diff --git "a/checkpoint-1068480/trainer_state.json" "b/checkpoint-1068480/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1068480/trainer_state.json" @@ -0,0 +1,12653 @@ +{ + "best_metric": 4.026948928833008, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/lstm/4/checkpoints/checkpoint-1068480", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1068480, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8194, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5486, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0539, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9878, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9434, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9114, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7517, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994131474623009e-05, + "loss": 6.6461, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993292879871958e-05, + "loss": 6.549, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4708, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4004, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3455, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.2713, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.1949, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.1449, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.084, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0493, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.9922, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9462, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9133, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8722, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8431, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8165, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7852, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7557, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.979036769104073e-05, + "loss": 5.7299, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.978198174353021e-05, + "loss": 5.6998, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6709, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6449, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6317, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.609, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.587, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 5.5662, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 5.5456, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 5.5391, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5277, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5037, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4646, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4736, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.437, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4315, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4222, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4133, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.3905, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3859, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3807, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3674, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.3574, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3373, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3251, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3296, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3082, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.2976, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2782, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2829, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2636, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2775, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2492, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2467, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.239, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.9496974179798646e-05, + "loss": 5.2178, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2206, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2062, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1948, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.1903, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.2079, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1826, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1684, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1504, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1494, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413147462300904e-05, + "loss": 5.1635, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404761514790384e-05, + "loss": 5.1584, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.939637556727987e-05, + "loss": 5.1325, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1492, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937962005106256e-05, + "loss": 5.1404, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937123410355204e-05, + "loss": 5.1257, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936284815604152e-05, + "loss": 5.106, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.109, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.0932, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933770669231369e-05, + "loss": 5.091, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932932074480317e-05, + "loss": 5.0907, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0813, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.0844, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0787, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0572, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0601, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0585, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0515, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262249543522744e-05, + "loss": 5.0396, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0377, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.0352, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0227, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.0248, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0107, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.013, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0082, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 4.9996, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.9799, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.9799, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9794, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 4.989, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9758, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9635, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9561, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9611, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9344, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.9379, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.9341, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.936, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.9265, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9328, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9106, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9341, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9127, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9136, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9159, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9144, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.8995, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.8896, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.8967, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.8887, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.889, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.8842, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.8729, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.8848, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.8642, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.8591, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8521, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8589, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8433, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.8617, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.8539, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.8408, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8331, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.8357, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8336, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8344, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8335, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8304, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8228, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8176, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.806, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8046, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8088, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.7913, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8045, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.8037, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.7927, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.7971, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.7918, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.747582912445068, + "eval_runtime": 297.2858, + "eval_samples_per_second": 1283.583, + "eval_steps_per_second": 40.113, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.7713, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.777, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.7895, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871737587978745e-05, + "loss": 4.7703, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7756, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7651, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7655, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7543, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675478899842306e-05, + "loss": 4.7625, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667092952331785e-05, + "loss": 4.7512, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865870700482127e-05, + "loss": 4.7718, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865032105731075e-05, + "loss": 4.7634, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7431, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7394, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.7379, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.739, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.7325, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.73, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.7264, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7376, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.729, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7326, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7273, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7351, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7113, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7112, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7045, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.7054, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.7048, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.7017, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7022, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.7004, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.6902, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.7041, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.7041, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.6896, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.6736, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.6864, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.6664, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.6762, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.6751, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.6796, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6679, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838206900979649e-05, + "loss": 4.6734, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837368306228597e-05, + "loss": 4.6753, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836529711477545e-05, + "loss": 4.6691, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.6698, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834854159855814e-05, + "loss": 4.6518, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834015565104763e-05, + "loss": 4.6561, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833176970353711e-05, + "loss": 4.6631, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.6524, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.6533, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.6361, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829824229229876e-05, + "loss": 4.6471, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6368, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6536, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827308444976719e-05, + "loss": 4.6383, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.6425, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256328933549886e-05, + "loss": 4.6434, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6207, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6325, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6322, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6171, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.6204, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206029627290495e-05, + "loss": 4.6404, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.6244, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.612, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.606, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172502216052144e-05, + "loss": 4.6106, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.6273, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.6262, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.608, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.6256, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.6237, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6133, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.5999, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810544739357545e-05, + "loss": 4.6131, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.6006, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.5959, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.6023, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.5939, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.6105, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.5969, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804676213980554e-05, + "loss": 4.589, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803837619229502e-05, + "loss": 4.5945, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8029990244784504e-05, + "loss": 4.5929, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.5909, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013218349763464e-05, + "loss": 4.5877, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.581, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.5919, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.5779, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.5838, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.5717, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.79629354223078e-05, + "loss": 4.5856, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795454947479728e-05, + "loss": 4.5815, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794616352728676e-05, + "loss": 4.5732, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793777757977624e-05, + "loss": 4.5596, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792939163226572e-05, + "loss": 4.5663, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.79210056847552e-05, + "loss": 4.5684, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.5803, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.5702, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5603, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5562, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.5658, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870722757299546e-05, + "loss": 4.5381, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5526, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5507, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5526, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5457, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5542, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.5421, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.5616, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.5453, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.5417, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786896039801804e-05, + "loss": 4.5618, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5566, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5428, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776175457607397e-05, + "loss": 4.535, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775336862856345e-05, + "loss": 4.5493, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774498268105293e-05, + "loss": 4.5381, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773659673354241e-05, + "loss": 4.5385, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772821078603189e-05, + "loss": 4.5455, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5293, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5461, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5282, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5307, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.5189, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5327, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5218, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5364, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765277001604468e-05, + "loss": 4.5339, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764438406853416e-05, + "loss": 4.5249, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763599812102364e-05, + "loss": 4.5101, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5266, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5204, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5267, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.525, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.5207, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5188, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5222, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5064, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5072, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.75521714035259e-05, + "loss": 4.5137, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543785456015375e-05, + "loss": 4.5018, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.5093, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5196, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751866037109128e-05, + "loss": 4.5035, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751027442358077e-05, + "loss": 4.5057, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.5063, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.471279144287109, + "eval_runtime": 296.6309, + "eval_samples_per_second": 1286.417, + "eval_steps_per_second": 40.201, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.4923, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.4952, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.5092, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.497, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5017, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.4862, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.5001, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.4813, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.4953, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.4879, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.5023, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.5026, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392887537237216e-05, + "loss": 4.4791, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.4833, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4837, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.4772, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4775, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.4765, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4745, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.4942, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4746, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4869, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4828, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4889, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292272545914704e-05, + "loss": 4.4638, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7283886598404184e-05, + "loss": 4.4727, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275500650893664e-05, + "loss": 4.4627, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4721, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4636, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4653, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4732, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723358729214479e-05, + "loss": 4.4668, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722520134463427e-05, + "loss": 4.4568, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.474, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4685, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720007625971017e-05, + "loss": 4.4615, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4499, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4616, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.4423, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4558, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715816290096131e-05, + "loss": 4.4501, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714977695345079e-05, + "loss": 