{
  "best_metric": 0.1521371454000473,
  "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold3/checkpoint-80",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 3.0353739261627197,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9389,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 3.079586982727051,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.9712,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 3.8306632041931152,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.9731,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 3.2806384563446045,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.8988,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 3.41788649559021,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.1089,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.304004669189453,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.7927,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.5689151287078857,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8516,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.956925630569458,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.759,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.612807035446167,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.6502,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.5955379009246826,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5151,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.45077192783355713,
      "eval_runtime": 19.4543,
      "eval_samples_per_second": 2.313,
      "eval_steps_per_second": 2.313,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.2867790460586548,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4612,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.2136120796203613,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4512,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.077429175376892,
      "learning_rate": 0.0001,
      "loss": 0.3338,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.920623242855072,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3453,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.8907867074012756,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2943,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.9528615474700928,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3191,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 1.134238600730896,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2663,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.716907799243927,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2384,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.8364075422286987,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2395,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.8391572833061218,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.221,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.24420633912086487,
      "eval_runtime": 19.4114,
      "eval_samples_per_second": 2.318,
      "eval_steps_per_second": 2.318,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.7686058878898621,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.2762,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.9789791107177734,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2539,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.6539018750190735,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1857,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.7087847590446472,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2487,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.8740436434745789,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2831,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.46257483959198,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3766,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.597014307975769,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1537,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.7003579139709473,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2213,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.7034401893615723,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2403,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.7190847992897034,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1814,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.19917474687099457,
      "eval_runtime": 19.4195,
      "eval_samples_per_second": 2.317,
      "eval_steps_per_second": 2.317,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.7159770727157593,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1513,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.7008103132247925,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1531,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.8912058472633362,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.177,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.9022628664970398,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2211,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.7523685097694397,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1406,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.8705664277076721,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1957,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.6962376236915588,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1963,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.5296832323074341,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1243,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.7059044241905212,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1349,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.9428603649139404,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.2227,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.1761385202407837,
      "eval_runtime": 19.4317,
      "eval_samples_per_second": 2.316,
      "eval_steps_per_second": 2.316,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.5007083415985107,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.121,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.7512481808662415,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1684,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.6420414447784424,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1388,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.5673903226852417,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1452,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5248191952705383,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1577,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.803503155708313,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1696,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.5884333252906799,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1812,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.7608354091644287,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1853,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.6819073557853699,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1221,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.6046553254127502,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1216,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.16881760954856873,
      "eval_runtime": 19.5117,
      "eval_samples_per_second": 2.306,
      "eval_steps_per_second": 2.306,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.3737536668777466,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.305,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.5390072464942932,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0894,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.6808497905731201,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1291,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.7322034239768982,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1315,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.8202535510063171,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1381,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.8872473239898682,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1334,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.7545626163482666,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1265,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.765016496181488,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1357,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.7760490775108337,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1434,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.5344038009643555,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0852,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.16612006723880768,
      "eval_runtime": 19.4967,
      "eval_samples_per_second": 2.308,
      "eval_steps_per_second": 2.308,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.9395344853401184,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1202,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.7595337629318237,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1121,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.8676968216896057,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1082,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5577676892280579,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0814,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.5301467180252075,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0662,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.7455857992172241,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1637,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.6989542245864868,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1148,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.6799095273017883,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0841,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.7823291420936584,
      "learning_rate": 5e-05,
      "loss": 0.1083,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.5670030117034912,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0674,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.16597549617290497,
      "eval_runtime": 19.5078,
      "eval_samples_per_second": 2.307,
      "eval_steps_per_second": 2.307,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.7792357802391052,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1497,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.5810841917991638,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.08,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.7231540679931641,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.108,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.61223304271698,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0985,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.755276620388031,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.158,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.13872230052948,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1831,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.696807324886322,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1083,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.595140278339386,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0964,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.6400544047355652,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0895,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.5612196922302246,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0806,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1521371454000473,
      "eval_runtime": 19.5316,
      "eval_samples_per_second": 2.304,
      "eval_steps_per_second": 2.304,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5586304664611816,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0869,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.6859959363937378,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.1162,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.6235560774803162,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0739,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5098514556884766,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0738,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5034618377685547,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0702,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.681019127368927,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0632,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.6398540139198303,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0748,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5484116673469543,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0588,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.8013283610343933,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0617,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.6180264353752136,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0799,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1602296084165573,
      "eval_runtime": 19.5397,
      "eval_samples_per_second": 2.303,
      "eval_steps_per_second": 2.303,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.6274417638778687,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0867,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.6344594359397888,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0533,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.7271066904067993,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0693,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.9942989945411682,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0942,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.9156520962715149,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1195,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.6745840907096863,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0844,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.9016881585121155,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0891,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5660194158554077,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0841,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.554365873336792,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0654,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.5465905070304871,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0608,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.15922702848911285,
      "eval_runtime": 19.5889,
      "eval_samples_per_second": 2.297,
      "eval_steps_per_second": 2.297,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.9192725419998169,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0893,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 1.5693391561508179,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1216,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.5942802429199219,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0526,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.5318936705589294,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0473,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.5006883144378662,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0444,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.5038785934448242,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0695,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.530846893787384,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0535,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.6184120774269104,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0661,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.6720767617225647,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0618,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.6421629786491394,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0784,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.16031911969184875,
      "eval_runtime": 19.6256,
      "eval_samples_per_second": 2.293,
      "eval_steps_per_second": 2.293,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.5215726494789124,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0658,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.5442056655883789,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0675,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.5384764075279236,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0665,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.5722429156303406,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0693,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.5756042003631592,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0543,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.4948265850543976,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0446,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.6645839810371399,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0946,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.647534966468811,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0772,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.6252390742301941,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0486,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.6391206383705139,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0911,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.15994727611541748,
      "eval_runtime": 19.5895,
      "eval_samples_per_second": 2.297,
      "eval_steps_per_second": 2.297,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.5276749730110168,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0623,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.6345894932746887,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0705,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.6102444529533386,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0694,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.5972200036048889,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0585,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.6772796511650085,
      "learning_rate": 0.0,
      "loss": 0.0688,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.279295183878226e+17,
      "train_loss": 0.19306774643063546,
      "train_runtime": 3422.3687,
      "train_samples_per_second": 0.592,
      "train_steps_per_second": 0.037
    }
  ],
  "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": 1.279295183878226e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}