905 }, { "epoch": 0.6990595611285266, "grad_norm": 1.2498855636222868, "learning_rate": 1.644289332047663e-05, "loss": 0.5662, "step": 4906 }, { "epoch": 0.6992020518666286, "grad_norm": 1.3797460342222738, "learning_rate": 1.64409911001869e-05, "loss": 0.5718, "step": 4907 }, { "epoch": 0.6993445426047307, "grad_norm": 1.253865182476567, "learning_rate": 1.643908848150738e-05, "loss": 0.6598, "step": 4908 }, { "epoch": 0.6994870333428327, "grad_norm": 1.5229853362503254, "learning_rate": 1.643718546455574e-05, "loss": 0.7244, "step": 4909 }, { "epoch": 0.6996295240809347, "grad_norm": 1.2839121249016054, "learning_rate": 1.6435282049449688e-05, "loss": 0.6198, "step": 4910 }, { "epoch": 0.6997720148190367, "grad_norm": 1.3919149024691222, "learning_rate": 1.6433378236306957e-05, "loss": 0.684, "step": 4911 }, { "epoch": 0.6999145055571387, "grad_norm": 1.3539360151311235, "learning_rate": 1.64314740252453e-05, "loss": 0.6873, "step": 4912 }, { "epoch": 0.7000569962952408, "grad_norm": 1.3458078299862426, "learning_rate": 1.64295694163825e-05, "loss": 0.6293, "step": 4913 }, { "epoch": 0.7001994870333428, "grad_norm": 1.4471706109424278, "learning_rate": 1.642766440983636e-05, "loss": 0.6788, "step": 4914 }, { "epoch": 0.7003419777714448, "grad_norm": 1.3327115136447678, "learning_rate": 1.6425759005724705e-05, "loss": 0.712, "step": 4915 }, { "epoch": 0.7004844685095469, "grad_norm": 1.4971442875630472, "learning_rate": 1.642385320416539e-05, "loss": 0.7028, "step": 4916 }, { "epoch": 0.700626959247649, "grad_norm": 1.4738203437036197, "learning_rate": 1.64219470052763e-05, "loss": 0.6863, "step": 4917 }, { "epoch": 0.700769449985751, "grad_norm": 1.3169011945977478, "learning_rate": 1.642004040917533e-05, "loss": 0.6712, "step": 4918 }, { "epoch": 0.700911940723853, "grad_norm": 1.305853447708106, "learning_rate": 1.641813341598041e-05, "loss": 0.6731, "step": 4919 }, { "epoch": 0.701054431461955, "grad_norm": 1.5942547058715142, "learning_rate": 1.641622602580949e-05, "loss": 0.7053, "step": 4920 }, { "epoch": 0.701196922200057, "grad_norm": 1.376832207762018, "learning_rate": 1.6414318238780545e-05, "loss": 0.6891, "step": 4921 }, { "epoch": 0.701339412938159, "grad_norm": 2.0832967490815246, "learning_rate": 1.6412410055011588e-05, "loss": 0.6342, "step": 4922 }, { "epoch": 0.7014819036762611, "grad_norm": 1.3103032998804616, "learning_rate": 1.6410501474620625e-05, "loss": 0.6408, "step": 4923 }, { "epoch": 0.7016243944143631, "grad_norm": 1.395827373969263, "learning_rate": 1.640859249772572e-05, "loss": 0.6165, "step": 4924 }, { "epoch": 0.7017668851524651, "grad_norm": 2.063911856671732, "learning_rate": 1.6406683124444946e-05, "loss": 0.7315, "step": 4925 }, { "epoch": 0.7019093758905671, "grad_norm": 1.4416429241474904, "learning_rate": 1.64047733548964e-05, "loss": 0.6295, "step": 4926 }, { "epoch": 0.7020518666286691, "grad_norm": 1.3229711452626516, "learning_rate": 1.6402863189198203e-05, "loss": 0.5961, "step": 4927 }, { "epoch": 0.7021943573667712, "grad_norm": 1.2377140279283563, "learning_rate": 1.6400952627468505e-05, "loss": 0.6629, "step": 4928 }, { "epoch": 0.7023368481048732, "grad_norm": 1.5407020715075344, "learning_rate": 1.6399041669825478e-05, "loss": 0.6433, "step": 4929 }, { "epoch": 0.7024793388429752, "grad_norm": 1.4935270762399446, "learning_rate": 1.6397130316387322e-05, "loss": 0.6342, "step": 4930 }, { "epoch": 0.7026218295810772, "grad_norm": 1.3322894458757524, "learning_rate": 1.6395218567272254e-05, "loss": 0.7151, "step": 4931 }, { "epoch": 0.7027643203191792, "grad_norm": 1.2786117248712854, "learning_rate": 1.6393306422598525e-05, "loss": 0.6006, "step": 4932 }, { "epoch": 0.7029068110572813, "grad_norm": 1.4892974732654563, "learning_rate": 1.6391393882484405e-05, "loss": 0.6124, "step": 4933 }, { "epoch": 0.7030493017953833, "grad_norm": 1.3405123865856057, "learning_rate": 1.638948094704818e-05, "loss": 0.6061, "step": 4934 }, { "epoch": 0.7031917925334853, "grad_norm": 1.347890162944523, "learning_rate": 1.638756761640818e-05, "loss": 0.5874, "step": 4935 }, { "epoch": 0.7033342832715873, "grad_norm": 1.3955268358343782, "learning_rate": 1.6385653890682747e-05, "loss": 0.6687, "step": 4936 }, { "epoch": 0.7034767740096893, "grad_norm": 1.1556157583824975, "learning_rate": 1.6383739769990246e-05, "loss": 0.6607, "step": 4937 }, { "epoch": 0.7036192647477914, "grad_norm": 1.3118440899257182, "learning_rate": 1.6381825254449068e-05, "loss": 0.6403, "step": 4938 }, { "epoch": 0.7037617554858934, "grad_norm": 1.4512590430749188, "learning_rate": 1.6379910344177635e-05, "loss": 0.6107, "step": 4939 }, { "epoch": 0.7039042462239954, "grad_norm": 1.7474420619738882, "learning_rate": 1.6377995039294385e-05, "loss": 0.6785, "step": 4940 }, { "epoch": 0.7040467369620975, "grad_norm": 1.2480359698355652, "learning_rate": 1.6376079339917788e-05, "loss": 0.658, "step": 4941 }, { "epoch": 0.7041892277001995, "grad_norm": 1.3412768333018994, "learning_rate": 1.6374163246166327e-05, "loss": 0.6177, "step": 4942 }, { "epoch": 0.7043317184383016, "grad_norm": 1.3219621034280113, "learning_rate": 1.6372246758158528e-05, "loss": 0.6379, "step": 4943 }, { "epoch": 0.7044742091764036, "grad_norm": 1.4821501791614484, "learning_rate": 1.637032987601292e-05, "loss": 0.6362, "step": 4944 }, { "epoch": 0.7046166999145056, "grad_norm": 1.527707788821247, "learning_rate": 1.6368412599848073e-05, "loss": 0.6697, "step": 4945 }, { "epoch": 0.7047591906526076, "grad_norm": 1.7217695697163704, "learning_rate": 1.6366494929782564e-05, "loss": 0.7116, "step": 4946 }, { "epoch": 0.7049016813907096, "grad_norm": 1.3278592896947823, "learning_rate": 1.636457686593502e-05, "loss": 0.5782, "step": 4947 }, { "epoch": 0.7050441721288117, "grad_norm": 1.5540052036306844, "learning_rate": 1.6362658408424068e-05, "loss": 0.6117, "step": 4948 }, { "epoch": 0.7051866628669137, "grad_norm": 1.300422928958158, "learning_rate": 1.636073955736837e-05, "loss": 0.6762, "step": 4949 }, { "epoch": 0.7053291536050157, "grad_norm": 1.3788477465662496, "learning_rate": 1.6358820312886616e-05, "loss": 0.7414, "step": 4950 }, { "epoch": 0.7054716443431177, "grad_norm": 2.2491164954442264, "learning_rate": 1.635690067509751e-05, "loss": 0.6839, "step": 4951 }, { "epoch": 0.7056141350812197, "grad_norm": 1.2992138423306971, "learning_rate": 1.635498064411979e-05, "loss": 0.7269, "step": 4952 }, { "epoch": 0.7057566258193217, "grad_norm": 1.240816000384259, "learning_rate": 1.6353060220072216e-05, "loss": 0.5929, "step": 4953 }, { "epoch": 0.7058991165574238, "grad_norm": 1.3809997833892997, "learning_rate": 1.635113940307356e-05, "loss": 0.7449, "step": 4954 }, { "epoch": 0.7060416072955258, "grad_norm": 1.5327555357704294, "learning_rate": 1.634921819324264e-05, "loss": 0.6779, "step": 4955 }, { "epoch": 0.7061840980336278, "grad_norm": 1.4404376728790924, "learning_rate": 1.634729659069828e-05, "loss": 0.637, "step": 4956 }, { "epoch": 0.7063265887717298, "grad_norm": 1.3863362190934938, "learning_rate": 1.634537459555934e-05, "loss": 0.6703, "step": 4957 }, { "epoch": 0.7064690795098318, "grad_norm": 1.2444409213290117, "learning_rate": 1.63434522079447e-05, "loss": 0.6768, "step": 4958 }, { "epoch": 0.7066115702479339, "grad_norm": 1.3058714909419882, "learning_rate": 1.6341529427973265e-05, "loss": 0.6148, "step": 4959 }, { "epoch": 0.7067540609860359, "grad_norm": 1.3765576593659974, "learning_rate": 1.6339606255763955e-05, "loss": 0.5878, "step": 4960 }, { "epoch": 0.7068965517241379, "grad_norm": 1.4035987483749517, "learning_rate": 1.6337682691435728e-05, "loss": 0.6772, "step": 4961 }, { "epoch": 0.7070390424622399, "grad_norm": 1.5134710183105395, "learning_rate": 1.6335758735107564e-05, "loss": 0.7912, "step": 4962 }, { "epoch": 0.7071815332003419, "grad_norm": 1.4183530889069151, "learning_rate": 1.6333834386898456e-05, "loss": 0.6173, "step": 4963 }, { "epoch": 0.707324023938444, "grad_norm": 2.029349963902059, "learning_rate": 1.633190964692744e-05, "loss": 0.5974, "step": 4964 }, { "epoch": 0.707466514676546, "grad_norm": 1.377229195194339, "learning_rate": 1.6329984515313558e-05, "loss": 0.7131, "step": 4965 }, { "epoch": 0.707609005414648, "grad_norm": 1.9288397385760585, "learning_rate": 1.6328058992175884e-05, "loss": 0.7124, "step": 4966 }, { "epoch": 0.7077514961527501, "grad_norm": 1.313824993192731, "learning_rate": 1.6326133077633514e-05, "loss": 0.6687, "step": 4967 }, { "epoch": 0.7078939868908521, "grad_norm": 1.407924528522086, "learning_rate": 1.632420677180558e-05, "loss": 0.6772, "step": 4968 }, { "epoch": 0.7080364776289542, "grad_norm": 1.3645177069559395, "learning_rate": 1.632228007481122e-05, "loss": 0.6309, "step": 4969 }, { "epoch": 0.7081789683670562, "grad_norm": 1.497520115329226, "learning_rate": 1.6320352986769605e-05, "loss": 0.7812, "step": 4970 }, { "epoch": 0.7083214591051582, "grad_norm": 1.4725003445566935, "learning_rate": 1.6318425507799933e-05, "loss": 0.7526, "step": 4971 }, { "epoch": 0.7084639498432602, "grad_norm": 1.23836311126605, "learning_rate": 1.631649763802142e-05, "loss": 0.6005, "step": 4972 }, { "epoch": 0.7086064405813622, "grad_norm": 1.2570659838986868, "learning_rate": 1.6314569377553308e-05, "loss": 0.6528, "step": 4973 }, { "epoch": 0.7087489313194643, "grad_norm": 1.4083496090138274, "learning_rate": 1.6312640726514866e-05, "loss": 0.6375, "step": 4974 }, { "epoch": 0.7088914220575663, "grad_norm": 1.4541230638127847, "learning_rate": 1.6310711685025387e-05, "loss": 0.7041, "step": 4975 }, { "epoch": 0.7090339127956683, "grad_norm": 1.2968243504523669, "learning_rate": 1.6308782253204185e-05, "loss": 0.6432, "step": 4976 }, { "epoch": 0.7091764035337703, "grad_norm": 1.3380675076435546, "learning_rate": 1.6306852431170602e-05, "loss": 0.6722, "step": 4977 }, { "epoch": 0.7093188942718723, "grad_norm": 1.257915280859317, "learning_rate": 1.6304922219043998e-05, "loss": 0.7119, "step": 4978 }, { "epoch": 0.7094613850099744, "grad_norm": 1.5207842238886342, "learning_rate": 1.6302991616943764e-05, "loss": 0.6045, "step": 4979 }, { "epoch": 0.7096038757480764, "grad_norm": 1.303617642997833, "learning_rate": 1.630106062498931e-05, "loss": 0.6072, "step": 4980 }, { "epoch": 0.7097463664861784, "grad_norm": 1.7484840055230453, "learning_rate": 1.6299129243300074e-05, "loss": 0.7756, "step": 4981 }, { "epoch": 0.7098888572242804, "grad_norm": 1.2964369855922948, "learning_rate": 1.6297197471995516e-05, "loss": 0.7129, "step": 4982 }, { "epoch": 0.7100313479623824, "grad_norm": 1.6491543691789166, "learning_rate": 1.6295265311195115e-05, "loss": 0.6757, "step": 4983 }, { "epoch": 0.7101738387004844, "grad_norm": 1.5975938584275202, "learning_rate": 1.6293332761018387e-05, "loss": 0.7564, "step": 4984 }, { "epoch": 0.7103163294385865, "grad_norm": 1.6917551467104583, "learning_rate": 1.6291399821584864e-05, "loss": 0.6384, "step": 4985 }, { "epoch": 0.7104588201766885, "grad_norm": 1.3722935808199457, "learning_rate": 1.6289466493014098e-05, "loss": 0.6274, "step": 4986 }, { "epoch": 0.7106013109147905, "grad_norm": 1.3330828135678452, "learning_rate": 1.6287532775425673e-05, "loss": 0.6534, "step": 4987 }, { "epoch": 0.7107438016528925, "grad_norm": 1.4212959440934236, "learning_rate": 1.6285598668939195e-05, "loss": 0.7556, "step": 4988 }, { "epoch": 0.7108862923909945, "grad_norm": 1.5286905750445983, "learning_rate": 1.628366417367429e-05, "loss": 0.6881, "step": 4989 }, { "epoch": 0.7110287831290966, "grad_norm": 1.3103120146589977, "learning_rate": 1.628172928975061e-05, "loss": 0.6807, "step": 4990 }, { "epoch": 0.7111712738671986, "grad_norm": 1.6133216115833484, "learning_rate": 1.6279794017287834e-05, "loss": 0.6631, "step": 4991 }, { "epoch": 0.7113137646053006, "grad_norm": 1.3529280013137477, "learning_rate": 1.6277858356405664e-05, "loss": 0.6046, "step": 4992 }, { "epoch": 0.7114562553434027, "grad_norm": 1.2609869931463, "learning_rate": 1.6275922307223822e-05, "loss": 0.6143, "step": 4993 }, { "epoch": 0.7115987460815048, "grad_norm": 1.3168296618178774, "learning_rate": 1.627398586986206e-05, "loss": 0.6513, "step": 4994 }, { "epoch": 0.7117412368196068, "grad_norm": 1.497294189565194, "learning_rate": 1.627204904444015e-05, "loss": 0.6827, "step": 4995 }, { "epoch": 0.7118837275577088, "grad_norm": 1.7130641540887297, "learning_rate": 1.6270111831077884e-05, "loss": 0.6467, "step": 4996 }, { "epoch": 0.7120262182958108, "grad_norm": 1.3666485102322963, "learning_rate": 1.6268174229895093e-05, "loss": 0.6899, "step": 4997 }, { "epoch": 0.7121687090339128, "grad_norm": 1.4318595043284796, "learning_rate": 1.6266236241011616e-05, "loss": 0.6224, "step": 4998 }, { "epoch": 0.7123111997720148, "grad_norm": 1.4021439640894806, "learning_rate": 1.626429786454732e-05, "loss": 0.6088, "step": 4999 }, { "epoch": 0.7124536905101169, "grad_norm": 1.3886348633193124, "learning_rate": 1.6262359100622103e-05, "loss": 0.705, "step": 5000 }, { "epoch": 0.7125961812482189, "grad_norm": 1.2041022035036055, "learning_rate": 1.6260419949355875e-05, "loss": 0.5673, "step": 5001 }, { "epoch": 0.7127386719863209, "grad_norm": 1.3241086895466396, "learning_rate": 1.625848041086859e-05, "loss": 0.6861, "step": 5002 }, { "epoch": 0.7128811627244229, "grad_norm": 1.3378512734448706, "learning_rate": 1.62565404852802e-05, "loss": 0.566, "step": 5003 }, { "epoch": 0.7130236534625249, "grad_norm": 1.4370562995064293, "learning_rate": 1.6254600172710694e-05, "loss": 0.693, "step": 5004 }, { "epoch": 0.713166144200627, "grad_norm": 1.3836870673052544, "learning_rate": 1.6252659473280092e-05, "loss": 0.6696, "step": 5005 }, { "epoch": 0.713308634938729, "grad_norm": 1.5721243216353238, "learning_rate": 1.6250718387108425e-05, "loss": 0.6456, "step": 5006 }, { "epoch": 0.713451125676831, "grad_norm": 1.37655399171402, "learning_rate": 1.624877691431576e-05, "loss": 0.599, "step": 5007 }, { "epoch": 0.713593616414933, "grad_norm": 1.3523614321561261, "learning_rate": 1.6246835055022173e-05, "loss": 0.6891, "step": 5008 }, { "epoch": 0.713736107153035, "grad_norm": 1.2594582632936289, "learning_rate": 1.624489280934778e-05, "loss": 0.6293, "step": 5009 }, { "epoch": 0.7138785978911371, "grad_norm": 1.3943214099426764, "learning_rate": 1.6242950177412708e-05, "loss": 0.6717, "step": 5010 }, { "epoch": 0.7140210886292391, "grad_norm": 1.3881054538962732, "learning_rate": 1.6241007159337114e-05, "loss": 0.6976, "step": 5011 }, { "epoch": 0.7141635793673411, "grad_norm": 1.4340664316379634, "learning_rate": 1.623906375524118e-05, "loss": 0.6573, "step": 5012 }, { "epoch": 0.7143060701054431, "grad_norm": 1.3616261544191919, "learning_rate": 1.6237119965245112e-05, "loss": 0.7773, "step": 5013 }, { "epoch": 0.7144485608435451, "grad_norm": 2.0094432338318002, "learning_rate": 1.6235175789469132e-05, "loss": 0.6287, "step": 5014 }, { "epoch": 0.7145910515816472, "grad_norm": 1.2265184660910178, "learning_rate": 1.6233231228033494e-05, "loss": 0.5831, "step": 5015 }, { "epoch": 0.7147335423197492, "grad_norm": 1.3462940829157437, "learning_rate": 1.6231286281058475e-05, "loss": 0.6244, "step": 5016 }, { "epoch": 0.7148760330578512, "grad_norm": 1.2882264532654444, "learning_rate": 1.6229340948664375e-05, "loss": 0.626, "step": 5017 }, { "epoch": 0.7150185237959532, "grad_norm": 1.3256249633153672, "learning_rate": 1.6227395230971512e-05, "loss": 0.618, "step": 5018 }, { "epoch": 0.7151610145340553, "grad_norm": 1.389687323214571, "learning_rate": 1.6225449128100238e-05, "loss": 0.7231, "step": 5019 }, { "epoch": 0.7153035052721574, "grad_norm": 1.4664831631286368, "learning_rate": 1.6223502640170924e-05, "loss": 0.7153, "step": 5020 }, { "epoch": 0.7154459960102594, "grad_norm": 1.4971053665823884, "learning_rate": 1.622155576730396e-05, "loss": 0.6419, "step": 5021 }, { "epoch": 0.7155884867483614, "grad_norm": 1.420731297196482, "learning_rate": 1.621960850961977e-05, "loss": 0.7201, "step": 5022 }, { "epoch": 0.7157309774864634, "grad_norm": 1.330574140449523, "learning_rate": 1.6217660867238792e-05, "loss": 0.6777, "step": 5023 }, { "epoch": 0.7158734682245654, "grad_norm": 1.2247726725653518, "learning_rate": 1.6215712840281496e-05, "loss": 0.5895, "step": 5024 }, { "epoch": 0.7160159589626675, "grad_norm": 1.3710969869195464, "learning_rate": 1.6213764428868365e-05, "loss": 0.6128, "step": 5025 }, { "epoch": 0.7161584497007695, "grad_norm": 1.3710039117427448, "learning_rate": 1.621181563311992e-05, "loss": 0.6816, "step": 5026 }, { "epoch": 0.7163009404388715, "grad_norm": 1.4431096944666433, "learning_rate": 1.6209866453156697e-05, "loss": 0.7774, "step": 5027 }, { "epoch": 0.7164434311769735, "grad_norm": 1.5016106712580057, "learning_rate": 1.6207916889099255e-05, "loss": 0.6923, "step": 5028 }, { "epoch": 0.7165859219150755, "grad_norm": 1.469633923274841, "learning_rate": 1.6205966941068177e-05, "loss": 0.6731, "step": 5029 }, { "epoch": 0.7167284126531775, "grad_norm": 1.1951007145218144, "learning_rate": 1.620401660918408e-05, "loss": 0.5587, "step": 5030 }, { "epoch": 0.7168709033912796, "grad_norm": 1.3440560287972483, "learning_rate": 1.620206589356759e-05, "loss": 0.602, "step": 5031 }, { "epoch": 0.7170133941293816, "grad_norm": 1.292304756701229, "learning_rate": 1.6200114794339362e-05, "loss": 0.6628, "step": 5032 }, { "epoch": 0.7171558848674836, "grad_norm": 4.320711710529676, "learning_rate": 1.6198163311620076e-05, "loss": 0.6621, "step": 5033 }, { "epoch": 0.7172983756055856, "grad_norm": 1.4204282003368596, "learning_rate": 1.619621144553044e-05, "loss": 0.7182, "step": 5034 }, { "epoch": 0.7174408663436876, "grad_norm": 1.3078342795729558, "learning_rate": 1.619425919619118e-05, "loss": 0.6101, "step": 5035 }, { "epoch": 0.7175833570817897, "grad_norm": 1.3325658798585434, "learning_rate": 1.6192306563723043e-05, "loss": 0.607, "step": 5036 }, { "epoch": 0.7177258478198917, "grad_norm": 1.268197774475131, "learning_rate": 1.6190353548246806e-05, "loss": 0.7197, "step": 5037 }, { "epoch": 0.7178683385579937, "grad_norm": 1.425649467602087, "learning_rate": 1.6188400149883272e-05, "loss": 0.7458, "step": 5038 }, { "epoch": 0.7180108292960957, "grad_norm": 1.3410242440367874, "learning_rate": 1.6186446368753256e-05, "loss": 0.7143, "step": 5039 }, { "epoch": 0.7181533200341977, "grad_norm": 1.6008218974007862, "learning_rate": 1.6184492204977608e-05, "loss": 0.7148, "step": 5040 }, { "epoch": 0.7182958107722998, "grad_norm": 1.385308190596614, "learning_rate": 1.6182537658677195e-05, "loss": 0.6606, "step": 5041 }, { "epoch": 0.7184383015104018, "grad_norm": 1.582902880010839, "learning_rate": 1.6180582729972912e-05, "loss": 0.6126, "step": 5042 }, { "epoch": 0.7185807922485038, "grad_norm": 1.405174189835199, "learning_rate": 1.6178627418985676e-05, "loss": 0.674, "step": 5043 }, { "epoch": 0.7187232829866058, "grad_norm": 1.459698812295354, "learning_rate": 1.6176671725836425e-05, "loss": 0.718, "step": 5044 }, { "epoch": 0.718865773724708, "grad_norm": 1.390173484013292, "learning_rate": 1.6174715650646126e-05, "loss": 0.7571, "step": 5045 }, { "epoch": 0.71900826446281, "grad_norm": 1.3425426972076302, "learning_rate": 1.6172759193535763e-05, "loss": 0.7055, "step": 5046 }, { "epoch": 0.719150755200912, "grad_norm": 1.3395348520147539, "learning_rate": 1.6170802354626352e-05, "loss": 0.571, "step": 5047 }, { "epoch": 0.719293245939014, "grad_norm": 1.2724662744880137, "learning_rate": 1.6168845134038925e-05, "loss": 0.689, "step": 5048 }, { "epoch": 0.719435736677116, "grad_norm": 1.3245664120574698, "learning_rate": 1.616688753189454e-05, "loss": 0.6716, "step": 5049 }, { "epoch": 0.719578227415218, "grad_norm": 1.31022236874848, "learning_rate": 1.6164929548314277e-05, "loss": 0.5776, "step": 5050 }, { "epoch": 0.7197207181533201, "grad_norm": 1.6942581258996765, "learning_rate": 1.616297118341925e-05, "loss": 0.7499, "step": 5051 }, { "epoch": 0.7198632088914221, "grad_norm": 1.3412330830035535, "learning_rate": 1.6161012437330578e-05, "loss": 0.701, "step": 5052 }, { "epoch": 0.7200056996295241, "grad_norm": 1.2365401357325487, "learning_rate": 1.6159053310169422e-05, "loss": 0.7101, "step": 5053 }, { "epoch": 0.7201481903676261, "grad_norm": 1.1899483009852903, "learning_rate": 1.6157093802056954e-05, "loss": 0.6639, "step": 5054 }, { "epoch": 0.7202906811057281, "grad_norm": 1.458403289443967, "learning_rate": 1.6155133913114376e-05, "loss": 0.6115, "step": 5055 }, { "epoch": 0.7204331718438302, "grad_norm": 1.4647048978125008, "learning_rate": 1.6153173643462906e-05, "loss": 0.7187, "step": 5056 }, { "epoch": 0.7205756625819322, "grad_norm": 1.2751063861790712, "learning_rate": 1.6151212993223802e-05, "loss": 0.5932, "step": 5057 }, { "epoch": 0.7207181533200342, "grad_norm": 1.303458537002391, "learning_rate": 1.6149251962518328e-05, "loss": 0.6424, "step": 5058 }, { "epoch": 0.7208606440581362, "grad_norm": 1.2757086181845188, "learning_rate": 1.6147290551467776e-05, "loss": 0.6437, "step": 5059 }, { "epoch": 0.7210031347962382, "grad_norm": 1.2547733407279773, "learning_rate": 1.6145328760193465e-05, "loss": 0.6712, "step": 5060 }, { "epoch": 0.7211456255343403, "grad_norm": 1.3003118367414, "learning_rate": 1.614336658881674e-05, "loss": 0.6933, "step": 5061 }, { "epoch": 0.7212881162724423, "grad_norm": 1.6364072412009825, "learning_rate": 1.614140403745896e-05, "loss": 0.7212, "step": 5062 }, { "epoch": 0.7214306070105443, "grad_norm": 1.4726826178337398, "learning_rate": 1.613944110624152e-05, "loss": 0.6367, "step": 5063 }, { "epoch": 0.7215730977486463, "grad_norm": 1.3282612492336632, "learning_rate": 1.6137477795285827e-05, "loss": 0.6981, "step": 5064 }, { "epoch": 0.7217155884867483, "grad_norm": 1.4355238929537508, "learning_rate": 1.613551410471332e-05, "loss": 0.7044, "step": 5065 }, { "epoch": 0.7218580792248503, "grad_norm": 1.3445129197859975, "learning_rate": 1.613355003464545e-05, "loss": 0.6469, "step": 5066 }, { "epoch": 0.7220005699629524, "grad_norm": 1.2873951242180157, "learning_rate": 1.613158558520371e-05, "loss": 0.645, "step": 5067 }, { "epoch": 0.7221430607010544, "grad_norm": 1.3678142194031435, "learning_rate": 1.6129620756509595e-05, "loss": 0.7398, "step": 5068 }, { "epoch": 0.7222855514391564, "grad_norm": 1.3227738362180976, "learning_rate": 1.6127655548684638e-05, "loss": 0.7191, "step": 5069 }, { "epoch": 0.7224280421772585, "grad_norm": 1.265078706370121, "learning_rate": 1.6125689961850395e-05, "loss": 0.5823, "step": 5070 }, { "epoch": 0.7225705329153606, "grad_norm": 1.373587641698007, "learning_rate": 1.6123723996128434e-05, "loss": 0.6761, "step": 5071 }, { "epoch": 0.7227130236534626, "grad_norm": 1.2777554374140927, "learning_rate": 1.6121757651640367e-05, "loss": 0.6012, "step": 5072 }, { "epoch": 0.7228555143915646, "grad_norm": 1.2546015850555656, "learning_rate": 1.6119790928507807e-05, "loss": 0.7096, "step": 5073 }, { "epoch": 0.7229980051296666, "grad_norm": 1.3809505480000623, "learning_rate": 1.6117823826852404e-05, "loss": 0.6856, "step": 5074 }, { "epoch": 0.7231404958677686, "grad_norm": 1.4141763619248604, "learning_rate": 1.6115856346795826e-05, "loss": 0.7009, "step": 5075 }, { "epoch": 0.7232829866058706, "grad_norm": 1.229731343502414, "learning_rate": 1.6113888488459762e-05, "loss": 0.6516, "step": 5076 }, { "epoch": 0.7234254773439727, "grad_norm": 1.4420457447641002, "learning_rate": 1.6111920251965937e-05, "loss": 0.7805, "step": 5077 }, { "epoch": 0.7235679680820747, "grad_norm": 1.463421816513306, "learning_rate": 1.6109951637436087e-05, "loss": 0.7036, "step": 5078 }, { "epoch": 0.7237104588201767, "grad_norm": 1.237379100574499, "learning_rate": 1.6107982644991974e-05, "loss": 0.6093, "step": 5079 }, { "epoch": 0.7238529495582787, "grad_norm": 1.2722585629716605, "learning_rate": 1.6106013274755387e-05, "loss": 0.7175, "step": 5080 }, { "epoch": 0.7239954402963807, "grad_norm": 1.3466246722286772, "learning_rate": 1.6104043526848135e-05, "loss": 0.7133, "step": 5081 }, { "epoch": 0.7241379310344828, "grad_norm": 1.33509167517428, "learning_rate": 1.6102073401392053e-05, "loss": 0.6064, "step": 5082 }, { "epoch": 0.7242804217725848, "grad_norm": 1.384193719978562, "learning_rate": 1.610010289850899e-05, "loss": 0.6566, "step": 5083 }, { "epoch": 0.7244229125106868, "grad_norm": 1.2996343296763682, "learning_rate": 1.6098132018320837e-05, "loss": 0.5992, "step": 5084 }, { "epoch": 0.7245654032487888, "grad_norm": 1.4175910965733818, "learning_rate": 1.6096160760949488e-05, "loss": 0.7216, "step": 5085 }, { "epoch": 0.7247078939868908, "grad_norm": 1.3187231954529934, "learning_rate": 1.609418912651688e-05, "loss": 0.6755, "step": 5086 }, { "epoch": 0.7248503847249929, "grad_norm": 1.4738320276739874, "learning_rate": 1.609221711514495e-05, "loss": 0.6823, "step": 5087 }, { "epoch": 0.7249928754630949, "grad_norm": 1.3044366840411517, "learning_rate": 1.609024472695568e-05, "loss": 0.6348, "step": 5088 }, { "epoch": 0.7251353662011969, "grad_norm": 1.2433150014187195, "learning_rate": 1.6088271962071067e-05, "loss": 0.6612, "step": 5089 }, { "epoch": 0.7252778569392989, "grad_norm": 1.4781706225143074, "learning_rate": 1.6086298820613126e-05, "loss": 0.7137, "step": 5090 }, { "epoch": 0.7254203476774009, "grad_norm": 1.3635171964981405, "learning_rate": 1.6084325302703906e-05, "loss": 0.6442, "step": 5091 }, { "epoch": 0.725562838415503, "grad_norm": 1.3824522790028455, "learning_rate": 1.608235140846547e-05, "loss": 0.6683, "step": 5092 }, { "epoch": 0.725705329153605, "grad_norm": 1.5810395389901215, "learning_rate": 1.608037713801991e-05, "loss": 0.667, "step": 5093 }, { "epoch": 0.725847819891707, "grad_norm": 1.3854640622409433, "learning_rate": 1.6078402491489333e-05, "loss": 0.6868, "step": 5094 }, { "epoch": 0.725990310629809, "grad_norm": 1.3920051060677243, "learning_rate": 1.6076427468995883e-05, "loss": 0.7485, "step": 5095 }, { "epoch": 0.7261328013679111, "grad_norm": 1.3566444093008958, "learning_rate": 1.6074452070661713e-05, "loss": 0.7038, "step": 5096 }, { "epoch": 0.7262752921060132, "grad_norm": 1.2988665369845218, "learning_rate": 1.6072476296609014e-05, "loss": 0.7191, "step": 5097 }, { "epoch": 0.7264177828441152, "grad_norm": 1.6488849385157718, "learning_rate": 1.6070500146959984e-05, "loss": 0.6961, "step": 5098 }, { "epoch": 0.7265602735822172, "grad_norm": 1.2737083632149513, "learning_rate": 1.6068523621836858e-05, "loss": 0.6324, "step": 5099 }, { "epoch": 0.7267027643203192, "grad_norm": 1.3740564074362287, "learning_rate": 1.6066546721361883e-05, "loss": 0.6733, "step": 5100 }, { "epoch": 0.7268452550584212, "grad_norm": 1.406218895883104, "learning_rate": 1.606456944565734e-05, "loss": 0.6364, "step": 5101 }, { "epoch": 0.7269877457965233, "grad_norm": 1.5166741042508007, "learning_rate": 1.606259179484553e-05, "loss": 0.6303, "step": 5102 }, { "epoch": 0.7271302365346253, "grad_norm": 1.5550768787697782, "learning_rate": 1.6060613769048764e-05, "loss": 0.6408, "step": 5103 }, { "epoch": 0.7272727272727273, "grad_norm": 1.817494237916051, "learning_rate": 1.6058635368389396e-05, "loss": 0.6342, "step": 5104 }, { "epoch": 0.7274152180108293, "grad_norm": 1.350782923785179, "learning_rate": 1.6056656592989794e-05, "loss": 0.6831, "step": 5105 }, { "epoch": 0.7275577087489313, "grad_norm": 1.3182879158753238, "learning_rate": 1.6054677442972347e-05, "loss": 0.6325, "step": 5106 }, { "epoch": 0.7277001994870334, "grad_norm": 1.2881219797315424, "learning_rate": 1.6052697918459473e-05, "loss": 0.6346, "step": 5107 }, { "epoch": 0.7278426902251354, "grad_norm": 1.3075604629713156, "learning_rate": 1.605071801957361e-05, "loss": 0.623, "step": 5108 }, { "epoch": 0.7279851809632374, "grad_norm": 1.3450516286366823, "learning_rate": 1.6048737746437216e-05, "loss": 0.6776, "step": 5109 }, { "epoch": 0.7281276717013394, "grad_norm": 1.4012597735100347, "learning_rate": 1.604675709917278e-05, "loss": 0.677, "step": 5110 }, { "epoch": 0.7282701624394414, "grad_norm": 1.4030850337005503, "learning_rate": 1.6044776077902803e-05, "loss": 0.7244, "step": 5111 }, { "epoch": 0.7284126531775434, "grad_norm": 1.3191564133615306, "learning_rate": 1.6042794682749818e-05, "loss": 0.7301, "step": 5112 }, { "epoch": 0.7285551439156455, "grad_norm": 1.3239176713325023, "learning_rate": 1.6040812913836383e-05, "loss": 0.6794, "step": 5113 }, { "epoch": 0.7286976346537475, "grad_norm": 1.3840919984763338, "learning_rate": 1.603883077128507e-05, "loss": 0.6903, "step": 5114 }, { "epoch": 0.7288401253918495, "grad_norm": 1.3848883312653013, "learning_rate": 1.603684825521848e-05, "loss": 0.6229, "step": 5115 }, { "epoch": 0.7289826161299515, "grad_norm": 1.3422097481042683, "learning_rate": 1.603486536575924e-05, "loss": 0.7158, "step": 5116 }, { "epoch": 0.7291251068680535, "grad_norm": 1.6426844006253263, "learning_rate": 1.6032882103029992e-05, "loss": 0.5514, "step": 5117 }, { "epoch": 0.7292675976061556, "grad_norm": 1.2421092494131514, "learning_rate": 1.6030898467153402e-05, "loss": 0.7287, "step": 5118 }, { "epoch": 0.7294100883442576, "grad_norm": 1.3450001224380594, "learning_rate": 1.6028914458252173e-05, "loss": 0.5279, "step": 5119 }, { "epoch": 0.7295525790823596, "grad_norm": 1.4209141306174264, "learning_rate": 1.6026930076449012e-05, "loss": 0.6722, "step": 5120 }, { "epoch": 0.7296950698204616, "grad_norm": 1.2819135000077855, "learning_rate": 1.6024945321866655e-05, "loss": 0.5804, "step": 5121 }, { "epoch": 0.7298375605585637, "grad_norm": 1.367245803828497, "learning_rate": 1.6022960194627876e-05, "loss": 0.6554, "step": 5122 }, { "epoch": 0.7299800512966658, "grad_norm": 1.2644866141791982, "learning_rate": 1.6020974694855445e-05, "loss": 0.6204, "step": 5123 }, { "epoch": 0.7301225420347678, "grad_norm": 1.3653254318998143, "learning_rate": 1.6018988822672182e-05, "loss": 0.6417, "step": 5124 }, { "epoch": 0.7302650327728698, "grad_norm": 1.233482674021854, "learning_rate": 1.601700257820091e-05, "loss": 0.5738, "step": 5125 }, { "epoch": 0.7304075235109718, "grad_norm": 1.3550591959334115, "learning_rate": 1.6015015961564483e-05, "loss": 0.7156, "step": 5126 }, { "epoch": 0.7305500142490738, "grad_norm": 1.4468317235890178, "learning_rate": 1.6013028972885777e-05, "loss": 0.6321, "step": 5127 }, { "epoch": 0.7306925049871759, "grad_norm": 1.349460045038505, "learning_rate": 1.60110416122877e-05, "loss": 0.7312, "step": 5128 }, { "epoch": 0.7308349957252779, "grad_norm": 1.3273033594375752, "learning_rate": 1.6009053879893164e-05, "loss": 0.6691, "step": 5129 }, { "epoch": 0.7309774864633799, "grad_norm": 1.5141201155066273, "learning_rate": 1.6007065775825122e-05, "loss": 0.7039, "step": 5130 }, { "epoch": 0.7311199772014819, "grad_norm": 1.455060479765802, "learning_rate": 1.600507730020654e-05, "loss": 0.725, "step": 5131 }, { "epoch": 0.7312624679395839, "grad_norm": 1.3740165177657178, "learning_rate": 1.600308845316041e-05, "loss": 0.6773, "step": 5132 }, { "epoch": 0.731404958677686, "grad_norm": 1.4207728594717297, "learning_rate": 1.6001099234809746e-05, "loss": 0.5675, "step": 5133 }, { "epoch": 0.731547449415788, "grad_norm": 1.4305215715242452, "learning_rate": 1.5999109645277585e-05, "loss": 0.677, "step": 5134 }, { "epoch": 0.73168994015389, "grad_norm": 1.1960603012724866, "learning_rate": 1.5997119684686992e-05, "loss": 0.6773, "step": 5135 }, { "epoch": 0.731832430891992, "grad_norm": 1.4397620446561465, "learning_rate": 1.5995129353161044e-05, "loss": 0.6672, "step": 5136 }, { "epoch": 0.731974921630094, "grad_norm": 1.4494140263171598, "learning_rate": 1.5993138650822856e-05, "loss": 0.7216, "step": 5137 }, { "epoch": 0.732117412368196, "grad_norm": 1.406272152317825, "learning_rate": 1.5991147577795545e-05, "loss": 0.6698, "step": 5138 }, { "epoch": 0.7322599031062981, "grad_norm": 1.4914168830523316, "learning_rate": 1.5989156134202276e-05, "loss": 0.636, "step": 5139 }, { "epoch": 0.7324023938444001, "grad_norm": 1.257143308548846, "learning_rate": 1.5987164320166216e-05, "loss": 0.6225, "step": 5140 }, { "epoch": 0.7325448845825021, "grad_norm": 1.388181293234277, "learning_rate": 1.598517213581057e-05, "loss": 0.6318, "step": 5141 }, { "epoch": 0.7326873753206041, "grad_norm": 1.356436484000262, "learning_rate": 1.598317958125855e-05, "loss": 0.6673, "step": 5142 }, { "epoch": 0.7328298660587061, "grad_norm": 1.4349128086729335, "learning_rate": 1.598118665663341e-05, "loss": 0.6919, "step": 5143 }, { "epoch": 0.7329723567968082, "grad_norm": 1.3854758327566767, "learning_rate": 1.597919336205841e-05, "loss": 0.6719, "step": 5144 }, { "epoch": 0.7331148475349102, "grad_norm": 1.3154842639482789, "learning_rate": 1.597719969765684e-05, "loss": 0.6564, "step": 5145 }, { "epoch": 0.7332573382730122, "grad_norm": 1.3715086001971142, "learning_rate": 1.5975205663552017e-05, "loss": 0.6535, "step": 5146 }, { "epoch": 0.7333998290111142, "grad_norm": 1.551700288946118, "learning_rate": 1.5973211259867274e-05, "loss": 0.5896, "step": 5147 }, { "epoch": 0.7335423197492164, "grad_norm": 1.4044144131175735, "learning_rate": 1.5971216486725966e-05, "loss": 0.6468, "step": 5148 }, { "epoch": 0.7336848104873184, "grad_norm": 1.1618996518700067, "learning_rate": 1.596922134425148e-05, "loss": 0.6422, "step": 5149 }, { "epoch": 0.7338273012254204, "grad_norm": 1.1887599566343188, "learning_rate": 1.596722583256722e-05, "loss": 0.6024, "step": 5150 }, { "epoch": 0.7339697919635224, "grad_norm": 1.3581353558011184, "learning_rate": 1.5965229951796605e-05, "loss": 0.6451, "step": 5151 }, { "epoch": 0.7341122827016244, "grad_norm": 1.2255727274350858, "learning_rate": 1.5963233702063092e-05, "loss": 0.6124, "step": 5152 }, { "epoch": 0.7342547734397264, "grad_norm": 1.7273616961446014, "learning_rate": 1.5961237083490154e-05, "loss": 0.6322, "step": 5153 }, { "epoch": 0.7343972641778285, "grad_norm": 1.3547751467660123, "learning_rate": 1.5959240096201283e-05, "loss": 0.5937, "step": 5154 }, { "epoch": 0.7345397549159305, "grad_norm": 2.0552484494310566, "learning_rate": 1.5957242740319995e-05, "loss": 0.6744, "step": 5155 }, { "epoch": 0.7346822456540325, "grad_norm": 1.1655853992047265, "learning_rate": 1.595524501596984e-05, "loss": 0.5638, "step": 5156 }, { "epoch": 0.7348247363921345, "grad_norm": 1.2900299898230032, "learning_rate": 1.595324692327437e-05, "loss": 0.6127, "step": 5157 }, { "epoch": 0.7349672271302365, "grad_norm": 1.381437375730542, "learning_rate": 1.595124846235718e-05, "loss": 0.6773, "step": 5158 }, { "epoch": 0.7351097178683386, "grad_norm": 1.3180958712544146, "learning_rate": 1.594924963334188e-05, "loss": 0.5903, "step": 5159 }, { "epoch": 0.7352522086064406, "grad_norm": 1.3381562990207274, "learning_rate": 1.5947250436352095e-05, "loss": 0.6505, "step": 5160 }, { "epoch": 0.7353946993445426, "grad_norm": 1.3125400859549994, "learning_rate": 1.5945250871511482e-05, "loss": 0.6086, "step": 5161 }, { "epoch": 0.7355371900826446, "grad_norm": 1.5073877502202422, "learning_rate": 1.5943250938943723e-05, "loss": 0.6787, "step": 5162 }, { "epoch": 0.7356796808207466, "grad_norm": 1.4678648825315632, "learning_rate": 1.5941250638772515e-05, "loss": 0.7094, "step": 5163 }, { "epoch": 0.7358221715588487, "grad_norm": 1.3709639975744419, "learning_rate": 1.5939249971121582e-05, "loss": 0.6516, "step": 5164 }, { "epoch": 0.7359646622969507, "grad_norm": 1.4283104102474142, "learning_rate": 1.5937248936114672e-05, "loss": 0.7242, "step": 5165 }, { "epoch": 0.7361071530350527, "grad_norm": 1.3556249809768406, "learning_rate": 1.5935247533875547e-05, "loss": 0.6145, "step": 5166 }, { "epoch": 0.7362496437731547, "grad_norm": 1.3090934889170867, "learning_rate": 1.5933245764528003e-05, "loss": 0.628, "step": 5167 }, { "epoch": 0.7363921345112567, "grad_norm": 1.2617626388125358, "learning_rate": 1.593124362819585e-05, "loss": 0.5257, "step": 5168 }, { "epoch": 0.7365346252493588, "grad_norm": 1.312797877426853, "learning_rate": 1.5929241125002936e-05, "loss": 0.5913, "step": 5169 }, { "epoch": 0.7366771159874608, "grad_norm": 1.2751971023499802, "learning_rate": 1.5927238255073106e-05, "loss": 0.6511, "step": 5170 }, { "epoch": 0.7368196067255628, "grad_norm": 1.627680034963339, "learning_rate": 1.592523501853025e-05, "loss": 0.686, "step": 5171 }, { "epoch": 0.7369620974636648, "grad_norm": 1.3650484322969108, "learning_rate": 1.5923231415498272e-05, "loss": 0.5609, "step": 5172 }, { "epoch": 0.7371045882017668, "grad_norm": 1.457688023229009, "learning_rate": 1.5921227446101092e-05, "loss": 0.6962, "step": 5173 }, { "epoch": 0.737247078939869, "grad_norm": 1.3428598843672752, "learning_rate": 1.5919223110462672e-05, "loss": 0.6628, "step": 5174 }, { "epoch": 0.737389569677971, "grad_norm": 1.2599211564086452, "learning_rate": 1.5917218408706977e-05, "loss": 0.5861, "step": 5175 }, { "epoch": 0.737532060416073, "grad_norm": 1.4221285226693974, "learning_rate": 1.5915213340958007e-05, "loss": 0.7009, "step": 5176 }, { "epoch": 0.737674551154175, "grad_norm": 1.3490337452932477, "learning_rate": 1.5913207907339773e-05, "loss": 0.6751, "step": 5177 }, { "epoch": 0.737817041892277, "grad_norm": 1.3593412963645033, "learning_rate": 1.591120210797632e-05, "loss": 0.6043, "step": 5178 }, { "epoch": 0.7379595326303791, "grad_norm": 1.3563765049543697, "learning_rate": 1.5909195942991714e-05, "loss": 0.702, "step": 5179 }, { "epoch": 0.7381020233684811, "grad_norm": 1.454542403437135, "learning_rate": 1.5907189412510035e-05, "loss": 0.594, "step": 5180 }, { "epoch": 0.7382445141065831, "grad_norm": 1.325772198526185, "learning_rate": 1.5905182516655395e-05, "loss": 0.6435, "step": 5181 }, { "epoch": 0.7383870048446851, "grad_norm": 1.518715649888741, "learning_rate": 1.5903175255551923e-05, "loss": 0.5659, "step": 5182 }, { "epoch": 0.7385294955827871, "grad_norm": 1.5404278048129443, "learning_rate": 1.5901167629323775e-05, "loss": 0.6767, "step": 5183 }, { "epoch": 0.7386719863208892, "grad_norm": 1.4804678404385694, "learning_rate": 1.5899159638095127e-05, "loss": 0.6878, "step": 5184 }, { "epoch": 0.7388144770589912, "grad_norm": 1.3726241594198312, "learning_rate": 1.5897151281990174e-05, "loss": 0.6438, "step": 5185 }, { "epoch": 0.7389569677970932, "grad_norm": 1.3958423870244039, "learning_rate": 1.5895142561133142e-05, "loss": 0.6894, "step": 5186 }, { "epoch": 0.7390994585351952, "grad_norm": 1.3693325584759568, "learning_rate": 1.5893133475648274e-05, "loss": 0.6247, "step": 5187 }, { "epoch": 0.7392419492732972, "grad_norm": 1.3086147219053084, "learning_rate": 1.5891124025659833e-05, "loss": 0.6816, "step": 5188 }, { "epoch": 0.7393844400113992, "grad_norm": 1.3764280168543581, "learning_rate": 1.5889114211292113e-05, "loss": 0.6446, "step": 5189 }, { "epoch": 0.7395269307495013, "grad_norm": 1.3162888067812104, "learning_rate": 1.588710403266942e-05, "loss": 0.6962, "step": 5190 }, { "epoch": 0.7396694214876033, "grad_norm": 1.2792504938753715, "learning_rate": 1.5885093489916093e-05, "loss": 0.6969, "step": 5191 }, { "epoch": 0.7398119122257053, "grad_norm": 1.3257331375101649, "learning_rate": 1.588308258315649e-05, "loss": 0.5616, "step": 5192 }, { "epoch": 0.7399544029638073, "grad_norm": 1.4595768405366023, "learning_rate": 1.588107131251498e-05, "loss": 0.598, "step": 5193 }, { "epoch": 0.7400968937019093, "grad_norm": 1.3174241888887839, "learning_rate": 1.5879059678115976e-05, "loss": 0.696, "step": 5194 }, { "epoch": 0.7402393844400114, "grad_norm": 1.3918351844711718, "learning_rate": 1.5877047680083894e-05, "loss": 0.6802, "step": 5195 }, { "epoch": 0.7403818751781134, "grad_norm": 1.4002690745272446, "learning_rate": 1.5875035318543188e-05, "loss": 0.6439, "step": 5196 }, { "epoch": 0.7405243659162154, "grad_norm": 1.1664340580048942, "learning_rate": 1.5873022593618323e-05, "loss": 0.6573, "step": 5197 }, { "epoch": 0.7406668566543174, "grad_norm": 1.2689613426697348, "learning_rate": 1.587100950543379e-05, "loss": 0.7256, "step": 5198 }, { "epoch": 0.7408093473924195, "grad_norm": 1.56502476115584, "learning_rate": 1.58689960541141e-05, "loss": 0.6137, "step": 5199 }, { "epoch": 0.7409518381305216, "grad_norm": 1.3909332713449503, "learning_rate": 1.5866982239783796e-05, "loss": 0.6642, "step": 5200 }, { "epoch": 0.7410943288686236, "grad_norm": 1.4025819847059888, "learning_rate": 1.5864968062567438e-05, "loss": 0.673, "step": 5201 }, { "epoch": 0.7412368196067256, "grad_norm": 1.9586180560572728, "learning_rate": 1.5862953522589603e-05, "loss": 0.6526, "step": 5202 }, { "epoch": 0.7413793103448276, "grad_norm": 1.3207989577125938, "learning_rate": 1.586093861997489e-05, "loss": 0.6267, "step": 5203 }, { "epoch": 0.7415218010829296, "grad_norm": 1.3882235806660483, "learning_rate": 1.5858923354847934e-05, "loss": 0.6137, "step": 5204 }, { "epoch": 0.7416642918210317, "grad_norm": 1.8100977423230662, "learning_rate": 1.5856907727333378e-05, "loss": 0.6769, "step": 5205 }, { "epoch": 0.7418067825591337, "grad_norm": 1.4274619894032254, "learning_rate": 1.58548917375559e-05, "loss": 0.6252, "step": 5206 }, { "epoch": 0.7419492732972357, "grad_norm": 1.5692392651090006, "learning_rate": 1.5852875385640186e-05, "loss": 0.6918, "step": 5207 }, { "epoch": 0.7420917640353377, "grad_norm": 2.09307806201612, "learning_rate": 1.5850858671710957e-05, "loss": 0.6135, "step": 5208 }, { "epoch": 0.7422342547734397, "grad_norm": 1.6077506953804694, "learning_rate": 1.584884159589295e-05, "loss": 0.7351, "step": 5209 }, { "epoch": 0.7423767455115418, "grad_norm": 1.4007529095893327, "learning_rate": 1.584682415831092e-05, "loss": 0.6218, "step": 5210 }, { "epoch": 0.7425192362496438, "grad_norm": 1.3509077714640663, "learning_rate": 1.5844806359089658e-05, "loss": 0.6842, "step": 5211 }, { "epoch": 0.7426617269877458, "grad_norm": 2.0521293337565, "learning_rate": 1.5842788198353968e-05, "loss": 0.6642, "step": 5212 }, { "epoch": 0.7428042177258478, "grad_norm": 1.3555711873313383, "learning_rate": 1.5840769676228673e-05, "loss": 0.6887, "step": 5213 }, { "epoch": 0.7429467084639498, "grad_norm": 1.350161814127973, "learning_rate": 1.5838750792838632e-05, "loss": 0.6009, "step": 5214 }, { "epoch": 0.7430891992020519, "grad_norm": 1.530694530012738, "learning_rate": 1.5836731548308705e-05, "loss": 0.6693, "step": 5215 }, { "epoch": 0.7432316899401539, "grad_norm": 1.2763005248680044, "learning_rate": 1.5834711942763794e-05, "loss": 0.6561, "step": 5216 }, { "epoch": 0.7433741806782559, "grad_norm": 1.4429839402739497, "learning_rate": 1.583269197632882e-05, "loss": 0.6709, "step": 5217 }, { "epoch": 0.7435166714163579, "grad_norm": 1.3155549063935124, "learning_rate": 1.583067164912872e-05, "loss": 0.6915, "step": 5218 }, { "epoch": 0.7436591621544599, "grad_norm": 1.23643997563239, "learning_rate": 1.582865096128845e-05, "loss": 0.5655, "step": 5219 }, { "epoch": 0.743801652892562, "grad_norm": 1.3636070694269384, "learning_rate": 1.5826629912932996e-05, "loss": 0.6928, "step": 5220 }, { "epoch": 0.743944143630664, "grad_norm": 1.2550498347229664, "learning_rate": 1.5824608504187373e-05, "loss": 0.6189, "step": 5221 }, { "epoch": 0.744086634368766, "grad_norm": 1.4467999758354153, "learning_rate": 1.5822586735176593e-05, "loss": 0.6494, "step": 5222 }, { "epoch": 0.744229125106868, "grad_norm": 1.3813090164148303, "learning_rate": 1.5820564606025725e-05, "loss": 0.7082, "step": 5223 }, { "epoch": 0.74437161584497, "grad_norm": 1.268736370468674, "learning_rate": 1.5818542116859833e-05, "loss": 0.7105, "step": 5224 }, { "epoch": 0.7445141065830722, "grad_norm": 1.4758055021400829, "learning_rate": 1.5816519267804014e-05, "loss": 0.6581, "step": 5225 }, { "epoch": 0.7446565973211742, "grad_norm": 1.3059446375448924, "learning_rate": 1.5814496058983385e-05, "loss": 0.6899, "step": 5226 }, { "epoch": 0.7447990880592762, "grad_norm": 1.5031674401327406, "learning_rate": 1.581247249052309e-05, "loss": 0.5829, "step": 5227 }, { "epoch": 0.7449415787973782, "grad_norm": 1.20290203530333, "learning_rate": 1.5810448562548284e-05, "loss": 0.6074, "step": 5228 }, { "epoch": 0.7450840695354802, "grad_norm": 1.8144083601597947, "learning_rate": 1.5808424275184157e-05, "loss": 0.6819, "step": 5229 }, { "epoch": 0.7452265602735823, "grad_norm": 1.3246821913796873, "learning_rate": 1.5806399628555912e-05, "loss": 0.6595, "step": 5230 }, { "epoch": 0.7453690510116843, "grad_norm": 1.378087299082483, "learning_rate": 1.5804374622788784e-05, "loss": 0.7517, "step": 5231 }, { "epoch": 0.7455115417497863, "grad_norm": 1.4007567332701252, "learning_rate": 1.5802349258008018e-05, "loss": 0.6834, "step": 5232 }, { "epoch": 0.7456540324878883, "grad_norm": 1.3807901919424304, "learning_rate": 1.580032353433889e-05, "loss": 0.6882, "step": 5233 }, { "epoch": 0.7457965232259903, "grad_norm": 1.3106692001290747, "learning_rate": 1.5798297451906693e-05, "loss": 0.7193, "step": 5234 }, { "epoch": 0.7459390139640923, "grad_norm": 1.2594198917390886, "learning_rate": 1.5796271010836754e-05, "loss": 0.659, "step": 5235 }, { "epoch": 0.7460815047021944, "grad_norm": 1.6394692060487703, "learning_rate": 1.57942442112544e-05, "loss": 0.6527, "step": 5236 }, { "epoch": 0.7462239954402964, "grad_norm": 1.742153420359013, "learning_rate": 1.5792217053284997e-05, "loss": 0.7038, "step": 5237 }, { "epoch": 0.7463664861783984, "grad_norm": 1.3501047137998383, "learning_rate": 1.5790189537053935e-05, "loss": 0.6478, "step": 5238 }, { "epoch": 0.7465089769165004, "grad_norm": 1.2545355203313477, "learning_rate": 1.578816166268662e-05, "loss": 0.5671, "step": 5239 }, { "epoch": 0.7466514676546024, "grad_norm": 1.4230120662141346, "learning_rate": 1.5786133430308473e-05, "loss": 0.7042, "step": 5240 }, { "epoch": 0.7467939583927045, "grad_norm": 1.5148578031959836, "learning_rate": 1.578410484004495e-05, "loss": 0.6254, "step": 5241 }, { "epoch": 0.7469364491308065, "grad_norm": 1.4292217460143062, "learning_rate": 1.578207589202152e-05, "loss": 0.6811, "step": 5242 }, { "epoch": 0.7470789398689085, "grad_norm": 1.292367535685714, "learning_rate": 1.5780046586363688e-05, "loss": 0.7249, "step": 5243 }, { "epoch": 0.7472214306070105, "grad_norm": 1.5638900233224726, "learning_rate": 1.5778016923196958e-05, "loss": 0.6658, "step": 5244 }, { "epoch": 0.7473639213451125, "grad_norm": 1.3856582608823582, "learning_rate": 1.577598690264688e-05, "loss": 0.6768, "step": 5245 }, { "epoch": 0.7475064120832146, "grad_norm": 1.2502936183068558, "learning_rate": 1.5773956524839003e-05, "loss": 0.5232, "step": 5246 }, { "epoch": 0.7476489028213166, "grad_norm": 1.2560053682592545, "learning_rate": 1.5771925789898924e-05, "loss": 0.6538, "step": 5247 }, { "epoch": 0.7477913935594186, "grad_norm": 1.3213573053173044, "learning_rate": 1.5769894697952245e-05, "loss": 0.6498, "step": 5248 }, { "epoch": 0.7479338842975206, "grad_norm": 1.453737282150072, "learning_rate": 1.5767863249124588e-05, "loss": 0.6594, "step": 5249 }, { "epoch": 0.7480763750356226, "grad_norm": 1.2854949420945536, "learning_rate": 1.5765831443541605e-05, "loss": 0.7065, "step": 5250 }, { "epoch": 0.7482188657737248, "grad_norm": 1.4039117457053836, "learning_rate": 1.576379928132897e-05, "loss": 0.7363, "step": 5251 }, { "epoch": 0.7483613565118268, "grad_norm": 1.310190710757942, "learning_rate": 1.5761766762612378e-05, "loss": 0.6005, "step": 5252 }, { "epoch": 0.7485038472499288, "grad_norm": 1.2857003393728006, "learning_rate": 1.5759733887517535e-05, "loss": 0.6571, "step": 5253 }, { "epoch": 0.7486463379880308, "grad_norm": 1.3257794285863882, "learning_rate": 1.5757700656170193e-05, "loss": 0.6236, "step": 5254 }, { "epoch": 0.7487888287261328, "grad_norm": 1.3188985926595842, "learning_rate": 1.5755667068696102e-05, "loss": 0.6794, "step": 5255 }, { "epoch": 0.7489313194642349, "grad_norm": 1.5047738140502156, "learning_rate": 1.575363312522105e-05, "loss": 0.6245, "step": 5256 }, { "epoch": 0.7490738102023369, "grad_norm": 1.4175460909106414, "learning_rate": 1.5751598825870837e-05, "loss": 0.6587, "step": 5257 }, { "epoch": 0.7492163009404389, "grad_norm": 1.5378636915038182, "learning_rate": 1.574956417077129e-05, "loss": 0.6932, "step": 5258 }, { "epoch": 0.7493587916785409, "grad_norm": 1.3628623331650407, "learning_rate": 1.5747529160048255e-05, "loss": 0.6529, "step": 5259 }, { "epoch": 0.7495012824166429, "grad_norm": 1.3681772584861205, "learning_rate": 1.5745493793827607e-05, "loss": 0.6129, "step": 5260 }, { "epoch": 0.749643773154745, "grad_norm": 1.3819442677385372, "learning_rate": 1.5743458072235235e-05, "loss": 0.6352, "step": 5261 }, { "epoch": 0.749786263892847, "grad_norm": 1.3483614065860987, "learning_rate": 1.5741421995397052e-05, "loss": 0.7096, "step": 5262 }, { "epoch": 0.749928754630949, "grad_norm": 1.2813463716686848, "learning_rate": 1.5739385563438994e-05, "loss": 0.6356, "step": 5263 }, { "epoch": 0.750071245369051, "grad_norm": 1.287893040967372, "learning_rate": 1.5737348776487023e-05, "loss": 0.6237, "step": 5264 }, { "epoch": 0.750213736107153, "grad_norm": 1.2288791908242003, "learning_rate": 1.5735311634667115e-05, "loss": 0.6621, "step": 5265 }, { "epoch": 0.750356226845255, "grad_norm": 1.3323668313609616, "learning_rate": 1.573327413810527e-05, "loss": 0.6555, "step": 5266 }, { "epoch": 0.7504987175833571, "grad_norm": 1.5156762556132213, "learning_rate": 1.5731236286927516e-05, "loss": 0.6039, "step": 5267 }, { "epoch": 0.7506412083214591, "grad_norm": 1.285870729669784, "learning_rate": 1.5729198081259895e-05, "loss": 0.695, "step": 5268 }, { "epoch": 0.7507836990595611, "grad_norm": 1.2318490069725467, "learning_rate": 1.5727159521228482e-05, "loss": 0.677, "step": 5269 }, { "epoch": 0.7509261897976631, "grad_norm": 1.5660920332683932, "learning_rate": 1.5725120606959355e-05, "loss": 0.6958, "step": 5270 }, { "epoch": 0.7510686805357651, "grad_norm": 1.3797213543489857, "learning_rate": 1.5723081338578635e-05, "loss": 0.6329, "step": 5271 }, { "epoch": 0.7512111712738672, "grad_norm": 1.466652796580258, "learning_rate": 1.5721041716212452e-05, "loss": 0.6569, "step": 5272 }, { "epoch": 0.7513536620119692, "grad_norm": 1.4721381680254195, "learning_rate": 1.571900173998696e-05, "loss": 0.6186, "step": 5273 }, { "epoch": 0.7514961527500712, "grad_norm": 1.2985275688947016, "learning_rate": 1.5716961410028337e-05, "loss": 0.591, "step": 5274 }, { "epoch": 0.7516386434881732, "grad_norm": 1.2402026055399646, "learning_rate": 1.5714920726462783e-05, "loss": 0.6895, "step": 5275 }, { "epoch": 0.7517811342262752, "grad_norm": 1.5432594641092998, "learning_rate": 1.5712879689416517e-05, "loss": 0.677, "step": 5276 }, { "epoch": 0.7519236249643774, "grad_norm": 1.5149360446070765, "learning_rate": 1.5710838299015786e-05, "loss": 0.6905, "step": 5277 }, { "epoch": 0.7520661157024794, "grad_norm": 1.4381080468629062, "learning_rate": 1.570879655538685e-05, "loss": 0.6604, "step": 5278 }, { "epoch": 0.7522086064405814, "grad_norm": 1.4413021552031968, "learning_rate": 1.5706754458655996e-05, "loss": 0.6656, "step": 5279 }, { "epoch": 0.7523510971786834, "grad_norm": 1.3261705872571619, "learning_rate": 1.570471200894953e-05, "loss": 0.6987, "step": 5280 }, { "epoch": 0.7524935879167854, "grad_norm": 1.415897567273651, "learning_rate": 1.5702669206393794e-05, "loss": 0.7326, "step": 5281 }, { "epoch": 0.7526360786548875, "grad_norm": 1.5128658938870154, "learning_rate": 1.5700626051115123e-05, "loss": 0.6493, "step": 5282 }, { "epoch": 0.7527785693929895, "grad_norm": 1.3703105613424211, "learning_rate": 1.5698582543239905e-05, "loss": 0.605, "step": 5283 }, { "epoch": 0.7529210601310915, "grad_norm": 1.3176354704379931, "learning_rate": 1.5696538682894525e-05, "loss": 0.6553, "step": 5284 }, { "epoch": 0.7530635508691935, "grad_norm": 1.3540776259858947, "learning_rate": 1.5694494470205408e-05, "loss": 0.6681, "step": 5285 }, { "epoch": 0.7532060416072955, "grad_norm": 1.290559551485133, "learning_rate": 1.5692449905298988e-05, "loss": 0.6369, "step": 5286 }, { "epoch": 0.7533485323453976, "grad_norm": 1.303991523848771, "learning_rate": 1.5690404988301728e-05, "loss": 0.5791, "step": 5287 }, { "epoch": 0.7534910230834996, "grad_norm": 1.5267862709366622, "learning_rate": 1.5688359719340113e-05, "loss": 0.6797, "step": 5288 }, { "epoch": 0.7536335138216016, "grad_norm": 1.3382650071560542, "learning_rate": 1.5686314098540643e-05, "loss": 0.5927, "step": 5289 }, { "epoch": 0.7537760045597036, "grad_norm": 1.4010545375367898, "learning_rate": 1.5684268126029847e-05, "loss": 0.6186, "step": 5290 }, { "epoch": 0.7539184952978056, "grad_norm": 1.3123940315708589, "learning_rate": 1.5682221801934275e-05, "loss": 0.5826, "step": 5291 }, { "epoch": 0.7540609860359077, "grad_norm": 1.3928534260516539, "learning_rate": 1.5680175126380488e-05, "loss": 0.7142, "step": 