4.458, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714139100594027e-05, + "loss": 4.4516, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713300505842975e-05, + "loss": 4.4545, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712461911091923e-05, + "loss": 4.4571, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711623316340871e-05, + "loss": 4.4541, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710784721589819e-05, + "loss": 4.4563, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099461268387667e-05, + "loss": 4.439, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091091699680876e-05, + "loss": 4.439, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082705752170356e-05, + "loss": 4.4535, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074319804659836e-05, + "loss": 4.4411, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706593385714932e-05, + "loss": 4.4406, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705756428844253e-05, + "loss": 4.428, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704917834093201e-05, + "loss": 4.4416, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.4264, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.446, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702403687720418e-05, + "loss": 4.4326, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701565092969366e-05, + "loss": 4.4414, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700726498218314e-05, + "loss": 4.4377, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699887903467262e-05, + "loss": 4.423, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699050946596583e-05, + "loss": 4.4291, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698212351845531e-05, + "loss": 4.4319, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697373757094479e-05, + "loss": 4.4184, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965368002238005e-05, + "loss": 4.4276, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956982054727485e-05, + "loss": 4.4355, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948596107216965e-05, + "loss": 4.4313, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940210159706445e-05, + "loss": 4.4189, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931824212195925e-05, + "loss": 4.4098, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.69234382646854e-05, + "loss": 4.4164, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915068695978614e-05, + "loss": 4.4327, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906682748468094e-05, + "loss": 4.4365, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898296800957574e-05, + "loss": 4.4199, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688992723225078e-05, + "loss": 4.4339, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688154128474026e-05, + "loss": 4.4342, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687315533722974e-05, + "loss": 4.4287, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686476938971923e-05, + "loss": 4.4065, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.68563834422087e-05, + "loss": 4.4279, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684799749469818e-05, + "loss": 4.4213, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683961154718766e-05, + "loss": 4.409, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4214, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4123, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4239, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680606775714558e-05, + "loss": 4.4177, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.4055, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4139, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4115, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677255672471097e-05, + "loss": 4.4141, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676417077720045e-05, + "loss": 4.4103, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4042, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4139, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4034, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730643365962096e-05, + "loss": 4.4089, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722273797255305e-05, + "loss": 4.4, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713887849744785e-05, + "loss": 4.4139, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705501902234265e-05, + "loss": 4.4082, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697115954723745e-05, + "loss": 4.3989, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688730007213225e-05, + "loss": 4.3942, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680344059702705e-05, + "loss": 4.4001, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671958112192185e-05, + "loss": 4.3942, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663572164681665e-05, + "loss": 4.413, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.3983, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.394, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.3889, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.3956, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.3777, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661327285842228e-05, + "loss": 4.3871, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660490328971549e-05, + "loss": 4.386, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659651734220497e-05, + "loss": 4.39, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658813139469445e-05, + "loss": 4.3788, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657974544718393e-05, + "loss": 4.3946, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657135949967341e-05, + "loss": 4.3777, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656297355216288e-05, + "loss": 4.4, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.3846, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546218035945586e-05, + "loss": 4.3816, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537832088435065e-05, + "loss": 4.4036, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.4017, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3861, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.3775, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650430467719671e-05, + "loss": 4.3879, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649591872968619e-05, + "loss": 4.3843, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648753278217567e-05, + "loss": 4.3803, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647914683466515e-05, + "loss": 4.3947, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.3742, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462391318447837e-05, + "loss": 4.3907, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645400537093732e-05, + "loss": 4.3768, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644563580223053e-05, + "loss": 4.3804, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643724985472001e-05, + "loss": 4.3657, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642886390720949e-05, + "loss": 4.383, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642047795969897e-05, + "loss": 4.3671, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3868, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3806, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639532011716741e-05, + "loss": 4.3779, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638693416965689e-05, + "loss": 4.3608, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637858097975383e-05, + "loss": 4.3783, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637019503224331e-05, + "loss": 4.3762, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636180908473279e-05, + "loss": 4.3755, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635342313722228e-05, + "loss": 4.3735, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634503718971176e-05, + "loss": 4.3797, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633665124220124e-05, + "loss": 4.3732, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328281673494446e-05, + "loss": 4.3793, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.3601, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3638, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303123830962886e-05, + "loss": 4.3689, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294737883452366e-05, + "loss": 4.3565, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286351935941846e-05, + "loss": 4.3667, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277965988431326e-05, + "loss": 4.3765, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269580040920806e-05, + "loss": 4.3618, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261210472214015e-05, + "loss": 4.3603, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252824524703495e-05, + "loss": 4.3693, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.337189197540283, + "eval_runtime": 311.5899, + "eval_samples_per_second": 1224.658, + "eval_steps_per_second": 38.271, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624445495599671e-05, + "loss": 4.3592, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623606900848619e-05, + "loss": 4.3548, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622768306097567e-05, + "loss": 4.3692, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621929711346515e-05, + "loss": 4.3534, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621091116595463e-05, + "loss": 4.3654, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620252521844411e-05, + "loss": 4.3498, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619413927093359e-05, + "loss": 4.3619, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618575332342307e-05, + "loss": 4.3443, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617738375471628e-05, + "loss": 4.3606, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616899780720576e-05, + "loss": 4.3507, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616061185969524e-05, + "loss": 4.3681, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615222591218472e-05, + "loss": 4.365, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614385634347793e-05, + "loss": 4.3461, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135470395967415e-05, + "loss": 4.3523, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127084448456895e-05, + "loss": 4.3489, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611869850094637e-05, + "loss": 4.3491, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611031255343585e-05, + "loss": 4.3403, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610192660592533e-05, + "loss": 4.3448, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609354065841481e-05, + "loss": 4.3421, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608515471090429e-05, + "loss": 4.3676, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.60767851421975e-05, + "loss": 4.3444, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606839919468698e-05, + "loss": 4.3512, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606001324717646e-05, + "loss": 4.3563, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605162729966594e-05, + "loss": 4.3586, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604325773095915e-05, + "loss": 4.3364, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603488816225236e-05, + "loss": 4.3426, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602650221474184e-05, + "loss": 4.3357, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601811626723132e-05, + "loss": 4.3433, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600974669852454e-05, + "loss": 4.3354, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600136075101402e-05, + "loss": 4.3366, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599297480350349e-05, + "loss": 4.3462, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598458885599297e-05, + "loss": 4.3421, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597620290848245e-05, + "loss": 4.3374, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596781696097193e-05, + "loss": 4.3453, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595943101346141e-05, + "loss": 4.3451, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595104506595089e-05, + "loss": 4.3369, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594265911844037e-05, + "loss": 4.3239, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593427317092985e-05, + "loss": 4.3394, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592588722341933e-05, + "loss": 4.317, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917517654712546e-05, + "loss": 4.332, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909131707202026e-05, + "loss": 4.3269, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900745759691506e-05, + "loss": 4.3375, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892359812180986e-05, + "loss": 4.3354, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883973864670466e-05, + "loss": 4.3294, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875587917159946e-05, + "loss": 4.3358, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867201969649426e-05, + "loss": 4.3358, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858832400942635e-05, + "loss": 4.3368, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850446453432115e-05, + "loss": 4.3187, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842060505921595e-05, + "loss": 4.3186, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833674558411075e-05, + "loss": 4.3362, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825288610900555e-05, + "loss": 4.3204, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5816902663390035e-05, + "loss": 4.319, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580853309468325e-05, + "loss": 4.3144, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580014714717273e-05, + "loss": 4.324, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791761199662204e-05, + "loss": 4.3123, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783375252151684e-05, + "loss": 4.3245, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774989304641164e-05, + "loss": 4.3174, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766603357130644e-05, + "loss": 4.3213, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758217409620124e-05, + "loss": 4.3234, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749831462109604e-05, + "loss": 4.3108, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574146189340281e-05, + "loss": 4.3095, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573309232469602e-05, + "loss": 4.321, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572470637718551e-05, + "loss": 4.3024, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571632042967499e-05, + "loss": 4.3124, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570793448216447e-05, + "loss": 4.3208, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569956491345768e-05, + "loss": 4.3228, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569117896594716e-05, + "loss": 4.3047, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568279301843664e-05, + "loss": 4.2986, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567440707092612e-05, + "loss": 4.3029, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.56660211234156e-05, + "loss": 4.3158, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565763517590508e-05, + "loss": 4.3243, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564924922839456e-05, + "loss": 4.3104, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564086328088404e-05, + "loss": 4.3219, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632493712177247e-05, + "loss": 4.3233, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624107764666726e-05, + "loss": 4.3187, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561573819595994e-05, + "loss": 4.3004, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.3152, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559898267974263e-05, + "loss": 4.3116, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559059673223211e-05, + "loss": 4.3012, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558221078472159e-05, + "loss": 4.3113, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557382483721107e-05, + "loss": 4.3061, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3126, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555705294219003e-05, + "loss": 4.3108, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554866699467951e-05, + "loss": 4.3, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.31, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3031, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552350915214795e-05, + "loss": 4.3062, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551512320463743e-05, + "loss": 4.3045, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550673725712691e-05, + "loss": 4.2972, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549836768842013e-05, + "loss": 4.3086, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548998174090961e-05, + "loss": 4.3024, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548159579339909e-05, + "loss": 4.2974, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547320984588857e-05, + "loss": 4.2963, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.3117, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456470708474985e-05, + "loss": 4.3047, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448084760964465e-05, + "loss": 4.2953, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439698813453945e-05, + "loss": 4.2904, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431312865943425e-05, + "loss": 4.2967, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422926918432905e-05, + "loss": 4.2903, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414540970922385e-05, + "loss": 4.3121, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406155023411865e-05, + "loss": 4.2977, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539778545470508e-05, + "loss": 4.2934, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538939950719456e-05, + "loss": 4.2881, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538101355968404e-05, + "loss": 4.2981, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537264399097725e-05, + "loss": 4.2716, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536427442227046e-05, + "loss": 4.2881, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535588847475994e-05, + "loss": 4.286, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534750252724942e-05, + "loss": 4.293, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53391165797389e-05, + "loss": 4.2791, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533073063222838e-05, + "loss": 4.2961, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532234468471786e-05, + "loss": 4.2776, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531395873720733e-05, + "loss": 4.2964, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530557278969682e-05, + "loss": 4.2894, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.52971868421863e-05, + "loss": 4.2816, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.3029, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.3046, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527204537845847e-05, + "loss": 4.2905, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526365943094795e-05, + "loss": 4.2813, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.2885, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.2842, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2823, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2984, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2782, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.291, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.2835, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196588229667516e-05, + "loss": 4.2879, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.2647, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517983271345021e-05, + "loss": 4.2914, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517144676593969e-05, + "loss": 4.2722, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516306081842917e-05, + "loss": 4.292, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515467487091865e-05, + "loss": 4.2838, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.2879, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2652, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512951702838709e-05, + "loss": 4.29, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.51211474596803e-05, + "loss": 4.2798, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511276151216978e-05, + "loss": 4.2831, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510437556465926e-05, + "loss": 4.2799, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509598961714874e-05, + "loss": 4.2899, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508760366963822e-05, + "loss": 4.2836, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079234100931436e-05, + "loss": 4.2836, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070848153420916e-05, + "loss": 4.2698, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062462205910396e-05, + "loss": 4.2741, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054076258399876e-05, + "loss": 4.2743, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504569031088935e-05, + "loss": 4.2683, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503730436337883e-05, + "loss": 4.2769, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502891841586831e-05, + "loss": 4.2828, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502053246835779e-05, + "loss": 4.2733, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012162899651e-05, + "loss": 4.2701, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500377695214048e-05, + "loss": 4.2798, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.255205154418945, + "eval_runtime": 311.0995, + "eval_samples_per_second": 1226.588, + "eval_steps_per_second": 38.332, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499539100462996e-05, + "loss": 4.2624, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498700505711944e-05, + "loss": 4.2648, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978619109608925e-05, + "loss": 4.2754, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970233162098405e-05, + "loss": 4.2667, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961847214587885e-05, + "loss": 4.2797, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953461267077365e-05, + "loss": 