{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.030150753768845,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 1.5723,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8685280723454155e-06,
      "loss": 1.3682,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.1314719276545845e-06,
      "loss": 1.3945,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.737056144690831e-06,
      "loss": 1.1943,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.982444017039271e-06,
      "loss": 1.1201,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.9507,
      "step": 6
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.0860331325016918e-05,
      "loss": 0.8657,
      "step": 7
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.1605584217036247e-05,
      "loss": 0.7603,
      "step": 8
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.2262943855309169e-05,
      "loss": 0.7432,
      "step": 9
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.2850972089384688e-05,
      "loss": 0.5391,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.3382908331057727e-05,
      "loss": 0.4824,
      "step": 11
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.3868528072345415e-05,
      "loss": 0.4417,
      "step": 12
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.4315254929650773e-05,
      "loss": 0.3767,
      "step": 13
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.4728859397362334e-05,
      "loss": 0.3174,
      "step": 14
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.5113915944693856e-05,
      "loss": 0.2817,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.5474112289381662e-05,
      "loss": 0.2033,
      "step": 16
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.581246474604569e-05,
      "loss": 0.2188,
      "step": 17
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.6131471927654584e-05,
      "loss": 0.1722,
      "step": 18
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.643322683504497e-05,
      "loss": 0.1549,
      "step": 19
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.67195001617301e-05,
      "loss": 0.1922,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.6991803252671504e-05,
      "loss": 0.1572,
      "step": 21
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7251436403403145e-05,
      "loss": 0.1202,
      "step": 22
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7499526414000294e-05,
      "loss": 0.178,
      "step": 23
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7737056144690832e-05,
      "loss": 0.1225,
      "step": 24
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7964888034078543e-05,
      "loss": 0.1224,
      "step": 25
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.818378300199619e-05,
      "loss": 0.0988,
      "step": 26
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8394415782963754e-05,
      "loss": 0.1161,
      "step": 27
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8597387469707752e-05,
      "loss": 0.0817,
      "step": 28
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.879323585457153e-05,
      "loss": 0.1048,
      "step": 29
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.898244401703927e-05,
      "loss": 0.1063,
      "step": 30
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.916544750264171e-05,
      "loss": 0.0691,
      "step": 31
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.934264036172708e-05,
      "loss": 0.0934,
      "step": 32
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9514380258712308e-05,
      "loss": 0.0874,
      "step": 33
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.968099281839111e-05,
      "loss": 0.094,
      "step": 34
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9842775342056188e-05,
      "loss": 0.091,
      "step": 35
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0572,
      "step": 36
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.0748,
      "step": 37
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 0.0929,
      "step": 38
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.0589,
      "step": 39
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.0685,
      "step": 40
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.0488,
      "step": 41
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.0631,
      "step": 42
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.0548,
      "step": 43
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.1035,
      "step": 44
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.071,
      "step": 45
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.0443,
      "step": 46
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.0568,
      "step": 47
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.0556,
      "step": 48
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.0482,
      "step": 49
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.0856,
      "step": 50
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.0387,
      "step": 51
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.0437,
      "step": 52
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.0388,
      "step": 53
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.0538,
      "step": 54
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.0593,
      "step": 55
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.0477,
      "step": 56
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.0529,
      "step": 57
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.0335,
      "step": 58
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.0445,
      "step": 59
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.0396,
      "step": 60
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.0373,
      "step": 61
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 0.0577,
      "step": 62
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.0401,
      "step": 63
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.0394,
      "step": 64
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.0495,
      "step": 65
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.0585,
      "step": 66
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.0378,
      "step": 67
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.0545,
      "step": 68
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.0353,
      "step": 69
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.04,
      "step": 70
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.0376,
      "step": 71
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.049,
      "step": 72
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.0417,
      "step": 73
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.0338,
      "step": 74