5292 }, { "epoch": 0.7542034767740097, "grad_norm": 1.2672596662990694, "learning_rate": 1.567812809949509e-05, "loss": 0.573, "step": 5293 }, { "epoch": 0.7543459675121117, "grad_norm": 1.215583226352201, "learning_rate": 1.5676080721404686e-05, "loss": 0.553, "step": 5294 }, { "epoch": 0.7544884582502137, "grad_norm": 1.1856101263954462, "learning_rate": 1.567403299223591e-05, "loss": 0.6038, "step": 5295 }, { "epoch": 0.7546309489883157, "grad_norm": 1.3710469386261108, "learning_rate": 1.5671984912115426e-05, "loss": 0.6172, "step": 5296 }, { "epoch": 0.7547734397264177, "grad_norm": 1.318054725511, "learning_rate": 1.5669936481169906e-05, "loss": 0.6307, "step": 5297 }, { "epoch": 0.7549159304645198, "grad_norm": 1.4648824057948437, "learning_rate": 1.5667887699526053e-05, "loss": 0.6101, "step": 5298 }, { "epoch": 0.7550584212026218, "grad_norm": 1.46068262758367, "learning_rate": 1.5665838567310585e-05, "loss": 0.6433, "step": 5299 }, { "epoch": 0.7552009119407238, "grad_norm": 1.3821997765341287, "learning_rate": 1.566378908465025e-05, "loss": 0.6727, "step": 5300 }, { "epoch": 0.7553434026788258, "grad_norm": 1.3624161760039102, "learning_rate": 1.566173925167181e-05, "loss": 0.5697, "step": 5301 }, { "epoch": 0.7554858934169278, "grad_norm": 1.3773935925040892, "learning_rate": 1.5659689068502057e-05, "loss": 0.5936, "step": 5302 }, { "epoch": 0.75562838415503, "grad_norm": 1.4075977382344547, "learning_rate": 1.565763853526779e-05, "loss": 0.613, "step": 5303 }, { "epoch": 0.755770874893132, "grad_norm": 1.3080608794606496, "learning_rate": 1.565558765209585e-05, "loss": 0.6394, "step": 5304 }, { "epoch": 0.755913365631234, "grad_norm": 1.367895803647275, "learning_rate": 1.5653536419113078e-05, "loss": 0.6629, "step": 5305 }, { "epoch": 0.756055856369336, "grad_norm": 1.446548084045197, "learning_rate": 1.5651484836446357e-05, "loss": 0.6507, "step": 5306 }, { "epoch": 0.756198347107438, "grad_norm": 1.3091680373681507, "learning_rate": 1.5649432904222576e-05, "loss": 0.7024, "step": 5307 }, { "epoch": 0.7563408378455401, "grad_norm": 1.380886706062139, "learning_rate": 1.5647380622568654e-05, "loss": 0.6021, "step": 5308 }, { "epoch": 0.7564833285836421, "grad_norm": 1.4644167373652823, "learning_rate": 1.564532799161153e-05, "loss": 0.7277, "step": 5309 }, { "epoch": 0.7566258193217441, "grad_norm": 1.2916484281808396, "learning_rate": 1.564327501147816e-05, "loss": 0.6317, "step": 5310 }, { "epoch": 0.7567683100598461, "grad_norm": 3.064983311992523, "learning_rate": 1.5641221682295528e-05, "loss": 0.6167, "step": 5311 }, { "epoch": 0.7569108007979481, "grad_norm": 1.2966524250658245, "learning_rate": 1.5639168004190638e-05, "loss": 0.7383, "step": 5312 }, { "epoch": 0.7570532915360502, "grad_norm": 1.4670710791481254, "learning_rate": 1.5637113977290513e-05, "loss": 0.5908, "step": 5313 }, { "epoch": 0.7571957822741522, "grad_norm": 1.2531522295022646, "learning_rate": 1.5635059601722197e-05, "loss": 0.5635, "step": 5314 }, { "epoch": 0.7573382730122542, "grad_norm": 1.423543219443543, "learning_rate": 1.5633004877612766e-05, "loss": 0.676, "step": 5315 }, { "epoch": 0.7574807637503562, "grad_norm": 1.350670749935982, "learning_rate": 1.5630949805089303e-05, "loss": 0.5854, "step": 5316 }, { "epoch": 0.7576232544884582, "grad_norm": 1.418884189004541, "learning_rate": 1.5628894384278915e-05, "loss": 0.7352, "step": 5317 }, { "epoch": 0.7577657452265603, "grad_norm": 1.3302155888024791, "learning_rate": 1.5626838615308743e-05, "loss": 0.6413, "step": 5318 }, { "epoch": 0.7579082359646623, "grad_norm": 1.3423224089964527, "learning_rate": 1.5624782498305936e-05, "loss": 0.6714, "step": 5319 }, { "epoch": 0.7580507267027643, "grad_norm": 1.489521388839765, "learning_rate": 1.562272603339767e-05, "loss": 0.7117, "step": 5320 }, { "epoch": 0.7581932174408663, "grad_norm": 1.2833814963304602, "learning_rate": 1.562066922071114e-05, "loss": 0.6224, "step": 5321 }, { "epoch": 0.7583357081789683, "grad_norm": 1.7509561324642073, "learning_rate": 1.561861206037357e-05, "loss": 0.6468, "step": 5322 }, { "epoch": 0.7584781989170704, "grad_norm": 1.3944131240434121, "learning_rate": 1.5616554552512198e-05, "loss": 0.7055, "step": 5323 }, { "epoch": 0.7586206896551724, "grad_norm": 1.3240959440128892, "learning_rate": 1.5614496697254283e-05, "loss": 0.6708, "step": 5324 }, { "epoch": 0.7587631803932744, "grad_norm": 1.3589635559656636, "learning_rate": 1.561243849472711e-05, "loss": 0.6001, "step": 5325 }, { "epoch": 0.7589056711313764, "grad_norm": 1.3164889133764126, "learning_rate": 1.561037994505798e-05, "loss": 0.5948, "step": 5326 }, { "epoch": 0.7590481618694784, "grad_norm": 1.3227341463367748, "learning_rate": 1.5608321048374223e-05, "loss": 0.5581, "step": 5327 }, { "epoch": 0.7591906526075805, "grad_norm": 1.4578043342578129, "learning_rate": 1.5606261804803188e-05, "loss": 0.6609, "step": 5328 }, { "epoch": 0.7593331433456826, "grad_norm": 1.3120406535301838, "learning_rate": 1.560420221447224e-05, "loss": 0.6875, "step": 5329 }, { "epoch": 0.7594756340837846, "grad_norm": 1.7431991154018192, "learning_rate": 1.5602142277508772e-05, "loss": 0.6212, "step": 5330 }, { "epoch": 0.7596181248218866, "grad_norm": 1.4328724382847353, "learning_rate": 1.560008199404019e-05, "loss": 0.6336, "step": 5331 }, { "epoch": 0.7597606155599886, "grad_norm": 1.3441202426650158, "learning_rate": 1.559802136419393e-05, "loss": 0.5896, "step": 5332 }, { "epoch": 0.7599031062980907, "grad_norm": 1.4002098945828165, "learning_rate": 1.5595960388097454e-05, "loss": 0.6376, "step": 5333 }, { "epoch": 0.7600455970361927, "grad_norm": 1.4491666703933717, "learning_rate": 1.559389906587823e-05, "loss": 0.6693, "step": 5334 }, { "epoch": 0.7601880877742947, "grad_norm": 1.3115867904005263, "learning_rate": 1.5591837397663754e-05, "loss": 0.6075, "step": 5335 }, { "epoch": 0.7603305785123967, "grad_norm": 1.4636346718597149, "learning_rate": 1.5589775383581553e-05, "loss": 0.6119, "step": 5336 }, { "epoch": 0.7604730692504987, "grad_norm": 1.272362297357952, "learning_rate": 1.5587713023759158e-05, "loss": 0.6588, "step": 5337 }, { "epoch": 0.7606155599886008, "grad_norm": 1.4555680611624477, "learning_rate": 1.5585650318324135e-05, "loss": 0.6988, "step": 5338 }, { "epoch": 0.7607580507267028, "grad_norm": 1.2769431283689403, "learning_rate": 1.558358726740407e-05, "loss": 0.665, "step": 5339 }, { "epoch": 0.7609005414648048, "grad_norm": 1.2739378521941838, "learning_rate": 1.558152387112656e-05, "loss": 0.6512, "step": 5340 }, { "epoch": 0.7610430322029068, "grad_norm": 17.38837874891463, "learning_rate": 1.557946012961924e-05, "loss": 0.594, "step": 5341 }, { "epoch": 0.7611855229410088, "grad_norm": 1.7937166329375342, "learning_rate": 1.5577396043009748e-05, "loss": 0.603, "step": 5342 }, { "epoch": 0.7613280136791108, "grad_norm": 1.2665276012482383, "learning_rate": 1.5575331611425757e-05, "loss": 0.6447, "step": 5343 }, { "epoch": 0.7614705044172129, "grad_norm": 1.4808338952580096, "learning_rate": 1.5573266834994955e-05, "loss": 0.6135, "step": 5344 }, { "epoch": 0.7616129951553149, "grad_norm": 1.4611243057342875, "learning_rate": 1.557120171384506e-05, "loss": 0.6996, "step": 5345 }, { "epoch": 0.7617554858934169, "grad_norm": 1.806084945260338, "learning_rate": 1.5569136248103792e-05, "loss": 0.698, "step": 5346 }, { "epoch": 0.7618979766315189, "grad_norm": 2.1935721836317863, "learning_rate": 1.5567070437898914e-05, "loss": 0.6226, "step": 5347 }, { "epoch": 0.7620404673696209, "grad_norm": 1.423429254800399, "learning_rate": 1.5565004283358198e-05, "loss": 0.6289, "step": 5348 }, { "epoch": 0.762182958107723, "grad_norm": 1.3322492432279687, "learning_rate": 1.556293778460944e-05, "loss": 0.7426, "step": 5349 }, { "epoch": 0.762325448845825, "grad_norm": 1.303283566133025, "learning_rate": 1.556087094178046e-05, "loss": 0.6644, "step": 5350 }, { "epoch": 0.762467939583927, "grad_norm": 1.3281591260903187, "learning_rate": 1.5558803754999093e-05, "loss": 0.627, "step": 5351 }, { "epoch": 0.762610430322029, "grad_norm": 1.909976992812906, "learning_rate": 1.5556736224393205e-05, "loss": 0.7049, "step": 5352 }, { "epoch": 0.762752921060131, "grad_norm": 1.3628891537116246, "learning_rate": 1.5554668350090668e-05, "loss": 0.6648, "step": 5353 }, { "epoch": 0.7628954117982332, "grad_norm": 1.4094011400891597, "learning_rate": 1.5552600132219394e-05, "loss": 0.6564, "step": 5354 }, { "epoch": 0.7630379025363352, "grad_norm": 1.2823600800979138, "learning_rate": 1.5550531570907302e-05, "loss": 0.6412, "step": 5355 }, { "epoch": 0.7631803932744372, "grad_norm": 1.6802702521381327, "learning_rate": 1.554846266628234e-05, "loss": 0.5954, "step": 5356 }, { "epoch": 0.7633228840125392, "grad_norm": 1.3897750737212673, "learning_rate": 1.5546393418472475e-05, "loss": 0.5853, "step": 5357 }, { "epoch": 0.7634653747506412, "grad_norm": 1.8157453524873006, "learning_rate": 1.554432382760569e-05, "loss": 0.6969, "step": 5358 }, { "epoch": 0.7636078654887433, "grad_norm": 1.2936259786367394, "learning_rate": 1.5542253893809993e-05, "loss": 0.5871, "step": 5359 }, { "epoch": 0.7637503562268453, "grad_norm": 1.450248168624866, "learning_rate": 1.554018361721342e-05, "loss": 0.7641, "step": 5360 }, { "epoch": 0.7638928469649473, "grad_norm": 1.2898349977463655, "learning_rate": 1.553811299794402e-05, "loss": 0.598, "step": 5361 }, { "epoch": 0.7640353377030493, "grad_norm": 1.556048630187273, "learning_rate": 1.5536042036129865e-05, "loss": 0.671, "step": 5362 }, { "epoch": 0.7641778284411513, "grad_norm": 1.171775377761149, "learning_rate": 1.5533970731899047e-05, "loss": 0.6016, "step": 5363 }, { "epoch": 0.7643203191792534, "grad_norm": 1.3105311779928572, "learning_rate": 1.5531899085379688e-05, "loss": 0.5822, "step": 5364 }, { "epoch": 0.7644628099173554, "grad_norm": 1.4207595552965238, "learning_rate": 1.5529827096699913e-05, "loss": 0.673, "step": 5365 }, { "epoch": 0.7646053006554574, "grad_norm": 1.3678570634803184, "learning_rate": 1.552775476598789e-05, "loss": 0.6066, "step": 5366 }, { "epoch": 0.7647477913935594, "grad_norm": 1.4474093224129625, "learning_rate": 1.552568209337179e-05, "loss": 0.702, "step": 5367 }, { "epoch": 0.7648902821316614, "grad_norm": 1.176919242206977, "learning_rate": 1.552360907897981e-05, "loss": 0.6427, "step": 5368 }, { "epoch": 0.7650327728697635, "grad_norm": 1.3241558892461809, "learning_rate": 1.552153572294018e-05, "loss": 0.6398, "step": 5369 }, { "epoch": 0.7651752636078655, "grad_norm": 1.3482306155330823, "learning_rate": 1.5519462025381134e-05, "loss": 0.6277, "step": 5370 }, { "epoch": 0.7653177543459675, "grad_norm": 1.2255830599146684, "learning_rate": 1.551738798643094e-05, "loss": 0.6607, "step": 5371 }, { "epoch": 0.7654602450840695, "grad_norm": 1.219911073152199, "learning_rate": 1.5515313606217878e-05, "loss": 0.6552, "step": 5372 }, { "epoch": 0.7656027358221715, "grad_norm": 1.4350667437168199, "learning_rate": 1.5513238884870258e-05, "loss": 0.641, "step": 5373 }, { "epoch": 0.7657452265602736, "grad_norm": 1.2802061157847562, "learning_rate": 1.5511163822516402e-05, "loss": 0.6801, "step": 5374 }, { "epoch": 0.7658877172983756, "grad_norm": 1.357599504966116, "learning_rate": 1.5509088419284654e-05, "loss": 0.6479, "step": 5375 }, { "epoch": 0.7660302080364776, "grad_norm": 1.4520261472875482, "learning_rate": 1.5507012675303396e-05, "loss": 0.6128, "step": 5376 }, { "epoch": 0.7661726987745796, "grad_norm": 1.2910899799712396, "learning_rate": 1.5504936590700997e-05, "loss": 0.6439, "step": 5377 }, { "epoch": 0.7663151895126816, "grad_norm": 1.3426730025389577, "learning_rate": 1.5502860165605886e-05, "loss": 0.6877, "step": 5378 }, { "epoch": 0.7664576802507836, "grad_norm": 1.3888204111307914, "learning_rate": 1.5500783400146485e-05, "loss": 0.7077, "step": 5379 }, { "epoch": 0.7666001709888858, "grad_norm": 1.5594480252686127, "learning_rate": 1.549870629445125e-05, "loss": 0.6303, "step": 5380 }, { "epoch": 0.7667426617269878, "grad_norm": 1.4406072533708119, "learning_rate": 1.5496628848648652e-05, "loss": 0.6781, "step": 5381 }, { "epoch": 0.7668851524650898, "grad_norm": 1.2936003528032567, "learning_rate": 1.5494551062867187e-05, "loss": 0.6734, "step": 5382 }, { "epoch": 0.7670276432031918, "grad_norm": 1.4741514845804609, "learning_rate": 1.549247293723537e-05, "loss": 0.7097, "step": 5383 }, { "epoch": 0.7671701339412939, "grad_norm": 1.304170733672806, "learning_rate": 1.5490394471881743e-05, "loss": 0.6664, "step": 5384 }, { "epoch": 0.7673126246793959, "grad_norm": 1.2616054075205132, "learning_rate": 1.5488315666934854e-05, "loss": 0.6037, "step": 5385 }, { "epoch": 0.7674551154174979, "grad_norm": 1.6029757443868786, "learning_rate": 1.548623652252329e-05, "loss": 0.7405, "step": 5386 }, { "epoch": 0.7675976061555999, "grad_norm": 1.411401200437626, "learning_rate": 1.548415703877565e-05, "loss": 0.6847, "step": 5387 }, { "epoch": 0.7677400968937019, "grad_norm": 2.8104590150908955, "learning_rate": 1.548207721582055e-05, "loss": 0.6771, "step": 5388 }, { "epoch": 0.767882587631804, "grad_norm": 1.5404978923430912, "learning_rate": 1.5479997053786632e-05, "loss": 0.6634, "step": 5389 }, { "epoch": 0.768025078369906, "grad_norm": 1.2059128418093916, "learning_rate": 1.547791655280256e-05, "loss": 0.5619, "step": 5390 }, { "epoch": 0.768167569108008, "grad_norm": 1.3632111655553272, "learning_rate": 1.5475835712997028e-05, "loss": 0.6285, "step": 5391 }, { "epoch": 0.76831005984611, "grad_norm": 1.377416146740362, "learning_rate": 1.5473754534498723e-05, "loss": 0.6426, "step": 5392 }, { "epoch": 0.768452550584212, "grad_norm": 1.3851900729525817, "learning_rate": 1.5471673017436382e-05, "loss": 0.6096, "step": 5393 }, { "epoch": 0.768595041322314, "grad_norm": 1.2742864764894966, "learning_rate": 1.5469591161938748e-05, "loss": 0.5812, "step": 5394 }, { "epoch": 0.7687375320604161, "grad_norm": 1.3008350387317353, "learning_rate": 1.5467508968134592e-05, "loss": 0.6581, "step": 5395 }, { "epoch": 0.7688800227985181, "grad_norm": 1.2566856448451458, "learning_rate": 1.5465426436152698e-05, "loss": 0.6598, "step": 5396 }, { "epoch": 0.7690225135366201, "grad_norm": 1.206681869509311, "learning_rate": 1.5463343566121872e-05, "loss": 0.5774, "step": 5397 }, { "epoch": 0.7691650042747221, "grad_norm": 1.2500754539948853, "learning_rate": 1.5461260358170953e-05, "loss": 0.6867, "step": 5398 }, { "epoch": 0.7693074950128241, "grad_norm": 1.3021128920091976, "learning_rate": 1.5459176812428785e-05, "loss": 0.7011, "step": 5399 }, { "epoch": 0.7694499857509262, "grad_norm": 1.3975107121895898, "learning_rate": 1.5457092929024245e-05, "loss": 0.6985, "step": 5400 }, { "epoch": 0.7695924764890282, "grad_norm": 1.2250536294654804, "learning_rate": 1.5455008708086224e-05, "loss": 0.5962, "step": 5401 }, { "epoch": 0.7697349672271302, "grad_norm": 1.3408722954775767, "learning_rate": 1.545292414974364e-05, "loss": 0.6934, "step": 5402 }, { "epoch": 0.7698774579652322, "grad_norm": 1.3072809541756552, "learning_rate": 1.5450839254125413e-05, "loss": 0.6141, "step": 5403 }, { "epoch": 0.7700199487033342, "grad_norm": 1.4152369598201597, "learning_rate": 1.5448754021360515e-05, "loss": 0.6055, "step": 5404 }, { "epoch": 0.7701624394414363, "grad_norm": 1.316412759673659, "learning_rate": 1.5446668451577914e-05, "loss": 0.7073, "step": 5405 }, { "epoch": 0.7703049301795384, "grad_norm": 1.2251274846799223, "learning_rate": 1.5444582544906614e-05, "loss": 0.6873, "step": 5406 }, { "epoch": 0.7704474209176404, "grad_norm": 1.3467030571188492, "learning_rate": 1.544249630147562e-05, "loss": 0.729, "step": 5407 }, { "epoch": 0.7705899116557424, "grad_norm": 1.2020351067359765, "learning_rate": 1.5440409721413984e-05, "loss": 0.6459, "step": 5408 }, { "epoch": 0.7707324023938444, "grad_norm": 1.4401323673103548, "learning_rate": 1.5438322804850762e-05, "loss": 0.7086, "step": 5409 }, { "epoch": 0.7708748931319465, "grad_norm": 1.2729600603465534, "learning_rate": 1.5436235551915032e-05, "loss": 0.6757, "step": 5410 }, { "epoch": 0.7710173838700485, "grad_norm": 1.2827192562287009, "learning_rate": 1.5434147962735893e-05, "loss": 0.6455, "step": 5411 }, { "epoch": 0.7711598746081505, "grad_norm": 1.3715307216806323, "learning_rate": 1.5432060037442473e-05, "loss": 0.6994, "step": 5412 }, { "epoch": 0.7713023653462525, "grad_norm": 2.2125534939610927, "learning_rate": 1.5429971776163913e-05, "loss": 0.7063, "step": 5413 }, { "epoch": 0.7714448560843545, "grad_norm": 1.3326424780573167, "learning_rate": 1.5427883179029377e-05, "loss": 0.6477, "step": 5414 }, { "epoch": 0.7715873468224566, "grad_norm": 1.3934361996189792, "learning_rate": 1.542579424616805e-05, "loss": 0.5953, "step": 5415 }, { "epoch": 0.7717298375605586, "grad_norm": 1.3313188337930568, "learning_rate": 1.5423704977709132e-05, "loss": 0.6387, "step": 5416 }, { "epoch": 0.7718723282986606, "grad_norm": 1.2015341483816004, "learning_rate": 1.5421615373781853e-05, "loss": 0.5532, "step": 5417 }, { "epoch": 0.7720148190367626, "grad_norm": 1.3386880533638572, "learning_rate": 1.541952543451546e-05, "loss": 0.6361, "step": 5418 }, { "epoch": 0.7721573097748646, "grad_norm": 1.368103907646325, "learning_rate": 1.541743516003922e-05, "loss": 0.6423, "step": 5419 }, { "epoch": 0.7722998005129666, "grad_norm": 1.424255579495456, "learning_rate": 1.541534455048242e-05, "loss": 0.6338, "step": 5420 }, { "epoch": 0.7724422912510687, "grad_norm": 1.3281629581611978, "learning_rate": 1.5413253605974375e-05, "loss": 0.6436, "step": 5421 }, { "epoch": 0.7725847819891707, "grad_norm": 1.279038764588182, "learning_rate": 1.5411162326644404e-05, "loss": 0.6239, "step": 5422 }, { "epoch": 0.7727272727272727, "grad_norm": 1.4549120060620986, "learning_rate": 1.5409070712621865e-05, "loss": 0.6563, "step": 5423 }, { "epoch": 0.7728697634653747, "grad_norm": 1.5701431679909243, "learning_rate": 1.5406978764036126e-05, "loss": 0.7293, "step": 5424 }, { "epoch": 0.7730122542034767, "grad_norm": 1.328718931248706, "learning_rate": 1.540488648101658e-05, "loss": 0.6455, "step": 5425 }, { "epoch": 0.7731547449415788, "grad_norm": 2.002989066927129, "learning_rate": 1.5402793863692644e-05, "loss": 0.6342, "step": 5426 }, { "epoch": 0.7732972356796808, "grad_norm": 1.3289213095025643, "learning_rate": 1.5400700912193738e-05, "loss": 0.6484, "step": 5427 }, { "epoch": 0.7734397264177828, "grad_norm": 1.3272539508318981, "learning_rate": 1.5398607626649328e-05, "loss": 0.6243, "step": 5428 }, { "epoch": 0.7735822171558848, "grad_norm": 1.3827028187784631, "learning_rate": 1.5396514007188886e-05, "loss": 0.6156, "step": 5429 }, { "epoch": 0.7737247078939868, "grad_norm": 1.37635044963549, "learning_rate": 1.53944200539419e-05, "loss": 0.6587, "step": 5430 }, { "epoch": 0.7738671986320889, "grad_norm": 2.122588621695194, "learning_rate": 1.53923257670379e-05, "loss": 0.5925, "step": 5431 }, { "epoch": 0.774009689370191, "grad_norm": 2.1952133740686213, "learning_rate": 1.5390231146606406e-05, "loss": 0.6063, "step": 5432 }, { "epoch": 0.774152180108293, "grad_norm": 1.3123985255242245, "learning_rate": 1.5388136192776985e-05, "loss": 0.6137, "step": 5433 }, { "epoch": 0.774294670846395, "grad_norm": 1.3928346679163204, "learning_rate": 1.5386040905679212e-05, "loss": 0.6719, "step": 5434 }, { "epoch": 0.774437161584497, "grad_norm": 1.2356391992235058, "learning_rate": 1.5383945285442683e-05, "loss": 0.6563, "step": 5435 }, { "epoch": 0.7745796523225991, "grad_norm": 1.2630949947346468, "learning_rate": 1.5381849332197025e-05, "loss": 0.6169, "step": 5436 }, { "epoch": 0.7747221430607011, "grad_norm": 1.3158449863156998, "learning_rate": 1.5379753046071866e-05, "loss": 0.6625, "step": 5437 }, { "epoch": 0.7748646337988031, "grad_norm": 1.754805059830619, "learning_rate": 1.5377656427196876e-05, "loss": 0.6699, "step": 5438 }, { "epoch": 0.7750071245369051, "grad_norm": 1.671881851754248, "learning_rate": 1.537555947570173e-05, "loss": 0.726, "step": 5439 }, { "epoch": 0.7751496152750071, "grad_norm": 1.4363752107282919, "learning_rate": 1.5373462191716127e-05, "loss": 0.7028, "step": 5440 }, { "epoch": 0.7752921060131092, "grad_norm": 1.3593423343104676, "learning_rate": 1.5371364575369794e-05, "loss": 0.6322, "step": 5441 }, { "epoch": 0.7754345967512112, "grad_norm": 1.4025239675207233, "learning_rate": 1.536926662679247e-05, "loss": 0.7364, "step": 5442 }, { "epoch": 0.7755770874893132, "grad_norm": 1.4636868590972751, "learning_rate": 1.5367168346113922e-05, "loss": 0.6802, "step": 5443 }, { "epoch": 0.7757195782274152, "grad_norm": 1.283453855016615, "learning_rate": 1.536506973346393e-05, "loss": 0.5498, "step": 5444 }, { "epoch": 0.7758620689655172, "grad_norm": 1.3974970771725321, "learning_rate": 1.53629707889723e-05, "loss": 0.6636, "step": 5445 }, { "epoch": 0.7760045597036193, "grad_norm": 1.4114471238739261, "learning_rate": 1.5360871512768855e-05, "loss": 0.5975, "step": 5446 }, { "epoch": 0.7761470504417213, "grad_norm": 1.1693793372247048, "learning_rate": 1.5358771904983435e-05, "loss": 0.6548, "step": 5447 }, { "epoch": 0.7762895411798233, "grad_norm": 1.402492821578417, "learning_rate": 1.5356671965745915e-05, "loss": 0.6239, "step": 5448 }, { "epoch": 0.7764320319179253, "grad_norm": 1.3210650455702868, "learning_rate": 1.5354571695186175e-05, "loss": 0.6465, "step": 5449 }, { "epoch": 0.7765745226560273, "grad_norm": 1.2229704571765074, "learning_rate": 1.5352471093434124e-05, "loss": 0.6693, "step": 5450 }, { "epoch": 0.7767170133941294, "grad_norm": 1.3849974864580963, "learning_rate": 1.535037016061969e-05, "loss": 0.5976, "step": 5451 }, { "epoch": 0.7768595041322314, "grad_norm": 1.3168916197178582, "learning_rate": 1.5348268896872812e-05, "loss": 0.6914, "step": 5452 }, { "epoch": 0.7770019948703334, "grad_norm": 1.249141057886412, "learning_rate": 1.534616730232347e-05, "loss": 0.7239, "step": 5453 }, { "epoch": 0.7771444856084354, "grad_norm": 1.477848044748311, "learning_rate": 1.534406537710164e-05, "loss": 0.7134, "step": 5454 }, { "epoch": 0.7772869763465374, "grad_norm": 1.4855162183740247, "learning_rate": 1.5341963121337343e-05, "loss": 0.6469, "step": 5455 }, { "epoch": 0.7774294670846394, "grad_norm": 1.2923844363730697, "learning_rate": 1.53398605351606e-05, "loss": 0.7128, "step": 5456 }, { "epoch": 0.7775719578227415, "grad_norm": 1.3542546042343637, "learning_rate": 1.5337757618701464e-05, "loss": 0.6085, "step": 5457 }, { "epoch": 0.7777144485608436, "grad_norm": 1.3925267845206437, "learning_rate": 1.5335654372090004e-05, "loss": 0.6751, "step": 5458 }, { "epoch": 0.7778569392989456, "grad_norm": 1.3301310044685504, "learning_rate": 1.533355079545631e-05, "loss": 0.7192, "step": 5459 }, { "epoch": 0.7779994300370476, "grad_norm": 1.3510912394123518, "learning_rate": 1.5331446888930493e-05, "loss": 0.6, "step": 5460 }, { "epoch": 0.7781419207751497, "grad_norm": 1.423034497278355, "learning_rate": 1.5329342652642688e-05, "loss": 0.7144, "step": 5461 }, { "epoch": 0.7782844115132517, "grad_norm": 1.56231390274382, "learning_rate": 1.5327238086723043e-05, "loss": 0.6243, "step": 5462 }, { "epoch": 0.7784269022513537, "grad_norm": 1.2315964894135578, "learning_rate": 1.5325133191301734e-05, "loss": 0.7328, "step": 5463 }, { "epoch": 0.7785693929894557, "grad_norm": 1.3238942400801768, "learning_rate": 1.5323027966508946e-05, "loss": 0.737, "step": 5464 }, { "epoch": 0.7787118837275577, "grad_norm": 1.2882368617963862, "learning_rate": 1.5320922412474895e-05, "loss": 0.6628, "step": 5465 }, { "epoch": 0.7788543744656597, "grad_norm": 1.2428294151853987, "learning_rate": 1.5318816529329822e-05, "loss": 0.6194, "step": 5466 }, { "epoch": 0.7789968652037618, "grad_norm": 1.2192165695325414, "learning_rate": 1.5316710317203972e-05, "loss": 0.6134, "step": 5467 }, { "epoch": 0.7791393559418638, "grad_norm": 1.3542887331423794, "learning_rate": 1.5314603776227622e-05, "loss": 0.6512, "step": 5468 }, { "epoch": 0.7792818466799658, "grad_norm": 1.441237447452736, "learning_rate": 1.531249690653106e-05, "loss": 0.7344, "step": 5469 }, { "epoch": 0.7794243374180678, "grad_norm": 1.9701190571323892, "learning_rate": 1.531038970824461e-05, "loss": 0.6414, "step": 5470 }, { "epoch": 0.7795668281561698, "grad_norm": 1.357380955119493, "learning_rate": 1.5308282181498606e-05, "loss": 0.6658, "step": 5471 }, { "epoch": 0.7797093188942719, "grad_norm": 1.2918315300014787, "learning_rate": 1.53061743264234e-05, "loss": 0.6214, "step": 5472 }, { "epoch": 0.7798518096323739, "grad_norm": 1.2150924669820038, "learning_rate": 1.5304066143149363e-05, "loss": 0.5929, "step": 5473 }, { "epoch": 0.7799943003704759, "grad_norm": 1.2796357989120444, "learning_rate": 1.53019576318069e-05, "loss": 0.6563, "step": 5474 }, { "epoch": 0.7801367911085779, "grad_norm": 1.287582696459766, "learning_rate": 1.529984879252642e-05, "loss": 0.6551, "step": 5475 }, { "epoch": 0.7802792818466799, "grad_norm": 1.19461363640969, "learning_rate": 1.529773962543837e-05, "loss": 0.5717, "step": 5476 }, { "epoch": 0.780421772584782, "grad_norm": 1.3383148064574424, "learning_rate": 1.529563013067319e-05, "loss": 0.6843, "step": 5477 }, { "epoch": 0.780564263322884, "grad_norm": 1.262105575007761, "learning_rate": 1.5293520308361372e-05, "loss": 0.7012, "step": 5478 }, { "epoch": 0.780706754060986, "grad_norm": 1.3542380816750343, "learning_rate": 1.5291410158633406e-05, "loss": 0.6962, "step": 5479 }, { "epoch": 0.780849244799088, "grad_norm": 1.4273692392841788, "learning_rate": 1.528929968161981e-05, "loss": 0.7406, "step": 5480 }, { "epoch": 0.78099173553719, "grad_norm": 1.4912599745144193, "learning_rate": 1.5287188877451126e-05, "loss": 0.7212, "step": 5481 }, { "epoch": 0.781134226275292, "grad_norm": 1.3786713594498565, "learning_rate": 1.5285077746257905e-05, "loss": 0.6475, "step": 5482 }, { "epoch": 0.7812767170133942, "grad_norm": 1.307821900705605, "learning_rate": 1.5282966288170732e-05, "loss": 0.688, "step": 5483 }, { "epoch": 0.7814192077514962, "grad_norm": 1.3308614769920122, "learning_rate": 1.52808545033202e-05, "loss": 0.6653, "step": 5484 }, { "epoch": 0.7815616984895982, "grad_norm": 1.3762958490923156, "learning_rate": 1.527874239183693e-05, "loss": 0.7278, "step": 5485 }, { "epoch": 0.7817041892277002, "grad_norm": 1.3737673194166125, "learning_rate": 1.5276629953851562e-05, "loss": 0.649, "step": 5486 }, { "epoch": 0.7818466799658023, "grad_norm": 1.4317283761226196, "learning_rate": 1.5274517189494756e-05, "loss": 0.6568, "step": 5487 }, { "epoch": 0.7819891707039043, "grad_norm": 1.4320191332662084, "learning_rate": 1.5272404098897186e-05, "loss": 0.6778, "step": 5488 }, { "epoch": 0.7821316614420063, "grad_norm": 1.299978852278681, "learning_rate": 1.5270290682189556e-05, "loss": 0.6785, "step": 5489 }, { "epoch": 0.7822741521801083, "grad_norm": 1.3538670855675232, "learning_rate": 1.5268176939502587e-05, "loss": 0.713, "step": 5490 }, { "epoch": 0.7824166429182103, "grad_norm": 1.3263014029600066, "learning_rate": 1.526606287096701e-05, "loss": 0.6246, "step": 5491 }, { "epoch": 0.7825591336563124, "grad_norm": 1.2899709966902972, "learning_rate": 1.5263948476713598e-05, "loss": 0.5833, "step": 5492 }, { "epoch": 0.7827016243944144, "grad_norm": 1.2832141060043556, "learning_rate": 1.5261833756873118e-05, "loss": 0.621, "step": 5493 }, { "epoch": 0.7828441151325164, "grad_norm": 1.1782639577121428, "learning_rate": 1.525971871157638e-05, "loss": 0.5934, "step": 5494 }, { "epoch": 0.7829866058706184, "grad_norm": 1.332865200269672, "learning_rate": 1.5257603340954195e-05, "loss": 0.6232, "step": 5495 }, { "epoch": 0.7831290966087204, "grad_norm": 1.3183221709093982, "learning_rate": 1.5255487645137414e-05, "loss": 0.6856, "step": 5496 }, { "epoch": 0.7832715873468225, "grad_norm": 1.2988099863577658, "learning_rate": 1.525337162425689e-05, "loss": 0.63, "step": 5497 }, { "epoch": 0.7834140780849245, "grad_norm": 1.5376634861547511, "learning_rate": 1.5251255278443507e-05, "loss": 0.7137, "step": 5498 }, { "epoch": 0.7835565688230265, "grad_norm": 1.3266192231052516, "learning_rate": 1.5249138607828165e-05, "loss": 0.643, "step": 5499 }, { "epoch": 0.7836990595611285, "grad_norm": 1.2886429394275016, "learning_rate": 1.5247021612541785e-05, "loss": 0.5523, "step": 5500 }, { "epoch": 0.7838415502992305, "grad_norm": 1.2638016788299409, "learning_rate": 1.5244904292715306e-05, "loss": 0.5774, "step": 5501 }, { "epoch": 0.7839840410373325, "grad_norm": 1.3448925948102126, "learning_rate": 1.524278664847969e-05, "loss": 0.6668, "step": 5502 }, { "epoch": 0.7841265317754346, "grad_norm": 1.3633030264808725, "learning_rate": 1.5240668679965924e-05, "loss": 0.5677, "step": 5503 }, { "epoch": 0.7842690225135366, "grad_norm": 1.2916861128072161, "learning_rate": 1.5238550387304999e-05, "loss": 0.6288, "step": 5504 }, { "epoch": 0.7844115132516386, "grad_norm": 1.5457351285105654, "learning_rate": 1.5236431770627941e-05, "loss": 0.7219, "step": 5505 }, { "epoch": 0.7845540039897406, "grad_norm": 1.6529751892946403, "learning_rate": 1.523431283006579e-05, "loss": 0.5754, "step": 5506 }, { "epoch": 0.7846964947278426, "grad_norm": 1.4073511659832252, "learning_rate": 1.5232193565749611e-05, "loss": 0.7096, "step": 5507 }, { "epoch": 0.7848389854659447, "grad_norm": 1.3142330521480292, "learning_rate": 1.523007397781048e-05, "loss": 0.7067, "step": 5508 }, { "epoch": 0.7849814762040468, "grad_norm": 1.8113603518256869, "learning_rate": 1.5227954066379505e-05, "loss": 0.613, "step": 5509 }, { "epoch": 0.7851239669421488, "grad_norm": 1.5194944171296125, "learning_rate": 1.5225833831587799e-05, "loss": 0.6475, "step": 5510 }, { "epoch": 0.7852664576802508, "grad_norm": 1.3182667839176265, "learning_rate": 1.5223713273566512e-05, "loss": 0.734, "step": 5511 }, { "epoch": 0.7854089484183528, "grad_norm": 1.2343864454564806, "learning_rate": 1.5221592392446798e-05, "loss": 0.6337, "step": 5512 }, { "epoch": 0.7855514391564549, "grad_norm": 1.3062261803437383, "learning_rate": 1.5219471188359837e-05, "loss": 0.5979, "step": 5513 }, { "epoch": 0.7856939298945569, "grad_norm": 1.3078323005655477, "learning_rate": 1.5217349661436842e-05, "loss": 0.6539, "step": 5514 }, { "epoch": 0.7858364206326589, "grad_norm": 1.410988281987752, "learning_rate": 1.5215227811809023e-05, "loss": 0.6659, "step": 5515 }, { "epoch": 0.7859789113707609, "grad_norm": 1.3922576242428604, "learning_rate": 1.5213105639607623e-05, "loss": 0.697, "step": 5516 }, { "epoch": 0.7861214021088629, "grad_norm": 1.299026323797154, "learning_rate": 1.5210983144963906e-05, "loss": 0.6812, "step": 5517 }, { "epoch": 0.786263892846965, "grad_norm": 1.2844744285924785, "learning_rate": 1.5208860328009157e-05, "loss": 0.6355, "step": 5518 }, { "epoch": 0.786406383585067, "grad_norm": 1.4018054589588607, "learning_rate": 1.5206737188874665e-05, "loss": 0.6015, "step": 5519 }, { "epoch": 0.786548874323169, "grad_norm": 1.6747824783645082, "learning_rate": 1.5204613727691759e-05, "loss": 0.6655, "step": 5520 }, { "epoch": 0.786691365061271, "grad_norm": 1.4264367605060468, "learning_rate": 1.5202489944591783e-05, "loss": 0.6797, "step": 5521 }, { "epoch": 0.786833855799373, "grad_norm": 1.3385034487985932, "learning_rate": 1.520036583970609e-05, "loss": 0.6671, "step": 5522 }, { "epoch": 0.7869763465374751, "grad_norm": 1.1703755215165064, "learning_rate": 1.5198241413166063e-05, "loss": 0.6192, "step": 5523 }, { "epoch": 0.7871188372755771, "grad_norm": 1.3597627520269107, "learning_rate": 1.5196116665103105e-05, "loss": 0.7368, "step": 5524 }, { "epoch": 0.7872613280136791, "grad_norm": 1.4498877188376318, "learning_rate": 1.5193991595648636e-05, "loss": 0.7103, "step": 5525 }, { "epoch": 0.7874038187517811, "grad_norm": 1.3532180292587013, "learning_rate": 1.5191866204934095e-05, "loss": 0.691, "step": 5526 }, { "epoch": 0.7875463094898831, "grad_norm": 1.3235261667467686, "learning_rate": 1.5189740493090942e-05, "loss": 0.6816, "step": 5527 }, { "epoch": 0.7876888002279852, "grad_norm": 1.3486764000902185, "learning_rate": 1.518761446025066e-05, "loss": 0.6187, "step": 5528 }, { "epoch": 0.7878312909660872, "grad_norm": 1.2945339710278325, "learning_rate": 1.5185488106544743e-05, "loss": 0.6965, "step": 5529 }, { "epoch": 0.7879737817041892, "grad_norm": 1.3143002889276276, "learning_rate": 1.5183361432104718e-05, "loss": 0.6459, "step": 5530 }, { "epoch": 0.7881162724422912, "grad_norm": 1.3462739951576572, "learning_rate": 1.518123443706212e-05, "loss": 0.7036, "step": 5531 }, { "epoch": 0.7882587631803932, "grad_norm": 1.3175815026945206, "learning_rate": 1.5179107121548509e-05, "loss": 0.6439, "step": 5532 }, { "epoch": 0.7884012539184952, "grad_norm": 1.248057261557105, "learning_rate": 1.5176979485695466e-05, "loss": 0.6617, "step": 5533 }, { "epoch": 0.7885437446565973, "grad_norm": 1.3240018100500386, "learning_rate": 1.5174851529634586e-05, "loss": 0.6844, "step": 5534 }, { "epoch": 0.7886862353946994, "grad_norm": 1.411205573420785, "learning_rate": 1.517272325349749e-05, "loss": 0.7527, "step": 5535 }, { "epoch": 0.7888287261328014, "grad_norm": 1.3693158057527475, "learning_rate": 1.517059465741582e-05, "loss": 0.6498, "step": 5536 }, { "epoch": 0.7889712168709034, "grad_norm": 1.3670888873058082, "learning_rate": 1.5168465741521233e-05, "loss": 0.6937, "step": 5537 }, { "epoch": 0.7891137076090055, "grad_norm": 1.2367675632869843, "learning_rate": 1.5166336505945403e-05, "loss": 0.6357, "step": 5538 }, { "epoch": 0.7892561983471075, "grad_norm": 1.25449585093086, "learning_rate": 1.5164206950820033e-05, "loss": 0.6601, "step": 5539 }, { "epoch": 0.7893986890852095, "grad_norm": 1.3092425306045228, "learning_rate": 1.5162077076276837e-05, "loss": 0.7336, "step": 5540 }, { "epoch": 0.7895411798233115, "grad_norm": 1.150699607206234, "learning_rate": 1.5159946882447555e-05, "loss": 0.4859, "step": 5541 }, { "epoch": 0.7896836705614135, "grad_norm": 1.2957716695692119, "learning_rate": 1.5157816369463943e-05, "loss": 0.7267, "step": 5542 }, { "epoch": 0.7898261612995156, "grad_norm": 1.2617647679206911, "learning_rate": 1.5155685537457779e-05, "loss": 0.567, "step": 5543 }, { "epoch": 0.7899686520376176, "grad_norm": 1.348921936820008, "learning_rate": 1.5153554386560862e-05, "loss": 0.6385, "step": 5544 }, { "epoch": 0.7901111427757196, "grad_norm": 1.392921926385639, "learning_rate": 1.5151422916905004e-05, "loss": 0.6033, "step": 5545 }, { "epoch": 0.7902536335138216, "grad_norm": 1.3726312329099195, "learning_rate": 1.514929112862204e-05, "loss": 0.6992, "step": 5546 }, { "epoch": 0.7903961242519236, "grad_norm": 1.3389035312582935, "learning_rate": 1.5147159021843834e-05, "loss": 0.6622, "step": 5547 }, { "epoch": 0.7905386149900256, "grad_norm": 1.2559325330996678, "learning_rate": 1.5145026596702254e-05, "loss": 0.6843, "step": 5548 }, { "epoch": 0.7906811057281277, "grad_norm": 1.2656591023481394, "learning_rate": 1.5142893853329197e-05, "loss": 0.6429, "step": 5549 }, { "epoch": 0.7908235964662297, "grad_norm": 1.5016075245535607, "learning_rate": 1.5140760791856579e-05, "loss": 0.6149, "step": 5550 }, { "epoch": 0.7909660872043317, "grad_norm": 1.3616641959507398, "learning_rate": 1.5138627412416337e-05, "loss": 0.5854, "step": 5551 }, { "epoch": 0.7911085779424337, "grad_norm": 1.4050578440544916, "learning_rate": 1.5136493715140423e-05, "loss": 0.6348, "step": 5552 }, { "epoch": 0.7912510686805357, "grad_norm": 1.3477809837687391, "learning_rate": 1.5134359700160809e-05, "loss": 0.6625, "step": 5553 }, { "epoch": 0.7913935594186378, "grad_norm": 1.2151407085399148, "learning_rate": 1.513222536760949e-05, "loss": 0.614, "step": 5554 }, { "epoch": 0.7915360501567398, "grad_norm": 1.5587519084936432, "learning_rate": 1.5130090717618482e-05, "loss": 0.7041, "step": 5555 }, { "epoch": 0.7916785408948418, "grad_norm": 1.3713578325038338, "learning_rate": 1.5127955750319813e-05, "loss": 0.7376, "step": 5556 }, { "epoch": 0.7918210316329438, "grad_norm": 1.3491065874080723, "learning_rate": 1.5125820465845537e-05, "loss": 0.6145, "step": 5557 }, { "epoch": 0.7919635223710458, "grad_norm": 1.3380242767692323, "learning_rate": 1.512368486432773e-05, "loss": 0.6901, "step": 5558 }, { "epoch": 0.7921060131091479, "grad_norm": 2.116200685853108, "learning_rate": 1.5121548945898483e-05, "loss": 0.6255, "step": 5559 }, { "epoch": 0.7922485038472499, "grad_norm": 1.2583071475040974, "learning_rate": 1.5119412710689902e-05, "loss": 0.5938, "step": 5560 }, { "epoch": 0.792390994585352, "grad_norm": 1.7153890341670988, "learning_rate": 1.5117276158834122e-05, "loss": 0.7168, "step": 5561 }, { "epoch": 0.792533485323454, "grad_norm": 1.2300753002446254, "learning_rate": 1.5115139290463292e-05, "loss": 0.7315, "step": 5562 }, { "epoch": 0.792675976061556, "grad_norm": 1.343823492298613, "learning_rate": 1.511300210570959e-05, "loss": 0.6072, "step": 5563 }, { "epoch": 0.7928184667996581, "grad_norm": 1.3535668429578065, "learning_rate": 1.511086460470519e-05, "loss": 0.7264, "step": 5564 }, { "epoch": 0.7929609575377601, "grad_norm": 1.2953283827605966, "learning_rate": 1.5108726787582311e-05, "loss": 0.6405, "step": 5565 }, { "epoch": 0.7931034482758621, "grad_norm": 1.2597286949007527, "learning_rate": 1.5106588654473184e-05, "loss": 0.6356, "step": 5566 }, { "epoch": 0.7932459390139641, "grad_norm": 1.2817090635776214, "learning_rate": 1.5104450205510053e-05, "loss": 0.6256, "step": 5567 }, { "epoch": 0.7933884297520661, "grad_norm": 1.4107469030362991, "learning_rate": 1.5102311440825186e-05, "loss": 0.6497, "step": 5568 }, { "epoch": 0.7935309204901682, "grad_norm": 1.2706718284425518, "learning_rate": 1.5100172360550873e-05, "loss": 0.6529, "step": 5569 }, { "epoch": 0.7936734112282702, "grad_norm": 1.3018623911717533, "learning_rate": 1.509803296481942e-05, "loss": 0.7056, "step": 5570 }, { "epoch": 0.7938159019663722, "grad_norm": 1.341896676614719, "learning_rate": 1.509589325376315e-05, "loss": 0.6999, "step": 5571 }, { "epoch": 0.7939583927044742, "grad_norm": 1.5055921553015164, "learning_rate": 1.509375322751441e-05, "loss": 0.6462, "step": 5572 }, { "epoch": 0.7941008834425762, "grad_norm": 1.3328768918762237, "learning_rate": 1.5091612886205576e-05, "loss": 0.6508, "step": 5573 }, { "epoch": 0.7942433741806783, "grad_norm": 1.4227207117479568, "learning_rate": 1.5089472229969015e-05, "loss": 0.6316, "step": 5574 }, { "epoch": 0.7943858649187803, "grad_norm": 1.3794032374659657, "learning_rate": 1.5087331258937145e-05, "loss": 0.6609, "step": 5575 }, { "epoch": 0.7945283556568823, "grad_norm": 1.293554929521968, "learning_rate": 1.5085189973242385e-05, "loss": 0.6539, "step": 5576 }, { "epoch": 0.7946708463949843, "grad_norm": 1.3590164215549703, "learning_rate": 1.5083048373017178e-05, "loss": 0.7027, "step": 5577 }, { "epoch": 0.7948133371330863, "grad_norm": 1.3594283731947678, "learning_rate": 1.5080906458393988e-05, "loss": 0.6279, "step": 5578 }, { "epoch": 0.7949558278711883, "grad_norm": 1.4002569580700444, "learning_rate": 1.5078764229505293e-05, "loss": 0.6026, "step": 5579 }, { "epoch": 0.7950983186092904, "grad_norm": 1.3689191604812518, "learning_rate": 1.5076621686483603e-05, "loss": 0.7526, "step": 5580 }, { "epoch": 0.7952408093473924, "grad_norm": 1.3199896964202176, "learning_rate": 1.5074478829461434e-05, "loss": 0.7705, "step": 5581 }, { "epoch": 0.7953833000854944, "grad_norm": 1.2446161806807532, "learning_rate": 1.5072335658571327e-05, "loss": 0.5936, "step": 5582 }, { "epoch": 0.7955257908235964, "grad_norm": 1.2021486036979725, "learning_rate": 1.5070192173945844e-05, "loss": 0.6272, "step": 5583 }, { "epoch": 0.7956682815616984, "grad_norm": 1.354131681348316, "learning_rate": 1.5068048375717559e-05, "loss": 0.6466, "step": 5584 }, { "epoch": 0.7958107722998005, "grad_norm": 1.3658210105180033, "learning_rate": 1.5065904264019075e-05, "loss": 0.6525, "step": 5585 }, { "epoch": 0.7959532630379025, "grad_norm": 1.4898736605112186, "learning_rate": 1.5063759838983008e-05, "loss": 0.7434, "step": 5586 }, { "epoch": 0.7960957537760046, "grad_norm": 1.179615465798665, "learning_rate": 1.5061615100741997e-05, "loss": 0.5761, "step": 5587 }, { "epoch": 0.7962382445141066, "grad_norm": 1.2881349916593094, "learning_rate": 1.50594700494287e-05, "loss": 0.6084, "step": 5588 }, { "epoch": 0.7963807352522086, "grad_norm": 1.362565204043936, "learning_rate": 1.5057324685175791e-05, "loss": 0.6522, "step": 5589 }, { "epoch": 0.7965232259903107, "grad_norm": 1.4047246116225285, "learning_rate": 1.5055179008115969e-05, "loss": 0.7094, "step": 5590 }, { "epoch": 0.7966657167284127, "grad_norm": 1.2854895786967968, "learning_rate": 1.5053033018381945e-05, "loss": 0.6619, "step": 5591 }, { "epoch": 0.7968082074665147, "grad_norm": 1.2363374806228788, "learning_rate": 1.5050886716106455e-05, "loss": 0.653, "step": 5592 }, { "epoch": 0.7969506982046167, "grad_norm": 1.3468158000713653, "learning_rate": 1.504874010142225e-05, "loss": 0.6977, "step": 5593 }, { "epoch": 0.7970931889427187, "grad_norm": 1.381093160259558, "learning_rate": 1.5046593174462106e-05, "loss": 0.6398, "step": 5594 }, { "epoch": 0.7972356796808208, "grad_norm": 1.3426868118121429, "learning_rate": 1.5044445935358816e-05, "loss": 0.6332, "step": 5595 }, { "epoch": 0.7973781704189228, "grad_norm": 1.4153013278116917, "learning_rate": 1.5042298384245191e-05, "loss": 0.6681, "step": 5596 }, { "epoch": 0.7975206611570248, "grad_norm": 1.2267777928078167, "learning_rate": 1.504015052125406e-05, "loss": 0.6461, "step": 5597 }, { "epoch": 0.7976631518951268, "grad_norm": 2.277865925403564, "learning_rate": 1.5038002346518275e-05, "loss": 0.6071, "step": 5598 }, { "epoch": 0.7978056426332288, "grad_norm": 1.2532006429295344, "learning_rate": 1.5035853860170702e-05, "loss": 0.6949, "step": 5599 }, { "epoch": 0.7979481333713309, "grad_norm": 1.4782897867023614, "learning_rate": 1.5033705062344232e-05, "loss": 0.663, "step": 5600 }, { "epoch": 0.7980906241094329, "grad_norm": 1.2726032720191625, "learning_rate": 1.5031555953171777e-05, "loss": 0.6562, "step": 5601 }, { "epoch": 0.7982331148475349, "grad_norm": 1.1672452112915161, "learning_rate": 1.502940653278626e-05, "loss": 0.5994, "step": 5602 }, { "epoch": 0.7983756055856369, "grad_norm": 1.2678362135595536, "learning_rate": 1.5027256801320626e-05, "loss": 0.6417, "step": 5603 }, { "epoch": 0.7985180963237389, "grad_norm": 1.3736729999691437, "learning_rate": 1.5025106758907844e-05, "loss": 0.6698, "step": 5604 }, { "epoch": 0.798660587061841, "grad_norm": 1.2587653916549095, "learning_rate": 1.50229564056809e-05, "loss": 0.6695, "step": 5605 }, { "epoch": 0.798803077799943, "grad_norm": 1.3183894523806552, "learning_rate": 1.5020805741772792e-05, "loss": 0.7591, "step": 5606 }, { "epoch": 0.798945568538045, "grad_norm": 1.301906758536401, "learning_rate": 1.5018654767316552e-05, "loss": 0.6564, "step": 5607 }, { "epoch": 0.799088059276147, "grad_norm": 1.2340853626741664, "learning_rate": 1.501650348244521e-05, "loss": 0.661, "step": 5608 }, { "epoch": 0.799230550014249, "grad_norm": 1.4458337752057184, "learning_rate": 1.5014351887291843e-05, "loss": 0.6368, "step": 5609 }, { "epoch": 0.799373040752351, "grad_norm": 1.4227795896302322, "learning_rate": 1.5012199981989522e-05, "loss": 0.6743, "step": 5610 }, { "epoch": 0.7995155314904531, "grad_norm": 1.701113112816388, "learning_rate": 1.5010047766671353e-05, "loss": 0.6736, "step": 5611 }, { "epoch": 0.7996580222285552, "grad_norm": 1.3005507475202993, "learning_rate": 1.5007895241470447e-05, "loss": 0.7067, "step": 5612 }, { "epoch": 0.7998005129666572, "grad_norm": 1.546022273391236, "learning_rate": 1.5005742406519952e-05, "loss": 0.6281, "step": 5613 }, { "epoch": 0.7999430037047592, "grad_norm": 1.7305475157177692, "learning_rate": 1.500358926195302e-05, "loss": 0.6092, "step": 5614 }, { "epoch": 0.8000854944428613, "grad_norm": 1.305484912923231, "learning_rate": 1.5001435807902831e-05, "loss": 0.6357, "step": 5615 }, { "epoch": 0.8002279851809633, "grad_norm": 1.325396332140043, "learning_rate": 1.4999282044502577e-05, "loss": 0.6298, "step": 5616 }, { "epoch": 0.8003704759190653, "grad_norm": 1.3734027456838445, "learning_rate": 1.4997127971885476e-05, "loss": 0.6231, "step": 5617 }, { "epoch": 0.8005129666571673, "grad_norm": 1.689228098504387, "learning_rate": 1.4994973590184766e-05, "loss": 0.6818, "step": 5618 }, { "epoch": 0.8006554573952693, "grad_norm": 1.4763626622472226, "learning_rate": 1.499281889953369e-05, "loss": 0.6126, "step": 5619 }, { "epoch": 0.8007979481333714, "grad_norm": 1.331968402611033, "learning_rate": 1.499066390006553e-05, "loss": 0.6444, "step": 5620 }, { "epoch": 0.8009404388714734, "grad_norm": 1.296693078990652, "learning_rate": 1.4988508591913573e-05, "loss": 0.6535, "step": 5621 }, { "epoch": 0.8010829296095754, "grad_norm": 1.3714743642505314, "learning_rate": 1.498635297521113e-05, "loss": 0.6616, "step": 5622 }, { "epoch": 0.8012254203476774, "grad_norm": 1.2288738898252152, "learning_rate": 1.4984197050091531e-05, "loss": 0.6382, "step": 5623 }, { "epoch": 0.8013679110857794, "grad_norm": 1.3757148058603392, "learning_rate": 1.4982040816688128e-05, "loss": 0.7317, "step": 5624 }, { "epoch": 0.8015104018238814, "grad_norm": 1.2774401568675602, "learning_rate": 1.4979884275134287e-05, "loss": 0.6716, "step": 5625 }, { "epoch": 0.8016528925619835, "grad_norm": 1.270765560780606, "learning_rate": 1.4977727425563391e-05, "loss": 0.66, "step": 5626 }, { "epoch": 0.8017953833000855, "grad_norm": 1.34039935617494, "learning_rate": 1.497557026810885e-05, "loss": 0.6684, "step": 5627 }, { "epoch": 0.8019378740381875, "grad_norm": 1.3065839171107243, "learning_rate": 1.4973412802904088e-05, "loss": 0.6531, "step": 5628 }, { "epoch": 0.8020803647762895, "grad_norm": 1.3250400291947568, "learning_rate": 1.497125503008255e-05, "loss": 0.623, "step": 5629 }, { "epoch": 0.8022228555143915, "grad_norm": 1.3533700871742205, "learning_rate": 1.49690969497777e-05, "loss": 0.6617, "step": 5630 }, { "epoch": 0.8023653462524936, "grad_norm": 1.4531664644930575, "learning_rate": 1.4966938562123015e-05, "loss": 0.624, "step": 5631 }, { "epoch": 0.8025078369905956, "grad_norm": 1.3584385776942804, "learning_rate": 1.4964779867252002e-05, "loss": 0.6922, "step": 5632 }, { "epoch": 0.8026503277286976, "grad_norm": 1.3292226386215678, "learning_rate": 1.4962620865298179e-05, "loss": 0.6507, "step": 5633 }, { "epoch": 0.8027928184667996, "grad_norm": 1.3561056494097972, "learning_rate": 1.4960461556395086e-05, "loss": 0.7186, "step": 5634 }, { "epoch": 0.8029353092049016, "grad_norm": 1.3936385128470214, "learning_rate": 1.4958301940676276e-05, "loss": 0.664, "step": 5635 }, { "epoch": 0.8030777999430037, "grad_norm": 1.4931249292328588, "learning_rate": 1.4956142018275333e-05, "loss": 0.6183, "step": 5636 }, { "epoch": 0.8032202906811057, "grad_norm": 1.3821877277158943, "learning_rate": 1.495398178932585e-05, "loss": 0.7008, "step": 5637 }, { "epoch": 0.8033627814192078, "grad_norm": 1.2469984811043406, "learning_rate": 1.4951821253961442e-05, "loss": 0.6164, "step": 5638 }, { "epoch": 0.8035052721573098, "grad_norm": 1.2704828314082333, "learning_rate": 1.4949660412315743e-05, "loss": 0.635, "step": 5639 }, { "epoch": 0.8036477628954118, "grad_norm": 1.4776983118732332, "learning_rate": 1.4947499264522409e-05, "loss": 0.752, "step": 5640 }, { "epoch": 0.8037902536335139, "grad_norm": 1.2021454109720242, "learning_rate": 1.4945337810715105e-05, "loss": 0.617, "step": 5641 }, { "epoch": 0.8039327443716159, "grad_norm": 1.2205239756695743, "learning_rate": 1.4943176051027525e-05, "loss": 0.5901, "step": 5642 }, { "epoch": 0.8040752351097179, "grad_norm": 1.4655822604045174, "learning_rate": 1.4941013985593382e-05, "loss": 0.606, "step": 5643 }, { "epoch": 0.8042177258478199, "grad_norm": 1.1829837857028287, "learning_rate": 1.4938851614546404e-05, "loss": 0.555, "step": 5644 }, { "epoch": 0.8043602165859219, "grad_norm": 1.2993923213817555, "learning_rate": 1.4936688938020335e-05, "loss": 0.6537, "step": 5645 }, { "epoch": 0.804502707324024, "grad_norm": 1.302288718634412, "learning_rate": 1.493452595614894e-05, "loss": 0.7016, "step": 5646 }, { "epoch": 0.804645198062126, "grad_norm": 1.4259017523408897, "learning_rate": 1.493236266906601e-05, "loss": 0.6815, "step": 5647 }, { "epoch": 0.804787688800228, "grad_norm": 1.2002200001813268, "learning_rate": 1.4930199076905347e-05, "loss": 0.6214, "step": 5648 }, { "epoch": 0.80493017953833, "grad_norm": 1.3773605368952473, "learning_rate": 1.4928035179800772e-05, "loss": 0.6767, "step": 5649 }, { "epoch": 0.805072670276432, "grad_norm": 1.1979480458965766, "learning_rate": 1.492587097788613e-05, "loss": 0.6653, "step": 5650 }, { "epoch": 0.805215161014534, "grad_norm": 1.4334060945380018, "learning_rate": 1.4923706471295278e-05, "loss": 0.5922, "step": 5651 }, { "epoch": 0.8053576517526361, "grad_norm": 1.2366701266704994, "learning_rate": 1.49215416601621e-05, "loss": 0.6347, "step": 5652 }, { "epoch": 0.8055001424907381, "grad_norm": 1.3112562343696845, "learning_rate": 1.4919376544620492e-05, "loss": 0.6296, "step": 5653 }, { "epoch": 0.8056426332288401, "grad_norm": 1.27053466450309, "learning_rate": 1.4917211124804369e-05, "loss": 0.6503, "step": 5654 }, { "epoch": 0.8057851239669421, "grad_norm": 1.3880229145559029, "learning_rate": 1.4915045400847675e-05, "loss": 0.6488, "step": 5655 }, { "epoch": 0.8059276147050441, "grad_norm": 1.2667146782632541, "learning_rate": 1.4912879372884354e-05, "loss": 0.5381, "step": 5656 }, { "epoch": 0.8060701054431462, "grad_norm": 1.6604966163600223, "learning_rate": 1.4910713041048387e-05, "loss": 0.6895, "step": 5657 }, { "epoch": 0.8062125961812482, "grad_norm": 1.2450128866379009, "learning_rate": 1.4908546405473768e-05, "loss": 0.6311, "step": 5658 }, { "epoch": 0.8063550869193502, "grad_norm": 1.9454989359346093, "learning_rate": 1.49063794662945e-05, "loss": 0.5885, "step": 5659 }, { "epoch": 0.8064975776574522, "grad_norm": 1.4072882882848672, "learning_rate": 1.4904212223644621e-05, "loss": 0.6405, "step": 5660 }, { "epoch": 0.8066400683955542, "grad_norm": 1.2718700740899813, "learning_rate": 1.4902044677658173e-05, "loss": 0.6694, "step": 5661 }, { "epoch": 0.8067825591336563, "grad_norm": 1.5571215744680282, "learning_rate": 1.4899876828469231e-05, "loss": 0.643, "step": 5662 }, { "epoch": 0.8069250498717583, "grad_norm": 1.5008477474756228, "learning_rate": 1.4897708676211879e-05, "loss": 0.6705, "step": 5663 }, { "epoch": 0.8070675406098604, "grad_norm": 1.4109279456246104, "learning_rate": 1.489554022102022e-05, "loss": 0.6121, "step": 5664 }, { "epoch": 0.8072100313479624, "grad_norm": 1.4766521016482097, "learning_rate": 1.4893371463028378e-05, "loss": 0.7332, "step": 5665 }, { "epoch": 0.8073525220860645, "grad_norm": 1.537188571924248, "learning_rate": 1.4891202402370495e-05, "loss": 0.7077, "step": 5666 }, { "epoch": 0.8074950128241665, "grad_norm": 1.372044036395219, "learning_rate": 1.4889033039180735e-05, "loss": 0.6902, "step": 5667 }, { "epoch": 0.8076375035622685, "grad_norm": 1.3733214977878272, "learning_rate": 1.4886863373593277e-05, "loss": 0.569, "step": 5668 }, { "epoch": 0.8077799943003705, "grad_norm": 1.555032865743537, "learning_rate": 1.4884693405742318e-05, "loss": 0.7116, "step": 5669 }, { "epoch": 0.8079224850384725, "grad_norm": 2.0517586080007097, "learning_rate": 1.488252313576208e-05, "loss": 0.7101, "step": 5670 }, { "epoch": 0.8080649757765745, "grad_norm": 1.3403236996364376, "learning_rate": 1.4880352563786793e-05, "loss": 0.7303, "step": 5671 }, { "epoch": 0.8082074665146766, "grad_norm": 1.284458079554801, "learning_rate": 1.4878181689950715e-05, "loss": 0.681, "step": 5672 }, { "epoch": 0.8083499572527786, "grad_norm": 1.6124745941356655, "learning_rate": 1.487601051438812e-05, "loss": 0.613, "step": 5673 }, { "epoch": 0.8084924479908806, "grad_norm": 1.365671610344625, "learning_rate": 1.4873839037233298e-05, "loss": 0.6601, "step": 5674 }, { "epoch": 0.8086349387289826, "grad_norm": 1.4279605594270666, "learning_rate": 1.4871667258620562e-05, "loss": 0.6676, "step": 5675 }, { "epoch": 0.8087774294670846, "grad_norm": 1.4627994609774104, "learning_rate": 1.486949517868424e-05, "loss": 0.5719, "step": 5676 }, { "epoch": 0.8089199202051867, "grad_norm": 1.3676659512138722, "learning_rate": 1.4867322797558679e-05, "loss": 0.6369, "step": 5677 }, { "epoch": 0.8090624109432887, "grad_norm": 1.4657135085777728, "learning_rate": 1.4865150115378248e-05, "loss": 0.5882, "step": 5678 }, { "epoch": 0.8092049016813907, "grad_norm": 1.437102662039904, "learning_rate": 1.4862977132277329e-05, "loss": 0.6479, "step": 5679 }, { "epoch": 