{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 17.142857142857142,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.000999404761904762,
      "loss": 3.0944,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0009988095238095238,
      "loss": 2.7802,
      "step": 2
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009982142857142857,
      "loss": 2.7798,
      "step": 3
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009976190476190477,
      "loss": 2.6729,
      "step": 4
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009970238095238096,
      "loss": 2.7544,
      "step": 5
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009964285714285715,
      "loss": 2.7115,
      "step": 6
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009958333333333334,
      "loss": 2.7491,
      "step": 7
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009952380952380953,
      "loss": 2.681,
      "step": 8
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0009946428571428571,
      "loss": 2.7396,
      "step": 9
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000994047619047619,
      "loss": 2.6911,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009934523809523809,
      "loss": 2.6725,
      "step": 11
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000992857142857143,
      "loss": 2.6951,
      "step": 12
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0009922619047619049,
      "loss": 2.6741,
      "step": 13
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009916666666666667,
      "loss": 2.6623,
      "step": 14
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009910714285714286,
      "loss": 2.6268,
      "step": 15
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009904761904761905,
      "loss": 2.6727,
      "step": 16
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0009898809523809524,
      "loss": 2.6174,
      "step": 17
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009892857142857142,
      "loss": 2.6544,
      "step": 18
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009886904761904763,
      "loss": 2.5404,
      "step": 19
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009880952380952382,
      "loss": 2.6286,
      "step": 20
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009875,
      "loss": 2.6824,
      "step": 21
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000986904761904762,
      "loss": 2.6012,
      "step": 22
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0009863095238095239,
      "loss": 2.6446,
      "step": 23
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0009857142857142857,
      "loss": 2.6437,
      "step": 24
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0009851190476190476,
      "loss": 2.6596,
      "step": 25
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0009845238095238097,
      "loss": 2.6554,
      "step": 26
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0009839285714285714,
      "loss": 2.6064,
      "step": 27
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009833333333333332,
      "loss": 2.5994,
      "step": 28
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0009827380952380951,
      "loss": 2.545,
      "step": 29
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0009821428571428572,
      "loss": 2.5704,
      "step": 30
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000981547619047619,
      "loss": 2.6461,
      "step": 31
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000980952380952381,
      "loss": 2.631,
      "step": 32
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0009803571428571428,
      "loss": 2.6678,
      "step": 33
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0009797619047619047,
      "loss": 2.5964,
      "step": 34
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0009791666666666666,
      "loss": 2.6566,
      "step": 35
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0009785714285714285,
      "loss": 2.4962,
      "step": 36
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0009779761904761906,
      "loss": 2.4815,
      "step": 37
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0009773809523809524,
      "loss": 2.4172,
      "step": 38
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0009767857142857143,
      "loss": 2.4641,
      "step": 39
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0009761904761904762,
      "loss": 2.4875,
      "step": 40
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0009755952380952381,
      "loss": 2.4486,
      "step": 41
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.000975,
      "loss": 2.4463,
      "step": 42
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0009744047619047619,
      "loss": 2.5063,
      "step": 43
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0009738095238095238,
      "loss": 2.4506,
      "step": 44
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0009732142857142857,
      "loss": 2.3862,
      "step": 45
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0009726190476190476,
      "loss": 2.4925,
      "step": 46
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0009720238095238096,
      "loss": 2.5,
      "step": 47
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0009714285714285714,
      "loss": 2.4658,
      "step": 48
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0009708333333333333,
      "loss": 2.3983,
      "step": 49
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0009702380952380953,
      "loss": 2.369,
      "step": 50
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0009696428571428572,
      "loss": 2.4849,
      "step": 51
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0009690476190476191,
      "loss": 2.4106,
      "step": 52
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0009684523809523809,
      "loss": 2.4363,
      "step": 53
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0009678571428571429,
      "loss": 2.4935,
      "step": 54
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0009672619047619048,
      "loss": 2.479,
      "step": 55
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0009666666666666667,
      "loss": 2.4299,
      "step": 56
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0009660714285714285,
      "loss": 2.3964,
      "step": 57
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0009654761904761905,
      "loss": 2.4865,
      "step": 58
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0009648809523809524,
      "loss": 2.3831,
      "step": 59
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0009642857142857143,
      "loss": 2.4304,
      "step": 60
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0009636904761904763,
      "loss": 2.4273,
      "step": 61
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0009630952380952382,
      "loss": 2.4427,
      "step": 62
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0009625,
      "loss": 2.4191,
      "step": 63
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0009619047619047619,
      "loss": 2.3902,
      "step": 64
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0009613095238095239,
      "loss": 2.4699,
      "step": 65
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0009607142857142858,
      "loss": 2.3978,
      "step": 66
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0009601190476190476,
      "loss": 2.4128,
      "step": 67
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0009595238095238095,
      "loss": 2.4585,
      "step": 68
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0009589285714285715,
      "loss": 2.4476,
      "step": 69
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0009583333333333334,
      "loss": 2.4231,
      "step": 70
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0009577380952380953,
      "loss": 2.2655,
      "step": 71
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0009571428571428573,
      "loss": 2.208,
      "step": 72
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0009565476190476191,
      "loss": 2.1758,
      "step": 73
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.000955952380952381,
      "loss": 2.3113,
      "step": 74
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0009553571428571429,
      "loss": 2.1739,
      "step": 75
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0009547619047619049,
      "loss": 2.2234,
      "step": 76
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0009541666666666667,
      "loss": 2.21,
      "step": 77
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0009535714285714286,
      "loss": 2.2316,
      "step": 78
