{
  "best_metric": 0.06382926553487778,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold1/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": 0.3751373291015625,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3193,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.4413926899433136,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3871,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.4548482894897461,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.3994,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.3753758668899536,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3376,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.41474097967147827,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.341,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.4442629814147949,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3472,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.4046342968940735,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2922,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.43675675988197327,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3189,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.35987773537635803,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.3015,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.6151788830757141,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2997,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.27861183881759644,
      "eval_runtime": 26.9718,
      "eval_samples_per_second": 1.668,
      "eval_steps_per_second": 1.668,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.602597177028656,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2762,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.45764604210853577,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2217,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.4448660612106323,
      "learning_rate": 0.0001,
      "loss": 0.2466,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.3779691159725189,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2313,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3031979501247406,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.2022,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.32314398884773254,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1895,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.37541085481643677,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1849,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.3200841248035431,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1738,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.354908287525177,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.163,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.3302294909954071,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1565,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.15649954974651337,
      "eval_runtime": 26.9212,
      "eval_samples_per_second": 1.672,
      "eval_steps_per_second": 1.672,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.27806010842323303,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1509,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.29654842615127563,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1293,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.3867642879486084,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.132,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4144921898841858,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1291,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.4134954512119293,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.145,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5466923117637634,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2045,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3219594955444336,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1135,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.23663724958896637,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1059,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.27023935317993164,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1241,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.28588056564331055,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0969,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.11529618501663208,
      "eval_runtime": 26.9142,
      "eval_samples_per_second": 1.672,
      "eval_steps_per_second": 1.672,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.2501027286052704,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0855,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.24449241161346436,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.101,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.3006822168827057,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1129,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.31985530257225037,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0976,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.34030166268348694,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1086,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.34291812777519226,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0946,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.20636491477489471,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0731,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.291526198387146,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0998,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.2789583206176758,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0961,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.33451035618782043,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.091,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.09263183921575546,
      "eval_runtime": 26.9537,
      "eval_samples_per_second": 1.67,
      "eval_steps_per_second": 1.67,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.29477977752685547,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0912,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.26489514112472534,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0747,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3357336223125458,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0823,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.2431459277868271,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0766,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.31044304370880127,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0788,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.25586599111557007,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0758,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2753075063228607,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0737,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.24979501962661743,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0597,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.2392245978116989,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0801,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.22869057953357697,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0647,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.08237497508525848,
      "eval_runtime": 26.9333,
      "eval_samples_per_second": 1.671,
      "eval_steps_per_second": 1.671,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.7654573917388916,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.115,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.2607990801334381,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0573,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.21061500906944275,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0506,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.4514831304550171,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0788,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.38376209139823914,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0554,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.20328734815120697,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0562,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.21448568999767303,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0686,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.2620505392551422,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0517,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.2610226273536682,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0594,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.24887007474899292,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0644,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07354918867349625,
      "eval_runtime": 26.9267,
      "eval_samples_per_second": 1.671,
      "eval_steps_per_second": 1.671,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.22720755636692047,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0665,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.24492129683494568,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0754,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.19352273643016815,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0568,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.3106859028339386,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0549,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.28062766790390015,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0806,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.14284111559391022,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0427,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2358120083808899,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0674,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.23373115062713623,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0646,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.21478624641895294,
      "learning_rate": 5e-05,
      "loss": 0.0465,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.20883594453334808,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0581,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06981310248374939,
      "eval_runtime": 26.9212,
      "eval_samples_per_second": 1.672,
      "eval_steps_per_second": 1.672,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.18839380145072937,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0478,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.26379862427711487,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0672,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.16544681787490845,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0607,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.1930951178073883,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0536,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.18506531417369843,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0591,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.3830253779888153,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1086,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.18167752027511597,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0489,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.20754455029964447,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0608,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.19427207112312317,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0506,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.18063730001449585,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0455,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06736921519041061,
      "eval_runtime": 26.9431,
      "eval_samples_per_second": 1.67,
      "eval_steps_per_second": 1.67,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.22500550746917725,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0447,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.21329432725906372,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0571,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.17836543917655945,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0453,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.20486213266849518,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0459,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.21644972264766693,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0471,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.21898981928825378,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0487,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.24306416511535645,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0529,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.23084181547164917,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0499,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.18299034237861633,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.045,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.2617104947566986,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0467,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06578466296195984,
      "eval_runtime": 26.9423,
      "eval_samples_per_second": 1.67,
      "eval_steps_per_second": 1.67,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.21765132248401642,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0568,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.2192198783159256,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0497,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.24346205592155457,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0487,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.1876707822084427,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0472,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.3032955825328827,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0542,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.21491743624210358,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.048,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.19251281023025513,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0513,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.19982850551605225,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.047,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.18531076610088348,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.047,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.17834027111530304,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0479,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06425812840461731,
      "eval_runtime": 26.9463,
      "eval_samples_per_second": 1.67,
      "eval_steps_per_second": 1.67,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.20841896533966064,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0594,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.33304062485694885,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0789,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.14293447136878967,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0355,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.20372606813907623,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0429,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.16863416135311127,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0453,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.15879668295383453,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0405,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.17416349053382874,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0476,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.15646155178546906,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0456,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.22114284336566925,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0571,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.1771191656589508,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0427,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06383614242076874,
      "eval_runtime": 26.9555,
      "eval_samples_per_second": 1.669,
      "eval_steps_per_second": 1.669,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.14602412283420563,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.039,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.20748545229434967,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0527,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.19688087701797485,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0486,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.17372861504554749,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0425,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.17414209246635437,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0505,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.19507907330989838,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0383,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.199944406747818,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0524,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.17430949211120605,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0376,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.2000775933265686,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0428,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.22385378181934357,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0577,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06382926553487778,
      "eval_runtime": 26.9709,
      "eval_samples_per_second": 1.668,
      "eval_steps_per_second": 1.668,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.18602363765239716,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0396,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.18225201964378357,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0478,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.1758757084608078,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0441,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.1525433361530304,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.038,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.1670604646205902,
      "learning_rate": 0.0,
      "loss": 0.0417,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.663137564251259e+17,
      "train_loss": 0.09969830414652825,
      "train_runtime": 4810.1308,
      "train_samples_per_second": 0.421,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.663137564251259e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}