{
  "best_metric": 0.08338318020105362,
  "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold9/checkpoint-120",
  "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": 0.2826780378818512,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.4475,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.370651513338089,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.5574,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.3204432427883148,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4707,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.6155232787132263,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.7984,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.25857576727867126,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3988,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.3235480487346649,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.4121,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.3344259262084961,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.4378,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.2913161516189575,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3659,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.3054957389831543,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3953,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.2586303651332855,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3604,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.36916977167129517,
      "eval_runtime": 30.7405,
      "eval_samples_per_second": 1.464,
      "eval_steps_per_second": 1.464,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.24952581524848938,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.3562,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.23936380445957184,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.3329,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.5967379808425903,
      "learning_rate": 0.0001,
      "loss": 1.5674,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.221438929438591,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3128,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.22267961502075195,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2781,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 1.7223466634750366,
      "learning_rate": 9.982307470588098e-05,
      "loss": 1.3694,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.18529340624809265,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2489,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.9717667102813721,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.7497,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.195225328207016,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2458,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 1.230882167816162,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.0978,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.24232548475265503,
      "eval_runtime": 30.6814,
      "eval_samples_per_second": 1.467,
      "eval_steps_per_second": 1.467,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.24475336074829102,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2418,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.24501371383666992,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2187,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.20740918815135956,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2392,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.43779733777046204,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.3195,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.18921704590320587,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2021,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.35293519496917725,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3194,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.18752332031726837,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2096,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.17827193439006805,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2094,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.19129422307014465,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2019,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.15638643503189087,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1519,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.17373767495155334,
      "eval_runtime": 30.6568,
      "eval_samples_per_second": 1.468,
      "eval_steps_per_second": 1.468,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.1718568354845047,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.175,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.1469532996416092,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1762,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.17532940208911896,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1685,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.17156614363193512,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1631,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.1629582941532135,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1459,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.4204743802547455,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.2361,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.139447882771492,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1327,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.16999711096286774,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1681,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.21967604756355286,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1998,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.1623128354549408,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1384,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.14366976916790009,
      "eval_runtime": 30.6257,
      "eval_samples_per_second": 1.469,
      "eval_steps_per_second": 1.469,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.16547121107578278,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1242,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.1796424686908722,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.119,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.18237937986850739,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1548,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.3381856679916382,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.2282,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.23263098299503326,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0974,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 1.7182976007461548,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.5229,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 1.5863111019134521,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.5414,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 1.312735676765442,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6299,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.27652668952941895,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1225,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.16268961131572723,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1076,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1253151148557663,
      "eval_runtime": 30.6409,
      "eval_samples_per_second": 1.469,
      "eval_steps_per_second": 1.469,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.2833295166492462,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2012,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.2018829882144928,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1282,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.23085522651672363,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1173,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.2957194149494171,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1238,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.17039451003074646,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.088,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2151472270488739,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1192,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.9544144868850708,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.2291,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2176048457622528,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1092,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.23733480274677277,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1396,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.2148839384317398,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1085,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.11200021207332611,
      "eval_runtime": 30.6401,
      "eval_samples_per_second": 1.469,
      "eval_steps_per_second": 1.469,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.26019155979156494,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1016,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.23437455296516418,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.103,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.27847492694854736,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0845,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.23731648921966553,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1125,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.2885424494743347,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1168,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.19283795356750488,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0977,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2518296539783478,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.148,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 1.0345851182937622,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.2995,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2350454479455948,
      "learning_rate": 5e-05,
      "loss": 0.0848,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.20267030596733093,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0884,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.10061758756637573,
      "eval_runtime": 30.6472,
      "eval_samples_per_second": 1.468,
      "eval_steps_per_second": 1.468,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.8772103190422058,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.3424,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.2521838843822479,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1399,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.5698731541633606,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.2464,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.22033175826072693,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1003,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.18919599056243896,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0794,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.6206218600273132,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1642,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.17653405666351318,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0865,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.2879301607608795,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0976,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.284013956785202,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0727,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.311202734708786,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.1071,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.0919496938586235,
      "eval_runtime": 30.6477,
      "eval_samples_per_second": 1.468,
      "eval_steps_per_second": 1.468,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2524774670600891,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1404,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.15348631143569946,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.056,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.2978706657886505,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0815,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.18923437595367432,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0691,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.22183537483215332,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0884,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.197841078042984,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0836,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.21364493668079376,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0753,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.23992352187633514,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1265,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.6090593338012695,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.2022,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.24616838991641998,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0761,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.08915931731462479,
      "eval_runtime": 30.6373,
      "eval_samples_per_second": 1.469,
      "eval_steps_per_second": 1.469,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2188810110092163,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0997,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.2753542959690094,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0757,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.29277193546295166,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0715,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.470039039850235,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.2083,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.28646910190582275,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0886,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.24302764236927032,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0739,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2692348062992096,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1328,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.29612597823143005,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1644,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2059725970029831,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0853,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.20432433485984802,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0661,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.0851048082113266,
      "eval_runtime": 30.6512,
      "eval_samples_per_second": 1.468,
      "eval_steps_per_second": 1.468,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.37761709094047546,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0903,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.39617136120796204,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1297,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.4556376039981842,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.2593,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.13825435936450958,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0541,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.22391359508037567,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1276,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.21886974573135376,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0647,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.3118118941783905,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.1693,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.1750730574131012,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0686,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.2192024439573288,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0899,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.17807216942310333,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0532,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.08351871371269226,
      "eval_runtime": 30.6518,
      "eval_samples_per_second": 1.468,
      "eval_steps_per_second": 1.468,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.21685345470905304,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0793,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.22611291706562042,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1055,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.182683065533638,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0778,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.24555885791778564,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0752,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.18942832946777344,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0761,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.23042131960391998,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0799,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.27033358812332153,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0769,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.17995911836624146,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0661,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.21021559834480286,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0939,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.16362504661083221,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0653,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08338318020105362,
      "eval_runtime": 30.6212,
      "eval_samples_per_second": 1.47,
      "eval_steps_per_second": 1.47,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.23219865560531616,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0894,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.179439514875412,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0718,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.21276654303073883,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0777,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.20002683997154236,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0788,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.1874803751707077,
      "learning_rate": 0.0,
      "loss": 0.0757,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.8383402746989773e+17,
      "train_loss": 0.21014132177829742,
      "train_runtime": 5737.5114,
      "train_samples_per_second": 0.353,
      "train_steps_per_second": 0.022
    }
  ],
  "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": 1.8383402746989773e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}