{
  "best_metric": 0.1526118367910385,
  "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold2/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": 3.324267864227295,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.8824,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 3.772010326385498,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0217,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.936983346939087,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.9738,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 3.3095853328704834,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.9806,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 3.2732605934143066,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.9825,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.2430715560913086,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.8401,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.7216999530792236,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8654,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.7098702192306519,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.6335,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.323167085647583,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.66,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.2665444612503052,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5271,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.41376835107803345,
      "eval_runtime": 19.9916,
      "eval_samples_per_second": 2.251,
      "eval_steps_per_second": 2.251,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.4854705333709717,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4697,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.481184482574463,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4148,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.0628679990768433,
      "learning_rate": 0.0001,
      "loss": 0.3145,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.8874875903129578,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3546,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.949169933795929,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2952,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.8709773421287537,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3071,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.861365020275116,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3171,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.7523361444473267,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2178,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.9647196531295776,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2621,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.9119033813476562,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2415,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.24120211601257324,
      "eval_runtime": 19.8813,
      "eval_samples_per_second": 2.263,
      "eval_steps_per_second": 2.263,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.8192622661590576,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.3078,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.7349185347557068,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2418,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.7860285639762878,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2397,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.7960241436958313,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2175,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7826849222183228,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2324,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.6150120496749878,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3671,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.5154799222946167,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1387,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.7099865674972534,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2061,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.7394788861274719,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2048,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.8293597102165222,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.2333,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.19428540766239166,
      "eval_runtime": 19.8665,
      "eval_samples_per_second": 2.265,
      "eval_steps_per_second": 2.265,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.7669761776924133,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1836,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.7724063396453857,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.2119,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.7689380049705505,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.159,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.6059253811836243,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1363,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.8414813280105591,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1661,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.7099294662475586,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1534,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.5352994203567505,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1045,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6543437838554382,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1726,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.7561731934547424,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1737,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.6613370180130005,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1313,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17908136546611786,
      "eval_runtime": 19.8685,
      "eval_samples_per_second": 2.265,
      "eval_steps_per_second": 2.265,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.7858165502548218,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1991,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.7983896136283875,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1506,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.9186017513275146,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1543,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.6011046171188354,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1337,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5651993751525879,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1113,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6962747573852539,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1753,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.6775630116462708,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1591,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.6391266584396362,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1287,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.766712486743927,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.144,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.932645857334137,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.2042,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1709691733121872,
      "eval_runtime": 19.8728,
      "eval_samples_per_second": 2.264,
      "eval_steps_per_second": 2.264,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.5101383924484253,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.3305,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.5564649701118469,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1135,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.5810534358024597,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1363,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.7076700925827026,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1426,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.7269027233123779,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0973,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.7406316995620728,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1156,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.5405313372612,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0899,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5942339897155762,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0979,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.8146897554397583,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.146,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.6308845281600952,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0957,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.16828767955303192,
      "eval_runtime": 19.9178,
      "eval_samples_per_second": 2.259,
      "eval_steps_per_second": 2.259,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5553184747695923,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0803,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.888594388961792,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1436,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.666602611541748,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1156,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 1.078997254371643,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1429,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.8159158825874329,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1099,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.6336838603019714,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1171,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.5012677311897278,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0732,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.6070263385772705,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0885,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.5377382040023804,
      "learning_rate": 5e-05,
      "loss": 0.0958,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.7391361594200134,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1144,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.15279018878936768,
      "eval_runtime": 19.9109,
      "eval_samples_per_second": 2.26,
      "eval_steps_per_second": 2.26,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.4712655246257782,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0859,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.5557748079299927,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0868,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.6238380074501038,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1083,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.6001799702644348,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1039,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.6734218597412109,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1277,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.1790510416030884,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1667,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.4805506765842438,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0648,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.5426501631736755,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.093,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.5554508566856384,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0929,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.4686053693294525,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0601,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1526118367910385,
      "eval_runtime": 19.95,
      "eval_samples_per_second": 2.256,
      "eval_steps_per_second": 2.256,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5823013186454773,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.077,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.40411487221717834,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0498,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.493167519569397,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0901,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5191380381584167,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0765,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.6160794496536255,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0628,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5761992931365967,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0803,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.4918973743915558,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0615,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5289252996444702,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0494,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.4954178035259247,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.058,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5118176341056824,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0503,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.15737877786159515,
      "eval_runtime": 19.938,
      "eval_samples_per_second": 2.257,
      "eval_steps_per_second": 2.257,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.8555914759635925,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1135,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.6344273686408997,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0937,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.5788564682006836,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0583,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.5486689209938049,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0657,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.6664198040962219,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.1034,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.6807722449302673,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0842,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.7279155254364014,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0528,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.6198822259902954,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0633,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.931343138217926,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0995,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.6226465702056885,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0589,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.1603512465953827,
      "eval_runtime": 19.9797,
      "eval_samples_per_second": 2.252,
      "eval_steps_per_second": 2.252,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 1.0965557098388672,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.133,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 2.0558958053588867,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1269,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.43456631898880005,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0298,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.5654471516609192,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0743,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.6615962982177734,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0574,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.5349050164222717,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0419,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.4661468267440796,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0658,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.6879638433456421,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0607,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.7850983142852783,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0845,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.5236866474151611,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.047,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.16228988766670227,
      "eval_runtime": 20.0158,
      "eval_samples_per_second": 2.248,
      "eval_steps_per_second": 2.248,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.7767862677574158,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0562,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.8253193497657776,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0717,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.6020078063011169,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0625,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.7748581171035767,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1106,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.5897596478462219,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0421,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.4962890148162842,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0496,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.5616406798362732,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0523,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.6767080426216125,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0676,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.8133295774459839,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.062,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.7260982990264893,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0555,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.16025380790233612,
      "eval_runtime": 20.02,
      "eval_samples_per_second": 2.248,
      "eval_steps_per_second": 2.248,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.6242182850837708,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0809,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.4834727942943573,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0373,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.6213196516036987,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0672,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.6868304014205933,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.063,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.46578410267829895,
      "learning_rate": 0.0,
      "loss": 0.0354,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.251548107725865e+17,
      "train_loss": 0.18899578626453878,
      "train_runtime": 3327.3943,
      "train_samples_per_second": 0.609,
      "train_steps_per_second": 0.038
    }
  ],
  "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": 1.251548107725865e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}