0.8093473924194927, "grad_norm": 1.290427158890735, "learning_rate": 1.4860803848390328e-05, "loss": 0.5849, "step": 5680 }, { "epoch": 0.8094898831575947, "grad_norm": 1.3506491967196252, "learning_rate": 1.4858630263851672e-05, "loss": 0.7093, "step": 5681 }, { "epoch": 0.8096323738956968, "grad_norm": 1.3886828201287769, "learning_rate": 1.4856456378795794e-05, "loss": 0.639, "step": 5682 }, { "epoch": 0.8097748646337988, "grad_norm": 1.4715398735953074, "learning_rate": 1.485428219335716e-05, "loss": 0.7187, "step": 5683 }, { "epoch": 0.8099173553719008, "grad_norm": 1.3036572443467431, "learning_rate": 1.4852107707670244e-05, "loss": 0.6819, "step": 5684 }, { "epoch": 0.8100598461100028, "grad_norm": 1.3915244158768556, "learning_rate": 1.4849932921869546e-05, "loss": 0.6186, "step": 5685 }, { "epoch": 0.8102023368481048, "grad_norm": 4.326817776436145, "learning_rate": 1.4847757836089577e-05, "loss": 0.6113, "step": 5686 }, { "epoch": 0.8103448275862069, "grad_norm": 1.508717356392951, "learning_rate": 1.4845582450464877e-05, "loss": 0.6874, "step": 5687 }, { "epoch": 0.8104873183243089, "grad_norm": 1.2916476428539676, "learning_rate": 1.4843406765129995e-05, "loss": 0.6418, "step": 5688 }, { "epoch": 0.8106298090624109, "grad_norm": 1.2519065773314246, "learning_rate": 1.48412307802195e-05, "loss": 0.6394, "step": 5689 }, { "epoch": 0.810772299800513, "grad_norm": 1.4897239765987418, "learning_rate": 1.4839054495867986e-05, "loss": 0.7504, "step": 5690 }, { "epoch": 0.810914790538615, "grad_norm": 1.3706234691586001, "learning_rate": 1.4836877912210056e-05, "loss": 0.7621, "step": 5691 }, { "epoch": 0.8110572812767171, "grad_norm": 1.2529966400675807, "learning_rate": 1.4834701029380346e-05, "loss": 0.633, "step": 5692 }, { "epoch": 0.8111997720148191, "grad_norm": 1.3514564158426392, "learning_rate": 1.483252384751349e-05, "loss": 0.5699, "step": 5693 }, { "epoch": 0.8113422627529211, "grad_norm": 1.379806327509141, "learning_rate": 1.4830346366744157e-05, "loss": 0.6673, "step": 5694 }, { "epoch": 0.8114847534910231, "grad_norm": 1.3401982911693304, "learning_rate": 1.4828168587207026e-05, "loss": 0.6931, "step": 5695 }, { "epoch": 0.8116272442291251, "grad_norm": 1.2002009187354958, "learning_rate": 1.4825990509036805e-05, "loss": 0.5527, "step": 5696 }, { "epoch": 0.8117697349672272, "grad_norm": 1.2549753840479048, "learning_rate": 1.4823812132368205e-05, "loss": 0.6088, "step": 5697 }, { "epoch": 0.8119122257053292, "grad_norm": 1.5473181175158028, "learning_rate": 1.4821633457335967e-05, "loss": 0.6707, "step": 5698 }, { "epoch": 0.8120547164434312, "grad_norm": 1.2450564823020336, "learning_rate": 1.4819454484074847e-05, "loss": 0.6569, "step": 5699 }, { "epoch": 0.8121972071815332, "grad_norm": 1.3312198404212456, "learning_rate": 1.4817275212719619e-05, "loss": 0.5429, "step": 5700 }, { "epoch": 0.8123396979196352, "grad_norm": 1.3123244376659666, "learning_rate": 1.4815095643405076e-05, "loss": 0.6664, "step": 5701 }, { "epoch": 0.8124821886577372, "grad_norm": 1.3080389128943388, "learning_rate": 1.4812915776266024e-05, "loss": 0.7658, "step": 5702 }, { "epoch": 0.8126246793958393, "grad_norm": 1.391074923793814, "learning_rate": 1.4810735611437304e-05, "loss": 0.7062, "step": 5703 }, { "epoch": 0.8127671701339413, "grad_norm": 1.2426899210797433, "learning_rate": 1.4808555149053756e-05, "loss": 0.6374, "step": 5704 }, { "epoch": 0.8129096608720433, "grad_norm": 1.9359627898234322, "learning_rate": 1.4806374389250247e-05, "loss": 0.6217, "step": 5705 }, { "epoch": 0.8130521516101453, "grad_norm": 1.2557733518033678, "learning_rate": 1.4804193332161665e-05, "loss": 0.6189, "step": 5706 }, { "epoch": 0.8131946423482473, "grad_norm": 1.6810736579775758, "learning_rate": 1.4802011977922912e-05, "loss": 0.6763, "step": 5707 }, { "epoch": 0.8133371330863494, "grad_norm": 1.356170632573754, "learning_rate": 1.4799830326668907e-05, "loss": 0.6811, "step": 5708 }, { "epoch": 0.8134796238244514, "grad_norm": 1.2865310568020853, "learning_rate": 1.4797648378534593e-05, "loss": 0.6852, "step": 5709 }, { "epoch": 0.8136221145625534, "grad_norm": 1.2560976185948138, "learning_rate": 1.4795466133654927e-05, "loss": 0.6507, "step": 5710 }, { "epoch": 0.8137646053006554, "grad_norm": 1.3929463413915664, "learning_rate": 1.4793283592164887e-05, "loss": 0.6771, "step": 5711 }, { "epoch": 0.8139070960387574, "grad_norm": 1.396442443290756, "learning_rate": 1.4791100754199467e-05, "loss": 0.7251, "step": 5712 }, { "epoch": 0.8140495867768595, "grad_norm": 1.2607301732668563, "learning_rate": 1.4788917619893681e-05, "loss": 0.5452, "step": 5713 }, { "epoch": 0.8141920775149615, "grad_norm": 1.2204873321266756, "learning_rate": 1.4786734189382559e-05, "loss": 0.5841, "step": 5714 }, { "epoch": 0.8143345682530635, "grad_norm": 1.3741042372971346, "learning_rate": 1.4784550462801158e-05, "loss": 0.6141, "step": 5715 }, { "epoch": 0.8144770589911656, "grad_norm": 1.5494028819015455, "learning_rate": 1.4782366440284537e-05, "loss": 0.6955, "step": 5716 }, { "epoch": 0.8146195497292676, "grad_norm": 1.3997871481540036, "learning_rate": 1.4780182121967786e-05, "loss": 0.5924, "step": 5717 }, { "epoch": 0.8147620404673697, "grad_norm": 1.2908523441573623, "learning_rate": 1.4777997507986013e-05, "loss": 0.7092, "step": 5718 }, { "epoch": 0.8149045312054717, "grad_norm": 1.4174900773916586, "learning_rate": 1.4775812598474339e-05, "loss": 0.6987, "step": 5719 }, { "epoch": 0.8150470219435737, "grad_norm": 1.2550190516163204, "learning_rate": 1.4773627393567903e-05, "loss": 0.6451, "step": 5720 }, { "epoch": 0.8151895126816757, "grad_norm": 1.3894757582741688, "learning_rate": 1.4771441893401871e-05, "loss": 0.657, "step": 5721 }, { "epoch": 0.8153320034197777, "grad_norm": 1.333030187880953, "learning_rate": 1.476925609811142e-05, "loss": 0.6252, "step": 5722 }, { "epoch": 0.8154744941578798, "grad_norm": 1.3353904464521629, "learning_rate": 1.476707000783174e-05, "loss": 0.6337, "step": 5723 }, { "epoch": 0.8156169848959818, "grad_norm": 1.1615966324492568, "learning_rate": 1.4764883622698047e-05, "loss": 0.5864, "step": 5724 }, { "epoch": 0.8157594756340838, "grad_norm": 1.6987262415069722, "learning_rate": 1.4762696942845583e-05, "loss": 0.6837, "step": 5725 }, { "epoch": 0.8159019663721858, "grad_norm": 1.2959892780169067, "learning_rate": 1.4760509968409589e-05, "loss": 0.6865, "step": 5726 }, { "epoch": 0.8160444571102878, "grad_norm": 1.267367919025049, "learning_rate": 1.4758322699525338e-05, "loss": 0.685, "step": 5727 }, { "epoch": 0.8161869478483899, "grad_norm": 1.3219925509852752, "learning_rate": 1.4756135136328118e-05, "loss": 0.5842, "step": 5728 }, { "epoch": 0.8163294385864919, "grad_norm": 1.5311575359946905, "learning_rate": 1.4753947278953235e-05, "loss": 0.6266, "step": 5729 }, { "epoch": 0.8164719293245939, "grad_norm": 1.3931465209693379, "learning_rate": 1.4751759127536012e-05, "loss": 0.7322, "step": 5730 }, { "epoch": 0.8166144200626959, "grad_norm": 1.2719518795059461, "learning_rate": 1.4749570682211787e-05, "loss": 0.6484, "step": 5731 }, { "epoch": 0.8167569108007979, "grad_norm": 1.206604682856041, "learning_rate": 1.4747381943115926e-05, "loss": 0.6396, "step": 5732 }, { "epoch": 0.8168994015389, "grad_norm": 1.369611615446905, "learning_rate": 1.4745192910383809e-05, "loss": 0.6779, "step": 5733 }, { "epoch": 0.817041892277002, "grad_norm": 1.3072806875644905, "learning_rate": 1.4743003584150828e-05, "loss": 0.6833, "step": 5734 }, { "epoch": 0.817184383015104, "grad_norm": 1.5684523291217656, "learning_rate": 1.4740813964552399e-05, "loss": 0.6, "step": 5735 }, { "epoch": 0.817326873753206, "grad_norm": 1.278409354686247, "learning_rate": 1.4738624051723954e-05, "loss": 0.6458, "step": 5736 }, { "epoch": 0.817469364491308, "grad_norm": 1.406593773020953, "learning_rate": 1.4736433845800947e-05, "loss": 0.6572, "step": 5737 }, { "epoch": 0.81761185522941, "grad_norm": 1.2409772842322948, "learning_rate": 1.4734243346918842e-05, "loss": 0.5949, "step": 5738 }, { "epoch": 0.8177543459675121, "grad_norm": 1.3166769803762637, "learning_rate": 1.473205255521313e-05, "loss": 0.6717, "step": 5739 }, { "epoch": 0.8178968367056141, "grad_norm": 1.2345898827023736, "learning_rate": 1.4729861470819318e-05, "loss": 0.6284, "step": 5740 }, { "epoch": 0.8180393274437162, "grad_norm": 1.3523542899209917, "learning_rate": 1.4727670093872927e-05, "loss": 0.6218, "step": 5741 }, { "epoch": 0.8181818181818182, "grad_norm": 1.3778938224761592, "learning_rate": 1.47254784245095e-05, "loss": 0.6797, "step": 5742 }, { "epoch": 0.8183243089199203, "grad_norm": 1.5371482906921319, "learning_rate": 1.4723286462864591e-05, "loss": 0.5893, "step": 5743 }, { "epoch": 0.8184667996580223, "grad_norm": 1.3663803460312098, "learning_rate": 1.472109420907379e-05, "loss": 0.6161, "step": 5744 }, { "epoch": 0.8186092903961243, "grad_norm": 1.2104317154812227, "learning_rate": 1.471890166327268e-05, "loss": 0.6412, "step": 5745 }, { "epoch": 0.8187517811342263, "grad_norm": 1.5214294619494895, "learning_rate": 1.4716708825596879e-05, "loss": 0.6434, "step": 5746 }, { "epoch": 0.8188942718723283, "grad_norm": 1.435194456148142, "learning_rate": 1.4714515696182021e-05, "loss": 0.5622, "step": 5747 }, { "epoch": 0.8190367626104303, "grad_norm": 1.3018365469294138, "learning_rate": 1.4712322275163759e-05, "loss": 0.6676, "step": 5748 }, { "epoch": 0.8191792533485324, "grad_norm": 1.2893475069232943, "learning_rate": 1.4710128562677754e-05, "loss": 0.6366, "step": 5749 }, { "epoch": 0.8193217440866344, "grad_norm": 1.3495259719850734, "learning_rate": 1.4707934558859697e-05, "loss": 0.7022, "step": 5750 }, { "epoch": 0.8194642348247364, "grad_norm": 1.3742318143763774, "learning_rate": 1.470574026384529e-05, "loss": 0.6312, "step": 5751 }, { "epoch": 0.8196067255628384, "grad_norm": 1.2826696157050597, "learning_rate": 1.4703545677770254e-05, "loss": 0.6069, "step": 5752 }, { "epoch": 0.8197492163009404, "grad_norm": 1.3901229286632104, "learning_rate": 1.4701350800770331e-05, "loss": 0.6691, "step": 5753 }, { "epoch": 0.8198917070390425, "grad_norm": 1.3355577551125217, "learning_rate": 1.4699155632981277e-05, "loss": 0.6784, "step": 5754 }, { "epoch": 0.8200341977771445, "grad_norm": 1.3292333250984436, "learning_rate": 1.4696960174538873e-05, "loss": 0.5916, "step": 5755 }, { "epoch": 0.8201766885152465, "grad_norm": 1.6464900639315772, "learning_rate": 1.4694764425578908e-05, "loss": 0.7842, "step": 5756 }, { "epoch": 0.8203191792533485, "grad_norm": 1.3834578453800497, "learning_rate": 1.4692568386237196e-05, "loss": 0.7273, "step": 5757 }, { "epoch": 0.8204616699914505, "grad_norm": 1.4675662829632035, "learning_rate": 1.4690372056649564e-05, "loss": 0.7205, "step": 5758 }, { "epoch": 0.8206041607295526, "grad_norm": 1.5872565531901255, "learning_rate": 1.4688175436951867e-05, "loss": 0.6378, "step": 5759 }, { "epoch": 0.8207466514676546, "grad_norm": 1.4772901038427635, "learning_rate": 1.4685978527279962e-05, "loss": 0.6191, "step": 5760 }, { "epoch": 0.8208891422057566, "grad_norm": 1.2587571609818533, "learning_rate": 1.4683781327769739e-05, "loss": 0.6011, "step": 5761 }, { "epoch": 0.8210316329438586, "grad_norm": 1.3543977603956048, "learning_rate": 1.46815838385571e-05, "loss": 0.6594, "step": 5762 }, { "epoch": 0.8211741236819606, "grad_norm": 1.2927997984308555, "learning_rate": 1.4679386059777963e-05, "loss": 0.6974, "step": 5763 }, { "epoch": 0.8213166144200627, "grad_norm": 1.448145031747027, "learning_rate": 1.4677187991568263e-05, "loss": 0.7391, "step": 5764 }, { "epoch": 0.8214591051581647, "grad_norm": 1.3571382056262016, "learning_rate": 1.4674989634063956e-05, "loss": 0.6451, "step": 5765 }, { "epoch": 0.8216015958962667, "grad_norm": 1.2631263025090451, "learning_rate": 1.467279098740102e-05, "loss": 0.6566, "step": 5766 }, { "epoch": 0.8217440866343688, "grad_norm": 1.3732679286857379, "learning_rate": 1.4670592051715442e-05, "loss": 0.7, "step": 5767 }, { "epoch": 0.8218865773724708, "grad_norm": 1.2636525748270788, "learning_rate": 1.4668392827143231e-05, "loss": 0.6176, "step": 5768 }, { "epoch": 0.8220290681105729, "grad_norm": 1.3623365614115295, "learning_rate": 1.4666193313820418e-05, "loss": 0.7103, "step": 5769 }, { "epoch": 0.8221715588486749, "grad_norm": 1.4632605168260522, "learning_rate": 1.4663993511883045e-05, "loss": 0.6156, "step": 5770 }, { "epoch": 0.8223140495867769, "grad_norm": 1.2952125310706155, "learning_rate": 1.4661793421467174e-05, "loss": 0.6092, "step": 5771 }, { "epoch": 0.8224565403248789, "grad_norm": 1.2706674601491315, "learning_rate": 1.4659593042708889e-05, "loss": 0.6487, "step": 5772 }, { "epoch": 0.8225990310629809, "grad_norm": 1.3550019404903217, "learning_rate": 1.4657392375744282e-05, "loss": 0.6428, "step": 5773 }, { "epoch": 0.822741521801083, "grad_norm": 1.3314510308557324, "learning_rate": 1.4655191420709476e-05, "loss": 0.6747, "step": 5774 }, { "epoch": 0.822884012539185, "grad_norm": 1.2484938713236617, "learning_rate": 1.4652990177740599e-05, "loss": 0.6445, "step": 5775 }, { "epoch": 0.823026503277287, "grad_norm": 1.3392508304447122, "learning_rate": 1.4650788646973805e-05, "loss": 0.6494, "step": 5776 }, { "epoch": 0.823168994015389, "grad_norm": 1.2721263855393312, "learning_rate": 1.4648586828545273e-05, "loss": 0.6765, "step": 5777 }, { "epoch": 0.823311484753491, "grad_norm": 1.2868534266212406, "learning_rate": 1.4646384722591173e-05, "loss": 0.6574, "step": 5778 }, { "epoch": 0.823453975491593, "grad_norm": 1.2230468829604486, "learning_rate": 1.4644182329247722e-05, "loss": 0.6928, "step": 5779 }, { "epoch": 0.8235964662296951, "grad_norm": 1.4176468413903431, "learning_rate": 1.4641979648651142e-05, "loss": 0.7076, "step": 5780 }, { "epoch": 0.8237389569677971, "grad_norm": 1.330503844493414, "learning_rate": 1.4639776680937672e-05, "loss": 0.6562, "step": 5781 }, { "epoch": 0.8238814477058991, "grad_norm": 1.9891358628710432, "learning_rate": 1.4637573426243567e-05, "loss": 0.6357, "step": 5782 }, { "epoch": 0.8240239384440011, "grad_norm": 1.2280437052851263, "learning_rate": 1.4635369884705108e-05, "loss": 0.6002, "step": 5783 }, { "epoch": 0.8241664291821031, "grad_norm": 1.4178277632996001, "learning_rate": 1.463316605645859e-05, "loss": 0.651, "step": 5784 }, { "epoch": 0.8243089199202052, "grad_norm": 1.291785757907274, "learning_rate": 1.4630961941640323e-05, "loss": 0.643, "step": 5785 }, { "epoch": 0.8244514106583072, "grad_norm": 1.4912124675637013, "learning_rate": 1.4628757540386631e-05, "loss": 0.6453, "step": 5786 }, { "epoch": 0.8245939013964092, "grad_norm": 2.67943886415, "learning_rate": 1.4626552852833871e-05, "loss": 0.6993, "step": 5787 }, { "epoch": 0.8247363921345112, "grad_norm": 1.3107456539100704, "learning_rate": 1.46243478791184e-05, "loss": 0.6975, "step": 5788 }, { "epoch": 0.8248788828726132, "grad_norm": 1.2384211092286186, "learning_rate": 1.4622142619376605e-05, "loss": 0.6622, "step": 5789 }, { "epoch": 0.8250213736107153, "grad_norm": 1.1665147700223832, "learning_rate": 1.4619937073744884e-05, "loss": 0.5815, "step": 5790 }, { "epoch": 0.8251638643488173, "grad_norm": 1.3436103368667462, "learning_rate": 1.4617731242359656e-05, "loss": 0.6705, "step": 5791 }, { "epoch": 0.8253063550869193, "grad_norm": 1.2868440418766214, "learning_rate": 1.4615525125357357e-05, "loss": 0.6747, "step": 5792 }, { "epoch": 0.8254488458250214, "grad_norm": 1.2595772797626807, "learning_rate": 1.4613318722874442e-05, "loss": 0.6347, "step": 5793 }, { "epoch": 0.8255913365631234, "grad_norm": 1.3627322732328677, "learning_rate": 1.4611112035047375e-05, "loss": 0.6217, "step": 5794 }, { "epoch": 0.8257338273012255, "grad_norm": 1.5308518982806802, "learning_rate": 1.4608905062012651e-05, "loss": 0.6825, "step": 5795 }, { "epoch": 0.8258763180393275, "grad_norm": 1.3468600216563946, "learning_rate": 1.4606697803906777e-05, "loss": 0.6145, "step": 5796 }, { "epoch": 0.8260188087774295, "grad_norm": 1.6257018703590154, "learning_rate": 1.460449026086627e-05, "loss": 0.7086, "step": 5797 }, { "epoch": 0.8261612995155315, "grad_norm": 1.2310974449256566, "learning_rate": 1.4602282433027678e-05, "loss": 0.6576, "step": 5798 }, { "epoch": 0.8263037902536335, "grad_norm": 1.4110152778684089, "learning_rate": 1.4600074320527557e-05, "loss": 0.6137, "step": 5799 }, { "epoch": 0.8264462809917356, "grad_norm": 1.2038486760362634, "learning_rate": 1.459786592350249e-05, "loss": 0.6821, "step": 5800 }, { "epoch": 0.8265887717298376, "grad_norm": 1.3489560593333494, "learning_rate": 1.459565724208906e-05, "loss": 0.6578, "step": 5801 }, { "epoch": 0.8267312624679396, "grad_norm": 1.2281474485825248, "learning_rate": 1.459344827642389e-05, "loss": 0.6527, "step": 5802 }, { "epoch": 0.8268737532060416, "grad_norm": 1.4067774607779093, "learning_rate": 1.45912390266436e-05, "loss": 0.6915, "step": 5803 }, { "epoch": 0.8270162439441436, "grad_norm": 1.4237484935275315, "learning_rate": 1.4589029492884845e-05, "loss": 0.6862, "step": 5804 }, { "epoch": 0.8271587346822457, "grad_norm": 1.2699833387193002, "learning_rate": 1.4586819675284286e-05, "loss": 0.5515, "step": 5805 }, { "epoch": 0.8273012254203477, "grad_norm": 1.380506405566398, "learning_rate": 1.4584609573978603e-05, "loss": 0.6811, "step": 5806 }, { "epoch": 0.8274437161584497, "grad_norm": 1.4543090285394307, "learning_rate": 1.45823991891045e-05, "loss": 0.6763, "step": 5807 }, { "epoch": 0.8275862068965517, "grad_norm": 1.2824297596487504, "learning_rate": 1.4580188520798692e-05, "loss": 0.6651, "step": 5808 }, { "epoch": 0.8277286976346537, "grad_norm": 1.3412238498729838, "learning_rate": 1.4577977569197915e-05, "loss": 0.6339, "step": 5809 }, { "epoch": 0.8278711883727558, "grad_norm": 1.2903316680085555, "learning_rate": 1.4575766334438918e-05, "loss": 0.6294, "step": 5810 }, { "epoch": 0.8280136791108578, "grad_norm": 1.4988189186698762, "learning_rate": 1.4573554816658474e-05, "loss": 0.6603, "step": 5811 }, { "epoch": 0.8281561698489598, "grad_norm": 1.3227807561166314, "learning_rate": 1.4571343015993373e-05, "loss": 0.6062, "step": 5812 }, { "epoch": 0.8282986605870618, "grad_norm": 1.0735934048439368, "learning_rate": 1.4569130932580415e-05, "loss": 0.5424, "step": 5813 }, { "epoch": 0.8284411513251638, "grad_norm": 1.3044490158841653, "learning_rate": 1.4566918566556425e-05, "loss": 0.6709, "step": 5814 }, { "epoch": 0.8285836420632658, "grad_norm": 1.5336332236933308, "learning_rate": 1.4564705918058239e-05, "loss": 0.6408, "step": 5815 }, { "epoch": 0.8287261328013679, "grad_norm": 1.3199418018390496, "learning_rate": 1.456249298722272e-05, "loss": 0.6512, "step": 5816 }, { "epoch": 0.8288686235394699, "grad_norm": 1.2816909980883564, "learning_rate": 1.456027977418674e-05, "loss": 0.6681, "step": 5817 }, { "epoch": 0.8290111142775719, "grad_norm": 1.517198025405016, "learning_rate": 1.4558066279087189e-05, "loss": 0.7269, "step": 5818 }, { "epoch": 0.829153605015674, "grad_norm": 1.8591582099784068, "learning_rate": 1.455585250206098e-05, "loss": 0.638, "step": 5819 }, { "epoch": 0.829296095753776, "grad_norm": 1.4629521728441381, "learning_rate": 1.4553638443245038e-05, "loss": 0.674, "step": 5820 }, { "epoch": 0.8294385864918781, "grad_norm": 1.1961220958687684, "learning_rate": 1.4551424102776306e-05, "loss": 0.6341, "step": 5821 }, { "epoch": 0.8295810772299801, "grad_norm": 1.5672505450459389, "learning_rate": 1.4549209480791753e-05, "loss": 0.6566, "step": 5822 }, { "epoch": 0.8297235679680821, "grad_norm": 1.256788885945392, "learning_rate": 1.4546994577428352e-05, "loss": 0.5749, "step": 5823 }, { "epoch": 0.8298660587061841, "grad_norm": 1.2463102348235235, "learning_rate": 1.45447793928231e-05, "loss": 0.656, "step": 5824 }, { "epoch": 0.8300085494442861, "grad_norm": 1.4036639947449803, "learning_rate": 1.4542563927113013e-05, "loss": 0.6644, "step": 5825 }, { "epoch": 0.8301510401823882, "grad_norm": 1.3126013187066847, "learning_rate": 1.4540348180435124e-05, "loss": 0.5794, "step": 5826 }, { "epoch": 0.8302935309204902, "grad_norm": 1.3579669415675346, "learning_rate": 1.4538132152926479e-05, "loss": 0.6443, "step": 5827 }, { "epoch": 0.8304360216585922, "grad_norm": 1.4150930475744834, "learning_rate": 1.4535915844724144e-05, "loss": 0.6869, "step": 5828 }, { "epoch": 0.8305785123966942, "grad_norm": 1.2728218217899736, "learning_rate": 1.4533699255965205e-05, "loss": 0.6815, "step": 5829 }, { "epoch": 0.8307210031347962, "grad_norm": 1.2987970843323517, "learning_rate": 1.4531482386786764e-05, "loss": 0.7001, "step": 5830 }, { "epoch": 0.8308634938728983, "grad_norm": 1.3599692594672295, "learning_rate": 1.4529265237325934e-05, "loss": 0.6494, "step": 5831 }, { "epoch": 0.8310059846110003, "grad_norm": 1.3847756992167612, "learning_rate": 1.4527047807719856e-05, "loss": 0.626, "step": 5832 }, { "epoch": 0.8311484753491023, "grad_norm": 1.2977853924578913, "learning_rate": 1.452483009810568e-05, "loss": 0.6076, "step": 5833 }, { "epoch": 0.8312909660872043, "grad_norm": 1.2907300131168695, "learning_rate": 1.4522612108620578e-05, "loss": 0.6547, "step": 5834 }, { "epoch": 0.8314334568253063, "grad_norm": 2.127734937394439, "learning_rate": 1.4520393839401734e-05, "loss": 0.6655, "step": 5835 }, { "epoch": 0.8315759475634084, "grad_norm": 1.2654713279636682, "learning_rate": 1.4518175290586358e-05, "loss": 0.5921, "step": 5836 }, { "epoch": 0.8317184383015104, "grad_norm": 2.168137766105797, "learning_rate": 1.4515956462311673e-05, "loss": 0.6434, "step": 5837 }, { "epoch": 0.8318609290396124, "grad_norm": 1.3460347861092892, "learning_rate": 1.4513737354714912e-05, "loss": 0.6599, "step": 5838 }, { "epoch": 0.8320034197777144, "grad_norm": 1.2702016147113309, "learning_rate": 1.4511517967933338e-05, "loss": 0.6275, "step": 5839 }, { "epoch": 0.8321459105158164, "grad_norm": 1.332749137586874, "learning_rate": 1.450929830210422e-05, "loss": 0.7061, "step": 5840 }, { "epoch": 0.8322884012539185, "grad_norm": 1.3769671626307525, "learning_rate": 1.4507078357364854e-05, "loss": 0.6882, "step": 5841 }, { "epoch": 0.8324308919920205, "grad_norm": 1.2930940982864558, "learning_rate": 1.4504858133852543e-05, "loss": 0.644, "step": 5842 }, { "epoch": 0.8325733827301225, "grad_norm": 1.4053044800540073, "learning_rate": 1.4502637631704621e-05, "loss": 0.6438, "step": 5843 }, { "epoch": 0.8327158734682245, "grad_norm": 1.3258715615747043, "learning_rate": 1.4500416851058425e-05, "loss": 0.5915, "step": 5844 }, { "epoch": 0.8328583642063266, "grad_norm": 1.3330864148873691, "learning_rate": 1.4498195792051318e-05, "loss": 0.5656, "step": 5845 }, { "epoch": 0.8330008549444287, "grad_norm": 1.4549134216822754, "learning_rate": 1.4495974454820672e-05, "loss": 0.6379, "step": 5846 }, { "epoch": 0.8331433456825307, "grad_norm": 1.2667604247538062, "learning_rate": 1.4493752839503887e-05, "loss": 0.6691, "step": 5847 }, { "epoch": 0.8332858364206327, "grad_norm": 1.2614768179418154, "learning_rate": 1.4491530946238375e-05, "loss": 0.6098, "step": 5848 }, { "epoch": 0.8334283271587347, "grad_norm": 1.3724251014966478, "learning_rate": 1.4489308775161564e-05, "loss": 0.6275, "step": 5849 }, { "epoch": 0.8335708178968367, "grad_norm": 1.4534195321932302, "learning_rate": 1.4487086326410898e-05, "loss": 0.6834, "step": 5850 }, { "epoch": 0.8337133086349388, "grad_norm": 1.415871048923804, "learning_rate": 1.4484863600123844e-05, "loss": 0.6595, "step": 5851 }, { "epoch": 0.8338557993730408, "grad_norm": 1.3806373697154177, "learning_rate": 1.4482640596437883e-05, "loss": 0.7636, "step": 5852 }, { "epoch": 0.8339982901111428, "grad_norm": 1.3911722901438326, "learning_rate": 1.4480417315490509e-05, "loss": 0.6125, "step": 5853 }, { "epoch": 0.8341407808492448, "grad_norm": 1.4389715650931212, "learning_rate": 1.4478193757419239e-05, "loss": 0.7063, "step": 5854 }, { "epoch": 0.8342832715873468, "grad_norm": 1.3830404345839271, "learning_rate": 1.4475969922361605e-05, "loss": 0.6433, "step": 5855 }, { "epoch": 0.8344257623254488, "grad_norm": 1.4004984362601767, "learning_rate": 1.4473745810455157e-05, "loss": 0.5959, "step": 5856 }, { "epoch": 0.8345682530635509, "grad_norm": 1.2880134296296957, "learning_rate": 1.4471521421837457e-05, "loss": 0.6029, "step": 5857 }, { "epoch": 0.8347107438016529, "grad_norm": 1.470748916929436, "learning_rate": 1.4469296756646097e-05, "loss": 0.6318, "step": 5858 }, { "epoch": 0.8348532345397549, "grad_norm": 1.3205417900709981, "learning_rate": 1.4467071815018671e-05, "loss": 0.7005, "step": 5859 }, { "epoch": 0.8349957252778569, "grad_norm": 1.3908751682428249, "learning_rate": 1.4464846597092796e-05, "loss": 0.6074, "step": 5860 }, { "epoch": 0.835138216015959, "grad_norm": 1.2423000324733764, "learning_rate": 1.4462621103006112e-05, "loss": 0.605, "step": 5861 }, { "epoch": 0.835280706754061, "grad_norm": 1.4475222173184759, "learning_rate": 1.4460395332896267e-05, "loss": 0.6555, "step": 5862 }, { "epoch": 0.835423197492163, "grad_norm": 1.6902645281807134, "learning_rate": 1.4458169286900927e-05, "loss": 0.648, "step": 5863 }, { "epoch": 0.835565688230265, "grad_norm": 1.4690679538517804, "learning_rate": 1.4455942965157785e-05, "loss": 0.6753, "step": 5864 }, { "epoch": 0.835708178968367, "grad_norm": 1.2308878251419808, "learning_rate": 1.445371636780454e-05, "loss": 0.6705, "step": 5865 }, { "epoch": 0.835850669706469, "grad_norm": 1.338133821481727, "learning_rate": 1.4451489494978914e-05, "loss": 0.592, "step": 5866 }, { "epoch": 0.8359931604445711, "grad_norm": 1.3525050797484304, "learning_rate": 1.444926234681864e-05, "loss": 0.6517, "step": 5867 }, { "epoch": 0.8361356511826731, "grad_norm": 1.3744182453434106, "learning_rate": 1.4447034923461476e-05, "loss": 0.6525, "step": 5868 }, { "epoch": 0.8362781419207751, "grad_norm": 1.273332564556238, "learning_rate": 1.4444807225045192e-05, "loss": 0.5633, "step": 5869 }, { "epoch": 0.8364206326588772, "grad_norm": 1.5109291486953158, "learning_rate": 1.4442579251707576e-05, "loss": 0.6391, "step": 5870 }, { "epoch": 0.8365631233969792, "grad_norm": 1.620159476773445, "learning_rate": 1.4440351003586433e-05, "loss": 0.6515, "step": 5871 }, { "epoch": 0.8367056141350813, "grad_norm": 1.2774692376851013, "learning_rate": 1.4438122480819586e-05, "loss": 0.6652, "step": 5872 }, { "epoch": 0.8368481048731833, "grad_norm": 1.5890075946663367, "learning_rate": 1.4435893683544873e-05, "loss": 0.6636, "step": 5873 }, { "epoch": 0.8369905956112853, "grad_norm": 1.1869114366554772, "learning_rate": 1.4433664611900154e-05, "loss": 0.5822, "step": 5874 }, { "epoch": 0.8371330863493873, "grad_norm": 1.2323721856008405, "learning_rate": 1.4431435266023295e-05, "loss": 0.6212, "step": 5875 }, { "epoch": 0.8372755770874893, "grad_norm": 1.6305407540049077, "learning_rate": 1.4429205646052191e-05, "loss": 0.6921, "step": 5876 }, { "epoch": 0.8374180678255914, "grad_norm": 1.3505478382561744, "learning_rate": 1.442697575212475e-05, "loss": 0.615, "step": 5877 }, { "epoch": 0.8375605585636934, "grad_norm": 1.2304378878770257, "learning_rate": 1.442474558437889e-05, "loss": 0.6539, "step": 5878 }, { "epoch": 0.8377030493017954, "grad_norm": 1.7125702700812495, "learning_rate": 1.4422515142952558e-05, "loss": 0.6308, "step": 5879 }, { "epoch": 0.8378455400398974, "grad_norm": 1.4277872224567025, "learning_rate": 1.4420284427983708e-05, "loss": 0.6516, "step": 5880 }, { "epoch": 0.8379880307779994, "grad_norm": 1.3911370359142285, "learning_rate": 1.441805343961032e-05, "loss": 0.6155, "step": 5881 }, { "epoch": 0.8381305215161015, "grad_norm": 1.2932202869626919, "learning_rate": 1.4415822177970379e-05, "loss": 0.5461, "step": 5882 }, { "epoch": 0.8382730122542035, "grad_norm": 1.660315124669425, "learning_rate": 1.4413590643201898e-05, "loss": 0.6469, "step": 5883 }, { "epoch": 0.8384155029923055, "grad_norm": 1.340251600784219, "learning_rate": 1.44113588354429e-05, "loss": 0.5879, "step": 5884 }, { "epoch": 0.8385579937304075, "grad_norm": 1.316799069461007, "learning_rate": 1.4409126754831429e-05, "loss": 0.6667, "step": 5885 }, { "epoch": 0.8387004844685095, "grad_norm": 1.4271608474308417, "learning_rate": 1.4406894401505543e-05, "loss": 0.6649, "step": 5886 }, { "epoch": 0.8388429752066116, "grad_norm": 1.425540321754118, "learning_rate": 1.4404661775603319e-05, "loss": 0.5815, "step": 5887 }, { "epoch": 0.8389854659447136, "grad_norm": 1.3152205328188904, "learning_rate": 1.4402428877262848e-05, "loss": 0.6795, "step": 5888 }, { "epoch": 0.8391279566828156, "grad_norm": 1.2784616862800182, "learning_rate": 1.4400195706622247e-05, "loss": 0.7088, "step": 5889 }, { "epoch": 0.8392704474209176, "grad_norm": 1.3879751040957362, "learning_rate": 1.439796226381963e-05, "loss": 0.6629, "step": 5890 }, { "epoch": 0.8394129381590196, "grad_norm": 1.269853547791905, "learning_rate": 1.439572854899315e-05, "loss": 0.5836, "step": 5891 }, { "epoch": 0.8395554288971216, "grad_norm": 1.3302435563691497, "learning_rate": 1.4393494562280967e-05, "loss": 0.5051, "step": 5892 }, { "epoch": 0.8396979196352237, "grad_norm": 1.303480878714371, "learning_rate": 1.4391260303821253e-05, "loss": 0.6205, "step": 5893 }, { "epoch": 0.8398404103733257, "grad_norm": 1.309331307146573, "learning_rate": 1.4389025773752206e-05, "loss": 0.7399, "step": 5894 }, { "epoch": 0.8399829011114277, "grad_norm": 1.6614838673039107, "learning_rate": 1.4386790972212035e-05, "loss": 0.6342, "step": 5895 }, { "epoch": 0.8401253918495298, "grad_norm": 1.3864445421364222, "learning_rate": 1.4384555899338968e-05, "loss": 0.7605, "step": 5896 }, { "epoch": 0.8402678825876319, "grad_norm": 2.0014589975665347, "learning_rate": 1.438232055527125e-05, "loss": 0.6477, "step": 5897 }, { "epoch": 0.8404103733257339, "grad_norm": 1.3392878117791076, "learning_rate": 1.4380084940147141e-05, "loss": 0.6036, "step": 5898 }, { "epoch": 0.8405528640638359, "grad_norm": 1.318723307932321, "learning_rate": 1.4377849054104918e-05, "loss": 0.6796, "step": 5899 }, { "epoch": 0.8406953548019379, "grad_norm": 1.4212044709832425, "learning_rate": 1.4375612897282878e-05, "loss": 0.6696, "step": 5900 }, { "epoch": 0.8408378455400399, "grad_norm": 1.412784529236937, "learning_rate": 1.4373376469819331e-05, "loss": 0.6629, "step": 5901 }, { "epoch": 0.840980336278142, "grad_norm": 1.3110985326493905, "learning_rate": 1.4371139771852605e-05, "loss": 0.7512, "step": 5902 }, { "epoch": 0.841122827016244, "grad_norm": 1.3927934526006407, "learning_rate": 1.4368902803521044e-05, "loss": 0.6731, "step": 5903 }, { "epoch": 0.841265317754346, "grad_norm": 1.4639774560276275, "learning_rate": 1.4366665564963014e-05, "loss": 0.7162, "step": 5904 }, { "epoch": 0.841407808492448, "grad_norm": 1.368381906461978, "learning_rate": 1.4364428056316885e-05, "loss": 0.6346, "step": 5905 }, { "epoch": 0.84155029923055, "grad_norm": 1.311615125833966, "learning_rate": 1.4362190277721057e-05, "loss": 0.642, "step": 5906 }, { "epoch": 0.841692789968652, "grad_norm": 1.2756686644690856, "learning_rate": 1.4359952229313945e-05, "loss": 0.6031, "step": 5907 }, { "epoch": 0.8418352807067541, "grad_norm": 1.263962081033434, "learning_rate": 1.4357713911233972e-05, "loss": 0.642, "step": 5908 }, { "epoch": 0.8419777714448561, "grad_norm": 1.4173755958867358, "learning_rate": 1.4355475323619583e-05, "loss": 0.6966, "step": 5909 }, { "epoch": 0.8421202621829581, "grad_norm": 1.3523408591089443, "learning_rate": 1.4353236466609245e-05, "loss": 0.6429, "step": 5910 }, { "epoch": 0.8422627529210601, "grad_norm": 2.4768969464834005, "learning_rate": 1.435099734034143e-05, "loss": 0.6052, "step": 5911 }, { "epoch": 0.8424052436591621, "grad_norm": 1.2786949116166895, "learning_rate": 1.4348757944954636e-05, "loss": 0.6309, "step": 5912 }, { "epoch": 0.8425477343972642, "grad_norm": 1.2529672089195427, "learning_rate": 1.4346518280587373e-05, "loss": 0.6664, "step": 5913 }, { "epoch": 0.8426902251353662, "grad_norm": 1.2243095613109851, "learning_rate": 1.4344278347378173e-05, "loss": 0.6454, "step": 5914 }, { "epoch": 0.8428327158734682, "grad_norm": 1.4257907107579157, "learning_rate": 1.4342038145465577e-05, "loss": 0.7052, "step": 5915 }, { "epoch": 0.8429752066115702, "grad_norm": 1.3911924569484055, "learning_rate": 1.433979767498815e-05, "loss": 0.652, "step": 5916 }, { "epoch": 0.8431176973496722, "grad_norm": 1.302920039924631, "learning_rate": 1.4337556936084466e-05, "loss": 0.6376, "step": 5917 }, { "epoch": 0.8432601880877743, "grad_norm": 1.4303925546282368, "learning_rate": 1.4335315928893126e-05, "loss": 0.7085, "step": 5918 }, { "epoch": 0.8434026788258763, "grad_norm": 1.3335143098425226, "learning_rate": 1.4333074653552732e-05, "loss": 0.6321, "step": 5919 }, { "epoch": 0.8435451695639783, "grad_norm": 1.2655806921675024, "learning_rate": 1.4330833110201921e-05, "loss": 0.595, "step": 5920 }, { "epoch": 0.8436876603020803, "grad_norm": 1.4183503538539184, "learning_rate": 1.432859129897933e-05, "loss": 0.6195, "step": 5921 }, { "epoch": 0.8438301510401824, "grad_norm": 1.2722796546075694, "learning_rate": 1.4326349220023626e-05, "loss": 0.6162, "step": 5922 }, { "epoch": 0.8439726417782845, "grad_norm": 1.4553956836583382, "learning_rate": 1.4324106873473484e-05, "loss": 0.6422, "step": 5923 }, { "epoch": 0.8441151325163865, "grad_norm": 1.4155705138568928, "learning_rate": 1.4321864259467599e-05, "loss": 0.6715, "step": 5924 }, { "epoch": 0.8442576232544885, "grad_norm": 1.4131754673039467, "learning_rate": 1.4319621378144681e-05, "loss": 0.6205, "step": 5925 }, { "epoch": 0.8444001139925905, "grad_norm": 1.2264164561220705, "learning_rate": 1.4317378229643459e-05, "loss": 0.6319, "step": 5926 }, { "epoch": 0.8445426047306925, "grad_norm": 1.662078691545778, "learning_rate": 1.4315134814102674e-05, "loss": 0.5935, "step": 5927 }, { "epoch": 0.8446850954687946, "grad_norm": 1.314596191323239, "learning_rate": 1.4312891131661087e-05, "loss": 0.624, "step": 5928 }, { "epoch": 0.8448275862068966, "grad_norm": 1.378135666281911, "learning_rate": 1.4310647182457475e-05, "loss": 0.7275, "step": 5929 }, { "epoch": 0.8449700769449986, "grad_norm": 1.309488178588322, "learning_rate": 1.4308402966630634e-05, "loss": 0.6751, "step": 5930 }, { "epoch": 0.8451125676831006, "grad_norm": 1.4011720936177767, "learning_rate": 1.430615848431937e-05, "loss": 0.7055, "step": 5931 }, { "epoch": 0.8452550584212026, "grad_norm": 1.3605562662471764, "learning_rate": 1.4303913735662512e-05, "loss": 0.586, "step": 5932 }, { "epoch": 0.8453975491593047, "grad_norm": 1.520257060270106, "learning_rate": 1.4301668720798902e-05, "loss": 0.5657, "step": 5933 }, { "epoch": 0.8455400398974067, "grad_norm": 1.2575240020429388, "learning_rate": 1.4299423439867396e-05, "loss": 0.5834, "step": 5934 }, { "epoch": 0.8456825306355087, "grad_norm": 1.2742084544225982, "learning_rate": 1.4297177893006875e-05, "loss": 0.6488, "step": 5935 }, { "epoch": 0.8458250213736107, "grad_norm": 1.2807030952788387, "learning_rate": 1.4294932080356227e-05, "loss": 0.6751, "step": 5936 }, { "epoch": 0.8459675121117127, "grad_norm": 1.401603555130136, "learning_rate": 1.4292686002054366e-05, "loss": 0.6521, "step": 5937 }, { "epoch": 0.8461100028498147, "grad_norm": 1.4245381669808628, "learning_rate": 1.429043965824021e-05, "loss": 0.6675, "step": 5938 }, { "epoch": 0.8462524935879168, "grad_norm": 1.3279965865552417, "learning_rate": 1.4288193049052704e-05, "loss": 0.5746, "step": 5939 }, { "epoch": 0.8463949843260188, "grad_norm": 1.6924659929133659, "learning_rate": 1.4285946174630805e-05, "loss": 0.6673, "step": 5940 }, { "epoch": 0.8465374750641208, "grad_norm": 1.551381026296719, "learning_rate": 1.4283699035113489e-05, "loss": 0.6348, "step": 5941 }, { "epoch": 0.8466799658022228, "grad_norm": 1.6056053553653806, "learning_rate": 1.4281451630639744e-05, "loss": 0.6216, "step": 5942 }, { "epoch": 0.8468224565403248, "grad_norm": 1.3192054239421063, "learning_rate": 1.4279203961348578e-05, "loss": 0.6496, "step": 5943 }, { "epoch": 0.8469649472784269, "grad_norm": 1.670258824502748, "learning_rate": 1.4276956027379019e-05, "loss": 0.6194, "step": 5944 }, { "epoch": 0.8471074380165289, "grad_norm": 1.7139071208185193, "learning_rate": 1.4274707828870098e-05, "loss": 0.7645, "step": 5945 }, { "epoch": 0.8472499287546309, "grad_norm": 1.443999688562048, "learning_rate": 1.4272459365960878e-05, "loss": 0.6595, "step": 5946 }, { "epoch": 0.8473924194927329, "grad_norm": 1.288564660420324, "learning_rate": 1.4270210638790427e-05, "loss": 0.6162, "step": 5947 }, { "epoch": 0.847534910230835, "grad_norm": 1.3852466002678874, "learning_rate": 1.426796164749784e-05, "loss": 0.6296, "step": 5948 }, { "epoch": 0.8476774009689371, "grad_norm": 1.2331516716120328, "learning_rate": 1.4265712392222215e-05, "loss": 0.5993, "step": 5949 }, { "epoch": 0.8478198917070391, "grad_norm": 1.3374976103213023, "learning_rate": 1.4263462873102674e-05, "loss": 0.701, "step": 5950 }, { "epoch": 0.8479623824451411, "grad_norm": 1.7318422762384709, "learning_rate": 1.4261213090278363e-05, "loss": 0.6428, "step": 5951 }, { "epoch": 0.8481048731832431, "grad_norm": 1.460600451705828, "learning_rate": 1.425896304388843e-05, "loss": 0.5953, "step": 5952 }, { "epoch": 0.8482473639213451, "grad_norm": 1.3755163765489689, "learning_rate": 1.4256712734072042e-05, "loss": 0.6633, "step": 5953 }, { "epoch": 0.8483898546594472, "grad_norm": 1.1936560395140792, "learning_rate": 1.4254462160968391e-05, "loss": 0.5878, "step": 5954 }, { "epoch": 0.8485323453975492, "grad_norm": 1.269554932629473, "learning_rate": 1.4252211324716681e-05, "loss": 0.5752, "step": 5955 }, { "epoch": 0.8486748361356512, "grad_norm": 1.404960544478942, "learning_rate": 1.4249960225456131e-05, "loss": 0.6644, "step": 5956 }, { "epoch": 0.8488173268737532, "grad_norm": 1.7219350421012247, "learning_rate": 1.424770886332597e-05, "loss": 0.6941, "step": 5957 }, { "epoch": 0.8489598176118552, "grad_norm": 1.3496691983260214, "learning_rate": 1.4245457238465457e-05, "loss": 0.6257, "step": 5958 }, { "epoch": 0.8491023083499573, "grad_norm": 1.666176984144299, "learning_rate": 1.4243205351013858e-05, "loss": 0.6406, "step": 5959 }, { "epoch": 0.8492447990880593, "grad_norm": 1.258469997071562, "learning_rate": 1.4240953201110454e-05, "loss": 0.6558, "step": 5960 }, { "epoch": 0.8493872898261613, "grad_norm": 1.454477331285035, "learning_rate": 1.423870078889455e-05, "loss": 0.6284, "step": 5961 }, { "epoch": 0.8495297805642633, "grad_norm": 1.3756243548312865, "learning_rate": 1.4236448114505464e-05, "loss": 0.6767, "step": 5962 }, { "epoch": 0.8496722713023653, "grad_norm": 1.4088113674519114, "learning_rate": 1.4234195178082524e-05, "loss": 0.7065, "step": 5963 }, { "epoch": 0.8498147620404674, "grad_norm": 1.295871307474339, "learning_rate": 1.4231941979765077e-05, "loss": 0.5909, "step": 5964 }, { "epoch": 0.8499572527785694, "grad_norm": 1.276446088606553, "learning_rate": 1.4229688519692497e-05, "loss": 0.633, "step": 5965 }, { "epoch": 0.8500997435166714, "grad_norm": 1.2683137041326218, "learning_rate": 1.4227434798004163e-05, "loss": 0.5662, "step": 5966 }, { "epoch": 0.8502422342547734, "grad_norm": 1.3178590512955919, "learning_rate": 1.422518081483947e-05, "loss": 0.6415, "step": 5967 }, { "epoch": 0.8503847249928754, "grad_norm": 1.3303856624436843, "learning_rate": 1.4222926570337831e-05, "loss": 0.6709, "step": 5968 }, { "epoch": 0.8505272157309774, "grad_norm": 1.3509945413876505, "learning_rate": 1.422067206463868e-05, "loss": 0.7069, "step": 5969 }, { "epoch": 0.8506697064690795, "grad_norm": 1.3344561934457275, "learning_rate": 1.4218417297881461e-05, "loss": 0.6194, "step": 5970 }, { "epoch": 0.8508121972071815, "grad_norm": 1.578842206269014, "learning_rate": 1.4216162270205635e-05, "loss": 0.5813, "step": 5971 }, { "epoch": 0.8509546879452835, "grad_norm": 1.5343748514540194, "learning_rate": 1.4213906981750682e-05, "loss": 0.6582, "step": 5972 }, { "epoch": 0.8510971786833855, "grad_norm": 1.6173834942524252, "learning_rate": 1.4211651432656099e-05, "loss": 0.6901, "step": 5973 }, { "epoch": 0.8512396694214877, "grad_norm": 1.317839180246474, "learning_rate": 1.4209395623061394e-05, "loss": 0.6234, "step": 5974 }, { "epoch": 0.8513821601595897, "grad_norm": 1.206478983317923, "learning_rate": 1.4207139553106096e-05, "loss": 0.6081, "step": 5975 }, { "epoch": 0.8515246508976917, "grad_norm": 1.3914648834803534, "learning_rate": 1.4204883222929745e-05, "loss": 0.658, "step": 5976 }, { "epoch": 0.8516671416357937, "grad_norm": 1.247664055392824, "learning_rate": 1.4202626632671903e-05, "loss": 0.6267, "step": 5977 }, { "epoch": 0.8518096323738957, "grad_norm": 1.726743163450992, "learning_rate": 1.4200369782472142e-05, "loss": 0.5993, "step": 5978 }, { "epoch": 0.8519521231119978, "grad_norm": 1.3929935397491884, "learning_rate": 1.4198112672470057e-05, "loss": 0.773, "step": 5979 }, { "epoch": 0.8520946138500998, "grad_norm": 1.3271436476101024, "learning_rate": 1.419585530280525e-05, "loss": 0.7071, "step": 5980 }, { "epoch": 0.8522371045882018, "grad_norm": 1.2298954528417851, "learning_rate": 1.4193597673617353e-05, "loss": 0.663, "step": 5981 }, { "epoch": 0.8523795953263038, "grad_norm": 1.331379707928383, "learning_rate": 1.4191339785046e-05, "loss": 0.6485, "step": 5982 }, { "epoch": 0.8525220860644058, "grad_norm": 1.3162995679282952, "learning_rate": 1.4189081637230844e-05, "loss": 0.7233, "step": 5983 }, { "epoch": 0.8526645768025078, "grad_norm": 2.35262666300808, "learning_rate": 1.4186823230311559e-05, "loss": 0.7108, "step": 5984 }, { "epoch": 0.8528070675406099, "grad_norm": 1.9736767939799742, "learning_rate": 1.4184564564427836e-05, "loss": 0.7172, "step": 5985 }, { "epoch": 0.8529495582787119, "grad_norm": 1.3697110436169604, "learning_rate": 1.4182305639719372e-05, "loss": 0.555, "step": 5986 }, { "epoch": 0.8530920490168139, "grad_norm": 1.6398400424172928, "learning_rate": 1.418004645632589e-05, "loss": 0.6256, "step": 5987 }, { "epoch": 0.8532345397549159, "grad_norm": 1.2959602838519928, "learning_rate": 1.417778701438713e-05, "loss": 0.6204, "step": 5988 }, { "epoch": 0.8533770304930179, "grad_norm": 1.4530631487791514, "learning_rate": 1.4175527314042838e-05, "loss": 0.6506, "step": 5989 }, { "epoch": 0.85351952123112, "grad_norm": 1.4356136672915403, "learning_rate": 1.417326735543278e-05, "loss": 0.6509, "step": 5990 }, { "epoch": 0.853662011969222, "grad_norm": 1.2739303959794148, "learning_rate": 1.4171007138696747e-05, "loss": 0.6354, "step": 5991 }, { "epoch": 0.853804502707324, "grad_norm": 1.8867393666933818, "learning_rate": 1.4168746663974529e-05, "loss": 0.6652, "step": 5992 }, { "epoch": 0.853946993445426, "grad_norm": 1.226500829417077, "learning_rate": 1.416648593140595e-05, "loss": 0.5867, "step": 5993 }, { "epoch": 0.854089484183528, "grad_norm": 1.2633718687514555, "learning_rate": 1.4164224941130833e-05, "loss": 0.674, "step": 5994 }, { "epoch": 0.85423197492163, "grad_norm": 1.3457113317813474, "learning_rate": 1.4161963693289033e-05, "loss": 0.6016, "step": 5995 }, { "epoch": 0.8543744656597321, "grad_norm": 1.4999000609927815, "learning_rate": 1.4159702188020413e-05, "loss": 0.6813, "step": 5996 }, { "epoch": 0.8545169563978341, "grad_norm": 1.3715067787526378, "learning_rate": 1.4157440425464843e-05, "loss": 0.6396, "step": 5997 }, { "epoch": 0.8546594471359361, "grad_norm": 1.5941226311392347, "learning_rate": 1.4155178405762229e-05, "loss": 0.6861, "step": 5998 }, { "epoch": 0.8548019378740382, "grad_norm": 1.4833136533100986, "learning_rate": 1.4152916129052476e-05, "loss": 0.6739, "step": 5999 }, { "epoch": 0.8549444286121403, "grad_norm": 1.4106569116643946, "learning_rate": 1.4150653595475514e-05, "loss": 0.6803, "step": 6000 }, { "epoch": 0.8550869193502423, "grad_norm": 1.3075830235045014, "learning_rate": 1.4148390805171282e-05, "loss": 0.6847, "step": 6001 }, { "epoch": 0.8552294100883443, "grad_norm": 1.2226537629079064, "learning_rate": 1.4146127758279741e-05, "loss": 0.5547, "step": 6002 }, { "epoch": 0.8553719008264463, "grad_norm": 1.3127367588658292, "learning_rate": 1.414386445494087e-05, "loss": 0.6129, "step": 6003 }, { "epoch": 0.8555143915645483, "grad_norm": 1.3141184224241178, "learning_rate": 1.4141600895294652e-05, "loss": 0.6375, "step": 6004 }, { "epoch": 0.8556568823026504, "grad_norm": 1.3388463191908353, "learning_rate": 1.4139337079481094e-05, "loss": 0.6502, "step": 6005 }, { "epoch": 0.8557993730407524, "grad_norm": 1.828872436799552, "learning_rate": 1.4137073007640224e-05, "loss": 0.5832, "step": 6006 }, { "epoch": 0.8559418637788544, "grad_norm": 1.2684328992593297, "learning_rate": 1.4134808679912074e-05, "loss": 0.6961, "step": 6007 }, { "epoch": 0.8560843545169564, "grad_norm": 1.5063228752447624, "learning_rate": 1.4132544096436698e-05, "loss": 0.6142, "step": 6008 }, { "epoch": 0.8562268452550584, "grad_norm": 1.3770813401300641, "learning_rate": 1.413027925735417e-05, "loss": 0.6746, "step": 6009 }, { "epoch": 0.8563693359931605, "grad_norm": 1.743153636124309, "learning_rate": 1.4128014162804573e-05, "loss": 0.6088, "step": 6010 }, { "epoch": 0.8565118267312625, "grad_norm": 1.2187994277114633, "learning_rate": 1.4125748812928008e-05, "loss": 0.5565, "step": 6011 }, { "epoch": 0.8566543174693645, "grad_norm": 1.2510168443130345, "learning_rate": 1.4123483207864592e-05, "loss": 0.5937, "step": 6012 }, { "epoch": 0.8567968082074665, "grad_norm": 1.4586834916137623, "learning_rate": 1.4121217347754456e-05, "loss": 0.6305, "step": 6013 }, { "epoch": 0.8569392989455685, "grad_norm": 1.3701454408318168, "learning_rate": 1.4118951232737755e-05, "loss": 0.6035, "step": 6014 }, { "epoch": 0.8570817896836705, "grad_norm": 1.2982544143647352, "learning_rate": 1.4116684862954644e-05, "loss": 0.6423, "step": 6015 }, { "epoch": 0.8572242804217726, "grad_norm": 1.4435116961895902, "learning_rate": 1.4114418238545309e-05, "loss": 0.6781, "step": 6016 }, { "epoch": 0.8573667711598746, "grad_norm": 1.2263912482431, "learning_rate": 1.4112151359649947e-05, "loss": 0.6166, "step": 6017 }, { "epoch": 0.8575092618979766, "grad_norm": 1.6897546504467005, "learning_rate": 1.4109884226408767e-05, "loss": 0.6608, "step": 6018 }, { "epoch": 0.8576517526360786, "grad_norm": 1.8840784756501723, "learning_rate": 1.4107616838961995e-05, "loss": 0.6316, "step": 6019 }, { "epoch": 0.8577942433741806, "grad_norm": 1.3793176488780772, "learning_rate": 1.4105349197449876e-05, "loss": 0.6741, "step": 6020 }, { "epoch": 0.8579367341122827, "grad_norm": 1.6883339363815948, "learning_rate": 1.4103081302012667e-05, "loss": 0.6446, "step": 6021 }, { "epoch": 0.8580792248503847, "grad_norm": 1.2420873669021726, "learning_rate": 1.4100813152790645e-05, "loss": 0.5823, "step": 6022 }, { "epoch": 0.8582217155884867, "grad_norm": 1.3328093296907548, "learning_rate": 1.4098544749924097e-05, "loss": 0.7823, "step": 6023 }, { "epoch": 0.8583642063265887, "grad_norm": 1.1612389428331915, "learning_rate": 1.4096276093553334e-05, "loss": 0.5776, "step": 6024 }, { "epoch": 0.8585066970646908, "grad_norm": 1.2903990153933114, "learning_rate": 1.4094007183818672e-05, "loss": 0.5629, "step": 6025 }, { "epoch": 0.8586491878027929, "grad_norm": 1.3904500511309643, "learning_rate": 1.4091738020860453e-05, "loss": 0.6729, "step": 6026 }, { "epoch": 0.8587916785408949, "grad_norm": 1.948234080627278, "learning_rate": 1.4089468604819023e-05, "loss": 0.6922, "step": 6027 }, { "epoch": 0.8589341692789969, "grad_norm": 1.3084187129430924, "learning_rate": 1.4087198935834759e-05, "loss": 0.661, "step": 6028 }, { "epoch": 0.8590766600170989, "grad_norm": 1.385033334761133, "learning_rate": 1.4084929014048037e-05, "loss": 0.634, "step": 6029 }, { "epoch": 0.8592191507552009, "grad_norm": 1.244503731991575, "learning_rate": 1.408265883959926e-05, "loss": 0.6013, "step": 6030 }, { "epoch": 0.859361641493303, "grad_norm": 1.3879137184519952, "learning_rate": 1.4080388412628846e-05, "loss": 0.5955, "step": 6031 }, { "epoch": 0.859504132231405, "grad_norm": 1.568207569891745, "learning_rate": 1.4078117733277225e-05, "loss": 0.6053, "step": 6032 }, { "epoch": 0.859646622969507, "grad_norm": 1.399605375148685, "learning_rate": 1.4075846801684842e-05, "loss": 0.672, "step": 6033 }, { "epoch": 0.859789113707609, "grad_norm": 1.3036557741309247, "learning_rate": 1.4073575617992159e-05, "loss": 0.7057, "step": 6034 }, { "epoch": 0.859931604445711, "grad_norm": 1.256901303475107, "learning_rate": 1.4071304182339656e-05, "loss": 0.6467, "step": 6035 }, { "epoch": 0.8600740951838131, "grad_norm": 1.8625965189687008, "learning_rate": 1.4069032494867823e-05, "loss": 0.6219, "step": 6036 }, { "epoch": 0.8602165859219151, "grad_norm": 1.3306995369953036, "learning_rate": 1.406676055571717e-05, "loss": 0.6724, "step": 6037 }, { "epoch": 0.8603590766600171, "grad_norm": 1.2993816449955746, "learning_rate": 1.4064488365028228e-05, "loss": 0.733, "step": 6038 }, { "epoch": 0.8605015673981191, "grad_norm": 1.4837719400374247, "learning_rate": 1.406221592294153e-05, "loss": 0.6508, "step": 6039 }, { "epoch": 0.8606440581362211, "grad_norm": 1.3134132933363099, "learning_rate": 1.405994322959763e-05, "loss": 0.6045, "step": 6040 }, { "epoch": 0.8607865488743232, "grad_norm": 1.7847190666472987, "learning_rate": 1.4057670285137106e-05, "loss": 0.6351, "step": 6041 }, { "epoch": 0.8609290396124252, "grad_norm": 1.4048972683481074, "learning_rate": 1.405539708970054e-05, "loss": 0.6346, "step": 6042 }, { "epoch": 0.8610715303505272, "grad_norm": 1.33220614989926, "learning_rate": 1.4053123643428535e-05, "loss": 0.631, "step": 6043 }, { "epoch": 0.8612140210886292, "grad_norm": 1.4188099074837786, "learning_rate": 1.4050849946461708e-05, "loss": 0.7045, "step": 6044 }, { "epoch": 0.8613565118267312, "grad_norm": 1.2627392181226862, "learning_rate": 1.4048575998940696e-05, "loss": 0.6692, "step": 6045 }, { "epoch": 0.8614990025648332, "grad_norm": 1.3603320838495423, "learning_rate": 1.4046301801006147e-05, "loss": 0.597, "step": 6046 }, { "epoch": 0.8616414933029353, "grad_norm": 1.336646111588417, "learning_rate": 1.404402735279872e-05, "loss": 0.6068, "step": 6047 }, { "epoch": 0.8617839840410373, "grad_norm": 1.7441091537244158, "learning_rate": 1.4041752654459102e-05, "loss": 0.6389, "step": 6048 }, { "epoch": 0.8619264747791393, "grad_norm": 1.2435092170836601, "learning_rate": 1.4039477706127982e-05, "loss": 0.6537, "step": 6049 }, { "epoch": 0.8620689655172413, "grad_norm": 1.4486497758114971, "learning_rate": 1.4037202507946072e-05, "loss": 0.7526, "step": 6050 }, { "epoch": 0.8622114562553435, "grad_norm": 1.370244797177332, "learning_rate": 1.4034927060054103e-05, "loss": 0.6083, "step": 6051 }, { "epoch": 0.8623539469934455, "grad_norm": 1.314054445340752, "learning_rate": 1.4032651362592809e-05, "loss": 0.7247, "step": 6052 }, { "epoch": 0.8624964377315475, "grad_norm": 1.3663127842516103, "learning_rate": 1.4030375415702952e-05, "loss": 0.6787, "step": 6053 }, { "epoch": 0.8626389284696495, "grad_norm": 1.2677853127992507, "learning_rate": 1.4028099219525305e-05, "loss": 0.6479, "step": 6054 }, { "epoch": 0.8627814192077515, "grad_norm": 1.5158986982900564, "learning_rate": 1.4025822774200654e-05, "loss": 0.7481, "step": 6055 }, { "epoch": 0.8629239099458536, "grad_norm": 1.2977341048246764, "learning_rate": 1.4023546079869803e-05, "loss": 0.6736, "step": 6056 }, { "epoch": 0.8630664006839556, "grad_norm": 1.3121240204390796, "learning_rate": 1.402126913667357e-05, "loss": 0.6638, "step": 6057 }, { "epoch": 0.8632088914220576, "grad_norm": 1.2921940667170362, "learning_rate": 1.4018991944752788e-05, "loss": 0.6539, "step": 6058 }, { "epoch": 0.8633513821601596, "grad_norm": 1.1774305875134734, "learning_rate": 1.401671450424831e-05, "loss": 0.5465, "step": 6059 }, { "epoch": 0.8634938728982616, "grad_norm": 1.351107793924131, "learning_rate": 1.4014436815300995e-05, "loss": 0.6518, "step": 6060 }, { "epoch": 0.8636363636363636, "grad_norm": 1.6155795055054654, "learning_rate": 1.4012158878051729e-05, "loss": 0.6024, "step": 6061 }, { "epoch": 0.8637788543744657, "grad_norm": 1.4112897542223737, "learning_rate": 1.4009880692641407e-05, "loss": 0.6469, "step": 6062 }, { "epoch": 0.8639213451125677, "grad_norm": 1.422490668021131, "learning_rate": 1.4007602259210937e-05, "loss": 0.6878, "step": 6063 }, { "epoch": 0.8640638358506697, "grad_norm": 1.754886533593039, "learning_rate": 1.4005323577901245e-05, "loss": 0.6469, "step": 6064 }, { "epoch": 0.8642063265887717, "grad_norm": 1.3470586371143851, "learning_rate": 1.4003044648853275e-05, "loss": 0.6425, "step": 6065 }, { "epoch": 0.8643488173268737, "grad_norm": 1.3377806383041426, "learning_rate": 