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0009529761904761904,
      "loss": 2.2044,
      "step": 79
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0009523809523809524,
      "loss": 2.1784,
      "step": 80
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0009517857142857143,
      "loss": 2.2489,
      "step": 81
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0009511904761904761,
      "loss": 2.2003,
      "step": 82
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0009505952380952381,
      "loss": 2.169,
      "step": 83
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00095,
      "loss": 2.2303,
      "step": 84
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0009494047619047619,
      "loss": 2.1744,
      "step": 85
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0009488095238095238,
      "loss": 2.1904,
      "step": 86
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0009482142857142857,
      "loss": 2.222,
      "step": 87
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0009476190476190476,
      "loss": 2.2467,
      "step": 88
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0009470238095238095,
      "loss": 2.2241,
      "step": 89
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0009464285714285714,
      "loss": 2.2339,
      "step": 90
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0009458333333333334,
      "loss": 2.2339,
      "step": 91
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0009452380952380952,
      "loss": 2.1653,
      "step": 92
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0009446428571428571,
      "loss": 2.2954,
      "step": 93
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0009440476190476191,
      "loss": 2.2859,
      "step": 94
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.000943452380952381,
      "loss": 2.2107,
      "step": 95
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0009428571428571429,
      "loss": 2.2142,
      "step": 96
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0009422619047619047,
      "loss": 2.2433,
      "step": 97
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0009416666666666667,
      "loss": 2.2417,
      "step": 98
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0009410714285714286,
      "loss": 2.2045,
      "step": 99
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0009404761904761905,
      "loss": 2.293,
      "step": 100
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0009398809523809523,
      "loss": 2.2051,
      "step": 101
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0009392857142857143,
      "loss": 2.2889,
      "step": 102
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0009386904761904762,
      "loss": 2.2,
      "step": 103
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0009380952380952381,
      "loss": 2.2298,
      "step": 104
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0009375,
      "loss": 2.2722,
      "step": 105
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.000936904761904762,
      "loss": 2.0032,
      "step": 106
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0009363095238095238,
      "loss": 1.9269,
      "step": 107
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0009357142857142857,
      "loss": 1.916,
      "step": 108
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0009351190476190477,
      "loss": 1.9165,
      "step": 109
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0009345238095238096,
      "loss": 1.9296,
      "step": 110
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0009339285714285714,
      "loss": 1.954,
      "step": 111
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0009333333333333333,
      "loss": 1.9457,
      "step": 112
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0009327380952380953,
      "loss": 1.9135,
      "step": 113
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0009321428571428572,
      "loss": 1.9383,
      "step": 114
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0009315476190476191,
      "loss": 1.9057,
      "step": 115
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0009309523809523809,
      "loss": 1.9541,
      "step": 116
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0009303571428571429,
      "loss": 1.8827,
      "step": 117
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0009297619047619048,
      "loss": 1.899,
      "step": 118
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0009291666666666667,
      "loss": 1.9095,
      "step": 119
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0009285714285714287,
      "loss": 1.936,
      "step": 120
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0009279761904761905,
      "loss": 1.9224,
      "step": 121
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0009273809523809524,
      "loss": 1.9547,
      "step": 122
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0009267857142857143,
      "loss": 1.9323,
      "step": 123
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0009261904761904763,
      "loss": 1.9938,
      "step": 124
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0009255952380952382,
      "loss": 1.8674,
      "step": 125
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.000925,
      "loss": 1.95,
      "step": 126
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0009244047619047619,
      "loss": 1.9374,
      "step": 127
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0009238095238095239,
      "loss": 1.9456,
      "step": 128
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0009232142857142858,
      "loss": 1.9791,
      "step": 129
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0009226190476190477,
      "loss": 2.0047,
      "step": 130
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0009220238095238096,
      "loss": 1.9971,
      "step": 131
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0009214285714285714,
      "loss": 2.0267,
      "step": 132
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0009208333333333333,
      "loss": 1.9374,
      "step": 133
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0009202380952380952,
      "loss": 1.9793,
      "step": 134
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0009196428571428572,
      "loss": 2.0483,
      "step": 135
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.000919047619047619,
      "loss": 2.0003,
      "step": 136
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0009184523809523809,
      "loss": 2.0185,
      "step": 137
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0009178571428571428,
      "loss": 2.0517,
      "step": 138
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0009172619047619048,
      "loss": 1.9824,
      "step": 139
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0009166666666666666,
      "loss": 2.0383,
      "step": 140
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0009160714285714285,
      "loss": 1.6818,
      "step": 141
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0009154761904761905,
      "loss": 1.6208,
      "step": 142
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0009148809523809524,
      "loss": 1.6843,
      "step": 143
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0009142857142857143,
      "loss": 1.5885,
      "step": 144
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0009136904761904761,
      "loss": 1.5799,
      "step": 145
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0009130952380952381,
      "loss": 1.6334,
      "step": 146
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0009125,
      "loss": 1.6297,
      "step": 147
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0009119047619047619,
      "loss": 1.5929,
      "step": 148
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0009113095238095238,
      "loss": 1.6621,
      "step": 149
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0009107142857142857,
      "loss": 1.626,
      "step": 150
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0009101190476190476,
      "loss": 1.6138,
      "step": 151
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0009095238095238095,
      "loss": 1.6465,
      "step": 152
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0009089285714285715,
      "loss": 1.6622,
      "step": 153
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0009083333333333334,
      "loss": 1.6662,
      "step": 154
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0009077380952380952,
      "loss": 1.6348,
      "step": 155
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0009071428571428571,
      "loss": 1.6196,