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.0359,
      "step": 75
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.039,
      "step": 76
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.0401,
      "step": 77
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.0271,
      "step": 78
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.0392,
      "step": 79
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.0477,
      "step": 80
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.0334,
      "step": 81
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.0444,
      "step": 82
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.031,
      "step": 83
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.0405,
      "step": 84
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.0315,
      "step": 85
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.0327,
      "step": 86
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.0279,
      "step": 87
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.0345,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.0347,
      "step": 89
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.0234,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.029,
      "step": 91
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 0.0405,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.0396,
      "step": 93
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.0325,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 0.0344,
      "step": 95
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.0303,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.0447,
      "step": 97
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.0219,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 0.0222,
      "step": 99
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 0.0225,
      "step": 100
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.0167,
      "step": 101
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 102
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.0135,
      "step": 103
    },
    {
      "epoch": 1.05,
      "learning_rate": 2e-05,
      "loss": 0.0161,
      "step": 104
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 0.017,
      "step": 105
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.019,
      "step": 106
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 0.0138,
      "step": 107
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.0123,
      "step": 108
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.0173,
      "step": 109
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.0142,
      "step": 110
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 0.019,
      "step": 111
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.0136,
      "step": 112
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.0173,
      "step": 113
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.0155,
      "step": 114
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.0116,
      "step": 115
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.0165,
      "step": 116
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 0.0225,
      "step": 117
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.0127,
      "step": 118
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 119
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 0.0202,
      "step": 120
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.0174,
      "step": 121
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 122
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 0.0192,
      "step": 123
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.014,
      "step": 124
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.0134,
      "step": 125
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 0.013,
      "step": 126
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.0125,
      "step": 127
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 0.0123,
      "step": 128
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.0134,
      "step": 129
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 0.0256,
      "step": 130
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.0161,
      "step": 131
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.0157,
      "step": 132
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 0.015,
      "step": 133
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.014,
      "step": 134
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.0145,
      "step": 135
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.01,
      "step": 136
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 0.0145,
      "step": 137
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.0148,
      "step": 138
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.0124,
      "step": 139
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 0.0094,
      "step": 140
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.0138,
      "step": 141
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.0187,
      "step": 142
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 0.0172,
      "step": 143
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.0105,
      "step": 144
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.014,
      "step": 145
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 0.0166,
      "step": 146
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.0178,
      "step": 147
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 0.0176,
      "step": 148
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.0248,
      "step": 149
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 0.0136,
      "step": 150
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.0111,
      "step": 151
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 0.0161,
      "step": 152
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.0138,
      "step": 153
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.012,
      "step": 154
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 0.0148,
      "step": 155
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.0127,
      "step": 156
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.0152,
      "step": 157
    },
    {
      "epoch": 1.59,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 158
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.0113,
      "step": 159
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.0171,
      "step": 160
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 0.0102,
      "step": 161
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.0145,
      "step": 162
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-05,
      "loss": 0.0196,
      "step": 163