4.2607, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945075319566845e-05, + "loss": 4.2699, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936689372056325e-05, + "loss": 4.2572, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928303424545805e-05, + "loss": 4.275, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919917477035285e-05, + "loss": 4.2642, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911531529524765e-05, + "loss": 4.2741, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490314558201424e-05, + "loss": 4.2798, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894776013307454e-05, + "loss": 4.2542, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886390065796934e-05, + "loss": 4.2697, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487800411828641e-05, + "loss": 4.2618, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486961817077589e-05, + "loss": 4.2638, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.48612486020691e-05, + "loss": 4.2524, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485286265455859e-05, + "loss": 4.2604, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484447670704806e-05, + "loss": 4.2566, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483609075953754e-05, + "loss": 4.2794, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482770481202702e-05, + "loss": 4.2576, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48193188645165e-05, + "loss": 4.2669, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481093291700598e-05, + "loss": 4.2732, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480254696949546e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479416102198494e-05, + "loss": 4.25, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478579145327815e-05, + "loss": 4.2632, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477740550576763e-05, + "loss": 4.2499, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476901955825711e-05, + "loss": 4.2585, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476063361074659e-05, + "loss": 4.2491, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475224766323607e-05, + "loss": 4.2573, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474387809452929e-05, + "loss": 4.2614, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473549214701877e-05, + "loss": 4.2588, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472710619950825e-05, + "loss": 4.2522, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471872025199773e-05, + "loss": 4.2645, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471033430448721e-05, + "loss": 4.2561, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470194835697669e-05, + "loss": 4.2592, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469356240946617e-05, + "loss": 4.244, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468517646195565e-05, + "loss": 4.2549, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467679051444512e-05, + "loss": 4.2408, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668420945738336e-05, + "loss": 4.2483, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660034998227816e-05, + "loss": 4.2451, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651649050717296e-05, + "loss": 4.2575, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643263103206776e-05, + "loss": 4.2531, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463489353449999e-05, + "loss": 4.252, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462650758698947e-05, + "loss": 4.2552, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461812163947895e-05, + "loss": 4.2553, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609735691968425e-05, + "loss": 4.2534, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460136612326164e-05, + "loss": 4.2448, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459298017575112e-05, + "loss": 4.2323, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584594228240594e-05, + "loss": 4.2574, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576208280730074e-05, + "loss": 4.2456, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456783871202329e-05, + "loss": 4.2395, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455945276451277e-05, + "loss": 4.2384, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455108319580598e-05, + "loss": 4.2447, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542697248295465e-05, + "loss": 4.2339, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534311300784945e-05, + "loss": 4.2387, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525925353274425e-05, + "loss": 4.2403, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517555784567634e-05, + "loss": 4.2405, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509169837057114e-05, + "loss": 4.2513, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500783889546594e-05, + "loss": 4.2308, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449239794203607e-05, + "loss": 4.2341, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448401199452555e-05, + "loss": 4.246, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447562604701503e-05, + "loss": 4.2289, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446724009950451e-05, + "loss": 4.2367, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445885415199399e-05, + "loss": 4.2408, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.44504845832872e-05, + "loss": 4.2451, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444209863577668e-05, + "loss": 4.2296, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443371268826616e-05, + "loss": 4.2233, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442532674075564e-05, + "loss": 4.2224, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441694079324512e-05, + "loss": 4.2396, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440857122453833e-05, + "loss": 4.251, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440018527702781e-05, + "loss": 4.2331, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439179932951729e-05, + "loss": 4.2454, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438341338200677e-05, + "loss": 4.2475, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437504381329998e-05, + "loss": 4.2467, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436665786578946e-05, + "loss": 4.2248, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435827191827894e-05, + "loss": 4.2399, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434988597076842e-05, + "loss": 4.2359, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.43415000232579e-05, + "loss": 4.2241, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333130454551117e-05, + "loss": 4.2398, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324744507040597e-05, + "loss": 4.2337, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316358559530076e-05, + "loss": 4.2338, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307972612019556e-05, + "loss": 4.2387, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299586664509036e-05, + "loss": 4.2312, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291217095802245e-05, + "loss": 4.2344, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282831148291725e-05, + "loss": 4.2279, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274445200781205e-05, + "loss": 4.2335, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266059253270685e-05, + "loss": 4.2259, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257673305760165e-05, + "loss": 4.2278, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249287358249645e-05, + "loss": 4.2325, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4240901410739125e-05, + "loss": 4.2318, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232515463228605e-05, + "loss": 4.2244, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422414589452182e-05, + "loss": 4.2231, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421577632581503e-05, + "loss": 4.2408, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420739037830451e-05, + "loss": 4.2344, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419900443079399e-05, + "loss": 4.2261, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419061848328347e-05, + "loss": 4.2192, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418223253577295e-05, + "loss": 4.2246, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417384658826243e-05, + "loss": 4.2227, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.41654606407519e-05, + "loss": 4.2345, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415709107204512e-05, + "loss": 4.2327, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41487051245346e-05, + "loss": 4.2224, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414031917702408e-05, + "loss": 4.2173, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413193322951356e-05, + "loss": 4.2297, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412354728200304e-05, + "loss": 4.1981, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411516133449252e-05, + "loss": 4.2226, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106791765785735e-05, + "loss": 4.2098, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409840581827521e-05, + "loss": 4.2216, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409001987076469e-05, + "loss": 4.2111, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408163392325417e-05, + "loss": 4.2247, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2158, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406486202823313e-05, + "loss": 4.2211, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405649245952634e-05, + "loss": 4.2243, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404810651201582e-05, + "loss": 4.2095, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40397205645053e-05, + "loss": 4.2338, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031334616994777e-05, + "loss": 4.2369, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402296504828799e-05, + "loss": 4.2227, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401457910077747e-05, + "loss": 4.2092, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400619315326695e-05, + "loss": 4.2229, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399780720575643e-05, + "loss": 4.2179, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398942125824591e-05, + "loss": 4.2106, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398103531073539e-05, + "loss": 4.2314, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397264936322487e-05, + "loss": 4.2121, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396426341571435e-05, + "loss": 4.22, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395587746820383e-05, + "loss": 4.2189, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394752427830077e-05, + "loss": 4.2186, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393913833079025e-05, + "loss": 4.2063, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930768762083466e-05, + "loss": 4.2155, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922382814572946e-05, + "loss": 4.2108, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913996867062426e-05, + "loss": 4.2267, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905610919551906e-05, + "loss": 4.2156, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897224972041386e-05, + "loss": 4.2185, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888839024530866e-05, + "loss": 4.2011, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880453077020346e-05, + "loss": 4.2227, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872067129509826e-05, + "loss": 4.2148, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.2183, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2113, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2244, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838539718271475e-05, + "loss": 4.2151, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830153770760955e-05, + "loss": 4.2217, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821767823250435e-05, + "loss": 4.2015, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813381875739915e-05, + "loss": 4.2114, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804995928229395e-05, + "loss": 4.2068, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796609980718875e-05, + "loss": 4.2038, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788224033208355e-05, + "loss": 4.2147, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779838085697835e-05, + "loss": 4.2139, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771468516991044e-05, + "loss": 4.212, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376309894828426e-05, + "loss": 4.1993, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375471300077374e-05, + "loss": 4.2162, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.199580669403076, + "eval_runtime": 287.876, + "eval_samples_per_second": 1325.539, + "eval_steps_per_second": 41.424, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374632705326321e-05, + "loss": 4.2055, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373794110575269e-05, + "loss": 4.1975, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372957153704591e-05, + "loss": 4.2147, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372118558953539e-05, + "loss": 4.206, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371279964202487e-05, + "loss": 4.2083, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370441369451435e-05, + "loss": 4.2026, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369602774700383e-05, + "loss": 4.2025, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368764179949331e-05, + "loss": 4.1958, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367925585198279e-05, + "loss": 4.2081, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367086990447227e-05, + "loss": 4.2033, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366250033576548e-05, + "loss": 4.2088, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365411438825496e-05, + "loss": 4.2145, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645744819548166e-05, + "loss": 4.1948, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637358872037646e-05, + "loss": 4.2064, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628972924527126e-05, + "loss": 4.2014, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620586977016606e-05, + "loss": 4.1984, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612201029506086e-05, + "loss": 4.1914, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3603815081995566e-05, + "loss": 4.1983, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359542913448505e-05, + "loss": 4.1925, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358704318697453e-05, + "loss": 4.2135, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357865723946401e-05, + "loss": 4.2031, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357027129195349e-05, + "loss": 4.2029, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.2121, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355351577573618e-05, + "loss": 4.2117, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354512982822566e-05, + "loss": 4.1873, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353674388071514e-05, + "loss": 4.2017, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352835793320462e-05, + "loss": 4.1912, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35199719856941e-05, + "loss": 4.1967, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511586038183575e-05, + "loss": 4.1879, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503200090673055e-05, + "loss": 4.1952, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349483052196627e-05, + "loss": 4.2021, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348644457445575e-05, + "loss": 4.1971, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478075005748966e-05, + "loss": 4.1949, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469689058238446e-05, + "loss": 4.2002, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461319489531655e-05, + "loss": 4.1993, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452933542021135e-05, + "loss": 4.1976, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444547594510615e-05, + "loss": 4.1867, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436161647000095e-05, + "loss": 4.1871, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427775699489575e-05, + "loss": 4.1844, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341938975197905e-05, + "loss": 4.1868, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341100380446853e-05, + "loss": 4.1866, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340261785695801e-05, + "loss": 4.1968, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339423190944749e-05, + "loss": 4.1944, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385845961936975e-05, + "loss": 4.1934, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377460014426455e-05, + "loss": 4.2015, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369074066915935e-05, + "loss": 4.1893, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360704498209144e-05, + "loss": 4.1958, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352318550698624e-05, + "loss": 4.1853, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343932603188104e-05, + "loss": 4.1725, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335546655677584e-05, + "loss": 4.1998, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332717708697079e-05, + "loss": 4.1837, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331879113946027e-05, + "loss": 4.1845, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331040519194975e-05, + "loss": 4.1798, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330201924443923e-05, + "loss": 4.185, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329364967573244e-05, + "loss": 4.1783, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328528010702566e-05, + "loss": 4.18, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327689415951514e-05, + "loss": 4.1834, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326850821200462e-05, + "loss": 4.182, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.32601222644941e-05, + "loss": 4.1937, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325173631698358e-05, + "loss": 4.1738, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324335036947306e-05, + "loss": 4.1747, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323496442196254e-05, + "loss": 4.1915, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322657847445202e-05, + "loss": 4.1731, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321820890574523e-05, + "loss": 4.1779, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209822958234707e-05, + "loss": 4.1806, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201437010724187e-05, + "loss": 4.1901, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193051063213666e-05, + "loss": 4.1732, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184681494506876e-05, + "loss": 4.1721, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317629554699636e-05, + "loss": 4.1609, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316790959948584e-05, + "loss": 4.184, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315952365197532e-05, + "loss": 4.1932, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.31511377044648e-05, + "loss": 4.1792, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314276813575801e-05, + "loss": 4.1859, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313439856705122e-05, + "loss": 4.1892, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.31260126195407e-05, + "loss": 4.1954, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311762667203018e-05, + "loss": 4.169, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310924072451966e-05, + "loss": 4.1854, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310085477700914e-05, + "loss": 4.1812, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309246882949862e-05, + "loss": 4.1664, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.30840828819881e-05, + "loss": 4.184, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307569693447758e-05, + "loss": 4.1812, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306731098696706e-05, + "loss": 4.1784, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305892503945654e-05, + "loss": 4.1846, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050555470749756e-05, + "loss": 4.1753, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042169523239236e-05, + "loss": 4.1734, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303378357572871e-05, + "loss": 4.1778, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025414007021925e-05, + "loss": 4.1803, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017028059511405e-05, + "loss": 4.1669, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008642112000885e-05, + "loss": 4.1735, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300025616449036e-05, + "loss": 4.181, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299187021697984e-05, + "loss": 4.1784, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298348426946932e-05, + "loss": 4.172, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.29750983219588e-05, + "loss": 4.1693, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966728753252014e-05, + "loss": 4.1875, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958342805741494e-05, + "loss": 4.1801, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949956858230974e-05, + "loss": 4.1759, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941570910720454e-05, + "loss": 4.1621, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933184963209934e-05, + "loss": 4.1706, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2924799015699413e-05, + "loss": 4.1712, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916413068188893e-05, + "loss": 4.179, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290802712067837e-05, + "loss": 4.1813, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289965755197158e-05, + "loss": 4.1685, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289127160446106e-05, + "loss": 4.1631, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288288565695054e-05, + "loss": 4.176, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287449970944002e-05, + "loss": 4.147, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286613014073324e-05, + "loss": 4.1693, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285774419322272e-05, + "loss": 