{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008705114254624592,
      "grad_norm": 1.703125,
      "learning_rate": 5e-05,
      "loss": 0.8632,
      "step": 1
    },
    {
      "epoch": 0.017410228509249184,
      "grad_norm": 2.015625,
      "learning_rate": 4.9956521739130436e-05,
      "loss": 0.7891,
      "step": 2
    },
    {
      "epoch": 0.026115342763873776,
      "grad_norm": 8.375,
      "learning_rate": 4.9913043478260876e-05,
      "loss": 0.7896,
      "step": 3
    },
    {
      "epoch": 0.03482045701849837,
      "grad_norm": 3.328125,
      "learning_rate": 4.986956521739131e-05,
      "loss": 0.9271,
      "step": 4
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 1.640625,
      "learning_rate": 4.9826086956521736e-05,
      "loss": 0.9154,
      "step": 5
    },
    {
      "epoch": 0.05223068552774755,
      "grad_norm": 1.5390625,
      "learning_rate": 4.9782608695652176e-05,
      "loss": 0.9267,
      "step": 6
    },
    {
      "epoch": 0.060935799782372145,
      "grad_norm": 2.71875,
      "learning_rate": 4.973913043478261e-05,
      "loss": 0.8189,
      "step": 7
    },
    {
      "epoch": 0.06964091403699674,
      "grad_norm": 1.5859375,
      "learning_rate": 4.969565217391304e-05,
      "loss": 0.8018,
      "step": 8
    },
    {
      "epoch": 0.07834602829162132,
      "grad_norm": 1.359375,
      "learning_rate": 4.9652173913043483e-05,
      "loss": 0.9439,
      "step": 9
    },
    {
      "epoch": 0.08705114254624592,
      "grad_norm": 2.375,
      "learning_rate": 4.960869565217392e-05,
      "loss": 0.8444,
      "step": 10
    },
    {
      "epoch": 0.0957562568008705,
      "grad_norm": 2.125,
      "learning_rate": 4.956521739130435e-05,
      "loss": 1.013,
      "step": 11
    },
    {
      "epoch": 0.1044613710554951,
      "grad_norm": 1.7109375,
      "learning_rate": 4.9521739130434784e-05,
      "loss": 1.1719,
      "step": 12
    },
    {
      "epoch": 0.11316648531011969,
      "grad_norm": 1.4296875,
      "learning_rate": 4.947826086956522e-05,
      "loss": 1.0034,
      "step": 13
    },
    {
      "epoch": 0.12187159956474429,
      "grad_norm": 1.25,
      "learning_rate": 4.943478260869566e-05,
      "loss": 1.0015,
      "step": 14
    },
    {
      "epoch": 0.1305767138193689,
      "grad_norm": 1.25,
      "learning_rate": 4.939130434782609e-05,
      "loss": 0.9413,
      "step": 15
    },
    {
      "epoch": 0.13928182807399347,
      "grad_norm": 1.5546875,
      "learning_rate": 4.9347826086956524e-05,
      "loss": 1.0435,
      "step": 16
    },
    {
      "epoch": 0.14798694232861806,
      "grad_norm": 2.265625,
      "learning_rate": 4.930434782608696e-05,
      "loss": 0.9285,
      "step": 17
    },
    {
      "epoch": 0.15669205658324264,
      "grad_norm": 1.3046875,
      "learning_rate": 4.926086956521739e-05,
      "loss": 0.91,
      "step": 18
    },
    {
      "epoch": 0.16539717083786726,
      "grad_norm": 1.296875,
      "learning_rate": 4.9217391304347824e-05,
      "loss": 0.937,
      "step": 19
    },
    {
      "epoch": 0.17410228509249184,
      "grad_norm": 1.28125,
      "learning_rate": 4.9173913043478265e-05,
      "loss": 0.9194,
      "step": 20
    },
    {
      "epoch": 0.18280739934711643,
      "grad_norm": 1.203125,
      "learning_rate": 4.91304347826087e-05,
      "loss": 0.9392,
      "step": 21
    },
    {
      "epoch": 0.191512513601741,
      "grad_norm": 1.3203125,
      "learning_rate": 4.908695652173913e-05,
      "loss": 0.935,
      "step": 22
    },
    {
      "epoch": 0.20021762785636563,
      "grad_norm": 1.2421875,
      "learning_rate": 4.904347826086957e-05,
      "loss": 0.7352,
      "step": 23
    },
    {
      "epoch": 0.2089227421109902,
