{
  "best_metric": 0.06073566526174545,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold5/checkpoint-110",
  "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": 0.5089470744132996,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3815,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5073229670524597,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3753,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.5411736965179443,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4066,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.4232228696346283,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.342,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.5526444315910339,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3714,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5825538635253906,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.3611,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.5616931319236755,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3504,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.5023133754730225,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3133,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.42280760407447815,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.2983,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.3856165111064911,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2467,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.25492945313453674,
      "eval_runtime": 40.048,
      "eval_samples_per_second": 1.124,
      "eval_steps_per_second": 1.124,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.41062799096107483,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.254,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.4514571726322174,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.243,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.47026196122169495,
      "learning_rate": 0.0001,
      "loss": 0.2297,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4855942130088806,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.2247,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.38430678844451904,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1896,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.5231757760047913,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1798,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.3248537480831146,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1568,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.28666460514068604,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.1615,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.35147878527641296,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1471,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.29020145535469055,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1355,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.14349183440208435,
      "eval_runtime": 36.8587,
      "eval_samples_per_second": 1.221,
      "eval_steps_per_second": 1.221,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.23674245178699493,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1367,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.5353243350982666,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1211,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.3355393409729004,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.1317,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.3303943872451782,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1166,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.38826799392700195,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1219,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.532281219959259,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.1853,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.26731204986572266,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1054,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.29407113790512085,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1071,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.27267706394195557,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0978,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.24943608045578003,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0888,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10462252050638199,
      "eval_runtime": 39.4036,
      "eval_samples_per_second": 1.142,
      "eval_steps_per_second": 1.142,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.22287291288375854,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0798,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.3025493919849396,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.0854,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.2630584239959717,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.0874,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.2585624158382416,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1101,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.4086993336677551,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.1042,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.26721611618995667,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0872,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.3374441862106323,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0809,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.6961419582366943,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0905,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.28977182507514954,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0868,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.27843841910362244,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0797,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.08712419122457504,
      "eval_runtime": 39.6685,
      "eval_samples_per_second": 1.134,
      "eval_steps_per_second": 1.134,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.3495345115661621,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0669,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.38774240016937256,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0825,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.3325645625591278,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0641,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.3744155764579773,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0972,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.2777160704135895,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0549,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.2846892476081848,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0744,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.28101393580436707,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.0792,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.2314194142818451,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0696,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.27051547169685364,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0833,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.2462378293275833,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0714,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07394019514322281,
      "eval_runtime": 39.7834,
      "eval_samples_per_second": 1.131,
      "eval_steps_per_second": 1.131,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.36648860573768616,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.1047,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.233634352684021,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.064,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.20728164911270142,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0483,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.22391606867313385,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.0586,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.45925095677375793,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0661,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2177632749080658,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0577,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.24321158230304718,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0633,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.33396846055984497,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0704,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.22802115976810455,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0573,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.31876590847969055,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0655,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06959837675094604,
      "eval_runtime": 39.6355,
      "eval_samples_per_second": 1.135,
      "eval_steps_per_second": 1.135,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.5507637858390808,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0637,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.1966722011566162,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0485,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.2679797112941742,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0551,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.2858840525150299,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0458,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.3398570418357849,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0595,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.18000096082687378,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0557,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2882992625236511,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0595,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.36553746461868286,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0458,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.27761128544807434,
      "learning_rate": 5e-05,
      "loss": 0.0498,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.2667608857154846,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0561,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06552238017320633,
      "eval_runtime": 40.2287,
      "eval_samples_per_second": 1.119,
      "eval_steps_per_second": 1.119,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.25627341866493225,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0527,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.3376663625240326,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0698,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.20134593546390533,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0417,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.23182067275047302,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0559,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.1877857893705368,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0462,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.4917484223842621,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0927,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.21955683827400208,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0428,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.24542005360126495,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.0512,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.1829456239938736,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0413,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.22936666011810303,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0469,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06305002421140671,
      "eval_runtime": 40.0175,
      "eval_samples_per_second": 1.125,
      "eval_steps_per_second": 1.125,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.23589807748794556,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0485,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.20686839520931244,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0441,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.21705253422260284,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0438,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.21880730986595154,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.0405,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.23122332990169525,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0494,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.21872824430465698,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0424,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.1837765872478485,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0424,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.3087025582790375,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0476,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.21478217840194702,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0488,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.32977259159088135,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0485,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.06213260814547539,
      "eval_runtime": 39.4359,
      "eval_samples_per_second": 1.141,
      "eval_steps_per_second": 1.141,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.27420830726623535,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.046,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.2179533690214157,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0414,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.23637732863426208,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0469,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.32427772879600525,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0534,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.22050276398658752,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.0519,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.18890249729156494,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.04,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.22632203996181488,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0461,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.3161475956439972,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0473,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.24656446278095245,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0468,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.2918907701969147,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0325,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.061909325420856476,
      "eval_runtime": 39.4086,
      "eval_samples_per_second": 1.142,
      "eval_steps_per_second": 1.142,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.26413750648498535,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0544,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.308793306350708,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0636,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.19618992507457733,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0416,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.16061368584632874,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0327,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.20122478902339935,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0489,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.2050655335187912,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.0394,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.16939817368984222,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0398,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.23342402279376984,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0425,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.21763187646865845,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.046,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.19756054878234863,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0408,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.06073566526174545,
      "eval_runtime": 39.7946,
      "eval_samples_per_second": 1.131,
      "eval_steps_per_second": 1.131,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.16051572561264038,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0356,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.16083630919456482,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0334,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.21160809695720673,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.042,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.20383642613887787,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0461,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.23017120361328125,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.0393,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.17443464696407318,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0331,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.21680469810962677,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0445,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.23114809393882751,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0457,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.24989353120326996,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0531,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.17355340719223022,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0437,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.06074053794145584,
      "eval_runtime": 40.1038,
      "eval_samples_per_second": 1.122,
      "eval_steps_per_second": 1.122,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.1802823841571808,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0396,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.13851328194141388,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.0299,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.2617752254009247,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0418,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.2130405753850937,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0445,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.16297677159309387,
      "learning_rate": 0.0,
      "loss": 0.0364,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.680029287736279e+17,
      "train_loss": 0.09535923935472965,
      "train_runtime": 6104.8734,
      "train_samples_per_second": 0.332,
      "train_steps_per_second": 0.02
    }
  ],
  "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": 1.680029287736279e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}