{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.229654403567447,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 9.2554,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-06,
      "loss": 9.5951,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.25e-05,
      "loss": 9.968,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 9.3248,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5e-05,
      "loss": 8.4478,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.125e-05,
      "loss": 8.8715,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 9.1145,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.375e-05,
      "loss": 8.4062,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 8.7625,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 7.9871,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.25e-05,
      "loss": 7.8684,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.875e-05,
      "loss": 7.4262,
      "step": 12
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.0718,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.125000000000001e-05,
      "loss": 6.7281,
      "step": 14
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.75e-05,
      "loss": 6.6335,
      "step": 15
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.375e-05,
      "loss": 5.8393,
      "step": 16
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 5.3873,
      "step": 17
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010625000000000001,
      "loss": 4.9589,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011250000000000001,
      "loss": 4.7494,
      "step": 19
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011875,
      "loss": 4.3132,
      "step": 20
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000125,
      "loss": 4.1908,
      "step": 21
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013125000000000002,
      "loss": 3.8402,
      "step": 22
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001375,
      "loss": 3.4314,
      "step": 23
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014375,
      "loss": 3.2802,
      "step": 24
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.1288,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015625,
      "loss": 3.0646,
      "step": 26
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016250000000000002,
      "loss": 3.0644,
      "step": 27
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016875,
      "loss": 2.4856,
      "step": 28
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000175,
      "loss": 2.3275,
      "step": 29
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00018125000000000001,
      "loss": 2.1863,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001875,
      "loss": 1.8291,
      "step": 31
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019375000000000002,
      "loss": 1.7732,
      "step": 32
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6838,
      "step": 33
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999866506037345,
      "loss": 1.3643,
      "step": 34
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999466027713507,
      "loss": 1.4643,
      "step": 35
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019998798575720776,
      "loss": 1.6028,
      "step": 36
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019997864167879312,
      "loss": 1.4206,
      "step": 37
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019996662829136676,
      "loss": 1.4531,
      "step": 38
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999519459156716,
      "loss": 1.2041,
      "step": 39
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999345949437094,
      "loss": 1.1949,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999145758387301,
      "loss": 0.9885,
      "step": 41
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001998918891352197,
      "loss": 1.1611,
      "step": 42
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019986653543888568,
      "loss": 0.9241,
      "step": 43
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019983851542664126,
      "loss": 1.3583,
      "step": 44
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019980782984658683,
      "loss": 1.1377,
      "step": 45
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019977447951799034,
      "loss": 1.2204,
      "step": 46
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019973846533126533,
      "loss": 0.9928,
      "step": 47
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019969978824794707,
      "loss": 1.0598,
      "step": 48
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000199658449300667,
      "loss": 1.25,
      "step": 49
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019961444959312508,
      "loss": 1.3713,
      "step": 50
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001995677903000604,
      "loss": 0.9969,
      "step": 51
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001995184726672197,
      "loss": 0.9356,
      "step": 52
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019946649801132427,
      "loss": 0.834,
      "step": 53
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019941186772003464,
      "loss": 0.9744,
      "step": 54
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019935458325191365,
      "loss": 0.8644,
      "step": 55
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001992946461363874,
      "loss": 1.1741,
      "step": 56
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001992320579737045,
      "loss": 0.7969,
      "step": 57
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019916682043489336,
      "loss": 0.9504,
      "step": 58
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019909893526171745,
      "loss": 1.3963,
      "step": 59
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019902840426662895,
      "loss": 1.0668,
      "step": 60
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019902840426662895,
      "loss": 0.6902,
      "step": 61
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019895522933272028,
      "loss": 1.2662,
      "step": 62
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019895522933272028,
      "loss": 2.0447,
      "step": 63
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019895522933272028,
      "loss": 0.7568,
      "step": 64
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019895522933272028,
      "loss": 0.9146,
      "step": 65
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019887941241367377,
      "loss": 1.1332,
      "step": 66
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019880095553370967,
      "loss": 1.1715,
      "step": 67
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.3658,
      "step": 68
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.6815,
      "step": 69
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.635,
      "step": 71
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.5615,
      "step": 72
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.7602,
      "step": 73
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.6762,
      "step": 74
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.5942,
      "step": 75
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.3533,
      "step": 76
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.4797,
      "step": 78
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.0598,