      "grad_norm": 1.2578125,
      "learning_rate": 4.9e-05,
      "loss": 0.8006,
      "step": 24
    },
    {
      "epoch": 0.2176278563656148,
      "grad_norm": 1.3046875,
      "learning_rate": 4.895652173913044e-05,
      "loss": 1.1003,
      "step": 25
    },
    {
      "epoch": 0.22633297062023938,
      "grad_norm": 1.578125,
      "learning_rate": 4.891304347826087e-05,
      "loss": 0.8786,
      "step": 26
    },
    {
      "epoch": 0.235038084874864,
      "grad_norm": 1.390625,
      "learning_rate": 4.8869565217391305e-05,
      "loss": 0.9133,
      "step": 27
    },
    {
      "epoch": 0.24374319912948858,
      "grad_norm": 1.109375,
      "learning_rate": 4.8826086956521746e-05,
      "loss": 0.9822,
      "step": 28
    },
    {
      "epoch": 0.25244831338411317,
      "grad_norm": 1.6640625,
      "learning_rate": 4.878260869565218e-05,
      "loss": 1.0016,
      "step": 29
    },
    {
      "epoch": 0.2611534276387378,
      "grad_norm": 1.34375,
      "learning_rate": 4.873913043478261e-05,
      "loss": 1.1215,
      "step": 30
    },
    {
      "epoch": 0.26985854189336234,
      "grad_norm": 1.171875,
      "learning_rate": 4.8695652173913046e-05,
      "loss": 1.1457,
      "step": 31
    },
    {
      "epoch": 0.27856365614798695,
      "grad_norm": 1.3671875,
      "learning_rate": 4.865217391304348e-05,
      "loss": 1.0368,
      "step": 32
    },
    {
      "epoch": 0.28726877040261156,
      "grad_norm": 1.140625,
      "learning_rate": 4.860869565217391e-05,
      "loss": 0.9539,
      "step": 33
    },
    {
      "epoch": 0.2959738846572361,
      "grad_norm": 1.4296875,
      "learning_rate": 4.856521739130435e-05,
      "loss": 0.9165,
      "step": 34
    },
    {
      "epoch": 0.30467899891186073,
      "grad_norm": 1.2265625,
      "learning_rate": 4.8521739130434786e-05,
      "loss": 1.03,
      "step": 35
    },
    {
      "epoch": 0.3133841131664853,
      "grad_norm": 1.5703125,
      "learning_rate": 4.847826086956522e-05,
      "loss": 1.2848,
      "step": 36
    },
    {
      "epoch": 0.3220892274211099,
      "grad_norm": 1.21875,
      "learning_rate": 4.843478260869565e-05,
      "loss": 0.8663,
      "step": 37
    },
    {
      "epoch": 0.3307943416757345,
      "grad_norm": 1.125,
      "learning_rate": 4.839130434782609e-05,
      "loss": 0.9547,
      "step": 38
    },
    {
      "epoch": 0.3394994559303591,
      "grad_norm": 1.328125,
      "learning_rate": 4.834782608695652e-05,
      "loss": 0.872,
      "step": 39
    },
    {
      "epoch": 0.3482045701849837,
      "grad_norm": 1.140625,
      "learning_rate": 4.830434782608696e-05,
      "loss": 0.8424,
      "step": 40
    },
    {
      "epoch": 0.35690968443960824,
      "grad_norm": 1.2578125,
      "learning_rate": 4.8260869565217394e-05,
      "loss": 0.8246,
      "step": 41
    },
    {
      "epoch": 0.36561479869423286,
      "grad_norm": 1.3046875,
      "learning_rate": 4.8217391304347834e-05,
      "loss": 0.8326,
      "step": 42
    },
    {
      "epoch": 0.37431991294885747,
      "grad_norm": 1.2109375,
      "learning_rate": 4.817391304347826e-05,
      "loss": 0.9043,
      "step": 43
    },
    {
      "epoch": 0.383025027203482,
      "grad_norm": 1.296875,
      "learning_rate": 4.8130434782608694e-05,
      "loss": 0.8888,
      "step": 44
    },
    {
      "epoch": 0.39173014145810664,
      "grad_norm": 1.2265625,
      "learning_rate": 4.8086956521739134e-05,
      "loss": 0.778,
      "step": 45
    },
    {
      "epoch": 0.40043525571273125,
      "grad_norm": 1.0546875,
      "learning_rate": 4.804347826086957e-05,
      "loss": 0.8684,
      "step": 46
    },
    {
      "epoch": 0.4091403699673558,