      "step": 156
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0009065476190476191,
      "loss": 1.6766,
      "step": 157
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.000905952380952381,
      "loss": 1.7069,
      "step": 158
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0009053571428571429,
      "loss": 1.6848,
      "step": 159
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0009047619047619047,
      "loss": 1.6884,
      "step": 160
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0009041666666666667,
      "loss": 1.6721,
      "step": 161
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0009035714285714286,
      "loss": 1.7116,
      "step": 162
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0009029761904761905,
      "loss": 1.693,
      "step": 163
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0009023809523809525,
      "loss": 1.6826,
      "step": 164
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0009017857142857143,
      "loss": 1.7061,
      "step": 165
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0009011904761904762,
      "loss": 1.6964,
      "step": 166
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0009005952380952381,
      "loss": 1.7903,
      "step": 167
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0009000000000000001,
      "loss": 1.6829,
      "step": 168
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.000899404761904762,
      "loss": 1.7047,
      "step": 169
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0008988095238095238,
      "loss": 1.7671,
      "step": 170
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0008982142857142857,
      "loss": 1.7184,
      "step": 171
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0008976190476190477,
      "loss": 1.8213,
      "step": 172
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0008970238095238096,
      "loss": 1.7688,
      "step": 173
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0008964285714285715,
      "loss": 1.7522,
      "step": 174
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0008958333333333334,
      "loss": 1.7862,
      "step": 175
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.0008952380952380953,
      "loss": 1.3871,
      "step": 176
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0008946428571428572,
      "loss": 1.3491,
      "step": 177
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0008940476190476191,
      "loss": 1.3399,
      "step": 178
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0008934523809523811,
      "loss": 1.3569,
      "step": 179
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0008928571428571429,
      "loss": 1.3734,
      "step": 180
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0008922619047619048,
      "loss": 1.3151,
      "step": 181
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.0008916666666666667,
      "loss": 1.3243,
      "step": 182
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.0008910714285714287,
      "loss": 1.342,
      "step": 183
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0008904761904761904,
      "loss": 1.3664,
      "step": 184
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0008898809523809523,
      "loss": 1.3493,
      "step": 185
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0008892857142857142,
      "loss": 1.32,
      "step": 186
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0008886904761904762,
      "loss": 1.3978,
      "step": 187
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0008880952380952381,
      "loss": 1.3762,
      "step": 188
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.0008874999999999999,
      "loss": 1.4172,
      "step": 189
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0008869047619047619,
      "loss": 1.3817,
      "step": 190
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.0008863095238095238,
      "loss": 1.3779,
      "step": 191
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0008857142857142857,
      "loss": 1.378,
      "step": 192
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0008851190476190476,
      "loss": 1.4245,
      "step": 193
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0008845238095238095,
      "loss": 1.4425,
      "step": 194
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0008839285714285714,
      "loss": 1.4324,
      "step": 195
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.0008833333333333333,
      "loss": 1.4264,
      "step": 196
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.0008827380952380952,
      "loss": 1.4395,
      "step": 197
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.0008821428571428572,
      "loss": 1.4549,
      "step": 198
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.000881547619047619,
      "loss": 1.501,
      "step": 199
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0008809523809523809,
      "loss": 1.432,
      "step": 200
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.0008803571428571429,
      "loss": 1.4922,
      "step": 201
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.0008797619047619048,
      "loss": 1.4622,
      "step": 202
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0008791666666666667,
      "loss": 1.4794,
      "step": 203
    },
    {
      "epoch": 5.83,
      "learning_rate": 0.0008785714285714285,
      "loss": 1.4938,
      "step": 204
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.0008779761904761905,
      "loss": 1.4792,
      "step": 205
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.0008773809523809524,
      "loss": 1.5192,
      "step": 206
    },
    {
      "epoch": 5.91,
      "learning_rate": 0.0008767857142857143,
      "loss": 1.5055,
      "step": 207
    },
    {
      "epoch": 5.94,
      "learning_rate": 0.0008761904761904762,
      "loss": 1.5484,
      "step": 208
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.0008755952380952381,
      "loss": 1.5096,
      "step": 209
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.000875,
      "loss": 1.5298,
      "step": 210
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.0008744047619047619,
      "loss": 1.1704,
      "step": 211
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.0008738095238095239,
      "loss": 1.1261,
      "step": 212
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.0008732142857142858,
      "loss": 1.1144,
      "step": 213
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.0008726190476190476,
      "loss": 1.0984,
      "step": 214
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.0008720238095238095,
      "loss": 1.0704,
      "step": 215
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.0008714285714285715,
      "loss": 1.0655,
      "step": 216
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.0008708333333333334,
      "loss": 1.09,
      "step": 217
    },
    {
      "epoch": 6.23,
      "learning_rate": 0.0008702380952380953,
      "loss": 1.0619,
      "step": 218
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.0008696428571428571,
      "loss": 1.1633,
      "step": 219
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.0008690476190476191,
      "loss": 1.1022,
      "step": 220
    },
    {
      "epoch": 6.31,
      "learning_rate": 0.000868452380952381,
      "loss": 1.1057,
      "step": 221
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.0008678571428571429,
      "loss": 1.1279,
      "step": 222
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.0008672619047619049,
      "loss": 1.0915,
      "step": 223
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0008666666666666667,
      "loss": 1.1731,
      "step": 224
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0008660714285714286,
      "loss": 1.1352,
      "step": 225
    },
    {
      "epoch": 6.46,
      "learning_rate": 0.0008654761904761905,
      "loss": 1.1632,
      "step": 226
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.0008648809523809525,
      "loss": 1.1691,
      "step": 227
    },
    {
      "epoch": 6.51,
      "learning_rate": 0.0008642857142857144,
      "loss": 1.181,
      "step": 228
    },
    {
      "epoch": 6.54,
      "learning_rate": 0.0008636904761904762,
      "loss": 1.1635,
      "step": 229
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.0008630952380952381,
      "loss": 1.1802,
      "step": 230
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.0008625000000000001,
      "loss": 1.2111,
      "step": 231
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.000861904761904762,
      "loss": 1.2503,
      "step": 232
    },
    {
      "epoch": 6.66,