4.1552, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.28493582457122e-05, + "loss": 4.1751, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284097229820168e-05, + "loss": 4.1575, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283260272949489e-05, + "loss": 4.1705, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282421678198437e-05, + "loss": 4.1619, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281583083447385e-05, + "loss": 4.1677, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807461265767056e-05, + "loss": 4.1719, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799075318256536e-05, + "loss": 4.165, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790689370746016e-05, + "loss": 4.1796, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782303423235496e-05, + "loss": 4.1823, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773917475724976e-05, + "loss": 4.1716, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765531528214456e-05, + "loss": 4.1601, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757145580703936e-05, + "loss": 4.1658, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748759633193416e-05, + "loss": 4.169, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274039006448663e-05, + "loss": 4.1559, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273200411697611e-05, + "loss": 4.1852, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272361816946559e-05, + "loss": 4.1564, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271523222195507e-05, + "loss": 4.1714, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270686265324828e-05, + "loss": 4.1666, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269847670573776e-05, + "loss": 4.1641, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269010713703097e-05, + "loss": 4.1563, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268172118952045e-05, + "loss": 4.1663, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267333524200993e-05, + "loss": 4.1604, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266494929449941e-05, + "loss": 4.176, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.166, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264817739947837e-05, + "loss": 4.1714, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263979145196785e-05, + "loss": 4.1503, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263140550445733e-05, + "loss": 4.173, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623035935750545e-05, + "loss": 4.1629, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261464998824002e-05, + "loss": 4.1674, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26062640407295e-05, + "loss": 4.1638, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259787809321898e-05, + "loss": 4.1733, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258950852451219e-05, + "loss": 4.1642, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258112257700167e-05, + "loss": 4.1767, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257273662949115e-05, + "loss": 4.151, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256436706078436e-05, + "loss": 4.1617, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255598111327384e-05, + "loss": 4.1587, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254759516576332e-05, + "loss": 4.1579, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.25392092182528e-05, + "loss": 4.1592, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253082327074228e-05, + "loss": 4.1636, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252243732323176e-05, + "loss": 4.1649, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251405137572124e-05, + "loss": 4.1492, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250566542821072e-05, + "loss": 4.1702, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.157918930053711, + "eval_runtime": 288.5832, + "eval_samples_per_second": 1322.291, + "eval_steps_per_second": 41.323, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249729585950393e-05, + "loss": 4.1588, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248890991199341e-05, + "loss": 4.1452, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248052396448289e-05, + "loss": 4.1661, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247213801697237e-05, + "loss": 4.156, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246375206946185e-05, + "loss": 4.1602, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245536612195133e-05, + "loss": 4.1534, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244698017444081e-05, + "loss": 4.1515, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243859422693029e-05, + "loss": 4.1495, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243020827941978e-05, + "loss": 4.1582, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242182233190926e-05, + "loss": 4.1539, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241343638439873e-05, + "loss": 4.1638, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240505043688821e-05, + "loss": 4.1654, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239668086818143e-05, + "loss": 4.1505, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238829492067091e-05, + "loss": 4.1541, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237990897316038e-05, + "loss": 4.1563, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237152302564986e-05, + "loss": 4.1484, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236313707813934e-05, + "loss": 4.1424, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235475113062882e-05, + "loss": 4.1509, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.23463651831183e-05, + "loss": 4.1488, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233797923560778e-05, + "loss": 4.162, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232959328809726e-05, + "loss": 4.158, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232120734058675e-05, + "loss": 4.1575, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231282139307623e-05, + "loss": 4.1627, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230443544556571e-05, + "loss": 4.1643, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296065876858916e-05, + "loss": 4.144, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287679929348396e-05, + "loss": 4.157, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279293981837876e-05, + "loss": 4.1407, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270908034327356e-05, + "loss": 4.1483, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262538465620565e-05, + "loss": 4.1477, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254152518110045e-05, + "loss": 4.1447, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245766570599525e-05, + "loss": 4.1579, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237380623089005e-05, + "loss": 4.1496, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228994675578485e-05, + "loss": 4.1477, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220608728067965e-05, + "loss": 4.154, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221223915936118e-05, + "loss": 4.1509, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220385321185066e-05, + "loss": 4.1543, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219546726434014e-05, + "loss": 4.1431, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218708131682962e-05, + "loss": 4.1413, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178695369319094e-05, + "loss": 4.1367, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170309421808574e-05, + "loss": 4.1419, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161923474298054e-05, + "loss": 4.1416, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215355390559126e-05, + "loss": 4.1504, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214516795808074e-05, + "loss": 4.1475, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213678201057022e-05, + "loss": 4.1471, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.21283960630597e-05, + "loss": 4.1562, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212001011554918e-05, + "loss": 4.1466, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111656925646134e-05, + "loss": 4.1507, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103270978135614e-05, + "loss": 4.1377, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094885030625094e-05, + "loss": 4.128, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208649908311457e-05, + "loss": 4.1572, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207811313560405e-05, + "loss": 4.1405, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206972718809353e-05, + "loss": 4.135, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206134124058301e-05, + "loss": 4.1396, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205295529307249e-05, + "loss": 4.1341, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204460210316943e-05, + "loss": 4.138, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203621615565891e-05, + "loss": 4.133, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027830208148385e-05, + "loss": 4.1382, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.20194606394416e-05, + "loss": 4.139, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201107469193109e-05, + "loss": 4.1508, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200268874442057e-05, + "loss": 4.1289, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199430279691004e-05, + "loss": 4.1285, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198591684939952e-05, + "loss": 4.1506, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977530901889e-05, + "loss": 4.1224, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196914495437848e-05, + "loss": 4.1322, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196075900686796e-05, + "loss": 4.1393, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195238943816117e-05, + "loss": 4.1494, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194400349065065e-05, + "loss": 4.1288, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193561754314013e-05, + "loss": 4.1273, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192723159562961e-05, + "loss": 4.118, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191884564811909e-05, + "loss": 4.1373, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191045970060857e-05, + "loss": 4.1512, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902090131901786e-05, + "loss": 4.136, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893704184391266e-05, + "loss": 4.1379, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885318236880746e-05, + "loss": 4.1458, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876932289370226e-05, + "loss": 4.1516, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868562720663435e-05, + "loss": 4.1275, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860176773152915e-05, + "loss": 4.14, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851790825642395e-05, + "loss": 4.1401, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843421256935604e-05, + "loss": 4.1226, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835035309425084e-05, + "loss": 4.1376, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826649361914564e-05, + "loss": 4.1382, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818263414404044e-05, + "loss": 4.1371, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809877466893524e-05, + "loss": 4.1382, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180149151938301e-05, + "loss": 4.1361, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179312195067622e-05, + "loss": 4.1296, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17847360031657e-05, + "loss": 4.1374, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177635005565518e-05, + "loss": 4.1357, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176796410814466e-05, + "loss": 4.1277, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175957816063414e-05, + "loss": 4.1331, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175119221312362e-05, + "loss": 4.1309, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17428062656131e-05, + "loss": 4.1374, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173442031810257e-05, + "loss": 4.1307, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172603437059205e-05, + "loss": 4.125, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171764842308153e-05, + "loss": 4.1463, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170926247557101e-05, + "loss": 4.1375, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170089290686423e-05, + "loss": 4.1328, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1202, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168412101184319e-05, + "loss": 4.1326, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167573506433267e-05, + "loss": 4.124, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166736549562588e-05, + "loss": 4.1336, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165897954811536e-05, + "loss": 4.1435, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165059360060484e-05, + "loss": 4.1252, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164220765309432e-05, + "loss": 4.1259, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16338217055838e-05, + "loss": 4.1306, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625452136877006e-05, + "loss": 4.1066, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161708256817022e-05, + "loss": 4.1301, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.16086966206597e-05, + "loss": 4.1113, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160031067314918e-05, + "loss": 4.1313, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159192472563866e-05, + "loss": 4.1173, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158353877812814e-05, + "loss": 4.1302, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157515283061762e-05, + "loss": 4.122, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1257, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.1366, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155002774569352e-05, + "loss": 4.1204, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1541641798183e-05, + "loss": 4.1367, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153325585067248e-05, + "loss": 4.1408, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152486990316196e-05, + "loss": 4.1287, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151648395565144e-05, + "loss": 4.1262, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150809800814092e-05, + "loss": 4.1188, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.14997120606304e-05, + "loss": 4.1295, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149132611311988e-05, + "loss": 4.1209, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482956544413095e-05, + "loss": 4.1419, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474570596902575e-05, + "loss": 4.1131, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466184649392055e-05, + "loss": 4.1308, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457798701881535e-05, + "loss": 4.129, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449429133174744e-05, + "loss": 4.1258, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441043185664224e-05, + "loss": 4.1133, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432657238153704e-05, + "loss": 4.1275, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142428766944691e-05, + "loss": 4.116, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141590172193639e-05, + "loss": 4.1394, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140751577442587e-05, + "loss": 4.1219, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139912982691535e-05, + "loss": 4.1295, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139074387940483e-05, + "loss": 4.11, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138235793189432e-05, + "loss": 4.1345, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.13739719843838e-05, + "loss": 4.1258, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136558603687328e-05, + "loss": 4.1283, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135721646816649e-05, + "loss": 4.1236, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134883052065597e-05, + "loss": 4.1263, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134044457314545e-05, + "loss": 4.1258, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133205862563493e-05, + "loss": 4.1402, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132368905692814e-05, + "loss": 4.1082, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131530310941762e-05, + "loss": 4.1244, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.13069171619071e-05, + "loss": 4.1193, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129853121439658e-05, + "loss": 4.121, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129016164568979e-05, + "loss": 4.118, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1281775698179273e-05, + "loss": 4.1238, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273389750668753e-05, + "loss": 4.1258, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126500380315823e-05, + "loss": 4.1138, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1256617855647707e-05, + "loss": 4.1299, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.1273651123046875, + "eval_runtime": 317.6105, + "eval_samples_per_second": 1201.443, + "eval_steps_per_second": 37.546, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248231908137186e-05, + "loss": 4.1171, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12398623394304e-05, + "loss": 4.1101, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123147639191988e-05, + "loss": 4.1278, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223090444409356e-05, + "loss": 4.1148, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214704496898835e-05, + "loss": 4.1213, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206318549388315e-05, + "loss": 4.1154, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197932601877795e-05, + "loss": 4.116, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118956303317101e-05, + "loss": 4.1096, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118117708566049e-05, + "loss": 4.1217, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117279113814997e-05, + "loss": 4.1144, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116440519063945e-05, + "loss": 4.1244, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115601924312893e-05, + "loss": 4.1257, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114764967442214e-05, + "loss": 4.1172, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113926372691162e-05, + "loss": 4.1163, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.11308777794011e-05, + "loss": 4.1151, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112249183189058e-05, + "loss": 4.1089, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111410588438006e-05, + "loss": 4.1082, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110571993686954e-05, + "loss": 4.1112, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109733398935902e-05, + "loss": 4.1142, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.10889480418485e-05, + "loss": 4.1192, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108056209433798e-05, + "loss": 4.126, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072192525631196e-05, + "loss": 4.119, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1063822956924405e-05, + "loss": 4.1227, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055437009413885e-05, + "loss": 4.1268, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047051061903365e-05, + "loss": 4.1032, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038665114392845e-05, + "loss": 4.1215, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030279166882325e-05, + "loss": 4.1086, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021893219371805e-05, + "loss": 4.1104, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013507271861285e-05, + "loss": 4.1073, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005121324350764e-05, + "loss": 4.1127, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996751755643974e-05, + "loss": 4.1143, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988365808133454e-05, + "loss": 4.1161, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979979860622933e-05, + "loss": 4.1127, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971593913112413e-05, + "loss": 4.1179, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096322434440563e-05, + "loss": 4.1081, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095483839689511e-05, + "loss": 4.1179, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094646882818832e-05, + "loss": 4.1138, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09380828806778e-05, + "loss": 4.0976, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092969693316728e-05, + "loss": 4.1015, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092131098565676e-05, + "loss": 4.1042, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091292503814624e-05, + "loss": 4.1088, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090453909063572e-05, + "loss": 4.1128, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089615314312519e-05, + "loss": 4.1106, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088776719561467e-05, + "loss": 4.107, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087939762690789e-05, + "loss": 4.1214, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087101167939737e-05, + "loss": 4.1097, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086262573188685e-05, + "loss": 4.1149, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085423978437633e-05, + "loss": 4.1042, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084585383686581e-05, + "loss": 4.085, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837484268159016e-05, + "loss": 4.1226, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829098320648496e-05, + "loss": 4.1069, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0820712373137976e-05, + "loss": 4.1052, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812326425627456e-05, + "loss": 4.1019, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803956856920665e-05, + "loss": 4.0987, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0795570909410145e-05, + "loss": 4.1016, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078720134070336e-05, + "loss": 4.096, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778815393192834e-05, + "loss": 