      "grad_norm": 1.5078125,
      "learning_rate": 4.8e-05,
      "loss": 0.9351,
      "step": 47
    },
    {
      "epoch": 0.4178454842219804,
      "grad_norm": 1.2421875,
      "learning_rate": 4.795652173913044e-05,
      "loss": 0.8708,
      "step": 48
    },
    {
      "epoch": 0.426550598476605,
      "grad_norm": 1.28125,
      "learning_rate": 4.7913043478260875e-05,
      "loss": 0.9919,
      "step": 49
    },
    {
      "epoch": 0.4352557127312296,
      "grad_norm": 1.1953125,
      "learning_rate": 4.78695652173913e-05,
      "loss": 0.8166,
      "step": 50
    },
    {
      "epoch": 0.4439608269858542,
      "grad_norm": 1.3203125,
      "learning_rate": 4.782608695652174e-05,
      "loss": 0.9542,
      "step": 51
    },
    {
      "epoch": 0.45266594124047876,
      "grad_norm": 1.2109375,
      "learning_rate": 4.7782608695652175e-05,
      "loss": 1.0959,
      "step": 52
    },
    {
      "epoch": 0.4613710554951034,
      "grad_norm": 1.140625,
      "learning_rate": 4.773913043478261e-05,
      "loss": 0.8695,
      "step": 53
    },
    {
      "epoch": 0.470076169749728,
      "grad_norm": 1.5234375,
      "learning_rate": 4.769565217391305e-05,
      "loss": 1.1411,
      "step": 54
    },
    {
      "epoch": 0.47878128400435255,
      "grad_norm": 1.125,
      "learning_rate": 4.765217391304348e-05,
      "loss": 0.8354,
      "step": 55
    },
    {
      "epoch": 0.48748639825897716,
      "grad_norm": 1.390625,
      "learning_rate": 4.7608695652173916e-05,
      "loss": 0.9133,
      "step": 56
    },
    {
      "epoch": 0.4961915125136017,
      "grad_norm": 1.2578125,
      "learning_rate": 4.756521739130435e-05,
      "loss": 0.9042,
      "step": 57
    },
    {
      "epoch": 0.5048966267682263,
      "grad_norm": 1.28125,
      "learning_rate": 4.752173913043478e-05,
      "loss": 0.9707,
      "step": 58
    },
    {
      "epoch": 0.5136017410228509,
      "grad_norm": 1.2734375,
      "learning_rate": 4.747826086956522e-05,
      "loss": 0.7845,
      "step": 59
    },
    {
      "epoch": 0.5223068552774756,
      "grad_norm": 1.3046875,
      "learning_rate": 4.7434782608695656e-05,
      "loss": 0.955,
      "step": 60
    },
    {
      "epoch": 0.5310119695321001,
      "grad_norm": 1.546875,
      "learning_rate": 4.739130434782609e-05,
      "loss": 0.9521,
      "step": 61
    },
    {
      "epoch": 0.5397170837867247,
      "grad_norm": 1.2578125,
      "learning_rate": 4.734782608695652e-05,
      "loss": 1.0155,
      "step": 62
    },
    {
      "epoch": 0.5484221980413493,
      "grad_norm": 1.3125,
      "learning_rate": 4.7304347826086956e-05,
      "loss": 1.0093,
      "step": 63
    },
    {
      "epoch": 0.5571273122959739,
      "grad_norm": 1.234375,
      "learning_rate": 4.726086956521739e-05,
      "loss": 0.8372,
      "step": 64
    },
    {
      "epoch": 0.5658324265505985,
      "grad_norm": 1.0703125,
      "learning_rate": 4.721739130434783e-05,
      "loss": 0.8776,
      "step": 65
    },
    {
      "epoch": 0.5745375408052231,
      "grad_norm": 1.2265625,
      "learning_rate": 4.7173913043478264e-05,
      "loss": 0.8854,
      "step": 66
    },
    {
      "epoch": 0.5832426550598476,
      "grad_norm": 1.1171875,
      "learning_rate": 4.71304347826087e-05,
      "loss": 0.8966,
      "step": 67
    },
    {
      "epoch": 0.5919477693144722,
      "grad_norm": 1.296875,
      "learning_rate": 4.708695652173914e-05,
      "loss": 0.9694,
      "step": 68
    },
    {
      "epoch": 0.6006528835690969,
      "grad_norm": 1.1875,
      "learning_rate": 4.7043478260869564e-05,
      "loss": 1.062,
      "step": 69
    },
    {
      "epoch": 0.6093579978237215,
      "grad_norm": 1.078125,
      "learning_rate": 4.7e-05,
