{
  "best_metric": 0.080467090010643,
  "best_model_checkpoint": "saves/psy-course-info-chain/Llama3-OpenBioLLM-8B/train/fold10/checkpoint-70",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 1.151665449142456,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3145,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.9972645044326782,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2579,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.9717741012573242,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2757,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 1.042287826538086,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3534,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.1523590087890625,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3839,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.1807069778442383,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3633,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.0031616687774658,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2488,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.2466661930084229,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2157,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.1059529781341553,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2556,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.9460064172744751,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1852,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.19416195154190063,
      "eval_runtime": 21.4786,
      "eval_samples_per_second": 2.095,
      "eval_steps_per_second": 2.095,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.0137423276901245,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2008,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.9474741220474243,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1851,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.7905036807060242,
      "learning_rate": 0.0001,
      "loss": 0.201,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.7932561635971069,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1753,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.8369474411010742,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2329,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.712482750415802,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1236,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.8241578340530396,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1499,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.6253908276557922,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1457,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.529045045375824,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.0863,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.5808553695678711,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1406,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.11978381127119064,
      "eval_runtime": 21.3776,
      "eval_samples_per_second": 2.105,
      "eval_steps_per_second": 2.105,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.5620546936988831,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1382,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.5028219819068909,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1092,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.5419264435768127,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0973,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.5416827201843262,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0786,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5326511859893799,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0748,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 1.2484720945358276,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2631,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.5504987239837646,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1221,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.5647097826004028,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1451,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.7091497778892517,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1128,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.5386999249458313,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0914,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10202428698539734,
      "eval_runtime": 21.4235,
      "eval_samples_per_second": 2.1,
      "eval_steps_per_second": 2.1,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.5247892141342163,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0912,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.41631463170051575,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0979,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.8200529217720032,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1317,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.5310624837875366,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0627,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.4706062078475952,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0756,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.6458783745765686,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1168,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.4390260577201843,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0968,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.4977874159812927,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0621,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.4581007659435272,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0761,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.6345964670181274,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1443,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.09560000896453857,
      "eval_runtime": 21.3699,
      "eval_samples_per_second": 2.106,
      "eval_steps_per_second": 2.106,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6047734022140503,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0791,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.532657265663147,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1083,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.4287898540496826,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0796,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.6789954900741577,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0997,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.45323219895362854,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0539,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.49983036518096924,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.091,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.3934876322746277,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0704,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.4937668740749359,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0798,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.41331249475479126,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0645,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.5399277210235596,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.082,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08480622619390488,
      "eval_runtime": 21.3804,
      "eval_samples_per_second": 2.105,
      "eval_steps_per_second": 2.105,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 1.3419924974441528,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1196,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.3526543378829956,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0552,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.5716381669044495,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0713,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4506434500217438,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0708,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.43828216195106506,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0701,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.5180737972259521,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0768,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.5429201126098633,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1308,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.4827474057674408,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0632,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.668199896812439,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0528,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.45363757014274597,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0707,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.08135872334241867,
      "eval_runtime": 21.3842,
      "eval_samples_per_second": 2.104,
      "eval_steps_per_second": 2.104,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.37034544348716736,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0687,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.4147774875164032,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0626,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.4404706656932831,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0576,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.5096293687820435,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0705,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.4868890941143036,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.069,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.4319659471511841,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0427,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.406623512506485,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.054,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.39108678698539734,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0527,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.554020345211029,
      "learning_rate": 5e-05,
      "loss": 0.0742,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.580782949924469,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0856,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.080467090010643,
      "eval_runtime": 21.4064,
      "eval_samples_per_second": 2.102,
      "eval_steps_per_second": 2.102,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.43095502257347107,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0378,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.39447301626205444,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0588,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.4076079726219177,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0409,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.3989277482032776,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0388,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.45276713371276855,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0345,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.6707313060760498,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0637,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.46799662709236145,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0511,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.6991556882858276,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0702,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.4488993287086487,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0511,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.5677701234817505,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.036,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.08287203311920166,
      "eval_runtime": 21.4222,
      "eval_samples_per_second": 2.101,
      "eval_steps_per_second": 2.101,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.36043116450309753,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0232,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.4948276877403259,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0612,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.4589063227176666,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0477,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5372574329376221,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0479,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.5621379017829895,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0358,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.8877462148666382,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0545,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.38995346426963806,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0599,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.42967477440834045,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0372,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.3516727089881897,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0278,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.5127808451652527,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0549,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.08548722416162491,
      "eval_runtime": 21.3936,
      "eval_samples_per_second": 2.103,
      "eval_steps_per_second": 2.103,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.4617702066898346,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0535,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.5598379373550415,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0437,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.45547932386398315,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0314,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.38878926634788513,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0246,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.6099169254302979,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0555,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.4386748671531677,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0451,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.5089120864868164,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.048,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.567168653011322,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0594,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.587039589881897,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0613,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.49638357758522034,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0341,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.0823778361082077,
      "eval_runtime": 21.431,
      "eval_samples_per_second": 2.1,
      "eval_steps_per_second": 2.1,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.6147500276565552,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0551,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.8957232236862183,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0876,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.34106171131134033,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0243,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.31608477234840393,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0263,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.3211493194103241,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0251,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.48900917172431946,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0389,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.418064683675766,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0281,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.3775902986526489,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0334,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.4342731535434723,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0286,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.4076210558414459,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0355,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.08354898542165756,
      "eval_runtime": 21.4314,
      "eval_samples_per_second": 2.1,
      "eval_steps_per_second": 2.1,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.44390958547592163,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0293,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.521616518497467,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0489,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.4781332015991211,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.042,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.44009116291999817,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.057,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.7173508405685425,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.038,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.43728527426719666,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0357,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.6256703734397888,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0269,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.6550281643867493,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0611,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.5331128835678101,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0384,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.4842231869697571,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.048,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08340723067522049,
      "eval_runtime": 21.4083,
      "eval_samples_per_second": 2.102,
      "eval_steps_per_second": 2.102,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.3888583183288574,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0204,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.3363063335418701,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0417,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.4593239426612854,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0371,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.4591008126735687,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0391,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.347429484128952,
      "learning_rate": 0.0,
      "loss": 0.0329,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3285578941359718e+17,
      "train_loss": 0.09023197002708912,
      "train_runtime": 3707.8482,
      "train_samples_per_second": 0.546,
      "train_steps_per_second": 0.034
    }
  ],
  "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": 1.3285578941359718e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}