4.1033, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077042944568232e-05, + "loss": 4.0999, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076205987697554e-05, + "loss": 4.1167, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753673929465017e-05, + "loss": 4.0947, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074528798195449e-05, + "loss": 4.0926, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073690203444397e-05, + "loss": 4.1156, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072851608693345e-05, + "loss": 4.0879, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072013013942293e-05, + "loss": 4.0943, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071174419191241e-05, + "loss": 4.1072, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070335824440189e-05, + "loss": 4.113, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069497229689137e-05, + "loss": 4.0942, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068658634938085e-05, + "loss": 4.0929, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067821678067406e-05, + "loss": 4.085, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066983083316354e-05, + "loss": 4.1024, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066144488565302e-05, + "loss": 4.1154, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653058938142505e-05, + "loss": 4.1019, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0644672990631985e-05, + "loss": 4.1031, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636287043121465e-05, + "loss": 4.1134, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0627901095610945e-05, + "loss": 4.1178, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619531526904154e-05, + "loss": 4.0903, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611145579393634e-05, + "loss": 4.1086, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602759631883114e-05, + "loss": 4.0985, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594373684372594e-05, + "loss": 4.0941, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585987736862074e-05, + "loss": 4.0991, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577601789351554e-05, + "loss": 4.1084, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056921584184103e-05, + "loss": 4.1029, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056084627313424e-05, + "loss": 4.1091, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055246032562372e-05, + "loss": 4.0994, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.05440743781132e-05, + "loss": 4.0931, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053568843060268e-05, + "loss": 4.1027, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052730248309216e-05, + "loss": 4.1009, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051893291438538e-05, + "loss": 4.0936, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051054696687485e-05, + "loss": 4.0984, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050216101936433e-05, + "loss": 4.0994, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049377507185381e-05, + "loss": 4.1045, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048538912434329e-05, + "loss": 4.0971, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047700317683277e-05, + "loss": 4.0879, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046861722932225e-05, + "loss": 4.1093, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046023128181173e-05, + "loss": 4.1051, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045186171310494e-05, + "loss": 4.0983, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044347576559443e-05, + "loss": 4.0898, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043508981808391e-05, + "loss": 4.0964, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042670387057339e-05, + "loss": 4.0905, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418334301866596e-05, + "loss": 4.1006, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0409948354356076e-05, + "loss": 4.1086, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0401562406845556e-05, + "loss": 4.0955, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393176459335036e-05, + "loss": 4.0931, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0384806890628245e-05, + "loss": 4.0925, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376420943117725e-05, + "loss": 4.0793, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368034995607205e-05, + "loss": 4.092, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0359665426900414e-05, + "loss": 4.0793, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351279479389894e-05, + "loss": 4.0993, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342893531879374e-05, + "loss": 4.0857, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033450758436886e-05, + "loss": 4.0959, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032612163685834e-05, + "loss": 4.0865, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031775206815155e-05, + "loss": 4.0955, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030936612064103e-05, + "loss": 4.0986, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030098017313051e-05, + "loss": 4.0891, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029259422561999e-05, + "loss": 4.1069, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028420827810947e-05, + "loss": 4.1051, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027582233059895e-05, + "loss": 4.0945, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026743638308843e-05, + "loss": 4.0968, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025905043557791e-05, + "loss": 4.0847, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025066448806738e-05, + "loss": 4.0961, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.02422949193606e-05, + "loss": 4.0927, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023390897185008e-05, + "loss": 4.1027, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022552302433956e-05, + "loss": 4.0828, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021713707682904e-05, + "loss": 4.0998, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208767508122255e-05, + "loss": 4.0993, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200381560611735e-05, + "loss": 4.0933, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191995613101214e-05, + "loss": 4.078, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018360966559069e-05, + "loss": 4.0968, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175240096883904e-05, + "loss": 4.0862, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016687052817711e-05, + "loss": 4.1025, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015848458066659e-05, + "loss": 4.0944, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015009863315607e-05, + "loss": 4.0955, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014171268564555e-05, + "loss": 4.0753, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013332673813503e-05, + "loss": 4.1065, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012494079062451e-05, + "loss": 4.0899, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011657122191773e-05, + "loss": 4.097, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010818527440721e-05, + "loss": 4.093, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009979932689669e-05, + "loss": 4.0928, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009141337938616e-05, + "loss": 4.0967, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008302743187564e-05, + "loss": 4.1064, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007464148436512e-05, + "loss": 4.0776, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.00662555368546e-05, + "loss": 4.0937, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005786958934408e-05, + "loss": 4.0865, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004948364183356e-05, + "loss": 4.0862, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004111407312677e-05, + "loss": 4.087, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0032744504419986e-05, + "loss": 4.0944, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024358556909466e-05, + "loss": 4.0949, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015972609398946e-05, + "loss": 4.0812, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007586661888426e-05, + "loss": 4.0979, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.103210926055908, + "eval_runtime": 316.9009, + "eval_samples_per_second": 1204.134, + "eval_steps_per_second": 37.63, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999200714377906e-05, + "loss": 4.0836, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9990814766867386e-05, + "loss": 4.0808, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9982428819356866e-05, + "loss": 4.0925, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974042871846346e-05, + "loss": 4.0817, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965656924335826e-05, + "loss": 4.0925, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957270976825306e-05, + "loss": 4.079, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9948885029314786e-05, + "loss": 4.0918, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940499081804266e-05, + "loss": 4.0771, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932113134293746e-05, + "loss": 4.0891, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992372718678322e-05, + "loss": 4.084, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915341239272706e-05, + "loss": 4.0906, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906955291762185e-05, + "loss": 4.096, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.98985857230554e-05, + "loss": 4.0838, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890199775544875e-05, + "loss": 4.0863, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881813828034354e-05, + "loss": 4.0849, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873427880523834e-05, + "loss": 4.0755, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865041933013314e-05, + "loss": 4.0759, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856655985502794e-05, + "loss": 4.0816, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848270037992274e-05, + "loss": 4.082, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839884090481754e-05, + "loss": 4.0841, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831498142971234e-05, + "loss": 4.0957, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823112195460714e-05, + "loss": 4.0884, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814726247950194e-05, + "loss": 4.0926, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806340300439674e-05, + "loss": 4.0925, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797954352929154e-05, + "loss": 4.0772, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978958478422237e-05, + "loss": 4.0874, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978121521551558e-05, + "loss": 4.0767, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977282926800506e-05, + "loss": 4.0809, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976444332049454e-05, + "loss": 4.0814, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975605737298402e-05, + "loss": 4.078, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974768780427723e-05, + "loss": 4.0839, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973930185676671e-05, + "loss": 4.0847, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973091590925619e-05, + "loss": 4.082, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972252996174567e-05, + "loss": 4.088, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971414401423515e-05, + "loss": 4.077, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970575806672463e-05, + "loss": 4.0885, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969740487682157e-05, + "loss": 4.0827, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968901892931105e-05, + "loss": 4.0685, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968063298180053e-05, + "loss": 4.0747, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967224703429001e-05, + "loss": 4.0695, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966386108677949e-05, + "loss": 4.0794, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965547513926897e-05, + "loss": 4.0833, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964708919175845e-05, + "loss": 4.08, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963870324424793e-05, + "loss": 4.0791, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630317296737406e-05, + "loss": 4.0886, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621931349226886e-05, + "loss": 4.0812, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96135617805201e-05, + "loss": 4.0868, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960517583300958e-05, + "loss": 4.0755, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959678988549906e-05, + "loss": 4.0479, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958840393798854e-05, + "loss": 4.0981, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958001799047802e-05, + "loss": 4.0726, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95716320429675e-05, + "loss": 4.0795, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956324609545698e-05, + "loss": 4.0711, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955486014794646e-05, + "loss": 4.0702, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954649057923967e-05, + "loss": 4.0684, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953810463172915e-05, + "loss": 4.0672, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952971868421863e-05, + "loss": 4.0738, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952133273670811e-05, + "loss": 4.0684, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951294678919759e-05, + "loss": 4.0886, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950456084168707e-05, + "loss": 4.0686, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949619127298028e-05, + "loss": 4.0643, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948780532546976e-05, + "loss": 4.0838, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479419377959246e-05, + "loss": 4.0609, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471033430448726e-05, + "loss": 4.0637, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.0786, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454277914231415e-05, + "loss": 4.0802, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9445891966720895e-05, + "loss": 4.0654, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437506019210375e-05, + "loss": 4.0653, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429120071699855e-05, + "loss": 4.056, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420734124189335e-05, + "loss": 4.072, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412364555482544e-05, + "loss": 4.0879, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403978607972024e-05, + "loss": 4.0709, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395592660461504e-05, + "loss": 4.0776, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.0803, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.93788371442442e-05, + "loss": 4.088, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937046757553741e-05, + "loss": 4.0641, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936208162802689e-05, + "loss": 4.0786, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935369568051637e-05, + "loss": 4.0687, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934530973300585e-05, + "loss": 4.0696, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933694016429906e-05, + "loss": 4.0686, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932855421678854e-05, + "loss": 4.0772, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932016826927802e-05, + "loss": 4.0727, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.93117823217675e-05, + "loss": 4.0827, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303412753060706e-05, + "loss": 4.0649, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295026805550186e-05, + "loss": 4.0662, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9286640858039666e-05, + "loss": 4.0779, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927825491052915e-05, + "loss": 4.0698, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926986896301863e-05, + "loss": 4.0621, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926149939431184e-05, + "loss": 4.072, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925311344680132e-05, + "loss": 4.0714, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.92447274992908e-05, + "loss": 4.0774, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923634155178028e-05, + "loss": 4.068, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922795560426976e-05, + "loss": 4.0595, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921956965675924e-05, + "loss": 4.0806, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921120008805245e-05, + "loss": 4.0752, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920281414054193e-05, + "loss": 4.0684, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919442819303141e-05, + "loss": 4.0649, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918604224552089e-05, + "loss": 4.0649, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917765629801037e-05, + "loss": 4.0624, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916927035049985e-05, + "loss": 4.0739, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916088440298933e-05, + "loss": 4.0797, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915251483428254e-05, + "loss": 4.0695, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914412888677202e-05, + "loss": 4.0645, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91357429392615e-05, + "loss": 4.0588, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912735699175098e-05, + "loss": 4.0581, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911897104424046e-05, + "loss": 4.0607, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911060147553367e-05, + "loss": 4.0537, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910221552802315e-05, + "loss": 4.0708, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909382958051263e-05, + "loss": 4.0585, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908544363300211e-05, + "loss": 4.0655, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907705768549159e-05, + "loss": 4.0558, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906867173798107e-05, + "loss": 4.0696, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060285790470555e-05, + "loss": 4.0716, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051916221763764e-05, + "loss": 4.0594, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043530274253244e-05, + "loss": 4.0806, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035144326742724e-05, + "loss": 4.0796, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026758379232204e-05, + "loss": 4.0662, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901838881052541e-05, + "loss": 4.0693, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901000286301489e-05, + "loss": 4.0586, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900161691550437e-05, + "loss": 4.0628, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899323096799385e-05, + "loss": 4.0721, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898484502048333e-05, + "loss": 4.0709, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897645907297281e-05, + "loss": 4.0562, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896807312546229e-05, + "loss": 4.0728, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895970355675551e-05, + "loss": 4.0726, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895131760924499e-05, + "loss": 4.0671, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894293166173447e-05, + "loss": 4.0541, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893454571422395e-05, + "loss": 4.0659, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892615976671343e-05, + "loss": 4.0565, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891779019800664e-05, + "loss": 4.077, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890940425049612e-05, + "loss": 4.0649, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.89010183029856e-05, + "loss": 4.0713, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889263235547508e-05, + "loss": 4.0482, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888424640796455e-05, + "loss": 4.0778, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887586046045403e-05, + "loss": 4.0606, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886747451294351e-05, + "loss": 4.0714, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0668, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885070261792248e-05, + "loss": 4.0629, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884231667041196e-05, + "loss": 4.0688, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833947101705167e-05, + "loss": 4.0779, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825561154194647e-05, + "loss": 4.0503, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817175206684127e-05, + "loss": 4.0697, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808789259173606e-05, + "loss": 4.0585, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800419690466816e-05, + "loss": 4.0592, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792033742956296e-05, + "loss": 4.061, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783647795445775e-05, + "loss": 4.0668, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775261847935255e-05, + "loss": 4.0656, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766875900424735e-05, + "loss": 4.0598, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758506331717944e-05, + "loss": 4.0699, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.0840983390808105, + "eval_runtime": 319.7445, + "eval_samples_per_second": 1193.425, + "eval_steps_per_second": 37.295, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875012038420743e-05, + "loss": 4.0558, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874173443669691e-05, + "loss": 4.0545, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873334848918639e-05, + "loss": 4.0642, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.87249789204796e-05, + "loss": 4.0569, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871659297296908e-05, + "loss": 4.064, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870820702545856e-05, + "loss": 