      "learning_rate": 0.0008613095238095238,
      "loss": 1.2305,
      "step": 233
    },
    {
      "epoch": 6.69,
      "learning_rate": 0.0008607142857142858,
      "loss": 1.2446,
      "step": 234
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0008601190476190477,
      "loss": 1.263,
      "step": 235
    },
    {
      "epoch": 6.74,
      "learning_rate": 0.0008595238095238096,
      "loss": 1.2407,
      "step": 236
    },
    {
      "epoch": 6.77,
      "learning_rate": 0.0008589285714285714,
      "loss": 1.303,
      "step": 237
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.0008583333333333333,
      "loss": 1.2309,
      "step": 238
    },
    {
      "epoch": 6.83,
      "learning_rate": 0.0008577380952380952,
      "loss": 1.2669,
      "step": 239
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.0008571428571428571,
      "loss": 1.226,
      "step": 240
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.000856547619047619,
      "loss": 1.2862,
      "step": 241
    },
    {
      "epoch": 6.91,
      "learning_rate": 0.000855952380952381,
      "loss": 1.2472,
      "step": 242
    },
    {
      "epoch": 6.94,
      "learning_rate": 0.0008553571428571428,
      "loss": 1.2928,
      "step": 243
    },
    {
      "epoch": 6.97,
      "learning_rate": 0.0008547619047619047,
      "loss": 1.2427,
      "step": 244
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0008541666666666666,
      "loss": 1.3195,
      "step": 245
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.0008535714285714286,
      "loss": 0.8949,
      "step": 246
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.0008529761904761905,
      "loss": 0.8907,
      "step": 247
    },
    {
      "epoch": 7.09,
      "learning_rate": 0.0008523809523809523,
      "loss": 0.8813,
      "step": 248
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0008517857142857143,
      "loss": 0.8702,
      "step": 249
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.0008511904761904762,
      "loss": 0.9105,
      "step": 250
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.0008505952380952381,
      "loss": 0.9096,
      "step": 251
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.00085,
      "loss": 0.9121,
      "step": 252
    },
    {
      "epoch": 7.23,
      "learning_rate": 0.0008494047619047619,
      "loss": 0.9063,
      "step": 253
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.0008488095238095238,
      "loss": 0.8976,
      "step": 254
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.0008482142857142857,
      "loss": 0.9283,
      "step": 255
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.0008476190476190476,
      "loss": 0.9409,
      "step": 256
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.0008470238095238096,
      "loss": 0.9311,
      "step": 257
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.0008464285714285714,
      "loss": 0.926,
      "step": 258
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.0008458333333333333,
      "loss": 0.9704,
      "step": 259
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0008452380952380953,
      "loss": 0.9515,
      "step": 260
    },
    {
      "epoch": 7.46,
      "learning_rate": 0.0008446428571428572,
      "loss": 0.9069,
      "step": 261
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.000844047619047619,
      "loss": 0.9359,
      "step": 262
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.0008434523809523809,
      "loss": 0.9482,
      "step": 263
    },
    {
      "epoch": 7.54,
      "learning_rate": 0.0008428571428571429,
      "loss": 0.9717,
      "step": 264
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.0008422619047619048,
      "loss": 0.9869,
      "step": 265
    },
    {
      "epoch": 7.6,
      "learning_rate": 0.0008416666666666667,
      "loss": 0.9728,
      "step": 266
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.0008410714285714285,
      "loss": 0.9516,
      "step": 267
    },
    {
      "epoch": 7.66,
      "learning_rate": 0.0008404761904761905,
      "loss": 0.9838,
      "step": 268
    },
    {
      "epoch": 7.69,
      "learning_rate": 0.0008398809523809524,
      "loss": 1.0044,
      "step": 269
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.0008392857142857143,
      "loss": 1.0153,
      "step": 270
    },
    {
      "epoch": 7.74,
      "learning_rate": 0.0008386904761904763,
      "loss": 1.0382,
      "step": 271
    },
    {
      "epoch": 7.77,
      "learning_rate": 0.0008380952380952382,
      "loss": 1.0109,
      "step": 272
    },
    {
      "epoch": 7.8,
      "learning_rate": 0.0008375,
      "loss": 0.9989,
      "step": 273
    },
    {
      "epoch": 7.83,
      "learning_rate": 0.0008369047619047619,
      "loss": 1.0631,
      "step": 274
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.0008363095238095239,
      "loss": 1.0546,
      "step": 275
    },
    {
      "epoch": 7.89,
      "learning_rate": 0.0008357142857142858,
      "loss": 1.0827,
      "step": 276
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.0008351190476190476,
      "loss": 1.087,
      "step": 277
    },
    {
      "epoch": 7.94,
      "learning_rate": 0.0008345238095238095,
      "loss": 1.041,
      "step": 278
    },
    {
      "epoch": 7.97,
      "learning_rate": 0.0008339285714285715,
      "loss": 1.0633,
      "step": 279
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0008333333333333334,
      "loss": 1.0709,
      "step": 280
    },
    {
      "epoch": 8.03,
      "learning_rate": 0.0008327380952380953,
      "loss": 0.7273,
      "step": 281
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.0008321428571428573,
      "loss": 0.726,
      "step": 282
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.0008315476190476191,
      "loss": 0.6943,
      "step": 283
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.000830952380952381,
      "loss": 0.7127,
      "step": 284
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0008303571428571429,
      "loss": 0.6915,
      "step": 285
    },
    {
      "epoch": 8.17,
      "learning_rate": 0.0008297619047619049,
      "loss": 0.7138,
      "step": 286
    },
    {
      "epoch": 8.2,
      "learning_rate": 0.0008291666666666667,
      "loss": 0.7356,
      "step": 287
    },
    {
      "epoch": 8.23,
      "learning_rate": 0.0008285714285714286,
      "loss": 0.678,
      "step": 288
    },
    {
      "epoch": 8.26,
      "learning_rate": 0.0008279761904761904,
      "loss": 0.7375,
      "step": 289
    },
    {
      "epoch": 8.29,
      "learning_rate": 0.0008273809523809524,
      "loss": 0.7284,
      "step": 290
    },
    {
      "epoch": 8.31,
      "learning_rate": 0.0008267857142857143,
      "loss": 0.7304,
      "step": 291
    },
    {
      "epoch": 8.34,
      "learning_rate": 0.0008261904761904761,
      "loss": 0.7633,
      "step": 292
    },
    {
      "epoch": 8.37,
      "learning_rate": 0.0008255952380952381,
      "loss": 0.7416,
      "step": 293
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.000825,
      "loss": 0.7895,
      "step": 294
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.0008244047619047619,
      "loss": 0.8037,
      "step": 295
    },
    {
      "epoch": 8.46,
      "learning_rate": 0.0008238095238095238,
      "loss": 0.7736,
      "step": 296
    },
    {
      "epoch": 8.49,
      "learning_rate": 0.0008232142857142857,
      "loss": 0.778,
      "step": 297
    },
    {
      "epoch": 8.51,
      "learning_rate": 0.0008226190476190476,
      "loss": 0.7644,
      "step": 298
    },
    {
      "epoch": 8.54,
      "learning_rate": 0.0008220238095238095,
      "loss": 0.7942,
      "step": 299
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.0008214285714285714,
      "loss": 0.7715,
      "step": 300
    },
    {
      "epoch": 8.6,
      "learning_rate": 0.0008208333333333334,
      "loss": 0.8288,
      "step": 301
    },
    {
      "epoch": 8.63,
      "learning_rate": 0.0008202380952380952,
      "loss": 0.8263,
      "step": 302
    },
    {
      "epoch": 8.66,
      "learning_rate": 0.0008196428571428571,
      "loss": 0.7923,
      "step": 303
    },
    {
      "epoch": 8.69,
      "learning_rate": 0.0008190476190476191,
      "loss": 0.8063,
      "step": 304
    },
    {
      "epoch": 8.71,
      "learning_rate": 0.000818452380952381,
      "loss": 0.8016,
      "step": 305
    },
    {
      "epoch": 8.74,
      "learning_rate": 0.0008178571428571428,
      "loss": 0.8467,
      "step": 306
    },
    {
      "epoch": 8.77,
      "learning_rate": 0.0008172619047619047,
      "loss": 0.8353,
      "step": 307
    },
    {
      "epoch": 8.8,
      "learning_rate": 0.0008166666666666667,
