{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1092896174863388,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001092896174863388,
      "grad_norm": 1.52214777469635,
      "learning_rate": 1e-05,
      "loss": 5.7187,
      "step": 1
    },
    {
      "epoch": 0.001092896174863388,
      "eval_loss": 5.797797203063965,
      "eval_runtime": 55.6063,
      "eval_samples_per_second": 55.407,
      "eval_steps_per_second": 1.744,
      "step": 1
    },
    {
      "epoch": 0.002185792349726776,
      "grad_norm": 1.465293049812317,
      "learning_rate": 2e-05,
      "loss": 5.7381,
      "step": 2
    },
    {
      "epoch": 0.003278688524590164,
      "grad_norm": 1.5233027935028076,
      "learning_rate": 3e-05,
      "loss": 5.7964,
      "step": 3
    },
    {
      "epoch": 0.004371584699453552,
      "grad_norm": 1.3974599838256836,
      "learning_rate": 4e-05,
      "loss": 5.7245,
      "step": 4
    },
    {
      "epoch": 0.00546448087431694,
      "grad_norm": 1.4633687734603882,
      "learning_rate": 5e-05,
      "loss": 5.683,
      "step": 5
    },
    {
      "epoch": 0.006557377049180328,
      "grad_norm": 1.150214672088623,
      "learning_rate": 6e-05,
      "loss": 5.6083,
      "step": 6
    },
    {
      "epoch": 0.007650273224043716,
      "grad_norm": 0.8514282703399658,
      "learning_rate": 7e-05,
      "loss": 5.4842,
      "step": 7
    },
    {
      "epoch": 0.008743169398907104,
      "grad_norm": 0.7441701292991638,
      "learning_rate": 8e-05,
      "loss": 5.5433,
      "step": 8
    },
    {
      "epoch": 0.009836065573770493,
      "grad_norm": 0.8355361819267273,
      "learning_rate": 9e-05,
      "loss": 5.4061,
      "step": 9
    },
    {
      "epoch": 0.009836065573770493,
      "eval_loss": 5.372408390045166,
      "eval_runtime": 55.7059,
      "eval_samples_per_second": 55.308,
      "eval_steps_per_second": 1.741,
      "step": 9
    },
    {
      "epoch": 0.01092896174863388,
      "grad_norm": 0.7220072746276855,
      "learning_rate": 0.0001,
      "loss": 5.2304,
      "step": 10
    },
    {
      "epoch": 0.012021857923497269,
      "grad_norm": 0.9673782587051392,
      "learning_rate": 9.99695413509548e-05,
      "loss": 5.28,
      "step": 11
    },
    {
      "epoch": 0.013114754098360656,
      "grad_norm": 0.8410780429840088,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.3055,
      "step": 12
    },
    {
      "epoch": 0.014207650273224045,
      "grad_norm": 1.2083158493041992,
      "learning_rate": 9.972609476841367e-05,
      "loss": 5.2112,
      "step": 13
    },
    {
      "epoch": 0.015300546448087432,
      "grad_norm": 0.7996488213539124,
      "learning_rate": 9.951340343707852e-05,
      "loss": 5.2837,
      "step": 14
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 0.7078868746757507,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.1988,
      "step": 15
    },
    {
      "epoch": 0.017486338797814208,
      "grad_norm": 1.7895820140838623,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.1302,
      "step": 16
    },
    {
      "epoch": 0.018579234972677595,
      "grad_norm": 1.1687918901443481,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.2009,
      "step": 17
    },
    {
      "epoch": 0.019672131147540985,
      "grad_norm": 0.8420019149780273,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.2331,
      "step": 18
    },
    {
      "epoch": 0.019672131147540985,
      "eval_loss": 5.167764186859131,
      "eval_runtime": 55.7371,
      "eval_samples_per_second": 55.277,
      "eval_steps_per_second": 1.74,
      "step": 18
    },
    {
      "epoch": 0.020765027322404372,
      "grad_norm": 1.4209792613983154,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.1434,
      "step": 19
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 0.8728744387626648,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.1567,
      "step": 20
    },
    {
      "epoch": 0.022950819672131147,
      "grad_norm": 1.877350926399231,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.1842,
      "step": 21
    },
    {
      "epoch": 0.024043715846994537,
      "grad_norm": 0.6153156757354736,
      "learning_rate": 9.567727288213005e-05,
      "loss": 5.172,
      "step": 22
    },
    {
      "epoch": 0.025136612021857924,
      "grad_norm": 0.973233163356781,
      "learning_rate": 9.493970231495835e-05,
      "loss": 5.1466,
      "step": 23
    },
    {
      "epoch": 0.02622950819672131,
      "grad_norm": 0.9793280363082886,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.1597,
      "step": 24
    },
    {
      "epoch": 0.0273224043715847,
      "grad_norm": 0.954116940498352,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.0359,
      "step": 25
    },
    {
