{
  "best_metric": 0.0571502149105072,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold9/checkpoint-120",
  "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": 0.4765857458114624,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3619,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5131862163543701,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4086,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5910043716430664,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4275,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.5172330141067505,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.387,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.490530401468277,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3332,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5742895007133484,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3555,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.6328803300857544,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3835,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.46983617544174194,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2978,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.4487275183200836,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2975,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.3872390687465668,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2816,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.25409311056137085,
      "eval_runtime": 27.2404,
      "eval_samples_per_second": 1.652,
      "eval_steps_per_second": 1.652,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.35417526960372925,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2466,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.3295939862728119,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1989,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.41062110662460327,
      "learning_rate": 0.0001,
      "loss": 0.2314,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4643949568271637,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2286,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3977035880088806,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.182,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.3915044367313385,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.164,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.3514534533023834,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1779,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3582478165626526,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1573,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.41230374574661255,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1588,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.374607115983963,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1331,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1375233232975006,
      "eval_runtime": 26.8728,
      "eval_samples_per_second": 1.675,
      "eval_steps_per_second": 1.675,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3414933681488037,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1431,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.32820576429367065,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1355,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.45149871706962585,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1481,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.2756034731864929,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1255,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.340408056974411,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1183,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5639249682426453,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.196,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3051528036594391,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1065,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.2941097915172577,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1233,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.33452537655830383,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1135,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.326133668422699,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0912,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.09772438555955887,
      "eval_runtime": 26.7812,
      "eval_samples_per_second": 1.68,
      "eval_steps_per_second": 1.68,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.30134323239326477,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1058,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.3074023127555847,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1049,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.2727581262588501,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0837,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.3754613697528839,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0954,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.23901955783367157,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0743,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.24290227890014648,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0927,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.31983983516693115,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0736,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.2886890172958374,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0982,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.26060405373573303,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1006,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.27505725622177124,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0775,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08066457509994507,
      "eval_runtime": 26.7197,
      "eval_samples_per_second": 1.684,
      "eval_steps_per_second": 1.684,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.2722552418708801,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0688,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.22803668677806854,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0667,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.2985488772392273,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0892,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.29945167899131775,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0909,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.2696605622768402,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0599,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.30636733770370483,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0695,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2586107552051544,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0797,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.2963797450065613,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0821,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.22889670729637146,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0684,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.18309615552425385,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0645,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06907966732978821,
      "eval_runtime": 26.6787,
      "eval_samples_per_second": 1.687,
      "eval_steps_per_second": 1.687,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4291956424713135,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0983,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.2932378053665161,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0661,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.3357841968536377,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0636,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4511604607105255,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0625,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.21153682470321655,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.044,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.39230433106422424,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0602,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.26901543140411377,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0628,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2329891175031662,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0544,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.30464011430740356,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0743,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3079742193222046,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0661,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06662120670080185,
      "eval_runtime": 26.6388,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.4467102587223053,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0512,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.3491066098213196,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0585,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.32959499955177307,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0476,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.646577000617981,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0742,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.38879451155662537,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0606,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.3059900403022766,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0566,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.4584454596042633,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0644,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.29891887307167053,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0631,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2763836681842804,
      "learning_rate": 5e-05,
      "loss": 0.0498,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.3524526059627533,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0551,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06300363689661026,
      "eval_runtime": 26.6396,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.2997761070728302,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0563,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.23334138095378876,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0556,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.2857862114906311,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0578,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.2881734371185303,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0606,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.27128085494041443,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0508,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.41678759455680847,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.101,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2324618101119995,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0424,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.21584343910217285,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0501,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.2190970629453659,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0392,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2742847204208374,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0568,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.05873293802142143,
      "eval_runtime": 26.6359,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.22463959455490112,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0531,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.18190327286720276,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0317,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.241811603307724,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0459,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.19854886829853058,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0415,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.21109993755817413,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.049,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.26670095324516296,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0506,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.23325346410274506,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0435,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.2384774088859558,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0547,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.2126290500164032,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.041,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.2142573893070221,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0398,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.05806836485862732,
      "eval_runtime": 26.6376,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.2453736662864685,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0592,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.24863556027412415,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0468,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.18378254771232605,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0406,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.28364312648773193,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0566,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.23827610909938812,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.053,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.18699252605438232,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0419,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.21499477326869965,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0483,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.20432835817337036,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0425,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.20419935882091522,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0488,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.337360680103302,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.043,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.057859718799591064,
      "eval_runtime": 26.6332,
      "eval_samples_per_second": 1.69,
      "eval_steps_per_second": 1.69,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.42661425471305847,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.056,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.3922339379787445,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0823,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.17035368084907532,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0441,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.14517277479171753,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0311,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.3005775511264801,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0525,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.18496297299861908,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0403,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.1880073994398117,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.041,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.2760629951953888,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0409,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.2295786291360855,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0465,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.18368776142597198,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0301,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.057394884526729584,
      "eval_runtime": 26.6435,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.26674389839172363,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0446,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.20280519127845764,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0461,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.26792800426483154,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0507,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.21940059959888458,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0421,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.17368973791599274,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0386,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.18779264390468597,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0452,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.16179600358009338,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0364,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.16752710938453674,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.042,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2159527838230133,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0551,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.15176013112068176,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0344,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.0571502149105072,
      "eval_runtime": 26.6402,
      "eval_samples_per_second": 1.689,
      "eval_steps_per_second": 1.689,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.1906135529279709,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0509,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.14304137229919434,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0435,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.202615424990654,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0387,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.19807615876197815,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0515,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.16352109611034393,
      "learning_rate": 0.0,
      "loss": 0.0409,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.6957036222532813e+17,
      "train_loss": 0.09776993304491043,
      "train_runtime": 4812.2365,
      "train_samples_per_second": 0.421,
      "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": 1.6957036222532813e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}