{
  "best_metric": 0.14292015135288239,
  "best_model_checkpoint": "saves/psy-course-info/MentaLLaMA-chat-7B/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": 0.8422476053237915,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.0487,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.9051148295402527,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0209,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.9381813406944275,
      "learning_rate": 2.307692307692308e-05,
      "loss": 1.1013,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.8974120616912842,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.9925,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.937398374080658,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.144,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.0170984268188477,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.0255,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 1.130664587020874,
      "learning_rate": 5.384615384615385e-05,
      "loss": 1.0834,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 1.1324275732040405,
      "learning_rate": 6.153846153846155e-05,
      "loss": 1.0371,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.1058732271194458,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.835,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 1.279205083847046,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.7489,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.6546934247016907,
      "eval_runtime": 22.3342,
      "eval_samples_per_second": 2.015,
      "eval_steps_per_second": 2.015,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 1.231115698814392,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.6589,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.9041948318481445,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.5391,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.6066773533821106,
      "learning_rate": 0.0001,
      "loss": 0.396,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.6248027682304382,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.4533,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.602263331413269,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.3779,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.5616060495376587,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.374,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.4809941053390503,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.2799,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.45627954602241516,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.2759,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.47322168946266174,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.2409,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.37448379397392273,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.2511,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.26364943385124207,
      "eval_runtime": 22.3262,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 2.016,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.4775635600090027,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.316,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.3825429677963257,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.2388,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.46930068731307983,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.255,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.4243314862251282,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.248,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.5047178864479065,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.3113,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.8807996511459351,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.4111,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3662039339542389,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1974,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.42856699228286743,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.245,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.45199066400527954,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2399,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.35965853929519653,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1969,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.19759851694107056,
      "eval_runtime": 22.3639,
      "eval_samples_per_second": 2.012,
      "eval_steps_per_second": 2.012,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.33116674423217773,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.1616,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.3540390431880951,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1805,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.3818235993385315,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1624,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.42187103629112244,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2047,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.39765650033950806,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1515,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.3528044819831848,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1846,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.4173314869403839,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.2213,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.38787856698036194,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1411,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.3698059320449829,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1522,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.39762231707572937,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.2206,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.17092598974704742,
      "eval_runtime": 22.3716,
      "eval_samples_per_second": 2.011,
      "eval_steps_per_second": 2.011,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.3720499873161316,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1414,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.35749444365501404,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.1736,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.2914219796657562,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.1502,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.32585427165031433,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1526,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.3194795250892639,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1494,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.39063727855682373,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.1879,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.2694467008113861,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1711,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.4016968905925751,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1974,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.32781171798706055,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1344,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.3214917778968811,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.1426,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.1621260643005371,
      "eval_runtime": 22.3816,
      "eval_samples_per_second": 2.011,
      "eval_steps_per_second": 2.011,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.7649836540222168,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.3342,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.28408119082450867,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1095,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.3678349554538727,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1384,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3446773588657379,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1228,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.3449733853340149,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1399,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.5579468607902527,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.162,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.3235398828983307,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1407,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.35329848527908325,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1415,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.36896228790283203,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1794,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.31548261642456055,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.1305,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.1542777568101883,
      "eval_runtime": 22.3743,
      "eval_samples_per_second": 2.011,
      "eval_steps_per_second": 2.011,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.39681529998779297,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1571,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.37882083654403687,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1374,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.38282206654548645,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1292,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.35533228516578674,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.1122,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.22896414995193481,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0724,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.3898186683654785,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.1696,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.42083269357681274,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1532,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.3295520842075348,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.103,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.44458335638046265,
      "learning_rate": 5e-05,
      "loss": 0.1352,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.27208536863327026,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0773,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.15219633281230927,
      "eval_runtime": 22.379,
      "eval_samples_per_second": 2.011,
      "eval_steps_per_second": 2.011,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.30918893218040466,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.1373,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.2998526990413666,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.113,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.3436013162136078,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.1298,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.3602356016635895,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1279,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.3665788769721985,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.1553,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.691739559173584,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1902,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.43758055567741394,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1331,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.3484525680541992,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1265,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.4110882878303528,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.1173,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.33643531799316406,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0848,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.1463339924812317,
      "eval_runtime": 22.3844,
      "eval_samples_per_second": 2.01,
      "eval_steps_per_second": 2.01,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.29669189453125,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1108,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.41252458095550537,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.1523,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.4312768578529358,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1146,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.35198500752449036,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.1208,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.34211111068725586,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0928,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.3491601049900055,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0859,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.358417272567749,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0999,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.374683141708374,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1056,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.345869779586792,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0825,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.4319433867931366,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1227,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.14589153230190277,
      "eval_runtime": 22.3951,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.30522212386131287,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.1082,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.30712464451789856,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0771,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.3888234794139862,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0949,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.46743959188461304,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.1441,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.4755515456199646,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.142,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.3827289938926697,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1065,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.39248624444007874,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1131,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.30873000621795654,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1009,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.4663596451282501,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0988,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.3064710199832916,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.085,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.14458218216896057,
      "eval_runtime": 22.4272,
      "eval_samples_per_second": 2.006,
      "eval_steps_per_second": 2.006,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.3911544680595398,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.6133930087089539,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1459,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.3166359066963196,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.1011,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.29334643483161926,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0827,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.3582095205783844,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0612,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.3122091591358185,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0894,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.3279852867126465,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0908,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.34310492873191833,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.1136,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.3044549524784088,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0889,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.3403724730014801,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.1099,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.14361289143562317,
      "eval_runtime": 22.4208,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 2.007,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.3872736990451813,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1072,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.3538377583026886,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.1022,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.31012803316116333,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0839,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.34009426832199097,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0902,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.39585646986961365,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.101,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.2982696294784546,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0703,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.3826141953468323,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.1398,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.3156748414039612,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.116,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.34730467200279236,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0935,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.3517928123474121,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.1193,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.14292015135288239,
      "eval_runtime": 22.4343,
      "eval_samples_per_second": 2.006,
      "eval_steps_per_second": 2.006,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.25127172470092773,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0778,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.4113193452358246,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.1122,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.295227587223053,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0973,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.38987869024276733,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.1006,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.3550569713115692,
      "learning_rate": 0.0,
      "loss": 0.0961,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.3980415377034445e+17,
      "train_loss": 0.229878327190876,
      "train_runtime": 4052.3329,
      "train_samples_per_second": 0.5,
      "train_steps_per_second": 0.031
    }
  ],
  "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": 1.3980415377034445e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}