      "step": 79
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.8546,
      "step": 80
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.5734,
      "step": 81
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.0866,
      "step": 82
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.238,
      "step": 83
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.8479,
      "step": 84
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.0991,
      "step": 85
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.9502,
      "step": 86
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.5053,
      "step": 87
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.4622,
      "step": 88
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.349,
      "step": 89
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.8208,
      "step": 91
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.5862,
      "step": 92
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.1249,
      "step": 93
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.8549,
      "step": 94
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.76,
      "step": 95
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.4468,
      "step": 96
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.3109,
      "step": 97
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.8511,
      "step": 98
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.9792,
      "step": 99
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.1989,
      "step": 100
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.438,
      "step": 102
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001987198607875319,
      "loss": 0.3758,
      "step": 103
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.2202,
      "step": 104
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.6621,
      "step": 105
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001987198607875319,
      "loss": 1.695,
      "step": 106
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.6176,
      "step": 107
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.211,
      "step": 108
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.0064,
      "step": 109
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019863613034027224,
      "loss": 3.5679,
      "step": 111
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.227,
      "step": 114
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.4384,
      "step": 117
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2177,
      "step": 120
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4402,
      "step": 121
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.744,
      "step": 122
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.5766,
      "step": 123
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1018,
      "step": 124
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.8572,
      "step": 130
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2196,
      "step": 133
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4427,
      "step": 134
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1912,
      "step": 135
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.8012,
      "step": 136
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.51,
      "step": 139
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1927,
      "step": 140
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2303,
      "step": 143
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1468,
      "step": 145
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4611,
      "step": 146
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.126,
      "step": 147
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.1252,
      "step": 148
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 151
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.677,
      "step": 152
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.2064,
      "step": 157
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4441,
      "step": 158
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.355,
      "step": 159
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4723,
      "step": 160
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4213,
      "step": 161
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.655,
      "step": 163
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.5043,
      "step": 164
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019863613034027224,
      "loss": 3.0041,
      "step": 165
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.6247,
      "step": 166
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4243,
      "step": 167
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.357,
      "step": 168
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.3537,
      "step": 173
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.5713,
      "step": 174
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.886,
      "step": 175
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.0761,
      "step": 176
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.2531,
      "step": 177
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.7733,
      "step": 178
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.3724,
      "step": 180
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1415,
      "step": 181
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.0002,
      "step": 182
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2229,
      "step": 183
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.7544,
      "step": 184
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.2167,
      "step": 185
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4988,
      "step": 186
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.9973,
      "step": 187
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.7653,
      "step": 188
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2718,
      "step": 189
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.0434,
      "step": 190
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.5341,
      "step": 194
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.7153,
      "step": 195
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.2904,
      "step": 196
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2691,
      "step": 197
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2125,
      "step": 198
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.536,
      "step": 200
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.6531,
      "step": 201
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 202
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 203
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.2077,
      "step": 204
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1067,
      "step": 205
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.369,
      "step": 206
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.6003,
      "step": 209
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.3425,
      "step": 211
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 212
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.3939,
      "step": 213
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1561,
      "step": 214
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.8341,
      "step": 217
