{
  "best_metric": 0.08445564657449722,
  "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold5/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": 0.19873352348804474,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2279,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.19135093688964844,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2097,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.195903018116951,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2678,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.16618940234184265,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2977,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.22122569382190704,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2522,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.19768942892551422,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.2155,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.19557900726795197,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3459,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.1716621220111847,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.2505,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.17522573471069336,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2537,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.15652352571487427,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2039,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.19913546741008759,
      "eval_runtime": 22.3003,
      "eval_samples_per_second": 2.018,
      "eval_steps_per_second": 2.018,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.14066259562969208,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1301,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.12863866984844208,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.182,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.11643149703741074,
      "learning_rate": 0.0001,
      "loss": 0.1146,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.08969127386808395,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2056,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.09307601302862167,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1562,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.1174452155828476,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1146,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.10195641964673996,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.184,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.10689202696084976,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1486,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.09121159464120865,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1271,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.09564100950956345,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1517,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1345672756433487,
      "eval_runtime": 22.3099,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.09878810495138168,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.17,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.11947475373744965,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.0929,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.1149665042757988,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1266,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.0947696641087532,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.146,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.08536741882562637,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.0832,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.14740338921546936,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1828,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.06886528432369232,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1278,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.07011701166629791,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.0975,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.07124074548482895,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0964,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.07033799588680267,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1017,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10418377071619034,
      "eval_runtime": 22.3166,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 2.016,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.07948324084281921,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0778,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.07857206463813782,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1152,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.07876370847225189,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0869,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.08307764679193497,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1233,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.07968820631504059,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1159,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.09034614264965057,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0917,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.08779443055391312,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0838,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.08167281001806259,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1377,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.09639780968427658,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.074,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.06817444413900375,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.1168,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.09589631855487823,
      "eval_runtime": 22.3188,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 2.016,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.08402331173419952,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.097,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.08021535724401474,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.094,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.06876428425312042,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0724,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.06988049298524857,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1633,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.062164779752492905,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.046,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.06028977036476135,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0717,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.06709367781877518,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.071,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.06051813066005707,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1172,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.087796151638031,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1358,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.05886015295982361,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0689,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.09081750363111496,
      "eval_runtime": 22.3083,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.13859763741493225,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1633,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.06950072199106216,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.1452,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.06361917406320572,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0634,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.08428295701742172,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1044,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.07331045717000961,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1347,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.06775527447462082,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.073,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.08314106613397598,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1168,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.08215145766735077,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.1297,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.07548442482948303,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0369,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.06501203775405884,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0824,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.08831462264060974,
      "eval_runtime": 22.3028,
      "eval_samples_per_second": 2.018,
      "eval_steps_per_second": 2.018,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.066471628844738,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0849,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.07570913434028625,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0608,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.0699690654873848,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.1321,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.06023552641272545,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0837,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.061797093600034714,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0972,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.06888198852539062,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0278,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.0992245078086853,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1057,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.0590776652097702,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0528,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.06296297162771225,
      "learning_rate": 5e-05,
      "loss": 0.0462,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.06537173688411713,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0818,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.08643952012062073,
      "eval_runtime": 22.3049,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.060881391167640686,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0504,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.06462173908948898,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1368,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.052473749965429306,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0378,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.05805649235844612,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0832,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.06838543713092804,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0536,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.1145360916852951,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1427,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.07607802003622055,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0504,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.06236179545521736,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1191,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.053727082908153534,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0909,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.07088236510753632,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0834,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.0854584351181984,
      "eval_runtime": 22.2765,
      "eval_samples_per_second": 2.02,
      "eval_steps_per_second": 2.02,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.0686681792140007,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.1314,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.051756151020526886,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0138,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.07298314571380615,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0929,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.0642247423529625,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0747,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.05583948642015457,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0459,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.04674788564443588,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0535,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.06361730396747589,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0627,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.054269008338451385,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0816,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.06462159007787704,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0993,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.07387321442365646,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.061,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.0851416140794754,
      "eval_runtime": 22.267,
      "eval_samples_per_second": 2.021,
      "eval_steps_per_second": 2.021,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.06755466014146805,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0453,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.054175738245248795,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0724,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.06587906926870346,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0792,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.07584559172391891,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0727,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.06739196926355362,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.063,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.07475075125694275,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1221,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.06914909183979034,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0946,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.07810596376657486,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1459,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.07366335391998291,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1165,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.06215855851769447,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0236,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.08476907014846802,
      "eval_runtime": 22.2508,
      "eval_samples_per_second": 2.022,
      "eval_steps_per_second": 2.022,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.08284192532300949,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0859,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.12411859631538391,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1522,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.06989350914955139,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.1115,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.06105631962418556,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0417,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.07013764977455139,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.1134,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.06461846828460693,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.061,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.06263217329978943,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0898,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.0546736940741539,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.023,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.07552754133939743,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0736,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.05515694618225098,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0572,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.0844709649682045,
      "eval_runtime": 22.246,
      "eval_samples_per_second": 2.023,
      "eval_steps_per_second": 2.023,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.04992398992180824,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0671,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.05586286261677742,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0664,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.08252695202827454,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0444,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.06904689222574234,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.092,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.07393740862607956,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0633,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.05798826366662979,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0232,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.07497933506965637,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0994,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.06766030937433243,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0369,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.07671058177947998,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0841,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.07792951911687851,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.1141,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.08445564657449722,
      "eval_runtime": 22.2286,
      "eval_samples_per_second": 2.024,
      "eval_steps_per_second": 2.024,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.06518019735813141,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0974,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.059662818908691406,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0572,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.0677414983510971,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0664,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.07458758354187012,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.1378,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.05868929624557495,
      "learning_rate": 0.0,
      "loss": 0.0765,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4325999912574157e+17,
      "train_loss": 0.10706765554845334,
      "train_runtime": 3446.7313,
      "train_samples_per_second": 0.588,
      "train_steps_per_second": 0.036
    }
  ],
  "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": 1.4325999912574157e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}