{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 511,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019569471624266144,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.003913894324853229,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.005870841487279843,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007827788649706457,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.009784735812133072,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.011741682974559686,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0136986301369863,
      "grad_norm": NaN,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.015655577299412915,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.01761252446183953,
      "grad_norm": NaN,
      "learning_rate": 9e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.019569471624266144,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.021526418786692758,
      "grad_norm": NaN,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.023483365949119372,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.025440313111545987,
      "grad_norm": NaN,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": NaN,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.029354207436399216,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.03131115459882583,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.033268101761252444,
      "grad_norm": NaN,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.03522504892367906,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03718199608610567,
      "grad_norm": NaN,
      "learning_rate": 1.9e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.03913894324853229,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": NaN,
      "learning_rate": 2.1e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.043052837573385516,
      "grad_norm": NaN,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.04500978473581213,
      "grad_norm": NaN,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.046966731898238745,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04892367906066536,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.050880626223091974,
      "grad_norm": NaN,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.05283757338551859,
      "grad_norm": NaN,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": NaN,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.05675146771037182,
      "grad_norm": NaN,
      "learning_rate": 2.9e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.05870841487279843,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.060665362035225046,
      "grad_norm": NaN,
      "learning_rate": 3.1e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.06262230919765166,
      "grad_norm": NaN,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.06457925636007827,
      "grad_norm": NaN,
      "learning_rate": 3.3e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.06653620352250489,
      "grad_norm": NaN,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.07045009784735812,
      "grad_norm": NaN,
      "learning_rate": 3.6e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.07240704500978473,
      "grad_norm": NaN,
      "learning_rate": 3.7e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.07436399217221135,
      "grad_norm": NaN,
      "learning_rate": 3.8e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.07632093933463796,
      "grad_norm": NaN,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.07827788649706457,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.08023483365949119,
      "grad_norm": NaN,
      "learning_rate": 4.1e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": NaN,
      "learning_rate": 4.2e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.08414872798434442,
      "grad_norm": NaN,
      "learning_rate": 4.3e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.08610567514677103,
      "grad_norm": NaN,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.08806262230919765,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.09001956947162426,
      "grad_norm": NaN,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.09197651663405088,
      "grad_norm": NaN,
      "learning_rate": 4.7e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.09393346379647749,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": NaN,
      "learning_rate": 4.9e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.09784735812133072,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.09980430528375733,
      "grad_norm": NaN,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.10176125244618395,
      "grad_norm": NaN,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.10371819960861056,
      "grad_norm": NaN,
      "learning_rate": 5.300000000000001e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.10567514677103718,
      "grad_norm": NaN,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.10763209393346379,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": NaN,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.11154598825831702,
      "grad_norm": NaN,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.11350293542074363,
      "grad_norm": NaN,
      "learning_rate": 5.8e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.11545988258317025,
      "grad_norm": NaN,
      "learning_rate": 5.9e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.11741682974559686,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.11937377690802348,
      "grad_norm": NaN,
      "learning_rate": 6.1e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.12133072407045009,
      "grad_norm": NaN,
      "learning_rate": 6.2e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": NaN,
      "learning_rate": 6.3e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.12524461839530332,
      "grad_norm": NaN,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.12720156555772993,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.12915851272015655,
      "grad_norm": NaN,
      "learning_rate": 6.6e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.13111545988258316,
      "grad_norm": NaN,
      "learning_rate": 6.7e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.13307240704500978,
      "grad_norm": NaN,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.1350293542074364,
      "grad_norm": NaN,
      "learning_rate": 6.9e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.13894324853228962,
      "grad_norm": NaN,
      "learning_rate": 7.1e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.14090019569471623,
      "grad_norm": NaN,
      "learning_rate": 7.2e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": NaN,
      "learning_rate": 7.3e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.14481409001956946,
      "grad_norm": NaN,
      "learning_rate": 7.4e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.14677103718199608,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.1487279843444227,
      "grad_norm": NaN,
      "learning_rate": 7.6e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": NaN,
      "learning_rate": 7.7e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.15264187866927592,
      "grad_norm": NaN,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.15459882583170254,
      "grad_norm": NaN,
      "learning_rate": 7.900000000000001e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.15655577299412915,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.15851272015655576,
      "grad_norm": NaN,
      "learning_rate": 8.1e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.16046966731898238,
      "grad_norm": NaN,
      "learning_rate": 8.2e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.162426614481409,
      "grad_norm": NaN,
      "learning_rate": 8.3e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": NaN,
      "learning_rate": 8.4e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.16634050880626222,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.16829745596868884,
      "grad_norm": NaN,
      "learning_rate": 8.6e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.17025440313111545,
      "grad_norm": NaN,
      "learning_rate": 8.7e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.17221135029354206,
      "grad_norm": NaN,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.17416829745596868,
      "grad_norm": NaN,
      "learning_rate": 8.900000000000001e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.1761252446183953,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": NaN,
      "learning_rate": 9.1e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.18003913894324852,
