{
  "best_metric": 0.061547331511974335,
  "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold10/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": 0.19440560042858124,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.2429,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.18476668000221252,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2565,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.2121252715587616,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.2015,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.1921861171722412,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3017,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.18879516422748566,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.2463,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.17186714708805084,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.2464,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.1876388043165207,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3299,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.19278578460216522,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.261,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.18014144897460938,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2089,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.15187592804431915,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2103,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.17452898621559143,
      "eval_runtime": 21.8897,
      "eval_samples_per_second": 2.056,
      "eval_steps_per_second": 2.056,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.15359655022621155,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2028,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.12749916315078735,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.21,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.10455162078142166,
      "learning_rate": 0.0001,
      "loss": 0.173,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.08849436044692993,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1354,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.08663274347782135,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1039,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.11078087985515594,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1582,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.10254587233066559,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1723,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.1016877219080925,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1669,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.0996580570936203,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1545,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.09017302095890045,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1083,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.11381040513515472,
      "eval_runtime": 21.8288,
      "eval_samples_per_second": 2.061,
      "eval_steps_per_second": 2.061,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.12739326059818268,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1446,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.11197912693023682,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1711,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.11346019804477692,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.133,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.1038404256105423,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.0899,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.07326199114322662,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1205,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.1390497237443924,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2943,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.06713442504405975,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1116,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.06063803657889366,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1203,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.07092577964067459,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1443,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.07295554131269455,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.1106,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.08223848044872284,
      "eval_runtime": 21.9018,
      "eval_samples_per_second": 2.055,
      "eval_steps_per_second": 2.055,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.07690256834030151,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0927,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.0761461928486824,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1436,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.06692412495613098,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.1216,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.06737225502729416,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.08530013263225555,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1355,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.07029202580451965,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.1375,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.07611638307571411,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0962,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.09558116644620895,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0782,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.08308538794517517,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.1074,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.0711466446518898,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.115,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.0722765102982521,
      "eval_runtime": 21.8928,
      "eval_samples_per_second": 2.055,
      "eval_steps_per_second": 2.055,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.07066932320594788,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0878,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.0678776279091835,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0638,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.08123959600925446,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0949,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.07733673602342606,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.1049,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.06929367780685425,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0586,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.10114534199237823,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0727,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.06785311549901962,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1185,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.06739966571331024,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0604,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.0732615664601326,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.076,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.07069004327058792,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0903,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.0675145760178566,
      "eval_runtime": 21.9052,
      "eval_samples_per_second": 2.054,
      "eval_steps_per_second": 2.054,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.1152932196855545,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1059,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.061211246997117996,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0881,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.08361011743545532,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.1072,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.06726044416427612,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.1046,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.07051020115613937,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1104,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.05748420208692551,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.082,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.08313898742198944,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.1901,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.06902708858251572,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0572,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.07308803498744965,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.05,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.06191898509860039,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0737,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06489859521389008,
      "eval_runtime": 21.8765,
      "eval_samples_per_second": 2.057,
      "eval_steps_per_second": 2.057,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.0679517388343811,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0675,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.055570054799318314,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0524,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.06902100145816803,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0386,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.06601161509752274,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.067,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.08528830856084824,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1527,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.046679627150297165,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0437,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.06345894932746887,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.1072,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.060195405036211014,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0894,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.0877985879778862,
      "learning_rate": 5e-05,
      "loss": 0.1327,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.07053381949663162,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.1055,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06331419944763184,
      "eval_runtime": 21.8435,
      "eval_samples_per_second": 2.06,
      "eval_steps_per_second": 2.06,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.06791283935308456,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0691,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.06513185054063797,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.108,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.07605980336666107,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0727,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.06514771282672882,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.1102,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.07374415546655655,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0795,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.16481050848960876,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0506,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.0726829245686531,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0676,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.06648536771535873,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.1014,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.06888164579868317,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0345,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.07184445858001709,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.108,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.062431298196315765,
      "eval_runtime": 21.8435,
      "eval_samples_per_second": 2.06,
      "eval_steps_per_second": 2.06,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.07358197867870331,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0594,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.06036700680851936,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0517,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.07146187126636505,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1013,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.06352803111076355,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.1068,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.05638516694307327,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0899,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.07684286683797836,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.1129,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.06539037823677063,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0963,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.07009128481149673,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.1263,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.06477431952953339,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0516,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.058393169194459915,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0542,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.062307436019182205,
      "eval_runtime": 21.7896,
      "eval_samples_per_second": 2.065,
      "eval_steps_per_second": 2.065,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.0711691826581955,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.08,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.0820746049284935,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.112,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.05699919909238815,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0504,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.07870594412088394,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0882,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.08601382374763489,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.104,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.07925941795110703,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0613,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.05285891890525818,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0359,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.07679113745689392,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.1379,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.06077484041452408,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0723,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.0774044618010521,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0684,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.06192609295248985,
      "eval_runtime": 21.7917,
      "eval_samples_per_second": 2.065,
      "eval_steps_per_second": 2.065,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.1012384220957756,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.1279,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.09754081070423126,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0829,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.06351117044687271,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.054,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.07060787826776505,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0579,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.056473296135663986,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0602,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.06499671936035156,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0518,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.08109067380428314,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.1259,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.0556601881980896,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0323,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.07055909931659698,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1058,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.05862484872341156,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0812,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.061585284769535065,
      "eval_runtime": 21.7513,
      "eval_samples_per_second": 2.069,
      "eval_steps_per_second": 2.069,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.05508541315793991,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0519,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.06993698328733444,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0853,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.05619633197784424,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0402,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.07234524935483932,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.1035,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.060880303382873535,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0575,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.06871213763952255,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0993,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.07386505603790283,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.1416,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.07733534276485443,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.1192,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.07387135177850723,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.1471,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.06633585691452026,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0876,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.061547331511974335,
      "eval_runtime": 21.7465,
      "eval_samples_per_second": 2.069,
      "eval_steps_per_second": 2.069,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.0668892189860344,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0875,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.05036670342087746,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0241,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.05016731470823288,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0442,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.058881908655166626,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0393,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.06545499712228775,
      "learning_rate": 0.0,
      "loss": 0.089,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.4286246027772723e+17,
      "train_loss": 0.1101770606637001,
      "train_runtime": 3342.894,
      "train_samples_per_second": 0.606,
      "train_steps_per_second": 0.037
    }
  ],
  "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": 1.4286246027772723e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}