      "loss": 0.8272,
      "step": 308
    },
    {
      "epoch": 8.83,
      "learning_rate": 0.0008160714285714286,
      "loss": 0.8852,
      "step": 309
    },
    {
      "epoch": 8.86,
      "learning_rate": 0.0008154761904761905,
      "loss": 0.8541,
      "step": 310
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.0008148809523809523,
      "loss": 0.8236,
      "step": 311
    },
    {
      "epoch": 8.91,
      "learning_rate": 0.0008142857142857143,
      "loss": 0.8609,
      "step": 312
    },
    {
      "epoch": 8.94,
      "learning_rate": 0.0008136904761904762,
      "loss": 0.8802,
      "step": 313
    },
    {
      "epoch": 8.97,
      "learning_rate": 0.0008130952380952381,
      "loss": 0.8615,
      "step": 314
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.0008125000000000001,
      "loss": 0.8514,
      "step": 315
    },
    {
      "epoch": 9.03,
      "learning_rate": 0.000811904761904762,
      "loss": 0.5529,
      "step": 316
    },
    {
      "epoch": 9.06,
      "learning_rate": 0.0008113095238095238,
      "loss": 0.5736,
      "step": 317
    },
    {
      "epoch": 9.09,
      "learning_rate": 0.0008107142857142857,
      "loss": 0.5647,
      "step": 318
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0008101190476190477,
      "loss": 0.5677,
      "step": 319
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.0008095238095238096,
      "loss": 0.5991,
      "step": 320
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.0008089285714285714,
      "loss": 0.5666,
      "step": 321
    },
    {
      "epoch": 9.2,
      "learning_rate": 0.0008083333333333333,
      "loss": 0.5902,
      "step": 322
    },
    {
      "epoch": 9.23,
      "learning_rate": 0.0008077380952380953,
      "loss": 0.5961,
      "step": 323
    },
    {
      "epoch": 9.26,
      "learning_rate": 0.0008071428571428572,
      "loss": 0.5684,
      "step": 324
    },
    {
      "epoch": 9.29,
      "learning_rate": 0.0008065476190476191,
      "loss": 0.5976,
      "step": 325
    },
    {
      "epoch": 9.31,
      "learning_rate": 0.0008059523809523809,
      "loss": 0.6033,
      "step": 326
    },
    {
      "epoch": 9.34,
      "learning_rate": 0.0008053571428571429,
      "loss": 0.5877,
      "step": 327
    },
    {
      "epoch": 9.37,
      "learning_rate": 0.0008047619047619048,
      "loss": 0.5943,
      "step": 328
    },
    {
      "epoch": 9.4,
      "learning_rate": 0.0008041666666666667,
      "loss": 0.6176,
      "step": 329
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.0008035714285714287,
      "loss": 0.6143,
      "step": 330
    },
    {
      "epoch": 9.46,
      "learning_rate": 0.0008029761904761905,
      "loss": 0.597,
      "step": 331
    },
    {
      "epoch": 9.49,
      "learning_rate": 0.0008023809523809524,
      "loss": 0.604,
      "step": 332
    },
    {
      "epoch": 9.51,
      "learning_rate": 0.0008017857142857143,
      "loss": 0.6036,
      "step": 333
    },
    {
      "epoch": 9.54,
      "learning_rate": 0.0008011904761904763,
      "loss": 0.6243,
      "step": 334
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.0008005952380952382,
      "loss": 0.6301,
      "step": 335
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.0008,
      "loss": 0.6271,
      "step": 336
    },
    {
      "epoch": 9.63,
      "learning_rate": 0.0007994047619047619,
      "loss": 0.6246,
      "step": 337
    },
    {
      "epoch": 9.66,
      "learning_rate": 0.0007988095238095239,
      "loss": 0.6597,
      "step": 338
    },
    {
      "epoch": 9.69,
      "learning_rate": 0.0007982142857142858,
      "loss": 0.6517,
      "step": 339
    },
    {
      "epoch": 9.71,
      "learning_rate": 0.0007976190476190477,
      "loss": 0.6645,
      "step": 340
    },
    {
      "epoch": 9.74,
      "learning_rate": 0.0007970238095238096,
      "loss": 0.6542,
      "step": 341
    },
    {
      "epoch": 9.77,
      "learning_rate": 0.0007964285714285714,
      "loss": 0.6496,
      "step": 342
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.0007958333333333333,
      "loss": 0.6309,
      "step": 343
    },
    {
      "epoch": 9.83,
      "learning_rate": 0.0007952380952380952,
      "loss": 0.6668,
      "step": 344
    },
    {
      "epoch": 9.86,
      "learning_rate": 0.0007946428571428572,
      "loss": 0.6841,
      "step": 345
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.000794047619047619,
      "loss": 0.6958,
      "step": 346
    },
    {
      "epoch": 9.91,
      "learning_rate": 0.0007934523809523809,
      "loss": 0.6592,
      "step": 347
    },
    {
      "epoch": 9.94,
      "learning_rate": 0.0007928571428571428,
      "loss": 0.6968,
      "step": 348
    },
    {
      "epoch": 9.97,
      "learning_rate": 0.0007922619047619048,
      "loss": 0.6916,
      "step": 349
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0007916666666666666,
      "loss": 0.7155,
      "step": 350
    },
    {
      "epoch": 10.03,
      "learning_rate": 0.0007910714285714285,
      "loss": 0.4288,
      "step": 351
    },
    {
      "epoch": 10.06,
      "learning_rate": 0.0007904761904761905,
      "loss": 0.4493,
      "step": 352
    },
    {
      "epoch": 10.09,
      "learning_rate": 0.0007898809523809524,
      "loss": 0.4152,
      "step": 353
    },
    {
      "epoch": 10.11,
      "learning_rate": 0.0007892857142857143,
      "loss": 0.4324,
      "step": 354
    },
    {
      "epoch": 10.14,
      "learning_rate": 0.0007886904761904761,
      "loss": 0.4334,
      "step": 355
    },
    {
      "epoch": 10.17,
      "learning_rate": 0.0007880952380952381,
      "loss": 0.4479,
      "step": 356
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.0007875,
      "loss": 0.4391,
      "step": 357
    },
    {
      "epoch": 10.23,
      "learning_rate": 0.0007869047619047619,
      "loss": 0.4534,
      "step": 358
    },
    {
      "epoch": 10.26,
      "learning_rate": 0.0007863095238095238,
      "loss": 0.4494,
      "step": 359
    },
    {
      "epoch": 10.29,
      "learning_rate": 0.0007857142857142857,
      "loss": 0.4519,
      "step": 360
    },
    {
      "epoch": 10.31,
      "learning_rate": 0.0007851190476190476,
      "loss": 0.4673,
      "step": 361
    },
    {
      "epoch": 10.34,
      "learning_rate": 0.0007845238095238095,
      "loss": 0.4628,
      "step": 362
    },
    {
      "epoch": 10.37,
      "learning_rate": 0.0007839285714285715,
      "loss": 0.4608,
      "step": 363
    },
    {
      "epoch": 10.4,
      "learning_rate": 0.0007833333333333334,
      "loss": 0.4755,
      "step": 364
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.0007827380952380952,
      "loss": 0.4771,
      "step": 365
    },
    {
      "epoch": 10.46,
      "learning_rate": 0.0007821428571428571,
      "loss": 0.4679,
      "step": 366
    },
    {
      "epoch": 10.49,
      "learning_rate": 0.0007815476190476191,
      "loss": 0.4985,
      "step": 367
    },
    {
      "epoch": 10.51,
      "learning_rate": 0.000780952380952381,
      "loss": 0.5242,
      "step": 368
    },
    {
      "epoch": 10.54,
      "learning_rate": 0.0007803571428571429,
      "loss": 0.478,
      "step": 369
    },
    {
      "epoch": 10.57,
      "learning_rate": 0.0007797619047619047,
      "loss": 0.5072,
      "step": 370
    },
    {
      "epoch": 10.6,
      "learning_rate": 0.0007791666666666667,
      "loss": 0.5001,
      "step": 371
    },
    {
      "epoch": 10.63,
      "learning_rate": 0.0007785714285714286,
      "loss": 0.5119,
      "step": 372
    },
    {
      "epoch": 10.66,
      "learning_rate": 0.0007779761904761905,
      "loss": 0.5212,
      "step": 373
    },
    {
      "epoch": 10.69,
      "learning_rate": 0.0007773809523809525,
      "loss": 0.5073,
      "step": 374
    },
    {
      "epoch": 10.71,
      "learning_rate": 0.0007767857142857143,
      "loss": 0.5089,
      "step": 375
    },
    {
      "epoch": 10.74,
      "learning_rate": 0.0007761904761904762,
      "loss": 0.5161,
      "step": 376
    },
    {
      "epoch": 10.77,
      "learning_rate": 0.0007755952380952381,
      "loss": 0.4861,
      "step": 377
    },
    {
      "epoch": 10.8,
      "learning_rate": 0.0007750000000000001,
      "loss": 0.531,
      "step": 378
    },
    {
      "epoch": 10.83,
      "learning_rate": 0.000774404761904762,
      "loss": 0.5244,
      "step": 379
    },
    {
      "epoch": 10.86,
      "learning_rate": 0.0007738095238095238,
      "loss": 0.5446,
      "step": 380
    },
    {
      "epoch": 10.89,
      "learning_rate": 0.0007732142857142857,
      "loss": 0.5515,
      "step": 381
    },
    {
      "epoch": 10.91,