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.0232,
      "step": 164
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.0173,
      "step": 165
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.0116,
      "step": 166
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.016,
      "step": 167
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.0094,
      "step": 168
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.0255,
      "step": 169
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 0.0133,
      "step": 170
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 0.0196,
      "step": 171
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 0.0168,
      "step": 172
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.0096,
      "step": 173
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.0125,
      "step": 174
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.0127,
      "step": 175
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.0199,
      "step": 176
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.0108,
      "step": 177
    },
    {
      "epoch": 1.79,
      "learning_rate": 2e-05,
      "loss": 0.0113,
      "step": 178
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.0161,
      "step": 179
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.0093,
      "step": 180
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 0.0165,
      "step": 181
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.0183,
      "step": 182
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.0144,
      "step": 183
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 0.0134,
      "step": 184
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.0154,
      "step": 185
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.0107,
      "step": 186
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 0.0097,
      "step": 187
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.0097,
      "step": 188
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.0096,
      "step": 189
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.011,
      "step": 190
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 0.0102,
      "step": 191
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.0194,
      "step": 192
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 193
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 0.0177,
      "step": 194
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.0148,
      "step": 195
    },
    {
      "epoch": 1.97,
      "learning_rate": 2e-05,
      "loss": 0.0113,
      "step": 196
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.0107,
      "step": 197
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 0.0089,
      "step": 198
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.0153,
      "step": 199
    },
    {
      "epoch": 2.01,
      "learning_rate": 2e-05,
      "loss": 0.0091,
      "step": 200
    },
    {
      "epoch": 2.02,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 201
    },
    {
      "epoch": 2.03,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 202
    },
    {
      "epoch": 2.04,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 203
    },
    {
      "epoch": 2.05,
      "learning_rate": 2e-05,
      "loss": 0.0055,
      "step": 204
    },
    {
      "epoch": 2.06,
      "learning_rate": 2e-05,
      "loss": 0.0085,
      "step": 205
    },
    {
      "epoch": 2.07,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 206
    },
    {
      "epoch": 2.08,
      "learning_rate": 2e-05,
      "loss": 0.0089,
      "step": 207
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 208
    },
    {
      "epoch": 2.1,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 209
    },
    {
      "epoch": 2.11,
      "learning_rate": 2e-05,
      "loss": 0.0069,
      "step": 210
    },
    {
      "epoch": 2.12,
      "learning_rate": 2e-05,
      "loss": 0.009,
      "step": 211
    },
    {
      "epoch": 2.13,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 212
    },
    {
      "epoch": 2.14,
      "learning_rate": 2e-05,
      "loss": 0.0085,
      "step": 213
    },
    {
      "epoch": 2.15,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 214
    },
    {
      "epoch": 2.16,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 215
    },
    {
      "epoch": 2.17,
      "learning_rate": 2e-05,
      "loss": 0.0084,
      "step": 216
    },
    {
      "epoch": 2.18,
      "learning_rate": 2e-05,
      "loss": 0.0064,
      "step": 217
    },
    {
      "epoch": 2.19,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 218
    },
    {
      "epoch": 2.2,
      "learning_rate": 2e-05,
      "loss": 0.0074,
      "step": 219
    },
    {
      "epoch": 2.21,
      "learning_rate": 2e-05,
      "loss": 0.006,
      "step": 220
    },
    {
      "epoch": 2.22,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 221
    },
    {
      "epoch": 2.23,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 222
    },
    {
      "epoch": 2.24,
      "learning_rate": 2e-05,
      "loss": 0.0065,
      "step": 223
    },
    {
      "epoch": 2.25,
      "learning_rate": 2e-05,
      "loss": 0.0068,
      "step": 224
    },
    {
      "epoch": 2.26,
      "learning_rate": 2e-05,
      "loss": 0.0089,
      "step": 225
    },
    {
      "epoch": 2.27,
      "learning_rate": 2e-05,
      "loss": 0.0079,
      "step": 226
    },
    {
      "epoch": 2.28,
      "learning_rate": 2e-05,
      "loss": 0.0071,
      "step": 227
    },
    {
      "epoch": 2.29,
      "learning_rate": 2e-05,
      "loss": 0.0067,
      "step": 228
    },
    {
      "epoch": 2.3,
      "learning_rate": 2e-05,
      "loss": 0.0079,
      "step": 229
    },
    {
      "epoch": 2.31,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 230
    },
    {
      "epoch": 2.32,
      "learning_rate": 2e-05,
      "loss": 0.0078,
      "step": 231
    },
    {
      "epoch": 2.33,
      "learning_rate": 2e-05,
      "loss": 0.0096,
      "step": 232
    },
    {
      "epoch": 2.34,
      "learning_rate": 2e-05,
      "loss": 0.0082,
      "step": 233
    },
    {
      "epoch": 2.35,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 234
    },
    {
      "epoch": 2.36,
      "learning_rate": 2e-05,
      "loss": 0.0075,
      "step": 235
    },
    {
      "epoch": 2.37,
      "learning_rate": 2e-05,
      "loss": 0.0114,
      "step": 236
    },
    {
      "epoch": 2.38,
      "learning_rate": 2e-05,
      "loss": 0.0075,
      "step": 237
    },
    {
      "epoch": 2.39,
      "learning_rate": 2e-05,
      "loss": 0.0094,
      "step": 238
    },
    {
      "epoch": 2.4,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 239
    },
    {
      "epoch": 2.41,
      "learning_rate": 2e-05,