      "grad_norm": NaN,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.18199608610567514,
      "grad_norm": NaN,
      "learning_rate": 9.300000000000001e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.18395303326810175,
      "grad_norm": NaN,
      "learning_rate": 9.4e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.18590998043052837,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.18786692759295498,
      "grad_norm": NaN,
      "learning_rate": 9.6e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.1898238747553816,
      "grad_norm": NaN,
      "learning_rate": 9.7e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": NaN,
      "learning_rate": 9.8e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.19373776908023482,
      "grad_norm": NaN,
      "learning_rate": 9.900000000000001e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.19569471624266144,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.19765166340508805,
      "grad_norm": NaN,
      "learning_rate": 9.999853932365624e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.19960861056751467,
      "grad_norm": NaN,
      "learning_rate": 9.999415737996796e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.20156555772994128,
      "grad_norm": NaN,
      "learning_rate": 9.998685442495921e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.2035225048923679,
      "grad_norm": NaN,
      "learning_rate": 9.997663088532015e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": NaN,
      "learning_rate": 9.996348735838206e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.20743639921722112,
      "grad_norm": NaN,
      "learning_rate": 9.994742461208251e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.20939334637964774,
      "grad_norm": NaN,
      "learning_rate": 9.992844358492045e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.21135029354207435,
      "grad_norm": NaN,
      "learning_rate": 9.990654538590136e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.21330724070450097,
      "grad_norm": NaN,
      "learning_rate": 9.988173129447252e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.21526418786692758,
      "grad_norm": NaN,
      "learning_rate": 9.985400276044812e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.2172211350293542,
      "grad_norm": NaN,
      "learning_rate": 9.982336140392477e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": NaN,
      "learning_rate": 9.978980901518663e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.22113502935420742,
      "grad_norm": NaN,
      "learning_rate": 9.975334755460092e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.22309197651663404,
      "grad_norm": NaN,
      "learning_rate": 9.971397915250335e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.22504892367906065,
      "grad_norm": NaN,
      "learning_rate": 9.967170610907369e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.22700587084148727,
      "grad_norm": NaN,
      "learning_rate": 9.96265308942013e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.22896281800391388,
      "grad_norm": NaN,
      "learning_rate": 9.957845614734089e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.2309197651663405,
      "grad_norm": NaN,
      "learning_rate": 9.952748467735829e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": NaN,
      "learning_rate": 9.94736194623663e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.23483365949119372,
      "grad_norm": NaN,
      "learning_rate": 9.941686364955076e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.23679060665362034,
      "grad_norm": NaN,
      "learning_rate": 9.935722055498655e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.23874755381604695,
      "grad_norm": NaN,
      "learning_rate": 9.9294693663444e-05,
      "loss": 0.0,
      "step": 122
    },
    {
      "epoch": 0.24070450097847357,
      "grad_norm": NaN,
      "learning_rate": 9.922928662818516e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.24266144814090018,
      "grad_norm": NaN,
      "learning_rate": 9.916100327075038e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.2446183953033268,
      "grad_norm": NaN,
      "learning_rate": 9.908984758073505e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": NaN,
      "learning_rate": 9.901582371555651e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.24853228962818003,
      "grad_norm": NaN,
      "learning_rate": 9.893893600021112e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.25048923679060664,
      "grad_norm": NaN,
      "learning_rate": 9.885918892702153e-05,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.25244618395303325,
      "grad_norm": NaN,
      "learning_rate": 9.877658715537429e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.25440313111545987,
      "grad_norm": NaN,
      "learning_rate": 9.869113551144754e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.2563600782778865,
      "grad_norm": NaN,
      "learning_rate": 9.860283898792909e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.2583170254403131,
      "grad_norm": NaN,
      "learning_rate": 9.851170274372465e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": NaN,
      "learning_rate": 9.841773210365646e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.2622309197651663,
      "grad_norm": NaN,
      "learning_rate": 9.832093255815217e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.26418786692759294,
      "grad_norm": NaN,
      "learning_rate": 9.8221309762924e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.26614481409001955,
      "grad_norm": NaN,
      "learning_rate": 9.811886953863841e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.26810176125244617,
      "grad_norm": NaN,
      "learning_rate": 9.801361787057585e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.2700587084148728,
      "grad_norm": NaN,
      "learning_rate": 9.79055609082812e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.2720156555772994,
      "grad_norm": NaN,
      "learning_rate": 9.779470496520442e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": NaN,
      "learning_rate": 9.768105651833162e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.2759295499021526,
      "grad_norm": NaN,
      "learning_rate": 9.756462220780674e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.27788649706457924,
      "grad_norm": NaN,
      "learning_rate": 9.744540883654349e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.27984344422700586,
      "grad_norm": NaN,
      "learning_rate": 9.732342336982791e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.28180039138943247,
      "grad_norm": NaN,
      "learning_rate": 9.719867293491145e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.2837573385518591,
      "grad_norm": NaN,
      "learning_rate": 9.707116482059446e-05,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": NaN,
      "learning_rate": 9.694090647680039e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": NaN,
      "learning_rate": 9.680790551414047e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.2896281800391389,
      "grad_norm": NaN,
      "learning_rate": 9.667216970346914e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.29158512720156554,
      "grad_norm": NaN,
      "learning_rate": 9.653370697542988e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.29354207436399216,
      "grad_norm": NaN,
      "learning_rate": 9.639252541999195e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.29549902152641877,
      "grad_norm": NaN,
      "learning_rate": 9.624863328597766e-05,
      "loss": 0.0,
      "step": 151
    },
    {
      "epoch": 0.2974559686888454,
      "grad_norm": NaN,
      "learning_rate": 9.610203898058049e-05,
      "loss": 0.0,
      "step": 152
    },
    {
      "epoch": 0.299412915851272,
      "grad_norm": NaN,
      "learning_rate": 9.595275106887378e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": NaN,
      "learning_rate": 9.580077827331038e-05,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.30332681017612523,
      "grad_norm": NaN,
      "learning_rate": 9.564612947321297e-05,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.30528375733855184,
      "grad_norm": NaN,
      "learning_rate": 9.548881370425531e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.30724070450097846,
      "grad_norm": NaN,
      "learning_rate": 9.53288401579343e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.30919765166340507,
      "grad_norm": NaN,
      "learning_rate": 9.516621818103295e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.3111545988258317,
      "grad_norm": NaN,
      "learning_rate": 9.50009572750742e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.3131115459882583,