      "epoch": 0.02841530054644809,
      "grad_norm": 0.7521523237228394,
      "learning_rate": 9.24024048078213e-05,
      "loss": 5.1146,
      "step": 26
    },
    {
      "epoch": 0.029508196721311476,
      "grad_norm": 0.5011205673217773,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.0219,
      "step": 27
    },
    {
      "epoch": 0.029508196721311476,
      "eval_loss": 5.060585975646973,
      "eval_runtime": 55.7106,
      "eval_samples_per_second": 55.304,
      "eval_steps_per_second": 1.741,
      "step": 27
    },
    {
      "epoch": 0.030601092896174863,
      "grad_norm": 0.7214334011077881,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.9877,
      "step": 28
    },
    {
      "epoch": 0.03169398907103825,
      "grad_norm": 2.0999269485473633,
      "learning_rate": 8.940053768033609e-05,
      "loss": 5.0469,
      "step": 29
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 0.9483531713485718,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.9721,
      "step": 30
    },
    {
      "epoch": 0.033879781420765025,
      "grad_norm": 0.9655952453613281,
      "learning_rate": 8.715724127386972e-05,
      "loss": 5.1057,
      "step": 31
    },
    {
      "epoch": 0.034972677595628415,
      "grad_norm": 0.6362683176994324,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.9924,
      "step": 32
    },
    {
      "epoch": 0.036065573770491806,
      "grad_norm": 0.835968554019928,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.9999,
      "step": 33
    },
    {
      "epoch": 0.03715846994535519,
      "grad_norm": 2.468137741088867,
      "learning_rate": 8.345653031794292e-05,
      "loss": 5.0356,
      "step": 34
    },
    {
      "epoch": 0.03825136612021858,
      "grad_norm": 1.0865174531936646,
      "learning_rate": 8.213938048432697e-05,
      "loss": 4.9696,
      "step": 35
    },
    {
      "epoch": 0.03934426229508197,
      "grad_norm": 1.0075640678405762,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.9541,
      "step": 36
    },
    {
      "epoch": 0.03934426229508197,
      "eval_loss": 4.962901592254639,
      "eval_runtime": 55.6825,
      "eval_samples_per_second": 55.332,
      "eval_steps_per_second": 1.742,
      "step": 36
    },
    {
      "epoch": 0.040437158469945354,
      "grad_norm": 1.3719457387924194,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.9748,
      "step": 37
    },
    {
      "epoch": 0.041530054644808745,
      "grad_norm": 1.7131140232086182,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.9173,
      "step": 38
    },
    {
      "epoch": 0.04262295081967213,
      "grad_norm": 0.6441985964775085,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.9594,
      "step": 39
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 2.106320381164551,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.8943,
      "step": 40
    },
    {
      "epoch": 0.04480874316939891,
      "grad_norm": 3.2894480228424072,
      "learning_rate": 7.347357813929454e-05,
      "loss": 4.9183,
      "step": 41
    },
    {
      "epoch": 0.04590163934426229,
      "grad_norm": 1.4625245332717896,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.8716,
      "step": 42
    },
    {
      "epoch": 0.046994535519125684,
      "grad_norm": 4.140956878662109,
      "learning_rate": 7.033683215379002e-05,
      "loss": 4.9576,
      "step": 43
    },
    {
      "epoch": 0.048087431693989074,
      "grad_norm": 4.324865341186523,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.9355,
      "step": 44
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 1.2742332220077515,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.9136,
      "step": 45
    },
    {
      "epoch": 0.04918032786885246,
      "eval_loss": 4.958442211151123,
      "eval_runtime": 55.6763,
      "eval_samples_per_second": 55.338,
      "eval_steps_per_second": 1.742,
      "step": 45
    },
    {
      "epoch": 0.05027322404371585,
      "grad_norm": 2.4827942848205566,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.9411,
      "step": 46
    },
    {
      "epoch": 0.05136612021857923,
      "grad_norm": 2.5973329544067383,
      "learning_rate": 6.378186779084995e-05,
      "loss": 4.9952,
      "step": 47
    },
    {
      "epoch": 0.05245901639344262,
      "grad_norm": 0.8299262523651123,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.9138,
      "step": 48
    },
    {
      "epoch": 0.053551912568306013,
      "grad_norm": 4.389142990112305,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 4.9635,
      "step": 49
    },
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 5.450596809387207,
      "learning_rate": 5.868240888334653e-05,
      "loss": 5.0935,
      "step": 50
    },
    {
      "epoch": 0.05573770491803279,