      "loss": 0.0091,
      "step": 240
    },
    {
      "epoch": 2.42,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 241
    },
    {
      "epoch": 2.43,
      "learning_rate": 2e-05,
      "loss": 0.0075,
      "step": 242
    },
    {
      "epoch": 2.44,
      "learning_rate": 2e-05,
      "loss": 0.0089,
      "step": 243
    },
    {
      "epoch": 2.45,
      "learning_rate": 2e-05,
      "loss": 0.0074,
      "step": 244
    },
    {
      "epoch": 2.46,
      "learning_rate": 2e-05,
      "loss": 0.008,
      "step": 245
    },
    {
      "epoch": 2.47,
      "learning_rate": 2e-05,
      "loss": 0.0076,
      "step": 246
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 0.0073,
      "step": 247
    },
    {
      "epoch": 2.49,
      "learning_rate": 2e-05,
      "loss": 0.011,
      "step": 248
    },
    {
      "epoch": 2.5,
      "learning_rate": 2e-05,
      "loss": 0.0069,
      "step": 249
    },
    {
      "epoch": 2.51,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 250
    },
    {
      "epoch": 2.52,
      "learning_rate": 2e-05,
      "loss": 0.0091,
      "step": 251
    },
    {
      "epoch": 2.53,
      "learning_rate": 2e-05,
      "loss": 0.0079,
      "step": 252
    },
    {
      "epoch": 2.54,
      "learning_rate": 2e-05,
      "loss": 0.007,
      "step": 253
    },
    {
      "epoch": 2.55,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 254
    },
    {
      "epoch": 2.56,
      "learning_rate": 2e-05,
      "loss": 0.0098,
      "step": 255
    },
    {
      "epoch": 2.57,
      "learning_rate": 2e-05,
      "loss": 0.006,
      "step": 256
    },
    {
      "epoch": 2.58,
      "learning_rate": 2e-05,
      "loss": 0.0055,
      "step": 257
    },
    {
      "epoch": 2.59,
      "learning_rate": 2e-05,
      "loss": 0.0083,
      "step": 258
    },
    {
      "epoch": 2.6,
      "learning_rate": 2e-05,
      "loss": 0.0084,
      "step": 259
    },
    {
      "epoch": 2.61,
      "learning_rate": 2e-05,
      "loss": 0.0076,
      "step": 260
    },
    {
      "epoch": 2.62,
      "learning_rate": 2e-05,
      "loss": 0.0074,
      "step": 261
    },
    {
      "epoch": 2.63,
      "learning_rate": 2e-05,
      "loss": 0.0069,
      "step": 262
    },
    {
      "epoch": 2.64,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 263
    },
    {
      "epoch": 2.65,
      "learning_rate": 2e-05,
      "loss": 0.0066,
      "step": 264
    },
    {
      "epoch": 2.66,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 265
    },
    {
      "epoch": 2.67,
      "learning_rate": 2e-05,
      "loss": 0.0078,
      "step": 266
    },
    {
      "epoch": 2.68,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 267
    },
    {
      "epoch": 2.69,
      "learning_rate": 2e-05,
      "loss": 0.0064,
      "step": 268
    },
    {
      "epoch": 2.7,
      "learning_rate": 2e-05,
      "loss": 0.007,
      "step": 269
    },
    {
      "epoch": 2.71,
      "learning_rate": 2e-05,
      "loss": 0.0064,
      "step": 270
    },
    {
      "epoch": 2.72,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 271
    },
    {
      "epoch": 2.73,
      "learning_rate": 2e-05,
      "loss": 0.0069,
      "step": 272
    },
    {
      "epoch": 2.74,
      "learning_rate": 2e-05,
      "loss": 0.0076,
      "step": 273
    },
    {
      "epoch": 2.75,
      "learning_rate": 2e-05,
      "loss": 0.0102,
      "step": 274
    },
    {
      "epoch": 2.76,
      "learning_rate": 2e-05,
      "loss": 0.0064,
      "step": 275
    },
    {
      "epoch": 2.77,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 276
    },
    {
      "epoch": 2.78,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 277
    },
    {
      "epoch": 2.79,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 278
    },
    {
      "epoch": 2.8,
      "learning_rate": 2e-05,
      "loss": 0.006,
      "step": 279
    },
    {
      "epoch": 2.81,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 280
    },
    {
      "epoch": 2.82,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 281
    },
    {
      "epoch": 2.83,
      "learning_rate": 2e-05,
      "loss": 0.0063,
      "step": 282
    },
    {
      "epoch": 2.84,
      "learning_rate": 2e-05,
      "loss": 0.0065,
      "step": 283
    },
    {
      "epoch": 2.85,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 284
    },
    {
      "epoch": 2.86,
      "learning_rate": 2e-05,
      "loss": 0.0068,
      "step": 285
    },
    {
      "epoch": 2.87,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 286
    },
    {
      "epoch": 2.88,
      "learning_rate": 2e-05,
      "loss": 0.006,
      "step": 287
    },
    {
      "epoch": 2.89,
      "learning_rate": 2e-05,
      "loss": 0.0071,
      "step": 288
    },
    {
      "epoch": 2.9,
      "learning_rate": 2e-05,
      "loss": 0.0071,
      "step": 289
    },
    {
      "epoch": 2.91,
      "learning_rate": 2e-05,
      "loss": 0.0082,
      "step": 290
    },
    {
      "epoch": 2.92,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 291
    },
    {
      "epoch": 2.93,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 292
    },
    {
      "epoch": 2.94,
      "learning_rate": 2e-05,
      "loss": 0.0087,
      "step": 293
    },
    {
      "epoch": 2.95,
      "learning_rate": 2e-05,
      "loss": 0.006,
      "step": 294
    },
    {
      "epoch": 2.96,
      "learning_rate": 2e-05,
      "loss": 0.0065,
      "step": 295
    },
    {
      "epoch": 2.97,
      "learning_rate": 2e-05,
      "loss": 0.0067,
      "step": 296
    },
    {
      "epoch": 2.98,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 297
    },
    {
      "epoch": 2.99,
      "learning_rate": 2e-05,
      "loss": 0.0071,
      "step": 298
    },
    {
      "epoch": 3.01,
      "learning_rate": 2e-05,
      "loss": 0.0077,
      "step": 299
    },
    {
      "epoch": 3.02,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 300
    },
    {
      "epoch": 3.03,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 301
    },
    {
      "epoch": 3.04,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 302
    },
    {
      "epoch": 3.05,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 303
    },
    {
      "epoch": 3.06,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 304
    },
    {
      "epoch": 3.07,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 305
    },
    {
      "epoch": 3.08,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 306
    },
    {
      "epoch": 3.09,
      "learning_rate": 2e-05,
      "loss": 0.0028,
      "step": 307
    },
    {
      "epoch": 3.1,
      "learning_rate": 2e-05,
      "loss": 0.0072,
      "step": 308
    },
    {
      "epoch": 3.11,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 309