      "grad_norm": NaN,
      "learning_rate": 9.48330670957659e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": NaN,
      "learning_rate": 9.46625574524366e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.31702544031311153,
      "grad_norm": NaN,
      "learning_rate": 9.448943830746237e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.31898238747553814,
      "grad_norm": NaN,
      "learning_rate": 9.431371977568483e-05,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.32093933463796476,
      "grad_norm": NaN,
      "learning_rate": 9.413541212382005e-05,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.32289628180039137,
      "grad_norm": NaN,
      "learning_rate": 9.395452576985879e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.324853228962818,
      "grad_norm": NaN,
      "learning_rate": 9.377107128245781e-05,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.3268101761252446,
      "grad_norm": NaN,
      "learning_rate": 9.358505938032227e-05,
      "loss": 0.0,
      "step": 167
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": NaN,
      "learning_rate": 9.33965009315796e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.33072407045009783,
      "grad_norm": NaN,
      "learning_rate": 9.320540695314439e-05,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.33268101761252444,
      "grad_norm": NaN,
      "learning_rate": 9.301178861007482e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.33463796477495106,
      "grad_norm": NaN,
      "learning_rate": 9.281565721492022e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.33659491193737767,
      "grad_norm": NaN,
      "learning_rate": 9.261702422706013e-05,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.3385518590998043,
      "grad_norm": NaN,
      "learning_rate": 9.241590125203485e-05,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.3405088062622309,
      "grad_norm": NaN,
      "learning_rate": 9.221230004086722e-05,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": NaN,
      "learning_rate": 9.20062324893762e-05,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.34442270058708413,
      "grad_norm": NaN,
      "learning_rate": 9.17977106374816e-05,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.34637964774951074,
      "grad_norm": NaN,
      "learning_rate": 9.158674666850095e-05,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.34833659491193736,
      "grad_norm": NaN,
      "learning_rate": 9.13733529084374e-05,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.350293542074364,
      "grad_norm": NaN,
      "learning_rate": 9.115754182525961e-05,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.3522504892367906,
      "grad_norm": NaN,
      "learning_rate": 9.093932602817335e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.3542074363992172,
      "grad_norm": NaN,
      "learning_rate": 9.071871826688471e-05,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": NaN,
      "learning_rate": 9.049573143085525e-05,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.35812133072407043,
      "grad_norm": NaN,
      "learning_rate": 9.027037854854878e-05,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.36007827788649704,
      "grad_norm": NaN,
      "learning_rate": 9.004267278667032e-05,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.36203522504892366,
      "grad_norm": NaN,
      "learning_rate": 8.981262744939663e-05,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.3639921722113503,
      "grad_norm": NaN,
      "learning_rate": 8.958025597759899e-05,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.3659491193737769,
      "grad_norm": NaN,
      "learning_rate": 8.934557194805788e-05,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.3679060665362035,
      "grad_norm": NaN,
      "learning_rate": 8.91085890726697e-05,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": NaN,
      "learning_rate": 8.886932119764566e-05,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.37181996086105673,
      "grad_norm": NaN,
      "learning_rate": 8.862778230270275e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.37377690802348335,
      "grad_norm": NaN,
      "learning_rate": 8.838398650024697e-05,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.37573385518590996,
      "grad_norm": NaN,
      "learning_rate": 8.813794803454877e-05,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.3776908023483366,
      "grad_norm": NaN,
      "learning_rate": 8.788968128091083e-05,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.3796477495107632,
      "grad_norm": NaN,
      "learning_rate": 8.76392007448281e-05,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.3816046966731898,
      "grad_norm": NaN,
      "learning_rate": 8.738652106114029e-05,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": NaN,
      "learning_rate": 8.71316569931769e-05,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 0.38551859099804303,
      "grad_norm": NaN,
      "learning_rate": 8.687462343189452e-05,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.38747553816046965,
      "grad_norm": NaN,
      "learning_rate": 8.661543539500686e-05,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.38943248532289626,
      "grad_norm": NaN,
      "learning_rate": 8.635410802610725e-05,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.3913894324853229,
      "grad_norm": NaN,
      "learning_rate": 8.609065659378395e-05,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.3933463796477495,
      "grad_norm": NaN,
      "learning_rate": 8.582509649072792e-05,
      "loss": 0.0,
      "step": 201
    },
    {
      "epoch": 0.3953033268101761,
      "grad_norm": NaN,
      "learning_rate": 8.555744323283364e-05,
      "loss": 0.0,
      "step": 202
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": NaN,
      "learning_rate": 8.528771245829234e-05,
      "loss": 0.0,
      "step": 203
    },
    {
      "epoch": 0.39921722113502933,
      "grad_norm": NaN,
      "learning_rate": 8.50159199266785e-05,
      "loss": 0.0,
      "step": 204
    },
    {
      "epoch": 0.40117416829745595,
      "grad_norm": NaN,
      "learning_rate": 8.474208151802898e-05,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 0.40313111545988256,
      "grad_norm": NaN,
      "learning_rate": 8.44662132319152e-05,
      "loss": 0.0,
      "step": 206
    },
    {
      "epoch": 0.4050880626223092,
      "grad_norm": NaN,
      "learning_rate": 8.418833118650831e-05,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 0.4070450097847358,
      "grad_norm": NaN,
      "learning_rate": 8.390845161763756e-05,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 0.4090019569471624,
      "grad_norm": NaN,
      "learning_rate": 8.362659087784153e-05,
      "loss": 0.0,
      "step": 209
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": NaN,
      "learning_rate": 8.334276543541284e-05,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.41291585127201563,
      "grad_norm": NaN,
      "learning_rate": 8.305699187343586e-05,
      "loss": 0.0,
      "step": 211
    },
    {
      "epoch": 0.41487279843444225,
      "grad_norm": NaN,
      "learning_rate": 8.276928688881783e-05,
      "loss": 0.0,
      "step": 212
    },
    {
      "epoch": 0.41682974559686886,
      "grad_norm": NaN,
      "learning_rate": 8.24796672913134e-05,
      "loss": 0.0,
      "step": 213
    },
    {
      "epoch": 0.4187866927592955,
      "grad_norm": NaN,
      "learning_rate": 8.218815000254232e-05,
      "loss": 0.0,
      "step": 214
    },
    {
      "epoch": 0.4207436399217221,
      "grad_norm": NaN,
      "learning_rate": 8.189475205500091e-05,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.4227005870841487,
      "grad_norm": NaN,
      "learning_rate": 8.159949059106682e-05,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": NaN,
      "learning_rate": 8.130238286199748e-05,
      "loss": 0.0,
      "step": 217
    },
    {
      "epoch": 0.42661448140900193,
      "grad_norm": NaN,
      "learning_rate": 8.100344622692212e-05,
      "loss": 0.0,
      "step": 218
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": NaN,
      "learning_rate": 8.070269815182761e-05,
      "loss": 0.0,
      "step": 219
    },
    {
      "epoch": 0.43052837573385516,
      "grad_norm": NaN,
      "learning_rate": 8.040015620853789e-05,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.4324853228962818,
      "grad_norm": NaN,
      "learning_rate": 8.009583807368735e-05,
      "loss": 0.0,
      "step": 221
    },
    {
      "epoch": 0.4344422700587084,
      "grad_norm": NaN,
      "learning_rate": 7.978976152768799e-05,
      "loss": 0.0,
      "step": 222
