{
  "best_metric": 0.06156276538968086,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold2/checkpoint-100",
  "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": 0.4031108617782593,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3449,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.434431791305542,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3746,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.4196051359176636,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3665,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.3727693557739258,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3439,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.44829314947128296,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3672,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.4394720494747162,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3189,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5172329545021057,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3395,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.36157336831092834,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2953,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.43025869131088257,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3233,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.4183492958545685,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.3004,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.27276843786239624,
      "eval_runtime": 27.8987,
      "eval_samples_per_second": 1.613,
      "eval_steps_per_second": 1.613,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.5038578510284424,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2684,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.4594784379005432,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2407,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.43960556387901306,
      "learning_rate": 0.0001,
      "loss": 0.2274,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.39729195833206177,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2404,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3684755265712738,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2007,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.33968350291252136,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1709,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.352060467004776,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1725,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.38479456305503845,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1823,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.3121379315853119,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1587,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.24845488369464874,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1499,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1545153111219406,
      "eval_runtime": 27.8573,
      "eval_samples_per_second": 1.615,
      "eval_steps_per_second": 1.615,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.31575530767440796,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1608,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.38354384899139404,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1501,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.2956995368003845,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1322,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.25874313712120056,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1183,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.3161133825778961,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1294,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5339604616165161,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2205,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3152259588241577,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0882,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2743331789970398,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1248,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.28483179211616516,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1112,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.26417264342308044,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1274,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1142813041806221,
      "eval_runtime": 27.8311,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.18823398649692535,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0893,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.26894041895866394,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1097,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.22209641337394714,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0909,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.26708224415779114,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0874,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.3010738790035248,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0905,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.2667326033115387,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0904,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.18752224743366241,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0821,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.20916959643363953,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0909,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.28659966588020325,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0894,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.22048696875572205,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0741,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08929622173309326,
      "eval_runtime": 27.8307,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.27605247497558594,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0783,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.24868641793727875,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0758,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.32589638233184814,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0751,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.22045288980007172,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0748,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.28820672631263733,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0603,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.21174830198287964,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0662,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2964930236339569,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0867,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.24062509834766388,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0682,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.32645395398139954,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0782,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.21925745904445648,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0683,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07862581312656403,
      "eval_runtime": 27.8332,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.37701308727264404,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1019,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.21924622356891632,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0567,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2244839370250702,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.066,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.2465217113494873,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0694,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.20421801507472992,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0439,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.19212143123149872,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0545,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.2588331401348114,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.076,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2755987048149109,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0534,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2839370667934418,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0668,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3290315866470337,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0485,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07326957583427429,
      "eval_runtime": 27.8338,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.31746363639831543,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0588,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.29342713952064514,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.06,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.22820597887039185,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0546,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.24872219562530518,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0681,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.21403007209300995,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0594,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.20784151554107666,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0572,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.19962583482265472,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0607,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.20555931329727173,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0592,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.18127670884132385,
      "learning_rate": 5e-05,
      "loss": 0.0571,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.25595560669898987,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0613,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06797000020742416,
      "eval_runtime": 27.8455,
      "eval_samples_per_second": 1.616,
      "eval_steps_per_second": 1.616,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.19163402915000916,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0532,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.20018424093723297,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0536,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.18809866905212402,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0529,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.2478126734495163,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.058,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.29429998993873596,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0598,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.46467360854148865,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.092,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.17061427235603333,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0428,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.16244040429592133,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0474,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.1740025132894516,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0414,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.27907049655914307,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0573,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06602052599191666,
      "eval_runtime": 27.8279,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2085799127817154,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0447,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.19969801604747772,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0361,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.16787903010845184,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0416,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.2372080385684967,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0506,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.17883242666721344,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0377,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.18266502022743225,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.05,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.2688904404640198,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0463,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.2217710167169571,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.043,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.1952497810125351,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0506,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.1916496306657791,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0433,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06376053392887115,
      "eval_runtime": 27.8266,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.20864562690258026,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0609,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.16575026512145996,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0434,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.19914768636226654,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.045,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.23677106201648712,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.055,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.22921641170978546,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0611,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.2426401674747467,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0535,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.22456574440002441,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0434,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.23578883707523346,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.047,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.26042094826698303,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0545,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.16356240212917328,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0397,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06156276538968086,
      "eval_runtime": 27.8105,
      "eval_samples_per_second": 1.618,
      "eval_steps_per_second": 1.618,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.23495279252529144,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0562,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.3945830166339874,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0842,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.1934359073638916,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.042,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.21007229387760162,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0527,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.1959836632013321,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0527,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.15436618030071259,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0295,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.22812116146087646,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0503,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.16382712125778198,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0387,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.20582491159439087,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0477,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.17316491901874542,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0368,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06206447258591652,
      "eval_runtime": 27.8323,
      "eval_samples_per_second": 1.617,
      "eval_steps_per_second": 1.617,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.2147095799446106,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0413,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.19017565250396729,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.041,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.17311109602451324,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0456,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.21769729256629944,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0594,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.17352813482284546,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0319,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.16673964262008667,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0445,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.15892541408538818,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0318,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.19156469404697418,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0499,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.1877230852842331,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.049,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.20868825912475586,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0535,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06184663251042366,
      "eval_runtime": 27.8396,
      "eval_samples_per_second": 1.616,
      "eval_steps_per_second": 1.616,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.22347162663936615,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0468,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.14199678599834442,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.034,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.17933087050914764,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0409,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.14693498611450195,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0384,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.1622653752565384,
      "learning_rate": 0.0,
      "loss": 0.0418,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.6454944552904294e+17,
      "train_loss": 0.09804612562060357,
      "train_runtime": 4758.7255,
      "train_samples_per_second": 0.426,
      "train_steps_per_second": 0.026
    }
  ],
  "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": 1.6454944552904294e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}