{
  "best_metric": 0.053196363151073456,
  "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold3/checkpoint-70",
  "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": 0.27642908692359924,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2335,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.2604428827762604,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1862,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.3132173418998718,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.1996,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.25304609537124634,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2053,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.24818304181098938,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3304,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.29132845997810364,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1885,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.2672402560710907,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2371,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.22117385268211365,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.1916,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.23741206526756287,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1629,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.19374148547649384,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1116,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.11964218318462372,
      "eval_runtime": 26.3774,
      "eval_samples_per_second": 1.706,
      "eval_steps_per_second": 1.706,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.21955297887325287,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1182,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.2291027456521988,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1108,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.17804846167564392,
      "learning_rate": 0.0001,
      "loss": 0.0853,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.20618094503879547,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.154,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.21770156919956207,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.093,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.17749617993831635,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.0961,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.15217655897140503,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1148,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.13357466459274292,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.122,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.12104997783899307,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.0974,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.11807096749544144,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0543,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.07165724784135818,
      "eval_runtime": 26.2224,
      "eval_samples_per_second": 1.716,
      "eval_steps_per_second": 1.716,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.14576560258865356,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0727,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.1458244025707245,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.07,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.1383245587348938,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1297,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.1325737088918686,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1272,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.10790367424488068,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0674,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.13592122495174408,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.0637,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.10866763442754745,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0901,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.1113622859120369,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1175,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.1071900799870491,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0721,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.10592512786388397,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0747,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.061504166573286057,
      "eval_runtime": 26.1782,
      "eval_samples_per_second": 1.719,
      "eval_steps_per_second": 1.719,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.10942697525024414,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0855,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.11112643778324127,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0845,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.12113000452518463,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0594,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.12321589142084122,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1154,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.09744105488061905,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0405,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.09617210179567337,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0595,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.10988622903823853,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1273,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.08965536952018738,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0432,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.09792012721300125,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0798,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.12043308466672897,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1014,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0576392225921154,
      "eval_runtime": 26.0695,
      "eval_samples_per_second": 1.726,
      "eval_steps_per_second": 1.726,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.09099707007408142,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0343,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.09687680006027222,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1036,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.09403926879167557,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0675,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.09448980540037155,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1089,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.09190331399440765,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0324,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.08157458901405334,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0347,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.10561530292034149,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0841,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.10906659066677094,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0867,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.11188874393701553,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0701,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.11076200753450394,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0608,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.055440351366996765,
      "eval_runtime": 26.2166,
      "eval_samples_per_second": 1.716,
      "eval_steps_per_second": 1.716,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.09179500490427017,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0514,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.09382931143045425,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0896,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.08963757008314133,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0475,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.10110442340373993,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0556,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.08257470279932022,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0368,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.11599816381931305,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1409,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.1167377158999443,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.105,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.08618653565645218,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0516,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.090789295732975,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0662,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.10416969656944275,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0319,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.054627370089292526,
      "eval_runtime": 26.0969,
      "eval_samples_per_second": 1.724,
      "eval_steps_per_second": 1.724,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.14076991379261017,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0618,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.09547543525695801,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0695,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.0978887751698494,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0601,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.09979033470153809,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0547,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.09591910988092422,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.033,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.11154092848300934,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0602,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.10924198478460312,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0513,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.10445116460323334,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0753,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.1256513148546219,
      "learning_rate": 5e-05,
      "loss": 0.0521,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.11680573970079422,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0476,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.053196363151073456,
      "eval_runtime": 26.2201,
      "eval_samples_per_second": 1.716,
      "eval_steps_per_second": 1.716,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.11419302225112915,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0745,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.12458746880292892,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0768,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.10679403692483902,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0206,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.16071341931819916,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1245,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.1192450001835823,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0364,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.11671276390552521,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0753,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.10692435503005981,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0571,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.14029507339000702,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0902,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.14004364609718323,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.087,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.12786024808883667,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0866,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.053591273725032806,
      "eval_runtime": 25.4289,
      "eval_samples_per_second": 1.77,
      "eval_steps_per_second": 1.77,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.12126544862985611,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0656,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.10200870782136917,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0508,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.1083173081278801,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0291,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.1219799667596817,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0582,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.09820209443569183,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0356,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.12968666851520538,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0656,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.0987592488527298,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0435,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.11198901385068893,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0393,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.0964149609208107,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0289,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.14315150678157806,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0563,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.05403430759906769,
      "eval_runtime": 26.3916,
      "eval_samples_per_second": 1.705,
      "eval_steps_per_second": 1.705,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.11734234541654587,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0415,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.10020370781421661,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.035,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.12581981718540192,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.057,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.17563146352767944,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0904,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.1290147304534912,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0573,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.11972296237945557,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0541,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.15634393692016602,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0854,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.10680607706308365,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0327,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.14576634764671326,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0835,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.10056203603744507,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0158,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.0534704253077507,
      "eval_runtime": 25.3421,
      "eval_samples_per_second": 1.776,
      "eval_steps_per_second": 1.776,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.12410066276788712,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0415,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.1401020884513855,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0752,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.10771016776561737,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0432,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.1075674444437027,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0474,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.13907349109649658,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0952,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.1203957200050354,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0546,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.1393885314464569,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0805,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.11346660554409027,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0441,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.12052503228187561,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0374,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.11487959325313568,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0306,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.05385005101561546,
      "eval_runtime": 26.4415,
      "eval_samples_per_second": 1.702,
      "eval_steps_per_second": 1.702,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.10462473332881927,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0318,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.10982673615217209,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0402,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.10813390463590622,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0342,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.1516677886247635,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0759,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.1074109822511673,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0247,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.1348678320646286,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.071,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.12272226065397263,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0483,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.09247682988643646,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0249,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.12911206483840942,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0512,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.13710449635982513,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0565,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05383634194731712,
      "eval_runtime": 26.0584,
      "eval_samples_per_second": 1.727,
      "eval_steps_per_second": 1.727,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.10670395940542221,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0244,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.11341248452663422,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0355,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.12191934138536453,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0496,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1311069130897522,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0647,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.13703693449497223,
      "learning_rate": 0.0,
      "loss": 0.0708,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.5558918187371725e+17,
      "train_loss": 0.07766047413647174,
      "train_runtime": 4420.5187,
      "train_samples_per_second": 0.458,
      "train_steps_per_second": 0.028
    }
  ],
  "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": 1.5558918187371725e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}