    },
    {
      "epoch": 0.436399217221135,
      "grad_norm": NaN,
      "learning_rate": 7.948194445369064e-05,
      "loss": 0.0,
      "step": 223
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": NaN,
      "learning_rate": 7.917240483654002e-05,
      "loss": 0.0,
      "step": 224
    },
    {
      "epoch": 0.44031311154598823,
      "grad_norm": NaN,
      "learning_rate": 7.886116076172398e-05,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 0.44227005870841485,
      "grad_norm": NaN,
      "learning_rate": 7.85482304143168e-05,
      "loss": 0.0,
      "step": 226
    },
    {
      "epoch": 0.44422700587084146,
      "grad_norm": NaN,
      "learning_rate": 7.823363207791672e-05,
      "loss": 0.0,
      "step": 227
    },
    {
      "epoch": 0.4461839530332681,
      "grad_norm": NaN,
      "learning_rate": 7.791738413357765e-05,
      "loss": 0.0,
      "step": 228
    },
    {
      "epoch": 0.4481409001956947,
      "grad_norm": NaN,
      "learning_rate": 7.759950505873522e-05,
      "loss": 0.0,
      "step": 229
    },
    {
      "epoch": 0.4500978473581213,
      "grad_norm": NaN,
      "learning_rate": 7.728001342612724e-05,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": NaN,
      "learning_rate": 7.695892790270849e-05,
      "loss": 0.0,
      "step": 231
    },
    {
      "epoch": 0.45401174168297453,
      "grad_norm": NaN,
      "learning_rate": 7.66362672485601e-05,
      "loss": 0.0,
      "step": 232
    },
    {
      "epoch": 0.45596868884540115,
      "grad_norm": NaN,
      "learning_rate": 7.631205031579345e-05,
      "loss": 0.0,
      "step": 233
    },
    {
      "epoch": 0.45792563600782776,
      "grad_norm": NaN,
      "learning_rate": 7.598629604744874e-05,
      "loss": 0.0,
      "step": 234
    },
    {
      "epoch": 0.4598825831702544,
      "grad_norm": NaN,
      "learning_rate": 7.565902347638806e-05,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 0.461839530332681,
      "grad_norm": NaN,
      "learning_rate": 7.533025172418353e-05,
      "loss": 0.0,
      "step": 236
    },
    {
      "epoch": 0.4637964774951076,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 237
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": NaN,
      "learning_rate": 7.46682875994727e-05,
      "loss": 0.0,
      "step": 238
    },
    {
      "epoch": 0.46771037181996084,
      "grad_norm": NaN,
      "learning_rate": 7.43351339035799e-05,
      "loss": 0.0,
      "step": 239
    },
    {
      "epoch": 0.46966731898238745,
      "grad_norm": NaN,
      "learning_rate": 7.400055837751047e-05,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.47162426614481406,
      "grad_norm": NaN,
      "learning_rate": 7.366458056952668e-05,
      "loss": 0.0,
      "step": 241
    },
    {
      "epoch": 0.4735812133072407,
      "grad_norm": NaN,
      "learning_rate": 7.332722010982195e-05,
      "loss": 0.0,
      "step": 242
    },
    {
      "epoch": 0.4755381604696673,
      "grad_norm": NaN,
      "learning_rate": 7.298849670937403e-05,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 0.4774951076320939,
      "grad_norm": NaN,
      "learning_rate": 7.264843015879322e-05,
      "loss": 0.0,
      "step": 244
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": NaN,
      "learning_rate": 7.230704032716614e-05,
      "loss": 0.0,
      "step": 245
    },
    {
      "epoch": 0.48140900195694714,
      "grad_norm": NaN,
      "learning_rate": 7.196434716089486e-05,
      "loss": 0.0,
      "step": 246
    },
    {
      "epoch": 0.48336594911937375,
      "grad_norm": NaN,
      "learning_rate": 7.162037068253142e-05,
      "loss": 0.0,
      "step": 247
    },
    {
      "epoch": 0.48532289628180036,
      "grad_norm": NaN,
      "learning_rate": 7.127513098960798e-05,
      "loss": 0.0,
      "step": 248
    },
    {
      "epoch": 0.487279843444227,
      "grad_norm": NaN,
      "learning_rate": 7.092864825346266e-05,
      "loss": 0.0,
      "step": 249
    },
    {
      "epoch": 0.4892367906066536,
      "grad_norm": NaN,
      "learning_rate": 7.05809427180609e-05,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.4911937377690802,
      "grad_norm": NaN,
      "learning_rate": 7.023203469881273e-05,
      "loss": 0.0,
      "step": 251
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": NaN,
      "learning_rate": 6.98819445813857e-05,
      "loss": 0.0,
      "step": 252
    },
    {
      "epoch": 0.49510763209393344,
      "grad_norm": NaN,
      "learning_rate": 6.953069282051396e-05,
      "loss": 0.0,
      "step": 253
    },
    {
      "epoch": 0.49706457925636005,
      "grad_norm": NaN,
      "learning_rate": 6.917829993880302e-05,
      "loss": 0.0,
      "step": 254
    },
    {
      "epoch": 0.49902152641878667,
      "grad_norm": NaN,
      "learning_rate": 6.88247865255307e-05,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 0.5009784735812133,
      "grad_norm": NaN,
      "learning_rate": 6.84701732354442e-05,
      "loss": 0.0,
      "step": 256
    },
    {
      "epoch": 0.50293542074364,
      "grad_norm": NaN,
      "learning_rate": 6.811448078755329e-05,
      "loss": 0.0,
      "step": 257
    },
    {
      "epoch": 0.5048923679060665,
      "grad_norm": NaN,
      "learning_rate": 6.775772996391974e-05,
      "loss": 0.0,
      "step": 258
    },
    {
      "epoch": 0.5068493150684932,
      "grad_norm": NaN,
      "learning_rate": 6.73999416084431e-05,
      "loss": 0.0,
      "step": 259
    },
    {
      "epoch": 0.5088062622309197,
      "grad_norm": NaN,
      "learning_rate": 6.704113662564284e-05,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.5107632093933464,
      "grad_norm": NaN,
      "learning_rate": 6.668133597943699e-05,
      "loss": 0.0,
      "step": 261
    },
    {
      "epoch": 0.512720156555773,
      "grad_norm": NaN,
      "learning_rate": 6.632056069191723e-05,
      "loss": 0.0,
      "step": 262
    },
    {
      "epoch": 0.5146771037181996,
      "grad_norm": NaN,
      "learning_rate": 6.595883184212067e-05,
      "loss": 0.0,
      "step": 263
    },
    {
      "epoch": 0.5166340508806262,
      "grad_norm": NaN,
      "learning_rate": 6.559617056479827e-05,
      "loss": 0.0,
      "step": 264
    },
    {
      "epoch": 0.5185909980430529,
      "grad_norm": NaN,
      "learning_rate": 6.523259804918e-05,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": NaN,
      "learning_rate": 6.486813553773673e-05,
      "loss": 0.0,
      "step": 266
    },
    {
      "epoch": 0.5225048923679061,
      "grad_norm": NaN,
      "learning_rate": 6.450280432493925e-05,
      "loss": 0.0,
      "step": 267
    },
    {
      "epoch": 0.5244618395303327,
      "grad_norm": NaN,
      "learning_rate": 6.413662575601391e-05,
      "loss": 0.0,
      "step": 268
    },
    {
      "epoch": 0.5264187866927593,
      "grad_norm": NaN,
      "learning_rate": 6.376962122569567e-05,
      "loss": 0.0,
      "step": 269
    },
    {
      "epoch": 0.5283757338551859,
      "grad_norm": NaN,
      "learning_rate": 6.340181217697797e-05,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.5303326810176126,
      "grad_norm": NaN,
      "learning_rate": 6.303322009985984e-05,
      "loss": 0.0,
      "step": 271
    },
    {
      "epoch": 0.5322896281800391,
      "grad_norm": NaN,
      "learning_rate": 6.266386653009038e-05,
      "loss": 0.0,
      "step": 272
    },
    {
      "epoch": 0.5342465753424658,
      "grad_norm": NaN,
      "learning_rate": 6.229377304791048e-05,
      "loss": 0.0,
      "step": 273
    },
    {
      "epoch": 0.5362035225048923,
      "grad_norm": NaN,
      "learning_rate": 6.192296127679193e-05,
      "loss": 0.0,
      "step": 274
    },
    {
      "epoch": 0.538160469667319,
      "grad_norm": NaN,
      "learning_rate": 6.155145288217398e-05,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 0.5401174168297456,
      "grad_norm": NaN,
      "learning_rate": 6.117926957019758e-05,
      "loss": 0.0,
      "step": 276
    },
    {
      "epoch": 0.5420743639921722,
      "grad_norm": NaN,
      "learning_rate": 6.0806433086437095e-05,
      "loss": 0.0,
      "step": 277
    },
    {
      "epoch": 0.5440313111545988,
      "grad_norm": NaN,
      "learning_rate": 6.043296521462982e-05,
      "loss": 0.0,
      "step": 278
    },
    {
      "epoch": 0.5459882583170255,
      "grad_norm": NaN,
      "learning_rate": 6.005888777540319e-05,
      "loss": 0.0,
      "step": 279
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": NaN,
      "learning_rate": 5.968422262499983e-05,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.5499021526418787,
      "grad_norm": NaN,
      "learning_rate": 5.930899165400062e-05,