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 218
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.7648,
      "step": 219
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0884,
      "step": 220
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1772,
      "step": 221
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 222
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.943,
      "step": 223
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.9696,
      "step": 224
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1053,
      "step": 225
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.1738,
      "step": 226
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 227
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0,
      "step": 228
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.9189,
      "step": 229
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.4056,
      "step": 230
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001985497664274326,
      "loss": 0.1359,
      "step": 231
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001984607713548251,
      "loss": 0.6309,
      "step": 232
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001983691474985108,
      "loss": 0.0,
      "step": 233
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019827489730473596,
      "loss": 0.3888,
      "step": 234
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019817802328986697,
      "loss": 0.787,
      "step": 235
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 236
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019797641421250725,
      "loss": 0.0,
      "step": 237
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019787168453273544,
      "loss": 0.1077,
      "step": 238
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019776434179716366,
      "loss": 0.0,
      "step": 239
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019765438887171327,
      "loss": 0.1153,
      "step": 240
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001975418286919947,
      "loss": 0.0,
      "step": 241
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019742666426322876,
      "loss": 0.0,
      "step": 242
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001973088986601667,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019718853502700783,
      "loss": 1.2459,
      "step": 244
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001970655765773159,
      "loss": 0.1139,
      "step": 245
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019694002659393305,
      "loss": 0.2691,
      "step": 246
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019681188842889222,
      "loss": 0.0,
      "step": 247
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019668116550332766,
      "loss": 0.4363,
      "step": 248
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001965478613073837,
      "loss": 0.0,
      "step": 249
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019641197940012137,
      "loss": 0.3793,
      "step": 250
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019627352340942353,
      "loss": 0.0,
      "step": 251
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019613249703189796,
      "loss": 0.1207,
      "step": 252
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019598890403277864,
      "loss": 0.0872,
      "step": 253
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001958427482458253,
      "loss": 0.0,
      "step": 254
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001956940335732209,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019554276398546768,
      "loss": 0.9294,
      "step": 256
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.000195388943521281,
      "loss": 0.6593,
      "step": 257
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019523257628748146,
      "loss": 0.5178,
      "step": 258
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019507366645888543,
      "loss": 0.0,
      "step": 259
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019491221827819347,
      "loss": 0.6078,
      "step": 260
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019474823605587703,
      "loss": 0.6807,
      "step": 261
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.2233,
      "step": 262
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019441268706641907,
      "loss": 0.0,
      "step": 263
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019424112925803039,
      "loss": 0.6479,
      "step": 264
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019406705532528374,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019389046991574298,
      "loss": 0.0,
      "step": 266
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019371137774402527,
      "loss": 0.2012,
      "step": 267
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001935297835916754,
      "loss": 0.0,
      "step": 268
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00019334569230703794,
      "loss": 0.0,
      "step": 269
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001931591088051279,
      "loss": 0.4641,
      "step": 270
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001929700380674995,
      "loss": 0.0,
      "step": 271
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019277848514211317,
      "loss": 0.2607,
      "step": 272
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00019258445514320065,
      "loss": 0.0,
      "step": 273
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.8596,
      "step": 274
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001921889847122605,
      "loss": 0.315,
      "step": 275
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019198755483881583,
      "loss": 0.0,
      "step": 276
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001917836690087291,
      "loss": 0.0,
      "step": 277
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019157733266550575,
      "loss": 1.0424,
      "step": 278
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019136855131807705,
      "loss": 0.181,
      "step": 279
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001911573305406528,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019094367597257282,
      "loss": 0.4583,
      "step": 281
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000190727593318156,
      "loss": 0.0,
      "step": 282
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019050908834654834,
      "loss": 0.0898,
      "step": 283
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019028816689156878,
      "loss": 2.3381,
      "step": 284
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019006483485155338,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001898390981891979,
      "loss": 0.4441,
      "step": 286
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001896109629313987,
      "loss": 0.0,
      "step": 287
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001893804351690917,
      "loss": 0.3223,
      "step": 288
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001891475210570898,
      "loss": 0.2783,
      "step": 289
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00018891222681391851,
      "loss": 0.8561,
      "step": 290
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00018867455872165008,
      "loss": 0.7544,
      "step": 291
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00018843452312573554,