    },
    {
      "epoch": 3.12,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 310
    },
    {
      "epoch": 3.13,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 311
    },
    {
      "epoch": 3.14,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 312
    },
    {
      "epoch": 3.15,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 313
    },
    {
      "epoch": 3.16,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 314
    },
    {
      "epoch": 3.17,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 315
    },
    {
      "epoch": 3.18,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 316
    },
    {
      "epoch": 3.19,
      "learning_rate": 2e-05,
      "loss": 0.0053,
      "step": 317
    },
    {
      "epoch": 3.2,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 318
    },
    {
      "epoch": 3.21,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 319
    },
    {
      "epoch": 3.22,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 320
    },
    {
      "epoch": 3.23,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 321
    },
    {
      "epoch": 3.24,
      "learning_rate": 2e-05,
      "loss": 0.0059,
      "step": 322
    },
    {
      "epoch": 3.25,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 323
    },
    {
      "epoch": 3.26,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 324
    },
    {
      "epoch": 3.27,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 325
    },
    {
      "epoch": 3.28,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 326
    },
    {
      "epoch": 3.29,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 327
    },
    {
      "epoch": 3.3,
      "learning_rate": 2e-05,
      "loss": 0.0065,
      "step": 328
    },
    {
      "epoch": 3.31,
      "learning_rate": 2e-05,
      "loss": 0.0086,
      "step": 329
    },
    {
      "epoch": 3.32,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 330
    },
    {
      "epoch": 3.33,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 331
    },
    {
      "epoch": 3.34,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 332
    },
    {
      "epoch": 3.35,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 333
    },
    {
      "epoch": 3.36,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 334
    },
    {
      "epoch": 3.37,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 335
    },
    {
      "epoch": 3.38,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 336
    },
    {
      "epoch": 3.39,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 337
    },
    {
      "epoch": 3.4,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 338
    },
    {
      "epoch": 3.41,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 339
    },
    {
      "epoch": 3.42,
      "learning_rate": 2e-05,
      "loss": 0.0058,
      "step": 340
    },
    {
      "epoch": 3.43,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 341
    },
    {
      "epoch": 3.44,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 342
    },
    {
      "epoch": 3.45,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 343
    },
    {
      "epoch": 3.46,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 344
    },
    {
      "epoch": 3.47,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 345
    },
    {
      "epoch": 3.48,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 346
    },
    {
      "epoch": 3.49,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 347
    },
    {
      "epoch": 3.5,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 348
    },
    {
      "epoch": 3.51,
      "learning_rate": 2e-05,
      "loss": 0.0031,
      "step": 349
    },
    {
      "epoch": 3.52,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 350
    },
    {
      "epoch": 3.53,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 351
    },
    {
      "epoch": 3.54,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 352
    },
    {
      "epoch": 3.55,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 353
    },
    {
      "epoch": 3.56,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 354
    },
    {
      "epoch": 3.57,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 355
    },
    {
      "epoch": 3.58,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 356
    },
    {
      "epoch": 3.59,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 357
    },
    {
      "epoch": 3.6,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 358
    },
    {
      "epoch": 3.61,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 359
    },
    {
      "epoch": 3.62,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 360
    },
    {
      "epoch": 3.63,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 361
    },
    {
      "epoch": 3.64,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 362
    },
    {
      "epoch": 3.65,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 363
    },
    {
      "epoch": 3.66,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 364
    },
    {
      "epoch": 3.67,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 365
    },
    {
      "epoch": 3.68,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 366
    },
    {
      "epoch": 3.69,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 367
    },
    {
      "epoch": 3.7,
      "learning_rate": 2e-05,
      "loss": 0.0087,
      "step": 368
    },
    {
      "epoch": 3.71,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 369
    },
    {
      "epoch": 3.72,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 370
    },
    {
      "epoch": 3.73,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 371
    },
    {
      "epoch": 3.74,
      "learning_rate": 2e-05,
      "loss": 0.0074,
      "step": 372
    },
    {
      "epoch": 3.75,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 373
    },
    {
      "epoch": 3.76,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 374
    },
    {
      "epoch": 3.77,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 375
    },
    {
      "epoch": 3.78,
      "learning_rate": 2e-05,
      "loss": 0.0059,
      "step": 376
    },
    {
      "epoch": 3.79,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 377
    },
    {
      "epoch": 3.8,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 378
    },
    {
      "epoch": 3.81,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 379
    },
    {
      "epoch": 3.82,
      "learning_rate": 2e-05,
      "loss": 0.0031,
      "step": 380
    },
    {
      "epoch": 3.83,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 381
    },
    {
      "epoch": 3.84,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 382
    },
    {
      "epoch": 3.85,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 383