      "loss": 0.0,
      "step": 281
    },
    {
      "epoch": 0.5518590998043053,
      "grad_norm": NaN,
      "learning_rate": 5.893321678604568e-05,
      "loss": 0.0,
      "step": 282
    },
    {
      "epoch": 0.5538160469667319,
      "grad_norm": NaN,
      "learning_rate": 5.8556919976553406e-05,
      "loss": 0.0,
      "step": 283
    },
    {
      "epoch": 0.5557729941291585,
      "grad_norm": NaN,
      "learning_rate": 5.818012321143773e-05,
      "loss": 0.0,
      "step": 284
    },
    {
      "epoch": 0.5577299412915852,
      "grad_norm": NaN,
      "learning_rate": 5.7802848505823485e-05,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.5596868884540117,
      "grad_norm": NaN,
      "learning_rate": 5.7425117902760194e-05,
      "loss": 0.0,
      "step": 286
    },
    {
      "epoch": 0.5616438356164384,
      "grad_norm": NaN,
      "learning_rate": 5.7046953471934086e-05,
      "loss": 0.0,
      "step": 287
    },
    {
      "epoch": 0.5636007827788649,
      "grad_norm": NaN,
      "learning_rate": 5.6668377308378694e-05,
      "loss": 0.0,
      "step": 288
    },
    {
      "epoch": 0.5655577299412916,
      "grad_norm": NaN,
      "learning_rate": 5.6289411531183875e-05,
      "loss": 0.0,
      "step": 289
    },
    {
      "epoch": 0.5675146771037182,
      "grad_norm": NaN,
      "learning_rate": 5.591007828220346e-05,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.5694716242661448,
      "grad_norm": NaN,
      "learning_rate": 5.553039972476158e-05,
      "loss": 0.0,
      "step": 291
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 5.515039804235772e-05,
      "loss": 0.0,
      "step": 292
    },
    {
      "epoch": 0.5733855185909981,
      "grad_norm": NaN,
      "learning_rate": 5.477009543737062e-05,
      "loss": 0.0,
      "step": 293
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": NaN,
      "learning_rate": 5.4389514129760985e-05,
      "loss": 0.0,
      "step": 294
    },
    {
      "epoch": 0.5772994129158513,
      "grad_norm": NaN,
      "learning_rate": 5.4008676355773344e-05,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 0.5792563600782779,
      "grad_norm": NaN,
      "learning_rate": 5.362760436663681e-05,
      "loss": 0.0,
      "step": 296
    },
    {
      "epoch": 0.5812133072407045,
      "grad_norm": NaN,
      "learning_rate": 5.324632042726494e-05,
      "loss": 0.0,
      "step": 297
    },
    {
      "epoch": 0.5831702544031311,
      "grad_norm": NaN,
      "learning_rate": 5.286484681495499e-05,
      "loss": 0.0,
      "step": 298
    },
    {
      "epoch": 0.5851272015655578,
      "grad_norm": NaN,
      "learning_rate": 5.24832058180862e-05,
      "loss": 0.0,
      "step": 299
    },
    {
      "epoch": 0.5870841487279843,
      "grad_norm": NaN,
      "learning_rate": 5.21014197348176e-05,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.589041095890411,
      "grad_norm": NaN,
      "learning_rate": 5.1719510871785194e-05,
      "loss": 0.0,
      "step": 301
    },
    {
      "epoch": 0.5909980430528375,
      "grad_norm": NaN,
      "learning_rate": 5.133750154279866e-05,
      "loss": 0.0,
      "step": 302
    },
    {
      "epoch": 0.5929549902152642,
      "grad_norm": NaN,
      "learning_rate": 5.09554140675376e-05,
      "loss": 0.0,
      "step": 303
    },
    {
      "epoch": 0.5949119373776908,
      "grad_norm": NaN,
      "learning_rate": 5.057327077024745e-05,
      "loss": 0.0,
      "step": 304
    },
    {
      "epoch": 0.5968688845401174,
      "grad_norm": NaN,
      "learning_rate": 5.01910939784352e-05,
      "loss": 0.0,
      "step": 305
    },
    {
      "epoch": 0.598825831702544,
      "grad_norm": NaN,
      "learning_rate": 4.98089060215648e-05,
      "loss": 0.0,
      "step": 306
    },
    {
      "epoch": 0.6007827788649707,
      "grad_norm": NaN,
      "learning_rate": 4.942672922975255e-05,
      "loss": 0.0,
      "step": 307
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": NaN,
      "learning_rate": 4.90445859324624e-05,
      "loss": 0.0,
      "step": 308
    },
    {
      "epoch": 0.6046966731898239,
      "grad_norm": NaN,
      "learning_rate": 4.866249845720133e-05,
      "loss": 0.0,
      "step": 309
    },
    {
      "epoch": 0.6066536203522505,
      "grad_norm": NaN,
      "learning_rate": 4.8280489128214804e-05,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.6086105675146771,
      "grad_norm": NaN,
      "learning_rate": 4.7898580265182395e-05,
      "loss": 0.0,
      "step": 311
    },
    {
      "epoch": 0.6105675146771037,
      "grad_norm": NaN,
      "learning_rate": 4.7516794181913806e-05,
      "loss": 0.0,
      "step": 312
    },
    {
      "epoch": 0.6125244618395304,
      "grad_norm": NaN,
      "learning_rate": 4.7135153185045014e-05,
      "loss": 0.0,
      "step": 313
    },
    {
      "epoch": 0.6144814090019569,
      "grad_norm": NaN,
      "learning_rate": 4.675367957273505e-05,
      "loss": 0.0,
      "step": 314
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": NaN,
      "learning_rate": 4.6372395633363204e-05,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 0.6183953033268101,
      "grad_norm": NaN,
      "learning_rate": 4.599132364422666e-05,
      "loss": 0.0,
      "step": 316
    },
    {
      "epoch": 0.6203522504892368,
      "grad_norm": NaN,
      "learning_rate": 4.5610485870239026e-05,
      "loss": 0.0,
      "step": 317
    },
    {
      "epoch": 0.6223091976516634,
      "grad_norm": NaN,
      "learning_rate": 4.5229904562629394e-05,
      "loss": 0.0,
      "step": 318
    },
    {
      "epoch": 0.62426614481409,
      "grad_norm": NaN,
      "learning_rate": 4.484960195764229e-05,
      "loss": 0.0,
      "step": 319
    },
    {
      "epoch": 0.6262230919765166,
      "grad_norm": NaN,
      "learning_rate": 4.446960027523843e-05,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.6281800391389433,
      "grad_norm": NaN,
      "learning_rate": 4.408992171779655e-05,
      "loss": 0.0,
      "step": 321
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": NaN,
      "learning_rate": 4.3710588468816136e-05,
      "loss": 0.0,
      "step": 322
    },
    {
      "epoch": 0.6320939334637965,
      "grad_norm": NaN,
      "learning_rate": 4.333162269162132e-05,
      "loss": 0.0,
      "step": 323
    },
    {
      "epoch": 0.6340508806262231,
      "grad_norm": NaN,
      "learning_rate": 4.295304652806592e-05,
      "loss": 0.0,
      "step": 324
    },
    {
      "epoch": 0.6360078277886497,
      "grad_norm": NaN,
      "learning_rate": 4.257488209723982e-05,
      "loss": 0.0,
      "step": 325
    },
    {
      "epoch": 0.6379647749510763,
      "grad_norm": NaN,
      "learning_rate": 4.219715149417652e-05,
      "loss": 0.0,
      "step": 326
    },
    {
      "epoch": 0.639921722113503,
      "grad_norm": NaN,
      "learning_rate": 4.181987678856229e-05,
      "loss": 0.0,
      "step": 327
    },
    {
      "epoch": 0.6418786692759295,
      "grad_norm": NaN,
      "learning_rate": 4.14430800234466e-05,
      "loss": 0.0,
      "step": 328
    },
    {
      "epoch": 0.6438356164383562,
      "grad_norm": NaN,
      "learning_rate": 4.1066783213954334e-05,
      "loss": 0.0,
      "step": 329
    },
    {
      "epoch": 0.6457925636007827,
      "grad_norm": NaN,
      "learning_rate": 4.0691008345999395e-05,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.6477495107632094,
      "grad_norm": NaN,
      "learning_rate": 4.031577737500018e-05,
      "loss": 0.0,
      "step": 331
    },
    {
      "epoch": 0.649706457925636,
      "grad_norm": NaN,
      "learning_rate": 3.994111222459682e-05,
      "loss": 0.0,
      "step": 332
    },
    {
      "epoch": 0.6516634050880626,
      "grad_norm": NaN,
      "learning_rate": 3.9567034785370184e-05,
      "loss": 0.0,
      "step": 333
    },
    {
      "epoch": 0.6536203522504892,
      "grad_norm": NaN,
      "learning_rate": 3.919356691356292e-05,
      "loss": 0.0,
      "step": 334
    },
    {
      "epoch": 0.6555772994129159,
      "grad_norm": NaN,
      "learning_rate": 3.882073042980245e-05,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": NaN,
      "learning_rate": 3.844854711782605e-05,
      "loss": 0.0,
      "step": 336
    },
    {
      "epoch": 0.6594911937377691,
      "grad_norm": NaN,
      "learning_rate": 3.807703872320809e-05,
      "loss": 0.0,
      "step": 337
    },
    {
      "epoch": 0.6614481409001957,
      "grad_norm": NaN,
      "learning_rate": 3.770622695208953e-05,
      "loss": 0.0,
      "step": 338
    },
    {
      "epoch": 0.6634050880626223,
      "grad_norm": NaN,
      "learning_rate": 3.733613346990963e-05,
      "loss": 0.0,
      "step": 339
    },