1.4000765472207982e-05, "loss": 0.6214, "step": 6066 }, { "epoch": 0.8644913080649758, "grad_norm": 1.2501955136745337, "learning_rate": 1.3998486048106338e-05, "loss": 0.6578, "step": 6067 }, { "epoch": 0.8646337988030778, "grad_norm": 1.424380803748071, "learning_rate": 1.3996206376689334e-05, "loss": 0.7413, "step": 6068 }, { "epoch": 0.8647762895411798, "grad_norm": 1.4308500488832903, "learning_rate": 1.399392645809797e-05, "loss": 0.5359, "step": 6069 }, { "epoch": 0.8649187802792818, "grad_norm": 1.3707735719030927, "learning_rate": 1.3991646292473266e-05, "loss": 0.6448, "step": 6070 }, { "epoch": 0.8650612710173838, "grad_norm": 2.3303591060028, "learning_rate": 1.3989365879956252e-05, "loss": 0.6817, "step": 6071 }, { "epoch": 0.8652037617554859, "grad_norm": 1.3154656311021027, "learning_rate": 1.3987085220687978e-05, "loss": 0.6683, "step": 6072 }, { "epoch": 0.8653462524935879, "grad_norm": 1.264438284314282, "learning_rate": 1.3984804314809508e-05, "loss": 0.5832, "step": 6073 }, { "epoch": 0.8654887432316899, "grad_norm": 1.4090139749933586, "learning_rate": 1.3982523162461922e-05, "loss": 0.6609, "step": 6074 }, { "epoch": 0.8656312339697919, "grad_norm": 1.310999203732869, "learning_rate": 1.3980241763786315e-05, "loss": 0.6897, "step": 6075 }, { "epoch": 0.8657737247078939, "grad_norm": 1.324624588261903, "learning_rate": 1.3977960118923796e-05, "loss": 0.635, "step": 6076 }, { "epoch": 0.8659162154459961, "grad_norm": 1.340128613999086, "learning_rate": 1.3975678228015488e-05, "loss": 0.6777, "step": 6077 }, { "epoch": 0.8660587061840981, "grad_norm": 1.5923611370957529, "learning_rate": 1.3973396091202536e-05, "loss": 0.7956, "step": 6078 }, { "epoch": 0.8662011969222001, "grad_norm": 1.3038505691221822, "learning_rate": 1.397111370862609e-05, "loss": 0.674, "step": 6079 }, { "epoch": 0.8663436876603021, "grad_norm": 1.1819986243257903, "learning_rate": 1.396883108042732e-05, "loss": 0.5981, "step": 6080 }, { "epoch": 0.8664861783984041, "grad_norm": 1.4497479998297924, "learning_rate": 1.3966548206747414e-05, "loss": 0.6178, "step": 6081 }, { "epoch": 0.8666286691365062, "grad_norm": 1.429236226663334, "learning_rate": 1.3964265087727575e-05, "loss": 0.611, "step": 6082 }, { "epoch": 0.8667711598746082, "grad_norm": 1.388863031152651, "learning_rate": 1.3961981723509017e-05, "loss": 0.5864, "step": 6083 }, { "epoch": 0.8669136506127102, "grad_norm": 1.549497403548116, "learning_rate": 1.3959698114232971e-05, "loss": 0.6453, "step": 6084 }, { "epoch": 0.8670561413508122, "grad_norm": 1.3487404558738683, "learning_rate": 1.3957414260040686e-05, "loss": 0.7117, "step": 6085 }, { "epoch": 0.8671986320889142, "grad_norm": 1.2062936601628964, "learning_rate": 1.3955130161073418e-05, "loss": 0.5706, "step": 6086 }, { "epoch": 0.8673411228270163, "grad_norm": 1.4453006022268184, "learning_rate": 1.3952845817472449e-05, "loss": 0.7047, "step": 6087 }, { "epoch": 0.8674836135651183, "grad_norm": 1.2907967748412734, "learning_rate": 1.3950561229379065e-05, "loss": 0.7064, "step": 6088 }, { "epoch": 0.8676261043032203, "grad_norm": 1.646045253660137, "learning_rate": 1.3948276396934578e-05, "loss": 0.6277, "step": 6089 }, { "epoch": 0.8677685950413223, "grad_norm": 1.2980782677555882, "learning_rate": 1.394599132028031e-05, "loss": 0.6998, "step": 6090 }, { "epoch": 0.8679110857794243, "grad_norm": 1.4014699067010152, "learning_rate": 1.3943705999557594e-05, "loss": 0.6124, "step": 6091 }, { "epoch": 0.8680535765175263, "grad_norm": 1.953606223040642, "learning_rate": 1.394142043490779e-05, "loss": 0.5754, "step": 6092 }, { "epoch": 0.8681960672556284, "grad_norm": 1.309334351243894, "learning_rate": 1.3939134626472257e-05, "loss": 0.6681, "step": 6093 }, { "epoch": 0.8683385579937304, "grad_norm": 1.2915760517238026, "learning_rate": 1.393684857439238e-05, "loss": 0.583, "step": 6094 }, { "epoch": 0.8684810487318324, "grad_norm": 1.282794706184363, "learning_rate": 1.3934562278809556e-05, "loss": 0.658, "step": 6095 }, { "epoch": 0.8686235394699344, "grad_norm": 1.2690815118046168, "learning_rate": 1.3932275739865202e-05, "loss": 0.6613, "step": 6096 }, { "epoch": 0.8687660302080364, "grad_norm": 1.31481997301472, "learning_rate": 1.392998895770074e-05, "loss": 0.5905, "step": 6097 }, { "epoch": 0.8689085209461385, "grad_norm": 1.9146839621891916, "learning_rate": 1.3927701932457616e-05, "loss": 0.641, "step": 6098 }, { "epoch": 0.8690510116842405, "grad_norm": 1.2724468746085686, "learning_rate": 1.3925414664277285e-05, "loss": 0.6042, "step": 6099 }, { "epoch": 0.8691935024223425, "grad_norm": 1.2275174444604426, "learning_rate": 1.3923127153301223e-05, "loss": 0.7019, "step": 6100 }, { "epoch": 0.8693359931604445, "grad_norm": 1.338605989815375, "learning_rate": 1.3920839399670916e-05, "loss": 0.6888, "step": 6101 }, { "epoch": 0.8694784838985465, "grad_norm": 1.5399547206870943, "learning_rate": 1.3918551403527862e-05, "loss": 0.7327, "step": 6102 }, { "epoch": 0.8696209746366487, "grad_norm": 1.3166324778441414, "learning_rate": 1.391626316501359e-05, "loss": 0.5814, "step": 6103 }, { "epoch": 0.8697634653747507, "grad_norm": 1.3181171993813023, "learning_rate": 1.3913974684269622e-05, "loss": 0.6443, "step": 6104 }, { "epoch": 0.8699059561128527, "grad_norm": 1.4935502610332791, "learning_rate": 1.3911685961437508e-05, "loss": 0.6583, "step": 6105 }, { "epoch": 0.8700484468509547, "grad_norm": 1.7492141985514242, "learning_rate": 1.3909396996658817e-05, "loss": 0.6128, "step": 6106 }, { "epoch": 0.8701909375890567, "grad_norm": 2.000911480024254, "learning_rate": 1.390710779007512e-05, "loss": 0.5946, "step": 6107 }, { "epoch": 0.8703334283271588, "grad_norm": 1.408211400045491, "learning_rate": 1.3904818341828012e-05, "loss": 0.58, "step": 6108 }, { "epoch": 0.8704759190652608, "grad_norm": 1.3444437462997443, "learning_rate": 1.39025286520591e-05, "loss": 0.6691, "step": 6109 }, { "epoch": 0.8706184098033628, "grad_norm": 1.3781703548036446, "learning_rate": 1.3900238720910002e-05, "loss": 0.7097, "step": 6110 }, { "epoch": 0.8707609005414648, "grad_norm": 1.4449694241739166, "learning_rate": 1.3897948548522366e-05, "loss": 0.5686, "step": 6111 }, { "epoch": 0.8709033912795668, "grad_norm": 1.2977965589959108, "learning_rate": 1.3895658135037834e-05, "loss": 0.6535, "step": 6112 }, { "epoch": 0.8710458820176689, "grad_norm": 1.4686264084921175, "learning_rate": 1.3893367480598081e-05, "loss": 0.7056, "step": 6113 }, { "epoch": 0.8711883727557709, "grad_norm": 1.3178299743421202, "learning_rate": 1.3891076585344782e-05, "loss": 0.589, "step": 6114 }, { "epoch": 0.8713308634938729, "grad_norm": 1.3565593847899744, "learning_rate": 1.3888785449419645e-05, "loss": 0.7097, "step": 6115 }, { "epoch": 0.8714733542319749, "grad_norm": 1.3375177620971057, "learning_rate": 1.3886494072964367e-05, "loss": 0.6913, "step": 6116 }, { "epoch": 0.8716158449700769, "grad_norm": 1.4744518842224832, "learning_rate": 1.3884202456120683e-05, "loss": 0.5706, "step": 6117 }, { "epoch": 0.871758335708179, "grad_norm": 1.4509710129551232, "learning_rate": 1.3881910599030337e-05, "loss": 0.6984, "step": 6118 }, { "epoch": 0.871900826446281, "grad_norm": 1.2576192176233154, "learning_rate": 1.3879618501835082e-05, "loss": 0.6317, "step": 6119 }, { "epoch": 0.872043317184383, "grad_norm": 1.371545912363076, "learning_rate": 1.3877326164676688e-05, "loss": 0.6565, "step": 6120 }, { "epoch": 0.872185807922485, "grad_norm": 1.5938128420950275, "learning_rate": 1.3875033587696945e-05, "loss": 0.671, "step": 6121 }, { "epoch": 0.872328298660587, "grad_norm": 1.4515760981815156, "learning_rate": 1.3872740771037652e-05, "loss": 0.6671, "step": 6122 }, { "epoch": 0.872470789398689, "grad_norm": 1.7671293989701724, "learning_rate": 1.3870447714840625e-05, "loss": 0.6938, "step": 6123 }, { "epoch": 0.8726132801367911, "grad_norm": 1.2675361097226538, "learning_rate": 1.386815441924769e-05, "loss": 0.5498, "step": 6124 }, { "epoch": 0.8727557708748931, "grad_norm": 1.4055837417245582, "learning_rate": 1.3865860884400701e-05, "loss": 0.6406, "step": 6125 }, { "epoch": 0.8728982616129951, "grad_norm": 1.3595448720301582, "learning_rate": 1.3863567110441518e-05, "loss": 0.6332, "step": 6126 }, { "epoch": 0.8730407523510971, "grad_norm": 1.4320263874279044, "learning_rate": 1.3861273097512008e-05, "loss": 0.7024, "step": 6127 }, { "epoch": 0.8731832430891993, "grad_norm": 1.271681586512713, "learning_rate": 1.3858978845754067e-05, "loss": 0.5915, "step": 6128 }, { "epoch": 0.8733257338273013, "grad_norm": 1.729221909927076, "learning_rate": 1.3856684355309598e-05, "loss": 0.7514, "step": 6129 }, { "epoch": 0.8734682245654033, "grad_norm": 1.2793877556855602, "learning_rate": 1.385438962632052e-05, "loss": 0.627, "step": 6130 }, { "epoch": 0.8736107153035053, "grad_norm": 1.4326963265022061, "learning_rate": 1.3852094658928769e-05, "loss": 0.6312, "step": 6131 }, { "epoch": 0.8737532060416073, "grad_norm": 1.387891088208878, "learning_rate": 1.384979945327629e-05, "loss": 0.675, "step": 6132 }, { "epoch": 0.8738956967797094, "grad_norm": 1.308007883727973, "learning_rate": 1.3847504009505053e-05, "loss": 0.6407, "step": 6133 }, { "epoch": 0.8740381875178114, "grad_norm": 1.294682321765281, "learning_rate": 1.384520832775703e-05, "loss": 0.6219, "step": 6134 }, { "epoch": 0.8741806782559134, "grad_norm": 1.3903038428826495, "learning_rate": 1.3842912408174215e-05, "loss": 0.6481, "step": 6135 }, { "epoch": 0.8743231689940154, "grad_norm": 1.261750179448038, "learning_rate": 1.384061625089862e-05, "loss": 0.5883, "step": 6136 }, { "epoch": 0.8744656597321174, "grad_norm": 1.4758494881280855, "learning_rate": 1.3838319856072266e-05, "loss": 0.7042, "step": 6137 }, { "epoch": 0.8746081504702194, "grad_norm": 1.3473555324432125, "learning_rate": 1.3836023223837186e-05, "loss": 0.6479, "step": 6138 }, { "epoch": 0.8747506412083215, "grad_norm": 1.3930866146693734, "learning_rate": 1.3833726354335434e-05, "loss": 0.6428, "step": 6139 }, { "epoch": 0.8748931319464235, "grad_norm": 1.4249004361913347, "learning_rate": 1.3831429247709084e-05, "loss": 0.5988, "step": 6140 }, { "epoch": 0.8750356226845255, "grad_norm": 1.4382531034821768, "learning_rate": 1.3829131904100204e-05, "loss": 0.6317, "step": 6141 }, { "epoch": 0.8751781134226275, "grad_norm": 1.146885189495699, "learning_rate": 1.3826834323650899e-05, "loss": 0.6399, "step": 6142 }, { "epoch": 0.8753206041607295, "grad_norm": 1.3399503024379524, "learning_rate": 1.3824536506503276e-05, "loss": 0.5939, "step": 6143 }, { "epoch": 0.8754630948988316, "grad_norm": 1.2223185347017664, "learning_rate": 1.3822238452799463e-05, "loss": 0.5334, "step": 6144 }, { "epoch": 0.8756055856369336, "grad_norm": 1.4125529679569315, "learning_rate": 1.38199401626816e-05, "loss": 0.576, "step": 6145 }, { "epoch": 0.8757480763750356, "grad_norm": 1.4096975950114208, "learning_rate": 1.3817641636291835e-05, "loss": 0.6681, "step": 6146 }, { "epoch": 0.8758905671131376, "grad_norm": 1.514526823007931, "learning_rate": 1.3815342873772344e-05, "loss": 0.6544, "step": 6147 }, { "epoch": 0.8760330578512396, "grad_norm": 1.6571847502932135, "learning_rate": 1.3813043875265308e-05, "loss": 0.703, "step": 6148 }, { "epoch": 0.8761755485893417, "grad_norm": 1.3802688531878808, "learning_rate": 1.3810744640912926e-05, "loss": 0.5783, "step": 6149 }, { "epoch": 0.8763180393274437, "grad_norm": 2.428099983067531, "learning_rate": 1.3808445170857407e-05, "loss": 0.5985, "step": 6150 }, { "epoch": 0.8764605300655457, "grad_norm": 1.5030184717469084, "learning_rate": 1.3806145465240986e-05, "loss": 0.6789, "step": 6151 }, { "epoch": 0.8766030208036477, "grad_norm": 1.3546327766474902, "learning_rate": 1.38038455242059e-05, "loss": 0.7331, "step": 6152 }, { "epoch": 0.8767455115417497, "grad_norm": 1.3501464023490917, "learning_rate": 1.3801545347894403e-05, "loss": 0.6575, "step": 6153 }, { "epoch": 0.8768880022798519, "grad_norm": 1.3043225824314242, "learning_rate": 1.379924493644877e-05, "loss": 0.6899, "step": 6154 }, { "epoch": 0.8770304930179539, "grad_norm": 1.8673131032658075, "learning_rate": 1.379694429001129e-05, "loss": 0.5781, "step": 6155 }, { "epoch": 0.8771729837560559, "grad_norm": 1.3919297491246039, "learning_rate": 1.3794643408724255e-05, "loss": 0.6494, "step": 6156 }, { "epoch": 0.8773154744941579, "grad_norm": 1.3716825506607775, "learning_rate": 1.3792342292729984e-05, "loss": 0.6535, "step": 6157 }, { "epoch": 0.8774579652322599, "grad_norm": 1.2531143044008992, "learning_rate": 1.3790040942170806e-05, "loss": 0.5364, "step": 6158 }, { "epoch": 0.877600455970362, "grad_norm": 1.2589806481221237, "learning_rate": 1.3787739357189068e-05, "loss": 0.618, "step": 6159 }, { "epoch": 0.877742946708464, "grad_norm": 1.4183348769312296, "learning_rate": 1.378543753792712e-05, "loss": 0.7454, "step": 6160 }, { "epoch": 0.877885437446566, "grad_norm": 1.3461621958358765, "learning_rate": 1.378313548452734e-05, "loss": 0.6624, "step": 6161 }, { "epoch": 0.878027928184668, "grad_norm": 1.3606830108228338, "learning_rate": 1.3780833197132113e-05, "loss": 0.6788, "step": 6162 }, { "epoch": 0.87817041892277, "grad_norm": 1.8267561624300157, "learning_rate": 1.3778530675883847e-05, "loss": 0.7297, "step": 6163 }, { "epoch": 0.878312909660872, "grad_norm": 1.4632675401762196, "learning_rate": 1.3776227920924953e-05, "loss": 0.6698, "step": 6164 }, { "epoch": 0.8784554003989741, "grad_norm": 1.2938354739634312, "learning_rate": 1.377392493239786e-05, "loss": 0.5865, "step": 6165 }, { "epoch": 0.8785978911370761, "grad_norm": 1.1963944235688517, "learning_rate": 1.3771621710445015e-05, "loss": 0.5057, "step": 6166 }, { "epoch": 0.8787403818751781, "grad_norm": 1.217124401286906, "learning_rate": 1.376931825520888e-05, "loss": 0.6542, "step": 6167 }, { "epoch": 0.8788828726132801, "grad_norm": 1.335224122362232, "learning_rate": 1.3767014566831925e-05, "loss": 0.6604, "step": 6168 }, { "epoch": 0.8790253633513821, "grad_norm": 1.4234451715394782, "learning_rate": 1.3764710645456639e-05, "loss": 0.7359, "step": 6169 }, { "epoch": 0.8791678540894842, "grad_norm": 1.2511806464273152, "learning_rate": 1.3762406491225526e-05, "loss": 0.6914, "step": 6170 }, { "epoch": 0.8793103448275862, "grad_norm": 1.4124602718279138, "learning_rate": 1.3760102104281104e-05, "loss": 0.5996, "step": 6171 }, { "epoch": 0.8794528355656882, "grad_norm": 1.3315824320100782, "learning_rate": 1.37577974847659e-05, "loss": 0.6492, "step": 6172 }, { "epoch": 0.8795953263037902, "grad_norm": 1.4539410991057469, "learning_rate": 1.3755492632822464e-05, "loss": 0.6288, "step": 6173 }, { "epoch": 0.8797378170418922, "grad_norm": 1.4090209967399285, "learning_rate": 1.3753187548593358e-05, "loss": 0.6708, "step": 6174 }, { "epoch": 0.8798803077799943, "grad_norm": 1.3105696931516904, "learning_rate": 1.375088223222115e-05, "loss": 0.6468, "step": 6175 }, { "epoch": 0.8800227985180963, "grad_norm": 1.3669921884755563, "learning_rate": 1.3748576683848435e-05, "loss": 0.6369, "step": 6176 }, { "epoch": 0.8801652892561983, "grad_norm": 1.3471560887898764, "learning_rate": 1.3746270903617815e-05, "loss": 0.6621, "step": 6177 }, { "epoch": 0.8803077799943003, "grad_norm": 1.3488842695983614, "learning_rate": 1.3743964891671908e-05, "loss": 0.6746, "step": 6178 }, { "epoch": 0.8804502707324023, "grad_norm": 1.3440595407178229, "learning_rate": 1.3741658648153343e-05, "loss": 0.5832, "step": 6179 }, { "epoch": 0.8805927614705045, "grad_norm": 1.2692592150326623, "learning_rate": 1.3739352173204768e-05, "loss": 0.6296, "step": 6180 }, { "epoch": 0.8807352522086065, "grad_norm": 1.314909181842233, "learning_rate": 1.3737045466968844e-05, "loss": 0.668, "step": 6181 }, { "epoch": 0.8808777429467085, "grad_norm": 1.369373511445501, "learning_rate": 1.3734738529588248e-05, "loss": 0.5956, "step": 6182 }, { "epoch": 0.8810202336848105, "grad_norm": 1.7125530836040506, "learning_rate": 1.3732431361205664e-05, "loss": 0.6562, "step": 6183 }, { "epoch": 0.8811627244229125, "grad_norm": 1.5217360668173074, "learning_rate": 1.3730123961963802e-05, "loss": 0.5734, "step": 6184 }, { "epoch": 0.8813052151610146, "grad_norm": 1.1545112259632488, "learning_rate": 1.3727816332005377e-05, "loss": 0.5747, "step": 6185 }, { "epoch": 0.8814477058991166, "grad_norm": 1.4495643687924762, "learning_rate": 1.3725508471473119e-05, "loss": 0.6259, "step": 6186 }, { "epoch": 0.8815901966372186, "grad_norm": 1.1340460926661846, "learning_rate": 1.3723200380509776e-05, "loss": 0.6241, "step": 6187 }, { "epoch": 0.8817326873753206, "grad_norm": 1.4584872184007445, "learning_rate": 1.3720892059258109e-05, "loss": 0.7092, "step": 6188 }, { "epoch": 0.8818751781134226, "grad_norm": 1.335807342592206, "learning_rate": 1.3718583507860894e-05, "loss": 0.6522, "step": 6189 }, { "epoch": 0.8820176688515247, "grad_norm": 1.3806966881524148, "learning_rate": 1.3716274726460916e-05, "loss": 0.6643, "step": 6190 }, { "epoch": 0.8821601595896267, "grad_norm": 1.4593100711960303, "learning_rate": 1.3713965715200984e-05, "loss": 0.5963, "step": 6191 }, { "epoch": 0.8823026503277287, "grad_norm": 1.3512459453091248, "learning_rate": 1.371165647422391e-05, "loss": 0.6484, "step": 6192 }, { "epoch": 0.8824451410658307, "grad_norm": 18.113201274699012, "learning_rate": 1.3709347003672531e-05, "loss": 0.568, "step": 6193 }, { "epoch": 0.8825876318039327, "grad_norm": 1.4538523785904678, "learning_rate": 1.3707037303689688e-05, "loss": 0.6858, "step": 6194 }, { "epoch": 0.8827301225420348, "grad_norm": 1.444877811155911, "learning_rate": 1.3704727374418244e-05, "loss": 0.6474, "step": 6195 }, { "epoch": 0.8828726132801368, "grad_norm": 1.3653229876003699, "learning_rate": 1.3702417216001073e-05, "loss": 0.6997, "step": 6196 }, { "epoch": 0.8830151040182388, "grad_norm": 1.3905130310129388, "learning_rate": 1.3700106828581064e-05, "loss": 0.683, "step": 6197 }, { "epoch": 0.8831575947563408, "grad_norm": 1.5908947208107285, "learning_rate": 1.3697796212301117e-05, "loss": 0.6681, "step": 6198 }, { "epoch": 0.8833000854944428, "grad_norm": 1.3295759003298644, "learning_rate": 1.3695485367304154e-05, "loss": 0.7224, "step": 6199 }, { "epoch": 0.8834425762325449, "grad_norm": 1.3563452209416162, "learning_rate": 1.3693174293733103e-05, "loss": 0.6794, "step": 6200 }, { "epoch": 0.8835850669706469, "grad_norm": 1.1760067868493462, "learning_rate": 1.3690862991730907e-05, "loss": 0.6041, "step": 6201 }, { "epoch": 0.8837275577087489, "grad_norm": 1.2922244271912986, "learning_rate": 1.3688551461440526e-05, "loss": 0.623, "step": 6202 }, { "epoch": 0.8838700484468509, "grad_norm": 1.316660279780822, "learning_rate": 1.3686239703004935e-05, "loss": 0.6286, "step": 6203 }, { "epoch": 0.8840125391849529, "grad_norm": 1.3428995614292611, "learning_rate": 1.3683927716567122e-05, "loss": 0.6697, "step": 6204 }, { "epoch": 0.884155029923055, "grad_norm": 1.319657639923775, "learning_rate": 1.3681615502270088e-05, "loss": 0.7057, "step": 6205 }, { "epoch": 0.8842975206611571, "grad_norm": 1.122818562026582, "learning_rate": 1.3679303060256846e-05, "loss": 0.6326, "step": 6206 }, { "epoch": 0.8844400113992591, "grad_norm": 1.3289645607303309, "learning_rate": 1.367699039067043e-05, "loss": 0.6756, "step": 6207 }, { "epoch": 0.8845825021373611, "grad_norm": 1.4907557974479047, "learning_rate": 1.367467749365388e-05, "loss": 0.6713, "step": 6208 }, { "epoch": 0.8847249928754631, "grad_norm": 1.3114443021963231, "learning_rate": 1.3672364369350254e-05, "loss": 0.6661, "step": 6209 }, { "epoch": 0.8848674836135652, "grad_norm": 1.380528972652068, "learning_rate": 1.3670051017902628e-05, "loss": 0.6464, "step": 6210 }, { "epoch": 0.8850099743516672, "grad_norm": 1.4412641118525835, "learning_rate": 1.3667737439454087e-05, "loss": 0.644, "step": 6211 }, { "epoch": 0.8851524650897692, "grad_norm": 1.2401840405337405, "learning_rate": 1.3665423634147726e-05, "loss": 0.5813, "step": 6212 }, { "epoch": 0.8852949558278712, "grad_norm": 1.4233945885929211, "learning_rate": 1.3663109602126663e-05, "loss": 0.6861, "step": 6213 }, { "epoch": 0.8854374465659732, "grad_norm": 1.4329347219574502, "learning_rate": 1.3660795343534025e-05, "loss": 0.6989, "step": 6214 }, { "epoch": 0.8855799373040752, "grad_norm": 1.290150111283868, "learning_rate": 1.3658480858512961e-05, "loss": 0.5697, "step": 6215 }, { "epoch": 0.8857224280421773, "grad_norm": 1.4416131373790864, "learning_rate": 1.3656166147206615e-05, "loss": 0.5557, "step": 6216 }, { "epoch": 0.8858649187802793, "grad_norm": 1.5157277975394527, "learning_rate": 1.3653851209758164e-05, "loss": 0.592, "step": 6217 }, { "epoch": 0.8860074095183813, "grad_norm": 1.3543957877849775, "learning_rate": 1.3651536046310791e-05, "loss": 0.6206, "step": 6218 }, { "epoch": 0.8861499002564833, "grad_norm": 1.3908660589467472, "learning_rate": 1.3649220657007697e-05, "loss": 0.6915, "step": 6219 }, { "epoch": 0.8862923909945853, "grad_norm": 1.3405106459391223, "learning_rate": 1.3646905041992087e-05, "loss": 0.7224, "step": 6220 }, { "epoch": 0.8864348817326874, "grad_norm": 1.2931038836777666, "learning_rate": 1.3644589201407192e-05, "loss": 0.5982, "step": 6221 }, { "epoch": 0.8865773724707894, "grad_norm": 1.2829266561736963, "learning_rate": 1.3642273135396256e-05, "loss": 0.5843, "step": 6222 }, { "epoch": 0.8867198632088914, "grad_norm": 1.649376213972141, "learning_rate": 1.3639956844102523e-05, "loss": 0.6105, "step": 6223 }, { "epoch": 0.8868623539469934, "grad_norm": 1.7944843143945512, "learning_rate": 1.3637640327669269e-05, "loss": 0.6128, "step": 6224 }, { "epoch": 0.8870048446850954, "grad_norm": 1.2970218791502932, "learning_rate": 1.363532358623977e-05, "loss": 0.6423, "step": 6225 }, { "epoch": 0.8871473354231975, "grad_norm": 1.3624214636452912, "learning_rate": 1.3633006619957324e-05, "loss": 0.6583, "step": 6226 }, { "epoch": 0.8872898261612995, "grad_norm": 1.321393632325807, "learning_rate": 1.3630689428965243e-05, "loss": 0.6398, "step": 6227 }, { "epoch": 0.8874323168994015, "grad_norm": 1.293430834713233, "learning_rate": 1.3628372013406846e-05, "loss": 0.6382, "step": 6228 }, { "epoch": 0.8875748076375035, "grad_norm": 1.2899376818255734, "learning_rate": 1.3626054373425475e-05, "loss": 0.6199, "step": 6229 }, { "epoch": 0.8877172983756055, "grad_norm": 1.342020560714264, "learning_rate": 1.3623736509164478e-05, "loss": 0.6853, "step": 6230 }, { "epoch": 0.8878597891137076, "grad_norm": 1.5024421899007339, "learning_rate": 1.3621418420767222e-05, "loss": 0.5971, "step": 6231 }, { "epoch": 0.8880022798518097, "grad_norm": 1.3553384156830393, "learning_rate": 1.3619100108377086e-05, "loss": 0.5834, "step": 6232 }, { "epoch": 0.8881447705899117, "grad_norm": 1.3544697073652379, "learning_rate": 1.3616781572137458e-05, "loss": 0.702, "step": 6233 }, { "epoch": 0.8882872613280137, "grad_norm": 2.3540283193154465, "learning_rate": 1.361446281219175e-05, "loss": 0.6189, "step": 6234 }, { "epoch": 0.8884297520661157, "grad_norm": 1.4267594127690815, "learning_rate": 1.3612143828683383e-05, "loss": 0.7039, "step": 6235 }, { "epoch": 0.8885722428042178, "grad_norm": 1.2314932022535527, "learning_rate": 1.3609824621755789e-05, "loss": 0.6341, "step": 6236 }, { "epoch": 0.8887147335423198, "grad_norm": 1.3511321448454903, "learning_rate": 1.3607505191552418e-05, "loss": 0.6239, "step": 6237 }, { "epoch": 0.8888572242804218, "grad_norm": 1.2519173060783548, "learning_rate": 1.3605185538216729e-05, "loss": 0.5549, "step": 6238 }, { "epoch": 0.8889997150185238, "grad_norm": 1.3162604947868053, "learning_rate": 1.36028656618922e-05, "loss": 0.5497, "step": 6239 }, { "epoch": 0.8891422057566258, "grad_norm": 1.4895573091240766, "learning_rate": 1.3600545562722318e-05, "loss": 0.7701, "step": 6240 }, { "epoch": 0.8892846964947279, "grad_norm": 1.564666256821069, "learning_rate": 1.359822524085059e-05, "loss": 0.6598, "step": 6241 }, { "epoch": 0.8894271872328299, "grad_norm": 1.1342921088751847, "learning_rate": 1.359590469642053e-05, "loss": 0.552, "step": 6242 }, { "epoch": 0.8895696779709319, "grad_norm": 1.4577753037626293, "learning_rate": 1.3593583929575671e-05, "loss": 0.6549, "step": 6243 }, { "epoch": 0.8897121687090339, "grad_norm": 1.2829684823109795, "learning_rate": 1.3591262940459559e-05, "loss": 0.647, "step": 6244 }, { "epoch": 0.8898546594471359, "grad_norm": 1.6103244676896975, "learning_rate": 1.358894172921575e-05, "loss": 0.6084, "step": 6245 }, { "epoch": 0.889997150185238, "grad_norm": 1.5758648912925262, "learning_rate": 1.3586620295987816e-05, "loss": 0.611, "step": 6246 }, { "epoch": 0.89013964092334, "grad_norm": 1.4266319408007508, "learning_rate": 1.3584298640919342e-05, "loss": 0.6879, "step": 6247 }, { "epoch": 0.890282131661442, "grad_norm": 1.3095657406288572, "learning_rate": 1.358197676415393e-05, "loss": 0.6151, "step": 6248 }, { "epoch": 0.890424622399544, "grad_norm": 1.5003157519323655, "learning_rate": 1.357965466583519e-05, "loss": 0.7347, "step": 6249 }, { "epoch": 0.890567113137646, "grad_norm": 1.365982630600521, "learning_rate": 1.3577332346106755e-05, "loss": 0.6728, "step": 6250 }, { "epoch": 0.890709603875748, "grad_norm": 5.51569378106433, "learning_rate": 1.3575009805112261e-05, "loss": 0.7266, "step": 6251 }, { "epoch": 0.8908520946138501, "grad_norm": 1.2787018338480816, "learning_rate": 1.3572687042995364e-05, "loss": 0.5938, "step": 6252 }, { "epoch": 0.8909945853519521, "grad_norm": 1.2976883477966539, "learning_rate": 1.3570364059899732e-05, "loss": 0.6174, "step": 6253 }, { "epoch": 0.8911370760900541, "grad_norm": 1.3751028789493163, "learning_rate": 1.3568040855969044e-05, "loss": 0.6414, "step": 6254 }, { "epoch": 0.8912795668281561, "grad_norm": 2.117174204541818, "learning_rate": 1.3565717431346998e-05, "loss": 0.7695, "step": 6255 }, { "epoch": 0.8914220575662581, "grad_norm": 1.2614361237202885, "learning_rate": 1.3563393786177303e-05, "loss": 0.7175, "step": 6256 }, { "epoch": 0.8915645483043603, "grad_norm": 1.279470825631841, "learning_rate": 1.3561069920603683e-05, "loss": 0.5937, "step": 6257 }, { "epoch": 0.8917070390424623, "grad_norm": 1.2368196522170376, "learning_rate": 1.3558745834769871e-05, "loss": 0.6398, "step": 6258 }, { "epoch": 0.8918495297805643, "grad_norm": 1.3574040102392984, "learning_rate": 1.3556421528819622e-05, "loss": 0.6534, "step": 6259 }, { "epoch": 0.8919920205186663, "grad_norm": 1.324640833374198, "learning_rate": 1.3554097002896693e-05, "loss": 0.6581, "step": 6260 }, { "epoch": 0.8921345112567683, "grad_norm": 1.4095591865729882, "learning_rate": 1.3551772257144864e-05, "loss": 0.6427, "step": 6261 }, { "epoch": 0.8922770019948704, "grad_norm": 1.6320525436660982, "learning_rate": 1.3549447291707925e-05, "loss": 0.5654, "step": 6262 }, { "epoch": 0.8924194927329724, "grad_norm": 1.4576832614446371, "learning_rate": 1.3547122106729685e-05, "loss": 0.6334, "step": 6263 }, { "epoch": 0.8925619834710744, "grad_norm": 1.2234268063407132, "learning_rate": 1.3544796702353955e-05, "loss": 0.5904, "step": 6264 }, { "epoch": 0.8927044742091764, "grad_norm": 1.4777691446975771, "learning_rate": 1.354247107872457e-05, "loss": 0.6818, "step": 6265 }, { "epoch": 0.8928469649472784, "grad_norm": 1.3306478028023982, "learning_rate": 1.3540145235985377e-05, "loss": 0.6354, "step": 6266 }, { "epoch": 0.8929894556853805, "grad_norm": 1.2503499472392214, "learning_rate": 1.3537819174280234e-05, "loss": 0.7218, "step": 6267 }, { "epoch": 0.8931319464234825, "grad_norm": 1.3084863886530498, "learning_rate": 1.3535492893753009e-05, "loss": 0.6486, "step": 6268 }, { "epoch": 0.8932744371615845, "grad_norm": 1.5638127260456, "learning_rate": 1.353316639454759e-05, "loss": 0.6084, "step": 6269 }, { "epoch": 0.8934169278996865, "grad_norm": 1.3965829942926078, "learning_rate": 1.3530839676807876e-05, "loss": 0.7008, "step": 6270 }, { "epoch": 0.8935594186377885, "grad_norm": 1.3588544921260868, "learning_rate": 1.3528512740677782e-05, "loss": 0.7256, "step": 6271 }, { "epoch": 0.8937019093758906, "grad_norm": 1.3071973846171776, "learning_rate": 1.3526185586301232e-05, "loss": 0.7035, "step": 6272 }, { "epoch": 0.8938444001139926, "grad_norm": 1.3154417572925525, "learning_rate": 1.3523858213822166e-05, "loss": 0.6319, "step": 6273 }, { "epoch": 0.8939868908520946, "grad_norm": 1.417409835295448, "learning_rate": 1.352153062338454e-05, "loss": 0.6783, "step": 6274 }, { "epoch": 0.8941293815901966, "grad_norm": 1.288877682791065, "learning_rate": 1.3519202815132316e-05, "loss": 0.5546, "step": 6275 }, { "epoch": 0.8942718723282986, "grad_norm": 1.4312861180005312, "learning_rate": 1.3516874789209476e-05, "loss": 0.6391, "step": 6276 }, { "epoch": 0.8944143630664007, "grad_norm": 1.2940153467577562, "learning_rate": 1.3514546545760014e-05, "loss": 0.6482, "step": 6277 }, { "epoch": 0.8945568538045027, "grad_norm": 1.327609444573547, "learning_rate": 1.3512218084927936e-05, "loss": 0.6516, "step": 6278 }, { "epoch": 0.8946993445426047, "grad_norm": 1.1225910866144109, "learning_rate": 1.3509889406857266e-05, "loss": 0.5807, "step": 6279 }, { "epoch": 0.8948418352807067, "grad_norm": 1.2537220141666146, "learning_rate": 1.3507560511692036e-05, "loss": 0.6852, "step": 6280 }, { "epoch": 0.8949843260188087, "grad_norm": 1.8769072545610908, "learning_rate": 1.350523139957629e-05, "loss": 0.6054, "step": 6281 }, { "epoch": 0.8951268167569107, "grad_norm": 1.3013150540724039, "learning_rate": 1.3502902070654096e-05, "loss": 0.6353, "step": 6282 }, { "epoch": 0.8952693074950129, "grad_norm": 1.4462962764836986, "learning_rate": 1.3500572525069525e-05, "loss": 0.664, "step": 6283 }, { "epoch": 0.8954117982331149, "grad_norm": 1.447632241665879, "learning_rate": 1.3498242762966656e-05, "loss": 0.636, "step": 6284 }, { "epoch": 0.8955542889712169, "grad_norm": 1.3828362702048984, "learning_rate": 1.3495912784489605e-05, "loss": 0.6538, "step": 6285 }, { "epoch": 0.8956967797093189, "grad_norm": 1.3735186305241553, "learning_rate": 1.3493582589782476e-05, "loss": 0.6705, "step": 6286 }, { "epoch": 0.895839270447421, "grad_norm": 1.5752906256003525, "learning_rate": 1.3491252178989403e-05, "loss": 0.6437, "step": 6287 }, { "epoch": 0.895981761185523, "grad_norm": 1.2233416639687331, "learning_rate": 1.3488921552254519e-05, "loss": 0.5805, "step": 6288 }, { "epoch": 0.896124251923625, "grad_norm": 1.2699975681513058, "learning_rate": 1.348659070972199e-05, "loss": 0.6522, "step": 6289 }, { "epoch": 0.896266742661727, "grad_norm": 1.7794557546169183, "learning_rate": 1.3484259651535973e-05, "loss": 0.7245, "step": 6290 }, { "epoch": 0.896409233399829, "grad_norm": 1.5570043462408494, "learning_rate": 1.3481928377840654e-05, "loss": 0.5946, "step": 6291 }, { "epoch": 0.896551724137931, "grad_norm": 1.2868970412158913, "learning_rate": 1.347959688878023e-05, "loss": 0.6242, "step": 6292 }, { "epoch": 0.8966942148760331, "grad_norm": 1.5336318658018722, "learning_rate": 1.3477265184498902e-05, "loss": 0.6569, "step": 6293 }, { "epoch": 0.8968367056141351, "grad_norm": 1.3192733784199837, "learning_rate": 1.3474933265140897e-05, "loss": 0.6255, "step": 6294 }, { "epoch": 0.8969791963522371, "grad_norm": 1.4254589600521725, "learning_rate": 1.3472601130850449e-05, "loss": 0.6321, "step": 6295 }, { "epoch": 0.8971216870903391, "grad_norm": 1.43249966405478, "learning_rate": 1.3470268781771804e-05, "loss": 0.6194, "step": 6296 }, { "epoch": 0.8972641778284411, "grad_norm": 1.274560043447764, "learning_rate": 1.3467936218049224e-05, "loss": 0.6535, "step": 6297 }, { "epoch": 0.8974066685665432, "grad_norm": 1.448759105063589, "learning_rate": 1.3465603439826983e-05, "loss": 0.6187, "step": 6298 }, { "epoch": 0.8975491593046452, "grad_norm": 1.3280449030792127, "learning_rate": 1.3463270447249364e-05, "loss": 0.6432, "step": 6299 }, { "epoch": 0.8976916500427472, "grad_norm": 1.5662716557467886, "learning_rate": 1.3460937240460676e-05, "loss": 0.577, "step": 6300 }, { "epoch": 0.8978341407808492, "grad_norm": 1.3032929769333987, "learning_rate": 1.345860381960523e-05, "loss": 0.5893, "step": 6301 }, { "epoch": 0.8979766315189512, "grad_norm": 1.4703588362788311, "learning_rate": 1.3456270184827351e-05, "loss": 0.6678, "step": 6302 }, { "epoch": 0.8981191222570533, "grad_norm": 1.268277526638542, "learning_rate": 1.345393633627138e-05, "loss": 0.6023, "step": 6303 }, { "epoch": 0.8982616129951553, "grad_norm": 1.2607626655295596, "learning_rate": 1.3451602274081678e-05, "loss": 0.6158, "step": 6304 }, { "epoch": 0.8984041037332573, "grad_norm": 1.3656550723344334, "learning_rate": 1.34492679984026e-05, "loss": 0.5943, "step": 6305 }, { "epoch": 0.8985465944713593, "grad_norm": 1.595079335018939, "learning_rate": 1.3446933509378532e-05, "loss": 0.5782, "step": 6306 }, { "epoch": 0.8986890852094613, "grad_norm": 1.2540204109494641, "learning_rate": 1.3444598807153873e-05, "loss": 0.5803, "step": 6307 }, { "epoch": 0.8988315759475634, "grad_norm": 1.2876684747155478, "learning_rate": 1.344226389187302e-05, "loss": 0.6167, "step": 6308 }, { "epoch": 0.8989740666856655, "grad_norm": 1.4067826602696687, "learning_rate": 1.3439928763680397e-05, "loss": 0.6363, "step": 6309 }, { "epoch": 0.8991165574237675, "grad_norm": 1.3322805489587115, "learning_rate": 1.3437593422720438e-05, "loss": 0.6237, "step": 6310 }, { "epoch": 0.8992590481618695, "grad_norm": 1.3976622932103762, "learning_rate": 1.343525786913759e-05, "loss": 0.7416, "step": 6311 }, { "epoch": 0.8994015388999715, "grad_norm": 1.21651681452043, "learning_rate": 1.3432922103076307e-05, "loss": 0.6724, "step": 6312 }, { "epoch": 0.8995440296380736, "grad_norm": 1.4080106896602496, "learning_rate": 1.3430586124681064e-05, "loss": 0.6515, "step": 6313 }, { "epoch": 0.8996865203761756, "grad_norm": 1.4353447825232786, "learning_rate": 1.3428249934096349e-05, "loss": 0.6793, "step": 6314 }, { "epoch": 0.8998290111142776, "grad_norm": 1.970037111597401, "learning_rate": 1.3425913531466659e-05, "loss": 0.7511, "step": 6315 }, { "epoch": 0.8999715018523796, "grad_norm": 1.4111472670384235, "learning_rate": 1.3423576916936507e-05, "loss": 0.632, "step": 6316 }, { "epoch": 0.9001139925904816, "grad_norm": 1.3819004243455006, "learning_rate": 1.3421240090650414e-05, "loss": 0.6986, "step": 6317 }, { "epoch": 0.9002564833285837, "grad_norm": 1.3409265007750732, "learning_rate": 1.341890305275292e-05, "loss": 0.6576, "step": 6318 }, { "epoch": 0.9003989740666857, "grad_norm": 1.3831413772250725, "learning_rate": 1.3416565803388579e-05, "loss": 0.6305, "step": 6319 }, { "epoch": 0.9005414648047877, "grad_norm": 1.4507306504507398, "learning_rate": 1.3414228342701952e-05, "loss": 0.6651, "step": 6320 }, { "epoch": 0.9006839555428897, "grad_norm": 1.2249863015452565, "learning_rate": 1.3411890670837613e-05, "loss": 0.6462, "step": 6321 }, { "epoch": 0.9008264462809917, "grad_norm": 1.521749174466338, "learning_rate": 1.3409552787940161e-05, "loss": 0.6213, "step": 6322 }, { "epoch": 0.9009689370190938, "grad_norm": 1.263777405953792, "learning_rate": 1.340721469415419e-05, "loss": 0.6918, "step": 6323 }, { "epoch": 0.9011114277571958, "grad_norm": 1.444898341850806, "learning_rate": 1.3404876389624324e-05, "loss": 0.6224, "step": 6324 }, { "epoch": 0.9012539184952978, "grad_norm": 1.3196670471287464, "learning_rate": 1.3402537874495189e-05, "loss": 0.5916, "step": 6325 }, { "epoch": 0.9013964092333998, "grad_norm": 1.3574955898403605, "learning_rate": 1.3400199148911428e-05, "loss": 0.6577, "step": 6326 }, { "epoch": 0.9015388999715018, "grad_norm": 1.1468213902691722, "learning_rate": 1.3397860213017695e-05, "loss": 0.5959, "step": 6327 }, { "epoch": 0.9016813907096038, "grad_norm": 1.2992828358997197, "learning_rate": 1.3395521066958657e-05, "loss": 0.6587, "step": 6328 }, { "epoch": 0.9018238814477059, "grad_norm": 1.3023842935789023, "learning_rate": 1.3393181710879002e-05, "loss": 0.6584, "step": 6329 }, { "epoch": 0.9019663721858079, "grad_norm": 1.46471293077968, "learning_rate": 1.339084214492342e-05, "loss": 0.6514, "step": 6330 }, { "epoch": 0.9021088629239099, "grad_norm": 1.23291946119451, "learning_rate": 1.3388502369236616e-05, "loss": 0.6093, "step": 6331 }, { "epoch": 0.9022513536620119, "grad_norm": 1.4458599533363379, "learning_rate": 1.3386162383963313e-05, "loss": 0.7037, "step": 6332 }, { "epoch": 0.9023938444001139, "grad_norm": 1.3460707383900345, "learning_rate": 1.3383822189248247e-05, "loss": 0.6535, "step": 6333 }, { "epoch": 0.902536335138216, "grad_norm": 1.13576620611977, "learning_rate": 1.3381481785236163e-05, "loss": 0.6376, "step": 6334 }, { "epoch": 0.9026788258763181, "grad_norm": 1.3195982963652753, "learning_rate": 1.3379141172071815e-05, "loss": 0.6888, "step": 6335 }, { "epoch": 0.9028213166144201, "grad_norm": 1.5073114256844073, "learning_rate": 1.3376800349899978e-05, "loss": 0.6034, "step": 6336 }, { "epoch": 0.9029638073525221, "grad_norm": 1.3414553187305815, "learning_rate": 1.3374459318865445e-05, "loss": 0.7176, "step": 6337 }, { "epoch": 0.9031062980906241, "grad_norm": 1.442461916443146, "learning_rate": 1.3372118079113006e-05, "loss": 0.6324, "step": 6338 }, { "epoch": 0.9032487888287262, "grad_norm": 1.5983079290901885, "learning_rate": 1.336977663078747e-05, "loss": 0.63, "step": 6339 }, { "epoch": 0.9033912795668282, "grad_norm": 1.2004847347449918, "learning_rate": 1.3367434974033664e-05, "loss": 0.5958, "step": 6340 }, { "epoch": 0.9035337703049302, "grad_norm": 1.288243486149528, "learning_rate": 1.336509310899643e-05, "loss": 0.6523, "step": 6341 }, { "epoch": 0.9036762610430322, "grad_norm": 1.8024360804668318, "learning_rate": 1.336275103582061e-05, "loss": 0.6429, "step": 6342 }, { "epoch": 0.9038187517811342, "grad_norm": 1.3370038611443276, "learning_rate": 1.3360408754651064e-05, "loss": 0.6742, "step": 6343 }, { "epoch": 0.9039612425192363, "grad_norm": 1.3280348371458057, "learning_rate": 1.3358066265632679e-05, "loss": 0.6466, "step": 6344 }, { "epoch": 0.9041037332573383, "grad_norm": 1.3429622695454806, "learning_rate": 1.3355723568910334e-05, "loss": 0.6041, "step": 6345 }, { "epoch": 0.9042462239954403, "grad_norm": 3.2406308062445435, "learning_rate": 1.3353380664628934e-05, "loss": 0.6793, "step": 6346 }, { "epoch": 0.9043887147335423, "grad_norm": 1.296436099585845, "learning_rate": 1.335103755293339e-05, "loss": 0.6205, "step": 6347 }, { "epoch": 0.9045312054716443, "grad_norm": 1.4479488154330171, "learning_rate": 1.3348694233968633e-05, "loss": 0.5884, "step": 6348 }, { "epoch": 0.9046736962097464, "grad_norm": 1.305249260597245, "learning_rate": 1.3346350707879598e-05, "loss": 0.5458, "step": 6349 }, { "epoch": 0.9048161869478484, "grad_norm": 1.336786068200726, "learning_rate": 1.334400697481124e-05, "loss": 0.6479, "step": 6350 }, { "epoch": 0.9049586776859504, "grad_norm": 1.3454530841627725, "learning_rate": 1.334166303490852e-05, "loss": 0.6543, "step": 6351 }, { "epoch": 0.9051011684240524, "grad_norm": 1.2924225946514363, "learning_rate": 1.3339318888316425e-05, "loss": 0.6957, "step": 6352 }, { "epoch": 0.9052436591621544, "grad_norm": 1.3694186600326501, "learning_rate": 1.3336974535179938e-05, "loss": 0.6613, "step": 6353 }, { "epoch": 0.9053861499002565, "grad_norm": 1.4016479064533731, "learning_rate": 1.3334629975644064e-05, "loss": 0.6491, "step": 6354 }, { "epoch": 0.9055286406383585, "grad_norm": 1.3669689514438867, "learning_rate": 1.3332285209853819e-05, "loss": 0.6826, "step": 6355 }, { "epoch": 0.9056711313764605, "grad_norm": 1.2608265614638057, "learning_rate": 1.3329940237954237e-05, "loss": 0.5926, "step": 6356 }, { "epoch": 0.9058136221145625, "grad_norm": 1.3146330297162445, "learning_rate": 1.3327595060090351e-05, "loss": 0.5741, "step": 6357 }, { "epoch": 0.9059561128526645, "grad_norm": 1.3742332007582632, "learning_rate": 1.3325249676407221e-05, "loss": 0.5804, "step": 6358 }, { "epoch": 0.9060986035907665, "grad_norm": 1.1944102021770209, "learning_rate": 1.3322904087049917e-05, "loss": 0.5472, "step": 6359 }, { "epoch": 0.9062410943288686, "grad_norm": 1.4356532674790117, "learning_rate": 1.3320558292163515e-05, "loss": 0.5794, "step": 6360 }, { "epoch": 0.9063835850669707, "grad_norm": 1.3898772996523905, "learning_rate": 1.3318212291893107e-05, "loss": 0.5818, "step": 6361 }, { "epoch": 0.9065260758050727, "grad_norm": 1.313187268678364, "learning_rate": 1.3315866086383799e-05, "loss": 0.6349, "step": 6362 }, { "epoch": 0.9066685665431747, "grad_norm": 1.29979259710097, "learning_rate": 1.3313519675780713e-05, "loss": 0.6163, "step": 6363 }, { "epoch": 0.9068110572812768, "grad_norm": 1.2106974353873696, "learning_rate": 1.331117306022897e-05, "loss": 0.5884, "step": 6364 }, { "epoch": 0.9069535480193788, "grad_norm": 1.2514447989029562, "learning_rate": 1.3308826239873725e-05, "loss": 0.5842, "step": 6365 }, { "epoch": 0.9070960387574808, "grad_norm": 1.2545815581100574, "learning_rate": 1.3306479214860127e-05, "loss": 0.7262, "step": 6366 }, { "epoch": 0.9072385294955828, "grad_norm": 2.4388012935349264, "learning_rate": 1.3304131985333348e-05, "loss": 0.6458, "step": 6367 }, { "epoch": 0.9073810202336848, "grad_norm": 1.3223531550628493, "learning_rate": 1.330178455143857e-05, "loss": 0.548, "step": 6368 }, { "epoch": 0.9075235109717869, "grad_norm": 1.4413748114594789, "learning_rate": 1.3299436913320982e-05, "loss": 0.669, "step": 6369 }, { "epoch": 0.9076660017098889, "grad_norm": 1.2904506025365028, "learning_rate": 1.3297089071125795e-05, "loss": 0.6846, "step": 6370 }, { "epoch": 0.9078084924479909, "grad_norm": 1.2975638823907247, "learning_rate": 1.329474102499823e-05, "loss": 0.6523, "step": 6371 }, { "epoch": 0.9079509831860929, "grad_norm": 1.3930097337359206, "learning_rate": 1.3292392775083514e-05, "loss": 0.6718, "step": 6372 }, { "epoch": 0.9080934739241949, "grad_norm": 1.3362970071943563, "learning_rate": 1.3290044321526893e-05, "loss": 0.7057, "step": 6373 }, { "epoch": 0.908235964662297, "grad_norm": 1.2944092555728062, "learning_rate": 1.3287695664473628e-05, "loss": 0.679, "step": 6374 }, { "epoch": 0.908378455400399, "grad_norm": 1.3579270343388006, "learning_rate": 1.3285346804068984e-05, "loss": 0.6998, "step": 6375 }, { "epoch": 0.908520946138501, "grad_norm": 1.3507750207518912, "learning_rate": 1.3282997740458245e-05, "loss": 0.6951, "step": 6376 }, { "epoch": 0.908663436876603, "grad_norm": 1.2304894541022222, "learning_rate": 1.3280648473786706e-05, "loss": 0.619, "step": 6377 }, { "epoch": 0.908805927614705, "grad_norm": 1.2950391780943216, "learning_rate": 1.3278299004199678e-05, "loss": 0.6064, "step": 6378 }, { "epoch": 0.908948418352807, "grad_norm": 1.413695260692835, "learning_rate": 1.327594933184247e-05, "loss": 0.7078, "step": 6379 }, { "epoch": 0.9090909090909091, "grad_norm": 1.4137800315672384, "learning_rate": 1.3273599456860424e-05, "loss": 0.6387, "step": 6380 }, { "epoch": 0.9092333998290111, "grad_norm": 1.2631848327130737, "learning_rate": 1.327124937939889e-05, "loss": 0.6479, "step": 6381 }, { "epoch": 0.9093758905671131, "grad_norm": 1.3285635976665093, "learning_rate": 1.3268899099603212e-05, "loss": 0.6404, "step": 6382 }, { "epoch": 0.9095183813052151, "grad_norm": 1.7253903449767565, "learning_rate": 1.3266548617618766e-05, "loss": 0.6422, "step": 6383 }, { "epoch": 0.9096608720433171, "grad_norm": 1.4448754892302968, "learning_rate": 1.3264197933590937e-05, "loss": 0.5642, "step": 6384 }, { "epoch": 0.9098033627814192, "grad_norm": 1.3495091767439509, "learning_rate": 1.326184704766512e-05, "loss": 0.6818, "step": 6385 }, { "epoch": 0.9099458535195213, "grad_norm": 1.42769173105354, "learning_rate": 1.3259495959986719e-05, "loss": 0.603, "step": 6386 }, { "epoch": 0.9100883442576233, "grad_norm": 1.3042939812954875, "learning_rate": 1.3257144670701155e-05, "loss": 0.637, "step": 6387 }, { "epoch": 0.9102308349957253, "grad_norm": 1.3925751914785223, "learning_rate": 1.3254793179953862e-05, "loss": 0.6395, "step": 6388 }, { "epoch": 0.9103733257338273, "grad_norm": 1.4814320683906894, "learning_rate": 1.3252441487890289e-05, "loss": 0.6807, "step": 6389 }, { "epoch": 0.9105158164719294, "grad_norm": 1.2511245974695113, "learning_rate": 1.3250089594655884e-05, "loss": 0.616, "step": 6390 }, { "epoch": 0.9106583072100314, "grad_norm": 1.2026503209521617, "learning_rate": 1.3247737500396123e-05, "loss": 0.6265, "step": 6391 }, { "epoch": 0.9108007979481334, "grad_norm": 1.3151359693317408, "learning_rate": 1.3245385205256484e-05, "loss": 0.6092, "step": 6392 }, { "epoch": 0.9109432886862354, "grad_norm": 1.4724375395885567, "learning_rate": 1.3243032709382471e-05, "loss": 0.7081, "step": 6393 }, { "epoch": 0.9110857794243374, "grad_norm": 1.4386398549543253, "learning_rate": 1.324068001291958e-05, "loss": 0.5812, "step": 6394 }, { "epoch": 0.9112282701624395, "grad_norm": 1.3587503980154991, "learning_rate": 1.3238327116013338e-05, "loss": 0.6736, "step": 6395 }, { "epoch": 0.9113707609005415, "grad_norm": 1.4225949645433338, "learning_rate": 1.3235974018809277e-05, "loss": 0.6829, "step": 6396 }, { "epoch": 0.9115132516386435, "grad_norm": 1.2762193404956537, "learning_rate": 1.3233620721452935e-05, "loss": 0.6615, "step": 6397 }, { "epoch": 0.9116557423767455, "grad_norm": 1.3752569733188533, "learning_rate": 1.3231267224089874e-05, "loss": 0.6441, "step": 6398 }, { "epoch": 0.9117982331148475, "grad_norm": 1.3491081490864043, "learning_rate": 1.322891352686566e-05, "loss": 0.6184, "step": 6399 }, { "epoch": 0.9119407238529496, "grad_norm": 1.2753777436943725, "learning_rate": 1.3226559629925881e-05, "loss": 0.6404, "step": 6400 }, { "epoch": 0.9120832145910516, "grad_norm": 1.4198576280178623, "learning_rate": 1.3224205533416122e-05, "loss": 0.6471, "step": 6401 }, { "epoch": 0.9122257053291536, "grad_norm": 1.3367583364001931, "learning_rate": 1.3221851237481994e-05, "loss": 0.5615, "step": 6402 }, { "epoch": 0.9123681960672556, "grad_norm": 1.4523654748683315, "learning_rate": 1.3219496742269116e-05, "loss": 0.6595, "step": 6403 }, { "epoch": 0.9125106868053576, "grad_norm": 1.4283181695127039, "learning_rate": 1.3217142047923117e-05, "loss": 0.7349, "step": 6404 }, { "epoch": 0.9126531775434596, "grad_norm": 1.5919094117841432, "learning_rate": 1.321478715458964e-05, "loss": 0.6271, "step": 6405 }, { "epoch": 0.9127956682815617, "grad_norm": 2.2722941812627564, "learning_rate": 1.3212432062414343e-05, "loss": 0.5885, "step": 6406 }, { "epoch": 0.9129381590196637, "grad_norm": 2.8846490107758047, "learning_rate": 1.321007677154289e-05, "loss": 0.6636, "step": 6407 }, { "epoch": 0.9130806497577657, "grad_norm": 1.406103737186234, "learning_rate": 1.3207721282120964e-05, "loss": 0.6059, "step": 6408 }, { "epoch": 0.9132231404958677, "grad_norm": 1.382309922374828, "learning_rate": 1.3205365594294257e-05, "loss": 0.6031, "step": 6409 }, { "epoch": 0.9133656312339697, "grad_norm": 1.2595185466612038, "learning_rate": 1.3203009708208472e-05, "loss": 0.6097, "step": 6410 }, { "epoch": 0.9135081219720718, "grad_norm": 1.293507361566443, "learning_rate": 1.3200653624009327e-05, "loss": 0.602, "step": 6411 }, { "epoch": 0.9136506127101739, "grad_norm": 1.635576563831584, "learning_rate": 1.3198297341842552e-05, "loss": 0.6543, "step": 6412 }, { "epoch": 0.9137931034482759, "grad_norm": 1.4481797357258035, "learning_rate": 1.3195940861853887e-05, "loss": 0.6805, "step": 6413 }, { "epoch": 0.9139355941863779, "grad_norm": 1.3777536001414963, "learning_rate": 1.3193584184189083e-05, "loss": 0.6936, "step": 6414 }, { "epoch": 0.91407808492448, "grad_norm": 1.3753295915793071, "learning_rate": 1.319122730899391e-05, "loss": 0.7146, "step": 6415 }, { "epoch": 0.914220575662582, "grad_norm": 2.3452775748085464, "learning_rate": 1.3188870236414146e-05, "loss": 0.6399, "step": 6416 }, { "epoch": 0.914363066400684, "grad_norm": 1.2918947226435427, "learning_rate": 1.3186512966595579e-05, "loss": 0.5731, "step": 6417 }, { "epoch": 0.914505557138786, "grad_norm": 1.3742312995758021, "learning_rate": 1.3184155499684013e-05, "loss": 0.6386, "step": 6418 }, { "epoch": 0.914648047876888, "grad_norm": 1.2072522706401942, "learning_rate": 1.3181797835825263e-05, "loss": 0.6114, "step": 6419 }, { "epoch": 0.91479053861499, "grad_norm": 1.340548606106439, "learning_rate": 1.3179439975165154e-05, "loss": 0.7223, "step": 6420 }, { "epoch": 0.9149330293530921, "grad_norm": 1.6147329978975067, "learning_rate": 1.3177081917849524e-05, "loss": 0.6289, "step": 6421 }, { "epoch": 0.9150755200911941, "grad_norm": 1.4037528397478893, "learning_rate": 1.3174723664024227e-05, "loss": 0.6288, "step": 6422 }, { "epoch": 0.9152180108292961, "grad_norm": 1.338878243360894, "learning_rate": 1.3172365213835125e-05, "loss": 0.6888, "step": 6423 }, { "epoch": 0.9153605015673981, "grad_norm": 1.4760312968172977, "learning_rate": 1.3170006567428094e-05, "loss": 0.6248, "step": 6424 }, { "epoch": 0.9155029923055001, "grad_norm": 1.3991809680318923, "learning_rate": 1.3167647724949022e-05, "loss": 0.6635, "step": 6425 }, { "epoch": 0.9156454830436022, "grad_norm": 1.3012656647334626, "learning_rate": 1.3165288686543809e-05, "loss": 0.6028, "step": 6426 }, { "epoch": 0.9157879737817042, "grad_norm": 1.3277689819186174, "learning_rate": 1.3162929452358364e-05, "loss": 0.7202, "step": 6427 }, { "epoch": 0.9159304645198062, "grad_norm": 1.3725232041539464, "learning_rate": 1.3160570022538615e-05, "loss": 0.6188, "step": 6428 }, { "epoch": 0.9160729552579082, "grad_norm": 1.263390959958037, "learning_rate": 1.3158210397230493e-05, "loss": 0.67, "step": 6429 }, { "epoch": 0.9162154459960102, "grad_norm": 1.3736758603968948, "learning_rate": 1.3155850576579949e-05, "loss": 0.6359, "step": 6430 }, { "epoch": 0.9163579367341123, "grad_norm": 1.3858835324212522, "learning_rate": 1.3153490560732944e-05, "loss": 0.6391, "step": 6431 }, { "epoch": 0.9165004274722143, "grad_norm": 1.3467446794119784, "learning_rate": 1.315113034983545e-05, "loss": 0.58, "step": 6432 }, { "epoch": 0.9166429182103163, "grad_norm": 1.4268764282384445, "learning_rate": 1.3148769944033453e-05, "loss": 0.6793, "step": 6433 }, { "epoch": 0.9167854089484183, "grad_norm": 1.1495295947205606, "learning_rate": 1.3146409343472946e-05, "loss": 0.666, "step": 6434 }, { "epoch": 0.9169278996865203, "grad_norm": 1.403310270932741, "learning_rate": 1.3144048548299937e-05, "loss": 0.5832, "step": 6435 }, { "epoch": 0.9170703904246224, "grad_norm": 1.2181659699852667, "learning_rate": 1.314168755866045e-05, "loss": 0.7205, "step": 6436 }, { "epoch": 0.9172128811627244, "grad_norm": 1.2291276350817668, "learning_rate": 1.3139326374700514e-05, "loss": 0.5969, "step": 6437 }, { "epoch": 0.9173553719008265, "grad_norm": 1.2131941861738325, "learning_rate": 1.3136964996566175e-05, "loss": 0.6041, "step": 6438 }, { "epoch": 0.9174978626389285, "grad_norm": 1.5052217964342123, "learning_rate": 1.3134603424403491e-05, "loss": 0.6168, "step": 6439 }, { "epoch": 0.9176403533770305, "grad_norm": 1.4193486991322937, "learning_rate": 1.3132241658358528e-05, "loss": 0.7178, "step": 6440 }, { "epoch": 0.9177828441151326, "grad_norm": 1.2354870577879076, "learning_rate": 1.3129879698577372e-05, "loss": 0.5616, "step": 6441 }, { "epoch": 0.9179253348532346, "grad_norm": 3.567411815518566, "learning_rate": 1.312751754520611e-05, "loss": 0.6711, "step": 6442 }, { "epoch": 0.9180678255913366, "grad_norm": 1.3679066798605257, "learning_rate": 1.3125155198390847e-05, "loss": 0.6457, "step": 6443 }, { "epoch": 0.9182103163294386, "grad_norm": 1.343806675411307, "learning_rate": 1.3122792658277698e-05, "loss": 0.6822, "step": 6444 }, { "epoch": 0.9183528070675406, "grad_norm": 1.2483335946844292, "learning_rate": 1.3120429925012796e-05, "loss": 0.5619, "step": 6445 }, { "epoch": 0.9184952978056427, "grad_norm": 1.3490774532043674, "learning_rate": 1.311806699874228e-05, "loss": 0.5955, "step": 6446 }, { "epoch": 0.9186377885437447, "grad_norm": 1.1327433726747183, "learning_rate": 1.31157038796123e-05, "loss": 0.5669, "step": 6447 }, { "epoch": 0.9187802792818467, "grad_norm": 1.3297709100927146, "learning_rate": 1.3113340567769027e-05, "loss": 0.5399, "step": 6448 }, { "epoch": 0.9189227700199487, "grad_norm": 1.2877678563566133, "learning_rate": 1.3110977063358626e-05, "loss": 0.6624, "step": 6449 }, { "epoch": 0.9190652607580507, "grad_norm": 1.3874041939794193, "learning_rate": 1.3108613366527295e-05, "loss": 0.6685, "step": 6450 }, { "epoch": 0.9192077514961527, "grad_norm": 3.1489387346021354, "learning_rate": 1.3106249477421224e-05, "loss": 0.6347, "step": 6451 }, { "epoch": 0.9193502422342548, "grad_norm": 1.9541580348843572, "learning_rate": 1.3103885396186636e-05, "loss": 0.6784, "step": 6452 }, { "epoch": 0.9194927329723568, "grad_norm": 