{
  "best_metric": 0.018380094319581985,
  "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/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": 0.15302065014839172,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1343,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.16171559691429138,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1422,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.21235737204551697,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.175,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.13357385993003845,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.1262,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.1656055599451065,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.1309,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.21017052233219147,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.1559,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.19282130897045135,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.164,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.13714855909347534,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.121,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.14305219054222107,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.1224,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.10971210151910782,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1079,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.12371170520782471,
      "eval_runtime": 27.496,
      "eval_samples_per_second": 1.637,
      "eval_steps_per_second": 1.637,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.10976401716470718,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1002,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.0844080001115799,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0787,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.08359840512275696,
      "learning_rate": 0.0001,
      "loss": 0.081,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.07813932001590729,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.0853,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.09291302412748337,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.0807,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.06838700920343399,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.0585,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.0799289271235466,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.065,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.08614151179790497,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.0622,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.0771934911608696,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.0637,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.06453464925289154,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.0481,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.05983788147568703,
      "eval_runtime": 27.0985,
      "eval_samples_per_second": 1.661,
      "eval_steps_per_second": 1.661,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.09980370849370956,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.06,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.08475111424922943,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0535,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.0963137298822403,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.0539,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.06946562975645065,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0477,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.06244807690382004,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0417,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.12603476643562317,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.0647,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.05846944823861122,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0357,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.051478784531354904,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0381,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.0632048100233078,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0362,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.05464872345328331,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0268,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.033964842557907104,
      "eval_runtime": 27.1208,
      "eval_samples_per_second": 1.659,
      "eval_steps_per_second": 1.659,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.06514594703912735,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.031,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.06183492764830589,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0329,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.05125824362039566,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0218,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.06549733132123947,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.027,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.0605190210044384,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0206,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.062435973435640335,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0288,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.058545876294374466,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0242,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.056647419929504395,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0284,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.06608887761831284,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0306,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.0640529915690422,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0273,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.026377426460385323,
      "eval_runtime": 27.1206,
      "eval_samples_per_second": 1.659,
      "eval_steps_per_second": 1.659,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.0527876541018486,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0212,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.05133755877614021,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0176,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.06008387356996536,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0251,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.05968204140663147,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0249,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.033979032188653946,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0152,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.05249929428100586,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0207,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.045286841690540314,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0221,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.056835971772670746,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0256,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.05012015998363495,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0208,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.048069827258586884,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0185,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.022256724536418915,
      "eval_runtime": 27.1528,
      "eval_samples_per_second": 1.657,
      "eval_steps_per_second": 1.657,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.08603884279727936,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0255,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.04315409064292908,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0188,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.037481315433979034,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0171,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.04968979209661484,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0181,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.04279967024922371,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0127,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.0425821878015995,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0166,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.03778501972556114,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0166,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.04220494255423546,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0167,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.051419638097286224,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0194,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.0585457906126976,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0193,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.02047140523791313,
      "eval_runtime": 27.1167,
      "eval_samples_per_second": 1.659,
      "eval_steps_per_second": 1.659,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.042119674384593964,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0147,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.05152701213955879,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0166,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.04182899370789528,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0135,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.052869729697704315,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.02,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.06037428602576256,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0175,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.05000188946723938,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0159,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.04615490511059761,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0177,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.048797909170389175,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0169,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.05034763365983963,
      "learning_rate": 5e-05,
      "loss": 0.0136,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.0487942099571228,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0151,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.01994810812175274,
      "eval_runtime": 27.1363,
      "eval_samples_per_second": 1.658,
      "eval_steps_per_second": 1.658,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.04914839193224907,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0187,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.04254300519824028,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0163,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.054740406572818756,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0178,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.06606375426054001,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0208,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.046502694487571716,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0159,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.07648506760597229,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0299,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.038912709802389145,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0122,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.037170540541410446,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0148,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.04788689315319061,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0118,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.04686618596315384,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0184,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.018717244267463684,
      "eval_runtime": 27.122,
      "eval_samples_per_second": 1.659,
      "eval_steps_per_second": 1.659,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.04185900837182999,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0158,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.034399326890707016,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0103,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.03679003193974495,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0135,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.048480838537216187,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0121,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.05045546963810921,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0148,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.04279428347945213,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0152,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.039656057953834534,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0133,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.03422383964061737,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0164,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.032390933483839035,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.012,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.04282541200518608,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0123,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.01881367154419422,
      "eval_runtime": 27.1533,
      "eval_samples_per_second": 1.657,
      "eval_steps_per_second": 1.657,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.0406196229159832,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0177,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.04053223505616188,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0136,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.035914190113544464,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0122,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.035513900220394135,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0157,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.049819763749837875,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0173,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.06253393739461899,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0174,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.035533446818590164,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0132,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.03573863208293915,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0122,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.03827377408742905,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.014,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.045009270310401917,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0121,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.018385054543614388,
      "eval_runtime": 27.1526,
      "eval_samples_per_second": 1.657,
      "eval_steps_per_second": 1.657,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.051141928881406784,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0156,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.08626056462526321,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0226,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.0381922610104084,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0139,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.03440139815211296,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0093,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.04220060631632805,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0147,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.047010231763124466,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0132,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.036207061260938644,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0123,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.03673166409134865,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0121,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.043294817209243774,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.015,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.039619337767362595,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0095,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.018397420644760132,
      "eval_runtime": 27.1681,
      "eval_samples_per_second": 1.656,
      "eval_steps_per_second": 1.656,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.04072614014148712,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0131,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.055798210203647614,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0139,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.039506252855062485,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.015,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.0429210364818573,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0113,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.0426989309489727,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.013,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.048751384019851685,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.015,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.05265915021300316,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.013,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.04089773818850517,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0139,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.04871585965156555,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.019,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.034352779388427734,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.011,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.018380094319581985,
      "eval_runtime": 27.2155,
      "eval_samples_per_second": 1.653,
      "eval_steps_per_second": 1.653,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.03931261599063873,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0159,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.03714591637253761,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0124,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.03457983583211899,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0102,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.04189521446824074,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0148,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.04194777458906174,
      "learning_rate": 0.0,
      "loss": 0.0128,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.8334743535787213e+17,
      "train_loss": 0.033509917281568054,
      "train_runtime": 5004.178,
      "train_samples_per_second": 0.405,
      "train_steps_per_second": 0.025
    }
  ],
  "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": 1.8334743535787213e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}