    {
      "epoch": 0.6653620352250489,
      "grad_norm": NaN,
      "learning_rate": 3.6966779900140194e-05,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 0.6673189823874756,
      "grad_norm": NaN,
      "learning_rate": 3.659818782302206e-05,
      "loss": 0.0,
      "step": 341
    },
    {
      "epoch": 0.6692759295499021,
      "grad_norm": NaN,
      "learning_rate": 3.623037877430434e-05,
      "loss": 0.0,
      "step": 342
    },
    {
      "epoch": 0.6712328767123288,
      "grad_norm": NaN,
      "learning_rate": 3.5863374243986094e-05,
      "loss": 0.0,
      "step": 343
    },
    {
      "epoch": 0.6731898238747553,
      "grad_norm": NaN,
      "learning_rate": 3.5497195675060765e-05,
      "loss": 0.0,
      "step": 344
    },
    {
      "epoch": 0.675146771037182,
      "grad_norm": NaN,
      "learning_rate": 3.513186446226327e-05,
      "loss": 0.0,
      "step": 345
    },
    {
      "epoch": 0.6771037181996086,
      "grad_norm": NaN,
      "learning_rate": 3.476740195082e-05,
      "loss": 0.0,
      "step": 346
    },
    {
      "epoch": 0.6790606653620352,
      "grad_norm": NaN,
      "learning_rate": 3.440382943520172e-05,
      "loss": 0.0,
      "step": 347
    },
    {
      "epoch": 0.6810176125244618,
      "grad_norm": NaN,
      "learning_rate": 3.404116815787933e-05,
      "loss": 0.0,
      "step": 348
    },
    {
      "epoch": 0.6829745596868885,
      "grad_norm": NaN,
      "learning_rate": 3.367943930808278e-05,
      "loss": 0.0,
      "step": 349
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": NaN,
      "learning_rate": 3.331866402056302e-05,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.6868884540117417,
      "grad_norm": NaN,
      "learning_rate": 3.295886337435717e-05,
      "loss": 0.0,
      "step": 351
    },
    {
      "epoch": 0.6888454011741683,
      "grad_norm": NaN,
      "learning_rate": 3.260005839155691e-05,
      "loss": 0.0,
      "step": 352
    },
    {
      "epoch": 0.6908023483365949,
      "grad_norm": NaN,
      "learning_rate": 3.224227003608027e-05,
      "loss": 0.0,
      "step": 353
    },
    {
      "epoch": 0.6927592954990215,
      "grad_norm": NaN,
      "learning_rate": 3.1885519212446716e-05,
      "loss": 0.0,
      "step": 354
    },
    {
      "epoch": 0.6947162426614482,
      "grad_norm": NaN,
      "learning_rate": 3.1529826764555806e-05,
      "loss": 0.0,
      "step": 355
    },
    {
      "epoch": 0.6966731898238747,
      "grad_norm": NaN,
      "learning_rate": 3.117521347446931e-05,
      "loss": 0.0,
      "step": 356
    },
    {
      "epoch": 0.6986301369863014,
      "grad_norm": NaN,
      "learning_rate": 3.082170006119698e-05,
      "loss": 0.0,
      "step": 357
    },
    {
      "epoch": 0.700587084148728,
      "grad_norm": NaN,
      "learning_rate": 3.046930717948604e-05,
      "loss": 0.0,
      "step": 358
    },
    {
      "epoch": 0.7025440313111546,
      "grad_norm": NaN,
      "learning_rate": 3.01180554186143e-05,
      "loss": 0.0,
      "step": 359
    },
    {
      "epoch": 0.7045009784735812,
      "grad_norm": NaN,
      "learning_rate": 2.9767965301187285e-05,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.7064579256360078,
      "grad_norm": NaN,
      "learning_rate": 2.9419057281939104e-05,
      "loss": 0.0,
      "step": 361
    },
    {
      "epoch": 0.7084148727984344,
      "grad_norm": NaN,
      "learning_rate": 2.9071351746537357e-05,
      "loss": 0.0,
      "step": 362
    },
    {
      "epoch": 0.7103718199608611,
      "grad_norm": NaN,
      "learning_rate": 2.8724869010392042e-05,
      "loss": 0.0,
      "step": 363
    },
    {
      "epoch": 0.7123287671232876,
      "grad_norm": NaN,
      "learning_rate": 2.8379629317468604e-05,
      "loss": 0.0,
      "step": 364
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": NaN,
      "learning_rate": 2.8035652839105155e-05,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 0.7162426614481409,
      "grad_norm": NaN,
      "learning_rate": 2.7692959672833857e-05,
      "loss": 0.0,
      "step": 366
    },
    {
      "epoch": 0.7181996086105675,
      "grad_norm": NaN,
      "learning_rate": 2.7351569841206793e-05,
      "loss": 0.0,
      "step": 367
    },
    {
      "epoch": 0.7201565557729941,
      "grad_norm": NaN,
      "learning_rate": 2.7011503290625985e-05,
      "loss": 0.0,
      "step": 368
    },
    {
      "epoch": 0.7221135029354208,
      "grad_norm": NaN,
      "learning_rate": 2.6672779890178047e-05,
      "loss": 0.0,
      "step": 369
    },
    {
      "epoch": 0.7240704500978473,
      "grad_norm": NaN,
      "learning_rate": 2.633541943047334e-05,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.726027397260274,
      "grad_norm": NaN,
      "learning_rate": 2.5999441622489533e-05,
      "loss": 0.0,
      "step": 371
    },
    {
      "epoch": 0.7279843444227005,
      "grad_norm": NaN,
      "learning_rate": 2.5664866096420114e-05,
      "loss": 0.0,
      "step": 372
    },
    {
      "epoch": 0.7299412915851272,
      "grad_norm": NaN,
      "learning_rate": 2.5331712400527298e-05,
      "loss": 0.0,
      "step": 373
    },
    {
      "epoch": 0.7318982387475538,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 374
    },
    {
      "epoch": 0.7338551859099804,
      "grad_norm": NaN,
      "learning_rate": 2.4669748275816472e-05,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 0.735812133072407,
      "grad_norm": NaN,
      "learning_rate": 2.4340976523611957e-05,
      "loss": 0.0,
      "step": 376
    },
    {
      "epoch": 0.7377690802348337,
      "grad_norm": NaN,
      "learning_rate": 2.4013703952551292e-05,
      "loss": 0.0,
      "step": 377
    },
    {
      "epoch": 0.7397260273972602,
      "grad_norm": NaN,
      "learning_rate": 2.368794968420655e-05,
      "loss": 0.0,
      "step": 378
    },
    {
      "epoch": 0.7416829745596869,
      "grad_norm": NaN,
      "learning_rate": 2.3363732751439925e-05,
      "loss": 0.0,
      "step": 379
    },
    {
      "epoch": 0.7436399217221135,
      "grad_norm": NaN,
      "learning_rate": 2.3041072097291528e-05,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 0.7455968688845401,
      "grad_norm": NaN,
      "learning_rate": 2.2719986573872765e-05,
      "loss": 0.0,
      "step": 381
    },
    {
      "epoch": 0.7475538160469667,
      "grad_norm": NaN,
      "learning_rate": 2.2400494941264787e-05,
      "loss": 0.0,
      "step": 382
    },
    {
      "epoch": 0.7495107632093934,
      "grad_norm": NaN,
      "learning_rate": 2.208261586642235e-05,
      "loss": 0.0,
      "step": 383
    },
    {
      "epoch": 0.7514677103718199,
      "grad_norm": NaN,
      "learning_rate": 2.1766367922083287e-05,
      "loss": 0.0,
      "step": 384
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": NaN,
      "learning_rate": 2.1451769585683197e-05,
      "loss": 0.0,
      "step": 385
    },
    {
      "epoch": 0.7553816046966731,
      "grad_norm": NaN,
      "learning_rate": 2.1138839238276025e-05,
      "loss": 0.0,
      "step": 386
    },
    {
      "epoch": 0.7573385518590998,
      "grad_norm": NaN,
      "learning_rate": 2.082759516345999e-05,
      "loss": 0.0,
      "step": 387
    },
    {
      "epoch": 0.7592954990215264,
      "grad_norm": NaN,
      "learning_rate": 2.0518055546309362e-05,
      "loss": 0.0,
      "step": 388
    },
    {
      "epoch": 0.761252446183953,
      "grad_norm": NaN,
      "learning_rate": 2.021023847231202e-05,
      "loss": 0.0,
      "step": 389
    },
    {
      "epoch": 0.7632093933463796,
      "grad_norm": NaN,
      "learning_rate": 1.9904161926312658e-05,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.7651663405088063,
      "grad_norm": NaN,
      "learning_rate": 1.9599843791462123e-05,
      "loss": 0.0,
      "step": 391
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": NaN,
      "learning_rate": 1.9297301848172395e-05,
      "loss": 0.0,
      "step": 392
    },
    {
      "epoch": 0.7690802348336595,
      "grad_norm": NaN,
      "learning_rate": 1.899655377307789e-05,
      "loss": 0.0,
      "step": 393
    },
    {
      "epoch": 0.7710371819960861,
      "grad_norm": NaN,
      "learning_rate": 1.8697617138002543e-05,
      "loss": 0.0,
      "step": 394
    },
    {
      "epoch": 0.7729941291585127,
      "grad_norm": NaN,
      "learning_rate": 1.8400509408933188e-05,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 0.7749510763209393,
      "grad_norm": NaN,
      "learning_rate": 1.81052479449991e-05,
      "loss": 0.0,
      "step": 396
    },
    {
      "epoch": 0.776908023483366,
      "grad_norm": NaN,
      "learning_rate": 1.781184999745768e-05,
      "loss": 0.0,