      "loss": 1.5485,
      "step": 292
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001881921264348355,
      "loss": 0.0,
      "step": 293
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.0,
      "step": 294
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00018770027571774031,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00018745083482336544,
      "loss": 0.0,
      "step": 296
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00018719905909729494,
      "loss": 3.7086,
      "step": 297
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001869449552616367,
      "loss": 1.2451,
      "step": 298
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00018668853010065634,
      "loss": 0.5947,
      "step": 299
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00018642979046059593,
      "loss": 1.9308,
      "step": 300
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00018616874324949159,
      "loss": 0.0,
      "step": 301
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00018590539543698854,
      "loss": 0.8493,
      "step": 302
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001856397540541554,
      "loss": 0.7325,
      "step": 303
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001853718261932964,
      "loss": 0.1978,
      "step": 304
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00018510161900776187,
      "loss": 0.0,
      "step": 305
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00018482913971175737,
      "loss": 0.2106,
      "step": 306
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00018455439558015115,
      "loss": 0.0,
      "step": 307
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00018427739394827973,
      "loss": 0.5134,
      "step": 308
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00018399814221175227,
      "loss": 0.1162,
      "step": 309
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00018371664782625287,
      "loss": 0.5827,
      "step": 310
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00018343291830734176,
      "loss": 0.0,
      "step": 311
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.7252,
      "step": 312
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00018285878422969983,
      "loss": 0.0,
      "step": 313
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001825683949996556,
      "loss": 0.2794,
      "step": 314
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00018227580129316366,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018198101092212267,
      "loss": 0.6174,
      "step": 316
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018168403175707954,
      "loss": 0.1033,
      "step": 317
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001813848717270195,
      "loss": 0.0,
      "step": 318
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00018108353881915402,
      "loss": 0.4028,
      "step": 319
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00018078004107870797,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00018047438660870446,
      "loss": 0.0,
      "step": 321
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00018016658356974884,
      "loss": 1.2,
      "step": 322
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001798566401798106,
      "loss": 1.112,
      "step": 323
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00017954456471400393,
      "loss": 0.0,
      "step": 324
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00017923036550436704,
      "loss": 0.3934,
      "step": 325
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.3015,
      "step": 326
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00017859562946503788,
      "loss": 0.0726,
      "step": 327
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00017827510958203147,
      "loss": 0.9278,
      "step": 328
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00017795249984811396,
      "loss": 0.6865,
      "step": 329
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00017762780887657574,
      "loss": 0.1301,
      "step": 330
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001773010453362737,
      "loss": 0.3788,
      "step": 331
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001769722179513998,
      "loss": 0.1105,
      "step": 332
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00017664133550124815,
      "loss": 0.8738,
      "step": 333
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00017630840681998066,
      "loss": 0.4048,
      "step": 334
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00017597344079639112,
      "loss": 0.9362,
      "step": 335
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00017563644637366788,
      "loss": 0.0,
      "step": 336
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00017529743254915512,
      "loss": 0.0,
      "step": 337
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001749564083741126,
      "loss": 0.24,
      "step": 338
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00017461338295347406,
      "loss": 0.0,
      "step": 339
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.000174268365445604,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001739213650620533,
      "loss": 0.1102,
      "step": 341
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00017357239106731317,
      "loss": 0.8462,
      "step": 342
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00017322145277856794,
      "loss": 0.0,
      "step": 343
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00017286855956544613,
      "loss": 0.103,
      "step": 344
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001725137208497705,
      "loss": 0.3364,
      "step": 345
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001721569461053062,
      "loss": 0.1886,
      "step": 346
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001717982448575082,
      "loss": 0.0,
      "step": 347
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00017143762668326667,
      "loss": 1.0661,
      "step": 348
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00017107510121065138,
      "loss": 0.9661,
      "step": 349
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.254,
      "step": 350
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001703443671369333,
      "loss": 0.4995,
      "step": 351
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016997617804554796,
      "loss": 0.0,
      "step": 352
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016960612067470288,
      "loss": 0.2468,
      "step": 353
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016923420490448296,
      "loss": 0.0,
      "step": 354
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001688604406645903,
      "loss": 0.0,
      "step": 355
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00016848483793407873,
      "loss": 0.0,
      "step": 356
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00016810740674108764,
      "loss": 0.0,
      "step": 357
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.6732,
      "step": 358
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00016734709932404403,
      "loss": 0.0,
      "step": 359
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00016696424339928152,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00016657959961007747,
      "loss": 0.1854,
      "step": 361
