{
  "best_metric": 0.06739914417266846,
  "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold2/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": 0.19077937304973602,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2338,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.17727194726467133,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2972,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.1859983205795288,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2317,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.1751106232404709,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.2946,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.18738967180252075,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2651,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.18814262747764587,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.2558,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.21018676459789276,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.2093,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.1821110099554062,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3403,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.18296223878860474,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2061,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.16537094116210938,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.1844,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.1829984486103058,
      "eval_runtime": 22.3199,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 2.016,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.14258871972560883,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.1666,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.116055428981781,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.1703,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.11263865977525711,
      "learning_rate": 0.0001,
      "loss": 0.1478,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.09919534623622894,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.152,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.10640931874513626,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1487,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.10122568160295486,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1584,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.09306957572698593,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.134,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.09648091346025467,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1563,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.09991016238927841,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.179,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.0870443657040596,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1185,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.1159573420882225,
      "eval_runtime": 22.3343,
      "eval_samples_per_second": 2.015,
      "eval_steps_per_second": 2.015,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.12216179072856903,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1378,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.10900968313217163,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.131,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.09788177907466888,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1267,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.09509879350662231,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1175,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.07913816720247269,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1185,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.1360471397638321,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.3032,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.060989461839199066,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0675,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.06774920970201492,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1693,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.06836458295583725,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1072,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.07043153792619705,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1092,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.0858113244175911,
      "eval_runtime": 22.3384,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.07222125679254532,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0845,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.075693778693676,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1642,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.07321791350841522,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1375,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.06815122067928314,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0684,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.07415533810853958,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0354,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.081488698720932,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0974,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.07327962666749954,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0843,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.0677095577120781,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.1439,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.07979962229728699,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1018,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.06939241290092468,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0995,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.07711561769247055,
      "eval_runtime": 22.3372,
      "eval_samples_per_second": 2.015,
      "eval_steps_per_second": 2.015,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.06919392943382263,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0538,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.0615607388317585,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.079,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.07704156637191772,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0911,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.0855034589767456,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1464,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.06922589987516403,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0858,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.06948332488536835,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0909,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.0712641030550003,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0985,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.07246934622526169,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0469,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.06269513815641403,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.1188,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.08746220171451569,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0472,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07317373156547546,
      "eval_runtime": 22.3371,
      "eval_samples_per_second": 2.015,
      "eval_steps_per_second": 2.015,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.1280466765165329,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1374,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.07242424786090851,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0809,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.09414707124233246,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1062,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.07751212269067764,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0604,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.06711921095848083,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1175,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.07885095477104187,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.1469,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.08243095129728317,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1168,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.07589109987020493,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0627,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.09104125201702118,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.1048,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.07193928956985474,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0496,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.07066290825605392,
      "eval_runtime": 22.313,
      "eval_samples_per_second": 2.017,
      "eval_steps_per_second": 2.017,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.06833218038082123,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0301,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.06492917984724045,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0887,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.06016537919640541,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.052,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.07493501156568527,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0575,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.07529838383197784,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1102,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.06590063869953156,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0616,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.07938098162412643,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0695,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.07568076997995377,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.1095,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.07372705638408661,
      "learning_rate": 5e-05,
      "loss": 0.0992,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.07286553829908371,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1027,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06911057978868484,
      "eval_runtime": 22.3177,
      "eval_samples_per_second": 2.016,
      "eval_steps_per_second": 2.016,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.06061169132590294,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0677,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.06704486161470413,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.1371,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.06215880438685417,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0889,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.06801719963550568,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0707,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.060576025396585464,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0512,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.12994828820228577,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0939,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.06527961790561676,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1218,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.07249095290899277,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1469,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.047334231436252594,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0381,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.06782688945531845,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0985,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06823357194662094,
      "eval_runtime": 22.2829,
      "eval_samples_per_second": 2.019,
      "eval_steps_per_second": 2.019,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.0564015693962574,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.063,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.06715361028909683,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0271,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.0604991614818573,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0707,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.06876682490110397,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0955,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.05650262162089348,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0652,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.05968635529279709,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.1037,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.05607614666223526,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0491,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.054088592529296875,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0635,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.066773921251297,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0999,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.07509192824363708,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0485,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06780579686164856,
      "eval_runtime": 22.2884,
      "eval_samples_per_second": 2.019,
      "eval_steps_per_second": 2.019,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.06333677470684052,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0889,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.0509658046066761,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0664,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.06007921323180199,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0653,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.06598193198442459,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0755,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.07450954616069794,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0992,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.07404863834381104,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.1128,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.0693865492939949,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0564,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.07623279094696045,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0872,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.07808290421962738,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.1072,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.064748115837574,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0836,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06749629229307175,
      "eval_runtime": 22.2654,
      "eval_samples_per_second": 2.021,
      "eval_steps_per_second": 2.021,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.08879992365837097,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0797,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.12393655627965927,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.1079,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.060529131442308426,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0558,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.05712978169322014,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0475,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.07743608951568604,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.157,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.056256335228681564,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0482,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.07397477328777313,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.13,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.0620802566409111,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0524,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.07110738009214401,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0896,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.05470067635178566,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0638,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06744737923145294,
      "eval_runtime": 22.2469,
      "eval_samples_per_second": 2.023,
      "eval_steps_per_second": 2.023,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.056704919785261154,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0503,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.062332309782505035,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0374,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.058511000126600266,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0254,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.07600726932287216,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1074,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.056519098579883575,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0138,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.06149820610880852,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0362,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.05897911265492439,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0772,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.06727366894483566,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0775,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.06633707135915756,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0787,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.08769124746322632,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.1399,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06739914417266846,
      "eval_runtime": 22.1885,
      "eval_samples_per_second": 2.028,
      "eval_steps_per_second": 2.028,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.05913535878062248,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0655,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.06610192358493805,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0978,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.059829652309417725,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0897,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.06724058836698532,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0994,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.0620194636285305,
      "learning_rate": 0.0,
      "loss": 0.0844,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4365073080170086e+17,
      "train_loss": 0.10746510825306177,
      "train_runtime": 3543.0104,
      "train_samples_per_second": 0.572,
      "train_steps_per_second": 0.035
    }
  ],
  "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": 1.4365073080170086e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}