      "learning_rate": 0.0007726190476190477,
      "loss": 0.5345,
      "step": 382
    },
    {
      "epoch": 10.94,
      "learning_rate": 0.0007720238095238096,
      "loss": 0.537,
      "step": 383
    },
    {
      "epoch": 10.97,
      "learning_rate": 0.0007714285714285715,
      "loss": 0.5589,
      "step": 384
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.0007708333333333334,
      "loss": 0.5459,
      "step": 385
    },
    {
      "epoch": 11.03,
      "learning_rate": 0.0007702380952380953,
      "loss": 0.3344,
      "step": 386
    },
    {
      "epoch": 11.06,
      "learning_rate": 0.0007696428571428572,
      "loss": 0.3352,
      "step": 387
    },
    {
      "epoch": 11.09,
      "learning_rate": 0.0007690476190476191,
      "loss": 0.3263,
      "step": 388
    },
    {
      "epoch": 11.11,
      "learning_rate": 0.0007684523809523811,
      "loss": 0.3501,
      "step": 389
    },
    {
      "epoch": 11.14,
      "learning_rate": 0.0007678571428571429,
      "loss": 0.3523,
      "step": 390
    },
    {
      "epoch": 11.17,
      "learning_rate": 0.0007672619047619048,
      "loss": 0.3379,
      "step": 391
    },
    {
      "epoch": 11.2,
      "learning_rate": 0.0007666666666666667,
      "loss": 0.3456,
      "step": 392
    },
    {
      "epoch": 11.23,
      "learning_rate": 0.0007660714285714287,
      "loss": 0.347,
      "step": 393
    },
    {
      "epoch": 11.26,
      "learning_rate": 0.0007654761904761904,
      "loss": 0.3622,
      "step": 394
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.0007648809523809523,
      "loss": 0.3612,
      "step": 395
    },
    {
      "epoch": 11.31,
      "learning_rate": 0.0007642857142857142,
      "loss": 0.3789,
      "step": 396
    },
    {
      "epoch": 11.34,
      "learning_rate": 0.0007636904761904762,
      "loss": 0.3491,
      "step": 397
    },
    {
      "epoch": 11.37,
      "learning_rate": 0.0007630952380952381,
      "loss": 0.3578,
      "step": 398
    },
    {
      "epoch": 11.4,
      "learning_rate": 0.0007624999999999999,
      "loss": 0.3524,
      "step": 399
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.0007619047619047619,
      "loss": 0.3671,
      "step": 400
    },
    {
      "epoch": 11.46,
      "learning_rate": 0.0007613095238095238,
      "loss": 0.374,
      "step": 401
    },
    {
      "epoch": 11.49,
      "learning_rate": 0.0007607142857142857,
      "loss": 0.3872,
      "step": 402
    },
    {
      "epoch": 11.51,
      "learning_rate": 0.0007601190476190476,
      "loss": 0.3801,
      "step": 403
    },
    {
      "epoch": 11.54,
      "learning_rate": 0.0007595238095238095,
      "loss": 0.3618,
      "step": 404
    },
    {
      "epoch": 11.57,
      "learning_rate": 0.0007589285714285714,
      "loss": 0.3929,
      "step": 405
    },
    {
      "epoch": 11.6,
      "learning_rate": 0.0007583333333333333,
      "loss": 0.4099,
      "step": 406
    },
    {
      "epoch": 11.63,
      "learning_rate": 0.0007577380952380952,
      "loss": 0.3778,
      "step": 407
    },
    {
      "epoch": 11.66,
      "learning_rate": 0.0007571428571428572,
      "loss": 0.3965,
      "step": 408
    },
    {
      "epoch": 11.69,
      "learning_rate": 0.000756547619047619,
      "loss": 0.4013,
      "step": 409
    },
    {
      "epoch": 11.71,
      "learning_rate": 0.0007559523809523809,
      "loss": 0.4031,
      "step": 410
    },
    {
      "epoch": 11.74,
      "learning_rate": 0.0007553571428571429,
      "loss": 0.398,
      "step": 411
    },
    {
      "epoch": 11.77,
      "learning_rate": 0.0007547619047619048,
      "loss": 0.4106,
      "step": 412
    },
    {
      "epoch": 11.8,
      "learning_rate": 0.0007541666666666667,
      "loss": 0.4031,
      "step": 413
    },
    {
      "epoch": 11.83,
      "learning_rate": 0.0007535714285714285,
      "loss": 0.4199,
      "step": 414
    },
    {
      "epoch": 11.86,
      "learning_rate": 0.0007529761904761905,
      "loss": 0.4012,
      "step": 415
    },
    {
      "epoch": 11.89,
      "learning_rate": 0.0007523809523809524,
      "loss": 0.4096,
      "step": 416
    },
    {
      "epoch": 11.91,
      "learning_rate": 0.0007517857142857143,
      "loss": 0.4237,
      "step": 417
    },
    {
      "epoch": 11.94,
      "learning_rate": 0.0007511904761904762,
      "loss": 0.4115,
      "step": 418
    },
    {
      "epoch": 11.97,
      "learning_rate": 0.0007505952380952381,
      "loss": 0.4459,
      "step": 419
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.00075,
      "loss": 0.4406,
      "step": 420
    },
    {
      "epoch": 12.03,
      "learning_rate": 0.0007494047619047619,
      "loss": 0.2561,
      "step": 421
    },
    {
      "epoch": 12.06,
      "learning_rate": 0.0007488095238095239,
      "loss": 0.2662,
      "step": 422
    },
    {
      "epoch": 12.09,
      "learning_rate": 0.0007482142857142858,
      "loss": 0.2538,
      "step": 423
    },
    {
      "epoch": 12.11,
      "learning_rate": 0.0007476190476190476,
      "loss": 0.2571,
      "step": 424
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.0007470238095238095,
      "loss": 0.2527,
      "step": 425
    },
    {
      "epoch": 12.17,
      "learning_rate": 0.0007464285714285715,
      "loss": 0.2739,
      "step": 426
    },
    {
      "epoch": 12.2,
      "learning_rate": 0.0007458333333333334,
      "loss": 0.2642,
      "step": 427
    },
    {
      "epoch": 12.23,
      "learning_rate": 0.0007452380952380953,
      "loss": 0.2736,
      "step": 428
    },
    {
      "epoch": 12.26,
      "learning_rate": 0.0007446428571428571,
      "loss": 0.2774,
      "step": 429
    },
    {
      "epoch": 12.29,
      "learning_rate": 0.0007440476190476191,
      "loss": 0.2684,
      "step": 430
    },
    {
      "epoch": 12.31,
      "learning_rate": 0.000743452380952381,
      "loss": 0.2727,
      "step": 431
    },
    {
      "epoch": 12.34,
      "learning_rate": 0.0007428571428571429,
      "loss": 0.2801,
      "step": 432
    },
    {
      "epoch": 12.37,
      "learning_rate": 0.0007422619047619049,
      "loss": 0.2685,
      "step": 433
    },
    {
      "epoch": 12.4,
      "learning_rate": 0.0007416666666666667,
      "loss": 0.2958,
      "step": 434
    },
    {
      "epoch": 12.43,
      "learning_rate": 0.0007410714285714286,
      "loss": 0.2868,
      "step": 435
    },
    {
      "epoch": 12.46,
      "learning_rate": 0.0007404761904761905,
      "loss": 0.2838,
      "step": 436
    },
    {
      "epoch": 12.49,
      "learning_rate": 0.0007398809523809525,
      "loss": 0.2976,
      "step": 437
    },
    {
      "epoch": 12.51,
      "learning_rate": 0.0007392857142857144,
      "loss": 0.2963,
      "step": 438
    },
    {
      "epoch": 12.54,
      "learning_rate": 0.0007386904761904762,
      "loss": 0.2891,
      "step": 439
    },
    {
      "epoch": 12.57,
      "learning_rate": 0.0007380952380952381,
      "loss": 0.2897,
      "step": 440
    },
    {
      "epoch": 12.6,
      "learning_rate": 0.0007375000000000001,
      "loss": 0.3013,
      "step": 441
    },
    {
      "epoch": 12.63,
      "learning_rate": 0.000736904761904762,
      "loss": 0.2977,
      "step": 442
    },
    {
      "epoch": 12.66,
      "learning_rate": 0.0007363095238095238,
      "loss": 0.2985,
      "step": 443
    },
    {
      "epoch": 12.69,
      "learning_rate": 0.0007357142857142858,
      "loss": 0.3097,
      "step": 444
    },
    {
      "epoch": 12.71,
      "learning_rate": 0.0007351190476190477,
      "loss": 0.3183,
      "step": 445
    },
    {
      "epoch": 12.74,
      "learning_rate": 0.0007345238095238096,
      "loss": 0.3192,
      "step": 446
    },
    {
      "epoch": 12.77,
      "learning_rate": 0.0007339285714285714,
      "loss": 0.3265,
      "step": 447
    },
    {
      "epoch": 12.8,
      "learning_rate": 0.0007333333333333333,
      "loss": 0.3033,
      "step": 448
    },
    {
      "epoch": 12.83,
      "learning_rate": 0.0007327380952380952,
      "loss": 0.313,
      "step": 449
    },
    {
      "epoch": 12.86,
      "learning_rate": 0.0007321428571428571,
      "loss": 0.3186,
      "step": 450
    },
    {
      "epoch": 12.89,
      "learning_rate": 0.000731547619047619,
      "loss": 0.3275,
      "step": 451
    },
    {
      "epoch": 12.91,
      "learning_rate": 0.000730952380952381,
      "loss": 0.3272,
      "step": 452
    },
    {
      "epoch": 12.94,
      "learning_rate": 0.0007303571428571428,
      "loss": 0.3336,
      "step": 453
    },
    {
      "epoch": 12.97,
      "learning_rate": 0.0007297619047619047,
      "loss": 0.3244,
      "step": 454
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.0007291666666666666,