      "loss": 0.8369,
      "step": 70
    },
    {
      "epoch": 0.6180631120783461,
      "grad_norm": 1.1953125,
      "learning_rate": 4.695652173913044e-05,
      "loss": 0.7927,
      "step": 71
    },
    {
      "epoch": 0.6267682263329706,
      "grad_norm": 1.4140625,
      "learning_rate": 4.691304347826087e-05,
      "loss": 1.3626,
      "step": 72
    },
    {
      "epoch": 0.6354733405875952,
      "grad_norm": 1.1328125,
      "learning_rate": 4.686956521739131e-05,
      "loss": 0.7737,
      "step": 73
    },
    {
      "epoch": 0.6441784548422198,
      "grad_norm": 1.0859375,
      "learning_rate": 4.6826086956521745e-05,
      "loss": 0.9044,
      "step": 74
    },
    {
      "epoch": 0.6528835690968444,
      "grad_norm": 1.078125,
      "learning_rate": 4.678260869565218e-05,
      "loss": 0.9451,
      "step": 75
    },
    {
      "epoch": 0.661588683351469,
      "grad_norm": 1.234375,
      "learning_rate": 4.673913043478261e-05,
      "loss": 1.0073,
      "step": 76
    },
    {
      "epoch": 0.6702937976060935,
      "grad_norm": 1.1484375,
      "learning_rate": 4.6695652173913045e-05,
      "loss": 1.0206,
      "step": 77
    },
    {
      "epoch": 0.6789989118607181,
      "grad_norm": 1.25,
      "learning_rate": 4.665217391304348e-05,
      "loss": 0.7854,
      "step": 78
    },
    {
      "epoch": 0.6877040261153428,
      "grad_norm": 1.0859375,
      "learning_rate": 4.660869565217392e-05,
      "loss": 0.9661,
      "step": 79
    },
    {
      "epoch": 0.6964091403699674,
      "grad_norm": 1.296875,
      "learning_rate": 4.656521739130435e-05,
      "loss": 1.0657,
      "step": 80
    },
    {
      "epoch": 0.705114254624592,
      "grad_norm": 1.0390625,
      "learning_rate": 4.6521739130434785e-05,
      "loss": 0.6992,
      "step": 81
    },
    {
      "epoch": 0.7138193688792165,
      "grad_norm": 1.0703125,
      "learning_rate": 4.647826086956522e-05,
      "loss": 0.8135,
      "step": 82
    },
    {
      "epoch": 0.7225244831338411,
      "grad_norm": 1.359375,
      "learning_rate": 4.643478260869565e-05,
      "loss": 1.1033,
      "step": 83
    },
    {
      "epoch": 0.7312295973884657,
      "grad_norm": 1.3828125,
      "learning_rate": 4.6391304347826086e-05,
      "loss": 0.8077,
      "step": 84
    },
    {
      "epoch": 0.7399347116430903,
      "grad_norm": 1.0859375,
      "learning_rate": 4.6347826086956526e-05,
      "loss": 0.8582,
      "step": 85
    },
    {
      "epoch": 0.7486398258977149,
      "grad_norm": 1.140625,
      "learning_rate": 4.630434782608696e-05,
      "loss": 1.0223,
      "step": 86
    },
    {
      "epoch": 0.7573449401523396,
      "grad_norm": 1.2734375,
      "learning_rate": 4.62608695652174e-05,
      "loss": 0.7866,
      "step": 87
    },
    {
      "epoch": 0.766050054406964,
      "grad_norm": 1.1484375,
      "learning_rate": 4.6217391304347826e-05,
      "loss": 0.804,
      "step": 88
    },
    {
      "epoch": 0.7747551686615887,
      "grad_norm": 0.96484375,
      "learning_rate": 4.617391304347826e-05,
      "loss": 0.681,
      "step": 89
    },
    {
      "epoch": 0.7834602829162133,
      "grad_norm": 1.0078125,
      "learning_rate": 4.61304347826087e-05,
      "loss": 0.9594,
      "step": 90
    },
    {
      "epoch": 0.7921653971708379,
      "grad_norm": 1.0546875,
      "learning_rate": 4.608695652173913e-05,
      "loss": 0.9842,
      "step": 91
    },
    {
      "epoch": 0.8008705114254625,
      "grad_norm": 1.09375,
      "learning_rate": 4.6043478260869567e-05,
      "loss": 0.9142,
      "step": 92
    },
    {
      "epoch": 0.809575625680087,
      "grad_norm": 1.15625,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.7379,