    },
    {
      "epoch": 3.86,
      "learning_rate": 2e-05,
      "loss": 0.0083,
      "step": 384
    },
    {
      "epoch": 3.87,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 385
    },
    {
      "epoch": 3.88,
      "learning_rate": 2e-05,
      "loss": 0.0064,
      "step": 386
    },
    {
      "epoch": 3.89,
      "learning_rate": 2e-05,
      "loss": 0.0065,
      "step": 387
    },
    {
      "epoch": 3.9,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 388
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 389
    },
    {
      "epoch": 3.92,
      "learning_rate": 2e-05,
      "loss": 0.0067,
      "step": 390
    },
    {
      "epoch": 3.93,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 391
    },
    {
      "epoch": 3.94,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 392
    },
    {
      "epoch": 3.95,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 393
    },
    {
      "epoch": 3.96,
      "learning_rate": 2e-05,
      "loss": 0.0084,
      "step": 394
    },
    {
      "epoch": 3.97,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 395
    },
    {
      "epoch": 3.98,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 396
    },
    {
      "epoch": 3.99,
      "learning_rate": 2e-05,
      "loss": 0.0061,
      "step": 397
    },
    {
      "epoch": 4.0,
      "learning_rate": 2e-05,
      "loss": 0.0062,
      "step": 398
    },
    {
      "epoch": 4.01,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 399
    },
    {
      "epoch": 4.02,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 400
    },
    {
      "epoch": 4.03,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 401
    },
    {
      "epoch": 4.04,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 402
    },
    {
      "epoch": 4.05,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 403
    },
    {
      "epoch": 4.06,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 404
    },
    {
      "epoch": 4.07,
      "learning_rate": 2e-05,
      "loss": 0.0054,
      "step": 405
    },
    {
      "epoch": 4.08,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 406
    },
    {
      "epoch": 4.09,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 407
    },
    {
      "epoch": 4.1,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 408
    },
    {
      "epoch": 4.11,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 409
    },
    {
      "epoch": 4.12,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 410
    },
    {
      "epoch": 4.13,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 411
    },
    {
      "epoch": 4.14,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 412
    },
    {
      "epoch": 4.15,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 413
    },
    {
      "epoch": 4.16,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 414
    },
    {
      "epoch": 4.17,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 415
    },
    {
      "epoch": 4.18,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 416
    },
    {
      "epoch": 4.19,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 417
    },
    {
      "epoch": 4.2,
      "learning_rate": 2e-05,
      "loss": 0.0028,
      "step": 418
    },
    {
      "epoch": 4.21,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 419
    },
    {
      "epoch": 4.22,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 420
    },
    {
      "epoch": 4.23,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 421
    },
    {
      "epoch": 4.24,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 422
    },
    {
      "epoch": 4.25,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 423
    },
    {
      "epoch": 4.26,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 424
    },
    {
      "epoch": 4.27,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 425
    },
    {
      "epoch": 4.28,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 426
    },
    {
      "epoch": 4.29,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 427
    },
    {
      "epoch": 4.3,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 428
    },
    {
      "epoch": 4.31,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 429
    },
    {
      "epoch": 4.32,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 430
    },
    {
      "epoch": 4.33,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 431
    },
    {
      "epoch": 4.34,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 432
    },
    {
      "epoch": 4.35,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 433
    },
    {
      "epoch": 4.36,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 434
    },
    {
      "epoch": 4.37,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 435
    },
    {
      "epoch": 4.38,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 436
    },
    {
      "epoch": 4.39,
      "learning_rate": 2e-05,
      "loss": 0.007,
      "step": 437
    },
    {
      "epoch": 4.4,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 438
    },
    {
      "epoch": 4.41,
      "learning_rate": 2e-05,
      "loss": 0.0031,
      "step": 439
    },
    {
      "epoch": 4.42,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 440
    },
    {
      "epoch": 4.43,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 441
    },
    {
      "epoch": 4.44,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 442
    },
    {
      "epoch": 4.45,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 443
    },
    {
      "epoch": 4.46,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 444
    },
    {
      "epoch": 4.47,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 445
    },
    {
      "epoch": 4.48,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 446
    },
    {
      "epoch": 4.49,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 447
    },
    {
      "epoch": 4.5,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 448
    },
    {
      "epoch": 4.51,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 449
    },
    {
      "epoch": 4.52,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 450
    },
    {
      "epoch": 4.53,
      "learning_rate": 2e-05,
      "loss": 0.0031,
      "step": 451
    },
    {
      "epoch": 4.54,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 452
    },
    {
      "epoch": 4.55,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 453
    },
    {
      "epoch": 4.56,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 454
    },
    {
      "epoch": 4.57,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 455
    },
    {
      "epoch": 4.58,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 456
    },
    {
      "epoch": 4.59,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 457