4.0534, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869982107794804e-05, + "loss": 4.0659, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869143513043752e-05, + "loss": 4.0516, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683049182927e-05, + "loss": 4.059, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867466323541648e-05, + "loss": 4.0604, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866627728790596e-05, + "loss": 4.0612, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86579240980029e-05, + "loss": 4.0668, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649554529296114e-05, + "loss": 4.0702, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641168581785594e-05, + "loss": 4.0514, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632782634275074e-05, + "loss": 4.0568, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624396686764554e-05, + "loss": 4.0512, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616010739254034e-05, + "loss": 4.0477, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860764117054724e-05, + "loss": 4.0579, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859925522303672e-05, + "loss": 4.0516, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.85908692755262e-05, + "loss": 4.0578, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858248332801568e-05, + "loss": 4.0704, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857409738050516e-05, + "loss": 4.0655, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856571143299464e-05, + "loss": 4.0653, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855732548548412e-05, + "loss": 4.065, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.85489395379736e-05, + "loss": 4.0499, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854055359046308e-05, + "loss": 4.0598, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853216764295256e-05, + "loss": 4.051, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852378169544204e-05, + "loss": 4.0576, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851539574793152e-05, + "loss": 4.0509, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850704255802847e-05, + "loss": 4.0534, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849865661051795e-05, + "loss": 4.0552, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849027066300743e-05, + "loss": 4.058, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848188471549691e-05, + "loss": 4.0561, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847349876798639e-05, + "loss": 4.0572, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846511282047586e-05, + "loss": 4.0539, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845672687296534e-05, + "loss": 4.0601, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8448357304258556e-05, + "loss": 4.0602, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8439971356748036e-05, + "loss": 4.0442, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8431585409237516e-05, + "loss": 4.0481, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423199461726996e-05, + "loss": 4.0455, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414813514216476e-05, + "loss": 4.0476, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8406427566705956e-05, + "loss": 4.055, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398041619195436e-05, + "loss": 4.0572, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8389672050488645e-05, + "loss": 4.055, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381286102978125e-05, + "loss": 4.0592, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372900155467605e-05, + "loss": 4.0572, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8364514207957085e-05, + "loss": 4.0597, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356128260446565e-05, + "loss": 4.0501, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8347758691739774e-05, + "loss": 4.0277, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339372744229254e-05, + "loss": 4.0694, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833098679671874e-05, + "loss": 4.0464, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832260084920822e-05, + "loss": 4.0524, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.83142149016977e-05, + "loss": 4.0485, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830582895418718e-05, + "loss": 4.0421, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829744300667666e-05, + "loss": 4.044, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828905705916614e-05, + "loss": 4.0413, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828067111165562e-05, + "loss": 4.0504, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827230154294883e-05, + "loss": 4.0419, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826391559543831e-05, + "loss": 4.0617, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825552964792779e-05, + "loss": 4.0445, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824714370041727e-05, + "loss": 4.0318, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823875775290675e-05, + "loss": 4.0606, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823038818419996e-05, + "loss": 4.0378, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822200223668944e-05, + "loss": 4.0371, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213616289178925e-05, + "loss": 4.0534, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205246720472134e-05, + "loss": 4.0582, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196860772961614e-05, + "loss": 4.0398, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188474825451094e-05, + "loss": 4.0391, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180088877940574e-05, + "loss": 4.0329, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817170293043005e-05, + "loss": 4.0466, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816333336172326e-05, + "loss": 4.0608, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815494741421274e-05, + "loss": 4.0483, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814656146670222e-05, + "loss": 4.0517, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138175519191696e-05, + "loss": 4.0519, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812980595048491e-05, + "loss": 4.0619, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812143638177813e-05, + "loss": 4.0418, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811305043426761e-05, + "loss": 4.0578, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810466448675709e-05, + "loss": 4.0387, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809627853924657e-05, + "loss": 4.0459, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808789259173605e-05, + "loss": 4.0432, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807950664422552e-05, + "loss": 4.0503, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071120696715e-05, + "loss": 4.0511, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806273474920448e-05, + "loss": 4.0583, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805434880169396e-05, + "loss": 4.039, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804597923298717e-05, + "loss": 4.0425, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803759328547665e-05, + "loss": 4.0503, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802920733796613e-05, + "loss": 4.0492, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802082139045561e-05, + "loss": 4.0374, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801246820055256e-05, + "loss": 4.0444, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800408225304204e-05, + "loss": 4.0487, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799569630553152e-05, + "loss": 4.0495, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987310358020995e-05, + "loss": 4.0446, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978924410510475e-05, + "loss": 4.033, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797055484180369e-05, + "loss": 4.0562, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962168894293164e-05, + "loss": 4.051, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953782946782644e-05, + "loss": 4.0435, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945396999272124e-05, + "loss": 4.0388, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937011051761604e-05, + "loss": 4.0417, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928625104251084e-05, + "loss": 4.0356, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920239156740564e-05, + "loss": 4.0516, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791186958803378e-05, + "loss": 4.0541, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790348364052326e-05, + "loss": 4.0412, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789509769301274e-05, + "loss": 4.0465, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788671174550222e-05, + "loss": 4.0354, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787834217679543e-05, + "loss": 4.0364, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786995622928491e-05, + "loss": 4.0326, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786157028177439e-05, + "loss": 4.033, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785318433426387e-05, + "loss": 4.0431, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784479838675335e-05, + "loss": 4.0368, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783641243924283e-05, + "loss": 4.039, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782802649173231e-05, + "loss": 4.0359, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781964054422179e-05, + "loss": 4.0397, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811270975515004e-05, + "loss": 4.049, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780290140680821e-05, + "loss": 4.0361, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779451545929769e-05, + "loss": 4.0537, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778612951178717e-05, + "loss": 4.0557, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777774356427665e-05, + "loss": 4.0453, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776935761676613e-05, + "loss": 4.0403, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776097166925561e-05, + "loss": 4.0358, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775258572174509e-05, + "loss": 4.0407, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.77442161530383e-05, + "loss": 4.0478, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773583020552778e-05, + "loss": 4.045, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772744425801726e-05, + "loss": 4.0347, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771905831050674e-05, + "loss": 4.0503, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771067236299622e-05, + "loss": 4.0514, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.77022864154857e-05, + "loss": 4.0364, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769390046797518e-05, + "loss": 4.0316, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768551452046466e-05, + "loss": 4.0453, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767714495175788e-05, + "loss": 4.0318, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7668775383051087e-05, + "loss": 4.0557, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7660389435540566e-05, + "loss": 4.038, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652003488030046e-05, + "loss": 4.0489, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7643617540519526e-05, + "loss": 4.0264, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635231593009e-05, + "loss": 4.0499, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762684564549848e-05, + "loss": 4.0468, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761845969798796e-05, + "loss": 4.0426, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761007375047744e-05, + "loss": 4.0439, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7601704181770655e-05, + "loss": 4.0376, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593318234260135e-05, + "loss": 4.0448, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584932286749615e-05, + "loss": 4.0622, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576546339239095e-05, + "loss": 4.0242, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568176770532304e-05, + "loss": 4.0465, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7559790823021784e-05, + "loss": 4.0373, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7551404875511264e-05, + "loss": 4.0326, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543018928000744e-05, + "loss": 4.0398, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753464935929395e-05, + "loss": 4.0415, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752626341178343e-05, + "loss": 4.0422, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751787746427291e-05, + "loss": 4.0396, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750949151676239e-05, + "loss": 4.0453, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.068212509155273, + "eval_runtime": 318.7899, + "eval_samples_per_second": 1196.998, + "eval_steps_per_second": 37.407, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750110556925188e-05, + "loss": 4.0247, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749271962174136e-05, + "loss": 4.0333, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748433367423084e-05, + "loss": 4.0392, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747594772672032e-05, + "loss": 4.0353, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.74675617792098e-05, + "loss": 4.0434, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745917583169928e-05, + "loss": 4.031, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745078988418876e-05, + "loss": 4.0413, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744240393667824e-05, + "loss": 4.0287, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743401798916771e-05, + "loss": 4.0381, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742563204165719e-05, + "loss": 4.0374, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741724609414667e-05, + "loss": 4.0349, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740886014663615e-05, + "loss": 4.0471, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740049057792936e-05, + "loss": 4.0485, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739210463041884e-05, + "loss": 4.0291, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738371868290833e-05, + "loss": 4.0365, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737533273539781e-05, + "loss": 4.0267, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736694678788729e-05, + "loss": 4.0271, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735856084037677e-05, + "loss": 4.0347, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735017489286625e-05, + "loss": 4.0267, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734178894535573e-05, + "loss": 4.0362, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733340299784521e-05, + "loss": 4.0488, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732501705033469e-05, + "loss": 4.0424, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731663110282417e-05, + "loss": 4.0449, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730824515531365e-05, + "loss": 4.0411, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729985920780313e-05, + "loss": 4.0326, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729148963909634e-05, + "loss": 4.0375, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728310369158582e-05, + "loss": 4.0282, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274734122879026e-05, + "loss": 4.0387, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726634817536851e-05, + "loss": 4.0275, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725796222785799e-05, + "loss": 4.0299, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724957628034747e-05, + "loss": 4.0328, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724119033283695e-05, + "loss": 4.0367, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723280438532643e-05, + "loss": 4.0395, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7224418437815906e-05, + "loss": 4.0328, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216032490305386e-05, + "loss": 4.0338, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.72076629215986e-05, + "loss": 4.0335, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199276974088075e-05, + "loss": 4.041, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190891026577555e-05, + "loss": 4.0231, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182505079067035e-05, + "loss": 4.0241, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174119131556515e-05, + "loss": 4.0256, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165733184045995e-05, + "loss": 4.0254, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715736361533921e-05, + "loss": 4.0313, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714897766782869e-05, + "loss": 4.0363, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714059172031817e-05, + "loss": 4.0332, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713220577280765e-05, + "loss": 4.0372, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712381982529713e-05, + "loss": 4.0344, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711545025659034e-05, + "loss": 4.0379, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710706430907982e-05, + "loss": 4.0302, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.70986783615693e-05, + "loss": 4.005, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709029241405878e-05, + "loss": 4.0447, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708192284535199e-05, + "loss": 4.0251, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707353689784147e-05, + "loss": 4.0314, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706515095033095e-05, + "loss": 4.0282, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056765002820435e-05, + "loss": 4.0173, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048395434113644e-05, + "loss": 4.0275, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040009486603124e-05, + "loss": 4.0186, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031623539092604e-05, + "loss": 4.0314, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023237591582084e-05, + "loss": 4.0183, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014851644071564e-05, + "loss": 4.0398, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006465696561044e-05, + "loss": 4.0229, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998079749050524e-05, + "loss": 4.0082, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989693801540004e-05, + "loss": 4.0424, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981307854029484e-05, + "loss": 4.016, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697293828532269e-05, + "loss": 4.0145, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696455233781217e-05, + "loss": 4.0322, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695618276910538e-05, + "loss": 4.0364, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694779682159487e-05, + "loss": 4.0186, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693941087408435e-05, + "loss": 4.0194, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693102492657383e-05, + "loss": 4.0118, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692263897906331e-05, + "loss": 4.0202, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691425303155279e-05, + "loss": 4.0353, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6905883462846e-05, + "loss": 4.0297, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689749751533548e-05, + "loss": 4.0299, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688911156782496e-05, + "loss": 4.0304, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688072562031444e-05, + "loss": 4.0392, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6872356051607646e-05, + "loss": 4.0247, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6863970104097126e-05, + "loss": 4.0334, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855584156586606e-05, + "loss": 4.0164, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847198209076086e-05, + "loss": 4.0236, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6838812261565566e-05, + "loss": 4.0212, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6830426314055046e-05, + "loss": 4.0278, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822040366544526e-05, + "loss": 4.0314, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6813654419034006e-05, + "loss": 4.0353, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6805284850327215e-05, + "loss": 4.0214, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6796898902816695e-05, + "loss": 4.0198, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678852933410991e-05, + "loss": 4.0266, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780143386599384e-05, + "loss": 4.0292, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6771757439088864e-05, + "loss": 4.0167, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6763371491578344e-05, + "loss": 4.0238, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6754985544067824e-05, + "loss": 4.0339, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746599596557304e-05, + "loss": 4.0244, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673821364904679e-05, + "loss": 4.023, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672982770153627e-05, + "loss": 4.0139, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672145813282948e-05, + "loss": 4.0306, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671307218531896e-05, + "loss": 4.0334, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670468623780844e-05, + "loss": 4.0241, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669630029029792e-05, + "loss": 4.0187, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668793072159113e-05, + "loss": 4.0194, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667954477408061e-05, + "loss": 4.0164, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667115882657009e-05, + "loss": 4.0294, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666277287905957e-05, + "loss": 4.0341, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665440331035278e-05, + "loss": 4.0189, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664601736284226e-05, + "loss": 4.0228, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637631415331745e-05, + "loss": 4.0188, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629261846624954e-05, + "loss": 