{
  "best_metric": 0.1046806052327156,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold9/checkpoint-50",
  "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": 1.1590155363082886,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3297,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.2303924560546875,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3929,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.025434136390686,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2866,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.2514833211898804,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3493,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.0900028944015503,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2991,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.3638954162597656,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.2481,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.9845355749130249,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.1959,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.1244865655899048,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2206,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.9195776581764221,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2474,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.2965734004974365,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2713,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1963089257478714,
      "eval_runtime": 21.5306,
      "eval_samples_per_second": 2.09,
      "eval_steps_per_second": 2.09,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.1459654569625854,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2275,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.9573066830635071,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.18,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.9153808355331421,
      "learning_rate": 0.0001,
      "loss": 0.2607,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.9068604707717896,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1843,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.66790372133255,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1198,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.7700053453445435,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1679,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.7242267727851868,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1994,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6281782984733582,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1405,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.5636272430419922,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1129,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.6139253973960876,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1005,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.13335928320884705,
      "eval_runtime": 21.2914,
      "eval_samples_per_second": 2.114,
      "eval_steps_per_second": 2.114,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.5671014189720154,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1393,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6873334646224976,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1247,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.610960841178894,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0952,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.44675588607788086,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1188,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4905669689178467,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1172,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.284014344215393,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2413,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3423492908477783,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0734,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.5073022246360779,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1105,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5469907522201538,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0933,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.6295572519302368,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1403,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.12132183462381363,
      "eval_runtime": 21.269,
      "eval_samples_per_second": 2.116,
      "eval_steps_per_second": 2.116,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5765777230262756,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0913,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.49298712611198425,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1037,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.5014662146568298,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1081,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.4635147750377655,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.099,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.6004471182823181,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1007,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.38633546233177185,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.083,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.6304664015769958,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0955,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6700285077095032,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.095,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5264943838119507,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0966,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.669002890586853,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0914,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.11680717766284943,
      "eval_runtime": 21.314,
      "eval_samples_per_second": 2.111,
      "eval_steps_per_second": 2.111,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.5533943176269531,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0592,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.5552099347114563,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.084,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.5851306915283203,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0908,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 1.099927544593811,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1195,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5323945879936218,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0601,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.4856466054916382,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0755,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.6813690662384033,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0933,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.5942478775978088,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0888,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.328844279050827,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.05,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.5661343336105347,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0964,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1046806052327156,
      "eval_runtime": 21.3173,
      "eval_samples_per_second": 2.111,
      "eval_steps_per_second": 2.111,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.9890033006668091,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1918,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.5015379190444946,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0766,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.36947399377822876,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0878,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.30124685168266296,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0565,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.29000329971313477,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0369,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.3812747001647949,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0709,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.5249848961830139,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0911,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.41945064067840576,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0577,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.3799711763858795,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.049,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.4861077070236206,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0598,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.1118868738412857,
      "eval_runtime": 21.3119,
      "eval_samples_per_second": 2.111,
      "eval_steps_per_second": 2.111,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.41540196537971497,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0487,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6737284064292908,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0659,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.5706254839897156,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0773,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.478893905878067,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0994,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.4565238356590271,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0628,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.4509061872959137,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0719,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.33175912499427795,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0497,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.44493886828422546,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0652,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6411983966827393,
      "learning_rate": 5e-05,
      "loss": 0.0777,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.5106154084205627,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0604,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.10917598754167557,
      "eval_runtime": 21.3292,
      "eval_samples_per_second": 2.11,
      "eval_steps_per_second": 2.11,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.46466803550720215,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0479,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.5217601656913757,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0535,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.502958357334137,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0783,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.4955649971961975,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0322,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.4796045124530792,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0531,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.281530499458313,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1018,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2785991430282593,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0251,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.44250643253326416,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0423,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.41457438468933105,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0403,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.38369667530059814,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0439,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.10951358079910278,
      "eval_runtime": 21.3206,
      "eval_samples_per_second": 2.111,
      "eval_steps_per_second": 2.111,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.6861261129379272,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0719,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.43095454573631287,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0327,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.4596267640590668,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0479,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.40898415446281433,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.038,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.43635109066963196,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.036,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.45546913146972656,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0544,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.6909031271934509,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0444,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5347234010696411,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0618,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.4470304250717163,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0314,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.3411533832550049,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.026,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.11183000355958939,
      "eval_runtime": 21.3654,
      "eval_samples_per_second": 2.106,
      "eval_steps_per_second": 2.106,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.586372435092926,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0761,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.7290622591972351,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0412,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.4405894875526428,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0289,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.5401649475097656,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0592,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.505775511264801,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0342,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.3230384886264801,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0209,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.4699391722679138,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0399,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.531794011592865,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0434,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.5548411011695862,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0619,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.562754213809967,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0326,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.11104591935873032,
      "eval_runtime": 21.3398,
      "eval_samples_per_second": 2.109,
      "eval_steps_per_second": 2.109,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.9833007454872131,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0767,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.9327598214149475,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0682,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.3662216365337372,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0332,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.4300500452518463,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0311,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.4222818911075592,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0375,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.3978478014469147,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0232,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.4640689194202423,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0372,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.4668560326099396,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0219,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.6405048966407776,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0384,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.3104925751686096,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0238,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.11366768181324005,
      "eval_runtime": 21.3311,
      "eval_samples_per_second": 2.11,
      "eval_steps_per_second": 2.11,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.6391770839691162,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0449,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.5848953723907471,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0463,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.3341389000415802,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0305,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.3900814950466156,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0433,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3766683340072632,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0212,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.47513872385025024,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.042,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.32467105984687805,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0211,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.4118802547454834,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0381,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.3926299512386322,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0378,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.41851699352264404,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0355,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.11356858909130096,
      "eval_runtime": 21.3524,
      "eval_samples_per_second": 2.107,
      "eval_steps_per_second": 2.107,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.5105354189872742,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0406,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.525077223777771,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0391,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.5416433811187744,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0412,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.45854198932647705,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0425,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.5192046761512756,
      "learning_rate": 0.0,
      "loss": 0.0415,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3313214032176742e+17,
      "train_loss": 0.09108274313807488,
      "train_runtime": 3702.9005,
      "train_samples_per_second": 0.547,
      "train_steps_per_second": 0.034
    }
  ],
  "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": 1.3313214032176742e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}