      "grad_norm": 2.6530776023864746,
      "learning_rate": 5.695865504800327e-05,
      "loss": 4.9609,
      "step": 51
    },
    {
      "epoch": 0.05683060109289618,
      "grad_norm": 1.504117727279663,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.8891,
      "step": 52
    },
    {
      "epoch": 0.05792349726775956,
      "grad_norm": 1.8544734716415405,
      "learning_rate": 5.348782368720626e-05,
      "loss": 4.9346,
      "step": 53
    },
    {
      "epoch": 0.05901639344262295,
      "grad_norm": 1.908761739730835,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.9979,
      "step": 54
    },
    {
      "epoch": 0.05901639344262295,
      "eval_loss": 4.928157329559326,
      "eval_runtime": 55.6535,
      "eval_samples_per_second": 55.36,
      "eval_steps_per_second": 1.743,
      "step": 54
    },
    {
      "epoch": 0.060109289617486336,
      "grad_norm": 0.9097221493721008,
      "learning_rate": 5e-05,
      "loss": 4.9558,
      "step": 55
    },
    {
      "epoch": 0.06120218579234973,
      "grad_norm": 1.899079442024231,
      "learning_rate": 4.825502516487497e-05,
      "loss": 4.9715,
      "step": 56
    },
    {
      "epoch": 0.06229508196721312,
      "grad_norm": 1.7221193313598633,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 4.9064,
      "step": 57
    },
    {
      "epoch": 0.0633879781420765,
      "grad_norm": 0.7375671863555908,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.8998,
      "step": 58
    },
    {
      "epoch": 0.06448087431693988,
      "grad_norm": 1.5496197938919067,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 4.9465,
      "step": 59
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 1.029213309288025,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.9669,
      "step": 60
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.6538008451461792,
      "learning_rate": 3.960441545911204e-05,
      "loss": 4.8936,
      "step": 61
    },
    {
      "epoch": 0.06775956284153005,
      "grad_norm": 1.0834981203079224,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.9531,
      "step": 62
    },
    {
      "epoch": 0.06885245901639345,
      "grad_norm": 0.691550612449646,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 4.9323,
      "step": 63
    },
    {
      "epoch": 0.06885245901639345,
      "eval_loss": 4.916704177856445,
      "eval_runtime": 55.705,
      "eval_samples_per_second": 55.309,
      "eval_steps_per_second": 1.741,
      "step": 63
    },
    {
      "epoch": 0.06994535519125683,
      "grad_norm": 0.45348408818244934,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.8709,
      "step": 64
    },
    {
      "epoch": 0.07103825136612021,
      "grad_norm": 1.04542875289917,
      "learning_rate": 3.289899283371657e-05,
      "loss": 4.952,
      "step": 65
    },
    {
      "epoch": 0.07213114754098361,
      "grad_norm": 0.697375476360321,
      "learning_rate": 3.12696703292044e-05,
      "loss": 4.9087,
      "step": 66
    },
    {
      "epoch": 0.073224043715847,
      "grad_norm": 0.8204128742218018,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 4.9664,
      "step": 67
    },
    {
      "epoch": 0.07431693989071038,
      "grad_norm": 1.083094835281372,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.9942,
      "step": 68
    },
    {
      "epoch": 0.07540983606557378,
      "grad_norm": 0.5777742862701416,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 4.9119,
      "step": 69
    },
    {
      "epoch": 0.07650273224043716,
      "grad_norm": 0.9902992248535156,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.8564,
      "step": 70
    },
    {
      "epoch": 0.07759562841530054,
      "grad_norm": 0.69707190990448,
      "learning_rate": 2.350403678833976e-05,
      "loss": 4.8472,
      "step": 71
    },
    {
      "epoch": 0.07868852459016394,
      "grad_norm": 0.5401630997657776,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 4.946,
      "step": 72
    },
    {
      "epoch": 0.07868852459016394,
      "eval_loss": 4.9106550216674805,
      "eval_runtime": 55.7387,
      "eval_samples_per_second": 55.276,
      "eval_steps_per_second": 1.74,
      "step": 72
    },
    {
      "epoch": 0.07978142076502732,
      "grad_norm": 0.41800597310066223,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.9306,
      "step": 73
    },
    {
      "epoch": 0.08087431693989071,
      "grad_norm": 0.9597459435462952,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 4.9114,
      "step": 74
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 0.4304816722869873,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 4.8847,
      "step": 75
    },
    {
      "epoch": 0.08306010928961749,
