{
  "best_metric": 0.10422473400831223,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold3/checkpoint-60",
  "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": 1.0809844732284546,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.4181,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 1.1642398834228516,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2992,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.0005384683609009,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3069,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.217094898223877,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3451,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.2359120845794678,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3318,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.3714345693588257,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3648,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.149124264717102,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2925,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.9799826741218567,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3271,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.1086472272872925,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2548,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.7744888067245483,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1561,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.21573886275291443,
      "eval_runtime": 22.4425,
      "eval_samples_per_second": 2.005,
      "eval_steps_per_second": 2.005,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.0863028764724731,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.153,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.867466390132904,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1839,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.9721124172210693,
      "learning_rate": 0.0001,
      "loss": 0.1822,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.8522771000862122,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1906,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.7154011726379395,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1911,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.699091911315918,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.176,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.7064182162284851,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1623,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6618867516517639,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1356,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.6859382390975952,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1349,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5718986988067627,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1162,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1449417918920517,
      "eval_runtime": 22.2421,
      "eval_samples_per_second": 2.023,
      "eval_steps_per_second": 2.023,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.5761432647705078,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0792,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6635696887969971,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1706,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.445147305727005,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0896,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.7820290923118591,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.122,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.514002799987793,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1008,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.593248724937439,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.0797,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.5707173943519592,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.108,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.6026235222816467,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1379,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.5049033164978027,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0972,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.5925488471984863,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1166,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.11997146904468536,
      "eval_runtime": 22.1623,
      "eval_samples_per_second": 2.03,
      "eval_steps_per_second": 2.03,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.3781605660915375,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.05,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.5409032702445984,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0851,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.7225788235664368,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0936,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.7821835279464722,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1377,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.6090335845947266,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0791,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.6183640956878662,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1193,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.8125379681587219,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1395,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6214229464530945,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1049,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.44177064299583435,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0682,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.6533269882202148,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.124,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.11143364012241364,
      "eval_runtime": 22.3144,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.37622198462486267,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0578,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.5329247117042542,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1073,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.49538928270339966,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0917,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.33952268958091736,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0682,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3845701515674591,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.075,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3605704605579376,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0516,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.4862770736217499,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0795,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.525028645992279,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1215,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.4393024444580078,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0775,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.49093130230903625,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0767,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.10658951848745346,
      "eval_runtime": 22.2573,
      "eval_samples_per_second": 2.022,
      "eval_steps_per_second": 2.022,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.9171443581581116,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1156,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.4602516293525696,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0505,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.4447534382343292,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.056,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.5238065719604492,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.073,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.46458911895751953,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0557,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.578309178352356,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.105,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.48329058289527893,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0892,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5552093982696533,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0728,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.6658794283866882,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.072,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.4494522511959076,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0544,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.10422473400831223,
      "eval_runtime": 22.2324,
      "eval_samples_per_second": 2.024,
      "eval_steps_per_second": 2.024,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5484684109687805,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0848,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6327154040336609,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0753,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.43651726841926575,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0607,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.601899266242981,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0535,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.34022286534309387,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0333,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.46373724937438965,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0698,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.4374874234199524,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0561,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.46656572818756104,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0489,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.5541983842849731,
      "learning_rate": 5e-05,
      "loss": 0.0713,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.5726492404937744,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0556,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.11096261441707611,
      "eval_runtime": 22.2661,
      "eval_samples_per_second": 2.021,
      "eval_steps_per_second": 2.021,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.5485683679580688,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0882,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.4317617416381836,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0594,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.37580421566963196,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0365,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.5181528329849243,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0602,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.5396584272384644,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0862,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.9760444164276123,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.121,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.543147623538971,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0525,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.5036170482635498,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0598,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.5058211088180542,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0418,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.6866286993026733,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.045,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1061539426445961,
      "eval_runtime": 22.2483,
      "eval_samples_per_second": 2.023,
      "eval_steps_per_second": 2.023,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5536800026893616,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0837,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.5335898995399475,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0662,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.5557556748390198,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.042,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.38917380571365356,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0378,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.48717647790908813,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0559,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5340138077735901,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0464,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.539394199848175,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0444,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5545044541358948,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0331,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5148292779922485,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0419,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5119119882583618,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0517,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.10765866190195084,
      "eval_runtime": 22.3153,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.49667975306510925,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0531,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.4810623526573181,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0393,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.6156262159347534,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0452,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.5836111307144165,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0626,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.740441620349884,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0723,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.4307105839252472,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0445,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.5607255101203918,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0624,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.3379635512828827,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0266,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.3855540454387665,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.036,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.4776158630847931,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0345,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.1057269275188446,
      "eval_runtime": 22.3123,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.7954503297805786,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0573,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.0858795642852783,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0929,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.46477824449539185,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0416,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.3171675205230713,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0308,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.39108040928840637,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0294,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.48646554350852966,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0467,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.34401169419288635,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0215,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.47339412569999695,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0429,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.4377497136592865,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0255,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.31617215275764465,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0296,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.10580828785896301,
      "eval_runtime": 22.1346,
      "eval_samples_per_second": 2.033,
      "eval_steps_per_second": 2.033,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.37426719069480896,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0281,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.47973543405532837,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.049,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.515800952911377,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0369,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.3938630223274231,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0481,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.3533174991607666,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0226,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.3289427161216736,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.024,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.5888838171958923,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0726,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.4907120168209076,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0405,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.3917694389820099,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0305,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4596107006072998,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.066,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.10624368488788605,
      "eval_runtime": 22.3381,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.34883761405944824,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0318,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.419063001871109,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0408,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.4434618651866913,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0416,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.47291696071624756,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0433,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.5572324991226196,
      "learning_rate": 0.0,
      "loss": 0.0417,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.351908642768814e+17,
      "train_loss": 0.09321212306618691,
      "train_runtime": 4012.3551,
      "train_samples_per_second": 0.505,
      "train_steps_per_second": 0.031
    }
  ],
  "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": 1.351908642768814e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}