1.2877187551931977, "learning_rate": 1.3101521122969749e-05, "loss": 0.5859, "step": 6453 }, { "epoch": 0.9196352237104588, "grad_norm": 1.2031156574097566, "learning_rate": 1.3099156657916798e-05, "loss": 0.5281, "step": 6454 }, { "epoch": 0.9197777144485608, "grad_norm": 1.2941841174633444, "learning_rate": 1.3096792001174033e-05, "loss": 0.6232, "step": 6455 }, { "epoch": 0.9199202051866628, "grad_norm": 1.463443667745299, "learning_rate": 1.3094427152887712e-05, "loss": 0.6972, "step": 6456 }, { "epoch": 0.9200626959247649, "grad_norm": 1.476426319866894, "learning_rate": 1.3092062113204104e-05, "loss": 0.5988, "step": 6457 }, { "epoch": 0.9202051866628669, "grad_norm": 1.3765730466869674, "learning_rate": 1.3089696882269496e-05, "loss": 0.6986, "step": 6458 }, { "epoch": 0.9203476774009689, "grad_norm": 1.1328413574286993, "learning_rate": 1.3087331460230182e-05, "loss": 0.5519, "step": 6459 }, { "epoch": 0.9204901681390709, "grad_norm": 1.3365803328995352, "learning_rate": 1.3084965847232464e-05, "loss": 0.7075, "step": 6460 }, { "epoch": 0.9206326588771729, "grad_norm": 1.3554628515196028, "learning_rate": 1.3082600043422669e-05, "loss": 0.7946, "step": 6461 }, { "epoch": 0.920775149615275, "grad_norm": 1.3108156777816713, "learning_rate": 1.308023404894712e-05, "loss": 0.6169, "step": 6462 }, { "epoch": 0.920917640353377, "grad_norm": 1.4114392823365958, "learning_rate": 1.3077867863952163e-05, "loss": 0.6533, "step": 6463 }, { "epoch": 0.9210601310914791, "grad_norm": 1.1994182211250224, "learning_rate": 1.307550148858415e-05, "loss": 0.5565, "step": 6464 }, { "epoch": 0.9212026218295811, "grad_norm": 1.2998201280734514, "learning_rate": 1.3073134922989448e-05, "loss": 0.6694, "step": 6465 }, { "epoch": 0.9213451125676831, "grad_norm": 1.2586346663723302, "learning_rate": 1.3070768167314431e-05, "loss": 0.624, "step": 6466 }, { "epoch": 0.9214876033057852, "grad_norm": 1.3704657547558525, "learning_rate": 1.3068401221705493e-05, "loss": 0.6794, "step": 6467 }, { "epoch": 0.9216300940438872, "grad_norm": 1.763697918706309, "learning_rate": 1.3066034086309032e-05, "loss": 0.6229, "step": 6468 }, { "epoch": 0.9217725847819892, "grad_norm": 1.509991221147483, "learning_rate": 1.3063666761271461e-05, "loss": 0.7049, "step": 6469 }, { "epoch": 0.9219150755200912, "grad_norm": 1.4275060245935522, "learning_rate": 1.3061299246739205e-05, "loss": 0.6188, "step": 6470 }, { "epoch": 0.9220575662581932, "grad_norm": 1.150685356442152, "learning_rate": 1.3058931542858702e-05, "loss": 0.5448, "step": 6471 }, { "epoch": 0.9222000569962953, "grad_norm": 1.2046931641570935, "learning_rate": 1.3056563649776394e-05, "loss": 0.6175, "step": 6472 }, { "epoch": 0.9223425477343973, "grad_norm": 1.4211055859704012, "learning_rate": 1.3054195567638746e-05, "loss": 0.6463, "step": 6473 }, { "epoch": 0.9224850384724993, "grad_norm": 1.3462799168451023, "learning_rate": 1.3051827296592225e-05, "loss": 0.6052, "step": 6474 }, { "epoch": 0.9226275292106013, "grad_norm": 1.244740131900233, "learning_rate": 1.304945883678332e-05, "loss": 0.626, "step": 6475 }, { "epoch": 0.9227700199487033, "grad_norm": 1.3346891628214772, "learning_rate": 1.304709018835852e-05, "loss": 0.6269, "step": 6476 }, { "epoch": 0.9229125106868054, "grad_norm": 1.3325442556338318, "learning_rate": 1.304472135146433e-05, "loss": 0.5844, "step": 6477 }, { "epoch": 0.9230550014249074, "grad_norm": 1.3854158545810487, "learning_rate": 1.3042352326247278e-05, "loss": 0.6227, "step": 6478 }, { "epoch": 0.9231974921630094, "grad_norm": 1.2599566850937036, "learning_rate": 1.3039983112853883e-05, "loss": 0.5742, "step": 6479 }, { "epoch": 0.9233399829011114, "grad_norm": 1.3598525630729605, "learning_rate": 1.3037613711430688e-05, "loss": 0.7021, "step": 6480 }, { "epoch": 0.9234824736392134, "grad_norm": 1.4151036705761217, "learning_rate": 1.3035244122124249e-05, "loss": 0.6398, "step": 6481 }, { "epoch": 0.9236249643773154, "grad_norm": 2.1795889987610995, "learning_rate": 1.3032874345081129e-05, "loss": 0.6919, "step": 6482 }, { "epoch": 0.9237674551154175, "grad_norm": 1.1960370598580379, "learning_rate": 1.3030504380447902e-05, "loss": 0.5958, "step": 6483 }, { "epoch": 0.9239099458535195, "grad_norm": 1.2487669647495836, "learning_rate": 1.3028134228371158e-05, "loss": 0.6262, "step": 6484 }, { "epoch": 0.9240524365916215, "grad_norm": 1.3084456729642873, "learning_rate": 1.3025763888997501e-05, "loss": 0.6114, "step": 6485 }, { "epoch": 0.9241949273297235, "grad_norm": 1.3867765392901301, "learning_rate": 1.302339336247353e-05, "loss": 0.6668, "step": 6486 }, { "epoch": 0.9243374180678255, "grad_norm": 1.3635877392853712, "learning_rate": 1.3021022648945878e-05, "loss": 0.6568, "step": 6487 }, { "epoch": 0.9244799088059276, "grad_norm": 1.3718913891122442, "learning_rate": 1.3018651748561171e-05, "loss": 0.6574, "step": 6488 }, { "epoch": 0.9246223995440296, "grad_norm": 1.3356905117013849, "learning_rate": 1.3016280661466063e-05, "loss": 0.6161, "step": 6489 }, { "epoch": 0.9247648902821317, "grad_norm": 1.2055438630918922, "learning_rate": 1.3013909387807205e-05, "loss": 0.6044, "step": 6490 }, { "epoch": 0.9249073810202337, "grad_norm": 1.4480575524804737, "learning_rate": 1.3011537927731265e-05, "loss": 0.6711, "step": 6491 }, { "epoch": 0.9250498717583358, "grad_norm": 1.533602805493045, "learning_rate": 1.3009166281384929e-05, "loss": 0.5781, "step": 6492 }, { "epoch": 0.9251923624964378, "grad_norm": 2.15417048764401, "learning_rate": 1.3006794448914886e-05, "loss": 0.635, "step": 6493 }, { "epoch": 0.9253348532345398, "grad_norm": 1.3412538495633601, "learning_rate": 1.3004422430467836e-05, "loss": 0.6368, "step": 6494 }, { "epoch": 0.9254773439726418, "grad_norm": 1.2790688766886635, "learning_rate": 1.3002050226190493e-05, "loss": 0.6234, "step": 6495 }, { "epoch": 0.9256198347107438, "grad_norm": 1.3014034658957263, "learning_rate": 1.299967783622959e-05, "loss": 0.688, "step": 6496 }, { "epoch": 0.9257623254488458, "grad_norm": 1.415533590756984, "learning_rate": 1.2997305260731858e-05, "loss": 0.5604, "step": 6497 }, { "epoch": 0.9259048161869479, "grad_norm": 1.3773844250331635, "learning_rate": 1.2994932499844052e-05, "loss": 0.6869, "step": 6498 }, { "epoch": 0.9260473069250499, "grad_norm": 1.3071788607472314, "learning_rate": 1.2992559553712927e-05, "loss": 0.7004, "step": 6499 }, { "epoch": 0.9261897976631519, "grad_norm": 1.153907889047531, "learning_rate": 1.299018642248526e-05, "loss": 0.5598, "step": 6500 }, { "epoch": 0.9263322884012539, "grad_norm": 1.3728528225605274, "learning_rate": 1.2987813106307829e-05, "loss": 0.7266, "step": 6501 }, { "epoch": 0.9264747791393559, "grad_norm": 1.4151975477091963, "learning_rate": 1.2985439605327435e-05, "loss": 0.5836, "step": 6502 }, { "epoch": 0.926617269877458, "grad_norm": 1.3063853992734344, "learning_rate": 1.2983065919690878e-05, "loss": 0.6262, "step": 6503 }, { "epoch": 0.92675976061556, "grad_norm": 1.3088422671058118, "learning_rate": 1.2980692049544982e-05, "loss": 0.6578, "step": 6504 }, { "epoch": 0.926902251353662, "grad_norm": 1.2737162756051037, "learning_rate": 1.2978317995036573e-05, "loss": 0.6655, "step": 6505 }, { "epoch": 0.927044742091764, "grad_norm": 1.3633407623626541, "learning_rate": 1.297594375631249e-05, "loss": 0.5633, "step": 6506 }, { "epoch": 0.927187232829866, "grad_norm": 1.455910346301773, "learning_rate": 1.297356933351959e-05, "loss": 0.6952, "step": 6507 }, { "epoch": 0.9273297235679681, "grad_norm": 1.3918294565101967, "learning_rate": 1.2971194726804734e-05, "loss": 0.6797, "step": 6508 }, { "epoch": 0.9274722143060701, "grad_norm": 1.376149977526017, "learning_rate": 1.2968819936314794e-05, "loss": 0.6562, "step": 6509 }, { "epoch": 0.9276147050441721, "grad_norm": 1.8770608413292427, "learning_rate": 1.2966444962196655e-05, "loss": 0.5716, "step": 6510 }, { "epoch": 0.9277571957822741, "grad_norm": 1.2960018511631142, "learning_rate": 1.2964069804597224e-05, "loss": 0.6208, "step": 6511 }, { "epoch": 0.9278996865203761, "grad_norm": 1.4102316229017462, "learning_rate": 1.2961694463663401e-05, "loss": 0.603, "step": 6512 }, { "epoch": 0.9280421772584782, "grad_norm": 1.3768971395110936, "learning_rate": 1.2959318939542107e-05, "loss": 0.6276, "step": 6513 }, { "epoch": 0.9281846679965802, "grad_norm": 1.3975115278209425, "learning_rate": 1.2956943232380278e-05, "loss": 0.6803, "step": 6514 }, { "epoch": 0.9283271587346823, "grad_norm": 1.381625500346174, "learning_rate": 1.2954567342324855e-05, "loss": 0.6092, "step": 6515 }, { "epoch": 0.9284696494727843, "grad_norm": 1.2707533186888937, "learning_rate": 1.2952191269522789e-05, "loss": 0.642, "step": 6516 }, { "epoch": 0.9286121402108863, "grad_norm": 1.4005920545777002, "learning_rate": 1.2949815014121047e-05, "loss": 0.6862, "step": 6517 }, { "epoch": 0.9287546309489884, "grad_norm": 1.4530247906805636, "learning_rate": 1.2947438576266609e-05, "loss": 0.5839, "step": 6518 }, { "epoch": 0.9288971216870904, "grad_norm": 1.4347070507272082, "learning_rate": 1.294506195610646e-05, "loss": 0.6306, "step": 6519 }, { "epoch": 0.9290396124251924, "grad_norm": 1.2974237422642676, "learning_rate": 1.29426851537876e-05, "loss": 0.6295, "step": 6520 }, { "epoch": 0.9291821031632944, "grad_norm": 1.3842514918743487, "learning_rate": 1.294030816945704e-05, "loss": 0.6645, "step": 6521 }, { "epoch": 0.9293245939013964, "grad_norm": 1.24412904025562, "learning_rate": 1.2937931003261799e-05, "loss": 0.6327, "step": 6522 }, { "epoch": 0.9294670846394985, "grad_norm": 1.7032570757673735, "learning_rate": 1.2935553655348914e-05, "loss": 0.6562, "step": 6523 }, { "epoch": 0.9296095753776005, "grad_norm": 1.5543699789387044, "learning_rate": 1.2933176125865428e-05, "loss": 0.5658, "step": 6524 }, { "epoch": 0.9297520661157025, "grad_norm": 1.3575808717212146, "learning_rate": 1.2930798414958393e-05, "loss": 0.7155, "step": 6525 }, { "epoch": 0.9298945568538045, "grad_norm": 1.2616907413808607, "learning_rate": 1.2928420522774882e-05, "loss": 0.6567, "step": 6526 }, { "epoch": 0.9300370475919065, "grad_norm": 1.317473775088316, "learning_rate": 1.2926042449461971e-05, "loss": 0.6978, "step": 6527 }, { "epoch": 0.9301795383300085, "grad_norm": 1.3420255507510195, "learning_rate": 1.2923664195166745e-05, "loss": 0.5932, "step": 6528 }, { "epoch": 0.9303220290681106, "grad_norm": 1.3839205599823137, "learning_rate": 1.292128576003631e-05, "loss": 0.5883, "step": 6529 }, { "epoch": 0.9304645198062126, "grad_norm": 1.9243702104825073, "learning_rate": 1.2918907144217776e-05, "loss": 0.5594, "step": 6530 }, { "epoch": 0.9306070105443146, "grad_norm": 1.3481950152527002, "learning_rate": 1.2916528347858262e-05, "loss": 0.6384, "step": 6531 }, { "epoch": 0.9307495012824166, "grad_norm": 1.7206380976997742, "learning_rate": 1.2914149371104902e-05, "loss": 0.5889, "step": 6532 }, { "epoch": 0.9308919920205186, "grad_norm": 1.2502047022339555, "learning_rate": 1.291177021410485e-05, "loss": 0.5657, "step": 6533 }, { "epoch": 0.9310344827586207, "grad_norm": 1.4623308278752027, "learning_rate": 1.2909390877005255e-05, "loss": 0.5812, "step": 6534 }, { "epoch": 0.9311769734967227, "grad_norm": 1.2677504994522868, "learning_rate": 1.2907011359953284e-05, "loss": 0.645, "step": 6535 }, { "epoch": 0.9313194642348247, "grad_norm": 1.327580189134056, "learning_rate": 1.2904631663096117e-05, "loss": 0.6216, "step": 6536 }, { "epoch": 0.9314619549729267, "grad_norm": 1.3415296165117692, "learning_rate": 1.2902251786580946e-05, "loss": 0.6482, "step": 6537 }, { "epoch": 0.9316044457110287, "grad_norm": 1.2894501175704658, "learning_rate": 1.2899871730554967e-05, "loss": 0.6024, "step": 6538 }, { "epoch": 0.9317469364491308, "grad_norm": 1.166128022344181, "learning_rate": 1.289749149516539e-05, "loss": 0.5709, "step": 6539 }, { "epoch": 0.9318894271872328, "grad_norm": 1.1938401184009053, "learning_rate": 1.2895111080559447e-05, "loss": 0.5658, "step": 6540 }, { "epoch": 0.9320319179253349, "grad_norm": 1.318555216443348, "learning_rate": 1.2892730486884367e-05, "loss": 0.7199, "step": 6541 }, { "epoch": 0.9321744086634369, "grad_norm": 1.2769359094621824, "learning_rate": 1.2890349714287394e-05, "loss": 0.659, "step": 6542 }, { "epoch": 0.932316899401539, "grad_norm": 1.4306486524114828, "learning_rate": 1.2887968762915784e-05, "loss": 0.71, "step": 6543 }, { "epoch": 0.932459390139641, "grad_norm": 1.2499923234880461, "learning_rate": 1.2885587632916808e-05, "loss": 0.668, "step": 6544 }, { "epoch": 0.932601880877743, "grad_norm": 1.162009051805114, "learning_rate": 1.2883206324437741e-05, "loss": 0.6089, "step": 6545 }, { "epoch": 0.932744371615845, "grad_norm": 1.2992321640190045, "learning_rate": 1.2880824837625866e-05, "loss": 0.6213, "step": 6546 }, { "epoch": 0.932886862353947, "grad_norm": 1.658138007895242, "learning_rate": 1.2878443172628499e-05, "loss": 0.7496, "step": 6547 }, { "epoch": 0.933029353092049, "grad_norm": 1.389421713873237, "learning_rate": 1.2876061329592941e-05, "loss": 0.6792, "step": 6548 }, { "epoch": 0.9331718438301511, "grad_norm": 1.491296773356174, "learning_rate": 1.2873679308666515e-05, "loss": 0.632, "step": 6549 }, { "epoch": 0.9333143345682531, "grad_norm": 1.3686988563078057, "learning_rate": 1.2871297109996554e-05, "loss": 0.576, "step": 6550 }, { "epoch": 0.9334568253063551, "grad_norm": 1.2651800863765337, "learning_rate": 1.2868914733730405e-05, "loss": 0.5866, "step": 6551 }, { "epoch": 0.9335993160444571, "grad_norm": 1.2110859220083576, "learning_rate": 1.2866532180015423e-05, "loss": 0.5575, "step": 6552 }, { "epoch": 0.9337418067825591, "grad_norm": 1.2207866359966677, "learning_rate": 1.2864149448998972e-05, "loss": 0.632, "step": 6553 }, { "epoch": 0.9338842975206612, "grad_norm": 1.3839620148612615, "learning_rate": 1.2861766540828429e-05, "loss": 0.6246, "step": 6554 }, { "epoch": 0.9340267882587632, "grad_norm": 1.344827582920332, "learning_rate": 1.2859383455651184e-05, "loss": 0.6438, "step": 6555 }, { "epoch": 0.9341692789968652, "grad_norm": 1.2735244937421262, "learning_rate": 1.285700019361464e-05, "loss": 0.6355, "step": 6556 }, { "epoch": 0.9343117697349672, "grad_norm": 1.333270236218049, "learning_rate": 1.2854616754866199e-05, "loss": 0.6572, "step": 6557 }, { "epoch": 0.9344542604730692, "grad_norm": 1.5424449411264263, "learning_rate": 1.2852233139553287e-05, "loss": 0.6407, "step": 6558 }, { "epoch": 0.9345967512111713, "grad_norm": 1.2408985595899285, "learning_rate": 1.2849849347823335e-05, "loss": 0.5992, "step": 6559 }, { "epoch": 0.9347392419492733, "grad_norm": 1.3911702696107102, "learning_rate": 1.284746537982379e-05, "loss": 0.7161, "step": 6560 }, { "epoch": 0.9348817326873753, "grad_norm": 1.5161462639710204, "learning_rate": 1.2845081235702094e-05, "loss": 0.6527, "step": 6561 }, { "epoch": 0.9350242234254773, "grad_norm": 1.2943069782417995, "learning_rate": 1.2842696915605725e-05, "loss": 0.6455, "step": 6562 }, { "epoch": 0.9351667141635793, "grad_norm": 1.368653872144086, "learning_rate": 1.2840312419682155e-05, "loss": 0.673, "step": 6563 }, { "epoch": 0.9353092049016813, "grad_norm": 1.2097273249947644, "learning_rate": 1.2837927748078864e-05, "loss": 0.5458, "step": 6564 }, { "epoch": 0.9354516956397834, "grad_norm": 1.325915256588374, "learning_rate": 1.2835542900943356e-05, "loss": 0.6315, "step": 6565 }, { "epoch": 0.9355941863778854, "grad_norm": 1.3183601685867736, "learning_rate": 1.2833157878423136e-05, "loss": 0.7125, "step": 6566 }, { "epoch": 0.9357366771159875, "grad_norm": 1.2555358755121293, "learning_rate": 1.2830772680665726e-05, "loss": 0.6036, "step": 6567 }, { "epoch": 0.9358791678540895, "grad_norm": 1.675173043398713, "learning_rate": 1.2828387307818648e-05, "loss": 0.6072, "step": 6568 }, { "epoch": 0.9360216585921916, "grad_norm": 1.3618779340528246, "learning_rate": 1.2826001760029453e-05, "loss": 0.6361, "step": 6569 }, { "epoch": 0.9361641493302936, "grad_norm": 1.5981389141402358, "learning_rate": 1.282361603744569e-05, "loss": 0.7018, "step": 6570 }, { "epoch": 0.9363066400683956, "grad_norm": 1.3610474987277583, "learning_rate": 1.2821230140214917e-05, "loss": 0.6494, "step": 6571 }, { "epoch": 0.9364491308064976, "grad_norm": 1.261866990146627, "learning_rate": 1.2818844068484708e-05, "loss": 0.6059, "step": 6572 }, { "epoch": 0.9365916215445996, "grad_norm": 1.329519915050639, "learning_rate": 1.281645782240265e-05, "loss": 0.5977, "step": 6573 }, { "epoch": 0.9367341122827016, "grad_norm": 1.3143745202355226, "learning_rate": 1.2814071402116338e-05, "loss": 0.6563, "step": 6574 }, { "epoch": 0.9368766030208037, "grad_norm": 1.3862147905866158, "learning_rate": 1.2811684807773371e-05, "loss": 0.7122, "step": 6575 }, { "epoch": 0.9370190937589057, "grad_norm": 1.3735103139262723, "learning_rate": 1.2809298039521372e-05, "loss": 0.6001, "step": 6576 }, { "epoch": 0.9371615844970077, "grad_norm": 1.3740290645456306, "learning_rate": 1.2806911097507964e-05, "loss": 0.6232, "step": 6577 }, { "epoch": 0.9373040752351097, "grad_norm": 1.2372928436616901, "learning_rate": 1.280452398188079e-05, "loss": 0.6294, "step": 6578 }, { "epoch": 0.9374465659732117, "grad_norm": 1.2990166432680834, "learning_rate": 1.2802136692787493e-05, "loss": 0.6417, "step": 6579 }, { "epoch": 0.9375890567113138, "grad_norm": 1.2789809319523564, "learning_rate": 1.2799749230375732e-05, "loss": 0.6319, "step": 6580 }, { "epoch": 0.9377315474494158, "grad_norm": 1.2656414862639218, "learning_rate": 1.2797361594793184e-05, "loss": 0.6578, "step": 6581 }, { "epoch": 0.9378740381875178, "grad_norm": 1.2530796204629724, "learning_rate": 1.2794973786187521e-05, "loss": 0.6278, "step": 6582 }, { "epoch": 0.9380165289256198, "grad_norm": 1.5095118798677971, "learning_rate": 1.2792585804706437e-05, "loss": 0.628, "step": 6583 }, { "epoch": 0.9381590196637218, "grad_norm": 1.2748069962998068, "learning_rate": 1.2790197650497637e-05, "loss": 0.5915, "step": 6584 }, { "epoch": 0.9383015104018239, "grad_norm": 1.2274732830488855, "learning_rate": 1.2787809323708833e-05, "loss": 0.6043, "step": 6585 }, { "epoch": 0.9384440011399259, "grad_norm": 1.4397713470430782, "learning_rate": 1.2785420824487747e-05, "loss": 0.5889, "step": 6586 }, { "epoch": 0.9385864918780279, "grad_norm": 1.3217580062633534, "learning_rate": 1.2783032152982111e-05, "loss": 0.6551, "step": 6587 }, { "epoch": 0.9387289826161299, "grad_norm": 1.245944829465134, "learning_rate": 1.2780643309339673e-05, "loss": 0.5649, "step": 6588 }, { "epoch": 0.9388714733542319, "grad_norm": 1.3803891759864106, "learning_rate": 1.2778254293708188e-05, "loss": 0.6198, "step": 6589 }, { "epoch": 0.939013964092334, "grad_norm": 1.4701580333555364, "learning_rate": 1.277586510623542e-05, "loss": 0.6186, "step": 6590 }, { "epoch": 0.939156454830436, "grad_norm": 1.2908748180799603, "learning_rate": 1.2773475747069147e-05, "loss": 0.6388, "step": 6591 }, { "epoch": 0.939298945568538, "grad_norm": 1.6635892822133937, "learning_rate": 1.2771086216357155e-05, "loss": 0.6333, "step": 6592 }, { "epoch": 0.9394414363066401, "grad_norm": 1.2438502678964574, "learning_rate": 1.2768696514247246e-05, "loss": 0.5452, "step": 6593 }, { "epoch": 0.9395839270447421, "grad_norm": 1.3055654162254753, "learning_rate": 1.2766306640887223e-05, "loss": 0.6945, "step": 6594 }, { "epoch": 0.9397264177828442, "grad_norm": 1.4007404233475769, "learning_rate": 1.2763916596424908e-05, "loss": 0.6823, "step": 6595 }, { "epoch": 0.9398689085209462, "grad_norm": 1.2417217107138354, "learning_rate": 1.2761526381008131e-05, "loss": 0.5931, "step": 6596 }, { "epoch": 0.9400113992590482, "grad_norm": 1.3425246888788975, "learning_rate": 1.275913599478473e-05, "loss": 0.627, "step": 6597 }, { "epoch": 0.9401538899971502, "grad_norm": 1.4969807206332315, "learning_rate": 1.2756745437902558e-05, "loss": 0.6232, "step": 6598 }, { "epoch": 0.9402963807352522, "grad_norm": 1.3770839669733255, "learning_rate": 1.2754354710509476e-05, "loss": 0.6957, "step": 6599 }, { "epoch": 0.9404388714733543, "grad_norm": 1.4889882598567894, "learning_rate": 1.2751963812753356e-05, "loss": 0.6834, "step": 6600 }, { "epoch": 0.9405813622114563, "grad_norm": 1.302232599137725, "learning_rate": 1.2749572744782077e-05, "loss": 0.5964, "step": 6601 }, { "epoch": 0.9407238529495583, "grad_norm": 1.428684593498268, "learning_rate": 1.2747181506743536e-05, "loss": 0.6279, "step": 6602 }, { "epoch": 0.9408663436876603, "grad_norm": 1.4679320542319751, "learning_rate": 1.2744790098785636e-05, "loss": 0.6872, "step": 6603 }, { "epoch": 0.9410088344257623, "grad_norm": 1.3408584105213446, "learning_rate": 1.274239852105629e-05, "loss": 0.6668, "step": 6604 }, { "epoch": 0.9411513251638643, "grad_norm": 1.6593206054751288, "learning_rate": 1.274000677370342e-05, "loss": 0.6608, "step": 6605 }, { "epoch": 0.9412938159019664, "grad_norm": 1.1649741879958588, "learning_rate": 1.2737614856874965e-05, "loss": 0.6118, "step": 6606 }, { "epoch": 0.9414363066400684, "grad_norm": 1.2723011379409537, "learning_rate": 1.2735222770718867e-05, "loss": 0.5851, "step": 6607 }, { "epoch": 0.9415787973781704, "grad_norm": 1.326745495192512, "learning_rate": 1.2732830515383089e-05, "loss": 0.5394, "step": 6608 }, { "epoch": 0.9417212881162724, "grad_norm": 1.5299733984559711, "learning_rate": 1.2730438091015587e-05, "loss": 0.5981, "step": 6609 }, { "epoch": 0.9418637788543744, "grad_norm": 1.257561107152878, "learning_rate": 1.2728045497764345e-05, "loss": 0.6586, "step": 6610 }, { "epoch": 0.9420062695924765, "grad_norm": 1.3683721316558723, "learning_rate": 1.272565273577735e-05, "loss": 0.6342, "step": 6611 }, { "epoch": 0.9421487603305785, "grad_norm": 1.3260110295815533, "learning_rate": 1.2723259805202595e-05, "loss": 0.6066, "step": 6612 }, { "epoch": 0.9422912510686805, "grad_norm": 1.4039374696735025, "learning_rate": 1.2720866706188091e-05, "loss": 0.6864, "step": 6613 }, { "epoch": 0.9424337418067825, "grad_norm": 1.390789028683077, "learning_rate": 1.2718473438881858e-05, "loss": 0.6677, "step": 6614 }, { "epoch": 0.9425762325448845, "grad_norm": 1.495008366969394, "learning_rate": 1.2716080003431927e-05, "loss": 0.6702, "step": 6615 }, { "epoch": 0.9427187232829866, "grad_norm": 1.3869775891507798, "learning_rate": 1.2713686399986332e-05, "loss": 0.6489, "step": 6616 }, { "epoch": 0.9428612140210886, "grad_norm": 1.3493092568757021, "learning_rate": 1.2711292628693122e-05, "loss": 0.6929, "step": 6617 }, { "epoch": 0.9430037047591906, "grad_norm": 1.3397397242560345, "learning_rate": 1.2708898689700363e-05, "loss": 0.6097, "step": 6618 }, { "epoch": 0.9431461954972927, "grad_norm": 1.236640944812848, "learning_rate": 1.2706504583156118e-05, "loss": 0.5805, "step": 6619 }, { "epoch": 0.9432886862353947, "grad_norm": 1.6057531609430433, "learning_rate": 1.2704110309208478e-05, "loss": 0.7363, "step": 6620 }, { "epoch": 0.9434311769734968, "grad_norm": 1.6070216089223914, "learning_rate": 1.2701715868005524e-05, "loss": 0.6052, "step": 6621 }, { "epoch": 0.9435736677115988, "grad_norm": 1.4414428826030332, "learning_rate": 1.2699321259695368e-05, "loss": 0.5939, "step": 6622 }, { "epoch": 0.9437161584497008, "grad_norm": 1.381186647436776, "learning_rate": 1.2696926484426111e-05, "loss": 0.6036, "step": 6623 }, { "epoch": 0.9438586491878028, "grad_norm": 1.331311784306557, "learning_rate": 1.2694531542345882e-05, "loss": 0.6883, "step": 6624 }, { "epoch": 0.9440011399259048, "grad_norm": 1.3812219217884263, "learning_rate": 1.269213643360281e-05, "loss": 0.6998, "step": 6625 }, { "epoch": 0.9441436306640069, "grad_norm": 1.1966263660085779, "learning_rate": 1.2689741158345044e-05, "loss": 0.5692, "step": 6626 }, { "epoch": 0.9442861214021089, "grad_norm": 1.2824147268018344, "learning_rate": 1.268734571672073e-05, "loss": 0.585, "step": 6627 }, { "epoch": 0.9444286121402109, "grad_norm": 1.4217199197625627, "learning_rate": 1.2684950108878033e-05, "loss": 0.6309, "step": 6628 }, { "epoch": 0.9445711028783129, "grad_norm": 1.4360242594570949, "learning_rate": 1.2682554334965129e-05, "loss": 0.6466, "step": 6629 }, { "epoch": 0.9447135936164149, "grad_norm": 1.3730282572845374, "learning_rate": 1.2680158395130203e-05, "loss": 0.6542, "step": 6630 }, { "epoch": 0.944856084354517, "grad_norm": 1.4902210707908101, "learning_rate": 1.2677762289521449e-05, "loss": 0.7126, "step": 6631 }, { "epoch": 0.944998575092619, "grad_norm": 1.3190139417688866, "learning_rate": 1.2675366018287065e-05, "loss": 0.626, "step": 6632 }, { "epoch": 0.945141065830721, "grad_norm": 1.2735915720065474, "learning_rate": 1.2672969581575274e-05, "loss": 0.5894, "step": 6633 }, { "epoch": 0.945283556568823, "grad_norm": 1.2863304515415097, "learning_rate": 1.2670572979534296e-05, "loss": 0.5936, "step": 6634 }, { "epoch": 0.945426047306925, "grad_norm": 1.3312402083264123, "learning_rate": 1.2668176212312369e-05, "loss": 0.5937, "step": 6635 }, { "epoch": 0.945568538045027, "grad_norm": 1.722248958682958, "learning_rate": 1.2665779280057736e-05, "loss": 0.6945, "step": 6636 }, { "epoch": 0.9457110287831291, "grad_norm": 1.4465008178387864, "learning_rate": 1.2663382182918658e-05, "loss": 0.7138, "step": 6637 }, { "epoch": 0.9458535195212311, "grad_norm": 1.336081025692225, "learning_rate": 1.2660984921043394e-05, "loss": 0.6695, "step": 6638 }, { "epoch": 0.9459960102593331, "grad_norm": 1.3709999235937453, "learning_rate": 1.2658587494580221e-05, "loss": 0.6418, "step": 6639 }, { "epoch": 0.9461385009974351, "grad_norm": 1.3023368636212478, "learning_rate": 1.265618990367743e-05, "loss": 0.621, "step": 6640 }, { "epoch": 0.9462809917355371, "grad_norm": 1.2536921703557569, "learning_rate": 1.2653792148483313e-05, "loss": 0.5856, "step": 6641 }, { "epoch": 0.9464234824736392, "grad_norm": 1.3260971120531921, "learning_rate": 1.2651394229146179e-05, "loss": 0.6559, "step": 6642 }, { "epoch": 0.9465659732117412, "grad_norm": 1.3022428765091754, "learning_rate": 1.2648996145814343e-05, "loss": 0.5802, "step": 6643 }, { "epoch": 0.9467084639498433, "grad_norm": 1.2932466201944086, "learning_rate": 1.2646597898636133e-05, "loss": 0.6792, "step": 6644 }, { "epoch": 0.9468509546879453, "grad_norm": 1.284523685864914, "learning_rate": 1.2644199487759888e-05, "loss": 0.6272, "step": 6645 }, { "epoch": 0.9469934454260474, "grad_norm": 1.2804325653468094, "learning_rate": 1.264180091333395e-05, "loss": 0.585, "step": 6646 }, { "epoch": 0.9471359361641494, "grad_norm": 1.1986841563445136, "learning_rate": 1.2639402175506679e-05, "loss": 0.4549, "step": 6647 }, { "epoch": 0.9472784269022514, "grad_norm": 1.2592347258289516, "learning_rate": 1.2637003274426443e-05, "loss": 0.538, "step": 6648 }, { "epoch": 0.9474209176403534, "grad_norm": 1.430695697023353, "learning_rate": 1.263460421024162e-05, "loss": 0.6184, "step": 6649 }, { "epoch": 0.9475634083784554, "grad_norm": 1.2762121261801078, "learning_rate": 1.2632204983100593e-05, "loss": 0.5673, "step": 6650 }, { "epoch": 0.9477058991165574, "grad_norm": 1.325678493539851, "learning_rate": 1.2629805593151765e-05, "loss": 0.5978, "step": 6651 }, { "epoch": 0.9478483898546595, "grad_norm": 1.305696049712385, "learning_rate": 1.2627406040543542e-05, "loss": 0.6494, "step": 6652 }, { "epoch": 0.9479908805927615, "grad_norm": 1.2868379275635644, "learning_rate": 1.2625006325424341e-05, "loss": 0.5643, "step": 6653 }, { "epoch": 0.9481333713308635, "grad_norm": 1.3121687608701575, "learning_rate": 1.262260644794259e-05, "loss": 0.6311, "step": 6654 }, { "epoch": 0.9482758620689655, "grad_norm": 1.138126736058737, "learning_rate": 1.2620206408246727e-05, "loss": 0.5059, "step": 6655 }, { "epoch": 0.9484183528070675, "grad_norm": 1.8648533500348037, "learning_rate": 1.2617806206485197e-05, "loss": 0.6218, "step": 6656 }, { "epoch": 0.9485608435451696, "grad_norm": 1.2790438078660686, "learning_rate": 1.2615405842806463e-05, "loss": 0.5805, "step": 6657 }, { "epoch": 0.9487033342832716, "grad_norm": 1.2029348291663984, "learning_rate": 1.2613005317358991e-05, "loss": 0.5955, "step": 6658 }, { "epoch": 0.9488458250213736, "grad_norm": 1.3961227178360396, "learning_rate": 1.2610604630291258e-05, "loss": 0.5854, "step": 6659 }, { "epoch": 0.9489883157594756, "grad_norm": 1.4280433120545415, "learning_rate": 1.2608203781751753e-05, "loss": 0.6155, "step": 6660 }, { "epoch": 0.9491308064975776, "grad_norm": 1.4042506748256929, "learning_rate": 1.2605802771888973e-05, "loss": 0.6621, "step": 6661 }, { "epoch": 0.9492732972356797, "grad_norm": 1.4449280654852334, "learning_rate": 1.2603401600851423e-05, "loss": 0.6438, "step": 6662 }, { "epoch": 0.9494157879737817, "grad_norm": 1.3198569074446842, "learning_rate": 1.2601000268787629e-05, "loss": 0.5804, "step": 6663 }, { "epoch": 0.9495582787118837, "grad_norm": 1.4483209300901605, "learning_rate": 1.2598598775846109e-05, "loss": 0.691, "step": 6664 }, { "epoch": 0.9497007694499857, "grad_norm": 1.3128141509904196, "learning_rate": 1.2596197122175409e-05, "loss": 0.574, "step": 6665 }, { "epoch": 0.9498432601880877, "grad_norm": 1.4646505697399146, "learning_rate": 1.259379530792407e-05, "loss": 0.6807, "step": 6666 }, { "epoch": 0.9499857509261898, "grad_norm": 1.334207094652663, "learning_rate": 1.2591393333240656e-05, "loss": 0.6353, "step": 6667 }, { "epoch": 0.9501282416642918, "grad_norm": 1.613852007711798, "learning_rate": 1.258899119827373e-05, "loss": 0.6437, "step": 6668 }, { "epoch": 0.9502707324023938, "grad_norm": 1.3142158189478075, "learning_rate": 1.258658890317187e-05, "loss": 0.5902, "step": 6669 }, { "epoch": 0.9504132231404959, "grad_norm": 1.3109068222650058, "learning_rate": 1.2584186448083664e-05, "loss": 0.6525, "step": 6670 }, { "epoch": 0.9505557138785979, "grad_norm": 1.5136639774327343, "learning_rate": 1.258178383315771e-05, "loss": 0.6531, "step": 6671 }, { "epoch": 0.9506982046167, "grad_norm": 1.2800090679505582, "learning_rate": 1.2579381058542614e-05, "loss": 0.7233, "step": 6672 }, { "epoch": 0.950840695354802, "grad_norm": 1.6990305461123678, "learning_rate": 1.2576978124386993e-05, "loss": 0.6053, "step": 6673 }, { "epoch": 0.950983186092904, "grad_norm": 1.1666098593843006, "learning_rate": 1.2574575030839478e-05, "loss": 0.6227, "step": 6674 }, { "epoch": 0.951125676831006, "grad_norm": 1.3264590587530916, "learning_rate": 1.2572171778048699e-05, "loss": 0.6627, "step": 6675 }, { "epoch": 0.951268167569108, "grad_norm": 1.2135325953058638, "learning_rate": 1.2569768366163306e-05, "loss": 0.6313, "step": 6676 }, { "epoch": 0.95141065830721, "grad_norm": 1.2381859084723879, "learning_rate": 1.2567364795331953e-05, "loss": 0.6096, "step": 6677 }, { "epoch": 0.9515531490453121, "grad_norm": 1.50344410691758, "learning_rate": 1.2564961065703311e-05, "loss": 0.7084, "step": 6678 }, { "epoch": 0.9516956397834141, "grad_norm": 1.2931001671077902, "learning_rate": 1.2562557177426053e-05, "loss": 0.6144, "step": 6679 }, { "epoch": 0.9518381305215161, "grad_norm": 1.2969385090097818, "learning_rate": 1.2560153130648866e-05, "loss": 0.6063, "step": 6680 }, { "epoch": 0.9519806212596181, "grad_norm": 1.3793371403573107, "learning_rate": 1.2557748925520446e-05, "loss": 0.6198, "step": 6681 }, { "epoch": 0.9521231119977202, "grad_norm": 1.4138756735759908, "learning_rate": 1.2555344562189498e-05, "loss": 0.6807, "step": 6682 }, { "epoch": 0.9522656027358222, "grad_norm": 1.394095704049453, "learning_rate": 1.2552940040804736e-05, "loss": 0.7041, "step": 6683 }, { "epoch": 0.9524080934739242, "grad_norm": 1.508609285819058, "learning_rate": 1.2550535361514884e-05, "loss": 0.6106, "step": 6684 }, { "epoch": 0.9525505842120262, "grad_norm": 1.2641068327667304, "learning_rate": 1.254813052446868e-05, "loss": 0.5581, "step": 6685 }, { "epoch": 0.9526930749501282, "grad_norm": 1.3335348061926784, "learning_rate": 1.2545725529814867e-05, "loss": 0.6324, "step": 6686 }, { "epoch": 0.9528355656882302, "grad_norm": 1.3200289230347524, "learning_rate": 1.25433203777022e-05, "loss": 0.5902, "step": 6687 }, { "epoch": 0.9529780564263323, "grad_norm": 1.34567575940782, "learning_rate": 1.2540915068279443e-05, "loss": 0.5971, "step": 6688 }, { "epoch": 0.9531205471644343, "grad_norm": 1.4381612455616521, "learning_rate": 1.2538509601695372e-05, "loss": 0.5787, "step": 6689 }, { "epoch": 0.9532630379025363, "grad_norm": 1.2378214486550705, "learning_rate": 1.2536103978098763e-05, "loss": 0.5821, "step": 6690 }, { "epoch": 0.9534055286406383, "grad_norm": 1.3082808798092211, "learning_rate": 1.2533698197638419e-05, "loss": 0.6625, "step": 6691 }, { "epoch": 0.9535480193787403, "grad_norm": 1.5814448671363828, "learning_rate": 1.2531292260463132e-05, "loss": 0.6554, "step": 6692 }, { "epoch": 0.9536905101168424, "grad_norm": 1.5671721203785869, "learning_rate": 1.252888616672173e-05, "loss": 0.6108, "step": 6693 }, { "epoch": 0.9538330008549444, "grad_norm": 1.3751043960735678, "learning_rate": 1.2526479916563021e-05, "loss": 0.5714, "step": 6694 }, { "epoch": 0.9539754915930464, "grad_norm": 1.3828952216716137, "learning_rate": 1.2524073510135842e-05, "loss": 0.6805, "step": 6695 }, { "epoch": 0.9541179823311485, "grad_norm": 1.4847644551638437, "learning_rate": 1.2521666947589036e-05, "loss": 0.6617, "step": 6696 }, { "epoch": 0.9542604730692505, "grad_norm": 1.7134133179498565, "learning_rate": 1.2519260229071452e-05, "loss": 0.6625, "step": 6697 }, { "epoch": 0.9544029638073526, "grad_norm": 1.3337435348384539, "learning_rate": 1.2516853354731955e-05, "loss": 0.5728, "step": 6698 }, { "epoch": 0.9545454545454546, "grad_norm": 1.6161863687316542, "learning_rate": 1.2514446324719407e-05, "loss": 0.6638, "step": 6699 }, { "epoch": 0.9546879452835566, "grad_norm": 1.3835037770611458, "learning_rate": 1.2512039139182699e-05, "loss": 0.6317, "step": 6700 }, { "epoch": 0.9548304360216586, "grad_norm": 1.4254805018211054, "learning_rate": 1.2509631798270717e-05, "loss": 0.6193, "step": 6701 }, { "epoch": 0.9549729267597606, "grad_norm": 1.2662124066406364, "learning_rate": 1.2507224302132355e-05, "loss": 0.6312, "step": 6702 }, { "epoch": 0.9551154174978627, "grad_norm": 1.373939906293955, "learning_rate": 1.2504816650916527e-05, "loss": 0.6292, "step": 6703 }, { "epoch": 0.9552579082359647, "grad_norm": 1.3348005681362551, "learning_rate": 1.2502408844772153e-05, "loss": 0.6987, "step": 6704 }, { "epoch": 0.9554003989740667, "grad_norm": 1.3399712628303542, "learning_rate": 1.2500000883848161e-05, "loss": 0.6859, "step": 6705 }, { "epoch": 0.9555428897121687, "grad_norm": 1.3116677927832976, "learning_rate": 1.2497592768293481e-05, "loss": 0.6303, "step": 6706 }, { "epoch": 0.9556853804502707, "grad_norm": 3.1875050456100076, "learning_rate": 1.2495184498257072e-05, "loss": 0.7164, "step": 6707 }, { "epoch": 0.9558278711883728, "grad_norm": 1.2627883440695518, "learning_rate": 1.249277607388788e-05, "loss": 0.5262, "step": 6708 }, { "epoch": 0.9559703619264748, "grad_norm": 1.3287961824903294, "learning_rate": 1.249036749533488e-05, "loss": 0.6726, "step": 6709 }, { "epoch": 0.9561128526645768, "grad_norm": 2.014260377818257, "learning_rate": 1.2487958762747045e-05, "loss": 0.6701, "step": 6710 }, { "epoch": 0.9562553434026788, "grad_norm": 1.2561551333917278, "learning_rate": 1.248554987627336e-05, "loss": 0.6185, "step": 6711 }, { "epoch": 0.9563978341407808, "grad_norm": 1.2891935149948754, "learning_rate": 1.2483140836062822e-05, "loss": 0.6451, "step": 6712 }, { "epoch": 0.9565403248788829, "grad_norm": 1.3961280263599054, "learning_rate": 1.248073164226443e-05, "loss": 0.5297, "step": 6713 }, { "epoch": 0.9566828156169849, "grad_norm": 1.4464139643285725, "learning_rate": 1.2478322295027204e-05, "loss": 0.6356, "step": 6714 }, { "epoch": 0.9568253063550869, "grad_norm": 1.2914146126309203, "learning_rate": 1.2475912794500165e-05, "loss": 0.6561, "step": 6715 }, { "epoch": 0.9569677970931889, "grad_norm": 1.4566219760284989, "learning_rate": 1.2473503140832346e-05, "loss": 0.6001, "step": 6716 }, { "epoch": 0.9571102878312909, "grad_norm": 1.3634340846411919, "learning_rate": 1.2471093334172793e-05, "loss": 0.5564, "step": 6717 }, { "epoch": 0.957252778569393, "grad_norm": 1.3876946260641216, "learning_rate": 1.2468683374670552e-05, "loss": 0.6335, "step": 6718 }, { "epoch": 0.957395269307495, "grad_norm": 1.1732243276701018, "learning_rate": 1.246627326247469e-05, "loss": 0.5877, "step": 6719 }, { "epoch": 0.957537760045597, "grad_norm": 1.2979959389157572, "learning_rate": 1.2463862997734273e-05, "loss": 0.6392, "step": 6720 }, { "epoch": 0.957680250783699, "grad_norm": 1.3394460409915359, "learning_rate": 1.2461452580598381e-05, "loss": 0.6278, "step": 6721 }, { "epoch": 0.9578227415218011, "grad_norm": 1.2780444261561554, "learning_rate": 1.245904201121611e-05, "loss": 0.5581, "step": 6722 }, { "epoch": 0.9579652322599032, "grad_norm": 1.2293056022526356, "learning_rate": 1.2456631289736558e-05, "loss": 0.6001, "step": 6723 }, { "epoch": 0.9581077229980052, "grad_norm": 1.4062896022184401, "learning_rate": 1.2454220416308826e-05, "loss": 0.6504, "step": 6724 }, { "epoch": 0.9582502137361072, "grad_norm": 1.4572117011857375, "learning_rate": 1.245180939108204e-05, "loss": 0.6252, "step": 6725 }, { "epoch": 0.9583927044742092, "grad_norm": 1.2451020682980827, "learning_rate": 1.2449398214205326e-05, "loss": 0.7084, "step": 6726 }, { "epoch": 0.9585351952123112, "grad_norm": 1.3551835971136061, "learning_rate": 1.2446986885827815e-05, "loss": 0.6468, "step": 6727 }, { "epoch": 0.9586776859504132, "grad_norm": 1.3936722266615469, "learning_rate": 1.2444575406098655e-05, "loss": 0.5721, "step": 6728 }, { "epoch": 0.9588201766885153, "grad_norm": 1.4330549468579625, "learning_rate": 1.2442163775167009e-05, "loss": 0.6344, "step": 6729 }, { "epoch": 0.9589626674266173, "grad_norm": 1.225646118357828, "learning_rate": 1.2439751993182035e-05, "loss": 0.5914, "step": 6730 }, { "epoch": 0.9591051581647193, "grad_norm": 1.3871279129963192, "learning_rate": 1.2437340060292908e-05, "loss": 0.7444, "step": 6731 }, { "epoch": 0.9592476489028213, "grad_norm": 1.2616830699949553, "learning_rate": 1.2434927976648811e-05, "loss": 0.6521, "step": 6732 }, { "epoch": 0.9593901396409233, "grad_norm": 1.4896518063792534, "learning_rate": 1.2432515742398938e-05, "loss": 0.6708, "step": 6733 }, { "epoch": 0.9595326303790254, "grad_norm": 1.5812536584339056, "learning_rate": 1.2430103357692493e-05, "loss": 0.6594, "step": 6734 }, { "epoch": 0.9596751211171274, "grad_norm": 1.3138858257261996, "learning_rate": 1.2427690822678684e-05, "loss": 0.6807, "step": 6735 }, { "epoch": 0.9598176118552294, "grad_norm": 1.3126291014332494, "learning_rate": 1.2425278137506732e-05, "loss": 0.5698, "step": 6736 }, { "epoch": 0.9599601025933314, "grad_norm": 1.2248073839358968, "learning_rate": 1.2422865302325871e-05, "loss": 0.6531, "step": 6737 }, { "epoch": 0.9601025933314334, "grad_norm": 1.305859790703053, "learning_rate": 1.2420452317285335e-05, "loss": 0.6338, "step": 6738 }, { "epoch": 0.9602450840695355, "grad_norm": 1.1795993955102257, "learning_rate": 1.2418039182534374e-05, "loss": 0.5938, "step": 6739 }, { "epoch": 0.9603875748076375, "grad_norm": 1.3768465167556296, "learning_rate": 1.2415625898222247e-05, "loss": 0.6676, "step": 6740 }, { "epoch": 0.9605300655457395, "grad_norm": 1.176271736457381, "learning_rate": 1.2413212464498226e-05, "loss": 0.5849, "step": 6741 }, { "epoch": 0.9606725562838415, "grad_norm": 1.4036717923172572, "learning_rate": 1.2410798881511577e-05, "loss": 0.6869, "step": 6742 }, { "epoch": 0.9608150470219435, "grad_norm": 1.3502009919522122, "learning_rate": 1.2408385149411588e-05, "loss": 0.6508, "step": 6743 }, { "epoch": 0.9609575377600456, "grad_norm": 1.3014498093345954, "learning_rate": 1.2405971268347558e-05, "loss": 0.6425, "step": 6744 }, { "epoch": 0.9611000284981476, "grad_norm": 1.248144636712542, "learning_rate": 1.2403557238468796e-05, "loss": 0.5545, "step": 6745 }, { "epoch": 0.9612425192362496, "grad_norm": 1.310790848321694, "learning_rate": 1.2401143059924601e-05, "loss": 0.5965, "step": 6746 }, { "epoch": 0.9613850099743516, "grad_norm": 1.2966506915640645, "learning_rate": 1.2398728732864307e-05, "loss": 0.6724, "step": 6747 }, { "epoch": 0.9615275007124537, "grad_norm": 1.443006045334174, "learning_rate": 1.2396314257437238e-05, "loss": 0.648, "step": 6748 }, { "epoch": 0.9616699914505558, "grad_norm": 1.3805733442880164, "learning_rate": 1.2393899633792742e-05, "loss": 0.6124, "step": 6749 }, { "epoch": 0.9618124821886578, "grad_norm": 1.265919073719681, "learning_rate": 1.2391484862080163e-05, "loss": 0.5968, "step": 6750 }, { "epoch": 0.9619549729267598, "grad_norm": 1.2524870659089975, "learning_rate": 1.238906994244886e-05, "loss": 0.6206, "step": 6751 }, { "epoch": 0.9620974636648618, "grad_norm": 1.2550074670032114, "learning_rate": 1.238665487504821e-05, "loss": 0.6132, "step": 6752 }, { "epoch": 0.9622399544029638, "grad_norm": 1.2323145749338054, "learning_rate": 1.2384239660027579e-05, "loss": 0.6194, "step": 6753 }, { "epoch": 0.9623824451410659, "grad_norm": 1.2958979308961076, "learning_rate": 1.238182429753636e-05, "loss": 0.6516, "step": 6754 }, { "epoch": 0.9625249358791679, "grad_norm": 1.3465927971582121, "learning_rate": 1.2379408787723945e-05, "loss": 0.6567, "step": 6755 }, { "epoch": 0.9626674266172699, "grad_norm": 1.2898130728911097, "learning_rate": 1.2376993130739743e-05, "loss": 0.6065, "step": 6756 }, { "epoch": 0.9628099173553719, "grad_norm": 1.3279424424094453, "learning_rate": 1.2374577326733161e-05, "loss": 0.6394, "step": 6757 }, { "epoch": 0.9629524080934739, "grad_norm": 1.2828028059416863, "learning_rate": 1.2372161375853631e-05, "loss": 0.663, "step": 6758 }, { "epoch": 0.963094898831576, "grad_norm": 1.3570819156443952, "learning_rate": 1.236974527825058e-05, "loss": 0.5984, "step": 6759 }, { "epoch": 0.963237389569678, "grad_norm": 1.3967288451556874, "learning_rate": 1.2367329034073447e-05, "loss": 0.5564, "step": 6760 }, { "epoch": 0.96337988030778, "grad_norm": 1.2350213756553832, "learning_rate": 1.2364912643471687e-05, "loss": 0.5316, "step": 6761 }, { "epoch": 0.963522371045882, "grad_norm": 1.427096620204314, "learning_rate": 1.2362496106594754e-05, "loss": 0.6876, "step": 6762 }, { "epoch": 0.963664861783984, "grad_norm": 1.2827146721224287, "learning_rate": 1.236007942359212e-05, "loss": 0.6416, "step": 6763 }, { "epoch": 0.963807352522086, "grad_norm": 1.3137227324080847, "learning_rate": 1.2357662594613264e-05, "loss": 0.6913, "step": 6764 }, { "epoch": 0.9639498432601881, "grad_norm": 1.2279880008602064, "learning_rate": 1.2355245619807663e-05, "loss": 0.5828, "step": 6765 }, { "epoch": 0.9640923339982901, "grad_norm": 1.2362810316469002, "learning_rate": 1.2352828499324824e-05, "loss": 0.62, "step": 6766 }, { "epoch": 0.9642348247363921, "grad_norm": 1.235093865999778, "learning_rate": 1.2350411233314247e-05, "loss": 0.5478, "step": 6767 }, { "epoch": 0.9643773154744941, "grad_norm": 1.3138298552795935, "learning_rate": 1.2347993821925444e-05, "loss": 0.6943, "step": 6768 }, { "epoch": 0.9645198062125961, "grad_norm": 1.2419377211332316, "learning_rate": 1.2345576265307934e-05, "loss": 0.6192, "step": 6769 }, { "epoch": 0.9646622969506982, "grad_norm": 1.2498333336256873, "learning_rate": 1.2343158563611257e-05, "loss": 0.7387, "step": 6770 }, { "epoch": 0.9648047876888002, "grad_norm": 1.4329669691442046, "learning_rate": 1.234074071698495e-05, "loss": 0.6881, "step": 6771 }, { "epoch": 0.9649472784269022, "grad_norm": 1.2958410443306978, "learning_rate": 1.2338322725578553e-05, "loss": 0.6964, "step": 6772 }, { "epoch": 0.9650897691650043, "grad_norm": 1.2346361121389193, "learning_rate": 1.2335904589541636e-05, "loss": 0.5935, "step": 6773 }, { "epoch": 0.9652322599031063, "grad_norm": 1.3395304508564396, "learning_rate": 1.2333486309023765e-05, "loss": 0.6297, "step": 6774 }, { "epoch": 0.9653747506412084, "grad_norm": 1.2132430654083002, "learning_rate": 1.233106788417451e-05, "loss": 0.6015, "step": 6775 }, { "epoch": 0.9655172413793104, "grad_norm": 1.2544046377946956, "learning_rate": 1.232864931514346e-05, "loss": 0.6358, "step": 6776 }, { "epoch": 0.9656597321174124, "grad_norm": 1.1841973824250853, "learning_rate": 1.2326230602080209e-05, "loss": 0.6145, "step": 6777 }, { "epoch": 0.9658022228555144, "grad_norm": 1.2861111185566751, "learning_rate": 1.2323811745134359e-05, "loss": 0.604, "step": 6778 }, { "epoch": 0.9659447135936164, "grad_norm": 1.4238074928585487, "learning_rate": 1.2321392744455521e-05, "loss": 0.6457, "step": 6779 }, { "epoch": 0.9660872043317185, "grad_norm": 1.347542745832444, "learning_rate": 1.2318973600193316e-05, "loss": 0.6225, "step": 6780 }, { "epoch": 0.9662296950698205, "grad_norm": 1.378780455808637, "learning_rate": 1.2316554312497374e-05, "loss": 0.6557, "step": 6781 }, { "epoch": 0.9663721858079225, "grad_norm": 1.2484331171725007, "learning_rate": 1.2314134881517337e-05, "loss": 0.5931, "step": 6782 }, { "epoch": 0.9665146765460245, "grad_norm": 1.351173692185341, "learning_rate": 1.2311715307402845e-05, "loss": 0.6182, "step": 6783 }, { "epoch": 0.9666571672841265, "grad_norm": 1.4212683982767282, "learning_rate": 1.2309295590303558e-05, "loss": 0.7043, "step": 6784 }, { "epoch": 0.9667996580222286, "grad_norm": 1.4302466176303505, "learning_rate": 1.2306875730369142e-05, "loss": 0.6711, "step": 6785 }, { "epoch": 0.9669421487603306, "grad_norm": 1.4191800755446573, "learning_rate": 1.2304455727749267e-05, "loss": 0.6643, "step": 6786 }, { "epoch": 0.9670846394984326, "grad_norm": 1.2578483017073099, "learning_rate": 1.2302035582593619e-05, "loss": 0.5817, "step": 6787 }, { "epoch": 0.9672271302365346, "grad_norm": 1.4879126867743737, "learning_rate": 1.2299615295051888e-05, "loss": 0.6284, "step": 6788 }, { "epoch": 0.9673696209746366, "grad_norm": 1.187443819253746, "learning_rate": 1.2297194865273778e-05, "loss": 0.6046, "step": 6789 }, { "epoch": 0.9675121117127387, "grad_norm": 2.042975577181799, "learning_rate": 1.2294774293408993e-05, "loss": 0.6387, "step": 6790 }, { "epoch": 0.9676546024508407, "grad_norm": 1.2469282175315708, "learning_rate": 1.2292353579607252e-05, "loss": 0.5168, "step": 6791 }, { "epoch": 0.9677970931889427, "grad_norm": 1.2656941126209411, "learning_rate": 1.2289932724018281e-05, "loss": 0.5928, "step": 6792 }, { "epoch": 0.9679395839270447, "grad_norm": 1.217587447100632, "learning_rate": 1.2287511726791822e-05, "loss": 0.5635, "step": 6793 }, { "epoch": 0.9680820746651467, "grad_norm": 1.4056537975219279, "learning_rate": 1.2285090588077604e-05, "loss": 0.6666, "step": 6794 }, { "epoch": 0.9682245654032487, "grad_norm": 1.2345488276832959, "learning_rate": 1.2282669308025397e-05, "loss": 0.6625, "step": 6795 }, { "epoch": 0.9683670561413508, "grad_norm": 1.4612665752209653, "learning_rate": 1.228024788678495e-05, "loss": 0.7101, "step": 6796 }, { "epoch": 0.9685095468794528, "grad_norm": 1.2481109551258471, "learning_rate": 1.2277826324506046e-05, "loss": 0.609, "step": 6797 }, { "epoch": 0.9686520376175548, "grad_norm": 1.448111159883984, "learning_rate": 1.2275404621338452e-05, "loss": 0.6687, "step": 6798 }, { "epoch": 0.9687945283556569, "grad_norm": 1.479420018124106, "learning_rate": 1.2272982777431959e-05, "loss": 0.6106, "step": 6799 }, { "epoch": 0.968937019093759, "grad_norm": 1.3354033750576562, "learning_rate": 1.2270560792936368e-05, "loss": 0.7563, "step": 6800 }, { "epoch": 0.969079509831861, "grad_norm": 1.3877239758992637, "learning_rate": 1.226813866800148e-05, "loss": 0.668, "step": 6801 }, { "epoch": 0.969222000569963, "grad_norm": 1.279080348891556, "learning_rate": 1.2265716402777108e-05, "loss": 0.6381, "step": 6802 }, { "epoch": 0.969364491308065, "grad_norm": 1.1633035020123472, "learning_rate": 1.2263293997413077e-05, "loss": 0.5922, "step": 6803 }, { "epoch": 0.969506982046167, "grad_norm": 1.2364625489431302, "learning_rate": 1.2260871452059223e-05, "loss": 0.6514, "step": 6804 }, { "epoch": 0.969649472784269, "grad_norm": 1.3546311844525212, "learning_rate": 1.2258448766865374e-05, "loss": 0.5995, "step": 6805 }, { "epoch": 0.9697919635223711, "grad_norm": 1.577982754578202, "learning_rate": 1.2256025941981386e-05, "loss": 0.5647, "step": 6806 }, { "epoch": 0.9699344542604731, "grad_norm": 1.3324304182456197, "learning_rate": 1.2253602977557117e-05, "loss": 0.6118, "step": 6807 }, { "epoch": 0.9700769449985751, "grad_norm": 1.2920028101357408, "learning_rate": 1.2251179873742432e-05, "loss": 0.6858, "step": 6808 }, { "epoch": 0.9702194357366771, "grad_norm": 1.357414072828395, "learning_rate": 1.2248756630687204e-05, "loss": 0.6308, "step": 6809 }, { "epoch": 0.9703619264747791, "grad_norm": 1.450628884591674, "learning_rate": 1.2246333248541315e-05, "loss": 0.6554, "step": 6810 }, { "epoch": 0.9705044172128812, "grad_norm": 1.2312351042416267, "learning_rate": 1.2243909727454661e-05, "loss": 0.6384, "step": 6811 }, { "epoch": 0.9706469079509832, "grad_norm": 1.2790308022439476, "learning_rate": 1.2241486067577137e-05, "loss": 0.6569, "step": 6812 }, { "epoch": 0.9707893986890852, "grad_norm": 1.2567278292715331, "learning_rate": 1.2239062269058654e-05, "loss": 0.6866, "step": 6813 }, { "epoch": 0.9709318894271872, "grad_norm": 1.1928950490094343, "learning_rate": 1.2236638332049133e-05, "loss": 0.5799, "step": 6814 }, { "epoch": 0.9710743801652892, "grad_norm": 1.2733372060850026, "learning_rate": 1.2234214256698494e-05, "loss": 0.5581, "step": 6815 }, { "epoch": 0.9712168709033913, "grad_norm": 1.3858074542783876, "learning_rate": 1.2231790043156672e-05, "loss": 0.7161, "step": 6816 }, { "epoch": 0.9713593616414933, "grad_norm": 1.2606957046575864, "learning_rate": 1.2229365691573615e-05, "loss": 0.6078, "step": 6817 }, { "epoch": 0.9715018523795953, "grad_norm": 1.3982745452668492, "learning_rate": 1.2226941202099271e-05, "loss": 0.7028, "step": 6818 }, { "epoch": 0.9716443431176973, "grad_norm": 1.8993381699882017, "learning_rate": 1.2224516574883604e-05, "loss": 0.6666, "step": 6819 }, { "epoch": 0.9717868338557993, "grad_norm": 1.5091514691190773, "learning_rate": 1.2222091810076578e-05, "loss": 0.7115, "step": 6820 }, { "epoch": 0.9719293245939014, "grad_norm": 1.4829292202259277, "learning_rate": 1.221966690782817e-05, "loss": 0.608, "step": 6821 }, { "epoch": 0.9720718153320034, "grad_norm": 1.4379966325469125, "learning_rate": 1.221724186828837e-05, "loss": 0.6701, "step": 6822 }, { "epoch": 0.9722143060701054, "grad_norm": 1.9079681864869955, "learning_rate": 1.2214816691607166e-05, "loss": 0.66, "step": 6823 }, { "epoch": 0.9723567968082074, "grad_norm": 1.2090335110130745, "learning_rate": 1.2212391377934567e-05, "loss": 0.6046, "step": 6824 }, { "epoch": 0.9724992875463095, "grad_norm": 1.5462868281779354, "learning_rate": 1.220996592742058e-05, "loss": 0.5865, "step": 6825 }, { "epoch": 0.9726417782844116, "grad_norm": 1.2322937026831153, "learning_rate": 1.2207540340215227e-05, "loss": 0.6011, "step": 6826 }, { "epoch": 0.9727842690225136, "grad_norm": 1.3060201539450809, "learning_rate": 1.2205114616468534e-05, "loss": 0.5796, "step": 6827 }, { "epoch": 0.9729267597606156, "grad_norm": 1.2866321923296893, "learning_rate": 1.2202688756330538e-05, "loss": 0.6758, "step": 6828 }, { "epoch": 0.9730692504987176, "grad_norm": 1.288498296174291, "learning_rate": 1.2200262759951287e-05, "loss": 0.6644, "step": 6829 }, { "epoch": 0.9732117412368196, "grad_norm": 1.3773341831394401, "learning_rate": 1.2197836627480829e-05, "loss": 0.5887, "step": 6830 }, { "epoch": 0.9733542319749217, "grad_norm": 1.2693814151237648, "learning_rate": 1.2195410359069229e-05, "loss": 0.6817, "step": 6831 }, { "epoch": 0.9734967227130237, "grad_norm": 1.3154045011930398, "learning_rate": 1.2192983954866555e-05, "loss": 0.6019, "step": 6832 }, { "epoch": 0.9736392134511257, "grad_norm": 1.2584462234222318, "learning_rate": 1.219055741502289e-05, "loss": 0.561, "step": 6833 }, { "epoch": 0.9737817041892277, "grad_norm": 1.1593937607459517, "learning_rate": 1.2188130739688318e-05, "loss": 0.6519, "step": 6834 }, { "epoch": 0.9739241949273297, "grad_norm": 1.3377858413889923, "learning_rate": 1.2185703929012934e-05, "loss": 0.5878, "step": 6835 }, { "epoch": 0.9740666856654318, "grad_norm": 1.3691365729406098, "learning_rate": 1.2183276983146839e-05, "loss": 0.6649, "step": 6836 }, { "epoch": 0.9742091764035338, "grad_norm": 1.4951142609959147, "learning_rate": 1.218084990224015e-05, "loss": 0.663, "step": 6837 }, { "epoch": 0.9743516671416358, "grad_norm": 1.30339811406274, "learning_rate": 1.2178422686442989e-05, "loss": 0.6468, "step": 6838 }, { "epoch": 0.9744941578797378, "grad_norm": 1.2806759041537736, "learning_rate": 1.2175995335905477e-05, "loss": 