      "step": 93
    },
    {
      "epoch": 0.8182807399347116,
      "grad_norm": 1.3984375,
      "learning_rate": 4.595652173913044e-05,
      "loss": 1.0656,
      "step": 94
    },
    {
      "epoch": 0.8269858541893362,
      "grad_norm": 1.15625,
      "learning_rate": 4.591304347826087e-05,
      "loss": 0.9404,
      "step": 95
    },
    {
      "epoch": 0.8356909684439608,
      "grad_norm": 1.109375,
      "learning_rate": 4.586956521739131e-05,
      "loss": 1.0705,
      "step": 96
    },
    {
      "epoch": 0.8443960826985855,
      "grad_norm": 1.1171875,
      "learning_rate": 4.582608695652174e-05,
      "loss": 1.1848,
      "step": 97
    },
    {
      "epoch": 0.85310119695321,
      "grad_norm": 1.15625,
      "learning_rate": 4.5782608695652174e-05,
      "loss": 0.8771,
      "step": 98
    },
    {
      "epoch": 0.8618063112078346,
      "grad_norm": 1.265625,
      "learning_rate": 4.5739130434782614e-05,
      "loss": 0.9586,
      "step": 99
    },
    {
      "epoch": 0.8705114254624592,
      "grad_norm": 1.1015625,
      "learning_rate": 4.569565217391305e-05,
      "loss": 0.7516,
      "step": 100
    },
    {
      "epoch": 0.8792165397170838,
      "grad_norm": 1.3125,
      "learning_rate": 4.565217391304348e-05,
      "loss": 0.8131,
      "step": 101
    },
    {
      "epoch": 0.8879216539717084,
      "grad_norm": 1.109375,
      "learning_rate": 4.5608695652173914e-05,
      "loss": 0.9118,
      "step": 102
    },
    {
      "epoch": 0.8966267682263329,
      "grad_norm": 1.4140625,
      "learning_rate": 4.556521739130435e-05,
      "loss": 0.8855,
      "step": 103
    },
    {
      "epoch": 0.9053318824809575,
      "grad_norm": 1.1796875,
      "learning_rate": 4.552173913043479e-05,
      "loss": 0.7721,
      "step": 104
    },
    {
      "epoch": 0.9140369967355821,
      "grad_norm": 1.2265625,
      "learning_rate": 4.547826086956522e-05,
      "loss": 0.7768,
      "step": 105
    },
    {
      "epoch": 0.9227421109902068,
      "grad_norm": 1.0703125,
      "learning_rate": 4.5434782608695655e-05,
      "loss": 0.9557,
      "step": 106
    },
    {
      "epoch": 0.9314472252448314,
      "grad_norm": 1.0625,
      "learning_rate": 4.539130434782609e-05,
      "loss": 0.8868,
      "step": 107
    },
    {
      "epoch": 0.940152339499456,
      "grad_norm": 1.15625,
      "learning_rate": 4.534782608695652e-05,
      "loss": 0.8889,
      "step": 108
    },
    {
      "epoch": 0.9488574537540805,
      "grad_norm": 1.15625,
      "learning_rate": 4.5304347826086955e-05,
      "loss": 1.1122,
      "step": 109
    },
    {
      "epoch": 0.9575625680087051,
      "grad_norm": 1.1875,
      "learning_rate": 4.5260869565217395e-05,
      "loss": 0.7954,
      "step": 110
    },
    {
      "epoch": 0.9662676822633297,
      "grad_norm": 1.1796875,
      "learning_rate": 4.521739130434783e-05,
      "loss": 0.8551,
      "step": 111
    },
    {
      "epoch": 0.9749727965179543,
      "grad_norm": 1.1953125,
      "learning_rate": 4.517391304347826e-05,
      "loss": 1.0285,
      "step": 112
    },
    {
      "epoch": 0.9836779107725789,
      "grad_norm": 1.25,
      "learning_rate": 4.51304347826087e-05,
      "loss": 1.0737,
      "step": 113
    },
    {
      "epoch": 0.9923830250272034,
      "grad_norm": 1.015625,
      "learning_rate": 4.508695652173913e-05,
      "loss": 0.8448,
      "step": 114
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2421875,
      "learning_rate": 4.504347826086956e-05,
      "loss": 0.9171,
      "step": 115
    }
  ],
  "logging_steps": 1,
  "max_steps": 1150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.91889867776983e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}