      "step": 397
    },
    {
      "epoch": 0.7788649706457925,
      "grad_norm": NaN,
      "learning_rate": 1.7520332708686615e-05,
      "loss": 0.0,
      "step": 398
    },
    {
      "epoch": 0.7808219178082192,
      "grad_norm": NaN,
      "learning_rate": 1.7230713111182168e-05,
      "loss": 0.0,
      "step": 399
    },
    {
      "epoch": 0.7827788649706457,
      "grad_norm": NaN,
      "learning_rate": 1.6943008126564163e-05,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.7847358121330724,
      "grad_norm": NaN,
      "learning_rate": 1.6657234564587182e-05,
      "loss": 0.0,
      "step": 401
    },
    {
      "epoch": 0.786692759295499,
      "grad_norm": NaN,
      "learning_rate": 1.6373409122158478e-05,
      "loss": 0.0,
      "step": 402
    },
    {
      "epoch": 0.7886497064579256,
      "grad_norm": NaN,
      "learning_rate": 1.6091548382362458e-05,
      "loss": 0.0,
      "step": 403
    },
    {
      "epoch": 0.7906066536203522,
      "grad_norm": NaN,
      "learning_rate": 1.58116688134917e-05,
      "loss": 0.0,
      "step": 404
    },
    {
      "epoch": 0.7925636007827789,
      "grad_norm": NaN,
      "learning_rate": 1.553378676808483e-05,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 0.7945205479452054,
      "grad_norm": NaN,
      "learning_rate": 1.5257918481971028e-05,
      "loss": 0.0,
      "step": 406
    },
    {
      "epoch": 0.7964774951076321,
      "grad_norm": NaN,
      "learning_rate": 1.4984080073321511e-05,
      "loss": 0.0,
      "step": 407
    },
    {
      "epoch": 0.7984344422700587,
      "grad_norm": NaN,
      "learning_rate": 1.4712287541707681e-05,
      "loss": 0.0,
      "step": 408
    },
    {
      "epoch": 0.8003913894324853,
      "grad_norm": NaN,
      "learning_rate": 1.444255676716637e-05,
      "loss": 0.0,
      "step": 409
    },
    {
      "epoch": 0.8023483365949119,
      "grad_norm": NaN,
      "learning_rate": 1.4174903509272087e-05,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.8043052837573386,
      "grad_norm": NaN,
      "learning_rate": 1.3909343406216068e-05,
      "loss": 0.0,
      "step": 411
    },
    {
      "epoch": 0.8062622309197651,
      "grad_norm": NaN,
      "learning_rate": 1.3645891973892772e-05,
      "loss": 0.0,
      "step": 412
    },
    {
      "epoch": 0.8082191780821918,
      "grad_norm": NaN,
      "learning_rate": 1.3384564604993161e-05,
      "loss": 0.0,
      "step": 413
    },
    {
      "epoch": 0.8101761252446184,
      "grad_norm": NaN,
      "learning_rate": 1.3125376568105491e-05,
      "loss": 0.0,
      "step": 414
    },
    {
      "epoch": 0.812133072407045,
      "grad_norm": NaN,
      "learning_rate": 1.2868343006823114e-05,
      "loss": 0.0,
      "step": 415
    },
    {
      "epoch": 0.8140900195694716,
      "grad_norm": NaN,
      "learning_rate": 1.2613478938859718e-05,
      "loss": 0.0,
      "step": 416
    },
    {
      "epoch": 0.8160469667318982,
      "grad_norm": NaN,
      "learning_rate": 1.2360799255171929e-05,
      "loss": 0.0,
      "step": 417
    },
    {
      "epoch": 0.8180039138943248,
      "grad_norm": NaN,
      "learning_rate": 1.2110318719089158e-05,
      "loss": 0.0,
      "step": 418
    },
    {
      "epoch": 0.8199608610567515,
      "grad_norm": NaN,
      "learning_rate": 1.1862051965451215e-05,
      "loss": 0.0,
      "step": 419
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": NaN,
      "learning_rate": 1.1616013499753031e-05,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.8238747553816047,
      "grad_norm": NaN,
      "learning_rate": 1.1372217697297249e-05,
      "loss": 0.0,
      "step": 421
    },
    {
      "epoch": 0.8258317025440313,
      "grad_norm": NaN,
      "learning_rate": 1.113067880235435e-05,
      "loss": 0.0,
      "step": 422
    },
    {
      "epoch": 0.8277886497064579,
      "grad_norm": NaN,
      "learning_rate": 1.0891410927330303e-05,
      "loss": 0.0,
      "step": 423
    },
    {
      "epoch": 0.8297455968688845,
      "grad_norm": NaN,
      "learning_rate": 1.065442805194214e-05,
      "loss": 0.0,
      "step": 424
    },
    {
      "epoch": 0.8317025440313112,
      "grad_norm": NaN,
      "learning_rate": 1.0419744022401018e-05,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 0.8336594911937377,
      "grad_norm": NaN,
      "learning_rate": 1.018737255060338e-05,
      "loss": 0.0,
      "step": 426
    },
    {
      "epoch": 0.8356164383561644,
      "grad_norm": NaN,
      "learning_rate": 9.957327213329687e-06,
      "loss": 0.0,
      "step": 427
    },
    {
      "epoch": 0.837573385518591,
      "grad_norm": NaN,
      "learning_rate": 9.72962145145121e-06,
      "loss": 0.0,
      "step": 428
    },
    {
      "epoch": 0.8395303326810176,
      "grad_norm": NaN,
      "learning_rate": 9.504268569144763e-06,
      "loss": 0.0,
      "step": 429
    },
    {
      "epoch": 0.8414872798434442,
      "grad_norm": NaN,
      "learning_rate": 9.281281733115288e-06,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 0.8434442270058709,
      "grad_norm": NaN,
      "learning_rate": 9.060673971826666e-06,
      "loss": 0.0,
      "step": 431
    },
    {
      "epoch": 0.8454011741682974,
      "grad_norm": NaN,
      "learning_rate": 8.842458174740397e-06,
      "loss": 0.0,
      "step": 432
    },
    {
      "epoch": 0.8473581213307241,
      "grad_norm": NaN,
      "learning_rate": 8.626647091562612e-06,
      "loss": 0.0,
      "step": 433
    },
    {
      "epoch": 0.8493150684931506,
      "grad_norm": NaN,
      "learning_rate": 8.413253331499049e-06,
      "loss": 0.0,
      "step": 434
    },
    {
      "epoch": 0.8512720156555773,
      "grad_norm": NaN,
      "learning_rate": 8.2022893625184e-06,
      "loss": 0.0,
      "step": 435
    },
    {
      "epoch": 0.8532289628180039,
      "grad_norm": NaN,
      "learning_rate": 7.993767510623834e-06,
      "loss": 0.0,
      "step": 436
    },
    {
      "epoch": 0.8551859099804305,
      "grad_norm": NaN,
      "learning_rate": 7.787699959132771e-06,
      "loss": 0.0,
      "step": 437
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": NaN,
      "learning_rate": 7.584098747965157e-06,
      "loss": 0.0,
      "step": 438
    },
    {
      "epoch": 0.8590998043052838,
      "grad_norm": NaN,
      "learning_rate": 7.382975772939865e-06,
      "loss": 0.0,
      "step": 439
    },
    {
      "epoch": 0.8610567514677103,
      "grad_norm": NaN,
      "learning_rate": 7.184342785079795e-06,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.863013698630137,
      "grad_norm": NaN,
      "learning_rate": 6.988211389925192e-06,
      "loss": 0.0,
      "step": 441
    },
    {
      "epoch": 0.8649706457925636,
      "grad_norm": NaN,
      "learning_rate": 6.794593046855613e-06,
      "loss": 0.0,
      "step": 442
    },
    {
      "epoch": 0.8669275929549902,
      "grad_norm": NaN,
      "learning_rate": 6.6034990684204155e-06,
      "loss": 0.0,
      "step": 443
    },
    {
      "epoch": 0.8688845401174168,
      "grad_norm": NaN,
      "learning_rate": 6.414940619677734e-06,
      "loss": 0.0,
      "step": 444
    },
    {
      "epoch": 0.8708414872798435,
      "grad_norm": NaN,
      "learning_rate": 6.228928717542204e-06,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 0.87279843444227,
      "grad_norm": NaN,
      "learning_rate": 6.045474230141207e-06,
      "loss": 0.0,
      "step": 446
    },
    {
      "epoch": 0.8747553816046967,
      "grad_norm": NaN,
      "learning_rate": 5.864587876179961e-06,
      "loss": 0.0,
      "step": 447
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": NaN,
      "learning_rate": 5.686280224315188e-06,
      "loss": 0.0,
      "step": 448
    },
    {
      "epoch": 0.8786692759295499,
      "grad_norm": NaN,
      "learning_rate": 5.51056169253763e-06,
      "loss": 0.0,
      "step": 449
    },
    {
      "epoch": 0.8806262230919765,
      "grad_norm": NaN,
      "learning_rate": 5.337442547563415e-06,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.8825831702544031,
      "grad_norm": NaN,
      "learning_rate": 5.166932904234101e-06,
      "loss": 0.0,
      "step": 451
    },
    {
      "epoch": 0.8845401174168297,
      "grad_norm": NaN,
      "learning_rate": 4.9990427249258175e-06,
      "loss": 0.0,
      "step": 452
    },
    {
      "epoch": 0.8864970645792564,
      "grad_norm": NaN,
      "learning_rate": 4.833781818967064e-06,
      "loss": 0.0,
      "step": 453
    },
    {
      "epoch": 0.8884540117416829,
      "grad_norm": NaN,
      "learning_rate": 4.671159842065698e-06,
      "loss": 0.0,
      "step": 454
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": NaN,
