{
  "best_metric": 0.14266666769981384,
  "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold10/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": 2.9342691898345947,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9672,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 2.9770865440368652,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.9822,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 3.5307414531707764,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.9294,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 2.9987173080444336,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.0225,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 2.7308285236358643,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.9703,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.0230767726898193,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.9267,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.4251708984375,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.7957,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.9444857835769653,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.617,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.183368444442749,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.7035,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.4162545204162598,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5161,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.41856592893600464,
      "eval_runtime": 20.2389,
      "eval_samples_per_second": 2.223,
      "eval_steps_per_second": 2.223,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.2647477388381958,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.432,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.318211555480957,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.5355,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.3575319051742554,
      "learning_rate": 0.0001,
      "loss": 0.3441,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.9630506634712219,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.3204,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.129729986190796,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.4131,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.9399763345718384,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.2158,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.8148107528686523,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2815,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6948516964912415,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2396,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.8203120827674866,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2702,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.7738016247749329,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2338,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.24493779242038727,
      "eval_runtime": 20.1327,
      "eval_samples_per_second": 2.235,
      "eval_steps_per_second": 2.235,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.8488219976425171,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.3073,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.675926685333252,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1976,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.7680459022521973,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2413,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.6361139416694641,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1712,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7143667936325073,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.168,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.554243803024292,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3792,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.7455339431762695,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2455,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.5568704009056091,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1841,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.7195683121681213,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2029,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.8117971420288086,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1994,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1937544047832489,
      "eval_runtime": 20.1473,
      "eval_samples_per_second": 2.234,
      "eval_steps_per_second": 2.234,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.6998987197875977,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.134,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.630284309387207,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1591,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.773307204246521,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.2136,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.8497766852378845,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1593,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.7530022263526917,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1775,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.7349281907081604,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1796,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.7540538311004639,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1895,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6085947155952454,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1316,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5312603712081909,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1456,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.810352623462677,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.2163,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17150431871414185,
      "eval_runtime": 20.1963,
      "eval_samples_per_second": 2.228,
      "eval_steps_per_second": 2.228,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6684698462486267,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1682,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.6570677161216736,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1223,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.6806609034538269,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1342,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.6625347137451172,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1631,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.7247101068496704,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1437,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.6127734780311584,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1601,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.6914538145065308,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1319,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.6021819114685059,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1517,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.482916921377182,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1194,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.7768675684928894,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1276,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.15364718437194824,
      "eval_runtime": 20.1492,
      "eval_samples_per_second": 2.233,
      "eval_steps_per_second": 2.233,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.451322317123413,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2229,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.5300964117050171,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0956,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.5868623852729797,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1176,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.6459300518035889,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1214,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.5935022234916687,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1325,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.6628939509391785,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1197,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.8179349303245544,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1862,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.6293999552726746,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1433,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.5513004660606384,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1042,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.5161257982254028,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1057,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.14459866285324097,
      "eval_runtime": 20.147,
      "eval_samples_per_second": 2.234,
      "eval_steps_per_second": 2.234,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.6414966583251953,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1252,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.5335237383842468,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0911,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.5199956297874451,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0799,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.6380789279937744,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1131,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.6987588405609131,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0969,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.553085207939148,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0928,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.528498649597168,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.077,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.5222181081771851,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.1075,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.6448318362236023,
      "learning_rate": 5e-05,
      "loss": 0.1043,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.7114214897155762,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1085,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.14266666769981384,
      "eval_runtime": 20.172,
      "eval_samples_per_second": 2.231,
      "eval_steps_per_second": 2.231,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.686777651309967,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0869,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.7996186017990112,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1316,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.7514344453811646,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1131,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.6073297262191772,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0899,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.5323072075843811,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0759,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.0053658485412598,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1202,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.5352737307548523,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0706,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.6176329255104065,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0858,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.504818856716156,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.063,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.8284781575202942,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0953,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.14604710042476654,
      "eval_runtime": 20.1748,
      "eval_samples_per_second": 2.231,
      "eval_steps_per_second": 2.231,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5600486993789673,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.063,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.6512521505355835,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0977,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.547960638999939,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0793,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5385531187057495,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0757,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.48342660069465637,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0689,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.5138679146766663,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0773,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.614950954914093,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.1143,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.6016719341278076,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0721,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5464275479316711,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0596,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.6324774026870728,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0821,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1470063030719757,
      "eval_runtime": 20.1497,
      "eval_samples_per_second": 2.233,
      "eval_steps_per_second": 2.233,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.9425758123397827,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0873,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.5515706539154053,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0598,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.5270301103591919,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0741,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.5560928583145142,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0492,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.7012993693351746,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0781,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.6937682032585144,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1019,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.707927405834198,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0858,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.6722747087478638,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0937,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.7355726361274719,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0844,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.6081374287605286,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0623,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.14688971638679504,
      "eval_runtime": 20.1552,
      "eval_samples_per_second": 2.233,
      "eval_steps_per_second": 2.233,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.7425580024719238,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0948,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.8317994475364685,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1085,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.3936798870563507,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0445,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.6239023208618164,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0702,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.49166139960289,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.045,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.4660905599594116,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.052,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.6027308106422424,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0573,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.5008475184440613,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0487,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.603857159614563,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0607,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.5066999793052673,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.06,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.15068334341049194,
      "eval_runtime": 20.1588,
      "eval_samples_per_second": 2.232,
      "eval_steps_per_second": 2.232,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.5949515104293823,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0548,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.5857564806938171,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0756,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.5539479851722717,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.062,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.5593045949935913,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0708,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.5724353194236755,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0466,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.5053752064704895,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0606,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.6070622801780701,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0723,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.6059235334396362,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0716,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.5221177339553833,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0505,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.5442896485328674,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0829,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.1498665064573288,
      "eval_runtime": 20.1753,
      "eval_samples_per_second": 2.23,
      "eval_steps_per_second": 2.23,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.4041250944137573,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0376,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.7015883922576904,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0856,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.434815913438797,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0517,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.5343510508537292,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0617,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.4980866611003876,
      "learning_rate": 0.0,
      "loss": 0.0655,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.2623709485216563e+17,
      "train_loss": 0.1886164007782936,
      "train_runtime": 3436.5874,
      "train_samples_per_second": 0.589,
      "train_steps_per_second": 0.036
    }
  ],
  "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": 1.2623709485216563e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}