0.684, "step": 6839 }, { "epoch": 0.9746366486178398, "grad_norm": 1.2915423882641435, "learning_rate": 1.2173567850777757e-05, "loss": 0.6897, "step": 6840 }, { "epoch": 0.9747791393559418, "grad_norm": 1.2288253106955367, "learning_rate": 1.2171140231209975e-05, "loss": 0.668, "step": 6841 }, { "epoch": 0.9749216300940439, "grad_norm": 1.38665008670832, "learning_rate": 1.2168712477352279e-05, "loss": 0.7106, "step": 6842 }, { "epoch": 0.9750641208321459, "grad_norm": 1.3166850892101225, "learning_rate": 1.2166284589354835e-05, "loss": 0.6379, "step": 6843 }, { "epoch": 0.9752066115702479, "grad_norm": 1.2460037803918789, "learning_rate": 1.2163856567367815e-05, "loss": 0.5992, "step": 6844 }, { "epoch": 0.9753491023083499, "grad_norm": 1.1502284120239663, "learning_rate": 1.2161428411541395e-05, "loss": 0.6278, "step": 6845 }, { "epoch": 0.9754915930464519, "grad_norm": 1.3735499326143015, "learning_rate": 1.2159000122025762e-05, "loss": 0.5877, "step": 6846 }, { "epoch": 0.975634083784554, "grad_norm": 1.6495173764301923, "learning_rate": 1.215657169897111e-05, "loss": 0.6507, "step": 6847 }, { "epoch": 0.975776574522656, "grad_norm": 1.4007694310401864, "learning_rate": 1.2154143142527646e-05, "loss": 0.6549, "step": 6848 }, { "epoch": 0.975919065260758, "grad_norm": 1.3991220143205225, "learning_rate": 1.2151714452845582e-05, "loss": 0.6862, "step": 6849 }, { "epoch": 0.97606155599886, "grad_norm": 1.3681228374952805, "learning_rate": 1.2149285630075134e-05, "loss": 0.6035, "step": 6850 }, { "epoch": 0.9762040467369621, "grad_norm": 1.3837800208742792, "learning_rate": 1.214685667436653e-05, "loss": 0.6416, "step": 6851 }, { "epoch": 0.9763465374750642, "grad_norm": 1.2130572353794655, "learning_rate": 1.2144427585870008e-05, "loss": 0.6084, "step": 6852 }, { "epoch": 0.9764890282131662, "grad_norm": 1.2961628169787207, "learning_rate": 1.2141998364735817e-05, "loss": 0.5433, "step": 6853 }, { "epoch": 0.9766315189512682, "grad_norm": 1.3440184973465938, "learning_rate": 1.2139569011114202e-05, "loss": 0.6535, "step": 6854 }, { "epoch": 0.9767740096893702, "grad_norm": 1.388132144677243, "learning_rate": 1.2137139525155428e-05, "loss": 0.6097, "step": 6855 }, { "epoch": 0.9769165004274722, "grad_norm": 1.4094512884281027, "learning_rate": 1.2134709907009767e-05, "loss": 0.7358, "step": 6856 }, { "epoch": 0.9770589911655743, "grad_norm": 1.3968834611281358, "learning_rate": 1.2132280156827489e-05, "loss": 0.7048, "step": 6857 }, { "epoch": 0.9772014819036763, "grad_norm": 1.357620801346697, "learning_rate": 1.2129850274758888e-05, "loss": 0.6964, "step": 6858 }, { "epoch": 0.9773439726417783, "grad_norm": 1.2490624334363631, "learning_rate": 1.212742026095425e-05, "loss": 0.6145, "step": 6859 }, { "epoch": 0.9774864633798803, "grad_norm": 1.2304495584874184, "learning_rate": 1.2124990115563879e-05, "loss": 0.6246, "step": 6860 }, { "epoch": 0.9776289541179823, "grad_norm": 1.5306822537156946, "learning_rate": 1.2122559838738088e-05, "loss": 0.6541, "step": 6861 }, { "epoch": 0.9777714448560844, "grad_norm": 1.3162999171966205, "learning_rate": 1.2120129430627194e-05, "loss": 0.6426, "step": 6862 }, { "epoch": 0.9779139355941864, "grad_norm": 1.3653614034768202, "learning_rate": 1.2117698891381524e-05, "loss": 0.6924, "step": 6863 }, { "epoch": 0.9780564263322884, "grad_norm": 1.2328436830871496, "learning_rate": 1.2115268221151409e-05, "loss": 0.6401, "step": 6864 }, { "epoch": 0.9781989170703904, "grad_norm": 1.2953271972223825, "learning_rate": 1.2112837420087191e-05, "loss": 0.6521, "step": 6865 }, { "epoch": 0.9783414078084924, "grad_norm": 1.4212336706211413, "learning_rate": 1.2110406488339224e-05, "loss": 0.6731, "step": 6866 }, { "epoch": 0.9784838985465945, "grad_norm": 1.2361702538401946, "learning_rate": 1.2107975426057865e-05, "loss": 0.6327, "step": 6867 }, { "epoch": 0.9786263892846965, "grad_norm": 1.5011562079808043, "learning_rate": 1.2105544233393483e-05, "loss": 0.6783, "step": 6868 }, { "epoch": 0.9787688800227985, "grad_norm": 1.2308160943936892, "learning_rate": 1.210311291049645e-05, "loss": 0.5526, "step": 6869 }, { "epoch": 0.9789113707609005, "grad_norm": 1.2682157140200423, "learning_rate": 1.2100681457517147e-05, "loss": 0.5975, "step": 6870 }, { "epoch": 0.9790538614990025, "grad_norm": 1.333612805014116, "learning_rate": 1.2098249874605972e-05, "loss": 0.6007, "step": 6871 }, { "epoch": 0.9791963522371046, "grad_norm": 1.1548818819823925, "learning_rate": 1.2095818161913315e-05, "loss": 0.6074, "step": 6872 }, { "epoch": 0.9793388429752066, "grad_norm": 1.2235906811206072, "learning_rate": 1.2093386319589588e-05, "loss": 0.6938, "step": 6873 }, { "epoch": 0.9794813337133086, "grad_norm": 1.1593444534920563, "learning_rate": 1.2090954347785207e-05, "loss": 0.5616, "step": 6874 }, { "epoch": 0.9796238244514106, "grad_norm": 1.4637660001796495, "learning_rate": 1.2088522246650592e-05, "loss": 0.7363, "step": 6875 }, { "epoch": 0.9797663151895126, "grad_norm": 1.284103778929905, "learning_rate": 1.2086090016336174e-05, "loss": 0.7324, "step": 6876 }, { "epoch": 0.9799088059276148, "grad_norm": 1.3108996271130604, "learning_rate": 1.2083657656992393e-05, "loss": 0.6751, "step": 6877 }, { "epoch": 0.9800512966657168, "grad_norm": 1.704031408964943, "learning_rate": 1.2081225168769697e-05, "loss": 0.5515, "step": 6878 }, { "epoch": 0.9801937874038188, "grad_norm": 1.4321337458665, "learning_rate": 1.207879255181854e-05, "loss": 0.6432, "step": 6879 }, { "epoch": 0.9803362781419208, "grad_norm": 1.3252088799187092, "learning_rate": 1.2076359806289381e-05, "loss": 0.6142, "step": 6880 }, { "epoch": 0.9804787688800228, "grad_norm": 1.348242786975642, "learning_rate": 1.2073926932332696e-05, "loss": 0.6005, "step": 6881 }, { "epoch": 0.9806212596181249, "grad_norm": 1.3873362340185191, "learning_rate": 1.2071493930098963e-05, "loss": 0.7328, "step": 6882 }, { "epoch": 0.9807637503562269, "grad_norm": 1.3261865153626016, "learning_rate": 1.2069060799738668e-05, "loss": 0.6229, "step": 6883 }, { "epoch": 0.9809062410943289, "grad_norm": 1.2389707602429636, "learning_rate": 1.2066627541402306e-05, "loss": 0.6299, "step": 6884 }, { "epoch": 0.9810487318324309, "grad_norm": 1.3491291383754007, "learning_rate": 1.2064194155240374e-05, "loss": 0.5658, "step": 6885 }, { "epoch": 0.9811912225705329, "grad_norm": 1.2823968881169503, "learning_rate": 1.2061760641403393e-05, "loss": 0.6622, "step": 6886 }, { "epoch": 0.981333713308635, "grad_norm": 1.3593949084717563, "learning_rate": 1.2059327000041871e-05, "loss": 0.6309, "step": 6887 }, { "epoch": 0.981476204046737, "grad_norm": 1.2682474026037922, "learning_rate": 1.205689323130634e-05, "loss": 0.6709, "step": 6888 }, { "epoch": 0.981618694784839, "grad_norm": 1.2342994010206094, "learning_rate": 1.2054459335347333e-05, "loss": 0.6139, "step": 6889 }, { "epoch": 0.981761185522941, "grad_norm": 1.2665862512009551, "learning_rate": 1.2052025312315392e-05, "loss": 0.7377, "step": 6890 }, { "epoch": 0.981903676261043, "grad_norm": 1.2946238550424267, "learning_rate": 1.2049591162361065e-05, "loss": 0.661, "step": 6891 }, { "epoch": 0.982046166999145, "grad_norm": 1.2856066813281237, "learning_rate": 1.2047156885634912e-05, "loss": 0.7031, "step": 6892 }, { "epoch": 0.9821886577372471, "grad_norm": 1.289820258916895, "learning_rate": 1.2044722482287501e-05, "loss": 0.5447, "step": 6893 }, { "epoch": 0.9823311484753491, "grad_norm": 1.3652630641380354, "learning_rate": 1.2042287952469399e-05, "loss": 0.6137, "step": 6894 }, { "epoch": 0.9824736392134511, "grad_norm": 1.3546678487763586, "learning_rate": 1.2039853296331188e-05, "loss": 0.5987, "step": 6895 }, { "epoch": 0.9826161299515531, "grad_norm": 1.4154196964974008, "learning_rate": 1.203741851402346e-05, "loss": 0.6277, "step": 6896 }, { "epoch": 0.9827586206896551, "grad_norm": 1.3639157318506856, "learning_rate": 1.2034983605696812e-05, "loss": 0.6553, "step": 6897 }, { "epoch": 0.9829011114277572, "grad_norm": 1.3989185293621365, "learning_rate": 1.2032548571501847e-05, "loss": 0.6226, "step": 6898 }, { "epoch": 0.9830436021658592, "grad_norm": 1.317480543012661, "learning_rate": 1.2030113411589176e-05, "loss": 0.7118, "step": 6899 }, { "epoch": 0.9831860929039612, "grad_norm": 1.4468086861596154, "learning_rate": 1.2027678126109423e-05, "loss": 0.6621, "step": 6900 }, { "epoch": 0.9833285836420632, "grad_norm": 1.2773869746824842, "learning_rate": 1.2025242715213217e-05, "loss": 0.6125, "step": 6901 }, { "epoch": 0.9834710743801653, "grad_norm": 1.5302621743607547, "learning_rate": 1.2022807179051186e-05, "loss": 0.6492, "step": 6902 }, { "epoch": 0.9836135651182674, "grad_norm": 1.26753689610031, "learning_rate": 1.2020371517773976e-05, "loss": 0.6674, "step": 6903 }, { "epoch": 0.9837560558563694, "grad_norm": 1.3974754827477611, "learning_rate": 1.2017935731532244e-05, "loss": 0.6255, "step": 6904 }, { "epoch": 0.9838985465944714, "grad_norm": 1.4116104493621469, "learning_rate": 1.2015499820476644e-05, "loss": 0.5288, "step": 6905 }, { "epoch": 0.9840410373325734, "grad_norm": 1.3314314629026733, "learning_rate": 1.201306378475784e-05, "loss": 0.6564, "step": 6906 }, { "epoch": 0.9841835280706754, "grad_norm": 1.4190821752482858, "learning_rate": 1.2010627624526515e-05, "loss": 0.6313, "step": 6907 }, { "epoch": 0.9843260188087775, "grad_norm": 1.3365154552418557, "learning_rate": 1.2008191339933344e-05, "loss": 0.5767, "step": 6908 }, { "epoch": 0.9844685095468795, "grad_norm": 1.3123867639977407, "learning_rate": 1.2005754931129015e-05, "loss": 0.6025, "step": 6909 }, { "epoch": 0.9846110002849815, "grad_norm": 1.3274628724554371, "learning_rate": 1.200331839826423e-05, "loss": 0.6179, "step": 6910 }, { "epoch": 0.9847534910230835, "grad_norm": 1.2225524181359846, "learning_rate": 1.2000881741489695e-05, "loss": 0.6369, "step": 6911 }, { "epoch": 0.9848959817611855, "grad_norm": 1.3106883256415203, "learning_rate": 1.1998444960956118e-05, "loss": 0.66, "step": 6912 }, { "epoch": 0.9850384724992876, "grad_norm": 1.4645975118554935, "learning_rate": 1.1996008056814224e-05, "loss": 0.633, "step": 6913 }, { "epoch": 0.9851809632373896, "grad_norm": 1.4138180078243008, "learning_rate": 1.1993571029214736e-05, "loss": 0.7199, "step": 6914 }, { "epoch": 0.9853234539754916, "grad_norm": 1.7025004996314324, "learning_rate": 1.1991133878308393e-05, "loss": 0.6653, "step": 6915 }, { "epoch": 0.9854659447135936, "grad_norm": 1.3438690518466498, "learning_rate": 1.1988696604245942e-05, "loss": 0.615, "step": 6916 }, { "epoch": 0.9856084354516956, "grad_norm": 1.2754344070523427, "learning_rate": 1.1986259207178123e-05, "loss": 0.6477, "step": 6917 }, { "epoch": 0.9857509261897976, "grad_norm": 1.230624816165258, "learning_rate": 1.1983821687255704e-05, "loss": 0.5923, "step": 6918 }, { "epoch": 0.9858934169278997, "grad_norm": 1.2196153869525062, "learning_rate": 1.198138404462945e-05, "loss": 0.6346, "step": 6919 }, { "epoch": 0.9860359076660017, "grad_norm": 1.340187378058046, "learning_rate": 1.1978946279450132e-05, "loss": 0.645, "step": 6920 }, { "epoch": 0.9861783984041037, "grad_norm": 1.2997990439850111, "learning_rate": 1.197650839186853e-05, "loss": 0.5976, "step": 6921 }, { "epoch": 0.9863208891422057, "grad_norm": 1.3227850071947262, "learning_rate": 1.1974070382035436e-05, "loss": 0.6534, "step": 6922 }, { "epoch": 0.9864633798803077, "grad_norm": 1.4394699303507386, "learning_rate": 1.197163225010165e-05, "loss": 0.6863, "step": 6923 }, { "epoch": 0.9866058706184098, "grad_norm": 1.4020158060615144, "learning_rate": 1.1969193996217966e-05, "loss": 0.6064, "step": 6924 }, { "epoch": 0.9867483613565118, "grad_norm": 1.2712159957130784, "learning_rate": 1.19667556205352e-05, "loss": 0.6527, "step": 6925 }, { "epoch": 0.9868908520946138, "grad_norm": 1.2977744305095265, "learning_rate": 1.1964317123204174e-05, "loss": 0.6004, "step": 6926 }, { "epoch": 0.9870333428327158, "grad_norm": 1.1694482771615884, "learning_rate": 1.1961878504375712e-05, "loss": 0.5702, "step": 6927 }, { "epoch": 0.987175833570818, "grad_norm": 1.2086576928778077, "learning_rate": 1.1959439764200651e-05, "loss": 0.6182, "step": 6928 }, { "epoch": 0.98731832430892, "grad_norm": 1.4045173858706133, "learning_rate": 1.1957000902829827e-05, "loss": 0.7344, "step": 6929 }, { "epoch": 0.987460815047022, "grad_norm": 1.3083627480120363, "learning_rate": 1.1954561920414094e-05, "loss": 0.678, "step": 6930 }, { "epoch": 0.987603305785124, "grad_norm": 1.442796036989506, "learning_rate": 1.1952122817104306e-05, "loss": 0.6468, "step": 6931 }, { "epoch": 0.987745796523226, "grad_norm": 1.4446769693597616, "learning_rate": 1.1949683593051324e-05, "loss": 0.6637, "step": 6932 }, { "epoch": 0.987888287261328, "grad_norm": 1.3526583994364352, "learning_rate": 1.1947244248406027e-05, "loss": 0.6341, "step": 6933 }, { "epoch": 0.9880307779994301, "grad_norm": 1.3248260964642922, "learning_rate": 1.194480478331929e-05, "loss": 0.6871, "step": 6934 }, { "epoch": 0.9881732687375321, "grad_norm": 1.4011667883132812, "learning_rate": 1.1942365197941998e-05, "loss": 0.6413, "step": 6935 }, { "epoch": 0.9883157594756341, "grad_norm": 1.2608743484268325, "learning_rate": 1.1939925492425049e-05, "loss": 0.5962, "step": 6936 }, { "epoch": 0.9884582502137361, "grad_norm": 1.210977683270926, "learning_rate": 1.1937485666919339e-05, "loss": 0.6819, "step": 6937 }, { "epoch": 0.9886007409518381, "grad_norm": 1.3868930387577427, "learning_rate": 1.1935045721575782e-05, "loss": 0.6767, "step": 6938 }, { "epoch": 0.9887432316899402, "grad_norm": 1.5858429624254167, "learning_rate": 1.1932605656545287e-05, "loss": 0.672, "step": 6939 }, { "epoch": 0.9888857224280422, "grad_norm": 1.2890606120176185, "learning_rate": 1.1930165471978785e-05, "loss": 0.6219, "step": 6940 }, { "epoch": 0.9890282131661442, "grad_norm": 1.2670204972538446, "learning_rate": 1.1927725168027204e-05, "loss": 0.626, "step": 6941 }, { "epoch": 0.9891707039042462, "grad_norm": 1.2853003221943655, "learning_rate": 1.1925284744841484e-05, "loss": 0.6271, "step": 6942 }, { "epoch": 0.9893131946423482, "grad_norm": 1.4282404103552238, "learning_rate": 1.1922844202572565e-05, "loss": 0.6075, "step": 6943 }, { "epoch": 0.9894556853804503, "grad_norm": 1.386530458107996, "learning_rate": 1.1920403541371406e-05, "loss": 0.6889, "step": 6944 }, { "epoch": 0.9895981761185523, "grad_norm": 1.2796538139752327, "learning_rate": 1.1917962761388966e-05, "loss": 0.5925, "step": 6945 }, { "epoch": 0.9897406668566543, "grad_norm": 1.2509901098645424, "learning_rate": 1.1915521862776209e-05, "loss": 0.5776, "step": 6946 }, { "epoch": 0.9898831575947563, "grad_norm": 1.3379011531893643, "learning_rate": 1.1913080845684113e-05, "loss": 0.6045, "step": 6947 }, { "epoch": 0.9900256483328583, "grad_norm": 1.2451864781372843, "learning_rate": 1.1910639710263665e-05, "loss": 0.5653, "step": 6948 }, { "epoch": 0.9901681390709604, "grad_norm": 1.474680633369622, "learning_rate": 1.1908198456665847e-05, "loss": 0.5943, "step": 6949 }, { "epoch": 0.9903106298090624, "grad_norm": 1.2312307187301001, "learning_rate": 1.190575708504166e-05, "loss": 0.6838, "step": 6950 }, { "epoch": 0.9904531205471644, "grad_norm": 1.2451920004854982, "learning_rate": 1.1903315595542107e-05, "loss": 0.5856, "step": 6951 }, { "epoch": 0.9905956112852664, "grad_norm": 1.2203739339329942, "learning_rate": 1.19008739883182e-05, "loss": 0.649, "step": 6952 }, { "epoch": 0.9907381020233684, "grad_norm": 1.5904279931750072, "learning_rate": 1.1898432263520961e-05, "loss": 0.584, "step": 6953 }, { "epoch": 0.9908805927614706, "grad_norm": 1.3866552337960694, "learning_rate": 1.1895990421301406e-05, "loss": 0.5925, "step": 6954 }, { "epoch": 0.9910230834995726, "grad_norm": 1.3462309295105173, "learning_rate": 1.189354846181058e-05, "loss": 0.6847, "step": 6955 }, { "epoch": 0.9911655742376746, "grad_norm": 1.3488876076390963, "learning_rate": 1.1891106385199522e-05, "loss": 0.6231, "step": 6956 }, { "epoch": 0.9913080649757766, "grad_norm": 1.2549518642174173, "learning_rate": 1.1888664191619276e-05, "loss": 0.6514, "step": 6957 }, { "epoch": 0.9914505557138786, "grad_norm": 1.2552555322810264, "learning_rate": 1.1886221881220897e-05, "loss": 0.5887, "step": 6958 }, { "epoch": 0.9915930464519807, "grad_norm": 1.1792020938591463, "learning_rate": 1.1883779454155452e-05, "loss": 0.6413, "step": 6959 }, { "epoch": 0.9917355371900827, "grad_norm": 1.2752954161341623, "learning_rate": 1.1881336910574004e-05, "loss": 0.6811, "step": 6960 }, { "epoch": 0.9918780279281847, "grad_norm": 1.2293897163108822, "learning_rate": 1.1878894250627633e-05, "loss": 0.5546, "step": 6961 }, { "epoch": 0.9920205186662867, "grad_norm": 1.3793284515335504, "learning_rate": 1.1876451474467423e-05, "loss": 0.6539, "step": 6962 }, { "epoch": 0.9921630094043887, "grad_norm": 1.5579931453662625, "learning_rate": 1.187400858224447e-05, "loss": 0.6098, "step": 6963 }, { "epoch": 0.9923055001424907, "grad_norm": 1.282009021293375, "learning_rate": 1.1871565574109864e-05, "loss": 0.638, "step": 6964 }, { "epoch": 0.9924479908805928, "grad_norm": 1.1960255174815613, "learning_rate": 1.1869122450214716e-05, "loss": 0.6288, "step": 6965 }, { "epoch": 0.9925904816186948, "grad_norm": 1.330064567473589, "learning_rate": 1.1866679210710137e-05, "loss": 0.6005, "step": 6966 }, { "epoch": 0.9927329723567968, "grad_norm": 1.240649605320677, "learning_rate": 1.1864235855747246e-05, "loss": 0.5691, "step": 6967 }, { "epoch": 0.9928754630948988, "grad_norm": 1.1708992812279675, "learning_rate": 1.1861792385477171e-05, "loss": 0.6076, "step": 6968 }, { "epoch": 0.9930179538330008, "grad_norm": 1.3394773661572643, "learning_rate": 1.1859348800051047e-05, "loss": 0.5677, "step": 6969 }, { "epoch": 0.9931604445711029, "grad_norm": 1.462832568636343, "learning_rate": 1.1856905099620014e-05, "loss": 0.6347, "step": 6970 }, { "epoch": 0.9933029353092049, "grad_norm": 1.4380106873096319, "learning_rate": 1.1854461284335223e-05, "loss": 0.5551, "step": 6971 }, { "epoch": 0.9934454260473069, "grad_norm": 1.2607041401351875, "learning_rate": 1.1852017354347827e-05, "loss": 0.6595, "step": 6972 }, { "epoch": 0.9935879167854089, "grad_norm": 1.3519515743576274, "learning_rate": 1.1849573309808986e-05, "loss": 0.6911, "step": 6973 }, { "epoch": 0.9937304075235109, "grad_norm": 1.2460397007719453, "learning_rate": 1.1847129150869875e-05, "loss": 0.5995, "step": 6974 }, { "epoch": 0.993872898261613, "grad_norm": 1.2837853146171914, "learning_rate": 1.1844684877681669e-05, "loss": 0.6536, "step": 6975 }, { "epoch": 0.994015388999715, "grad_norm": 1.6234082753290042, "learning_rate": 1.1842240490395547e-05, "loss": 0.5744, "step": 6976 }, { "epoch": 0.994157879737817, "grad_norm": 1.2589890561477457, "learning_rate": 1.1839795989162705e-05, "loss": 0.6157, "step": 6977 }, { "epoch": 0.994300370475919, "grad_norm": 1.2933042513482969, "learning_rate": 1.1837351374134343e-05, "loss": 0.6338, "step": 6978 }, { "epoch": 0.994442861214021, "grad_norm": 1.198756794478731, "learning_rate": 1.1834906645461661e-05, "loss": 0.5558, "step": 6979 }, { "epoch": 0.9945853519521232, "grad_norm": 1.254183403079512, "learning_rate": 1.1832461803295871e-05, "loss": 0.5413, "step": 6980 }, { "epoch": 0.9947278426902252, "grad_norm": 1.251958920898494, "learning_rate": 1.1830016847788195e-05, "loss": 0.5981, "step": 6981 }, { "epoch": 0.9948703334283272, "grad_norm": 1.3548098070807206, "learning_rate": 1.1827571779089862e-05, "loss": 0.6814, "step": 6982 }, { "epoch": 0.9950128241664292, "grad_norm": 1.3681326383973431, "learning_rate": 1.1825126597352092e-05, "loss": 0.6188, "step": 6983 }, { "epoch": 0.9951553149045312, "grad_norm": 1.4241819007694663, "learning_rate": 1.182268130272614e-05, "loss": 0.6302, "step": 6984 }, { "epoch": 0.9952978056426333, "grad_norm": 1.3724531017229298, "learning_rate": 1.1820235895363243e-05, "loss": 0.6706, "step": 6985 }, { "epoch": 0.9954402963807353, "grad_norm": 1.3520991094778911, "learning_rate": 1.1817790375414663e-05, "loss": 0.6603, "step": 6986 }, { "epoch": 0.9955827871188373, "grad_norm": 1.654045332157852, "learning_rate": 1.1815344743031654e-05, "loss": 0.6705, "step": 6987 }, { "epoch": 0.9957252778569393, "grad_norm": 1.2470468648608866, "learning_rate": 1.1812898998365488e-05, "loss": 0.6535, "step": 6988 }, { "epoch": 0.9958677685950413, "grad_norm": 1.3076234543573035, "learning_rate": 1.1810453141567435e-05, "loss": 0.6318, "step": 6989 }, { "epoch": 0.9960102593331434, "grad_norm": 1.4884188040072577, "learning_rate": 1.1808007172788782e-05, "loss": 0.6188, "step": 6990 }, { "epoch": 0.9961527500712454, "grad_norm": 1.1504964244738871, "learning_rate": 1.1805561092180814e-05, "loss": 0.6298, "step": 6991 }, { "epoch": 0.9962952408093474, "grad_norm": 1.354128761411234, "learning_rate": 1.1803114899894829e-05, "loss": 0.6519, "step": 6992 }, { "epoch": 0.9964377315474494, "grad_norm": 1.2456621998864577, "learning_rate": 1.1800668596082135e-05, "loss": 0.5817, "step": 6993 }, { "epoch": 0.9965802222855514, "grad_norm": 1.31670240925235, "learning_rate": 1.1798222180894028e-05, "loss": 0.6303, "step": 6994 }, { "epoch": 0.9967227130236535, "grad_norm": 1.370131326531244, "learning_rate": 1.1795775654481833e-05, "loss": 0.6683, "step": 6995 }, { "epoch": 0.9968652037617555, "grad_norm": 1.4570143937539812, "learning_rate": 1.179332901699687e-05, "loss": 0.6147, "step": 6996 }, { "epoch": 0.9970076944998575, "grad_norm": 1.3757973752216708, "learning_rate": 1.1790882268590473e-05, "loss": 0.6293, "step": 6997 }, { "epoch": 0.9971501852379595, "grad_norm": 1.5881857192645665, "learning_rate": 1.1788435409413976e-05, "loss": 0.6149, "step": 6998 }, { "epoch": 0.9972926759760615, "grad_norm": 1.3902670340775158, "learning_rate": 1.1785988439618723e-05, "loss": 0.5942, "step": 6999 }, { "epoch": 0.9974351667141635, "grad_norm": 1.380058423184742, "learning_rate": 1.1783541359356066e-05, "loss": 0.6396, "step": 7000 }, { "epoch": 0.9975776574522656, "grad_norm": 1.383489486481697, "learning_rate": 1.1781094168777361e-05, "loss": 0.6543, "step": 7001 }, { "epoch": 0.9977201481903676, "grad_norm": 1.3546816500980343, "learning_rate": 1.1778646868033972e-05, "loss": 0.5831, "step": 7002 }, { "epoch": 0.9978626389284696, "grad_norm": 1.3334591609091342, "learning_rate": 1.1776199457277269e-05, "loss": 0.6579, "step": 7003 }, { "epoch": 0.9980051296665716, "grad_norm": 1.282127326223095, "learning_rate": 1.1773751936658633e-05, "loss": 0.6553, "step": 7004 }, { "epoch": 0.9981476204046736, "grad_norm": 1.2826431119834163, "learning_rate": 1.1771304306329448e-05, "loss": 0.6465, "step": 7005 }, { "epoch": 0.9982901111427758, "grad_norm": 1.297223765745408, "learning_rate": 1.1768856566441103e-05, "loss": 0.586, "step": 7006 }, { "epoch": 0.9984326018808778, "grad_norm": 1.234134099510419, "learning_rate": 1.1766408717144997e-05, "loss": 0.6486, "step": 7007 }, { "epoch": 0.9985750926189798, "grad_norm": 1.1747120470847718, "learning_rate": 1.1763960758592538e-05, "loss": 0.6119, "step": 7008 }, { "epoch": 0.9987175833570818, "grad_norm": 1.4713809532119493, "learning_rate": 1.1761512690935135e-05, "loss": 0.6757, "step": 7009 }, { "epoch": 0.9988600740951838, "grad_norm": 1.3471217581978225, "learning_rate": 1.1759064514324208e-05, "loss": 0.6478, "step": 7010 }, { "epoch": 0.9990025648332859, "grad_norm": 1.2867073360771446, "learning_rate": 1.1756616228911178e-05, "loss": 0.6493, "step": 7011 }, { "epoch": 0.9991450555713879, "grad_norm": 1.3057702602362298, "learning_rate": 1.1754167834847484e-05, "loss": 0.651, "step": 7012 }, { "epoch": 0.9992875463094899, "grad_norm": 1.261706538598417, "learning_rate": 1.1751719332284557e-05, "loss": 0.6655, "step": 7013 }, { "epoch": 0.9994300370475919, "grad_norm": 1.2730108416462367, "learning_rate": 1.1749270721373848e-05, "loss": 0.6649, "step": 7014 }, { "epoch": 0.9995725277856939, "grad_norm": 1.6310498513640819, "learning_rate": 1.1746822002266808e-05, "loss": 0.5587, "step": 7015 }, { "epoch": 0.999715018523796, "grad_norm": 1.2253355543915285, "learning_rate": 1.1744373175114895e-05, "loss": 0.6703, "step": 7016 }, { "epoch": 0.999857509261898, "grad_norm": 1.273586382872255, "learning_rate": 1.1741924240069575e-05, "loss": 0.6744, "step": 7017 }, { "epoch": 1.0, "grad_norm": 1.3355133787289262, "learning_rate": 1.173947519728232e-05, "loss": 0.6196, "step": 7018 }, { "epoch": 1.000142490738102, "grad_norm": 1.140661111509938, "learning_rate": 1.1737026046904608e-05, "loss": 0.503, "step": 7019 }, { "epoch": 1.000284981476204, "grad_norm": 1.1839376433975675, "learning_rate": 1.1734576789087924e-05, "loss": 0.4861, "step": 7020 }, { "epoch": 1.000427472214306, "grad_norm": 1.1220479951269327, "learning_rate": 1.1732127423983761e-05, "loss": 0.4856, "step": 7021 }, { "epoch": 1.000569962952408, "grad_norm": 1.1819297592470555, "learning_rate": 1.1729677951743619e-05, "loss": 0.4702, "step": 7022 }, { "epoch": 1.00071245369051, "grad_norm": 1.2023826520326233, "learning_rate": 1.1727228372519007e-05, "loss": 0.4775, "step": 7023 }, { "epoch": 1.0008549444286121, "grad_norm": 1.2289565975031613, "learning_rate": 1.1724778686461426e-05, "loss": 0.5234, "step": 7024 }, { "epoch": 1.0009974351667141, "grad_norm": 1.1797072336127996, "learning_rate": 1.17223288937224e-05, "loss": 0.4377, "step": 7025 }, { "epoch": 1.0011399259048162, "grad_norm": 1.1885007221392276, "learning_rate": 1.1719878994453459e-05, "loss": 0.487, "step": 7026 }, { "epoch": 1.0012824166429182, "grad_norm": 1.066803349574759, "learning_rate": 1.171742898880613e-05, "loss": 0.4561, "step": 7027 }, { "epoch": 1.0014249073810202, "grad_norm": 1.3239640317529342, "learning_rate": 1.171497887693195e-05, "loss": 0.4313, "step": 7028 }, { "epoch": 1.0015673981191222, "grad_norm": 1.1415578959794805, "learning_rate": 1.171252865898247e-05, "loss": 0.4349, "step": 7029 }, { "epoch": 1.0017098888572242, "grad_norm": 1.172903464611767, "learning_rate": 1.1710078335109236e-05, "loss": 0.4244, "step": 7030 }, { "epoch": 1.0018523795953262, "grad_norm": 1.469110999871794, "learning_rate": 1.1707627905463808e-05, "loss": 0.5495, "step": 7031 }, { "epoch": 1.0019948703334283, "grad_norm": 1.484678949591142, "learning_rate": 1.1705177370197748e-05, "loss": 0.4976, "step": 7032 }, { "epoch": 1.0021373610715303, "grad_norm": 1.3781984875056723, "learning_rate": 1.170272672946263e-05, "loss": 0.4955, "step": 7033 }, { "epoch": 1.0022798518096323, "grad_norm": 1.289372587902519, "learning_rate": 1.1700275983410033e-05, "loss": 0.4666, "step": 7034 }, { "epoch": 1.0024223425477343, "grad_norm": 1.3930196858830022, "learning_rate": 1.1697825132191538e-05, "loss": 0.422, "step": 7035 }, { "epoch": 1.0025648332858363, "grad_norm": 1.3601100613065717, "learning_rate": 1.1695374175958735e-05, "loss": 0.4986, "step": 7036 }, { "epoch": 1.0027073240239384, "grad_norm": 1.374616613101303, "learning_rate": 1.1692923114863227e-05, "loss": 0.4639, "step": 7037 }, { "epoch": 1.0028498147620404, "grad_norm": 1.3055996835241521, "learning_rate": 1.1690471949056612e-05, "loss": 0.4415, "step": 7038 }, { "epoch": 1.0029923055001424, "grad_norm": 1.4127400178770204, "learning_rate": 1.16880206786905e-05, "loss": 0.5036, "step": 7039 }, { "epoch": 1.0031347962382444, "grad_norm": 1.4262369051991628, "learning_rate": 1.1685569303916513e-05, "loss": 0.5279, "step": 7040 }, { "epoch": 1.0032772869763464, "grad_norm": 1.2888184524376642, "learning_rate": 1.1683117824886268e-05, "loss": 0.4648, "step": 7041 }, { "epoch": 1.0034197777144485, "grad_norm": 1.41802622159306, "learning_rate": 1.1680666241751397e-05, "loss": 0.4764, "step": 7042 }, { "epoch": 1.0035622684525505, "grad_norm": 1.3220020816179192, "learning_rate": 1.1678214554663536e-05, "loss": 0.4572, "step": 7043 }, { "epoch": 1.0037047591906527, "grad_norm": 1.4677399371103883, "learning_rate": 1.1675762763774327e-05, "loss": 0.5069, "step": 7044 }, { "epoch": 1.0038472499287547, "grad_norm": 1.4103697681539944, "learning_rate": 1.1673310869235422e-05, "loss": 0.519, "step": 7045 }, { "epoch": 1.0039897406668568, "grad_norm": 1.429460208780881, "learning_rate": 1.1670858871198472e-05, "loss": 0.4278, "step": 7046 }, { "epoch": 1.0041322314049588, "grad_norm": 1.3273209081089437, "learning_rate": 1.1668406769815136e-05, "loss": 0.4269, "step": 7047 }, { "epoch": 1.0042747221430608, "grad_norm": 1.3370696449451835, "learning_rate": 1.166595456523709e-05, "loss": 0.4779, "step": 7048 }, { "epoch": 1.0044172128811628, "grad_norm": 1.2241272022588918, "learning_rate": 1.1663502257616002e-05, "loss": 0.4431, "step": 7049 }, { "epoch": 1.0045597036192648, "grad_norm": 1.3236609074043408, "learning_rate": 1.1661049847103554e-05, "loss": 0.4352, "step": 7050 }, { "epoch": 1.0047021943573669, "grad_norm": 1.2085631441082592, "learning_rate": 1.1658597333851435e-05, "loss": 0.4723, "step": 7051 }, { "epoch": 1.0048446850954689, "grad_norm": 1.293147793300051, "learning_rate": 1.1656144718011339e-05, "loss": 0.4273, "step": 7052 }, { "epoch": 1.004987175833571, "grad_norm": 1.2992074049833924, "learning_rate": 1.1653691999734965e-05, "loss": 0.4582, "step": 7053 }, { "epoch": 1.005129666571673, "grad_norm": 1.4475254001389382, "learning_rate": 1.1651239179174017e-05, "loss": 0.5188, "step": 7054 }, { "epoch": 1.005272157309775, "grad_norm": 1.3739145811794637, "learning_rate": 1.1648786256480209e-05, "loss": 0.4353, "step": 7055 }, { "epoch": 1.005414648047877, "grad_norm": 1.291413130033746, "learning_rate": 1.1646333231805258e-05, "loss": 0.4127, "step": 7056 }, { "epoch": 1.005557138785979, "grad_norm": 1.3218965883158005, "learning_rate": 1.1643880105300894e-05, "loss": 0.3941, "step": 7057 }, { "epoch": 1.005699629524081, "grad_norm": 1.2996123305227443, "learning_rate": 1.1641426877118842e-05, "loss": 0.4526, "step": 7058 }, { "epoch": 1.005842120262183, "grad_norm": 1.5195677747696157, "learning_rate": 1.1638973547410844e-05, "loss": 0.466, "step": 7059 }, { "epoch": 1.005984611000285, "grad_norm": 1.343537081675462, "learning_rate": 1.1636520116328645e-05, "loss": 0.4733, "step": 7060 }, { "epoch": 1.006127101738387, "grad_norm": 1.27201431653096, "learning_rate": 1.163406658402399e-05, "loss": 0.4313, "step": 7061 }, { "epoch": 1.006269592476489, "grad_norm": 1.3586321395127388, "learning_rate": 1.1631612950648641e-05, "loss": 0.4674, "step": 7062 }, { "epoch": 1.006412083214591, "grad_norm": 1.3204011885048954, "learning_rate": 1.1629159216354358e-05, "loss": 0.4384, "step": 7063 }, { "epoch": 1.006554573952693, "grad_norm": 1.3237104611377446, "learning_rate": 1.1626705381292908e-05, "loss": 0.4277, "step": 7064 }, { "epoch": 1.0066970646907951, "grad_norm": 1.3807159174218029, "learning_rate": 1.162425144561607e-05, "loss": 0.4758, "step": 7065 }, { "epoch": 1.0068395554288971, "grad_norm": 1.238229472523843, "learning_rate": 1.1621797409475626e-05, "loss": 0.4553, "step": 7066 }, { "epoch": 1.0069820461669992, "grad_norm": 1.3535409133529346, "learning_rate": 1.161934327302336e-05, "loss": 0.4716, "step": 7067 }, { "epoch": 1.0071245369051012, "grad_norm": 1.356147649454663, "learning_rate": 1.1616889036411067e-05, "loss": 0.4597, "step": 7068 }, { "epoch": 1.0072670276432032, "grad_norm": 1.3410456482403357, "learning_rate": 1.1614434699790548e-05, "loss": 0.4691, "step": 7069 }, { "epoch": 1.0074095183813052, "grad_norm": 1.4535887143062705, "learning_rate": 1.1611980263313607e-05, "loss": 0.4738, "step": 7070 }, { "epoch": 1.0075520091194072, "grad_norm": 1.4034514164349108, "learning_rate": 1.1609525727132062e-05, "loss": 0.4581, "step": 7071 }, { "epoch": 1.0076944998575093, "grad_norm": 1.5533330812491914, "learning_rate": 1.1607071091397727e-05, "loss": 0.42, "step": 7072 }, { "epoch": 1.0078369905956113, "grad_norm": 1.4268740686431265, "learning_rate": 1.1604616356262426e-05, "loss": 0.4852, "step": 7073 }, { "epoch": 1.0079794813337133, "grad_norm": 1.2140442987345865, "learning_rate": 1.160216152187799e-05, "loss": 0.4276, "step": 7074 }, { "epoch": 1.0081219720718153, "grad_norm": 1.6362979819099877, "learning_rate": 1.1599706588396263e-05, "loss": 0.4404, "step": 7075 }, { "epoch": 1.0082644628099173, "grad_norm": 1.4059586154868045, "learning_rate": 1.1597251555969078e-05, "loss": 0.421, "step": 7076 }, { "epoch": 1.0084069535480193, "grad_norm": 1.3346126757856787, "learning_rate": 1.1594796424748292e-05, "loss": 0.5161, "step": 7077 }, { "epoch": 1.0085494442861214, "grad_norm": 1.257966217993295, "learning_rate": 1.1592341194885755e-05, "loss": 0.4387, "step": 7078 }, { "epoch": 1.0086919350242234, "grad_norm": 1.3603052154109923, "learning_rate": 1.1589885866533331e-05, "loss": 0.4562, "step": 7079 }, { "epoch": 1.0088344257623254, "grad_norm": 1.4826069443830658, "learning_rate": 1.1587430439842885e-05, "loss": 0.4904, "step": 7080 }, { "epoch": 1.0089769165004274, "grad_norm": 1.2677234947403453, "learning_rate": 1.1584974914966298e-05, "loss": 0.4411, "step": 7081 }, { "epoch": 1.0091194072385294, "grad_norm": 1.2738481525862042, "learning_rate": 1.1582519292055442e-05, "loss": 0.4527, "step": 7082 }, { "epoch": 1.0092618979766315, "grad_norm": 1.230034613051168, "learning_rate": 1.1580063571262208e-05, "loss": 0.3835, "step": 7083 }, { "epoch": 1.0094043887147335, "grad_norm": 1.7935756297960044, "learning_rate": 1.1577607752738485e-05, "loss": 0.4803, "step": 7084 }, { "epoch": 1.0095468794528355, "grad_norm": 1.2852045335686517, "learning_rate": 1.1575151836636167e-05, "loss": 0.4539, "step": 7085 }, { "epoch": 1.0096893701909375, "grad_norm": 1.2467163429959935, "learning_rate": 1.1572695823107167e-05, "loss": 0.4464, "step": 7086 }, { "epoch": 1.0098318609290395, "grad_norm": 1.3899791108685804, "learning_rate": 1.1570239712303388e-05, "loss": 0.4766, "step": 7087 }, { "epoch": 1.0099743516671416, "grad_norm": 1.1901072024516857, "learning_rate": 1.156778350437675e-05, "loss": 0.4166, "step": 7088 }, { "epoch": 1.0101168424052436, "grad_norm": 1.351094442881772, "learning_rate": 1.1565327199479173e-05, "loss": 0.4312, "step": 7089 }, { "epoch": 1.0102593331433456, "grad_norm": 1.6273742529614486, "learning_rate": 1.1562870797762584e-05, "loss": 0.4688, "step": 7090 }, { "epoch": 1.0104018238814476, "grad_norm": 1.3165539423798418, "learning_rate": 1.156041429937892e-05, "loss": 0.4444, "step": 7091 }, { "epoch": 1.0105443146195496, "grad_norm": 1.410721756786482, "learning_rate": 1.1557957704480117e-05, "loss": 0.4813, "step": 7092 }, { "epoch": 1.0106868053576517, "grad_norm": 1.363142017707758, "learning_rate": 1.1555501013218124e-05, "loss": 0.4187, "step": 7093 }, { "epoch": 1.0108292960957537, "grad_norm": 1.289139112224418, "learning_rate": 1.1553044225744893e-05, "loss": 0.4389, "step": 7094 }, { "epoch": 1.0109717868338557, "grad_norm": 1.3881632516416484, "learning_rate": 1.155058734221238e-05, "loss": 0.4734, "step": 7095 }, { "epoch": 1.011114277571958, "grad_norm": 1.240232873338853, "learning_rate": 1.154813036277255e-05, "loss": 0.4254, "step": 7096 }, { "epoch": 1.01125676831006, "grad_norm": 1.3872292444580334, "learning_rate": 1.1545673287577372e-05, "loss": 0.5056, "step": 7097 }, { "epoch": 1.011399259048162, "grad_norm": 1.254307023318639, "learning_rate": 1.1543216116778823e-05, "loss": 0.4101, "step": 7098 }, { "epoch": 1.011541749786264, "grad_norm": 1.3350954574070317, "learning_rate": 1.1540758850528879e-05, "loss": 0.4136, "step": 7099 }, { "epoch": 1.011684240524366, "grad_norm": 1.3154354168975453, "learning_rate": 1.1538301488979537e-05, "loss": 0.414, "step": 7100 }, { "epoch": 1.011826731262468, "grad_norm": 1.4173866953077228, "learning_rate": 1.1535844032282786e-05, "loss": 0.4195, "step": 7101 }, { "epoch": 1.01196922200057, "grad_norm": 1.3056324815966698, "learning_rate": 1.153338648059062e-05, "loss": 0.4346, "step": 7102 }, { "epoch": 1.012111712738672, "grad_norm": 1.276179234810891, "learning_rate": 1.1530928834055052e-05, "loss": 0.4068, "step": 7103 }, { "epoch": 1.012254203476774, "grad_norm": 1.314375639857281, "learning_rate": 1.1528471092828088e-05, "loss": 0.4287, "step": 7104 }, { "epoch": 1.012396694214876, "grad_norm": 1.4593091101785522, "learning_rate": 1.1526013257061748e-05, "loss": 0.485, "step": 7105 }, { "epoch": 1.0125391849529781, "grad_norm": 1.4074975299610073, "learning_rate": 1.1523555326908054e-05, "loss": 0.4775, "step": 7106 }, { "epoch": 1.0126816756910801, "grad_norm": 1.2898875801274623, "learning_rate": 1.1521097302519029e-05, "loss": 0.4151, "step": 7107 }, { "epoch": 1.0128241664291822, "grad_norm": 1.500099463774971, "learning_rate": 1.1518639184046716e-05, "loss": 0.5041, "step": 7108 }, { "epoch": 1.0129666571672842, "grad_norm": 1.3614686701539882, "learning_rate": 1.151618097164315e-05, "loss": 0.4312, "step": 7109 }, { "epoch": 1.0131091479053862, "grad_norm": 1.5088696203864365, "learning_rate": 1.1513722665460376e-05, "loss": 0.46, "step": 7110 }, { "epoch": 1.0132516386434882, "grad_norm": 1.2164081695727655, "learning_rate": 1.151126426565045e-05, "loss": 0.4122, "step": 7111 }, { "epoch": 1.0133941293815902, "grad_norm": 1.2882444775878978, "learning_rate": 1.1508805772365429e-05, "loss": 0.4258, "step": 7112 }, { "epoch": 1.0135366201196923, "grad_norm": 1.2758707003601517, "learning_rate": 1.1506347185757372e-05, "loss": 0.5109, "step": 7113 }, { "epoch": 1.0136791108577943, "grad_norm": 1.3123176727467096, "learning_rate": 1.1503888505978349e-05, "loss": 0.4516, "step": 7114 }, { "epoch": 1.0138216015958963, "grad_norm": 1.4084261939569724, "learning_rate": 1.1501429733180442e-05, "loss": 0.4562, "step": 7115 }, { "epoch": 1.0139640923339983, "grad_norm": 1.2432334715160713, "learning_rate": 1.1498970867515724e-05, "loss": 0.4172, "step": 7116 }, { "epoch": 1.0141065830721003, "grad_norm": 1.2071145307942999, "learning_rate": 1.1496511909136282e-05, "loss": 0.4032, "step": 7117 }, { "epoch": 1.0142490738102024, "grad_norm": 1.2326474518227701, "learning_rate": 1.1494052858194212e-05, "loss": 0.3838, "step": 7118 }, { "epoch": 1.0143915645483044, "grad_norm": 1.2331925849465943, "learning_rate": 1.1491593714841612e-05, "loss": 0.4481, "step": 7119 }, { "epoch": 1.0145340552864064, "grad_norm": 1.1734518535322425, "learning_rate": 1.1489134479230579e-05, "loss": 0.4448, "step": 7120 }, { "epoch": 1.0146765460245084, "grad_norm": 1.385997476904483, "learning_rate": 1.1486675151513225e-05, "loss": 0.4806, "step": 7121 }, { "epoch": 1.0148190367626104, "grad_norm": 1.4084600716714664, "learning_rate": 1.1484215731841668e-05, "loss": 0.4731, "step": 7122 }, { "epoch": 1.0149615275007124, "grad_norm": 1.4341531587353582, "learning_rate": 1.1481756220368032e-05, "loss": 0.4688, "step": 7123 }, { "epoch": 1.0151040182388145, "grad_norm": 1.365028467146126, "learning_rate": 1.1479296617244433e-05, "loss": 0.5101, "step": 7124 }, { "epoch": 1.0152465089769165, "grad_norm": 1.5268379811488053, "learning_rate": 1.1476836922623011e-05, "loss": 0.4196, "step": 7125 }, { "epoch": 1.0153889997150185, "grad_norm": 1.5330082990647964, "learning_rate": 1.1474377136655902e-05, "loss": 0.4823, "step": 7126 }, { "epoch": 1.0155314904531205, "grad_norm": 1.3147077626922599, "learning_rate": 1.1471917259495246e-05, "loss": 0.3898, "step": 7127 }, { "epoch": 1.0156739811912225, "grad_norm": 1.3042877696693709, "learning_rate": 1.1469457291293194e-05, "loss": 0.437, "step": 7128 }, { "epoch": 1.0158164719293246, "grad_norm": 1.4590036105564508, "learning_rate": 1.1466997232201901e-05, "loss": 0.4569, "step": 7129 }, { "epoch": 1.0159589626674266, "grad_norm": 1.349550379678877, "learning_rate": 1.146453708237353e-05, "loss": 0.4547, "step": 7130 }, { "epoch": 1.0161014534055286, "grad_norm": 1.246003908022959, "learning_rate": 1.146207684196024e-05, "loss": 0.4396, "step": 7131 }, { "epoch": 1.0162439441436306, "grad_norm": 1.3725137623733183, "learning_rate": 1.145961651111421e-05, "loss": 0.4758, "step": 7132 }, { "epoch": 1.0163864348817326, "grad_norm": 1.327074247991896, "learning_rate": 1.145715608998761e-05, "loss": 0.4593, "step": 7133 }, { "epoch": 1.0165289256198347, "grad_norm": 1.2979119769689011, "learning_rate": 1.145469557873263e-05, "loss": 0.4084, "step": 7134 }, { "epoch": 1.0166714163579367, "grad_norm": 1.3512491063077543, "learning_rate": 1.145223497750145e-05, "loss": 0.4266, "step": 7135 }, { "epoch": 1.0168139070960387, "grad_norm": 1.2862612977278056, "learning_rate": 1.1449774286446269e-05, "loss": 0.4511, "step": 7136 }, { "epoch": 1.0169563978341407, "grad_norm": 1.3197595963612851, "learning_rate": 1.1447313505719285e-05, "loss": 0.4587, "step": 7137 }, { "epoch": 1.0170988885722427, "grad_norm": 1.3430973357321279, "learning_rate": 1.1444852635472706e-05, "loss": 0.4062, "step": 7138 }, { "epoch": 1.0172413793103448, "grad_norm": 1.4117684980247072, "learning_rate": 1.1442391675858735e-05, "loss": 0.4746, "step": 7139 }, { "epoch": 1.0173838700484468, "grad_norm": 1.2014285457284364, "learning_rate": 1.1439930627029593e-05, "loss": 0.3821, "step": 7140 }, { "epoch": 1.0175263607865488, "grad_norm": 1.3410448984609182, "learning_rate": 1.14374694891375e-05, "loss": 0.5247, "step": 7141 }, { "epoch": 1.0176688515246508, "grad_norm": 1.6260239486795602, "learning_rate": 1.1435008262334686e-05, "loss": 0.5259, "step": 7142 }, { "epoch": 1.0178113422627528, "grad_norm": 1.3538998518521246, "learning_rate": 1.1432546946773378e-05, "loss": 0.4049, "step": 7143 }, { "epoch": 1.0179538330008548, "grad_norm": 1.2255427681129816, "learning_rate": 1.1430085542605818e-05, "loss": 0.4294, "step": 7144 }, { "epoch": 1.0180963237389569, "grad_norm": 1.393916916716138, "learning_rate": 1.1427624049984249e-05, "loss": 0.4468, "step": 7145 }, { "epoch": 1.0182388144770589, "grad_norm": 1.316641346388838, "learning_rate": 1.1425162469060918e-05, "loss": 0.4689, "step": 7146 }, { "epoch": 1.018381305215161, "grad_norm": 1.3307640426910856, "learning_rate": 1.142270079998808e-05, "loss": 0.4969, "step": 7147 }, { "epoch": 1.0185237959532631, "grad_norm": 1.3665251103449225, "learning_rate": 1.1420239042917995e-05, "loss": 0.451, "step": 7148 }, { "epoch": 1.0186662866913652, "grad_norm": 1.3225563329934684, "learning_rate": 1.1417777198002931e-05, "loss": 0.4064, "step": 7149 }, { "epoch": 1.0188087774294672, "grad_norm": 1.3409300723751072, "learning_rate": 1.1415315265395153e-05, "loss": 0.3969, "step": 7150 }, { "epoch": 1.0189512681675692, "grad_norm": 1.435498820869531, "learning_rate": 1.141285324524694e-05, "loss": 0.5215, "step": 7151 }, { "epoch": 1.0190937589056712, "grad_norm": 1.277338178936767, "learning_rate": 1.1410391137710576e-05, "loss": 0.4317, "step": 7152 }, { "epoch": 1.0192362496437732, "grad_norm": 1.391424891699956, "learning_rate": 1.1407928942938344e-05, "loss": 0.5039, "step": 7153 }, { "epoch": 1.0193787403818753, "grad_norm": 1.3886450705754305, "learning_rate": 1.1405466661082539e-05, "loss": 0.4572, "step": 7154 }, { "epoch": 1.0195212311199773, "grad_norm": 1.185819423279474, "learning_rate": 1.1403004292295454e-05, "loss": 0.3847, "step": 7155 }, { "epoch": 1.0196637218580793, "grad_norm": 1.3370736059971424, "learning_rate": 1.1400541836729397e-05, "loss": 0.4533, "step": 7156 }, { "epoch": 1.0198062125961813, "grad_norm": 1.3486062290218448, "learning_rate": 1.1398079294536677e-05, "loss": 0.4684, "step": 7157 }, { "epoch": 1.0199487033342833, "grad_norm": 1.2098391228054652, "learning_rate": 1.1395616665869602e-05, "loss": 0.4006, "step": 7158 }, { "epoch": 1.0200911940723854, "grad_norm": 1.3187193161724777, "learning_rate": 1.1393153950880497e-05, "loss": 0.4966, "step": 7159 }, { "epoch": 1.0202336848104874, "grad_norm": 1.3029392835180995, "learning_rate": 1.1390691149721687e-05, "loss": 0.4245, "step": 7160 }, { "epoch": 1.0203761755485894, "grad_norm": 1.4207012093302, "learning_rate": 1.1388228262545496e-05, "loss": 0.4595, "step": 7161 }, { "epoch": 1.0205186662866914, "grad_norm": 1.215946246411547, "learning_rate": 1.138576528950426e-05, "loss": 0.4258, "step": 7162 }, { "epoch": 1.0206611570247934, "grad_norm": 1.2838346928279016, "learning_rate": 1.1383302230750324e-05, "loss": 0.4461, "step": 7163 }, { "epoch": 1.0208036477628954, "grad_norm": 1.3904460759163788, "learning_rate": 1.1380839086436032e-05, "loss": 0.4252, "step": 7164 }, { "epoch": 1.0209461385009975, "grad_norm": 1.4856985087845698, "learning_rate": 1.1378375856713732e-05, "loss": 0.4555, "step": 7165 }, { "epoch": 1.0210886292390995, "grad_norm": 1.391964924588095, "learning_rate": 1.1375912541735785e-05, "loss": 0.4283, "step": 7166 }, { "epoch": 1.0212311199772015, "grad_norm": 1.5013722104155804, "learning_rate": 1.1373449141654552e-05, "loss": 0.4797, "step": 7167 }, { "epoch": 1.0213736107153035, "grad_norm": 1.214163558832294, "learning_rate": 1.1370985656622393e-05, "loss": 0.4378, "step": 7168 }, { "epoch": 1.0215161014534055, "grad_norm": 1.4576987564735269, "learning_rate": 1.1368522086791688e-05, "loss": 0.4505, "step": 7169 }, { "epoch": 1.0216585921915076, "grad_norm": 1.339845325606919, "learning_rate": 1.1366058432314811e-05, "loss": 0.4419, "step": 7170 }, { "epoch": 1.0218010829296096, "grad_norm": 1.2235506809715315, "learning_rate": 1.1363594693344146e-05, "loss": 0.4405, "step": 7171 }, { "epoch": 1.0219435736677116, "grad_norm": 1.3077422546710413, "learning_rate": 1.1361130870032078e-05, "loss": 0.3954, "step": 7172 }, { "epoch": 1.0220860644058136, "grad_norm": 1.2844241926034672, "learning_rate": 1.1358666962531003e-05, "loss": 0.4353, "step": 7173 }, { "epoch": 1.0222285551439156, "grad_norm": 1.4345504149500796, "learning_rate": 1.1356202970993317e-05, "loss": 0.4577, "step": 7174 }, { "epoch": 1.0223710458820177, "grad_norm": 1.357540288918549, "learning_rate": 1.1353738895571427e-05, "loss": 0.4578, "step": 7175 }, { "epoch": 1.0225135366201197, "grad_norm": 1.2904395143291538, "learning_rate": 1.1351274736417737e-05, "loss": 0.4515, "step": 7176 }, { "epoch": 1.0226560273582217, "grad_norm": 1.456350995794641, "learning_rate": 1.1348810493684664e-05, "loss": 0.4951, "step": 7177 }, { "epoch": 1.0227985180963237, "grad_norm": 1.4495117801921462, "learning_rate": 1.1346346167524624e-05, "loss": 0.4492, "step": 7178 }, { "epoch": 1.0229410088344257, "grad_norm": 1.4020589153139198, "learning_rate": 1.1343881758090046e-05, "loss": 0.419, "step": 7179 }, { "epoch": 1.0230834995725278, "grad_norm": 1.3845158586621713, "learning_rate": 1.1341417265533353e-05, "loss": 0.4569, "step": 7180 }, { "epoch": 1.0232259903106298, "grad_norm": 1.293394414575806, "learning_rate": 1.1338952690006984e-05, "loss": 0.4699, "step": 7181 }, { "epoch": 1.0233684810487318, "grad_norm": 1.253291526422326, "learning_rate": 1.133648803166338e-05, "loss": 0.4496, "step": 7182 }, { "epoch": 1.0235109717868338, "grad_norm": 1.8091892470371116, "learning_rate": 1.1334023290654978e-05, "loss": 0.4093, "step": 7183 }, { "epoch": 1.0236534625249358, "grad_norm": 1.2656749084146206, "learning_rate": 1.1331558467134236e-05, "loss": 0.4025, "step": 7184 }, { "epoch": 1.0237959532630379, "grad_norm": 1.400667692758108, "learning_rate": 1.1329093561253603e-05, "loss": 0.469, "step": 7185 }, { "epoch": 1.0239384440011399, "grad_norm": 1.3166634928758572, "learning_rate": 1.1326628573165546e-05, "loss": 0.3768, "step": 7186 }, { "epoch": 1.0240809347392419, "grad_norm": 1.3969878238855236, "learning_rate": 1.1324163503022521e-05, "loss": 0.4397, "step": 7187 }, { "epoch": 1.024223425477344, "grad_norm": 1.4199949418025546, "learning_rate": 1.1321698350977004e-05, "loss": 0.5051, "step": 7188 }, { "epoch": 1.024365916215446, "grad_norm": 1.303823244104154, "learning_rate": 1.1319233117181469e-05, "loss": 0.4315, "step": 7189 }, { "epoch": 1.024508406953548, "grad_norm": 1.4692947217420704, "learning_rate": 1.1316767801788399e-05, "loss": 0.4427, "step": 7190 }, { "epoch": 1.02465089769165, "grad_norm": 1.4070455034440144, "learning_rate": 1.1314302404950272e-05, "loss": 0.3984, "step": 7191 }, { "epoch": 1.024793388429752, "grad_norm": 1.280376816517104, "learning_rate": 1.1311836926819586e-05, "loss": 0.4095, "step": 7192 }, { "epoch": 1.024935879167854, "grad_norm": 1.2862149461765515, "learning_rate": 1.1309371367548832e-05, "loss": 0.4597, "step": 7193 }, { "epoch": 1.025078369905956, "grad_norm": 1.3506600768490704, "learning_rate": 1.1306905727290512e-05, "loss": 0.4657, "step": 7194 }, { "epoch": 1.025220860644058, "grad_norm": 1.4042579415720013, "learning_rate": 1.1304440006197131e-05, "loss": 0.4578, "step": 7195 }, { "epoch": 1.02536335138216, "grad_norm": 1.244802658409797, "learning_rate": 1.1301974204421199e-05, "loss": 0.4104, "step": 7196 }, { "epoch": 1.025505842120262, "grad_norm": 1.4484715574877605, "learning_rate": 1.1299508322115233e-05, "loss": 0.4499, "step": 7197 }, { "epoch": 1.025648332858364, "grad_norm": 1.31302648977394, "learning_rate": 1.1297042359431752e-05, "loss": 0.4229, "step": 7198 }, { "epoch": 1.0257908235964663, "grad_norm": 1.295271972556249, "learning_rate": 1.129457631652328e-05, "loss": 0.4433, "step": 7199 }, { "epoch": 1.0259333143345684, "grad_norm": 3.266987412094393, "learning_rate": 1.129211019354235e-05, "loss": 0.4403, "step": 7200 }, { "epoch": 1.0260758050726704, "grad_norm": 1.313401924317741, "learning_rate": 1.1289643990641495e-05, "loss": 0.4546, "step": 7201 }, { "epoch": 1.0262182958107724, "grad_norm": 1.8510932838545011, "learning_rate": 1.1287177707973256e-05, "loss": 0.4616, "step": 7202 }, { "epoch": 1.0263607865488744, "grad_norm": 1.3180372593051115, "learning_rate": 1.1284711345690177e-05, "loss": 0.4313, "step": 7203 }, { "epoch": 1.0265032772869764, "grad_norm": 1.3104475883205429, "learning_rate": 1.1282244903944814e-05, "loss": 0.4391, "step": 7204 }, { "epoch": 1.0266457680250785, "grad_norm": 1.3345016252222703, "learning_rate": 1.1279778382889717e-05, "loss": 0.444, "step": 7205 }, { "epoch": 1.0267882587631805, "grad_norm": 1.2778187889772652, "learning_rate": 1.1277311782677442e-05, "loss": 0.4565, "step": 7206 }, { "epoch": 1.0269307495012825, "grad_norm": 1.3702177540509315, "learning_rate": 1.127484510346056e-05, "loss": 0.4618, "step": 7207 }, { "epoch": 1.0270732402393845, "grad_norm": 1.3665726464205712, "learning_rate": 1.1272378345391642e-05, "loss": 0.46, "step": 7208 }, { "epoch": 1.0272157309774865, "grad_norm": 1.3569599373485448, "learning_rate": 1.1269911508623255e-05, "loss": 0.4473, "step": 7209 }, { "epoch": 1.0273582217155885, "grad_norm": 1.406975154785442, "learning_rate": 1.1267444593307984e-05, "loss": 0.4655, "step": 7210 }, { "epoch": 1.0275007124536906, "grad_norm": 1.3081959670764853, "learning_rate": 1.1264977599598413e-05, "loss": 0.5016, "step": 7211 }, { "epoch": 1.0276432031917926, "grad_norm": 1.2664874488654458, "learning_rate": 1.126251052764713e-05, "loss": 0.4019, "step": 7212 }, { "epoch": 1.0277856939298946, "grad_norm": 1.3386643679422383, "learning_rate": 1.1260043377606729e-05, "loss": 0.4481, "step": 7213 }, { "epoch": 1.0279281846679966, "grad_norm": 1.3742224594710695, "learning_rate": 1.1257576149629808e-05, "loss": 0.4743, "step": 7214 }, { "epoch": 1.0280706754060986, "grad_norm": 1.2430950284340447, "learning_rate": 1.1255108843868971e-05, "loss": 0.3708, "step": 7215 }, { "epoch": 1.0282131661442007, "grad_norm": 1.4265045073982614, "learning_rate": 1.1252641460476828e-05, "loss": 0.4747, "step": 7216 }, { "epoch": 1.0283556568823027, "grad_norm": 1.4511743795105183, "learning_rate": 1.1250173999605989e-05, "loss": 0.4554, "step": 7217 }, { "epoch": 1.0284981476204047, "grad_norm": 1.3924862350937497, "learning_rate": 1.1247706461409076e-05, "loss": 0.4339, "step": 7218 }, { "epoch": 1.0286406383585067, "grad_norm": 1.2369349539578518, "learning_rate": 1.1245238846038711e-05, "loss": 0.418, "step": 7219 }, { "epoch": 1.0287831290966087, "grad_norm": 1.672582392321571, "learning_rate": 1.1242771153647519e-05, "loss": 0.4609, "step": 7220 }, { "epoch": 1.0289256198347108, "grad_norm": 1.3735318126810447, "learning_rate": 1.1240303384388134e-05, "loss": 0.431, "step": 7221 }, { "epoch": 1.0290681105728128, "grad_norm": 1.315114023720362, "learning_rate": 1.1237835538413191e-05, "loss": 0.4367, "step": 7222 }, { "epoch": 1.0292106013109148, "grad_norm": 5.347938511786345, "learning_rate": 1.1235367615875337e-05, "loss": 0.4368, "step": 7223 }, { "epoch": 1.0293530920490168, "grad_norm": 1.4051984073440205, "learning_rate": 1.123289961692721e-05, "loss": 0.4496, "step": 7224 }, { "epoch": 1.0294955827871188, "grad_norm": 1.2995689693932824, "learning_rate": 1.1230431541721471e-05, "loss": 0.4087, "step": 7225 }, { "epoch": 1.0296380735252209, "grad_norm": 1.4270107864831163, "learning_rate": 