{
  "best_metric": 0.05186542496085167,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold6/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": 0.6418177485466003,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.4269,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5023269653320312,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3725,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.637933611869812,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.403,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.48793259263038635,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3676,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.4619690775871277,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3513,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5265172719955444,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3685,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5432477593421936,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3767,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.48470965027809143,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3139,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.43081748485565186,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2924,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.38443735241889954,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2565,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.24733728170394897,
      "eval_runtime": 34.3182,
      "eval_samples_per_second": 1.311,
      "eval_steps_per_second": 1.311,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.4220511317253113,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2792,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.3678396940231323,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2269,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.41348424553871155,
      "learning_rate": 0.0001,
      "loss": 0.2143,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.44538193941116333,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1962,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.4586395025253296,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2022,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.4219096302986145,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1908,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.3466053009033203,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1611,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.4137932360172272,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1635,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.30859240889549255,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1439,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.30716457962989807,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1517,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1348874419927597,
      "eval_runtime": 33.8033,
      "eval_samples_per_second": 1.331,
      "eval_steps_per_second": 1.331,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.2876456081867218,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1404,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.2793624699115753,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1536,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.4382656216621399,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1255,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.42443719506263733,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1318,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.26582303643226624,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1322,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.4341706931591034,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1944,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3172090947628021,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0976,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.29426926374435425,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1136,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.2985455095767975,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1083,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.24896445870399475,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1035,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.09732979536056519,
      "eval_runtime": 33.3429,
      "eval_samples_per_second": 1.35,
      "eval_steps_per_second": 1.35,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.2638566493988037,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1195,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.33488255739212036,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0988,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.1871066838502884,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.081,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.21633964776992798,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0933,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.22650441527366638,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0944,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.27795323729515076,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0921,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.1986841857433319,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0757,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.4019611179828644,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.096,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.25638747215270996,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0857,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.2488611936569214,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0832,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.07449408620595932,
      "eval_runtime": 33.384,
      "eval_samples_per_second": 1.348,
      "eval_steps_per_second": 1.348,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.2547208070755005,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0765,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.24872475862503052,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0824,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.2691059708595276,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0809,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.30335408449172974,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0726,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3296601474285126,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.087,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3648730516433716,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0605,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.31005141139030457,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0888,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.2493203580379486,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0649,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.2655886709690094,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0874,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.2251734584569931,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0682,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.06475568562746048,
      "eval_runtime": 33.5739,
      "eval_samples_per_second": 1.34,
      "eval_steps_per_second": 1.34,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4998580515384674,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1123,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.20724184811115265,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0561,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.20959147810935974,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0607,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.2903861999511719,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0715,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.22137732803821564,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0618,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.20143303275108337,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0511,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3506109416484833,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0699,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.24251845479011536,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0713,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.24824124574661255,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0629,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3177408277988434,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0573,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.05842459574341774,
      "eval_runtime": 33.6467,
      "eval_samples_per_second": 1.337,
      "eval_steps_per_second": 1.337,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.2138853222131729,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0544,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2515881657600403,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0564,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.22868186235427856,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0744,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.21388305723667145,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0492,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.23071438074111938,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0584,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.35726767778396606,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0649,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.21322651207447052,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0538,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.4072442650794983,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0584,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2884412109851837,
      "learning_rate": 5e-05,
      "loss": 0.0596,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.19641831517219543,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0587,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.05657793581485748,
      "eval_runtime": 33.6041,
      "eval_samples_per_second": 1.339,
      "eval_steps_per_second": 1.339,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.26623716950416565,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0569,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.2026822417974472,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0473,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.225466787815094,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0584,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.18842445313930511,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0477,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.26801425218582153,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0551,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.41480809450149536,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0964,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.18684034049510956,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0494,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.22116324305534363,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0446,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.16841326653957367,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0489,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.20607370138168335,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0482,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.05409104377031326,
      "eval_runtime": 33.474,
      "eval_samples_per_second": 1.344,
      "eval_steps_per_second": 1.344,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2047753632068634,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0387,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.19060064852237701,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0454,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.1896040141582489,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0487,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.32006198167800903,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.05,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.21525046229362488,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0393,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.2281985878944397,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0533,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.17396704852581024,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0443,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.25189152359962463,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0473,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.2589864432811737,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0437,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.23333081603050232,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0567,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.05488782376050949,
      "eval_runtime": 33.9566,
      "eval_samples_per_second": 1.325,
      "eval_steps_per_second": 1.325,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.24443674087524414,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0553,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.24234531819820404,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0485,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.22655388712882996,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0436,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.20061157643795013,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0452,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.17764154076576233,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0471,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.17860907316207886,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0395,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.25244444608688354,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0482,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.5204274654388428,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0617,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2649965286254883,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0508,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.18821243941783905,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0441,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05232510715723038,
      "eval_runtime": 33.9471,
      "eval_samples_per_second": 1.326,
      "eval_steps_per_second": 1.326,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.3393254578113556,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0573,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.4414481818675995,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0854,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.21363762021064758,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0411,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.18734785914421082,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0355,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.18587791919708252,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0455,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.17148074507713318,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0323,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.19548922777175903,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0433,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.187666654586792,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0418,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.1861037015914917,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0433,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.2393113672733307,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0487,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.05202333629131317,
      "eval_runtime": 31.1511,
      "eval_samples_per_second": 1.445,
      "eval_steps_per_second": 1.445,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.15231628715991974,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.04,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.14807255566120148,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0365,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.1760508120059967,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0468,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.18777866661548615,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0442,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.18296711146831512,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0481,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.18189838528633118,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0462,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.19102239608764648,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0408,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.1832924783229828,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0487,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.1657048910856247,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0384,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.18505889177322388,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0487,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05186542496085167,
      "eval_runtime": 30.3117,
      "eval_samples_per_second": 1.485,
      "eval_steps_per_second": 1.485,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.17708715796470642,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0452,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.1928071677684784,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0459,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.19813640415668488,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0509,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1988469809293747,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0439,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.15975457429885864,
      "learning_rate": 0.0,
      "loss": 0.0403,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.7251051914244915e+17,
      "train_loss": 0.09884123867750168,
      "train_runtime": 6201.0589,
      "train_samples_per_second": 0.327,
      "train_steps_per_second": 0.02
    }
  ],
  "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": 1.7251051914244915e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}