    },
    {
      "epoch": 4.6,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 458
    },
    {
      "epoch": 4.61,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 459
    },
    {
      "epoch": 4.62,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 460
    },
    {
      "epoch": 4.63,
      "learning_rate": 2e-05,
      "loss": 0.0031,
      "step": 461
    },
    {
      "epoch": 4.64,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 462
    },
    {
      "epoch": 4.65,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 463
    },
    {
      "epoch": 4.66,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 464
    },
    {
      "epoch": 4.67,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 465
    },
    {
      "epoch": 4.68,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 466
    },
    {
      "epoch": 4.69,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 467
    },
    {
      "epoch": 4.7,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 468
    },
    {
      "epoch": 4.71,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 469
    },
    {
      "epoch": 4.72,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 470
    },
    {
      "epoch": 4.73,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 471
    },
    {
      "epoch": 4.74,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 472
    },
    {
      "epoch": 4.75,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 473
    },
    {
      "epoch": 4.76,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 474
    },
    {
      "epoch": 4.77,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 475
    },
    {
      "epoch": 4.78,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 476
    },
    {
      "epoch": 4.79,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 477
    },
    {
      "epoch": 4.8,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 478
    },
    {
      "epoch": 4.81,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 479
    },
    {
      "epoch": 4.82,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 480
    },
    {
      "epoch": 4.83,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 481
    },
    {
      "epoch": 4.84,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 482
    },
    {
      "epoch": 4.85,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 483
    },
    {
      "epoch": 4.86,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 484
    },
    {
      "epoch": 4.87,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 485
    },
    {
      "epoch": 4.88,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 486
    },
    {
      "epoch": 4.89,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 487
    },
    {
      "epoch": 4.9,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 488
    },
    {
      "epoch": 4.91,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 489
    },
    {
      "epoch": 4.92,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 490
    },
    {
      "epoch": 4.93,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 491
    },
    {
      "epoch": 4.94,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 492
    },
    {
      "epoch": 4.95,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 493
    },
    {
      "epoch": 4.96,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 494
    },
    {
      "epoch": 4.97,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 495
    },
    {
      "epoch": 4.98,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 496
    },
    {
      "epoch": 4.99,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 497
    },
    {
      "epoch": 5.01,
      "learning_rate": 2e-05,
      "loss": 0.0025,
      "step": 498
    },
    {
      "epoch": 5.02,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 499
    },
    {
      "epoch": 5.03,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 500
    },
    {
      "epoch": 5.04,
      "learning_rate": 2e-05,
      "loss": 0.0056,
      "step": 501
    },
    {
      "epoch": 5.05,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 502
    },
    {
      "epoch": 5.06,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 503
    },
    {
      "epoch": 5.07,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 504
    },
    {
      "epoch": 5.08,
      "learning_rate": 2e-05,
      "loss": 0.0023,
      "step": 505
    },
    {
      "epoch": 5.09,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 506
    },
    {
      "epoch": 5.1,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 507
    },
    {
      "epoch": 5.11,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 508
    },
    {
      "epoch": 5.12,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 509
    },
    {
      "epoch": 5.13,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 510
    },
    {
      "epoch": 5.14,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 511
    },
    {
      "epoch": 5.15,
      "learning_rate": 2e-05,
      "loss": 0.0028,
      "step": 512
    },
    {
      "epoch": 5.16,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 513
    },
    {
      "epoch": 5.17,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 514
    },
    {
      "epoch": 5.18,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 515
    },
    {
      "epoch": 5.19,
      "learning_rate": 2e-05,
      "loss": 0.0034,
      "step": 516
    },
    {
      "epoch": 5.2,
      "learning_rate": 2e-05,
      "loss": 0.0053,
      "step": 517
    },
    {
      "epoch": 5.21,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 518
    },
    {
      "epoch": 5.22,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 519
    },
    {
      "epoch": 5.23,
      "learning_rate": 2e-05,
      "loss": 0.0039,
      "step": 520
    },
    {
      "epoch": 5.24,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 521
    },
    {
      "epoch": 5.25,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 522
    },
    {
      "epoch": 5.26,
      "learning_rate": 2e-05,
      "loss": 0.0025,
      "step": 523
    },
    {
      "epoch": 5.27,
      "learning_rate": 2e-05,
      "loss": 0.0025,
      "step": 524
    },
    {
      "epoch": 5.28,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 525
    },
    {
      "epoch": 5.29,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 526
    },
    {
      "epoch": 5.3,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 527
    },
    {
      "epoch": 5.31,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 528
    },
    {
      "epoch": 5.32,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 529
    },
    {
      "epoch": 5.33,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 530
    },
    {
      "epoch": 5.34,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 531