1.122796339041077e-05, "loss": 0.4178, "step": 7226 }, { "epoch": 1.0297805642633229, "grad_norm": 1.3645915895097858, "learning_rate": 1.1225495163147772e-05, "loss": 0.4005, "step": 7227 }, { "epoch": 1.029923055001425, "grad_norm": 1.2337569062355829, "learning_rate": 1.1223026860085137e-05, "loss": 0.3724, "step": 7228 }, { "epoch": 1.030065545739527, "grad_norm": 1.3773462298387906, "learning_rate": 1.1220558481375538e-05, "loss": 0.4469, "step": 7229 }, { "epoch": 1.030208036477629, "grad_norm": 1.5325637685559865, "learning_rate": 1.121809002717165e-05, "loss": 0.4075, "step": 7230 }, { "epoch": 1.030350527215731, "grad_norm": 1.5914168953176513, "learning_rate": 1.121562149762615e-05, "loss": 0.4476, "step": 7231 }, { "epoch": 1.030493017953833, "grad_norm": 1.5508440698161672, "learning_rate": 1.1213152892891726e-05, "loss": 0.4776, "step": 7232 }, { "epoch": 1.030635508691935, "grad_norm": 1.335346542855174, "learning_rate": 1.1210684213121064e-05, "loss": 0.4502, "step": 7233 }, { "epoch": 1.030777999430037, "grad_norm": 1.3790907003846968, "learning_rate": 1.120821545846686e-05, "loss": 0.4603, "step": 7234 }, { "epoch": 1.030920490168139, "grad_norm": 1.3579742018496235, "learning_rate": 1.1205746629081811e-05, "loss": 0.4356, "step": 7235 }, { "epoch": 1.031062980906241, "grad_norm": 1.2211887760852882, "learning_rate": 1.1203277725118615e-05, "loss": 0.4325, "step": 7236 }, { "epoch": 1.031205471644343, "grad_norm": 1.4400502560369073, "learning_rate": 1.1200808746729985e-05, "loss": 0.38, "step": 7237 }, { "epoch": 1.031347962382445, "grad_norm": 1.5420988750510192, "learning_rate": 1.1198339694068632e-05, "loss": 0.4862, "step": 7238 }, { "epoch": 1.031490453120547, "grad_norm": 1.594582103207134, "learning_rate": 1.119587056728727e-05, "loss": 0.4676, "step": 7239 }, { "epoch": 1.0316329438586491, "grad_norm": 1.1845934858876979, "learning_rate": 1.1193401366538624e-05, "loss": 0.3897, "step": 7240 }, { "epoch": 1.0317754345967511, "grad_norm": 1.2606263545711243, "learning_rate": 1.1190932091975412e-05, "loss": 0.373, "step": 7241 }, { "epoch": 1.0319179253348532, "grad_norm": 1.6359629912139326, "learning_rate": 1.1188462743750377e-05, "loss": 0.4746, "step": 7242 }, { "epoch": 1.0320604160729552, "grad_norm": 1.2009196059444034, "learning_rate": 1.1185993322016241e-05, "loss": 0.3938, "step": 7243 }, { "epoch": 1.0322029068110572, "grad_norm": 1.4362051603499628, "learning_rate": 1.1183523826925749e-05, "loss": 0.5089, "step": 7244 }, { "epoch": 1.0323453975491592, "grad_norm": 1.4844811406016716, "learning_rate": 1.1181054258631645e-05, "loss": 0.4167, "step": 7245 }, { "epoch": 1.0324878882872612, "grad_norm": 1.3836538317396436, "learning_rate": 1.1178584617286676e-05, "loss": 0.4058, "step": 7246 }, { "epoch": 1.0326303790253633, "grad_norm": 1.3510333974765798, "learning_rate": 1.1176114903043595e-05, "loss": 0.4409, "step": 7247 }, { "epoch": 1.0327728697634653, "grad_norm": 1.3796298149811357, "learning_rate": 1.1173645116055161e-05, "loss": 0.4419, "step": 7248 }, { "epoch": 1.0329153605015673, "grad_norm": 1.468684032372082, "learning_rate": 1.1171175256474137e-05, "loss": 0.4138, "step": 7249 }, { "epoch": 1.0330578512396693, "grad_norm": 1.4225043186130355, "learning_rate": 1.1168705324453284e-05, "loss": 0.429, "step": 7250 }, { "epoch": 1.0332003419777713, "grad_norm": 1.3904928699934342, "learning_rate": 1.1166235320145378e-05, "loss": 0.4854, "step": 7251 }, { "epoch": 1.0333428327158736, "grad_norm": 1.3604219729750242, "learning_rate": 1.116376524370319e-05, "loss": 0.4223, "step": 7252 }, { "epoch": 1.0334853234539756, "grad_norm": 1.3680173452946853, "learning_rate": 1.1161295095279503e-05, "loss": 0.4083, "step": 7253 }, { "epoch": 1.0336278141920776, "grad_norm": 1.570510958392698, "learning_rate": 1.1158824875027101e-05, "loss": 0.4542, "step": 7254 }, { "epoch": 1.0337703049301796, "grad_norm": 1.224636668030431, "learning_rate": 1.115635458309877e-05, "loss": 0.4327, "step": 7255 }, { "epoch": 1.0339127956682816, "grad_norm": 1.3155867924331588, "learning_rate": 1.1153884219647308e-05, "loss": 0.4762, "step": 7256 }, { "epoch": 1.0340552864063837, "grad_norm": 2.0082278132981313, "learning_rate": 1.115141378482551e-05, "loss": 0.4286, "step": 7257 }, { "epoch": 1.0341977771444857, "grad_norm": 1.4037738420827515, "learning_rate": 1.1148943278786175e-05, "loss": 0.4544, "step": 7258 }, { "epoch": 1.0343402678825877, "grad_norm": 1.405916545728382, "learning_rate": 1.1146472701682111e-05, "loss": 0.4317, "step": 7259 }, { "epoch": 1.0344827586206897, "grad_norm": 1.6202282417105403, "learning_rate": 1.1144002053666135e-05, "loss": 0.5256, "step": 7260 }, { "epoch": 1.0346252493587917, "grad_norm": 1.3706412815520619, "learning_rate": 1.1141531334891054e-05, "loss": 0.4081, "step": 7261 }, { "epoch": 1.0347677400968938, "grad_norm": 1.3706030692417033, "learning_rate": 1.1139060545509688e-05, "loss": 0.4828, "step": 7262 }, { "epoch": 1.0349102308349958, "grad_norm": 1.4752623411297636, "learning_rate": 1.1136589685674866e-05, "loss": 0.434, "step": 7263 }, { "epoch": 1.0350527215730978, "grad_norm": 1.3817460170006222, "learning_rate": 1.1134118755539416e-05, "loss": 0.4504, "step": 7264 }, { "epoch": 1.0351952123111998, "grad_norm": 1.2807089337429025, "learning_rate": 1.1131647755256162e-05, "loss": 0.4369, "step": 7265 }, { "epoch": 1.0353377030493018, "grad_norm": 1.3488583323626193, "learning_rate": 1.1129176684977951e-05, "loss": 0.4579, "step": 7266 }, { "epoch": 1.0354801937874039, "grad_norm": 1.384558054772714, "learning_rate": 1.1126705544857621e-05, "loss": 0.4784, "step": 7267 }, { "epoch": 1.0356226845255059, "grad_norm": 1.4443841163499316, "learning_rate": 1.1124234335048015e-05, "loss": 0.4663, "step": 7268 }, { "epoch": 1.035765175263608, "grad_norm": 2.1892492578864453, "learning_rate": 1.1121763055701984e-05, "loss": 0.4166, "step": 7269 }, { "epoch": 1.03590766600171, "grad_norm": 1.3365018254268883, "learning_rate": 1.1119291706972386e-05, "loss": 0.4428, "step": 7270 }, { "epoch": 1.036050156739812, "grad_norm": 1.2166465261236286, "learning_rate": 1.1116820289012076e-05, "loss": 0.3818, "step": 7271 }, { "epoch": 1.036192647477914, "grad_norm": 1.554842438935543, "learning_rate": 1.1114348801973916e-05, "loss": 0.493, "step": 7272 }, { "epoch": 1.036335138216016, "grad_norm": 1.2971023942568665, "learning_rate": 1.1111877246010774e-05, "loss": 0.3899, "step": 7273 }, { "epoch": 1.036477628954118, "grad_norm": 1.39674763652604, "learning_rate": 1.110940562127552e-05, "loss": 0.4406, "step": 7274 }, { "epoch": 1.03662011969222, "grad_norm": 1.2807540027928184, "learning_rate": 1.1106933927921033e-05, "loss": 0.4159, "step": 7275 }, { "epoch": 1.036762610430322, "grad_norm": 1.3210054315467437, "learning_rate": 1.1104462166100192e-05, "loss": 0.4361, "step": 7276 }, { "epoch": 1.036905101168424, "grad_norm": 1.339133584181976, "learning_rate": 1.1101990335965878e-05, "loss": 0.5043, "step": 7277 }, { "epoch": 1.037047591906526, "grad_norm": 1.3354613188019762, "learning_rate": 1.1099518437670982e-05, "loss": 0.4288, "step": 7278 }, { "epoch": 1.037190082644628, "grad_norm": 1.3564272225384482, "learning_rate": 1.1097046471368399e-05, "loss": 0.5023, "step": 7279 }, { "epoch": 1.03733257338273, "grad_norm": 1.3699053841779327, "learning_rate": 1.1094574437211019e-05, "loss": 0.4131, "step": 7280 }, { "epoch": 1.0374750641208321, "grad_norm": 1.4491779862895193, "learning_rate": 1.1092102335351742e-05, "loss": 0.4713, "step": 7281 }, { "epoch": 1.0376175548589341, "grad_norm": 1.3395679086865704, "learning_rate": 1.1089630165943483e-05, "loss": 0.4461, "step": 7282 }, { "epoch": 1.0377600455970362, "grad_norm": 1.4870699462493209, "learning_rate": 1.1087157929139144e-05, "loss": 0.437, "step": 7283 }, { "epoch": 1.0379025363351382, "grad_norm": 1.3435828903398774, "learning_rate": 1.1084685625091643e-05, "loss": 0.4444, "step": 7284 }, { "epoch": 1.0380450270732402, "grad_norm": 1.2005771900176916, "learning_rate": 1.108221325395389e-05, "loss": 0.3729, "step": 7285 }, { "epoch": 1.0381875178113422, "grad_norm": 1.3780849864305587, "learning_rate": 1.1079740815878814e-05, "loss": 0.4528, "step": 7286 }, { "epoch": 1.0383300085494442, "grad_norm": 1.2544855942775748, "learning_rate": 1.1077268311019338e-05, "loss": 0.4036, "step": 7287 }, { "epoch": 1.0384724992875463, "grad_norm": 1.4283730249038038, "learning_rate": 1.107479573952839e-05, "loss": 0.4996, "step": 7288 }, { "epoch": 1.0386149900256483, "grad_norm": 1.2180021466255082, "learning_rate": 1.1072323101558908e-05, "loss": 0.3467, "step": 7289 }, { "epoch": 1.0387574807637503, "grad_norm": 1.4801023851561448, "learning_rate": 1.1069850397263828e-05, "loss": 0.487, "step": 7290 }, { "epoch": 1.0388999715018523, "grad_norm": 1.3419534879279829, "learning_rate": 1.1067377626796092e-05, "loss": 0.4113, "step": 7291 }, { "epoch": 1.0390424622399543, "grad_norm": 1.2940145454348144, "learning_rate": 1.1064904790308649e-05, "loss": 0.4493, "step": 7292 }, { "epoch": 1.0391849529780564, "grad_norm": 1.3692380632012355, "learning_rate": 1.1062431887954446e-05, "loss": 0.4115, "step": 7293 }, { "epoch": 1.0393274437161584, "grad_norm": 1.3074943541354003, "learning_rate": 1.105995891988644e-05, "loss": 0.433, "step": 7294 }, { "epoch": 1.0394699344542604, "grad_norm": 1.4816129915588037, "learning_rate": 1.1057485886257589e-05, "loss": 0.4989, "step": 7295 }, { "epoch": 1.0396124251923624, "grad_norm": 1.3165939769833779, "learning_rate": 1.1055012787220854e-05, "loss": 0.4454, "step": 7296 }, { "epoch": 1.0397549159304644, "grad_norm": 1.450702116529721, "learning_rate": 1.1052539622929207e-05, "loss": 0.5521, "step": 7297 }, { "epoch": 1.0398974066685664, "grad_norm": 1.3528017053348398, "learning_rate": 1.105006639353561e-05, "loss": 0.4184, "step": 7298 }, { "epoch": 1.0400398974066685, "grad_norm": 1.4723643157951951, "learning_rate": 1.1047593099193045e-05, "loss": 0.4368, "step": 7299 }, { "epoch": 1.0401823881447705, "grad_norm": 1.2917107161378087, "learning_rate": 1.1045119740054491e-05, "loss": 0.4252, "step": 7300 }, { "epoch": 1.0403248788828725, "grad_norm": 1.402079832832335, "learning_rate": 1.104264631627293e-05, "loss": 0.3891, "step": 7301 }, { "epoch": 1.0404673696209747, "grad_norm": 1.4014262996534899, "learning_rate": 1.1040172828001343e-05, "loss": 0.4734, "step": 7302 }, { "epoch": 1.0406098603590768, "grad_norm": 1.5580964709023142, "learning_rate": 1.1037699275392724e-05, "loss": 0.4863, "step": 7303 }, { "epoch": 1.0407523510971788, "grad_norm": 1.2737927134627467, "learning_rate": 1.1035225658600072e-05, "loss": 0.4233, "step": 7304 }, { "epoch": 1.0408948418352808, "grad_norm": 1.320504141278187, "learning_rate": 1.1032751977776384e-05, "loss": 0.4228, "step": 7305 }, { "epoch": 1.0410373325733828, "grad_norm": 1.289058993331335, "learning_rate": 1.1030278233074658e-05, "loss": 0.3543, "step": 7306 }, { "epoch": 1.0411798233114848, "grad_norm": 1.4032217947475194, "learning_rate": 1.1027804424647907e-05, "loss": 0.4466, "step": 7307 }, { "epoch": 1.0413223140495869, "grad_norm": 1.422148401424519, "learning_rate": 1.102533055264914e-05, "loss": 0.4658, "step": 7308 }, { "epoch": 1.0414648047876889, "grad_norm": 1.3762233865118672, "learning_rate": 1.1022856617231367e-05, "loss": 0.4715, "step": 7309 }, { "epoch": 1.041607295525791, "grad_norm": 1.3860286165455689, "learning_rate": 1.102038261854761e-05, "loss": 0.4892, "step": 7310 }, { "epoch": 1.041749786263893, "grad_norm": 1.4987952189984568, "learning_rate": 1.101790855675089e-05, "loss": 0.4191, "step": 7311 }, { "epoch": 1.041892277001995, "grad_norm": 1.4920114181617812, "learning_rate": 1.1015434431994241e-05, "loss": 0.5106, "step": 7312 }, { "epoch": 1.042034767740097, "grad_norm": 1.294761556734052, "learning_rate": 1.1012960244430681e-05, "loss": 0.4225, "step": 7313 }, { "epoch": 1.042177258478199, "grad_norm": 1.476053037351435, "learning_rate": 1.1010485994213253e-05, "loss": 0.4495, "step": 7314 }, { "epoch": 1.042319749216301, "grad_norm": 1.3063429328205294, "learning_rate": 1.100801168149499e-05, "loss": 0.3957, "step": 7315 }, { "epoch": 1.042462239954403, "grad_norm": 1.3857509069850948, "learning_rate": 1.1005537306428937e-05, "loss": 0.4463, "step": 7316 }, { "epoch": 1.042604730692505, "grad_norm": 1.3652992686949623, "learning_rate": 1.1003062869168138e-05, "loss": 0.4351, "step": 7317 }, { "epoch": 1.042747221430607, "grad_norm": 1.4825679541291157, "learning_rate": 1.1000588369865639e-05, "loss": 0.5056, "step": 7318 }, { "epoch": 1.042889712168709, "grad_norm": 1.3123969478097088, "learning_rate": 1.0998113808674499e-05, "loss": 0.4582, "step": 7319 }, { "epoch": 1.043032202906811, "grad_norm": 1.3882076059793145, "learning_rate": 1.0995639185747775e-05, "loss": 0.4047, "step": 7320 }, { "epoch": 1.043174693644913, "grad_norm": 1.200248310093673, "learning_rate": 1.0993164501238524e-05, "loss": 0.4116, "step": 7321 }, { "epoch": 1.0433171843830151, "grad_norm": 1.3126291819410276, "learning_rate": 1.0990689755299816e-05, "loss": 0.4818, "step": 7322 }, { "epoch": 1.0434596751211171, "grad_norm": 1.4009928772712492, "learning_rate": 1.0988214948084717e-05, "loss": 0.437, "step": 7323 }, { "epoch": 1.0436021658592192, "grad_norm": 1.4570612850378635, "learning_rate": 1.0985740079746297e-05, "loss": 0.4502, "step": 7324 }, { "epoch": 1.0437446565973212, "grad_norm": 1.428906332681528, "learning_rate": 1.098326515043763e-05, "loss": 0.4659, "step": 7325 }, { "epoch": 1.0438871473354232, "grad_norm": 1.4556812633522753, "learning_rate": 1.0980790160311805e-05, "loss": 0.4849, "step": 7326 }, { "epoch": 1.0440296380735252, "grad_norm": 1.5805219391758996, "learning_rate": 1.0978315109521903e-05, "loss": 0.5077, "step": 7327 }, { "epoch": 1.0441721288116272, "grad_norm": 1.416801574461032, "learning_rate": 1.0975839998221006e-05, "loss": 0.4093, "step": 7328 }, { "epoch": 1.0443146195497293, "grad_norm": 2.1453488734552346, "learning_rate": 1.0973364826562208e-05, "loss": 0.4405, "step": 7329 }, { "epoch": 1.0444571102878313, "grad_norm": 1.3903741886952685, "learning_rate": 1.0970889594698605e-05, "loss": 0.41, "step": 7330 }, { "epoch": 1.0445996010259333, "grad_norm": 1.4388733620085774, "learning_rate": 1.0968414302783299e-05, "loss": 0.4432, "step": 7331 }, { "epoch": 1.0447420917640353, "grad_norm": 1.3957865564933305, "learning_rate": 1.0965938950969382e-05, "loss": 0.4491, "step": 7332 }, { "epoch": 1.0448845825021373, "grad_norm": 1.597598637315175, "learning_rate": 1.096346353940997e-05, "loss": 0.4689, "step": 7333 }, { "epoch": 1.0450270732402394, "grad_norm": 1.391596593609071, "learning_rate": 1.0960988068258171e-05, "loss": 0.4373, "step": 7334 }, { "epoch": 1.0451695639783414, "grad_norm": 1.4396411991058597, "learning_rate": 1.0958512537667094e-05, "loss": 0.4371, "step": 7335 }, { "epoch": 1.0453120547164434, "grad_norm": 1.4444691001007293, "learning_rate": 1.0956036947789861e-05, "loss": 0.5037, "step": 7336 }, { "epoch": 1.0454545454545454, "grad_norm": 1.4379875126606854, "learning_rate": 1.095356129877959e-05, "loss": 0.4429, "step": 7337 }, { "epoch": 1.0455970361926474, "grad_norm": 1.4110112152004928, "learning_rate": 1.0951085590789407e-05, "loss": 0.4888, "step": 7338 }, { "epoch": 1.0457395269307495, "grad_norm": 2.0091093619809848, "learning_rate": 1.0948609823972436e-05, "loss": 0.4434, "step": 7339 }, { "epoch": 1.0458820176688515, "grad_norm": 1.41946298947914, "learning_rate": 1.0946133998481815e-05, "loss": 0.4616, "step": 7340 }, { "epoch": 1.0460245084069535, "grad_norm": 1.56476890530508, "learning_rate": 1.0943658114470679e-05, "loss": 0.5168, "step": 7341 }, { "epoch": 1.0461669991450555, "grad_norm": 1.411353535963786, "learning_rate": 1.0941182172092162e-05, "loss": 0.495, "step": 7342 }, { "epoch": 1.0463094898831575, "grad_norm": 1.2992629884785016, "learning_rate": 1.0938706171499407e-05, "loss": 0.5161, "step": 7343 }, { "epoch": 1.0464519806212595, "grad_norm": 1.5078603759219558, "learning_rate": 1.0936230112845565e-05, "loss": 0.4568, "step": 7344 }, { "epoch": 1.0465944713593616, "grad_norm": 1.2135213434420051, "learning_rate": 1.0933753996283783e-05, "loss": 0.4186, "step": 7345 }, { "epoch": 1.0467369620974636, "grad_norm": 1.2178580651894553, "learning_rate": 1.0931277821967215e-05, "loss": 0.422, "step": 7346 }, { "epoch": 1.0468794528355656, "grad_norm": 1.295969374359755, "learning_rate": 1.0928801590049015e-05, "loss": 0.4226, "step": 7347 }, { "epoch": 1.0470219435736676, "grad_norm": 1.322105152259166, "learning_rate": 1.0926325300682345e-05, "loss": 0.4722, "step": 7348 }, { "epoch": 1.0471644343117696, "grad_norm": 1.2389090985275037, "learning_rate": 1.0923848954020374e-05, "loss": 0.4516, "step": 7349 }, { "epoch": 1.0473069250498717, "grad_norm": 1.2636016261263152, "learning_rate": 1.0921372550216265e-05, "loss": 0.4301, "step": 7350 }, { "epoch": 1.0474494157879737, "grad_norm": 2.476178345341996, "learning_rate": 1.0918896089423188e-05, "loss": 0.4582, "step": 7351 }, { "epoch": 1.0475919065260757, "grad_norm": 1.2676377031866544, "learning_rate": 1.091641957179432e-05, "loss": 0.4599, "step": 7352 }, { "epoch": 1.0477343972641777, "grad_norm": 1.3593159663238645, "learning_rate": 1.091394299748284e-05, "loss": 0.4294, "step": 7353 }, { "epoch": 1.0478768880022797, "grad_norm": 1.6464722369967923, "learning_rate": 1.0911466366641927e-05, "loss": 0.5074, "step": 7354 }, { "epoch": 1.048019378740382, "grad_norm": 1.5264426320565632, "learning_rate": 1.0908989679424766e-05, "loss": 0.4591, "step": 7355 }, { "epoch": 1.048161869478484, "grad_norm": 1.6193782586600873, "learning_rate": 1.0906512935984552e-05, "loss": 0.4357, "step": 7356 }, { "epoch": 1.048304360216586, "grad_norm": 1.1946142775440352, "learning_rate": 1.090403613647447e-05, "loss": 0.3777, "step": 7357 }, { "epoch": 1.048446850954688, "grad_norm": 1.4018377494575005, "learning_rate": 1.0901559281047718e-05, "loss": 0.4476, "step": 7358 }, { "epoch": 1.04858934169279, "grad_norm": 1.4439536064356011, "learning_rate": 1.0899082369857495e-05, "loss": 0.4013, "step": 7359 }, { "epoch": 1.048731832430892, "grad_norm": 1.2586971074054467, "learning_rate": 1.0896605403057003e-05, "loss": 0.4272, "step": 7360 }, { "epoch": 1.048874323168994, "grad_norm": 1.3353597170048817, "learning_rate": 1.0894128380799446e-05, "loss": 0.3657, "step": 7361 }, { "epoch": 1.0490168139070961, "grad_norm": 1.4103389018008186, "learning_rate": 1.089165130323804e-05, "loss": 0.4772, "step": 7362 }, { "epoch": 1.0491593046451981, "grad_norm": 1.4214822277011139, "learning_rate": 1.0889174170525994e-05, "loss": 0.4379, "step": 7363 }, { "epoch": 1.0493017953833002, "grad_norm": 1.6020837066814446, "learning_rate": 1.0886696982816524e-05, "loss": 0.4084, "step": 7364 }, { "epoch": 1.0494442861214022, "grad_norm": 1.2565500896349013, "learning_rate": 1.0884219740262849e-05, "loss": 0.4597, "step": 7365 }, { "epoch": 1.0495867768595042, "grad_norm": 1.265186483385863, "learning_rate": 1.0881742443018192e-05, "loss": 0.4162, "step": 7366 }, { "epoch": 1.0497292675976062, "grad_norm": 1.4975420072135135, "learning_rate": 1.087926509123578e-05, "loss": 0.4319, "step": 7367 }, { "epoch": 1.0498717583357082, "grad_norm": 1.4416818803898637, "learning_rate": 1.0876787685068845e-05, "loss": 0.5106, "step": 7368 }, { "epoch": 1.0500142490738102, "grad_norm": 1.3213342875127148, "learning_rate": 1.0874310224670615e-05, "loss": 0.4051, "step": 7369 }, { "epoch": 1.0501567398119123, "grad_norm": 1.9392297134671006, "learning_rate": 1.087183271019433e-05, "loss": 0.45, "step": 7370 }, { "epoch": 1.0502992305500143, "grad_norm": 1.5011517350793462, "learning_rate": 1.0869355141793234e-05, "loss": 0.4601, "step": 7371 }, { "epoch": 1.0504417212881163, "grad_norm": 1.4287091375414, "learning_rate": 1.0866877519620562e-05, "loss": 0.4401, "step": 7372 }, { "epoch": 1.0505842120262183, "grad_norm": 1.296368012580524, "learning_rate": 1.0864399843829563e-05, "loss": 0.4209, "step": 7373 }, { "epoch": 1.0507267027643203, "grad_norm": 1.3853374053840692, "learning_rate": 1.0861922114573492e-05, "loss": 0.4513, "step": 7374 }, { "epoch": 1.0508691935024224, "grad_norm": 1.2815448306438542, "learning_rate": 1.0859444332005596e-05, "loss": 0.5404, "step": 7375 }, { "epoch": 1.0510116842405244, "grad_norm": 1.394528791933829, "learning_rate": 1.085696649627913e-05, "loss": 0.4416, "step": 7376 }, { "epoch": 1.0511541749786264, "grad_norm": 1.3872220146751704, "learning_rate": 1.085448860754736e-05, "loss": 0.4393, "step": 7377 }, { "epoch": 1.0512966657167284, "grad_norm": 1.477964678624085, "learning_rate": 1.0852010665963545e-05, "loss": 0.4592, "step": 7378 }, { "epoch": 1.0514391564548304, "grad_norm": 1.5592154703926004, "learning_rate": 1.0849532671680955e-05, "loss": 0.4768, "step": 7379 }, { "epoch": 1.0515816471929325, "grad_norm": 1.4138157587502902, "learning_rate": 1.0847054624852857e-05, "loss": 0.4236, "step": 7380 }, { "epoch": 1.0517241379310345, "grad_norm": 1.3384241318000574, "learning_rate": 1.0844576525632522e-05, "loss": 0.4375, "step": 7381 }, { "epoch": 1.0518666286691365, "grad_norm": 1.3449650146723475, "learning_rate": 1.0842098374173229e-05, "loss": 0.5148, "step": 7382 }, { "epoch": 1.0520091194072385, "grad_norm": 1.3596255905148362, "learning_rate": 1.0839620170628255e-05, "loss": 0.4644, "step": 7383 }, { "epoch": 1.0521516101453405, "grad_norm": 1.36503394348338, "learning_rate": 1.0837141915150883e-05, "loss": 0.4531, "step": 7384 }, { "epoch": 1.0522941008834426, "grad_norm": 1.5062323024893514, "learning_rate": 1.0834663607894403e-05, "loss": 0.4612, "step": 7385 }, { "epoch": 1.0524365916215446, "grad_norm": 2.7486608289342955, "learning_rate": 1.0832185249012098e-05, "loss": 0.4519, "step": 7386 }, { "epoch": 1.0525790823596466, "grad_norm": 1.3198098687797102, "learning_rate": 1.082970683865726e-05, "loss": 0.4879, "step": 7387 }, { "epoch": 1.0527215730977486, "grad_norm": 1.3371672321050427, "learning_rate": 1.0827228376983187e-05, "loss": 0.4082, "step": 7388 }, { "epoch": 1.0528640638358506, "grad_norm": 1.4916721522568717, "learning_rate": 1.0824749864143178e-05, "loss": 0.4831, "step": 7389 }, { "epoch": 1.0530065545739526, "grad_norm": 1.346646438431305, "learning_rate": 1.0822271300290534e-05, "loss": 0.43, "step": 7390 }, { "epoch": 1.0531490453120547, "grad_norm": 1.4007352414664331, "learning_rate": 1.0819792685578558e-05, "loss": 0.439, "step": 7391 }, { "epoch": 1.0532915360501567, "grad_norm": 1.3348138120205257, "learning_rate": 1.0817314020160559e-05, "loss": 0.4255, "step": 7392 }, { "epoch": 1.0534340267882587, "grad_norm": 1.2846645578920213, "learning_rate": 1.0814835304189851e-05, "loss": 0.4503, "step": 7393 }, { "epoch": 1.0535765175263607, "grad_norm": 1.410822963203248, "learning_rate": 1.0812356537819744e-05, "loss": 0.4422, "step": 7394 }, { "epoch": 1.0537190082644627, "grad_norm": 1.4760939508904256, "learning_rate": 1.0809877721203555e-05, "loss": 0.4273, "step": 7395 }, { "epoch": 1.0538614990025648, "grad_norm": 1.2846368506663277, "learning_rate": 1.0807398854494607e-05, "loss": 0.4355, "step": 7396 }, { "epoch": 1.0540039897406668, "grad_norm": 1.4386617649476516, "learning_rate": 1.0804919937846222e-05, "loss": 0.5184, "step": 7397 }, { "epoch": 1.0541464804787688, "grad_norm": 1.3940840930098812, "learning_rate": 1.0802440971411726e-05, "loss": 0.4903, "step": 7398 }, { "epoch": 1.0542889712168708, "grad_norm": 1.2821190115872694, "learning_rate": 1.079996195534445e-05, "loss": 0.3956, "step": 7399 }, { "epoch": 1.0544314619549728, "grad_norm": 1.4267250773169613, "learning_rate": 1.0797482889797725e-05, "loss": 0.4324, "step": 7400 }, { "epoch": 1.0545739526930749, "grad_norm": 1.1431615629454153, "learning_rate": 1.0795003774924893e-05, "loss": 0.3998, "step": 7401 }, { "epoch": 1.0547164434311769, "grad_norm": 1.2840282242000605, "learning_rate": 1.0792524610879285e-05, "loss": 0.4158, "step": 7402 }, { "epoch": 1.054858934169279, "grad_norm": 1.4028375045175547, "learning_rate": 1.0790045397814246e-05, "loss": 0.4825, "step": 7403 }, { "epoch": 1.055001424907381, "grad_norm": 1.580341081744253, "learning_rate": 1.0787566135883121e-05, "loss": 0.4792, "step": 7404 }, { "epoch": 1.0551439156454832, "grad_norm": 1.348258811309408, "learning_rate": 1.0785086825239257e-05, "loss": 0.4892, "step": 7405 }, { "epoch": 1.0552864063835852, "grad_norm": 1.442309958884126, "learning_rate": 1.0782607466036006e-05, "loss": 0.423, "step": 7406 }, { "epoch": 1.0554288971216872, "grad_norm": 1.3406401814600672, "learning_rate": 1.0780128058426722e-05, "loss": 0.3858, "step": 7407 }, { "epoch": 1.0555713878597892, "grad_norm": 1.2486885846693077, "learning_rate": 1.0777648602564762e-05, "loss": 0.3947, "step": 7408 }, { "epoch": 1.0557138785978912, "grad_norm": 1.3957238451423208, "learning_rate": 1.0775169098603487e-05, "loss": 0.4698, "step": 7409 }, { "epoch": 1.0558563693359933, "grad_norm": 1.3201942125917887, "learning_rate": 1.0772689546696256e-05, "loss": 0.432, "step": 7410 }, { "epoch": 1.0559988600740953, "grad_norm": 1.255492564758233, "learning_rate": 1.0770209946996437e-05, "loss": 0.4004, "step": 7411 }, { "epoch": 1.0561413508121973, "grad_norm": 1.3682194839003583, "learning_rate": 1.07677302996574e-05, "loss": 0.3959, "step": 7412 }, { "epoch": 1.0562838415502993, "grad_norm": 1.3024164883870444, "learning_rate": 1.0765250604832516e-05, "loss": 0.4303, "step": 7413 }, { "epoch": 1.0564263322884013, "grad_norm": 1.455144684795496, "learning_rate": 1.0762770862675158e-05, "loss": 0.4199, "step": 7414 }, { "epoch": 1.0565688230265033, "grad_norm": 1.384238099145576, "learning_rate": 1.0760291073338708e-05, "loss": 0.452, "step": 7415 }, { "epoch": 1.0567113137646054, "grad_norm": 1.4409536833452063, "learning_rate": 1.0757811236976541e-05, "loss": 0.4263, "step": 7416 }, { "epoch": 1.0568538045027074, "grad_norm": 1.3489695050313353, "learning_rate": 1.0755331353742045e-05, "loss": 0.4217, "step": 7417 }, { "epoch": 1.0569962952408094, "grad_norm": 1.508702819447209, "learning_rate": 1.0752851423788604e-05, "loss": 0.4321, "step": 7418 }, { "epoch": 1.0571387859789114, "grad_norm": 1.2683138214267802, "learning_rate": 1.0750371447269607e-05, "loss": 0.4631, "step": 7419 }, { "epoch": 1.0572812767170134, "grad_norm": 1.3644465762559441, "learning_rate": 1.0747891424338448e-05, "loss": 0.4485, "step": 7420 }, { "epoch": 1.0574237674551155, "grad_norm": 1.440596016098115, "learning_rate": 1.074541135514852e-05, "loss": 0.4257, "step": 7421 }, { "epoch": 1.0575662581932175, "grad_norm": 1.368553506185036, "learning_rate": 1.0742931239853222e-05, "loss": 0.4586, "step": 7422 }, { "epoch": 1.0577087489313195, "grad_norm": 1.40502331622934, "learning_rate": 1.0740451078605958e-05, "loss": 0.4383, "step": 7423 }, { "epoch": 1.0578512396694215, "grad_norm": 1.2920130233844738, "learning_rate": 1.0737970871560124e-05, "loss": 0.4427, "step": 7424 }, { "epoch": 1.0579937304075235, "grad_norm": 1.4496519086085886, "learning_rate": 1.073549061886913e-05, "loss": 0.5183, "step": 7425 }, { "epoch": 1.0581362211456256, "grad_norm": 1.508898261059028, "learning_rate": 1.0733010320686389e-05, "loss": 0.4544, "step": 7426 }, { "epoch": 1.0582787118837276, "grad_norm": 1.5717555232632843, "learning_rate": 1.0730529977165307e-05, "loss": 0.4753, "step": 7427 }, { "epoch": 1.0584212026218296, "grad_norm": 1.237699459889483, "learning_rate": 1.0728049588459301e-05, "loss": 0.3846, "step": 7428 }, { "epoch": 1.0585636933599316, "grad_norm": 1.2740213398355655, "learning_rate": 1.072556915472179e-05, "loss": 0.4291, "step": 7429 }, { "epoch": 1.0587061840980336, "grad_norm": 1.3103886357703687, "learning_rate": 1.0723088676106194e-05, "loss": 0.4035, "step": 7430 }, { "epoch": 1.0588486748361357, "grad_norm": 1.4114435452158072, "learning_rate": 1.0720608152765938e-05, "loss": 0.4828, "step": 7431 }, { "epoch": 1.0589911655742377, "grad_norm": 1.8840894519627434, "learning_rate": 1.0718127584854445e-05, "loss": 0.4732, "step": 7432 }, { "epoch": 1.0591336563123397, "grad_norm": 1.405627639676342, "learning_rate": 1.0715646972525143e-05, "loss": 0.4279, "step": 7433 }, { "epoch": 1.0592761470504417, "grad_norm": 1.2370486289285951, "learning_rate": 1.0713166315931464e-05, "loss": 0.4366, "step": 7434 }, { "epoch": 1.0594186377885437, "grad_norm": 1.372042777595421, "learning_rate": 1.0710685615226843e-05, "loss": 0.4447, "step": 7435 }, { "epoch": 1.0595611285266457, "grad_norm": 1.4875613159513923, "learning_rate": 1.0708204870564718e-05, "loss": 0.417, "step": 7436 }, { "epoch": 1.0597036192647478, "grad_norm": 1.2857459619740956, "learning_rate": 1.0705724082098528e-05, "loss": 0.4449, "step": 7437 }, { "epoch": 1.0598461100028498, "grad_norm": 1.2331259811249606, "learning_rate": 1.0703243249981717e-05, "loss": 0.408, "step": 7438 }, { "epoch": 1.0599886007409518, "grad_norm": 1.3532572059700747, "learning_rate": 1.0700762374367726e-05, "loss": 0.4167, "step": 7439 }, { "epoch": 1.0601310914790538, "grad_norm": 1.350546032301832, "learning_rate": 1.0698281455410002e-05, "loss": 0.4443, "step": 7440 }, { "epoch": 1.0602735822171558, "grad_norm": 1.276825896584305, "learning_rate": 1.0695800493262e-05, "loss": 0.4249, "step": 7441 }, { "epoch": 1.0604160729552579, "grad_norm": 1.2734229983351728, "learning_rate": 1.0693319488077174e-05, "loss": 0.3936, "step": 7442 }, { "epoch": 1.0605585636933599, "grad_norm": 1.3208230385835211, "learning_rate": 1.0690838440008974e-05, "loss": 0.4223, "step": 7443 }, { "epoch": 1.060701054431462, "grad_norm": 1.3675208874172011, "learning_rate": 1.0688357349210862e-05, "loss": 0.4579, "step": 7444 }, { "epoch": 1.060843545169564, "grad_norm": 1.535430099914119, "learning_rate": 1.0685876215836302e-05, "loss": 0.4428, "step": 7445 }, { "epoch": 1.060986035907666, "grad_norm": 1.4277268050644978, "learning_rate": 1.068339504003875e-05, "loss": 0.4684, "step": 7446 }, { "epoch": 1.061128526645768, "grad_norm": 1.4925615560791816, "learning_rate": 1.0680913821971677e-05, "loss": 0.4741, "step": 7447 }, { "epoch": 1.06127101738387, "grad_norm": 1.3011586659369632, "learning_rate": 1.0678432561788551e-05, "loss": 0.4338, "step": 7448 }, { "epoch": 1.061413508121972, "grad_norm": 1.3324755305172615, "learning_rate": 1.0675951259642846e-05, "loss": 0.4084, "step": 7449 }, { "epoch": 1.061555998860074, "grad_norm": 1.3151728074961493, "learning_rate": 1.0673469915688033e-05, "loss": 0.417, "step": 7450 }, { "epoch": 1.061698489598176, "grad_norm": 1.3899075865001227, "learning_rate": 1.0670988530077588e-05, "loss": 0.378, "step": 7451 }, { "epoch": 1.061840980336278, "grad_norm": 1.934846910793076, "learning_rate": 1.0668507102964995e-05, "loss": 0.4594, "step": 7452 }, { "epoch": 1.06198347107438, "grad_norm": 1.3340633616747963, "learning_rate": 1.0666025634503734e-05, "loss": 0.419, "step": 7453 }, { "epoch": 1.062125961812482, "grad_norm": 1.2110930753680602, "learning_rate": 1.0663544124847285e-05, "loss": 0.3691, "step": 7454 }, { "epoch": 1.062268452550584, "grad_norm": 1.215996968515527, "learning_rate": 1.066106257414914e-05, "loss": 0.4542, "step": 7455 }, { "epoch": 1.0624109432886861, "grad_norm": 1.376527463276582, "learning_rate": 1.0658580982562785e-05, "loss": 0.4322, "step": 7456 }, { "epoch": 1.0625534340267881, "grad_norm": 1.3108845923559607, "learning_rate": 1.0656099350241715e-05, "loss": 0.4862, "step": 7457 }, { "epoch": 1.0626959247648902, "grad_norm": 1.3056127538079747, "learning_rate": 1.0653617677339423e-05, "loss": 0.4163, "step": 7458 }, { "epoch": 1.0628384155029924, "grad_norm": 1.317108799183746, "learning_rate": 1.0651135964009406e-05, "loss": 0.431, "step": 7459 }, { "epoch": 1.0629809062410944, "grad_norm": 1.4175903018880742, "learning_rate": 1.0648654210405167e-05, "loss": 0.4476, "step": 7460 }, { "epoch": 1.0631233969791964, "grad_norm": 1.3266647757633176, "learning_rate": 1.0646172416680203e-05, "loss": 0.3783, "step": 7461 }, { "epoch": 1.0632658877172985, "grad_norm": 1.3098236289138445, "learning_rate": 1.064369058298802e-05, "loss": 0.4377, "step": 7462 }, { "epoch": 1.0634083784554005, "grad_norm": 1.3219701811483833, "learning_rate": 1.0641208709482123e-05, "loss": 0.4137, "step": 7463 }, { "epoch": 1.0635508691935025, "grad_norm": 1.3107796012986732, "learning_rate": 1.063872679631603e-05, "loss": 0.4139, "step": 7464 }, { "epoch": 1.0636933599316045, "grad_norm": 1.2687983552543527, "learning_rate": 1.0636244843643242e-05, "loss": 0.3988, "step": 7465 }, { "epoch": 1.0638358506697065, "grad_norm": 1.3560931762472301, "learning_rate": 1.063376285161728e-05, "loss": 0.4457, "step": 7466 }, { "epoch": 1.0639783414078086, "grad_norm": 1.4764184203544564, "learning_rate": 1.0631280820391658e-05, "loss": 0.5039, "step": 7467 }, { "epoch": 1.0641208321459106, "grad_norm": 2.4978019303786962, "learning_rate": 1.06287987501199e-05, "loss": 0.4594, "step": 7468 }, { "epoch": 1.0642633228840126, "grad_norm": 1.3816767184979388, "learning_rate": 1.062631664095552e-05, "loss": 0.4434, "step": 7469 }, { "epoch": 1.0644058136221146, "grad_norm": 1.8237172552089422, "learning_rate": 1.0623834493052045e-05, "loss": 0.5072, "step": 7470 }, { "epoch": 1.0645483043602166, "grad_norm": 1.6901751701076464, "learning_rate": 1.062135230656301e-05, "loss": 0.5183, "step": 7471 }, { "epoch": 1.0646907950983187, "grad_norm": 1.433428673204705, "learning_rate": 1.0618870081641928e-05, "loss": 0.4594, "step": 7472 }, { "epoch": 1.0648332858364207, "grad_norm": 1.3532389196762842, "learning_rate": 1.0616387818442341e-05, "loss": 0.4252, "step": 7473 }, { "epoch": 1.0649757765745227, "grad_norm": 1.308709086086135, "learning_rate": 1.0613905517117779e-05, "loss": 0.477, "step": 7474 }, { "epoch": 1.0651182673126247, "grad_norm": 1.2907632197415067, "learning_rate": 1.0611423177821785e-05, "loss": 0.4225, "step": 7475 }, { "epoch": 1.0652607580507267, "grad_norm": 1.4128430416050788, "learning_rate": 1.0608940800707886e-05, "loss": 0.4726, "step": 7476 }, { "epoch": 1.0654032487888287, "grad_norm": 1.4331390932254338, "learning_rate": 1.0606458385929625e-05, "loss": 0.4378, "step": 7477 }, { "epoch": 1.0655457395269308, "grad_norm": 1.3391805803924293, "learning_rate": 1.0603975933640552e-05, "loss": 0.5204, "step": 7478 }, { "epoch": 1.0656882302650328, "grad_norm": 1.381414867791442, "learning_rate": 1.0601493443994206e-05, "loss": 0.4591, "step": 7479 }, { "epoch": 1.0658307210031348, "grad_norm": 1.396848055186015, "learning_rate": 1.0599010917144136e-05, "loss": 0.5008, "step": 7480 }, { "epoch": 1.0659732117412368, "grad_norm": 1.5705432030418882, "learning_rate": 1.0596528353243895e-05, "loss": 0.4871, "step": 7481 }, { "epoch": 1.0661157024793388, "grad_norm": 1.3446514137887497, "learning_rate": 1.0594045752447031e-05, "loss": 0.4441, "step": 7482 }, { "epoch": 1.0662581932174409, "grad_norm": 1.3603145281646436, "learning_rate": 1.0591563114907105e-05, "loss": 0.3946, "step": 7483 }, { "epoch": 1.0664006839555429, "grad_norm": 1.278024884945061, "learning_rate": 1.0589080440777662e-05, "loss": 0.4816, "step": 7484 }, { "epoch": 1.066543174693645, "grad_norm": 1.4001928659643326, "learning_rate": 1.0586597730212267e-05, "loss": 0.439, "step": 7485 }, { "epoch": 1.066685665431747, "grad_norm": 1.3113214383353484, "learning_rate": 1.0584114983364488e-05, "loss": 0.396, "step": 7486 }, { "epoch": 1.066828156169849, "grad_norm": 1.181705039500185, "learning_rate": 1.058163220038788e-05, "loss": 0.348, "step": 7487 }, { "epoch": 1.066970646907951, "grad_norm": 1.2654392887698764, "learning_rate": 1.057914938143601e-05, "loss": 0.4049, "step": 7488 }, { "epoch": 1.067113137646053, "grad_norm": 1.2545968958198577, "learning_rate": 1.0576666526662447e-05, "loss": 0.4026, "step": 7489 }, { "epoch": 1.067255628384155, "grad_norm": 1.415474745069166, "learning_rate": 1.0574183636220765e-05, "loss": 0.4529, "step": 7490 }, { "epoch": 1.067398119122257, "grad_norm": 1.5718055160377367, "learning_rate": 1.0571700710264527e-05, "loss": 0.474, "step": 7491 }, { "epoch": 1.067540609860359, "grad_norm": 1.248590251592516, "learning_rate": 1.0569217748947317e-05, "loss": 0.4074, "step": 7492 }, { "epoch": 1.067683100598461, "grad_norm": 1.425261446833552, "learning_rate": 1.0566734752422707e-05, "loss": 0.4224, "step": 7493 }, { "epoch": 1.067825591336563, "grad_norm": 1.575157780237149, "learning_rate": 1.0564251720844277e-05, "loss": 0.5115, "step": 7494 }, { "epoch": 1.067968082074665, "grad_norm": 1.4371386612079242, "learning_rate": 1.0561768654365607e-05, "loss": 0.415, "step": 7495 }, { "epoch": 1.0681105728127671, "grad_norm": 1.428774843583999, "learning_rate": 1.0559285553140282e-05, "loss": 0.4856, "step": 7496 }, { "epoch": 1.0682530635508691, "grad_norm": 1.5221349498078114, "learning_rate": 1.0556802417321887e-05, "loss": 0.4982, "step": 7497 }, { "epoch": 1.0683955542889711, "grad_norm": 1.2982085715301084, "learning_rate": 1.0554319247064009e-05, "loss": 0.4409, "step": 7498 }, { "epoch": 1.0685380450270732, "grad_norm": 1.3799979197556906, "learning_rate": 1.0551836042520239e-05, "loss": 0.4972, "step": 7499 }, { "epoch": 1.0686805357651752, "grad_norm": 1.4329498272239194, "learning_rate": 1.0549352803844163e-05, "loss": 0.4663, "step": 7500 }, { "epoch": 1.0688230265032772, "grad_norm": 1.3745865695216404, "learning_rate": 1.0546869531189385e-05, "loss": 0.462, "step": 7501 }, { "epoch": 1.0689655172413792, "grad_norm": 1.5591549413306465, "learning_rate": 1.0544386224709493e-05, "loss": 0.4293, "step": 7502 }, { "epoch": 1.0691080079794812, "grad_norm": 1.4609143012229517, "learning_rate": 1.0541902884558088e-05, "loss": 0.4655, "step": 7503 }, { "epoch": 1.0692504987175833, "grad_norm": 1.3118692619280858, "learning_rate": 1.0539419510888769e-05, "loss": 0.4156, "step": 7504 }, { "epoch": 1.0693929894556853, "grad_norm": 1.4896405750198165, "learning_rate": 1.0536936103855143e-05, "loss": 0.4309, "step": 7505 }, { "epoch": 1.0695354801937873, "grad_norm": 1.3190739600581043, "learning_rate": 1.0534452663610806e-05, "loss": 0.4471, "step": 7506 }, { "epoch": 1.0696779709318895, "grad_norm": 1.4776914166929929, "learning_rate": 1.0531969190309366e-05, "loss": 0.4562, "step": 7507 }, { "epoch": 1.0698204616699916, "grad_norm": 1.3900497066772004, "learning_rate": 1.052948568410444e-05, "loss": 0.4027, "step": 7508 }, { "epoch": 1.0699629524080936, "grad_norm": 1.2359030297337386, "learning_rate": 1.0527002145149632e-05, "loss": 0.4015, "step": 7509 }, { "epoch": 1.0701054431461956, "grad_norm": 1.3910589389643435, "learning_rate": 1.0524518573598552e-05, "loss": 0.412, "step": 7510 }, { "epoch": 1.0702479338842976, "grad_norm": 1.3290368897149298, "learning_rate": 1.052203496960482e-05, "loss": 0.4638, "step": 7511 }, { "epoch": 1.0703904246223996, "grad_norm": 1.4307233214787838, "learning_rate": 1.0519551333322052e-05, "loss": 0.4807, "step": 7512 }, { "epoch": 1.0705329153605017, "grad_norm": 1.357190779672438, "learning_rate": 1.0517067664903861e-05, "loss": 0.489, "step": 7513 }, { "epoch": 1.0706754060986037, "grad_norm": 1.4027182761137424, "learning_rate": 1.0514583964503869e-05, "loss": 0.4887, "step": 7514 }, { "epoch": 1.0708178968367057, "grad_norm": 1.30946322491329, "learning_rate": 1.0512100232275703e-05, "loss": 0.3862, "step": 7515 }, { "epoch": 1.0709603875748077, "grad_norm": 1.3525347296888022, "learning_rate": 1.0509616468372988e-05, "loss": 0.435, "step": 7516 }, { "epoch": 1.0711028783129097, "grad_norm": 1.919781683943264, "learning_rate": 1.0507132672949346e-05, "loss": 0.5027, "step": 7517 }, { "epoch": 1.0712453690510118, "grad_norm": 1.5867329311568492, "learning_rate": 1.0504648846158403e-05, "loss": 0.5843, "step": 7518 }, { "epoch": 1.0713878597891138, "grad_norm": 1.5940102827905624, "learning_rate": 1.0502164988153795e-05, "loss": 0.4894, "step": 7519 }, { "epoch": 1.0715303505272158, "grad_norm": 1.4491317937375272, "learning_rate": 1.0499681099089153e-05, "loss": 0.4098, "step": 7520 }, { "epoch": 1.0716728412653178, "grad_norm": 1.4023800346506683, "learning_rate": 1.0497197179118109e-05, "loss": 0.4682, "step": 7521 }, { "epoch": 1.0718153320034198, "grad_norm": 1.5369817468657025, "learning_rate": 1.04947132283943e-05, "loss": 0.4731, "step": 7522 }, { "epoch": 1.0719578227415218, "grad_norm": 1.2265222387035462, "learning_rate": 1.0492229247071368e-05, "loss": 0.3434, "step": 7523 }, { "epoch": 1.0721003134796239, "grad_norm": 1.3205383411497333, "learning_rate": 1.0489745235302946e-05, "loss": 0.4785, "step": 7524 }, { "epoch": 1.0722428042177259, "grad_norm": 1.3542301224975286, "learning_rate": 1.048726119324268e-05, "loss": 0.3881, "step": 7525 }, { "epoch": 1.072385294955828, "grad_norm": 1.408438268932234, "learning_rate": 1.048477712104421e-05, "loss": 0.4811, "step": 7526 }, { "epoch": 1.07252778569393, "grad_norm": 1.3228250269906388, "learning_rate": 1.0482293018861186e-05, "loss": 0.4373, "step": 7527 }, { "epoch": 1.072670276432032, "grad_norm": 1.359646820691286, "learning_rate": 1.0479808886847254e-05, "loss": 0.4756, "step": 7528 }, { "epoch": 1.072812767170134, "grad_norm": 1.3762989053390442, "learning_rate": 1.0477324725156058e-05, "loss": 0.4385, "step": 7529 }, { "epoch": 1.072955257908236, "grad_norm": 1.3578325178677033, "learning_rate": 1.0474840533941257e-05, "loss": 0.4663, "step": 7530 }, { "epoch": 1.073097748646338, "grad_norm": 1.2682164818926658, "learning_rate": 1.04723563133565e-05, "loss": 0.4984, "step": 7531 }, { "epoch": 1.07324023938444, "grad_norm": 1.3552313853108287, "learning_rate": 1.0469872063555441e-05, "loss": 0.4298, "step": 7532 }, { "epoch": 1.073382730122542, "grad_norm": 1.3612929436462617, "learning_rate": 1.0467387784691738e-05, "loss": 0.4577, "step": 7533 }, { "epoch": 1.073525220860644, "grad_norm": 1.412848267146623, "learning_rate": 1.0464903476919047e-05, "loss": 0.4378, "step": 7534 }, { "epoch": 1.073667711598746, "grad_norm": 1.315311848546428, "learning_rate": 1.0462419140391034e-05, "loss": 0.4334, "step": 7535 }, { "epoch": 1.073810202336848, "grad_norm": 1.2361811911630884, "learning_rate": 1.045993477526135e-05, "loss": 0.3827, "step": 7536 }, { "epoch": 1.0739526930749501, "grad_norm": 1.4951564941213873, "learning_rate": 1.0457450381683665e-05, "loss": 0.4377, "step": 7537 }, { "epoch": 1.0740951838130521, "grad_norm": 1.3207530093480244, "learning_rate": 1.0454965959811649e-05, "loss": 0.4854, "step": 7538 }, { "epoch": 1.0742376745511542, "grad_norm": 1.286106622263511, "learning_rate": 1.0452481509798961e-05, "loss": 0.4425, "step": 7539 }, { "epoch": 1.0743801652892562, "grad_norm": 1.415992638463982, "learning_rate": 1.0449997031799275e-05, "loss": 0.4356, "step": 7540 }, { "epoch": 1.0745226560273582, "grad_norm": 1.540245272607198, "learning_rate": 1.044751252596626e-05, "loss": 0.4733, "step": 7541 }, { "epoch": 1.0746651467654602, "grad_norm": 1.4466007133154202, "learning_rate": 1.0445027992453588e-05, "loss": 0.4879, "step": 7542 }, { "epoch": 1.0748076375035622, "grad_norm": 1.2407209122841694, "learning_rate": 1.0442543431414928e-05, "loss": 0.4307, "step": 7543 }, { "epoch": 1.0749501282416642, "grad_norm": 1.5500193951963241, "learning_rate": 1.0440058843003964e-05, "loss": 0.4618, "step": 7544 }, { "epoch": 1.0750926189797663, "grad_norm": 1.2375627982229462, "learning_rate": 1.0437574227374372e-05, "loss": 0.3954, "step": 7545 }, { "epoch": 1.0752351097178683, "grad_norm": 1.3194542750457898, "learning_rate": 1.0435089584679828e-05, "loss": 0.4189, "step": 7546 }, { "epoch": 1.0753776004559703, "grad_norm": 1.3728213843327102, "learning_rate": 1.0432604915074011e-05, "loss": 0.4612, "step": 7547 }, { "epoch": 1.0755200911940723, "grad_norm": 1.407158520574078, "learning_rate": 1.043012021871061e-05, "loss": 0.428, "step": 7548 }, { "epoch": 1.0756625819321743, "grad_norm": 1.5308290670705835, "learning_rate": 1.0427635495743304e-05, "loss": 0.5284, "step": 7549 }, { "epoch": 1.0758050726702764, "grad_norm": 1.3655321378074023, "learning_rate": 1.0425150746325781e-05, "loss": 0.4425, "step": 7550 }, { "epoch": 1.0759475634083784, "grad_norm": 1.319189315238714, "learning_rate": 1.0422665970611722e-05, "loss": 0.4157, "step": 7551 }, { "epoch": 1.0760900541464804, "grad_norm": 1.503058341747074, "learning_rate": 1.0420181168754827e-05, "loss": 0.4339, "step": 7552 }, { "epoch": 1.0762325448845824, "grad_norm": 1.4762819170534036, "learning_rate": 1.041769634090878e-05, "loss": 0.5207, "step": 7553 }, { "epoch": 1.0763750356226844, "grad_norm": 1.3413226972287018, "learning_rate": 1.0415211487227275e-05, "loss": 0.4247, "step": 7554 }, { "epoch": 1.0765175263607865, "grad_norm": 1.5119088074209315, "learning_rate": 1.0412726607864003e-05, "loss": 0.4367, "step": 7555 }, { "epoch": 1.0766600170988885, "grad_norm": 1.303906398958097, "learning_rate": 1.0410241702972661e-05, "loss": 0.4408, "step": 7556 }, { "epoch": 1.0768025078369905, "grad_norm": 1.341343738554522, "learning_rate": 1.040775677270695e-05, "loss": 0.4427, "step": 7557 }, { "epoch": 1.0769449985750925, "grad_norm": 1.3627141005431442, "learning_rate": 1.0405271817220556e-05, "loss": 0.3988, "step": 7558 }, { "epoch": 1.0770874893131945, "grad_norm": 1.2177406151741608, "learning_rate": 1.0402786836667195e-05, "loss": 0.3764, "step": 7559 }, { "epoch": 1.0772299800512966, "grad_norm": 1.2290250771352436, "learning_rate": 1.0400301831200564e-05, "loss": 0.4308, "step": 7560 }, { "epoch": 1.0773724707893986, "grad_norm": 1.2324845637612947, "learning_rate": 1.0397816800974358e-05, "loss": 0.4081, "step": 7561 }, { "epoch": 1.0775149615275008, "grad_norm": 1.2366892191326213, "learning_rate": 1.0395331746142287e-05, "loss": 0.4204, "step": 7562 }, { "epoch": 1.0776574522656028, "grad_norm": 1.44066231508475, "learning_rate": 1.039284666685806e-05, "loss": 0.4377, "step": 7563 }, { "epoch": 1.0777999430037049, "grad_norm": 1.393042260313692, "learning_rate": 1.0390361563275383e-05, "loss": 0.5064, "step": 7564 }, { "epoch": 1.0779424337418069, "grad_norm": 1.2811899504874777, "learning_rate": 1.0387876435547964e-05, "loss": 0.4006, "step": 7565 }, { "epoch": 1.078084924479909, "grad_norm": 1.4384659171372487, "learning_rate": 1.0385391283829513e-05, "loss": 0.451, "step": 7566 }, { "epoch": 1.078227415218011, "grad_norm": 1.2978897955127886, "learning_rate": 1.0382906108273745e-05, "loss": 0.3915, "step": 7567 }, { "epoch": 1.078369905956113, "grad_norm": 1.7030766597826899, "learning_rate": 1.0380420909034374e-05, "loss": 0.4724, "step": 7568 }, { "epoch": 1.078512396694215, "grad_norm": 1.5039818254243384, "learning_rate": 1.037793568626511e-05, "loss": 0.4412, "step": 7569 }, { "epoch": 1.078654887432317, "grad_norm": 1.3207049242058941, "learning_rate": 1.0375450440119677e-05, "loss": 0.3995, "step": 7570 }, { "epoch": 1.078797378170419, "grad_norm": 2.09274905527199, "learning_rate": 1.0372965170751786e-05, "loss": 0.4464, "step": 7571 }, { "epoch": 1.078939868908521, "grad_norm": 1.3823291683551238, "learning_rate": 1.0370479878315159e-05, "loss": 0.4477, "step": 7572 }, { "epoch": 1.079082359646623, "grad_norm": 1.2780607177662526, "learning_rate": 1.036799456296352e-05, "loss": 0.4355, "step": 7573 }, { "epoch": 1.079224850384725, "grad_norm": 1.5663954746994035, "learning_rate": 1.0365509224850587e-05, "loss": 0.4775, "step": 7574 }, { "epoch": 1.079367341122827, "grad_norm": 1.4149704943673145, "learning_rate": 1.0363023864130089e-05, "loss": 0.4663, "step": 7575 }, { "epoch": 1.079509831860929, "grad_norm": 1.3822820228328032, "learning_rate": 1.0360538480955744e-05, "loss": 0.4536, "step": 7576 }, { "epoch": 1.079652322599031, "grad_norm": 1.3129695721010224, "learning_rate": 1.0358053075481284e-05, "loss": 0.503, "step": 7577 }, { "epoch": 1.0797948133371331, "grad_norm": 1.4487911073873896, "learning_rate": 1.0355567647860437e-05, "loss": 0.4842, "step": 7578 }, { "epoch": 1.0799373040752351, "grad_norm": 1.3849871582849846, "learning_rate": 1.0353082198246928e-05, "loss": 0.4177, "step": 7579 }, { "epoch": 1.0800797948133372, "grad_norm": 1.3513394393496456, "learning_rate": 1.035059672679449e-05, "loss": 0.4143, "step": 7580 }, { "epoch": 1.0802222855514392, "grad_norm": 1.2928842958178834, "learning_rate": 1.0348111233656858e-05, "loss": 0.4056, "step": 7581 }, { "epoch": 1.0803647762895412, "grad_norm": 1.3521947082275994, "learning_rate": 1.0345625718987762e-05, "loss": 0.4661, "step": 7582 }, { "epoch": 1.0805072670276432, "grad_norm": 1.314917261099397, "learning_rate": 1.0343140182940936e-05, "loss": 0.4921, "step": 7583 }, { "epoch": 1.0806497577657452, "grad_norm": 1.3695198716119807, "learning_rate": 1.0340654625670117e-05, "loss": 0.4401, "step": 7584 }, { "epoch": 1.0807922485038473, "grad_norm": 1.4898973310801094, "learning_rate": 1.0338169047329042e-05, "loss": 0.4699, "step": 7585 }, { "epoch": 1.0809347392419493, "grad_norm": 1.3299919716156954, "learning_rate": 1.0335683448071452e-05, "loss": 0.4724, "step": 7586 }, { "epoch": 1.0810772299800513, "grad_norm": 1.2992247359977966, "learning_rate": 1.0333197828051084e-05, "loss": 0.4125, "step": 7587 }, { "epoch": 1.0812197207181533, "grad_norm": 1.3040921679049677, "learning_rate": 1.0330712187421681e-05, "loss": 0.5147, "step": 7588 }, { "epoch": 1.0813622114562553, "grad_norm": 1.4898791045694335, "learning_rate": 1.0328226526336985e-05, "loss": 0.4921, "step": 7589 }, { "epoch": 1.0815047021943573, "grad_norm": 1.3623624858207246, "learning_rate": 1.032574084495074e-05, "loss": 0.4588, "step": 7590 }, { "epoch": 1.0816471929324594, "grad_norm": 1.4114013230504203, "learning_rate": 1.032325514341669e-05, "loss": 0.4537, "step": 7591 }, { "epoch": 1.0817896836705614, "grad_norm": 1.7693790818027304, "learning_rate": 1.0320769421888581e-05, "loss": 0.3849, "step": 7592 }, { "epoch": 1.0819321744086634, "grad_norm": 1.4844657267785182, "learning_rate": 1.0318283680520162e-05, "loss": 0.49, "step": 7593 }, { "epoch": 1.0820746651467654, "grad_norm": 1.3078011524064934, "learning_rate": 1.031579791946518e-05, "loss": 0.4041, "step": 7594 }, { "epoch": 1.0822171558848674, "grad_norm": 1.3198981129537684, "learning_rate": 1.0313312138877387e-05, "loss": 0.4327, "step": 7595 }, { "epoch": 1.0823596466229695, "grad_norm": 1.3804016585479146, "learning_rate": 1.0310826338910534e-05, "loss": 0.4381, "step": 7596 }, { "epoch": 1.0825021373610715, "grad_norm": 1.3355629168086092, "learning_rate": 1.0308340519718371e-05, "loss": 0.4463, "step": 7597 }, { "epoch": 1.0826446280991735, "grad_norm": 1.3457591365598702, "learning_rate": 1.0305854681454652e-05, "loss": 0.4407, "step": 7598 }, { "epoch": 1.0827871188372755, "grad_norm": 1.7246128514671888, "learning_rate": 1.0303368824273134e-05, "loss": 0.4559, "step": 7599 }, { "epoch": 1.0829296095753775, "grad_norm": 1.2669034191475388, "learning_rate": 1.030088294832757e-05, "loss": 0.3844, "step": 7600 }, { "epoch": 1.0830721003134796, "grad_norm": 1.2738795706830024, "learning_rate": 1.0298397053771718e-05, "loss": 0.4721, "step": 7601 }, { "epoch": 1.0832145910515816, "grad_norm": 1.5587223466065039, "learning_rate": 1.0295911140759338e-05, "loss": 0.442, "step": 7602 }, { "epoch": 1.0833570817896836, "grad_norm": 1.5093838993069915, "learning_rate": 1.0293425209444187e-05, "loss": 0.4167, "step": 7603 }, { "epoch": 1.0834995725277856, "grad_norm": 1.3755660544480475, "learning_rate": 1.0290939259980026e-05, "loss": 0.4122, "step": 7604 }, { "epoch": 1.0836420632658876, "grad_norm": 1.474841038583209, "learning_rate": 1.0288453292520619e-05, "loss": 0.4766, "step": 7605 }, { "epoch": 1.0837845540039897, "grad_norm": 1.551915272700917, "learning_rate": 1.0285967307219727e-05, "loss": 0.4663, "step": 7606 }, { "epoch": 1.0839270447420917, "grad_norm": 1.4201548732304115, "learning_rate": 1.028348130423111e-05, "loss": 0.4912, "step": 7607 }, { "epoch": 1.0840695354801937, "grad_norm": 1.34515462871336, "learning_rate": 1.0280995283708537e-05, "loss": 0.4681, "step": 7608 }, { "epoch": 1.0842120262182957, "grad_norm": 1.4724780188681608, "learning_rate": 1.0278509245805774e-05, "loss": 0.5002, "step": 7609 }, { "epoch": 1.084354516956398, "grad_norm": 1.2803174592671331, "learning_rate": 1.0276023190676587e-05, "loss": 0.4002, "step": 7610 }, { "epoch": 1.0844970076945, "grad_norm": 1.2892785274469598, "learning_rate": 1.0273537118474743e-05, "loss": 0.4659, "step": 7611 }, { "epoch": 1.084639498432602, "grad_norm": 1.2892001736615872, "learning_rate": 1.0271051029354015e-05, "loss": 0.3826, "step": 7612 }, { "epoch": 1.084781989170704, "grad_norm": 1.3978588652931323, "learning_rate": 1.0268564923468172e-05, "loss": 