      "loss": 0.3403,
      "step": 455
    },
    {
      "epoch": 13.03,
      "learning_rate": 0.0007285714285714286,
      "loss": 0.1931,
      "step": 456
    },
    {
      "epoch": 13.06,
      "learning_rate": 0.0007279761904761905,
      "loss": 0.2104,
      "step": 457
    },
    {
      "epoch": 13.09,
      "learning_rate": 0.0007273809523809523,
      "loss": 0.2025,
      "step": 458
    },
    {
      "epoch": 13.11,
      "learning_rate": 0.0007267857142857143,
      "loss": 0.1933,
      "step": 459
    },
    {
      "epoch": 13.14,
      "learning_rate": 0.0007261904761904762,
      "loss": 0.2002,
      "step": 460
    },
    {
      "epoch": 13.17,
      "learning_rate": 0.0007255952380952381,
      "loss": 0.2097,
      "step": 461
    },
    {
      "epoch": 13.2,
      "learning_rate": 0.000725,
      "loss": 0.2097,
      "step": 462
    },
    {
      "epoch": 13.23,
      "learning_rate": 0.0007244047619047619,
      "loss": 0.2061,
      "step": 463
    },
    {
      "epoch": 13.26,
      "learning_rate": 0.0007238095238095238,
      "loss": 0.2,
      "step": 464
    },
    {
      "epoch": 13.29,
      "learning_rate": 0.0007232142857142857,
      "loss": 0.2082,
      "step": 465
    },
    {
      "epoch": 13.31,
      "learning_rate": 0.0007226190476190476,
      "loss": 0.209,
      "step": 466
    },
    {
      "epoch": 13.34,
      "learning_rate": 0.0007220238095238096,
      "loss": 0.2083,
      "step": 467
    },
    {
      "epoch": 13.37,
      "learning_rate": 0.0007214285714285714,
      "loss": 0.215,
      "step": 468
    },
    {
      "epoch": 13.4,
      "learning_rate": 0.0007208333333333333,
      "loss": 0.2113,
      "step": 469
    },
    {
      "epoch": 13.43,
      "learning_rate": 0.0007202380952380953,
      "loss": 0.2186,
      "step": 470
    },
    {
      "epoch": 13.46,
      "learning_rate": 0.0007196428571428572,
      "loss": 0.2164,
      "step": 471
    },
    {
      "epoch": 13.49,
      "learning_rate": 0.000719047619047619,
      "loss": 0.2197,
      "step": 472
    },
    {
      "epoch": 13.51,
      "learning_rate": 0.0007184523809523809,
      "loss": 0.2256,
      "step": 473
    },
    {
      "epoch": 13.54,
      "learning_rate": 0.0007178571428571429,
      "loss": 0.2165,
      "step": 474
    },
    {
      "epoch": 13.57,
      "learning_rate": 0.0007172619047619048,
      "loss": 0.2227,
      "step": 475
    },
    {
      "epoch": 13.6,
      "learning_rate": 0.0007166666666666667,
      "loss": 0.2245,
      "step": 476
    },
    {
      "epoch": 13.63,
      "learning_rate": 0.0007160714285714285,
      "loss": 0.2239,
      "step": 477
    },
    {
      "epoch": 13.66,
      "learning_rate": 0.0007154761904761905,
      "loss": 0.2251,
      "step": 478
    },
    {
      "epoch": 13.69,
      "learning_rate": 0.0007148809523809524,
      "loss": 0.2305,
      "step": 479
    },
    {
      "epoch": 13.71,
      "learning_rate": 0.0007142857142857143,
      "loss": 0.2334,
      "step": 480
    },
    {
      "epoch": 13.74,
      "learning_rate": 0.0007136904761904763,
      "loss": 0.229,
      "step": 481
    },
    {
      "epoch": 13.77,
      "learning_rate": 0.0007130952380952381,
      "loss": 0.2363,
      "step": 482
    },
    {
      "epoch": 13.8,
      "learning_rate": 0.0007125,
      "loss": 0.2382,
      "step": 483
    },
    {
      "epoch": 13.83,
      "learning_rate": 0.0007119047619047619,
      "loss": 0.2374,
      "step": 484
    },
    {
      "epoch": 13.86,
      "learning_rate": 0.0007113095238095239,
      "loss": 0.2433,
      "step": 485
    },
    {
      "epoch": 13.89,
      "learning_rate": 0.0007107142857142858,
      "loss": 0.2349,
      "step": 486
    },
    {
      "epoch": 13.91,
      "learning_rate": 0.0007101190476190476,
      "loss": 0.2549,
      "step": 487
    },
    {
      "epoch": 13.94,
      "learning_rate": 0.0007095238095238095,
      "loss": 0.2481,
      "step": 488
    },
    {
      "epoch": 13.97,
      "learning_rate": 0.0007089285714285715,
      "loss": 0.2504,
      "step": 489
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.0007083333333333334,
      "loss": 0.2521,
      "step": 490
    },
    {
      "epoch": 14.03,
      "learning_rate": 0.0007077380952380953,
      "loss": 0.1489,
      "step": 491
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.0007071428571428572,
      "loss": 0.15,
      "step": 492
    },
    {
      "epoch": 14.09,
      "learning_rate": 0.0007065476190476191,
      "loss": 0.1499,
      "step": 493
    },
    {
      "epoch": 14.11,
      "learning_rate": 0.000705952380952381,
      "loss": 0.1515,
      "step": 494
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.0007053571428571429,
      "loss": 0.1542,
      "step": 495
    },
    {
      "epoch": 14.17,
      "learning_rate": 0.0007047619047619049,
      "loss": 0.1523,
      "step": 496
    },
    {
      "epoch": 14.2,
      "learning_rate": 0.0007041666666666667,
      "loss": 0.1605,
      "step": 497
    },
    {
      "epoch": 14.23,
      "learning_rate": 0.0007035714285714286,
      "loss": 0.1572,
      "step": 498
    },
    {
      "epoch": 14.26,
      "learning_rate": 0.0007029761904761904,
      "loss": 0.1634,
      "step": 499
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.0007023809523809524,
      "loss": 0.1548,
      "step": 500
    },
    {
      "epoch": 14.31,
      "learning_rate": 0.0007017857142857143,
      "loss": 0.1521,
      "step": 501
    },
    {
      "epoch": 14.34,
      "learning_rate": 0.0007011904761904761,
      "loss": 0.1644,
      "step": 502
    },
    {
      "epoch": 14.37,
      "learning_rate": 0.0007005952380952381,
      "loss": 0.155,
      "step": 503
    },
    {
      "epoch": 14.4,
      "learning_rate": 0.0007,
      "loss": 0.1674,
      "step": 504
    },
    {
      "epoch": 14.43,
      "learning_rate": 0.0006994047619047619,
      "loss": 0.1619,
      "step": 505
    },
    {
      "epoch": 14.46,
      "learning_rate": 0.0006988095238095237,
      "loss": 0.1644,
      "step": 506
    },
    {
      "epoch": 14.49,
      "learning_rate": 0.0006982142857142857,
      "loss": 0.1723,
      "step": 507
    },
    {
      "epoch": 14.51,
      "learning_rate": 0.0006976190476190476,
      "loss": 0.1621,
      "step": 508
    },
    {
      "epoch": 14.54,
      "learning_rate": 0.0006970238095238095,
      "loss": 0.1647,
      "step": 509
    },
    {
      "epoch": 14.57,
      "learning_rate": 0.0006964285714285714,
      "loss": 0.1741,
      "step": 510
    },
    {
      "epoch": 14.6,
      "learning_rate": 0.0006958333333333334,
      "loss": 0.1673,
      "step": 511
    },
    {
      "epoch": 14.63,
      "learning_rate": 0.0006952380952380952,
      "loss": 0.1752,
      "step": 512
    },
    {
      "epoch": 14.66,
      "learning_rate": 0.0006946428571428571,
      "loss": 0.167,
      "step": 513
    },
    {
      "epoch": 14.69,
      "learning_rate": 0.0006940476190476191,
      "loss": 0.1718,
      "step": 514
    },
    {
      "epoch": 14.71,
      "learning_rate": 0.000693452380952381,
      "loss": 0.1787,
      "step": 515
    },
    {
      "epoch": 14.74,
      "learning_rate": 0.0006928571428571428,
      "loss": 0.1747,
      "step": 516
    },
    {
      "epoch": 14.77,
      "learning_rate": 0.0006922619047619047,
      "loss": 0.1766,
      "step": 517
    },
    {
      "epoch": 14.8,
      "learning_rate": 0.0006916666666666667,
      "loss": 0.1782,
      "step": 518
    },
    {
      "epoch": 14.83,
      "learning_rate": 0.0006910714285714286,
      "loss": 0.1799,
      "step": 519
    },
    {
      "epoch": 14.86,
      "learning_rate": 0.0006904761904761905,
      "loss": 0.169,
      "step": 520
    },
    {
      "epoch": 14.89,
      "learning_rate": 0.0006898809523809523,
      "loss": 0.1802,
      "step": 521
    },
    {
      "epoch": 14.91,
      "learning_rate": 0.0006892857142857143,
      "loss": 0.18,
      "step": 522
    },
    {
      "epoch": 14.94,
      "learning_rate": 0.0006886904761904762,
      "loss": 0.1823,
      "step": 523
    },
    {
      "epoch": 14.97,
      "learning_rate": 0.0006880952380952381,
      "loss": 0.1829,
      "step": 524
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.0006875,
      "loss": 0.1885,
      "step": 525
    },
    {
      "epoch": 15.03,
      "learning_rate": 0.000686904761904762,
      "loss": 0.1171,
      "step": 526
    },
    {
      "epoch": 15.06,
      "learning_rate": 0.0006863095238095238,
      "loss": 0.1126,
      "step": 527
    },
    {
      "epoch": 15.09,
      "learning_rate": 0.0006857142857142857,
      "loss": 0.1186,
      "step": 528