4.0111, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620875899114434e-05, + "loss": 4.0146, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612489951603914e-05, + "loss": 4.0121, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604104004093393e-05, + "loss": 4.0171, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595718056582873e-05, + "loss": 4.0183, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658733210907235e-05, + "loss": 4.0145, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657894616156183e-05, + "loss": 4.0176, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657056021405131e-05, + "loss": 4.0162, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656219064534452e-05, + "loss": 4.0278, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553804697834e-05, + "loss": 4.0132, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654541875032348e-05, + "loss": 4.0342, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653703280281296e-05, + "loss": 4.0326, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652866323410618e-05, + "loss": 4.0273, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652027728659566e-05, + "loss": 4.0191, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651189133908514e-05, + "loss": 4.0155, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650350539157462e-05, + "loss": 4.0191, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64951194440641e-05, + "loss": 4.0293, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648674987535731e-05, + "loss": 4.024, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6478380306650516e-05, + "loss": 4.0152, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469994359139996e-05, + "loss": 4.0243, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6461608411629476e-05, + "loss": 4.033, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453222464118956e-05, + "loss": 4.0164, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6444836516608436e-05, + "loss": 4.012, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6436450569097916e-05, + "loss": 4.0229, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642808100039113e-05, + "loss": 4.0085, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641969505288061e-05, + "loss": 4.0377, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641130910537009e-05, + "loss": 4.0159, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640292315785957e-05, + "loss": 4.028, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394537210349045e-05, + "loss": 4.007, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386151262838525e-05, + "loss": 4.0255, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6377765315328005e-05, + "loss": 4.0238, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6369379367817485e-05, + "loss": 4.0244, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636102617791443e-05, + "loss": 4.0219, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635264023040391e-05, + "loss": 4.0185, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634425428289339e-05, + "loss": 4.023, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633586833538287e-05, + "loss": 4.04, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632748238787235e-05, + "loss": 4.0065, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631909644036183e-05, + "loss": 4.0219, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631071049285131e-05, + "loss": 4.0196, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630234092414452e-05, + "loss": 4.0135, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293954976634e-05, + "loss": 4.0193, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628556902912348e-05, + "loss": 4.0215, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627718308161296e-05, + "loss": 4.0199, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626879713410244e-05, + "loss": 4.0177, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626041118659192e-05, + "loss": 4.0227, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.054370403289795, + "eval_runtime": 298.866, + "eval_samples_per_second": 1276.796, + "eval_steps_per_second": 39.901, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.62520252390814e-05, + "loss": 4.0123, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624365567037461e-05, + "loss": 4.0126, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623528610166782e-05, + "loss": 4.0201, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.62269001541573e-05, + "loss": 4.0149, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621851420664678e-05, + "loss": 4.0235, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621012825913626e-05, + "loss": 4.0133, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620174231162574e-05, + "loss": 4.0189, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619335636411522e-05, + "loss": 4.0131, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61849704166047e-05, + "loss": 4.0182, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617658446909418e-05, + "loss": 4.0121, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616819852158366e-05, + "loss": 4.0169, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615982895287687e-05, + "loss": 4.0315, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615145938417008e-05, + "loss": 4.0227, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614307343665956e-05, + "loss": 4.0091, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613468748914904e-05, + "loss": 4.017, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612630154163852e-05, + "loss": 4.0053, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611791559412801e-05, + "loss": 4.0098, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610954602542122e-05, + "loss": 4.0177, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61011600779107e-05, + "loss": 4.0056, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609277413040018e-05, + "loss": 4.0165, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608438818288966e-05, + "loss": 4.0242, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607600223537914e-05, + "loss": 4.0229, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6067616287868617e-05, + "loss": 4.025, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6059230340358097e-05, + "loss": 4.0216, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050844392847576e-05, + "loss": 4.0104, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6042474824140786e-05, + "loss": 4.0157, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034088876630266e-05, + "loss": 4.0084, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6025702929119745e-05, + "loss": 4.0159, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017316981609225e-05, + "loss": 4.0099, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008931034098705e-05, + "loss": 4.0142, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600056146539192e-05, + "loss": 4.0129, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59921755178814e-05, + "loss": 4.0127, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598378957037088e-05, + "loss": 4.0161, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5975403622860354e-05, + "loss": 4.0151, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967017675349834e-05, + "loss": 4.012, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595864810664305e-05, + "loss": 4.0169, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595026215913253e-05, + "loss": 4.0239, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5941876211622e-05, + "loss": 4.0026, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593349026411148e-05, + "loss": 4.0037, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592510431660096e-05, + "loss": 4.0065, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591671836909044e-05, + "loss": 4.0028, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590833242157993e-05, + "loss": 4.0137, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589994647406941e-05, + "loss": 4.0137, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891593284166355e-05, + "loss": 4.0185, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588320733665583e-05, + "loss": 4.016, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587482138914531e-05, + "loss": 4.0156, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866451820438524e-05, + "loss": 4.0173, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858065872928004e-05, + "loss": 4.0122, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.584967992541748e-05, + "loss": 3.9889, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584129397790696e-05, + "loss": 4.0237, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583290803039644e-05, + "loss": 4.0053, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582452208288592e-05, + "loss": 4.0132, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.58161361353754e-05, + "loss": 4.0027, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807750187864884e-05, + "loss": 4.0009, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799364240354364e-05, + "loss": 4.0088, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790978292843844e-05, + "loss": 4.0025, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5782592345333323e-05, + "loss": 4.0113, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577422277662653e-05, + "loss": 3.996, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576583682911601e-05, + "loss": 4.0224, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575745088160549e-05, + "loss": 4.0088, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574906493409497e-05, + "loss": 3.9846, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574067898658445e-05, + "loss": 4.021, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573229303907393e-05, + "loss": 3.9973, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572390709156341e-05, + "loss": 3.9976, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5715521144052885e-05, + "loss": 4.0103, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57071515753461e-05, + "loss": 4.017, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569876562783558e-05, + "loss": 3.9987, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569037968032506e-05, + "loss": 4.0047, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568199373281454e-05, + "loss": 3.9884, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567360778530402e-05, + "loss": 4.0011, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566523821659724e-05, + "loss": 4.0208, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565685226908672e-05, + "loss": 4.0101, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564846632157619e-05, + "loss": 4.012, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640096752869406e-05, + "loss": 4.0114, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631710805358886e-05, + "loss": 4.0213, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562332485784836e-05, + "loss": 4.0081, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561493891033784e-05, + "loss": 4.0142, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560655296282732e-05, + "loss": 3.9991, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.55981670153168e-05, + "loss": 4.0059, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589781067806286e-05, + "loss": 4.0025, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581411499099495e-05, + "loss": 4.0077, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573025551588975e-05, + "loss": 4.0108, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5564639604078455e-05, + "loss": 4.016, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5556253656567935e-05, + "loss": 4.0106, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547867709057415e-05, + "loss": 3.998, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5539481761546895e-05, + "loss": 4.0083, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531095814036375e-05, + "loss": 4.0108, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522726245329584e-05, + "loss": 3.9959, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5514340297819064e-05, + "loss": 4.0053, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505954350308544e-05, + "loss": 4.0132, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5497568402798024e-05, + "loss": 4.0034, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548919883409124e-05, + "loss": 4.0097, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548081288658072e-05, + "loss": 3.9949, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.54724269390702e-05, + "loss": 4.0135, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546404099155968e-05, + "loss": 4.0109, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545567142285289e-05, + "loss": 4.0108, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544728547534237e-05, + "loss": 3.9926, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543889952783185e-05, + "loss": 4.0054, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543051358032133e-05, + "loss": 3.9954, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542214401161454e-05, + "loss": 4.012, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541375806410402e-05, + "loss": 4.0185, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.54053721165935e-05, + "loss": 3.9971, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539698616908298e-05, + "loss": 4.0066, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538860022157246e-05, + "loss": 3.9972, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538021427406194e-05, + "loss": 3.9941, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371828326551424e-05, + "loss": 3.9976, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5363442379040904e-05, + "loss": 3.9959, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535505643153038e-05, + "loss": 4.0008, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534668686282359e-05, + "loss": 4.0005, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533830091531307e-05, + "loss": 3.999, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532991496780255e-05, + "loss": 3.9944, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5321529020292026e-05, + "loss": 3.9992, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531315945158524e-05, + "loss": 4.0145, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530478988287845e-05, + "loss": 3.9972, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529642031417166e-05, + "loss": 4.0115, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528803436666115e-05, + "loss": 4.0108, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527964841915063e-05, + "loss": 4.0166, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527126247164011e-05, + "loss": 4.0, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526287652412959e-05, + "loss": 3.9982, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254490576619067e-05, + "loss": 4.0032, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5246104629108547e-05, + "loss": 4.0092, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237718681598027e-05, + "loss": 4.0103, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.52293327340875e-05, + "loss": 4.0009, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522094678657698e-05, + "loss": 4.0013, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5212577217870196e-05, + "loss": 4.0151, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520419127035967e-05, + "loss": 4.0054, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519580532284915e-05, + "loss": 3.992, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518741937533863e-05, + "loss": 4.0033, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517903342782811e-05, + "loss": 3.9945, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170647480317595e-05, + "loss": 4.0192, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162277911610804e-05, + "loss": 3.9995, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153891964100284e-05, + "loss": 4.0098, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145506016589764e-05, + "loss": 3.9901, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137120069079244e-05, + "loss": 4.0092, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128734121568724e-05, + "loss": 4.0061, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120348174058204e-05, + "loss": 4.0043, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111962226547684e-05, + "loss": 4.0078, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103576279037164e-05, + "loss": 3.9991, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509520671033037e-05, + "loss": 4.0094, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508682076281985e-05, + "loss": 4.0225, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507843481530933e-05, + "loss": 3.9905, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507004886779881e-05, + "loss": 4.0023, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506167929909203e-05, + "loss": 4.004, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505329335158151e-05, + "loss": 3.9974, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504490740407099e-05, + "loss": 3.9997, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503652145656047e-05, + "loss": 4.0069, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502813550904995e-05, + "loss": 4.0, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501974956153943e-05, + "loss": 4.0006, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501137999283264e-05, + "loss": 4.0083, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.04392671585083, + "eval_runtime": 305.8145, + "eval_samples_per_second": 1247.786, + "eval_steps_per_second": 38.994, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500299404532212e-05, + "loss": 3.9899, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.49946080978116e-05, + "loss": 3.9918, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498622215030108e-05, + "loss": 4.0036, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497783620279056e-05, + "loss": 4.0001, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496945025528003e-05, + "loss": 4.0013, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496106430776952e-05, + "loss": 3.9937, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952678360259e-05, + "loss": 4.0076, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494429241274848e-05, + "loss": 3.9919, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493590646523796e-05, + "loss": 4.0009, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492752051772744e-05, + "loss": 3.9949, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491913457021692e-05, + "loss": 4.0007, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49107486227064e-05, + "loss": 4.0101, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902379053999606e-05, + "loss": 4.01, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893993106489086e-05, + "loss": 3.9886, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885607158978566e-05, + "loss": 4.0014, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877221211468046e-05, + "loss": 3.986, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868835263957526e-05, + "loss": 3.9964, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860449316447006e-05, + "loss": 3.9975, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852063368936486e-05, + "loss": 3.9891, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843677421425966e-05, + "loss": 4.0002, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4835291473915446e-05, + "loss": 4.0065, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4826905526404926e-05, + "loss": 4.0029, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4818519578894406e-05, + "loss": 4.0089, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810133631383886e-05, + "loss": 4.0089, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48017640626771e-05, + "loss": 3.9911, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793378115166575e-05, + "loss": 4.0019, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4784992167656055e-05, + "loss": 3.9923, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477662259894927e-05, + "loss": 3.9976, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4768236651438744e-05, + "loss": 3.9927, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4759850703928224e-05, + "loss": 3.9947, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4751464756417704e-05, + "loss": 4.0005, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743078808907184e-05, + "loss": 3.9954, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.47347092402004e-05, + "loss": 3.9965, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472632329268988e-05, + "loss": 4.0028, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471793734517936e-05, + "loss": 3.9952, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709567776472575e-05, + "loss": 3.9983, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470118182896205e-05, + "loss": 4.0065, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469279588145153e-05, + "loss": 3.9831, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468440993394101e-05, + "loss": 3.9934, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467602398643049e-05, + "loss": 3.991, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466763803891997e-05, + "loss": 3.9839, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465925209140945e-05, + "loss": 3.9962, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465086614389893e-05, + "loss": 3.996, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464248019638841e-05, + "loss": 4.0, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463409424887789e-05, + "loss": 3.9991, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462570830136737e-05, + "loss": 3.9991, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617338732660584e-05, + "loss": 4.0024, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608952785150064e-05, + "loss": 3.9958, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600566837639544e-05, + "loss": 3.976, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592180890129024e-05, + "loss": 4.0018, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583794942618504e-05, + "loss": 3.9905, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457542537391171e-05, + "loss": 3.9952, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456703942640119e-05, + "loss": 3.9887, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455865347889067e-05, + "loss": 