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00016619317822595667,
      "loss": 0.0,
      "step": 362
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00016580498956390342,
      "loss": 1.3683,
      "step": 363
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00016541504398808631,
      "loss": 0.6392,
      "step": 364
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016502335190958135,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00016462992378609407,
      "loss": 0.0,
      "step": 366
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00016423477012168038,
      "loss": 0.0,
      "step": 367
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00016383790146646588,
      "loss": 2.2779,
      "step": 368
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00016343932841636456,
      "loss": 0.0,
      "step": 369
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001630390616127955,
      "loss": 1.1432,
      "step": 370
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00016263711174239914,
      "loss": 0.2808,
      "step": 371
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00016223348953675162,
      "loss": 0.2215,
      "step": 372
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00016182820577207842,
      "loss": 0.2374,
      "step": 373
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001614212712689668,
      "loss": 0.1185,
      "step": 374
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00016101269689207655,
      "loss": 1.9245,
      "step": 375
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00016060249354985025,
      "loss": 0.0,
      "step": 376
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00016019067219422178,
      "loss": 0.0,
      "step": 377
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001597772438203241,
      "loss": 0.1409,
      "step": 378
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001593622194661956,
      "loss": 0.4018,
      "step": 379
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015894561021248535,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015852742718215743,
      "loss": 0.8553,
      "step": 381
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015810768154019385,
      "loss": 0.0,
      "step": 382
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001576863844932963,
      "loss": 0.0,
      "step": 383
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015726354728958736,
      "loss": 0.5503,
      "step": 384
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001568391812183097,
      "loss": 0.0961,
      "step": 385
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015641329760952513,
      "loss": 0.6591,
      "step": 386
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015598590783381163,
      "loss": 0.0,
      "step": 387
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.122,
      "step": 388
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015512665546467007,
      "loss": 0.0,
      "step": 389
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015426151587427547,
      "loss": 0.0,
      "step": 391
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015382676721935345,
      "loss": 0.3215,
      "step": 392
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015339058145474085,
      "loss": 0.0,
      "step": 393
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015295297022607088,
      "loss": 0.2013,
      "step": 394
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015251394521703494,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00015207351814907068,
      "loss": 0.3587,
      "step": 396
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.000151631700781049,
      "loss": 0.0,
      "step": 397
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00015118850490896012,
      "loss": 0.7218,
      "step": 398
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001507439423655987,
      "loss": 1.1481,
      "step": 399
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00015029802502024788,
      "loss": 0.4194,
      "step": 400
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001498507647783623,
      "loss": 0.0,
      "step": 401
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014940217358125042,
      "loss": 0.0,
      "step": 402
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001489522634057555,
      "loss": 2.2446,
      "step": 403
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014850104626393598,
      "loss": 0.3913,
      "step": 404
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014804853420274472,
      "loss": 0.1975,
      "step": 405
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.1008,
      "step": 406
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001471396736825998,
      "loss": 0.3,
      "step": 407
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014668334948912453,
      "loss": 0.0,
      "step": 408
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014622577890658665,
      "loss": 0.3837,
      "step": 409
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014576697415156817,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014530694747360204,
      "loss": 0.0,
      "step": 411
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014484571115484508,
      "loss": 0.0,
      "step": 412
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001443832775097501,
      "loss": 0.7469,
      "step": 413
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014391965888473703,
      "loss": 0.0,
      "step": 414
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001434548676578634,
      "loss": 0.0,
      "step": 415
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001429889162384937,
      "loss": 0.0,
      "step": 416
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014252181706696817,
      "loss": 0.7078,
      "step": 417
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014205358261427074,
      "loss": 0.308,
      "step": 418
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014158422538169596,
      "loss": 0.6541,
      "step": 419
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001411137579005151,
      "loss": 1.7852,
      "step": 420
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001406421927316419,
      "loss": 0.4482,
      "step": 421
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.0,
      "step": 422
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00013969581972067164,
      "loss": 0.0,
      "step": 423
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001392210371455913,
      "loss": 0.4676,
      "step": 424
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00013874520741617735,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.000138268343236509,
      "loss": 1.6066,
      "step": 426
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00013779045733828407,
      "loss": 0.617,
      "step": 427
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013731156248047904,
      "loss": 0.2663,
      "step": 428
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013683167144900834,
      "loss": 0.1382,
      "step": 429
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013635079705638298,
      "loss": 0.2504,
      "step": 430
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013586895214136874,
      "loss": 0.294,
      "step": 431
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00013538614956864296,
      "loss": 0.0,