    },
    {
      "epoch": 15.11,
      "learning_rate": 0.0006851190476190477,
      "loss": 0.1164,
      "step": 529
    },
    {
      "epoch": 15.14,
      "learning_rate": 0.0006845238095238096,
      "loss": 0.1163,
      "step": 530
    },
    {
      "epoch": 15.17,
      "learning_rate": 0.0006839285714285714,
      "loss": 0.1204,
      "step": 531
    },
    {
      "epoch": 15.2,
      "learning_rate": 0.0006833333333333333,
      "loss": 0.1212,
      "step": 532
    },
    {
      "epoch": 15.23,
      "learning_rate": 0.0006827380952380953,
      "loss": 0.1188,
      "step": 533
    },
    {
      "epoch": 15.26,
      "learning_rate": 0.0006821428571428572,
      "loss": 0.1154,
      "step": 534
    },
    {
      "epoch": 15.29,
      "learning_rate": 0.0006815476190476191,
      "loss": 0.1244,
      "step": 535
    },
    {
      "epoch": 15.31,
      "learning_rate": 0.0006809523809523809,
      "loss": 0.1214,
      "step": 536
    },
    {
      "epoch": 15.34,
      "learning_rate": 0.0006803571428571429,
      "loss": 0.1294,
      "step": 537
    },
    {
      "epoch": 15.37,
      "learning_rate": 0.0006797619047619048,
      "loss": 0.1232,
      "step": 538
    },
    {
      "epoch": 15.4,
      "learning_rate": 0.0006791666666666667,
      "loss": 0.1262,
      "step": 539
    },
    {
      "epoch": 15.43,
      "learning_rate": 0.0006785714285714287,
      "loss": 0.1195,
      "step": 540
    },
    {
      "epoch": 15.46,
      "learning_rate": 0.0006779761904761905,
      "loss": 0.123,
      "step": 541
    },
    {
      "epoch": 15.49,
      "learning_rate": 0.0006773809523809524,
      "loss": 0.1266,
      "step": 542
    },
    {
      "epoch": 15.51,
      "learning_rate": 0.0006767857142857143,
      "loss": 0.1345,
      "step": 543
    },
    {
      "epoch": 15.54,
      "learning_rate": 0.0006761904761904763,
      "loss": 0.1174,
      "step": 544
    },
    {
      "epoch": 15.57,
      "learning_rate": 0.0006755952380952382,
      "loss": 0.1293,
      "step": 545
    },
    {
      "epoch": 15.6,
      "learning_rate": 0.000675,
      "loss": 0.1293,
      "step": 546
    },
    {
      "epoch": 15.63,
      "learning_rate": 0.0006744047619047619,
      "loss": 0.1269,
      "step": 547
    },
    {
      "epoch": 15.66,
      "learning_rate": 0.0006738095238095239,
      "loss": 0.1321,
      "step": 548
    },
    {
      "epoch": 15.69,
      "learning_rate": 0.0006732142857142858,
      "loss": 0.1318,
      "step": 549
    },
    {
      "epoch": 15.71,
      "learning_rate": 0.0006726190476190477,
      "loss": 0.1283,
      "step": 550
    },
    {
      "epoch": 15.74,
      "learning_rate": 0.0006720238095238096,
      "loss": 0.128,
      "step": 551
    },
    {
      "epoch": 15.77,
      "learning_rate": 0.0006714285714285714,
      "loss": 0.1295,
      "step": 552
    },
    {
      "epoch": 15.8,
      "learning_rate": 0.0006708333333333333,
      "loss": 0.1323,
      "step": 553
    },
    {
      "epoch": 15.83,
      "learning_rate": 0.0006702380952380952,
      "loss": 0.1348,
      "step": 554
    },
    {
      "epoch": 15.86,
      "learning_rate": 0.0006696428571428571,
      "loss": 0.1276,
      "step": 555
    },
    {
      "epoch": 15.89,
      "learning_rate": 0.000669047619047619,
      "loss": 0.1356,
      "step": 556
    },
    {
      "epoch": 15.91,
      "learning_rate": 0.0006684523809523809,
      "loss": 0.1404,
      "step": 557
    },
    {
      "epoch": 15.94,
      "learning_rate": 0.0006678571428571428,
      "loss": 0.1311,
      "step": 558
    },
    {
      "epoch": 15.97,
      "learning_rate": 0.0006672619047619048,
      "loss": 0.1401,
      "step": 559
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.1411,
      "step": 560
    },
    {
      "epoch": 16.03,
      "learning_rate": 0.0006660714285714285,
      "loss": 0.0862,
      "step": 561
    },
    {
      "epoch": 16.06,
      "learning_rate": 0.0006654761904761905,
      "loss": 0.0902,
      "step": 562
    },
    {
      "epoch": 16.09,
      "learning_rate": 0.0006648809523809524,
      "loss": 0.0871,
      "step": 563
    },
    {
      "epoch": 16.11,
      "learning_rate": 0.0006642857142857143,
      "loss": 0.0906,
      "step": 564
    },
    {
      "epoch": 16.14,
      "learning_rate": 0.0006636904761904761,
      "loss": 0.0891,
      "step": 565
    },
    {
      "epoch": 16.17,
      "learning_rate": 0.0006630952380952381,
      "loss": 0.0917,
      "step": 566
    },
    {
      "epoch": 16.2,
      "learning_rate": 0.0006625,
      "loss": 0.0906,
      "step": 567
    },
    {
      "epoch": 16.23,
      "learning_rate": 0.0006619047619047619,
      "loss": 0.0927,
      "step": 568
    },
    {
      "epoch": 16.26,
      "learning_rate": 0.0006613095238095238,
      "loss": 0.0927,
      "step": 569
    },
    {
      "epoch": 16.29,
      "learning_rate": 0.0006607142857142857,
      "loss": 0.0934,
      "step": 570
    },
    {
      "epoch": 16.31,
      "learning_rate": 0.0006601190476190476,
      "loss": 0.0956,
      "step": 571
    },
    {
      "epoch": 16.34,
      "learning_rate": 0.0006595238095238095,
      "loss": 0.0933,
      "step": 572
    },
    {
      "epoch": 16.37,
      "learning_rate": 0.0006589285714285715,
      "loss": 0.0993,
      "step": 573
    },
    {
      "epoch": 16.4,
      "learning_rate": 0.0006583333333333334,
      "loss": 0.095,
      "step": 574
    },
    {
      "epoch": 16.43,
      "learning_rate": 0.0006577380952380952,
      "loss": 0.0963,
      "step": 575
    },
    {
      "epoch": 16.46,
      "learning_rate": 0.0006571428571428571,
      "loss": 0.0948,
      "step": 576
    },
    {
      "epoch": 16.49,
      "learning_rate": 0.0006565476190476191,
      "loss": 0.0952,
      "step": 577
    },
    {
      "epoch": 16.51,
      "learning_rate": 0.000655952380952381,
      "loss": 0.1001,
      "step": 578
    },
    {
      "epoch": 16.54,
      "learning_rate": 0.0006553571428571429,
      "loss": 0.0924,
      "step": 579
    },
    {
      "epoch": 16.57,
      "learning_rate": 0.0006547619047619047,
      "loss": 0.0962,
      "step": 580
    },
    {
      "epoch": 16.6,
      "learning_rate": 0.0006541666666666667,
      "loss": 0.0949,
      "step": 581
    },
    {
      "epoch": 16.63,
      "learning_rate": 0.0006535714285714286,
      "loss": 0.1,
      "step": 582
    },
    {
      "epoch": 16.66,
      "learning_rate": 0.0006529761904761905,
      "loss": 0.1009,
      "step": 583
    },
    {
      "epoch": 16.69,
      "learning_rate": 0.0006523809523809525,
      "loss": 0.1023,
      "step": 584
    },
    {
      "epoch": 16.71,
      "learning_rate": 0.0006517857142857143,
      "loss": 0.0995,
      "step": 585
    },
    {
      "epoch": 16.74,
      "learning_rate": 0.0006511904761904762,
      "loss": 0.1015,
      "step": 586
    },
    {
      "epoch": 16.77,
      "learning_rate": 0.0006505952380952381,
      "loss": 0.0966,
      "step": 587
    },
    {
      "epoch": 16.8,
      "learning_rate": 0.0006500000000000001,
      "loss": 0.1019,
      "step": 588
    },
    {
      "epoch": 16.83,
      "learning_rate": 0.000649404761904762,
      "loss": 0.0996,
      "step": 589
    },
    {
      "epoch": 16.86,
      "learning_rate": 0.0006488095238095238,
      "loss": 0.103,
      "step": 590
    },
    {
      "epoch": 16.89,
      "learning_rate": 0.0006482142857142857,
      "loss": 0.1042,
      "step": 591
    },
    {
      "epoch": 16.91,
      "learning_rate": 0.0006476190476190477,
      "loss": 0.1039,
      "step": 592
    },
    {
      "epoch": 16.94,
      "learning_rate": 0.0006470238095238096,
      "loss": 0.1058,
      "step": 593
    },
    {
      "epoch": 16.97,
      "learning_rate": 0.0006464285714285715,
      "loss": 0.0994,
      "step": 594
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.0006458333333333334,
      "loss": 0.1062,
      "step": 595
    },
    {
      "epoch": 17.03,
      "learning_rate": 0.0006452380952380953,
      "loss": 0.0709,
      "step": 596
    },
    {
      "epoch": 17.06,
      "learning_rate": 0.0006446428571428572,
      "loss": 0.0733,
      "step": 597
    },
    {
      "epoch": 17.09,
      "learning_rate": 0.0006440476190476191,
      "loss": 0.0724,
      "step": 598
    },
    {
      "epoch": 17.11,
      "learning_rate": 0.0006434523809523811,
      "loss": 0.0733,
      "step": 599
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.0006428571428571429,
      "loss": 0.0741,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 1680,
  "num_train_epochs": 48,
  "save_steps": 100,
  "total_flos": 3.463615849187021e+17,
  "trial_name": null,
  "trial_params": null
}