    },
    {
      "epoch": 5.35,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 532
    },
    {
      "epoch": 5.36,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 533
    },
    {
      "epoch": 5.37,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 534
    },
    {
      "epoch": 5.38,
      "learning_rate": 2e-05,
      "loss": 0.0015,
      "step": 535
    },
    {
      "epoch": 5.39,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 536
    },
    {
      "epoch": 5.4,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 537
    },
    {
      "epoch": 5.41,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 538
    },
    {
      "epoch": 5.42,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 539
    },
    {
      "epoch": 5.43,
      "learning_rate": 2e-05,
      "loss": 0.005,
      "step": 540
    },
    {
      "epoch": 5.44,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 541
    },
    {
      "epoch": 5.45,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 542
    },
    {
      "epoch": 5.46,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 543
    },
    {
      "epoch": 5.47,
      "learning_rate": 2e-05,
      "loss": 0.0029,
      "step": 544
    },
    {
      "epoch": 5.48,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 545
    },
    {
      "epoch": 5.49,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 546
    },
    {
      "epoch": 5.5,
      "learning_rate": 2e-05,
      "loss": 0.0024,
      "step": 547
    },
    {
      "epoch": 5.51,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 548
    },
    {
      "epoch": 5.52,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 549
    },
    {
      "epoch": 5.53,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 550
    },
    {
      "epoch": 5.54,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 551
    },
    {
      "epoch": 5.55,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 552
    },
    {
      "epoch": 5.56,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 553
    },
    {
      "epoch": 5.57,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 554
    },
    {
      "epoch": 5.58,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 555
    },
    {
      "epoch": 5.59,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 556
    },
    {
      "epoch": 5.6,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 557
    },
    {
      "epoch": 5.61,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 558
    },
    {
      "epoch": 5.62,
      "learning_rate": 2e-05,
      "loss": 0.0058,
      "step": 559
    },
    {
      "epoch": 5.63,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 560
    },
    {
      "epoch": 5.64,
      "learning_rate": 2e-05,
      "loss": 0.0046,
      "step": 561
    },
    {
      "epoch": 5.65,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 562
    },
    {
      "epoch": 5.66,
      "learning_rate": 2e-05,
      "loss": 0.0033,
      "step": 563
    },
    {
      "epoch": 5.67,
      "learning_rate": 2e-05,
      "loss": 0.0049,
      "step": 564
    },
    {
      "epoch": 5.68,
      "learning_rate": 2e-05,
      "loss": 0.0021,
      "step": 565
    },
    {
      "epoch": 5.69,
      "learning_rate": 2e-05,
      "loss": 0.0055,
      "step": 566
    },
    {
      "epoch": 5.7,
      "learning_rate": 2e-05,
      "loss": 0.004,
      "step": 567
    },
    {
      "epoch": 5.71,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 568
    },
    {
      "epoch": 5.72,
      "learning_rate": 2e-05,
      "loss": 0.0045,
      "step": 569
    },
    {
      "epoch": 5.73,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 570
    },
    {
      "epoch": 5.74,
      "learning_rate": 2e-05,
      "loss": 0.0044,
      "step": 571
    },
    {
      "epoch": 5.75,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 572
    },
    {
      "epoch": 5.76,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 573
    },
    {
      "epoch": 5.77,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 574
    },
    {
      "epoch": 5.78,
      "learning_rate": 2e-05,
      "loss": 0.0036,
      "step": 575
    },
    {
      "epoch": 5.79,
      "learning_rate": 2e-05,
      "loss": 0.0052,
      "step": 576
    },
    {
      "epoch": 5.8,
      "learning_rate": 2e-05,
      "loss": 0.0027,
      "step": 577
    },
    {
      "epoch": 5.81,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 578
    },
    {
      "epoch": 5.82,
      "learning_rate": 2e-05,
      "loss": 0.0069,
      "step": 579
    },
    {
      "epoch": 5.83,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 580
    },
    {
      "epoch": 5.84,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 581
    },
    {
      "epoch": 5.85,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 582
    },
    {
      "epoch": 5.86,
      "learning_rate": 2e-05,
      "loss": 0.0026,
      "step": 583
    },
    {
      "epoch": 5.87,
      "learning_rate": 2e-05,
      "loss": 0.0051,
      "step": 584
    },
    {
      "epoch": 5.88,
      "learning_rate": 2e-05,
      "loss": 0.0042,
      "step": 585
    },
    {
      "epoch": 5.89,
      "learning_rate": 2e-05,
      "loss": 0.0047,
      "step": 586
    },
    {
      "epoch": 5.9,
      "learning_rate": 2e-05,
      "loss": 0.0041,
      "step": 587
    },
    {
      "epoch": 5.91,
      "learning_rate": 2e-05,
      "loss": 0.0057,
      "step": 588
    },
    {
      "epoch": 5.92,
      "learning_rate": 2e-05,
      "loss": 0.0048,
      "step": 589
    },
    {
      "epoch": 5.93,
      "learning_rate": 2e-05,
      "loss": 0.0058,
      "step": 590
    },
    {
      "epoch": 5.94,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 591
    },
    {
      "epoch": 5.95,
      "learning_rate": 2e-05,
      "loss": 0.0037,
      "step": 592
    },
    {
      "epoch": 5.96,
      "learning_rate": 2e-05,
      "loss": 0.0043,
      "step": 593
    },
    {
      "epoch": 5.97,
      "learning_rate": 2e-05,
      "loss": 0.0038,
      "step": 594
    },
    {
      "epoch": 5.98,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 595
    },
    {
      "epoch": 5.99,
      "learning_rate": 2e-05,
      "loss": 0.0032,
      "step": 596
    },
    {
      "epoch": 6.0,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 597
    },
    {
      "epoch": 6.01,
      "learning_rate": 2e-05,
      "loss": 0.0035,
      "step": 598
    },
    {
      "epoch": 6.02,
      "learning_rate": 2e-05,
      "loss": 0.003,
      "step": 599
    },
    {
      "epoch": 6.03,
      "learning_rate": 2e-05,
      "loss": 0.0024,
      "step": 600
    }
  ],
  "max_steps": 1188,
  "num_train_epochs": 12,
  "total_flos": 1271977497329664.0,
  "trial_name": null,
  "trial_params": null
}