      "step": 432
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001349024022284514,
      "loss": 0.0,
      "step": 433
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013441772303626387,
      "loss": 0.7406,
      "step": 434
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013393212493242963,
      "loss": 0.5646,
      "step": 435
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013344562088183165,
      "loss": 0.2678,
      "step": 436
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013295822387354071,
      "loss": 0.9045,
      "step": 437
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013246994692046836,
      "loss": 2.233,
      "step": 438
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001319808030590197,
      "loss": 0.0,
      "step": 439
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001314908053487452,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013099996687199203,
      "loss": 0.7132,
      "step": 441
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013050830073355488,
      "loss": 0.0,
      "step": 442
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.000130015820060326,
      "loss": 0.0,
      "step": 443
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00012952253800094468,
      "loss": 0.0,
      "step": 444
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00012902846772544624,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00012853362242491053,
      "loss": 0.2216,
      "step": 446
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00012803801531110955,
      "loss": 1.9331,
      "step": 447
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001275416596161548,
      "loss": 0.328,
      "step": 448
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00012704456859214397,
      "loss": 0.0,
      "step": 449
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00012654675551080724,
      "loss": 0.5864,
      "step": 450
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00012604823366315273,
      "loss": 0.0,
      "step": 451
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00012554901635911187,
      "loss": 0.0,
      "step": 452
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00012504911692718385,
      "loss": 0.1276,
      "step": 453
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.0,
      "step": 454
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001240473250843669,
      "loss": 0.6042,
      "step": 455
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00012354545942011057,
      "loss": 0.2888,
      "step": 456
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00012304296512051814,
      "loss": 0.6748,
      "step": 457
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00012253985560158062,
      "loss": 0.1189,
      "step": 458
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00012203614429571475,
      "loss": 0.0,
      "step": 459
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00012153184465140413,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00012102697013284034,
      "loss": 0.0,
      "step": 461
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00012052153421956342,
      "loss": 0.3809,
      "step": 462
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00012001555040610197,
      "loss": 0.0,
      "step": 463
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.0458,
      "step": 464
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00011900199312952047,
      "loss": 0.7787,
      "step": 465
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00011849444672715586,
      "loss": 1.0734,
      "step": 466
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001179864065453951,
      "loss": 0.7641,
      "step": 467
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00011747788614829758,
      "loss": 0.1514,
      "step": 468
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00011696889911274393,
      "loss": 0.0,
      "step": 469
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00011645945902807341,
      "loss": 1.34,
      "step": 470
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001159495794957211,
      "loss": 0.9174,
      "step": 471
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00011543927412885489,
      "loss": 1.1492,
      "step": 472
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001149285565520119,
      "loss": 0.2276,
      "step": 473
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00011441744040073468,
      "loss": 0.0,
      "step": 474
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001139059393212074,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00011339406696989128,
      "loss": 0.0,
      "step": 476
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00011288183701315995,
      "loss": 0.13,
      "step": 477
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00011236926312693479,
      "loss": 0.7612,
      "step": 478
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00011185635899631963,
      "loss": 0.0,
      "step": 479
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00011134313831523547,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00011082961478605475,
      "loss": 0.0,
      "step": 481
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00011031580211923571,
      "loss": 0.0,
      "step": 482
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001098017140329561,
      "loss": 1.1886,
      "step": 483
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00010928736425274701,
      "loss": 1.2054,
      "step": 484
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00010877276651112662,
      "loss": 0.0,
      "step": 485
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.0,
      "step": 486
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00010774288210645862,
      "loss": 0.4863,
      "step": 487
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00010722762294008106,
      "loss": 0.0,
      "step": 488
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00010671217080489814,
      "loss": 0.0,
      "step": 489
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00010619653946285947,
      "loss": 0.929,
      "step": 490
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00010568074268069928,
      "loss": 0.262,
      "step": 491
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00010516479422956882,
      "loss": 0.7501,
      "step": 492
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00010464870788466873,
      "loss": 0.3049,
      "step": 493
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00010413249742488131,
      "loss": 0.8594,
      "step": 494
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00010361617663240253,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00010309975929237408,
      "loss": 0.6285,
      "step": 496
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00010258325919251537,
      "loss": 1.0879,
      "step": 497
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00010206669012275545,
      "loss": 0.6124,
      "step": 498
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00010155006587486469,
      "loss": 0.0,
      "step": 499
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00010103340024208674,
      "loss": 0.4775,
      "step": 500
    }
  ],
  "max_steps": 640,
  "num_train_epochs": 3,
  "total_flos": 1.6543227452424192e+16,
  "trial_name": null,
  "trial_params": null
}