{
  "best_metric": 0.057855527848005295,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold3/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": 0.43872907757759094,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3538,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5765560865402222,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.4287,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5987914800643921,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3868,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.4892619550228119,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3734,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.46643370389938354,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3679,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5569127798080444,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3842,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5182462334632874,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3544,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.496831476688385,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3267,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.4914007782936096,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3522,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.4265078008174896,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2701,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.2549773156642914,
      "eval_runtime": 33.5154,
      "eval_samples_per_second": 1.343,
      "eval_steps_per_second": 1.343,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.3845345377922058,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2177,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.46175315976142883,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2558,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.45730653405189514,
      "learning_rate": 0.0001,
      "loss": 0.2209,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.40768519043922424,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1989,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.43529772758483887,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1948,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.4391089081764221,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1771,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.4091953933238983,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1691,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3098650872707367,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1548,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.43342655897140503,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1551,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.28990423679351807,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1363,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.139180526137352,
      "eval_runtime": 33.5267,
      "eval_samples_per_second": 1.342,
      "eval_steps_per_second": 1.342,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.3364715576171875,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1371,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.3973502218723297,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1415,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.32426103949546814,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1133,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4437778890132904,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1318,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.309876024723053,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1257,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.98726487159729,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2076,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.27744409441947937,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1107,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.28345128893852234,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1279,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.2953401803970337,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1198,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.32110661268234253,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1012,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10243012011051178,
      "eval_runtime": 33.2568,
      "eval_samples_per_second": 1.353,
      "eval_steps_per_second": 1.353,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.2970160245895386,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1009,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.3055447041988373,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1049,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.21210183203220367,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0801,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.4238249957561493,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1182,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.25568047165870667,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.093,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.29029378294944763,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0834,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.24616555869579315,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.1008,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.2167835384607315,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0749,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.2983323037624359,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0842,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.31312185525894165,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0887,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08230571448802948,
      "eval_runtime": 33.5498,
      "eval_samples_per_second": 1.341,
      "eval_steps_per_second": 1.341,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.19386306405067444,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0624,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.31059572100639343,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0733,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.22865495085716248,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0698,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.24698993563652039,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0887,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3261677324771881,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.073,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.250406950712204,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0657,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.25181251764297485,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0739,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.3292807340621948,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0789,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.21894961595535278,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.067,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.46411725878715515,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0817,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.0711514800786972,
      "eval_runtime": 33.4198,
      "eval_samples_per_second": 1.347,
      "eval_steps_per_second": 1.347,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4228726029396057,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1035,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.24060393869876862,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0587,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.27049294114112854,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.056,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4131258726119995,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0652,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.1956382691860199,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0516,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.3911266624927521,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0689,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.30997759103775024,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0799,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.21100758016109467,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0587,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2619315981864929,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0739,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.3173605501651764,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.059,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06486237049102783,
      "eval_runtime": 33.0237,
      "eval_samples_per_second": 1.363,
      "eval_steps_per_second": 1.363,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.4663178622722626,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0779,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.205601304769516,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0461,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.24373941123485565,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0569,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.25226688385009766,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.05,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.24552692472934723,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0521,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.2296784520149231,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0658,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.22731678187847137,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0581,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.2066715806722641,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.053,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.25149860978126526,
      "learning_rate": 5e-05,
      "loss": 0.0634,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.351080060005188,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.049,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.061878032982349396,
      "eval_runtime": 33.6656,
      "eval_samples_per_second": 1.337,
      "eval_steps_per_second": 1.337,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.22770968079566956,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0576,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.24687135219573975,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0534,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.1623242348432541,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0408,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.2659016251564026,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0691,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.2567993402481079,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0588,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.42135751247406006,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0915,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2453581839799881,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0506,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.19938619434833527,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.05,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.18165546655654907,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0396,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.2509499788284302,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0601,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.059784527868032455,
      "eval_runtime": 33.3869,
      "eval_samples_per_second": 1.348,
      "eval_steps_per_second": 1.348,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.24859386682510376,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0524,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.22265814244747162,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0499,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.20550431311130524,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0466,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.18201954662799835,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0418,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.3383719027042389,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0444,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.23454077541828156,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0534,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.21181105077266693,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0378,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.18853436410427094,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0424,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.20674189925193787,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0436,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.2574480175971985,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0516,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.059570278972387314,
      "eval_runtime": 33.8094,
      "eval_samples_per_second": 1.331,
      "eval_steps_per_second": 1.331,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.24527369439601898,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0582,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.1810523271560669,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0414,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.2509377896785736,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0524,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.21463577449321747,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0516,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.2788424491882324,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0604,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.2470029592514038,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.046,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.1849908083677292,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0438,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.24283722043037415,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0392,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.27562907338142395,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0481,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.19304096698760986,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0378,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05850343033671379,
      "eval_runtime": 33.9632,
      "eval_samples_per_second": 1.325,
      "eval_steps_per_second": 1.325,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.22554069757461548,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.053,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.30230197310447693,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0659,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.19100959599018097,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0398,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.18058200180530548,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0371,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.2269684225320816,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0515,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.17553439736366272,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.04,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.17995917797088623,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0367,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.19451750814914703,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0552,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.24076087772846222,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0474,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.1976129412651062,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0456,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.058137014508247375,
      "eval_runtime": 34.0766,
      "eval_samples_per_second": 1.321,
      "eval_steps_per_second": 1.321,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.18842600286006927,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0337,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.1806812286376953,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0328,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.2175861895084381,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.045,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.22417177259922028,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0558,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.21496397256851196,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.037,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.18527212738990784,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0372,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.20612825453281403,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0501,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.15812154114246368,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0373,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.19522911310195923,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0491,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.18593372404575348,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.046,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.057855527848005295,
      "eval_runtime": 33.8522,
      "eval_samples_per_second": 1.329,
      "eval_steps_per_second": 1.329,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.20006082952022552,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0399,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.16816085577011108,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0422,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.17069809138774872,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0407,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.18310150504112244,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0348,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.29563766717910767,
      "learning_rate": 0.0,
      "loss": 0.0465,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.7198491055239987e+17,
      "train_loss": 0.09856468495726585,
      "train_runtime": 5992.0416,
      "train_samples_per_second": 0.338,
      "train_steps_per_second": 0.021
    }
  ],
  "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": 1.7198491055239987e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}