3.9822, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455026753138015e-05, + "loss": 3.9925, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454189796267336e-05, + "loss": 3.9832, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453351201516284e-05, + "loss": 3.9953, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452512606765232e-05, + "loss": 3.9763, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.45167401201418e-05, + "loss": 4.006, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450835417263129e-05, + "loss": 3.9925, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.44999846039245e-05, + "loss": 3.9708, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449159865641398e-05, + "loss": 4.0024, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448321270890346e-05, + "loss": 3.9794, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447482676139293e-05, + "loss": 3.9854, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446644081388241e-05, + "loss": 3.9891, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458071245175627e-05, + "loss": 4.0018, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449685297665107e-05, + "loss": 3.985, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444129935015458e-05, + "loss": 3.9871, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443291340264406e-05, + "loss": 3.9693, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442452745513354e-05, + "loss": 3.9909, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416141507623026e-05, + "loss": 4.0008, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4407771938916235e-05, + "loss": 3.9963, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4399385991405715e-05, + "loss": 3.9921, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4391000043895195e-05, + "loss": 3.9959, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382614096384675e-05, + "loss": 4.0067, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374244527677884e-05, + "loss": 3.9886, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.43658749589711e-05, + "loss": 3.9949, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435748901146058e-05, + "loss": 3.986, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349103063950053e-05, + "loss": 3.9923, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340717116439533e-05, + "loss": 3.9852, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433233116892901e-05, + "loss": 3.9885, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432394522141849e-05, + "loss": 3.9989, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431555927390798e-05, + "loss": 3.997, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430717332639746e-05, + "loss": 4.0003, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429880375769067e-05, + "loss": 3.9787, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429041781018015e-05, + "loss": 3.994, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428203186266963e-05, + "loss": 3.9943, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427364591515911e-05, + "loss": 3.982, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265292725256054e-05, + "loss": 3.9843, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425690677774553e-05, + "loss": 3.9956, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424852083023501e-05, + "loss": 3.9913, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424013488272449e-05, + "loss": 3.9888, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423174893521397e-05, + "loss": 3.9839, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422336298770345e-05, + "loss": 3.9946, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4214977040192934e-05, + "loss": 3.9988, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4206591092682414e-05, + "loss": 3.9917, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419822152397562e-05, + "loss": 3.9785, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.41898355764651e-05, + "loss": 3.9893, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418144962895458e-05, + "loss": 3.9814, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417306368144406e-05, + "loss": 3.9934, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416469411273727e-05, + "loss": 4.0024, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415630816522675e-05, + "loss": 3.9829, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414792221771623e-05, + "loss": 3.9878, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413953627020571e-05, + "loss": 3.9845, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413116670149892e-05, + "loss": 3.9801, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41227807539884e-05, + "loss": 3.976, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411439480647789e-05, + "loss": 3.9837, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106025237771096e-05, + "loss": 3.9831, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4097639290260576e-05, + "loss": 3.9851, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4089253342750056e-05, + "loss": 3.981, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4080867395239536e-05, + "loss": 3.9791, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4072481447729016e-05, + "loss": 3.9818, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064095500218496e-05, + "loss": 3.9994, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4055709552707976e-05, + "loss": 3.9826, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4047323605197456e-05, + "loss": 3.9976, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4038954036490665e-05, + "loss": 3.9926, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4030584467783874e-05, + "loss": 4.0016, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022198520273354e-05, + "loss": 3.9887, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013812572762834e-05, + "loss": 3.9813, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400542662525232e-05, + "loss": 3.9884, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39970406777418e-05, + "loss": 3.9909, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398865473023128e-05, + "loss": 3.9889, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398026878272076e-05, + "loss": 3.9897, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397189921401397e-05, + "loss": 3.9839, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396351326650345e-05, + "loss": 3.9991, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395512731899293e-05, + "loss": 3.9848, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394674137148241e-05, + "loss": 3.9792, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393837180277562e-05, + "loss": 3.9862, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39299858552651e-05, + "loss": 3.981, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392159990775458e-05, + "loss": 3.9999, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391321396024406e-05, + "loss": 3.983, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390482801273354e-05, + "loss": 3.9931, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389644206522302e-05, + "loss": 3.9792, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888072496516235e-05, + "loss": 3.9921, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879686549005715e-05, + "loss": 3.9921, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387130060149519e-05, + "loss": 3.9892, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386291465398467e-05, + "loss": 3.985, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385452870647415e-05, + "loss": 3.9907, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384614275896363e-05, + "loss": 3.9948, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383775681145311e-05, + "loss": 4.0041, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382937086394259e-05, + "loss": 3.9775, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3821001295235797e-05, + "loss": 3.9844, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812615347725277e-05, + "loss": 3.9881, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380424577901849e-05, + "loss": 3.9828, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379585983150797e-05, + "loss": 3.983, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378747388399745e-05, + "loss": 3.9933, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377908793648693e-05, + "loss": 3.9815, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377071836778014e-05, + "loss": 3.9927, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376233242026962e-05, + "loss": 3.9855, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.03481912612915, + "eval_runtime": 316.2016, + "eval_samples_per_second": 1206.796, + "eval_steps_per_second": 37.713, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.37539464727591e-05, + "loss": 3.9868, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374556052524858e-05, + "loss": 3.9729, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373717457773806e-05, + "loss": 3.9885, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372880500903127e-05, + "loss": 3.9864, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372041906152075e-05, + "loss": 3.9852, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371203311401023e-05, + "loss": 3.9834, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370364716649971e-05, + "loss": 3.9864, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.36952612189892e-05, + "loss": 3.9815, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368687527147868e-05, + "loss": 3.981, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367848932396816e-05, + "loss": 3.9857, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367010337645764e-05, + "loss": 3.9828, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366171742894712e-05, + "loss": 3.9925, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3653364239044055e-05, + "loss": 3.9998, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3644978291533535e-05, + "loss": 3.975, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3636592344023015e-05, + "loss": 3.9803, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3628206396512495e-05, + "loss": 3.9758, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3619820449001975e-05, + "loss": 3.981, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3611434501491455e-05, + "loss": 3.9832, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603048553980935e-05, + "loss": 3.9726, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3594662606470415e-05, + "loss": 3.98, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358629303776363e-05, + "loss": 3.9972, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357792346905684e-05, + "loss": 3.9847, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356953752154632e-05, + "loss": 3.9927, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.35611515740358e-05, + "loss": 3.994, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355276562652528e-05, + "loss": 3.9804, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354439605781849e-05, + "loss": 3.9888, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353601011030797e-05, + "loss": 3.9743, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352762416279745e-05, + "loss": 3.9829, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351923821528693e-05, + "loss": 3.9803, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351085226777641e-05, + "loss": 3.9769, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350248269906962e-05, + "loss": 3.9874, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494096751559104e-05, + "loss": 3.9794, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485710804048584e-05, + "loss": 3.9865, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477324856538064e-05, + "loss": 3.9817, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468938909027544e-05, + "loss": 3.9812, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346056934032075e-05, + "loss": 3.9888, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345218339281023e-05, + "loss": 3.9925, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344379744529971e-05, + "loss": 3.9632, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343541149778919e-05, + "loss": 3.981, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342702555027867e-05, + "loss": 3.9779, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3418639602768146e-05, + "loss": 3.968, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3410253655257626e-05, + "loss": 3.9803, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3401867707747106e-05, + "loss": 3.9879, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339349813904032e-05, + "loss": 3.9841, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.33851121915298e-05, + "loss": 3.9853, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337672624401928e-05, + "loss": 3.9847, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336834029650876e-05, + "loss": 3.9847, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335997072780197e-05, + "loss": 3.9805, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335158478029145e-05, + "loss": 3.9622, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334319883278093e-05, + "loss": 3.9855, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333481288527041e-05, + "loss": 3.9781, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332642693775989e-05, + "loss": 3.9819, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.33180573690531e-05, + "loss": 3.9718, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330967142154258e-05, + "loss": 3.9703, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330128547403206e-05, + "loss": 3.9754, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329289952652154e-05, + "loss": 3.9673, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328451357901102e-05, + "loss": 3.9857, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3276144010304236e-05, + "loss": 3.9663, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3267758062793716e-05, + "loss": 3.9861, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3259372115283195e-05, + "loss": 3.9812, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3250986167772675e-05, + "loss": 3.9599, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3242600220262155e-05, + "loss": 3.9836, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234230651555364e-05, + "loss": 3.9675, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225844704044844e-05, + "loss": 3.9713, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217458756534324e-05, + "loss": 3.9708, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3209072809023804e-05, + "loss": 3.9887, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3200686861513284e-05, + "loss": 3.9723, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3192300914002764e-05, + "loss": 3.9716, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3183914966492244e-05, + "loss": 3.954, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3175529018981724e-05, + "loss": 3.9704, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3167143071471204e-05, + "loss": 3.9882, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315877350276442e-05, + "loss": 3.9855, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.31503875552539e-05, + "loss": 3.9743, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314200160774338e-05, + "loss": 3.984, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313361566023286e-05, + "loss": 3.9908, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.31252624703298e-05, + "loss": 3.9726, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311687652281928e-05, + "loss": 3.9778, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310849057530876e-05, + "loss": 3.9761, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310010462779824e-05, + "loss": 3.9746, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309173505909145e-05, + "loss": 3.9684, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308334911158093e-05, + "loss": 3.9749, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074963164070414e-05, + "loss": 3.9838, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066577216559894e-05, + "loss": 3.9835, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058191269049374e-05, + "loss": 3.9842, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049805321538854e-05, + "loss": 3.9634, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041419374028334e-05, + "loss": 3.9799, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303303342651781e-05, + "loss": 3.9783, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302464747900729e-05, + "loss": 3.9712, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.30162779103005e-05, + "loss": 3.9721, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300790834159371e-05, + "loss": 3.98, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299952239408319e-05, + "loss": 3.9739, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299113644657267e-05, + "loss": 3.978, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298275049906215e-05, + "loss": 3.9701, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297436455155163e-05, + "loss": 3.983, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296599498284485e-05, + "loss": 3.9822, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295760903533433e-05, + "loss": 3.9795, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294922308782381e-05, + "loss": 3.9615, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294083714031328e-05, + "loss": 3.9758, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293245119280276e-05, + "loss": 3.9696, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292406524529224e-05, + "loss": 3.9763, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291567929778172e-05, + "loss": 3.9898, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290730972907493e-05, + "loss": 3.9675, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289892378156441e-05, + "loss": 3.9735, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289053783405389e-05, + "loss": 3.967, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288215188654337e-05, + "loss": 3.9735, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287376593903285e-05, + "loss": 3.9616, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.28654127491298e-05, + "loss": 3.968, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285702680161928e-05, + "loss": 3.9705, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2848640854108754e-05, + "loss": 3.9728, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2840254906598234e-05, + "loss": 3.9662, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2831868959087714e-05, + "loss": 3.9667, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823483011577194e-05, + "loss": 3.9654, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2815097064066674e-05, + "loss": 3.9834, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806711116556154e-05, + "loss": 3.9695, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279834154784936e-05, + "loss": 3.9799, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278995560033884e-05, + "loss": 3.9805, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278156965282832e-05, + "loss": 3.9898, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27731837053178e-05, + "loss": 3.9722, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276479775780728e-05, + "loss": 3.9694, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275641181029677e-05, + "loss": 3.9744, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274802586278625e-05, + "loss": 3.976, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273963991527573e-05, + "loss": 3.9743, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273127034656894e-05, + "loss": 3.9778, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272290077786215e-05, + "loss": 3.9694, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271451483035163e-05, + "loss": 3.982, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270614526164484e-05, + "loss": 3.974, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269775931413432e-05, + "loss": 3.9679, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.26893733666238e-05, + "loss": 3.971, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268098741911328e-05, + "loss": 3.9695, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672601471602757e-05, + "loss": 3.9808, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664215524092237e-05, + "loss": 3.9751, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265582957658172e-05, + "loss": 3.9772, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26474436290712e-05, + "loss": 3.9697, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263905768156068e-05, + "loss": 3.9757, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263067173405016e-05, + "loss": 3.9802, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2622285786539636e-05, + "loss": 3.9743, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2613899839029116e-05, + "loss": 3.9734, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260553027032233e-05, + "loss": 3.9745, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259714432281181e-05, + "loss": 3.9785, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588758375301285e-05, + "loss": 3.9911, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.25803888065945e-05, + "loss": 3.9684, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257200285908398e-05, + "loss": 3.9671, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256361691157346e-05, + "loss": 3.9711, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255523096406294e-05, + "loss": 3.9722, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254686139535616e-05, + "loss": 3.9654, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253847544784564e-05, + "loss": 3.98, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253008950033511e-05, + "loss": 3.9705, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252170355282459e-05, + "loss": 3.9796, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251331760531407e-05, + "loss": 3.9686, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.026948928833008, + "eval_runtime": 316.4767, + "eval_samples_per_second": 1205.747, + "eval_steps_per_second": 37.68, + "step": 1068480 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 4.4451422658283923e+17, + "trial_name": null, + "trial_params": null +}