      "grad_norm": 0.7232154011726379,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 4.9066,
      "step": 76
    },
    {
      "epoch": 0.08415300546448087,
      "grad_norm": 0.6170682907104492,
      "learning_rate": 1.526708147705013e-05,
      "loss": 4.923,
      "step": 77
    },
    {
      "epoch": 0.08524590163934426,
      "grad_norm": 0.49551859498023987,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 4.9564,
      "step": 78
    },
    {
      "epoch": 0.08633879781420765,
      "grad_norm": 0.46370407938957214,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 4.9055,
      "step": 79
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 0.5205159783363342,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.8709,
      "step": 80
    },
    {
      "epoch": 0.08852459016393442,
      "grad_norm": 0.6012383699417114,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 4.9006,
      "step": 81
    },
    {
      "epoch": 0.08852459016393442,
      "eval_loss": 4.908712387084961,
      "eval_runtime": 55.644,
      "eval_samples_per_second": 55.37,
      "eval_steps_per_second": 1.743,
      "step": 81
    },
    {
      "epoch": 0.08961748633879782,
      "grad_norm": 0.6838329434394836,
      "learning_rate": 9.549150281252633e-06,
      "loss": 5.003,
      "step": 82
    },
    {
      "epoch": 0.0907103825136612,
      "grad_norm": 0.6821178793907166,
      "learning_rate": 8.548121372247918e-06,
      "loss": 4.9449,
      "step": 83
    },
    {
      "epoch": 0.09180327868852459,
      "grad_norm": 0.5011351108551025,
      "learning_rate": 7.597595192178702e-06,
      "loss": 4.8949,
      "step": 84
    },
    {
      "epoch": 0.09289617486338798,
      "grad_norm": 0.6648871898651123,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.8848,
      "step": 85
    },
    {
      "epoch": 0.09398907103825137,
      "grad_norm": 0.5797678828239441,
      "learning_rate": 5.852620357053651e-06,
      "loss": 4.8899,
      "step": 86
    },
    {
      "epoch": 0.09508196721311475,
      "grad_norm": 0.9921677112579346,
      "learning_rate": 5.060297685041659e-06,
      "loss": 4.984,
      "step": 87
    },
    {
      "epoch": 0.09617486338797815,
      "grad_norm": 0.5813995599746704,
      "learning_rate": 4.322727117869951e-06,
      "loss": 4.8188,
      "step": 88
    },
    {
      "epoch": 0.09726775956284153,
      "grad_norm": 0.5218381285667419,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 4.8906,
      "step": 89
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 0.8028129935264587,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.8837,
      "step": 90
    },
    {
      "epoch": 0.09836065573770492,
      "eval_loss": 4.907496929168701,
      "eval_runtime": 55.6919,
      "eval_samples_per_second": 55.322,
      "eval_steps_per_second": 1.742,
      "step": 90
    },
    {
      "epoch": 0.0994535519125683,
      "grad_norm": 0.45788004994392395,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 4.8955,
      "step": 91
    },
    {
      "epoch": 0.1005464480874317,
      "grad_norm": 0.4592156708240509,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 4.8768,
      "step": 92
    },
    {
      "epoch": 0.10163934426229508,
      "grad_norm": 0.5255284309387207,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 4.9354,
      "step": 93
    },
    {
      "epoch": 0.10273224043715846,
      "grad_norm": 0.7076261043548584,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 4.8474,
      "step": 94
    },
    {
      "epoch": 0.10382513661202186,
      "grad_norm": 0.6252774000167847,
      "learning_rate": 7.596123493895991e-07,
      "loss": 4.8941,
      "step": 95
    },
    {
      "epoch": 0.10491803278688525,
      "grad_norm": 0.45233267545700073,
      "learning_rate": 4.865965629214819e-07,
      "loss": 4.8658,
      "step": 96
    },
    {
      "epoch": 0.10601092896174863,
      "grad_norm": 0.4194464683532715,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 4.8726,
      "step": 97
    },
    {
      "epoch": 0.10710382513661203,
      "grad_norm": 0.4344501495361328,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 4.8811,
      "step": 98
    },
    {
      "epoch": 0.10819672131147541,
      "grad_norm": 0.7105288505554199,
      "learning_rate": 3.04586490452119e-08,
      "loss": 4.962,
      "step": 99
    },
    {
      "epoch": 0.10819672131147541,
      "eval_loss": 4.906777858734131,
      "eval_runtime": 55.621,
      "eval_samples_per_second": 55.393,
      "eval_steps_per_second": 1.744,
      "step": 99
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.42179667949676514,
      "learning_rate": 0.0,
      "loss": 4.9524,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.34220225606058e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}