{
  "best_metric": 0.15171197056770325,
  "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold9/checkpoint-100",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 3.164632558822632,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9306,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 3.5490176677703857,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.9539,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 3.2523374557495117,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.0283,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 2.921321153640747,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.9386,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.969313621520996,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0028,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.673182725906372,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.9471,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.804046869277954,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8592,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.966957449913025,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.5573,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.7136402130126953,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.6202,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.2622791528701782,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5414,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.4767262637615204,
      "eval_runtime": 20.1773,
      "eval_samples_per_second": 2.23,
      "eval_steps_per_second": 2.23,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.4296376705169678,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4666,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.2342653274536133,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4349,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.1100136041641235,
      "learning_rate": 0.0001,
      "loss": 0.3994,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.9704046845436096,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3595,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.0280709266662598,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2996,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.9458633661270142,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2754,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.9331815242767334,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3655,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.8337064981460571,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.256,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.838422417640686,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.3121,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 1.0396910905838013,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2625,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.2796812951564789,
      "eval_runtime": 20.0635,
      "eval_samples_per_second": 2.243,
      "eval_steps_per_second": 2.243,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.9817348718643188,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.326,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.7887865304946899,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2324,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.6901564598083496,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2246,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.8042709827423096,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.279,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.6765527725219727,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.183,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.4221432209014893,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3358,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.6143414974212646,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1872,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.740685224533081,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1799,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5720812678337097,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1728,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.9697518348693848,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2122,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.21663405001163483,
      "eval_runtime": 20.0507,
      "eval_samples_per_second": 2.244,
      "eval_steps_per_second": 2.244,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.766406238079071,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1908,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.8469014167785645,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2085,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.6874857544898987,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1455,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.800626277923584,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.222,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.6434504389762878,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1692,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.6304237842559814,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1483,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.691754937171936,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1739,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.7274345755577087,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1723,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.557968258857727,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1434,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.7214641571044922,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1414,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.18512263894081116,
      "eval_runtime": 20.102,
      "eval_samples_per_second": 2.239,
      "eval_steps_per_second": 2.239,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.7218368649482727,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1526,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.5913806557655334,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.135,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.7210223078727722,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.2156,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.9081677794456482,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1705,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.7074072957038879,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1314,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6262356042861938,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1138,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.8130413889884949,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1455,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.8630567789077759,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1607,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.48933014273643494,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1171,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.8019640445709229,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1575,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.174514040350914,
      "eval_runtime": 20.0599,
      "eval_samples_per_second": 2.243,
      "eval_steps_per_second": 2.243,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.3741053342819214,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2711,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.5855741500854492,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1321,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.7712327241897583,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.139,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.5616917014122009,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0961,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.4694013297557831,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0857,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.6574388742446899,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1145,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.5970843434333801,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1041,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.6216567754745483,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1094,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.5913412570953369,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1132,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.6296737194061279,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1175,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.1684415638446808,
      "eval_runtime": 20.0629,
      "eval_samples_per_second": 2.243,
      "eval_steps_per_second": 2.243,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.6460537910461426,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0963,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6800506711006165,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.112,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.7320341467857361,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1131,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.8068739175796509,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1886,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.7426419854164124,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.114,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.9800764322280884,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1466,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.5939916372299194,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1142,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.5675904750823975,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.111,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6916811466217041,
      "learning_rate": 5e-05,
      "loss": 0.1029,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.6540643572807312,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1083,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.15919220447540283,
      "eval_runtime": 20.0917,
      "eval_samples_per_second": 2.24,
      "eval_steps_per_second": 2.24,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.6630744338035583,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.6264397501945496,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.107,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.8252314925193787,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1177,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5916221737861633,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0805,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.6091346144676208,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1117,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.1812632083892822,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1299,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.4243829846382141,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0539,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.6078281402587891,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0839,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.551660418510437,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0879,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.671269953250885,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0848,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.16666051745414734,
      "eval_runtime": 20.0676,
      "eval_samples_per_second": 2.242,
      "eval_steps_per_second": 2.242,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.8196060657501221,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1082,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.4849521815776825,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0454,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.5302721858024597,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0872,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.584001898765564,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0816,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5196976661682129,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0623,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5309479236602783,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0651,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.7327566742897034,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0958,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.581312894821167,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0743,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.6637649536132812,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0514,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.45748892426490784,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0528,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.15304026007652283,
      "eval_runtime": 20.0941,
      "eval_samples_per_second": 2.239,
      "eval_steps_per_second": 2.239,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.8669251203536987,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1338,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.8855804800987244,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0931,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.6329140663146973,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0746,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.6610190868377686,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0963,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.8602515459060669,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.09,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.3644033670425415,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0393,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.5531057119369507,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0771,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.8466161489486694,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0839,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.820703387260437,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1057,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.7727490067481995,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0859,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.15171197056770325,
      "eval_runtime": 20.0575,
      "eval_samples_per_second": 2.244,
      "eval_steps_per_second": 2.244,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 1.0898189544677734,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1256,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.9092823266983032,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1089,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.6199166774749756,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0453,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.5870338082313538,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0562,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.6727953553199768,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0581,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.49598875641822815,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.044,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.6405553221702576,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0673,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.6487284302711487,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0863,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.682708740234375,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0739,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.4283440113067627,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0417,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.15383554995059967,
      "eval_runtime": 20.0872,
      "eval_samples_per_second": 2.24,
      "eval_steps_per_second": 2.24,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.8055588006973267,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0776,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.7525231242179871,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0834,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.47448545694351196,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0515,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.5870132446289062,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0788,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.5103846192359924,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0548,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5356786251068115,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0582,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.6629040241241455,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0631,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.5497284531593323,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0654,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.6678840517997742,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0904,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4796382188796997,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0552,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.15243226289749146,
      "eval_runtime": 20.1158,
      "eval_samples_per_second": 2.237,
      "eval_steps_per_second": 2.237,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.7403225302696228,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0826,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.9023314118385315,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0612,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.534042239189148,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0532,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.5294525027275085,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0755,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.5494197607040405,
      "learning_rate": 0.0,
      "loss": 0.0628,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.2642241251999744e+17,
      "train_loss": 0.1930472597181797,
      "train_runtime": 3444.4411,
      "train_samples_per_second": 0.588,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2642241251999744e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}