{
  "best_metric": 0.1446181833744049,
  "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold7/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": 2.8090898990631104,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.8452,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 3.196436882019043,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.1544,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 3.146308183670044,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.0329,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 3.1190414428710938,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.9807,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 3.179785966873169,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.9417,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.373579263687134,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.9497,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 2.7033121585845947,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.8615,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.9419089555740356,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.6059,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.7023926973342896,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.5686,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.4074822664260864,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.5152,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.40210485458374023,
      "eval_runtime": 21.8904,
      "eval_samples_per_second": 2.056,
      "eval_steps_per_second": 2.056,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.2224056720733643,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.4967,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.158743977546692,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.4315,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 1.0430325269699097,
      "learning_rate": 0.0001,
      "loss": 0.3754,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 1.2053385972976685,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4545,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.9384275078773499,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.389,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.9630246758460999,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.3299,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 1.0223737955093384,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.3088,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.7628927230834961,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2536,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.8488684296607971,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2138,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.751465380191803,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.255,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.24276258051395416,
      "eval_runtime": 21.832,
      "eval_samples_per_second": 2.061,
      "eval_steps_per_second": 2.061,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.7181167602539062,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.29,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.8676367402076721,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2095,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.7417449355125427,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.2106,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.6582796573638916,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.2063,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.864949107170105,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.2704,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.4476206302642822,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.391,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.7565575838088989,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2162,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.8352069854736328,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.2008,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.6915799975395203,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1646,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.7537572979927063,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1667,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.1936158686876297,
      "eval_runtime": 21.803,
      "eval_samples_per_second": 2.064,
      "eval_steps_per_second": 2.064,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.8252488970756531,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1747,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.6539340019226074,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1798,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.6117671132087708,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1824,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.6725478172302246,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1933,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.672620415687561,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1669,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.7408488988876343,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.2236,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.47701603174209595,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1233,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.47141847014427185,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1385,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5656715631484985,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1804,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.7662757039070129,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1828,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.1701781004667282,
      "eval_runtime": 21.8226,
      "eval_samples_per_second": 2.062,
      "eval_steps_per_second": 2.062,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.5816585421562195,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1401,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.6936994791030884,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1547,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.6066691279411316,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.13,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.7891752123832703,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1853,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.688183605670929,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1621,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.7442600131034851,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1836,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.6249017715454102,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1552,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.6753774881362915,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1783,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.49632036685943604,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1078,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.4803180992603302,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0999,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.15381264686584473,
      "eval_runtime": 21.8507,
      "eval_samples_per_second": 2.059,
      "eval_steps_per_second": 2.059,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.989392876625061,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.2619,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.550094723701477,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1388,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.5499678254127502,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1172,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.7452659010887146,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1775,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.6021642088890076,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0988,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.538462221622467,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0882,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.6635704040527344,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1304,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.5516647100448608,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1219,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.9784972071647644,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1535,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.635651171207428,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0806,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.14715269207954407,
      "eval_runtime": 21.8498,
      "eval_samples_per_second": 2.06,
      "eval_steps_per_second": 2.06,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.6960918307304382,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.139,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.6210731863975525,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1122,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.67148357629776,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0944,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.6136399507522583,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0979,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.6648707985877991,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1205,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.789014995098114,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1153,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.5909283757209778,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0878,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.7139335870742798,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.111,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.9861350059509277,
      "learning_rate": 5e-05,
      "loss": 0.1111,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.6590979695320129,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0949,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.1566891223192215,
      "eval_runtime": 21.8443,
      "eval_samples_per_second": 2.06,
      "eval_steps_per_second": 2.06,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.7557806968688965,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1166,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.8364277482032776,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1241,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.806387186050415,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.109,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.6932835578918457,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0942,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.7545567750930786,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0957,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 1.3815081119537354,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1282,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.5079225301742554,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0594,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.4906536042690277,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0569,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.46550002694129944,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0663,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.5002123117446899,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0817,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.14886444807052612,
      "eval_runtime": 21.893,
      "eval_samples_per_second": 2.055,
      "eval_steps_per_second": 2.055,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.5167155861854553,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0684,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.5850850939750671,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0886,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.5644994974136353,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0723,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.6688368916511536,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0899,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.6288519501686096,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0866,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.6659860610961914,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.076,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.8878741264343262,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.095,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.5188856720924377,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0745,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.5599380731582642,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0697,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.6973344087600708,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0966,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.14620588719844818,
      "eval_runtime": 21.8797,
      "eval_samples_per_second": 2.057,
      "eval_steps_per_second": 2.057,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.6226915717124939,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0472,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.8030417561531067,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.112,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.7283187508583069,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0814,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.5894272327423096,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0691,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.6748326420783997,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.089,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.5697019100189209,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0681,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.6080767512321472,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0674,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.7150622010231018,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0988,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.6841306090354919,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0963,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.48094356060028076,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0643,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.1446181833744049,
      "eval_runtime": 21.888,
      "eval_samples_per_second": 2.056,
      "eval_steps_per_second": 2.056,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 1.0606417655944824,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1115,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.9782896637916565,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1218,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.5276650190353394,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0614,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.5087840557098389,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0473,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.507355809211731,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0593,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.49832481145858765,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0521,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.5444963574409485,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0677,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.5338418483734131,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0691,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.608767569065094,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0796,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.6579325795173645,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0684,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.14537793397903442,
      "eval_runtime": 21.9242,
      "eval_samples_per_second": 2.053,
      "eval_steps_per_second": 2.053,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.48264560103416443,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0486,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.7303544878959656,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1129,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.48692673444747925,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0583,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.516774594783783,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0681,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.49828052520751953,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0426,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.38917046785354614,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.045,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.46058839559555054,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0382,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.5386350750923157,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0704,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.42913708090782166,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0463,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4173838794231415,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0564,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.145659938454628,
      "eval_runtime": 21.884,
      "eval_samples_per_second": 2.056,
      "eval_steps_per_second": 2.056,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.541107177734375,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0667,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.6090491414070129,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0855,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.5394759178161621,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0819,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.5912527441978455,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0643,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.5840889811515808,
      "learning_rate": 0.0,
      "loss": 0.0573,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.252407866106839e+17,
      "train_loss": 0.19367746832966803,
      "train_runtime": 3417.3047,
      "train_samples_per_second": 0.593,
      "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": 1.252407866106839e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}