      "learning_rate": 4.51118629574469e-06,
      "loss": 0.0,
      "step": 455
    },
    {
      "epoch": 0.8923679060665362,
      "grad_norm": NaN,
      "learning_rate": 4.353870526787035e-06,
      "loss": 0.0,
      "step": 456
    },
    {
      "epoch": 0.8943248532289628,
      "grad_norm": NaN,
      "learning_rate": 4.199221726689634e-06,
      "loss": 0.0,
      "step": 457
    },
    {
      "epoch": 0.8962818003913894,
      "grad_norm": NaN,
      "learning_rate": 4.0472489311262356e-06,
      "loss": 0.0,
      "step": 458
    },
    {
      "epoch": 0.898238747553816,
      "grad_norm": NaN,
      "learning_rate": 3.897961019419516e-06,
      "loss": 0.0,
      "step": 459
    },
    {
      "epoch": 0.9001956947162426,
      "grad_norm": NaN,
      "learning_rate": 3.7513667140223417e-06,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 0.9021526418786693,
      "grad_norm": NaN,
      "learning_rate": 3.6074745800080577e-06,
      "loss": 0.0,
      "step": 461
    },
    {
      "epoch": 0.9041095890410958,
      "grad_norm": NaN,
      "learning_rate": 3.4662930245701276e-06,
      "loss": 0.0,
      "step": 462
    },
    {
      "epoch": 0.9060665362035225,
      "grad_norm": NaN,
      "learning_rate": 3.3278302965308596e-06,
      "loss": 0.0,
      "step": 463
    },
    {
      "epoch": 0.9080234833659491,
      "grad_norm": NaN,
      "learning_rate": 3.192094485859526e-06,
      "loss": 0.0,
      "step": 464
    },
    {
      "epoch": 0.9099804305283757,
      "grad_norm": NaN,
      "learning_rate": 3.05909352319963e-06,
      "loss": 0.0,
      "step": 465
    },
    {
      "epoch": 0.9119373776908023,
      "grad_norm": NaN,
      "learning_rate": 2.928835179405548e-06,
      "loss": 0.0,
      "step": 466
    },
    {
      "epoch": 0.913894324853229,
      "grad_norm": NaN,
      "learning_rate": 2.8013270650885548e-06,
      "loss": 0.0,
      "step": 467
    },
    {
      "epoch": 0.9158512720156555,
      "grad_norm": NaN,
      "learning_rate": 2.6765766301720896e-06,
      "loss": 0.0,
      "step": 468
    },
    {
      "epoch": 0.9178082191780822,
      "grad_norm": NaN,
      "learning_rate": 2.554591163456527e-06,
      "loss": 0.0,
      "step": 469
    },
    {
      "epoch": 0.9197651663405088,
      "grad_norm": NaN,
      "learning_rate": 2.435377792193272e-06,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 0.9217221135029354,
      "grad_norm": NaN,
      "learning_rate": 2.31894348166839e-06,
      "loss": 0.0,
      "step": 471
    },
    {
      "epoch": 0.923679060665362,
      "grad_norm": NaN,
      "learning_rate": 2.205295034795596e-06,
      "loss": 0.0,
      "step": 472
    },
    {
      "epoch": 0.9256360078277887,
      "grad_norm": NaN,
      "learning_rate": 2.094439091718797e-06,
      "loss": 0.0,
      "step": 473
    },
    {
      "epoch": 0.9275929549902152,
      "grad_norm": NaN,
      "learning_rate": 1.9863821294241526e-06,
      "loss": 0.0,
      "step": 474
    },
    {
      "epoch": 0.9295499021526419,
      "grad_norm": NaN,
      "learning_rate": 1.8811304613615909e-06,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 0.9315068493150684,
      "grad_norm": NaN,
      "learning_rate": 1.7786902370759916e-06,
      "loss": 0.0,
      "step": 476
    },
    {
      "epoch": 0.9334637964774951,
      "grad_norm": NaN,
      "learning_rate": 1.6790674418478369e-06,
      "loss": 0.0,
      "step": 477
    },
    {
      "epoch": 0.9354207436399217,
      "grad_norm": NaN,
      "learning_rate": 1.5822678963435478e-06,
      "loss": 0.0,
      "step": 478
    },
    {
      "epoch": 0.9373776908023483,
      "grad_norm": NaN,
      "learning_rate": 1.4882972562753617e-06,
      "loss": 0.0,
      "step": 479
    },
    {
      "epoch": 0.9393346379647749,
      "grad_norm": NaN,
      "learning_rate": 1.3971610120709189e-06,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 0.9412915851272016,
      "grad_norm": NaN,
      "learning_rate": 1.3088644885524637e-06,
      "loss": 0.0,
      "step": 481
    },
    {
      "epoch": 0.9432485322896281,
      "grad_norm": NaN,
      "learning_rate": 1.2234128446257208e-06,
      "loss": 0.0,
      "step": 482
    },
    {
      "epoch": 0.9452054794520548,
      "grad_norm": NaN,
      "learning_rate": 1.140811072978476e-06,
      "loss": 0.0,
      "step": 483
    },
    {
      "epoch": 0.9471624266144814,
      "grad_norm": NaN,
      "learning_rate": 1.0610639997888916e-06,
      "loss": 0.0,
      "step": 484
    },
    {
      "epoch": 0.949119373776908,
      "grad_norm": NaN,
      "learning_rate": 9.841762844434886e-07,
      "loss": 0.0,
      "step": 485
    },
    {
      "epoch": 0.9510763209393346,
      "grad_norm": NaN,
      "learning_rate": 9.101524192649591e-07,
      "loss": 0.0,
      "step": 486
    },
    {
      "epoch": 0.9530332681017613,
      "grad_norm": NaN,
      "learning_rate": 8.389967292496359e-07,
      "loss": 0.0,
      "step": 487
    },
    {
      "epoch": 0.9549902152641878,
      "grad_norm": NaN,
      "learning_rate": 7.707133718148518e-07,
      "loss": 0.0,
      "step": 488
    },
    {
      "epoch": 0.9569471624266145,
      "grad_norm": NaN,
      "learning_rate": 7.053063365559998e-07,
      "loss": 0.0,
      "step": 489
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": NaN,
      "learning_rate": 6.427794450134528e-07,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 0.9608610567514677,
      "grad_norm": NaN,
      "learning_rate": 5.831363504492482e-07,
      "loss": 0.0,
      "step": 491
    },
    {
      "epoch": 0.9628180039138943,
      "grad_norm": NaN,
      "learning_rate": 5.263805376336972e-07,
      "loss": 0.0,
      "step": 492
    },
    {
      "epoch": 0.9647749510763209,
      "grad_norm": NaN,
      "learning_rate": 4.7251532264170895e-07,
      "loss": 0.0,
      "step": 493
    },
    {
      "epoch": 0.9667318982387475,
      "grad_norm": NaN,
      "learning_rate": 4.2154385265910646e-07,
      "loss": 0.0,
      "step": 494
    },
    {
      "epoch": 0.9686888454011742,
      "grad_norm": NaN,
      "learning_rate": 3.734691057987016e-07,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 0.9706457925636007,
      "grad_norm": NaN,
      "learning_rate": 3.282938909263122e-07,
      "loss": 0.0,
      "step": 496
    },
    {
      "epoch": 0.9726027397260274,
      "grad_norm": NaN,
      "learning_rate": 2.86020847496643e-07,
      "loss": 0.0,
      "step": 497
    },
    {
      "epoch": 0.974559686888454,
      "grad_norm": NaN,
      "learning_rate": 2.4665244539908707e-07,
      "loss": 0.0,
      "step": 498
    },
    {
      "epoch": 0.9765166340508806,
      "grad_norm": NaN,
      "learning_rate": 2.101909848133743e-07,
      "loss": 0.0,
      "step": 499
    },
    {
      "epoch": 0.9784735812133072,
      "grad_norm": NaN,
      "learning_rate": 1.766385960752348e-07,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.9804305283757339,
      "grad_norm": NaN,
      "learning_rate": 1.459972395518816e-07,
      "loss": 0.0,
      "step": 501
    },
    {
      "epoch": 0.9823874755381604,
      "grad_norm": NaN,
      "learning_rate": 1.1826870552749669e-07,
      "loss": 0.0,
      "step": 502
    },
    {
      "epoch": 0.9843444227005871,
      "grad_norm": NaN,
      "learning_rate": 9.345461409863699e-08,
      "loss": 0.0,
      "step": 503
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": NaN,
      "learning_rate": 7.155641507955446e-08,
      "loss": 0.0,
      "step": 504
    },
    {
      "epoch": 0.9882583170254403,
      "grad_norm": NaN,
      "learning_rate": 5.257538791749172e-08,
      "loss": 0.0,
      "step": 505
    },
    {
      "epoch": 0.9902152641878669,
      "grad_norm": NaN,
      "learning_rate": 3.651264161794732e-08,
      "loss": 0.0,
      "step": 506
    },
    {
      "epoch": 0.9921722113502935,
      "grad_norm": NaN,
      "learning_rate": 2.3369114679866468e-08,
      "loss": 0.0,
      "step": 507
    },
    {
      "epoch": 0.9941291585127201,
      "grad_norm": NaN,
      "learning_rate": 1.3145575040801606e-08,
      "loss": 0.0,
      "step": 508
    },
    {
      "epoch": 0.9960861056751468,
      "grad_norm": NaN,
      "learning_rate": 5.842620032053825e-09,
      "loss": 0.0,
      "step": 509
    },
    {
      "epoch": 0.9980430528375733,
      "grad_norm": NaN,
      "learning_rate": 1.460676343767453e-09,
      "loss": 0.0,
      "step": 510
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 511
    }
  ],
  "logging_steps": 1,
  "max_steps": 511,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 239,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7125804330293658e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}