0.4878, "step": 7613 }, { "epoch": 1.084924479908806, "grad_norm": 1.1722707343185383, "learning_rate": 1.026607880097098e-05, "loss": 0.3807, "step": 7614 }, { "epoch": 1.085066970646908, "grad_norm": 1.261702614858896, "learning_rate": 1.0263592662016217e-05, "loss": 0.3955, "step": 7615 }, { "epoch": 1.08520946138501, "grad_norm": 1.3600968732757692, "learning_rate": 1.0261106506757654e-05, "loss": 0.5096, "step": 7616 }, { "epoch": 1.085351952123112, "grad_norm": 1.4290339850637048, "learning_rate": 1.0258620335349065e-05, "loss": 0.5203, "step": 7617 }, { "epoch": 1.085494442861214, "grad_norm": 1.3959292595119155, "learning_rate": 1.0256134147944228e-05, "loss": 0.4848, "step": 7618 }, { "epoch": 1.0856369335993161, "grad_norm": 1.270497114248808, "learning_rate": 1.0253647944696917e-05, "loss": 0.4071, "step": 7619 }, { "epoch": 1.0857794243374181, "grad_norm": 1.5353115374861626, "learning_rate": 1.0251161725760912e-05, "loss": 0.4463, "step": 7620 }, { "epoch": 1.0859219150755202, "grad_norm": 1.3680642460047812, "learning_rate": 1.0248675491289986e-05, "loss": 0.4226, "step": 7621 }, { "epoch": 1.0860644058136222, "grad_norm": 1.3863118229819362, "learning_rate": 1.024618924143792e-05, "loss": 0.4056, "step": 7622 }, { "epoch": 1.0862068965517242, "grad_norm": 1.3687765058254175, "learning_rate": 1.0243702976358495e-05, "loss": 0.4094, "step": 7623 }, { "epoch": 1.0863493872898262, "grad_norm": 1.3567348765985345, "learning_rate": 1.0241216696205495e-05, "loss": 0.4232, "step": 7624 }, { "epoch": 1.0864918780279282, "grad_norm": 1.3444099525724351, "learning_rate": 1.0238730401132699e-05, "loss": 0.4624, "step": 7625 }, { "epoch": 1.0866343687660303, "grad_norm": 1.3058418919173949, "learning_rate": 1.023624409129389e-05, "loss": 0.439, "step": 7626 }, { "epoch": 1.0867768595041323, "grad_norm": 1.5352357777869678, "learning_rate": 1.0233757766842853e-05, "loss": 0.4549, "step": 7627 }, { "epoch": 1.0869193502422343, "grad_norm": 1.4129146550594165, "learning_rate": 1.0231271427933371e-05, "loss": 0.4778, "step": 7628 }, { "epoch": 1.0870618409803363, "grad_norm": 1.4798007381790914, "learning_rate": 1.022878507471923e-05, "loss": 0.4977, "step": 7629 }, { "epoch": 1.0872043317184383, "grad_norm": 1.5762762781376662, "learning_rate": 1.0226298707354216e-05, "loss": 0.4593, "step": 7630 }, { "epoch": 1.0873468224565404, "grad_norm": 1.2790165086719185, "learning_rate": 1.022381232599212e-05, "loss": 0.4284, "step": 7631 }, { "epoch": 1.0874893131946424, "grad_norm": 1.4541445342154677, "learning_rate": 1.0221325930786728e-05, "loss": 0.4727, "step": 7632 }, { "epoch": 1.0876318039327444, "grad_norm": 1.4071773676035404, "learning_rate": 1.0218839521891825e-05, "loss": 0.4443, "step": 7633 }, { "epoch": 1.0877742946708464, "grad_norm": 1.32409194902191, "learning_rate": 1.0216353099461211e-05, "loss": 0.4717, "step": 7634 }, { "epoch": 1.0879167854089484, "grad_norm": 1.3275601729970146, "learning_rate": 1.0213866663648668e-05, "loss": 0.4907, "step": 7635 }, { "epoch": 1.0880592761470504, "grad_norm": 1.2804531759488358, "learning_rate": 1.0211380214607992e-05, "loss": 0.4275, "step": 7636 }, { "epoch": 1.0882017668851525, "grad_norm": 1.2539824135360589, "learning_rate": 1.020889375249297e-05, "loss": 0.4284, "step": 7637 }, { "epoch": 1.0883442576232545, "grad_norm": 1.4093648952622262, "learning_rate": 1.0206407277457402e-05, "loss": 0.4706, "step": 7638 }, { "epoch": 1.0884867483613565, "grad_norm": 1.2632643243883848, "learning_rate": 1.0203920789655078e-05, "loss": 0.4242, "step": 7639 }, { "epoch": 1.0886292390994585, "grad_norm": 1.368312887585969, "learning_rate": 1.0201434289239793e-05, "loss": 0.4307, "step": 7640 }, { "epoch": 1.0887717298375605, "grad_norm": 1.4571370569431479, "learning_rate": 1.0198947776365346e-05, "loss": 0.5272, "step": 7641 }, { "epoch": 1.0889142205756626, "grad_norm": 1.3702856593337103, "learning_rate": 1.0196461251185535e-05, "loss": 0.4479, "step": 7642 }, { "epoch": 1.0890567113137646, "grad_norm": 1.3539400339828875, "learning_rate": 1.0193974713854147e-05, "loss": 0.4277, "step": 7643 }, { "epoch": 1.0891992020518666, "grad_norm": 1.3395705222284782, "learning_rate": 1.0191488164524989e-05, "loss": 0.4759, "step": 7644 }, { "epoch": 1.0893416927899686, "grad_norm": 1.3550355819676698, "learning_rate": 1.0189001603351856e-05, "loss": 0.404, "step": 7645 }, { "epoch": 1.0894841835280706, "grad_norm": 1.2886022543857638, "learning_rate": 1.0186515030488549e-05, "loss": 0.4526, "step": 7646 }, { "epoch": 1.0896266742661727, "grad_norm": 1.8244836631711054, "learning_rate": 1.0184028446088868e-05, "loss": 0.4136, "step": 7647 }, { "epoch": 1.0897691650042747, "grad_norm": 1.4517532537221962, "learning_rate": 1.018154185030661e-05, "loss": 0.4649, "step": 7648 }, { "epoch": 1.0899116557423767, "grad_norm": 1.3491108690794988, "learning_rate": 1.0179055243295587e-05, "loss": 0.445, "step": 7649 }, { "epoch": 1.0900541464804787, "grad_norm": 1.3310789021789002, "learning_rate": 1.0176568625209588e-05, "loss": 0.4317, "step": 7650 }, { "epoch": 1.0901966372185807, "grad_norm": 1.288664912082596, "learning_rate": 1.0174081996202425e-05, "loss": 0.4087, "step": 7651 }, { "epoch": 1.0903391279566828, "grad_norm": 1.3912071505833117, "learning_rate": 1.0171595356427895e-05, "loss": 0.4454, "step": 7652 }, { "epoch": 1.0904816186947848, "grad_norm": 1.327639802816622, "learning_rate": 1.016910870603981e-05, "loss": 0.4198, "step": 7653 }, { "epoch": 1.0906241094328868, "grad_norm": 1.3409444254168215, "learning_rate": 1.016662204519197e-05, "loss": 0.4967, "step": 7654 }, { "epoch": 1.0907666001709888, "grad_norm": 1.3856992012166847, "learning_rate": 1.016413537403818e-05, "loss": 0.4446, "step": 7655 }, { "epoch": 1.0909090909090908, "grad_norm": 1.448527630845381, "learning_rate": 1.016164869273225e-05, "loss": 0.5052, "step": 7656 }, { "epoch": 1.0910515816471928, "grad_norm": 2.7652866799510645, "learning_rate": 1.0159162001427984e-05, "loss": 0.4749, "step": 7657 }, { "epoch": 1.0911940723852949, "grad_norm": 2.0154901932638305, "learning_rate": 1.0156675300279189e-05, "loss": 0.4881, "step": 7658 }, { "epoch": 1.0913365631233969, "grad_norm": 1.3749506019210558, "learning_rate": 1.0154188589439673e-05, "loss": 0.4714, "step": 7659 }, { "epoch": 1.091479053861499, "grad_norm": 1.300632148868017, "learning_rate": 1.0151701869063247e-05, "loss": 0.4322, "step": 7660 }, { "epoch": 1.091621544599601, "grad_norm": 1.3981498265271115, "learning_rate": 1.0149215139303718e-05, "loss": 0.4041, "step": 7661 }, { "epoch": 1.091764035337703, "grad_norm": 1.2861939058653955, "learning_rate": 1.0146728400314898e-05, "loss": 0.4132, "step": 7662 }, { "epoch": 1.091906526075805, "grad_norm": 1.4073043435157326, "learning_rate": 1.0144241652250595e-05, "loss": 0.4782, "step": 7663 }, { "epoch": 1.092049016813907, "grad_norm": 1.3620986484794844, "learning_rate": 1.0141754895264624e-05, "loss": 0.4544, "step": 7664 }, { "epoch": 1.0921915075520092, "grad_norm": 1.1954348154921575, "learning_rate": 1.0139268129510791e-05, "loss": 0.4269, "step": 7665 }, { "epoch": 1.0923339982901112, "grad_norm": 1.4523561315686337, "learning_rate": 1.0136781355142911e-05, "loss": 0.4437, "step": 7666 }, { "epoch": 1.0924764890282133, "grad_norm": 1.4031521934589166, "learning_rate": 1.0134294572314796e-05, "loss": 0.5017, "step": 7667 }, { "epoch": 1.0926189797663153, "grad_norm": 1.2767078827997207, "learning_rate": 1.013180778118026e-05, "loss": 0.432, "step": 7668 }, { "epoch": 1.0927614705044173, "grad_norm": 1.3155431608869972, "learning_rate": 1.0129320981893116e-05, "loss": 0.5071, "step": 7669 }, { "epoch": 1.0929039612425193, "grad_norm": 1.3729347096295486, "learning_rate": 1.0126834174607176e-05, "loss": 0.4697, "step": 7670 }, { "epoch": 1.0930464519806213, "grad_norm": 1.4354194209317515, "learning_rate": 1.0124347359476259e-05, "loss": 0.4783, "step": 7671 }, { "epoch": 1.0931889427187234, "grad_norm": 1.2780363942491269, "learning_rate": 1.012186053665418e-05, "loss": 0.4805, "step": 7672 }, { "epoch": 1.0933314334568254, "grad_norm": 1.4261006827761649, "learning_rate": 1.011937370629475e-05, "loss": 0.4103, "step": 7673 }, { "epoch": 1.0934739241949274, "grad_norm": 1.3058357847469846, "learning_rate": 1.0116886868551785e-05, "loss": 0.486, "step": 7674 }, { "epoch": 1.0936164149330294, "grad_norm": 1.3596343439590033, "learning_rate": 1.011440002357911e-05, "loss": 0.4054, "step": 7675 }, { "epoch": 1.0937589056711314, "grad_norm": 1.4068081017468939, "learning_rate": 1.0111913171530532e-05, "loss": 0.4514, "step": 7676 }, { "epoch": 1.0939013964092335, "grad_norm": 1.211060730370342, "learning_rate": 1.0109426312559873e-05, "loss": 0.4714, "step": 7677 }, { "epoch": 1.0940438871473355, "grad_norm": 1.2845725442769, "learning_rate": 1.0106939446820952e-05, "loss": 0.445, "step": 7678 }, { "epoch": 1.0941863778854375, "grad_norm": 2.0984234148413208, "learning_rate": 1.0104452574467586e-05, "loss": 0.448, "step": 7679 }, { "epoch": 1.0943288686235395, "grad_norm": 1.522839368579498, "learning_rate": 1.010196569565359e-05, "loss": 0.4642, "step": 7680 }, { "epoch": 1.0944713593616415, "grad_norm": 1.2378083346686664, "learning_rate": 1.0099478810532785e-05, "loss": 0.4227, "step": 7681 }, { "epoch": 1.0946138500997435, "grad_norm": 1.330013674544887, "learning_rate": 1.0096991919258996e-05, "loss": 0.4091, "step": 7682 }, { "epoch": 1.0947563408378456, "grad_norm": 1.2278399135289195, "learning_rate": 1.0094505021986036e-05, "loss": 0.4045, "step": 7683 }, { "epoch": 1.0948988315759476, "grad_norm": 1.4013257020961685, "learning_rate": 1.0092018118867728e-05, "loss": 0.4459, "step": 7684 }, { "epoch": 1.0950413223140496, "grad_norm": 1.383014821190559, "learning_rate": 1.0089531210057893e-05, "loss": 0.4154, "step": 7685 }, { "epoch": 1.0951838130521516, "grad_norm": 1.2730776914499404, "learning_rate": 1.0087044295710353e-05, "loss": 0.403, "step": 7686 }, { "epoch": 1.0953263037902536, "grad_norm": 1.402293253131784, "learning_rate": 1.0084557375978925e-05, "loss": 0.4211, "step": 7687 }, { "epoch": 1.0954687945283557, "grad_norm": 1.602392986275882, "learning_rate": 1.0082070451017432e-05, "loss": 0.4282, "step": 7688 }, { "epoch": 1.0956112852664577, "grad_norm": 1.5124717386954551, "learning_rate": 1.0079583520979694e-05, "loss": 0.4428, "step": 7689 }, { "epoch": 1.0957537760045597, "grad_norm": 1.1970116977375818, "learning_rate": 1.0077096586019544e-05, "loss": 0.3859, "step": 7690 }, { "epoch": 1.0958962667426617, "grad_norm": 1.4666081385519554, "learning_rate": 1.0074609646290792e-05, "loss": 0.4509, "step": 7691 }, { "epoch": 1.0960387574807637, "grad_norm": 1.5445332845556912, "learning_rate": 1.0072122701947264e-05, "loss": 0.4474, "step": 7692 }, { "epoch": 1.0961812482188658, "grad_norm": 1.4096583652152184, "learning_rate": 1.0069635753142787e-05, "loss": 0.4399, "step": 7693 }, { "epoch": 1.0963237389569678, "grad_norm": 1.3995970233496902, "learning_rate": 1.0067148800031184e-05, "loss": 0.4751, "step": 7694 }, { "epoch": 1.0964662296950698, "grad_norm": 1.2967159846407819, "learning_rate": 1.0064661842766275e-05, "loss": 0.3979, "step": 7695 }, { "epoch": 1.0966087204331718, "grad_norm": 1.3024778001861315, "learning_rate": 1.0062174881501881e-05, "loss": 0.4276, "step": 7696 }, { "epoch": 1.0967512111712738, "grad_norm": 1.5376740820865582, "learning_rate": 1.0059687916391836e-05, "loss": 0.4549, "step": 7697 }, { "epoch": 1.0968937019093759, "grad_norm": 1.3183327976201056, "learning_rate": 1.0057200947589955e-05, "loss": 0.4507, "step": 7698 }, { "epoch": 1.0970361926474779, "grad_norm": 1.4571214345348311, "learning_rate": 1.005471397525007e-05, "loss": 0.4001, "step": 7699 }, { "epoch": 1.09717868338558, "grad_norm": 1.321812424607501, "learning_rate": 1.0052226999526001e-05, "loss": 0.4264, "step": 7700 }, { "epoch": 1.097321174123682, "grad_norm": 1.3202884411301723, "learning_rate": 1.0049740020571577e-05, "loss": 0.4449, "step": 7701 }, { "epoch": 1.097463664861784, "grad_norm": 1.264436766214335, "learning_rate": 1.0047253038540618e-05, "loss": 0.4552, "step": 7702 }, { "epoch": 1.097606155599886, "grad_norm": 1.956379962327765, "learning_rate": 1.004476605358695e-05, "loss": 0.471, "step": 7703 }, { "epoch": 1.097748646337988, "grad_norm": 1.2597479614421643, "learning_rate": 1.0042279065864404e-05, "loss": 0.4089, "step": 7704 }, { "epoch": 1.09789113707609, "grad_norm": 1.301003388103893, "learning_rate": 1.0039792075526804e-05, "loss": 0.4427, "step": 7705 }, { "epoch": 1.098033627814192, "grad_norm": 1.2307274091591622, "learning_rate": 1.0037305082727973e-05, "loss": 0.4215, "step": 7706 }, { "epoch": 1.098176118552294, "grad_norm": 1.21845281971565, "learning_rate": 1.0034818087621738e-05, "loss": 0.3874, "step": 7707 }, { "epoch": 1.098318609290396, "grad_norm": 1.471065061656921, "learning_rate": 1.0032331090361926e-05, "loss": 0.4554, "step": 7708 }, { "epoch": 1.098461100028498, "grad_norm": 1.5521528766724526, "learning_rate": 1.0029844091102365e-05, "loss": 0.4345, "step": 7709 }, { "epoch": 1.0986035907666, "grad_norm": 1.3068428393112947, "learning_rate": 1.0027357089996879e-05, "loss": 0.4204, "step": 7710 }, { "epoch": 1.098746081504702, "grad_norm": 1.2948323820624317, "learning_rate": 1.0024870087199292e-05, "loss": 0.3578, "step": 7711 }, { "epoch": 1.0988885722428041, "grad_norm": 1.1601849757582186, "learning_rate": 1.0022383082863438e-05, "loss": 0.4326, "step": 7712 }, { "epoch": 1.0990310629809061, "grad_norm": 1.4916911340056254, "learning_rate": 1.0019896077143139e-05, "loss": 0.4715, "step": 7713 }, { "epoch": 1.0991735537190084, "grad_norm": 1.5917826927492968, "learning_rate": 1.0017409070192224e-05, "loss": 0.4894, "step": 7714 }, { "epoch": 1.0993160444571104, "grad_norm": 1.4454193954644183, "learning_rate": 1.0014922062164515e-05, "loss": 0.484, "step": 7715 }, { "epoch": 1.0994585351952124, "grad_norm": 1.4011281348396676, "learning_rate": 1.0012435053213847e-05, "loss": 0.4294, "step": 7716 }, { "epoch": 1.0996010259333144, "grad_norm": 1.452971109308412, "learning_rate": 1.0009948043494043e-05, "loss": 0.4621, "step": 7717 }, { "epoch": 1.0997435166714165, "grad_norm": 1.2903840827387814, "learning_rate": 1.0007461033158924e-05, "loss": 0.4562, "step": 7718 }, { "epoch": 1.0998860074095185, "grad_norm": 1.503965418872551, "learning_rate": 1.0004974022362331e-05, "loss": 0.4065, "step": 7719 }, { "epoch": 1.1000284981476205, "grad_norm": 1.451933123363865, "learning_rate": 1.000248701125808e-05, "loss": 0.4451, "step": 7720 }, { "epoch": 1.1001709888857225, "grad_norm": 1.4215665662393613, "learning_rate": 1e-05, "loss": 0.4472, "step": 7721 }, { "epoch": 1.1003134796238245, "grad_norm": 1.3224304565566671, "learning_rate": 9.99751298874192e-06, "loss": 0.4326, "step": 7722 }, { "epoch": 1.1004559703619265, "grad_norm": 1.3487846490477988, "learning_rate": 9.995025977637672e-06, "loss": 0.4583, "step": 7723 }, { "epoch": 1.1005984611000286, "grad_norm": 1.332054660741854, "learning_rate": 9.992538966841075e-06, "loss": 0.4209, "step": 7724 }, { "epoch": 1.1007409518381306, "grad_norm": 1.3138435136746127, "learning_rate": 9.990051956505962e-06, "loss": 0.4282, "step": 7725 }, { "epoch": 1.1008834425762326, "grad_norm": 1.231753820912484, "learning_rate": 9.987564946786155e-06, "loss": 0.4461, "step": 7726 }, { "epoch": 1.1010259333143346, "grad_norm": 1.8302134202439109, "learning_rate": 9.985077937835488e-06, "loss": 0.4675, "step": 7727 }, { "epoch": 1.1011684240524366, "grad_norm": 1.303958072506779, "learning_rate": 9.982590929807781e-06, "loss": 0.4445, "step": 7728 }, { "epoch": 1.1013109147905387, "grad_norm": 1.520688452514819, "learning_rate": 9.980103922856861e-06, "loss": 0.4836, "step": 7729 }, { "epoch": 1.1014534055286407, "grad_norm": 1.4797048709958898, "learning_rate": 9.977616917136565e-06, "loss": 0.492, "step": 7730 }, { "epoch": 1.1015958962667427, "grad_norm": 1.2428801696147882, "learning_rate": 9.97512991280071e-06, "loss": 0.4203, "step": 7731 }, { "epoch": 1.1017383870048447, "grad_norm": 1.2938579694731007, "learning_rate": 9.972642910003128e-06, "loss": 0.4395, "step": 7732 }, { "epoch": 1.1018808777429467, "grad_norm": 1.2883197098990928, "learning_rate": 9.970155908897637e-06, "loss": 0.4221, "step": 7733 }, { "epoch": 1.1020233684810488, "grad_norm": 1.4536223535130643, "learning_rate": 9.967668909638078e-06, "loss": 0.466, "step": 7734 }, { "epoch": 1.1021658592191508, "grad_norm": 1.4167578248601758, "learning_rate": 9.965181912378265e-06, "loss": 0.4923, "step": 7735 }, { "epoch": 1.1023083499572528, "grad_norm": 1.411658069974503, "learning_rate": 9.962694917272028e-06, "loss": 0.4325, "step": 7736 }, { "epoch": 1.1024508406953548, "grad_norm": 1.4003907051401197, "learning_rate": 9.960207924473198e-06, "loss": 0.4461, "step": 7737 }, { "epoch": 1.1025933314334568, "grad_norm": 1.3405896930843875, "learning_rate": 9.957720934135598e-06, "loss": 0.4032, "step": 7738 }, { "epoch": 1.1027358221715589, "grad_norm": 1.4909631951219295, "learning_rate": 9.955233946413052e-06, "loss": 0.5267, "step": 7739 }, { "epoch": 1.1028783129096609, "grad_norm": 1.4187385111404656, "learning_rate": 9.952746961459385e-06, "loss": 0.4747, "step": 7740 }, { "epoch": 1.103020803647763, "grad_norm": 1.5322711839031342, "learning_rate": 9.950259979428428e-06, "loss": 0.4279, "step": 7741 }, { "epoch": 1.103163294385865, "grad_norm": 1.3180915890719056, "learning_rate": 9.947773000474e-06, "loss": 0.4587, "step": 7742 }, { "epoch": 1.103305785123967, "grad_norm": 1.4315419923628565, "learning_rate": 9.945286024749931e-06, "loss": 0.5232, "step": 7743 }, { "epoch": 1.103448275862069, "grad_norm": 1.3280932162149468, "learning_rate": 9.942799052410046e-06, "loss": 0.3964, "step": 7744 }, { "epoch": 1.103590766600171, "grad_norm": 1.402279904224908, "learning_rate": 9.940312083608167e-06, "loss": 0.4671, "step": 7745 }, { "epoch": 1.103733257338273, "grad_norm": 1.467995515958638, "learning_rate": 9.937825118498122e-06, "loss": 0.3978, "step": 7746 }, { "epoch": 1.103875748076375, "grad_norm": 1.4477440308875256, "learning_rate": 9.93533815723373e-06, "loss": 0.4952, "step": 7747 }, { "epoch": 1.104018238814477, "grad_norm": 1.4448203872659582, "learning_rate": 9.932851199968821e-06, "loss": 0.4321, "step": 7748 }, { "epoch": 1.104160729552579, "grad_norm": 1.4409715437096857, "learning_rate": 9.930364246857216e-06, "loss": 0.4276, "step": 7749 }, { "epoch": 1.104303220290681, "grad_norm": 1.2562756124992553, "learning_rate": 9.927877298052741e-06, "loss": 0.4328, "step": 7750 }, { "epoch": 1.104445711028783, "grad_norm": 1.2517751766134386, "learning_rate": 9.925390353709211e-06, "loss": 0.4205, "step": 7751 }, { "epoch": 1.104588201766885, "grad_norm": 1.5586050781745828, "learning_rate": 9.922903413980461e-06, "loss": 0.5112, "step": 7752 }, { "epoch": 1.1047306925049871, "grad_norm": 1.5233873389198007, "learning_rate": 9.920416479020308e-06, "loss": 0.4384, "step": 7753 }, { "epoch": 1.1048731832430891, "grad_norm": 1.3905777203446854, "learning_rate": 9.917929548982571e-06, "loss": 0.4669, "step": 7754 }, { "epoch": 1.1050156739811912, "grad_norm": 4.040377055564319, "learning_rate": 9.915442624021081e-06, "loss": 0.405, "step": 7755 }, { "epoch": 1.1051581647192932, "grad_norm": 1.3981168276873903, "learning_rate": 9.91295570428965e-06, "loss": 0.4386, "step": 7756 }, { "epoch": 1.1053006554573952, "grad_norm": 1.4226992120781763, "learning_rate": 9.910468789942112e-06, "loss": 0.471, "step": 7757 }, { "epoch": 1.1054431461954972, "grad_norm": 1.3329364837370647, "learning_rate": 9.907981881132275e-06, "loss": 0.4775, "step": 7758 }, { "epoch": 1.1055856369335992, "grad_norm": 1.2953688970063904, "learning_rate": 9.905494978013964e-06, "loss": 0.4032, "step": 7759 }, { "epoch": 1.1057281276717013, "grad_norm": 1.4579645027277228, "learning_rate": 9.903008080741007e-06, "loss": 0.4823, "step": 7760 }, { "epoch": 1.1058706184098033, "grad_norm": 1.2696711789980906, "learning_rate": 9.900521189467217e-06, "loss": 0.469, "step": 7761 }, { "epoch": 1.1060131091479053, "grad_norm": 1.3210688319468082, "learning_rate": 9.898034304346416e-06, "loss": 0.4936, "step": 7762 }, { "epoch": 1.1061555998860073, "grad_norm": 1.3747751632500327, "learning_rate": 9.895547425532418e-06, "loss": 0.5042, "step": 7763 }, { "epoch": 1.1062980906241093, "grad_norm": 1.3126963371440696, "learning_rate": 9.893060553179053e-06, "loss": 0.4641, "step": 7764 }, { "epoch": 1.1064405813622114, "grad_norm": 1.2969277287829524, "learning_rate": 9.89057368744013e-06, "loss": 0.4502, "step": 7765 }, { "epoch": 1.1065830721003134, "grad_norm": 1.3844977329155315, "learning_rate": 9.88808682846947e-06, "loss": 0.4774, "step": 7766 }, { "epoch": 1.1067255628384154, "grad_norm": 1.4450691900878603, "learning_rate": 9.885599976420894e-06, "loss": 0.4916, "step": 7767 }, { "epoch": 1.1068680535765176, "grad_norm": 1.8916376936842436, "learning_rate": 9.883113131448215e-06, "loss": 0.423, "step": 7768 }, { "epoch": 1.1070105443146196, "grad_norm": 1.2455970292830554, "learning_rate": 9.880626293705255e-06, "loss": 0.4171, "step": 7769 }, { "epoch": 1.1071530350527217, "grad_norm": 1.3217654171671143, "learning_rate": 9.878139463345822e-06, "loss": 0.4636, "step": 7770 }, { "epoch": 1.1072955257908237, "grad_norm": 1.3081801897627368, "learning_rate": 9.875652640523743e-06, "loss": 0.444, "step": 7771 }, { "epoch": 1.1074380165289257, "grad_norm": 1.2796775351731333, "learning_rate": 9.873165825392826e-06, "loss": 0.4333, "step": 7772 }, { "epoch": 1.1075805072670277, "grad_norm": 1.6008227317033765, "learning_rate": 9.870679018106886e-06, "loss": 0.5285, "step": 7773 }, { "epoch": 1.1077229980051297, "grad_norm": 1.3154552019414212, "learning_rate": 9.868192218819743e-06, "loss": 0.4263, "step": 7774 }, { "epoch": 1.1078654887432318, "grad_norm": 1.2886496630201303, "learning_rate": 9.865705427685207e-06, "loss": 0.4488, "step": 7775 }, { "epoch": 1.1080079794813338, "grad_norm": 1.5780586372168044, "learning_rate": 9.863218644857094e-06, "loss": 0.46, "step": 7776 }, { "epoch": 1.1081504702194358, "grad_norm": 1.5336968867953817, "learning_rate": 9.860731870489212e-06, "loss": 0.4477, "step": 7777 }, { "epoch": 1.1082929609575378, "grad_norm": 1.2803967357568242, "learning_rate": 9.858245104735381e-06, "loss": 0.4297, "step": 7778 }, { "epoch": 1.1084354516956398, "grad_norm": 1.3743393827295425, "learning_rate": 9.855758347749409e-06, "loss": 0.4429, "step": 7779 }, { "epoch": 1.1085779424337419, "grad_norm": 1.343843721422124, "learning_rate": 9.853271599685103e-06, "loss": 0.4291, "step": 7780 }, { "epoch": 1.1087204331718439, "grad_norm": 1.4690300105070668, "learning_rate": 9.850784860696283e-06, "loss": 0.4663, "step": 7781 }, { "epoch": 1.108862923909946, "grad_norm": 1.807627188658373, "learning_rate": 9.848298130936755e-06, "loss": 0.4156, "step": 7782 }, { "epoch": 1.109005414648048, "grad_norm": 1.353276386253271, "learning_rate": 9.84581141056033e-06, "loss": 0.4553, "step": 7783 }, { "epoch": 1.10914790538615, "grad_norm": 1.2834036897127772, "learning_rate": 9.843324699720814e-06, "loss": 0.4364, "step": 7784 }, { "epoch": 1.109290396124252, "grad_norm": 1.327042827783559, "learning_rate": 9.84083799857202e-06, "loss": 0.3619, "step": 7785 }, { "epoch": 1.109432886862354, "grad_norm": 1.513343233605633, "learning_rate": 9.838351307267754e-06, "loss": 0.4169, "step": 7786 }, { "epoch": 1.109575377600456, "grad_norm": 1.6148272261479542, "learning_rate": 9.83586462596182e-06, "loss": 0.5251, "step": 7787 }, { "epoch": 1.109717868338558, "grad_norm": 1.2537496065053348, "learning_rate": 9.833377954808034e-06, "loss": 0.4169, "step": 7788 }, { "epoch": 1.10986035907666, "grad_norm": 1.3322168478749434, "learning_rate": 9.83089129396019e-06, "loss": 0.4822, "step": 7789 }, { "epoch": 1.110002849814762, "grad_norm": 1.2184020220880176, "learning_rate": 9.828404643572108e-06, "loss": 0.4275, "step": 7790 }, { "epoch": 1.110145340552864, "grad_norm": 1.4089193933755353, "learning_rate": 9.825918003797579e-06, "loss": 0.4099, "step": 7791 }, { "epoch": 1.110287831290966, "grad_norm": 1.3482103427640797, "learning_rate": 9.823431374790417e-06, "loss": 0.491, "step": 7792 }, { "epoch": 1.110430322029068, "grad_norm": 1.2085912844591153, "learning_rate": 9.820944756704417e-06, "loss": 0.3626, "step": 7793 }, { "epoch": 1.1105728127671701, "grad_norm": 1.3710395079326958, "learning_rate": 9.81845814969339e-06, "loss": 0.4234, "step": 7794 }, { "epoch": 1.1107153035052721, "grad_norm": 1.3923649370197588, "learning_rate": 9.815971553911136e-06, "loss": 0.4563, "step": 7795 }, { "epoch": 1.1108577942433742, "grad_norm": 1.497977093857856, "learning_rate": 9.813484969511451e-06, "loss": 0.4401, "step": 7796 }, { "epoch": 1.1110002849814762, "grad_norm": 1.3591065073263182, "learning_rate": 9.810998396648147e-06, "loss": 0.4756, "step": 7797 }, { "epoch": 1.1111427757195782, "grad_norm": 1.4225057037157047, "learning_rate": 9.808511835475014e-06, "loss": 0.4309, "step": 7798 }, { "epoch": 1.1112852664576802, "grad_norm": 1.1954958688000703, "learning_rate": 9.806025286145858e-06, "loss": 0.4297, "step": 7799 }, { "epoch": 1.1114277571957822, "grad_norm": 1.2722829772428295, "learning_rate": 9.80353874881447e-06, "loss": 0.3924, "step": 7800 }, { "epoch": 1.1115702479338843, "grad_norm": 1.2808372462445523, "learning_rate": 9.801052223634656e-06, "loss": 0.4907, "step": 7801 }, { "epoch": 1.1117127386719863, "grad_norm": 1.2378284517345401, "learning_rate": 9.798565710760209e-06, "loss": 0.3737, "step": 7802 }, { "epoch": 1.1118552294100883, "grad_norm": 1.2654039773205932, "learning_rate": 9.796079210344924e-06, "loss": 0.3873, "step": 7803 }, { "epoch": 1.1119977201481903, "grad_norm": 1.3921792783463922, "learning_rate": 9.793592722542603e-06, "loss": 0.4301, "step": 7804 }, { "epoch": 1.1121402108862923, "grad_norm": 1.3424777313397211, "learning_rate": 9.791106247507034e-06, "loss": 0.4227, "step": 7805 }, { "epoch": 1.1122827016243944, "grad_norm": 1.2955685435065185, "learning_rate": 9.788619785392015e-06, "loss": 0.4761, "step": 7806 }, { "epoch": 1.1124251923624964, "grad_norm": 1.2061234467750355, "learning_rate": 9.786133336351335e-06, "loss": 0.4095, "step": 7807 }, { "epoch": 1.1125676831005984, "grad_norm": 1.3265922995311292, "learning_rate": 9.783646900538794e-06, "loss": 0.3884, "step": 7808 }, { "epoch": 1.1127101738387004, "grad_norm": 1.2727795908405943, "learning_rate": 9.781160478108177e-06, "loss": 0.433, "step": 7809 }, { "epoch": 1.1128526645768024, "grad_norm": 1.6844453043967704, "learning_rate": 9.778674069213274e-06, "loss": 0.4127, "step": 7810 }, { "epoch": 1.1129951553149044, "grad_norm": 1.405617151128812, "learning_rate": 9.776187674007883e-06, "loss": 0.4546, "step": 7811 }, { "epoch": 1.1131376460530065, "grad_norm": 1.5656739143239433, "learning_rate": 9.773701292645786e-06, "loss": 0.4464, "step": 7812 }, { "epoch": 1.1132801367911085, "grad_norm": 1.3360050138869497, "learning_rate": 9.771214925280776e-06, "loss": 0.3924, "step": 7813 }, { "epoch": 1.1134226275292105, "grad_norm": 1.4479286711863444, "learning_rate": 9.768728572066632e-06, "loss": 0.4684, "step": 7814 }, { "epoch": 1.1135651182673125, "grad_norm": 1.318414711512742, "learning_rate": 9.766242233157153e-06, "loss": 0.4136, "step": 7815 }, { "epoch": 1.1137076090054145, "grad_norm": 1.3627201945549008, "learning_rate": 9.763755908706114e-06, "loss": 0.4182, "step": 7816 }, { "epoch": 1.1138500997435168, "grad_norm": 1.4296588633324614, "learning_rate": 9.761269598867303e-06, "loss": 0.4604, "step": 7817 }, { "epoch": 1.1139925904816188, "grad_norm": 1.3762334974350083, "learning_rate": 9.758783303794508e-06, "loss": 0.3859, "step": 7818 }, { "epoch": 1.1141350812197208, "grad_norm": 1.3001622516117757, "learning_rate": 9.756297023641506e-06, "loss": 0.4377, "step": 7819 }, { "epoch": 1.1142775719578228, "grad_norm": 1.3625546895492724, "learning_rate": 9.753810758562084e-06, "loss": 0.4344, "step": 7820 }, { "epoch": 1.1144200626959249, "grad_norm": 1.5351152216667032, "learning_rate": 9.751324508710019e-06, "loss": 0.4492, "step": 7821 }, { "epoch": 1.1145625534340269, "grad_norm": 1.2994955299378192, "learning_rate": 9.748838274239095e-06, "loss": 0.4175, "step": 7822 }, { "epoch": 1.114705044172129, "grad_norm": 1.3693731991771063, "learning_rate": 9.746352055303087e-06, "loss": 0.4525, "step": 7823 }, { "epoch": 1.114847534910231, "grad_norm": 1.397356109112275, "learning_rate": 9.743865852055772e-06, "loss": 0.4395, "step": 7824 }, { "epoch": 1.114990025648333, "grad_norm": 1.3037004056624926, "learning_rate": 9.741379664650937e-06, "loss": 0.4097, "step": 7825 }, { "epoch": 1.115132516386435, "grad_norm": 1.5345411008427623, "learning_rate": 9.738893493242345e-06, "loss": 0.4527, "step": 7826 }, { "epoch": 1.115275007124537, "grad_norm": 1.4608134119919334, "learning_rate": 9.736407337983786e-06, "loss": 0.4568, "step": 7827 }, { "epoch": 1.115417497862639, "grad_norm": 1.3031585070447194, "learning_rate": 9.733921199029023e-06, "loss": 0.4056, "step": 7828 }, { "epoch": 1.115559988600741, "grad_norm": 1.392058542843566, "learning_rate": 9.731435076531835e-06, "loss": 0.4766, "step": 7829 }, { "epoch": 1.115702479338843, "grad_norm": 1.4363051165095524, "learning_rate": 9.728948970645987e-06, "loss": 0.4384, "step": 7830 }, { "epoch": 1.115844970076945, "grad_norm": 1.4357783089464096, "learning_rate": 9.726462881525257e-06, "loss": 0.4521, "step": 7831 }, { "epoch": 1.115987460815047, "grad_norm": 1.3250975857280078, "learning_rate": 9.723976809323416e-06, "loss": 0.4384, "step": 7832 }, { "epoch": 1.116129951553149, "grad_norm": 1.3678743237617905, "learning_rate": 9.721490754194227e-06, "loss": 0.4169, "step": 7833 }, { "epoch": 1.116272442291251, "grad_norm": 1.4245645787506667, "learning_rate": 9.719004716291466e-06, "loss": 0.4569, "step": 7834 }, { "epoch": 1.1164149330293531, "grad_norm": 1.3737696379251008, "learning_rate": 9.716518695768892e-06, "loss": 0.4409, "step": 7835 }, { "epoch": 1.1165574237674551, "grad_norm": 1.4106567393170357, "learning_rate": 9.71403269278028e-06, "loss": 0.4099, "step": 7836 }, { "epoch": 1.1166999145055572, "grad_norm": 1.3379131779507976, "learning_rate": 9.711546707479383e-06, "loss": 0.4264, "step": 7837 }, { "epoch": 1.1168424052436592, "grad_norm": 1.3261678134368782, "learning_rate": 9.709060740019974e-06, "loss": 0.4225, "step": 7838 }, { "epoch": 1.1169848959817612, "grad_norm": 1.3960952874732304, "learning_rate": 9.706574790555816e-06, "loss": 0.4356, "step": 7839 }, { "epoch": 1.1171273867198632, "grad_norm": 1.2814725693012887, "learning_rate": 9.704088859240662e-06, "loss": 0.4041, "step": 7840 }, { "epoch": 1.1172698774579652, "grad_norm": 1.533716588756154, "learning_rate": 9.701602946228284e-06, "loss": 0.489, "step": 7841 }, { "epoch": 1.1174123681960673, "grad_norm": 1.4151155997645384, "learning_rate": 9.699117051672433e-06, "loss": 0.5021, "step": 7842 }, { "epoch": 1.1175548589341693, "grad_norm": 1.3394598724918914, "learning_rate": 9.696631175726871e-06, "loss": 0.4653, "step": 7843 }, { "epoch": 1.1176973496722713, "grad_norm": 1.4254294346369822, "learning_rate": 9.69414531854535e-06, "loss": 0.5142, "step": 7844 }, { "epoch": 1.1178398404103733, "grad_norm": 1.4223663313525639, "learning_rate": 9.69165948028163e-06, "loss": 0.4805, "step": 7845 }, { "epoch": 1.1179823311484753, "grad_norm": 1.3779317850265083, "learning_rate": 9.68917366108947e-06, "loss": 0.4602, "step": 7846 }, { "epoch": 1.1181248218865774, "grad_norm": 1.3059602748915997, "learning_rate": 9.686687861122613e-06, "loss": 0.4364, "step": 7847 }, { "epoch": 1.1182673126246794, "grad_norm": 1.2676284346664666, "learning_rate": 9.684202080534822e-06, "loss": 0.4115, "step": 7848 }, { "epoch": 1.1184098033627814, "grad_norm": 1.3156947022040508, "learning_rate": 9.68171631947984e-06, "loss": 0.4023, "step": 7849 }, { "epoch": 1.1185522941008834, "grad_norm": 1.292984899178208, "learning_rate": 9.679230578111422e-06, "loss": 0.4522, "step": 7850 }, { "epoch": 1.1186947848389854, "grad_norm": 1.2774341453588043, "learning_rate": 9.676744856583312e-06, "loss": 0.4193, "step": 7851 }, { "epoch": 1.1188372755770875, "grad_norm": 1.247911440194706, "learning_rate": 9.674259155049262e-06, "loss": 0.4853, "step": 7852 }, { "epoch": 1.1189797663151895, "grad_norm": 1.3925718661845392, "learning_rate": 9.671773473663017e-06, "loss": 0.4359, "step": 7853 }, { "epoch": 1.1191222570532915, "grad_norm": 1.253222219608727, "learning_rate": 9.66928781257832e-06, "loss": 0.4047, "step": 7854 }, { "epoch": 1.1192647477913935, "grad_norm": 1.3824245764048593, "learning_rate": 9.666802171948917e-06, "loss": 0.4241, "step": 7855 }, { "epoch": 1.1194072385294955, "grad_norm": 1.3168550758755393, "learning_rate": 9.664316551928551e-06, "loss": 0.4121, "step": 7856 }, { "epoch": 1.1195497292675975, "grad_norm": 1.6389466285075582, "learning_rate": 9.661830952670963e-06, "loss": 0.4613, "step": 7857 }, { "epoch": 1.1196922200056996, "grad_norm": 1.2399648905698835, "learning_rate": 9.659345374329886e-06, "loss": 0.3958, "step": 7858 }, { "epoch": 1.1198347107438016, "grad_norm": 1.3355772821612104, "learning_rate": 9.65685981705907e-06, "loss": 0.4324, "step": 7859 }, { "epoch": 1.1199772014819036, "grad_norm": 1.5898400635022134, "learning_rate": 9.654374281012243e-06, "loss": 0.4585, "step": 7860 }, { "epoch": 1.1201196922200056, "grad_norm": 1.5306177234879876, "learning_rate": 9.651888766343144e-06, "loss": 0.4231, "step": 7861 }, { "epoch": 1.1202621829581076, "grad_norm": 1.4018936560848154, "learning_rate": 9.649403273205513e-06, "loss": 0.4359, "step": 7862 }, { "epoch": 1.1204046736962097, "grad_norm": 1.5401832733534533, "learning_rate": 9.646917801753074e-06, "loss": 0.4895, "step": 7863 }, { "epoch": 1.1205471644343117, "grad_norm": 1.760282573003568, "learning_rate": 9.644432352139568e-06, "loss": 0.5235, "step": 7864 }, { "epoch": 1.1206896551724137, "grad_norm": 1.3505608301741165, "learning_rate": 9.641946924518717e-06, "loss": 0.4143, "step": 7865 }, { "epoch": 1.1208321459105157, "grad_norm": 1.5220053432683283, "learning_rate": 9.639461519044261e-06, "loss": 0.5009, "step": 7866 }, { "epoch": 1.1209746366486177, "grad_norm": 1.410196344596612, "learning_rate": 9.636976135869914e-06, "loss": 0.4466, "step": 7867 }, { "epoch": 1.1211171273867198, "grad_norm": 1.3295052791594606, "learning_rate": 9.634490775149415e-06, "loss": 0.4837, "step": 7868 }, { "epoch": 1.1212596181248218, "grad_norm": 1.4633442046463212, "learning_rate": 9.632005437036484e-06, "loss": 0.4399, "step": 7869 }, { "epoch": 1.1214021088629238, "grad_norm": 1.1450364958979926, "learning_rate": 9.629520121684841e-06, "loss": 0.3725, "step": 7870 }, { "epoch": 1.1215445996010258, "grad_norm": 1.2736249402213935, "learning_rate": 9.627034829248217e-06, "loss": 0.4282, "step": 7871 }, { "epoch": 1.121687090339128, "grad_norm": 1.3921014381174364, "learning_rate": 9.624549559880328e-06, "loss": 0.4252, "step": 7872 }, { "epoch": 1.12182958107723, "grad_norm": 1.2991694032089947, "learning_rate": 9.622064313734894e-06, "loss": 0.3803, "step": 7873 }, { "epoch": 1.121972071815332, "grad_norm": 1.3916606042963622, "learning_rate": 9.619579090965629e-06, "loss": 0.4712, "step": 7874 }, { "epoch": 1.1221145625534341, "grad_norm": 1.3856152812381488, "learning_rate": 9.617093891726255e-06, "loss": 0.4298, "step": 7875 }, { "epoch": 1.1222570532915361, "grad_norm": 1.5218231343508823, "learning_rate": 9.61460871617049e-06, "loss": 0.42, "step": 7876 }, { "epoch": 1.1223995440296382, "grad_norm": 1.5117140078491975, "learning_rate": 9.612123564452038e-06, "loss": 0.3944, "step": 7877 }, { "epoch": 1.1225420347677402, "grad_norm": 1.303756727047439, "learning_rate": 9.60963843672462e-06, "loss": 0.4627, "step": 7878 }, { "epoch": 1.1226845255058422, "grad_norm": 1.3004741255573864, "learning_rate": 9.607153333141943e-06, "loss": 0.3905, "step": 7879 }, { "epoch": 1.1228270162439442, "grad_norm": 1.3714363035554942, "learning_rate": 9.604668253857716e-06, "loss": 0.4326, "step": 7880 }, { "epoch": 1.1229695069820462, "grad_norm": 1.4171624536327985, "learning_rate": 9.602183199025645e-06, "loss": 0.4703, "step": 7881 }, { "epoch": 1.1231119977201482, "grad_norm": 1.3460084764000966, "learning_rate": 9.599698168799441e-06, "loss": 0.4541, "step": 7882 }, { "epoch": 1.1232544884582503, "grad_norm": 1.9250904418237482, "learning_rate": 9.597213163332808e-06, "loss": 0.464, "step": 7883 }, { "epoch": 1.1233969791963523, "grad_norm": 1.521631456819819, "learning_rate": 9.594728182779442e-06, "loss": 0.4607, "step": 7884 }, { "epoch": 1.1235394699344543, "grad_norm": 1.600430518831559, "learning_rate": 9.592243227293057e-06, "loss": 0.4231, "step": 7885 }, { "epoch": 1.1236819606725563, "grad_norm": 1.4126131307200565, "learning_rate": 9.589758297027342e-06, "loss": 0.4399, "step": 7886 }, { "epoch": 1.1238244514106583, "grad_norm": 1.5707976847404008, "learning_rate": 9.587273392136004e-06, "loss": 0.4076, "step": 7887 }, { "epoch": 1.1239669421487604, "grad_norm": 1.3057486859488414, "learning_rate": 9.584788512772729e-06, "loss": 0.4054, "step": 7888 }, { "epoch": 1.1241094328868624, "grad_norm": 1.2469878480281158, "learning_rate": 9.582303659091222e-06, "loss": 0.4329, "step": 7889 }, { "epoch": 1.1242519236249644, "grad_norm": 1.5843853371363332, "learning_rate": 9.579818831245175e-06, "loss": 0.5096, "step": 7890 }, { "epoch": 1.1243944143630664, "grad_norm": 1.4394152997046012, "learning_rate": 9.577334029388276e-06, "loss": 0.4481, "step": 7891 }, { "epoch": 1.1245369051011684, "grad_norm": 1.2464255782903557, "learning_rate": 9.574849253674224e-06, "loss": 0.3578, "step": 7892 }, { "epoch": 1.1246793958392705, "grad_norm": 1.3822620344375642, "learning_rate": 9.572364504256698e-06, "loss": 0.3961, "step": 7893 }, { "epoch": 1.1248218865773725, "grad_norm": 1.317532068103885, "learning_rate": 9.569879781289395e-06, "loss": 0.4184, "step": 7894 }, { "epoch": 1.1249643773154745, "grad_norm": 1.2357243703717045, "learning_rate": 9.56739508492599e-06, "loss": 0.3653, "step": 7895 }, { "epoch": 1.1251068680535765, "grad_norm": 1.402240160796247, "learning_rate": 9.564910415320174e-06, "loss": 0.5106, "step": 7896 }, { "epoch": 1.1252493587916785, "grad_norm": 1.4411577701159939, "learning_rate": 9.56242577262563e-06, "loss": 0.5126, "step": 7897 }, { "epoch": 1.1253918495297806, "grad_norm": 1.4250036587619501, "learning_rate": 9.559941156996036e-06, "loss": 0.4291, "step": 7898 }, { "epoch": 1.1255343402678826, "grad_norm": 1.6137992808466899, "learning_rate": 9.557456568585073e-06, "loss": 0.4084, "step": 7899 }, { "epoch": 1.1256768310059846, "grad_norm": 1.3458418795353448, "learning_rate": 9.554972007546416e-06, "loss": 0.4412, "step": 7900 }, { "epoch": 1.1258193217440866, "grad_norm": 1.426117738930924, "learning_rate": 9.552487474033745e-06, "loss": 0.5066, "step": 7901 }, { "epoch": 1.1259618124821886, "grad_norm": 1.1969617976860512, "learning_rate": 9.550002968200728e-06, "loss": 0.4209, "step": 7902 }, { "epoch": 1.1261043032202906, "grad_norm": 1.4478787657133974, "learning_rate": 9.547518490201039e-06, "loss": 0.425, "step": 7903 }, { "epoch": 1.1262467939583927, "grad_norm": 1.3428525148156065, "learning_rate": 9.545034040188353e-06, "loss": 0.4493, "step": 7904 }, { "epoch": 1.1263892846964947, "grad_norm": 1.3653056782207633, "learning_rate": 9.542549618316335e-06, "loss": 0.4383, "step": 7905 }, { "epoch": 1.1265317754345967, "grad_norm": 1.3500429226551751, "learning_rate": 9.540065224738654e-06, "loss": 0.4263, "step": 7906 }, { "epoch": 1.1266742661726987, "grad_norm": 1.3652636980607522, "learning_rate": 9.537580859608971e-06, "loss": 0.4697, "step": 7907 }, { "epoch": 1.1268167569108007, "grad_norm": 1.3446553442497018, "learning_rate": 9.535096523080955e-06, "loss": 0.4167, "step": 7908 }, { "epoch": 1.1269592476489028, "grad_norm": 1.2776734067765014, "learning_rate": 9.532612215308266e-06, "loss": 0.4757, "step": 7909 }, { "epoch": 1.1271017383870048, "grad_norm": 1.7090945036015492, "learning_rate": 9.530127936444564e-06, "loss": 0.4616, "step": 7910 }, { "epoch": 1.1272442291251068, "grad_norm": 1.3328776053522313, "learning_rate": 9.527643686643502e-06, "loss": 0.4329, "step": 7911 }, { "epoch": 1.1273867198632088, "grad_norm": 1.5097436156211763, "learning_rate": 9.525159466058745e-06, "loss": 0.4149, "step": 7912 }, { "epoch": 1.1275292106013108, "grad_norm": 1.552467452519273, "learning_rate": 9.522675274843944e-06, "loss": 0.4774, "step": 7913 }, { "epoch": 1.1276717013394129, "grad_norm": 1.5841866513342782, "learning_rate": 9.520191113152749e-06, "loss": 0.485, "step": 7914 }, { "epoch": 1.1278141920775149, "grad_norm": 1.3893052340757204, "learning_rate": 9.517706981138817e-06, "loss": 0.3754, "step": 7915 }, { "epoch": 1.127956682815617, "grad_norm": 1.548525137301463, "learning_rate": 9.515222878955793e-06, "loss": 0.4675, "step": 7916 }, { "epoch": 1.128099173553719, "grad_norm": 1.3675238492327768, "learning_rate": 9.512738806757327e-06, "loss": 0.4636, "step": 7917 }, { "epoch": 1.1282416642918212, "grad_norm": 1.450424044999027, "learning_rate": 9.510254764697057e-06, "loss": 0.451, "step": 7918 }, { "epoch": 1.1283841550299232, "grad_norm": 1.3263547654670733, "learning_rate": 9.507770752928636e-06, "loss": 0.4334, "step": 7919 }, { "epoch": 1.1285266457680252, "grad_norm": 1.5529255822586012, "learning_rate": 9.505286771605702e-06, "loss": 0.5233, "step": 7920 }, { "epoch": 1.1286691365061272, "grad_norm": 1.3435907252754302, "learning_rate": 9.502802820881893e-06, "loss": 0.4291, "step": 7921 }, { "epoch": 1.1288116272442292, "grad_norm": 1.5223540507650466, "learning_rate": 9.500318900910852e-06, "loss": 0.4351, "step": 7922 }, { "epoch": 1.1289541179823313, "grad_norm": 1.3827950842940249, "learning_rate": 9.497835011846208e-06, "loss": 0.4423, "step": 7923 }, { "epoch": 1.1290966087204333, "grad_norm": 1.49726780650418, "learning_rate": 9.495351153841602e-06, "loss": 0.4952, "step": 7924 }, { "epoch": 1.1292390994585353, "grad_norm": 1.2641725040841048, "learning_rate": 9.49286732705066e-06, "loss": 0.4226, "step": 7925 }, { "epoch": 1.1293815901966373, "grad_norm": 1.2586008802210298, "learning_rate": 9.490383531627014e-06, "loss": 0.4387, "step": 7926 }, { "epoch": 1.1295240809347393, "grad_norm": 1.3827005565883972, "learning_rate": 9.4878997677243e-06, "loss": 0.5067, "step": 7927 }, { "epoch": 1.1296665716728413, "grad_norm": 1.30305328282091, "learning_rate": 9.485416035496131e-06, "loss": 0.4077, "step": 7928 }, { "epoch": 1.1298090624109434, "grad_norm": 1.4378624379755305, "learning_rate": 9.482932335096144e-06, "loss": 0.4798, "step": 7929 }, { "epoch": 1.1299515531490454, "grad_norm": 1.389999641462356, "learning_rate": 9.480448666677952e-06, "loss": 0.4221, "step": 7930 }, { "epoch": 1.1300940438871474, "grad_norm": 1.6733336341763472, "learning_rate": 9.477965030395183e-06, "loss": 0.4157, "step": 7931 }, { "epoch": 1.1302365346252494, "grad_norm": 1.2303555685778553, "learning_rate": 9.47548142640145e-06, "loss": 0.4625, "step": 7932 }, { "epoch": 1.1303790253633514, "grad_norm": 1.4307197385339825, "learning_rate": 9.47299785485037e-06, "loss": 0.4143, "step": 7933 }, { "epoch": 1.1305215161014535, "grad_norm": 1.3747551816001693, "learning_rate": 9.470514315895563e-06, "loss": 0.4167, "step": 7934 }, { "epoch": 1.1306640068395555, "grad_norm": 1.2760068014565582, "learning_rate": 9.468030809690634e-06, "loss": 0.3996, "step": 7935 }, { "epoch": 1.1308064975776575, "grad_norm": 1.415386073972435, "learning_rate": 9.465547336389199e-06, "loss": 0.4305, "step": 7936 }, { "epoch": 1.1309489883157595, "grad_norm": 1.3817273408962445, "learning_rate": 9.463063896144863e-06, "loss": 0.4488, "step": 7937 }, { "epoch": 1.1310914790538615, "grad_norm": 1.909654461465886, "learning_rate": 9.460580489111234e-06, "loss": 0.5001, "step": 7938 }, { "epoch": 1.1312339697919636, "grad_norm": 1.3839255033123674, "learning_rate": 9.458097115441916e-06, "loss": 0.4176, "step": 7939 }, { "epoch": 1.1313764605300656, "grad_norm": 1.3154060381355663, "learning_rate": 9.455613775290507e-06, "loss": 0.4035, "step": 7940 }, { "epoch": 1.1315189512681676, "grad_norm": 1.4804311118475348, "learning_rate": 9.453130468810618e-06, "loss": 0.4686, "step": 7941 }, { "epoch": 1.1316614420062696, "grad_norm": 1.3519338824232767, "learning_rate": 9.450647196155838e-06, "loss": 0.3996, "step": 7942 }, { "epoch": 1.1318039327443716, "grad_norm": 1.388654424472641, "learning_rate": 9.448163957479766e-06, "loss": 0.4605, "step": 7943 }, { "epoch": 1.1319464234824737, "grad_norm": 1.4066233179904715, "learning_rate": 9.445680752935993e-06, "loss": 0.4518, "step": 7944 }, { "epoch": 1.1320889142205757, "grad_norm": 1.3676406110374113, "learning_rate": 9.443197582678116e-06, "loss": 0.3884, "step": 7945 }, { "epoch": 1.1322314049586777, "grad_norm": 1.4670555219232, "learning_rate": 9.440714446859722e-06, "loss": 0.4789, "step": 7946 }, { "epoch": 1.1323738956967797, "grad_norm": 1.489985421388474, "learning_rate": 9.438231345634393e-06, "loss": 0.4504, "step": 7947 }, { "epoch": 1.1325163864348817, "grad_norm": 1.464284867769521, "learning_rate": 9.435748279155727e-06, "loss": 0.4606, "step": 7948 }, { "epoch": 1.1326588771729837, "grad_norm": 1.3731880628932482, "learning_rate": 9.433265247577296e-06, "loss": 0.4592, "step": 7949 }, { "epoch": 1.1328013679110858, "grad_norm": 1.5737706401794507, "learning_rate": 9.430782251052688e-06, "loss": 0.5022, "step": 7950 }, { "epoch": 1.1329438586491878, "grad_norm": 1.4956998778365087, "learning_rate": 9.428299289735475e-06, "loss": 0.441, "step": 7951 }, { "epoch": 1.1330863493872898, "grad_norm": 1.3840727980832346, "learning_rate": 9.42581636377924e-06, "loss": 0.4774, "step": 7952 }, { "epoch": 1.1332288401253918, "grad_norm": 1.389250012982398, "learning_rate": 9.423333473337556e-06, "loss": 0.4186, "step": 7953 }, { "epoch": 1.1333713308634938, "grad_norm": 1.3201992845456016, "learning_rate": 9.420850618563992e-06, "loss": 0.4775, "step": 7954 }, { "epoch": 1.1335138216015959, "grad_norm": 1.4327283209062747, "learning_rate": 9.418367799612124e-06, "loss": 0.4879, "step": 7955 }, { "epoch": 1.1336563123396979, "grad_norm": 1.3790074156883851, "learning_rate": 9.415885016635515e-06, "loss": 0.4514, "step": 7956 }, { "epoch": 1.1337988030778, "grad_norm": 1.3416682491047476, "learning_rate": 9.413402269787735e-06, "loss": 0.3869, "step": 7957 }, { "epoch": 1.133941293815902, "grad_norm": 1.6184953271400335, "learning_rate": 9.41091955922234e-06, "loss": 0.4412, "step": 7958 }, { "epoch": 1.134083784554004, "grad_norm": 1.4198427523966437, "learning_rate": 9.408436885092902e-06, "loss": 0.454, "step": 7959 }, { "epoch": 1.134226275292106, "grad_norm": 1.256860686951129, "learning_rate": 9.40595424755297e-06, "loss": 0.3973, "step": 7960 }, { "epoch": 1.134368766030208, "grad_norm": 1.4442233521534917, "learning_rate": 9.40347164675611e-06, "loss": 0.493, "step": 7961 }, { "epoch": 1.13451125676831, "grad_norm": 1.3766833587205456, "learning_rate": 9.400989082855865e-06, "loss": 0.454, "step": 7962 }, { "epoch": 1.134653747506412, "grad_norm": 1.3933166104462265, "learning_rate": 9.398506556005794e-06, "loss": 0.4544, "step": 7963 }, { "epoch": 1.134796238244514, "grad_norm": 1.4228541503309475, "learning_rate": 9.39602406635945e-06, "loss": 0.4357, "step": 7964 }, { "epoch": 1.134938728982616, "grad_norm": 1.202538475636112, "learning_rate": 9.393541614070377e-06, "loss": 0.4119, "step": 7965 }, { "epoch": 1.135081219720718, "grad_norm": 1.4373037635440735, "learning_rate": 9.391059199292121e-06, "loss": 0.4157, "step": 7966 }, { "epoch": 1.13522371045882, "grad_norm": 1.3888694475716423, "learning_rate": 9.388576822178218e-06, "loss": 0.3966, "step": 7967 }, { "epoch": 1.135366201196922, "grad_norm": 1.3230393159763443, "learning_rate": 9.386094482882223e-06, "loss": 0.4129, "step": 7968 }, { "epoch": 1.1355086919350241, "grad_norm": 1.3927883234071639, "learning_rate": 9.38361218155766e-06, "loss": 0.4027, "step": 7969 }, { "epoch": 1.1356511826731261, "grad_norm": 1.4313865844552787, "learning_rate": 9.381129918358071e-06, "loss": 0.4889, "step": 7970 }, { "epoch": 1.1357936734112282, "grad_norm": 1.2744993271180547, "learning_rate": 9.378647693436996e-06, "loss": 0.4318, "step": 7971 }, { "epoch": 1.1359361641493302, "grad_norm": 1.4519701312844437, "learning_rate": 9.376165506947955e-06, "loss": 0.4475, "step": 7972 }, { "epoch": 1.1360786548874322, "grad_norm": 1.4774884824272356, "learning_rate": 9.373683359044483e-06, "loss": 0.501, "step": 7973 }, { "epoch": 1.1362211456255342, "grad_norm": 1.4937854411573601, "learning_rate": 9.371201249880102e-06, "loss": 0.4447, "step": 7974 }, { "epoch": 1.1363636363636362, "grad_norm": 1.5544023294880476, "learning_rate": 9.368719179608343e-06, "loss": 0.4971, "step": 7975 }, { "epoch": 1.1365061271017385, "grad_norm": 1.6932231933350042, "learning_rate": 9.366237148382722e-06, "loss": 0.4609, "step": 7976 }, { "epoch": 1.1366486178398405, "grad_norm": 1.4456822769228506, "learning_rate": 9.363755156356758e-06, "loss": 0.4446, "step": 7977 }, { "epoch": 1.1367911085779425, "grad_norm": 1.3506780818949542, "learning_rate": 9.361273203683974e-06, "loss": 0.4316, "step": 7978 }, { "epoch": 1.1369335993160445, "grad_norm": 1.4738436102800947, "learning_rate": 9.358791290517877e-06, "loss": 0.4725, "step": 7979 }, { "epoch": 1.1370760900541466, "grad_norm": 1.4321136398636936, "learning_rate": 9.356309417011986e-06, "loss": 0.489, "step": 7980 }, { "epoch": 1.1372185807922486, "grad_norm": 1.3155724823339818, "learning_rate": 9.3538275833198e-06, "loss": 0.4337, "step": 7981 }, { "epoch": 1.1373610715303506, "grad_norm": 1.372587195224977, "learning_rate": 9.351345789594838e-06, "loss": 0.4866, "step": 7982 }, { "epoch": 1.1375035622684526, "grad_norm": 1.448736038553629, "learning_rate": 9.348864035990595e-06, "loss": 0.3981, "step": 7983 }, { "epoch": 1.1376460530065546, "grad_norm": 1.2557615168680647, "learning_rate": 9.346382322660577e-06, "loss": 0.4726, "step": 7984 }, { "epoch": 1.1377885437446567, "grad_norm": 1.3292419520442533, "learning_rate": 9.343900649758288e-06, "loss": 0.3979, "step": 7985 }, { "epoch": 1.1379310344827587, "grad_norm": 1.3314647572899703, "learning_rate": 9.341419017437217e-06, "loss": 0.4072, "step": 7986 }, { "epoch": 1.1380735252208607, "grad_norm": 1.3913290850492968, "learning_rate": 9.338937425850865e-06, "loss": 0.4813, "step": 7987 }, { "epoch": 1.1382160159589627, "grad_norm": 1.2778907114925213, "learning_rate": 9.336455875152716e-06, "loss": 0.4532, "step": 7988 }, { "epoch": 1.1383585066970647, "grad_norm": 1.3833198839749548, "learning_rate": 9.333974365496272e-06, "loss": 0.4202, "step": 7989 }, { "epoch": 1.1385009974351668, "grad_norm": 1.6934146455098482, "learning_rate": 9.331492897035008e-06, "loss": 0.4415, "step": 7990 }, { "epoch": 1.1386434881732688, "grad_norm": 1.7613555346798575, "learning_rate": 9.32901146992241e-06, "loss": 0.432, "step": 7991 }, { "epoch": 1.1387859789113708, "grad_norm": 1.3719994539508067, "learning_rate": 9.32653008431197e-06, "loss": 0.4247, "step": 7992 }, { "epoch": 1.1389284696494728, "grad_norm": 1.3099213903947826, "learning_rate": 9.324048740357156e-06, "loss": 0.3927, "step": 7993 }, { "epoch": 1.1390709603875748, "grad_norm": 1.2366446873433432, "learning_rate": 9.321567438211452e-06, "loss": 0.4722, "step": 7994 }, { "epoch": 1.1392134511256768, "grad_norm": 1.2492335890126058, "learning_rate": 9.319086178028326e-06, "loss": 0.3856, "step": 7995 }, { "epoch": 1.1393559418637789, "grad_norm": 1.2823026069675696, "learning_rate": 9.316604959961256e-06, "loss": 0.4453, "step": 7996 }, { "epoch": 1.1394984326018809, "grad_norm": 1.3438951637508232, "learning_rate": 9.314123784163703e-06, "loss": 0.4444, "step": 7997 }, { "epoch": 1.139640923339983, "grad_norm": 1.4251174290347577, "learning_rate": 9.31164265078914e-06, "loss": 0.4626, "step": 7998 }, { "epoch": 1.139783414078085, "grad_norm": 1.466718445102242, "learning_rate": 9.309161559991029e-06, "loss": 0.4286, "step": 7999 }, { "epoch": 1.139925904816187, "grad_norm": 1.4338092271821683, "learning_rate": 9.306680511922827e-06, "loss": 0.4679, "step": 8000 } ], "logging_steps": 1, "max_steps": 14036, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 2000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2098298159169536.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }