{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990726429675425,
  "eval_steps": 500,
  "global_step": 404,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.8153,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.5156,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.4043,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.3099,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.1404,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.0705,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0426,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0642,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0677,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0091,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.0296,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.0148,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.9546,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.9748,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9543,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9525,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9367,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9432,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.9686,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.968,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.965,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.9883,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.985,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.9249,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.9026,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.9078,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9862,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9261,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9255,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9118,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.9403,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.9632,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.9383,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.9658,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.9183,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.9462,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.9275,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.9243,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.9286,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.9015,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.9461,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.9275,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.92,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9182,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9037,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9474,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9114,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9204,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9192,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9507,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8962,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9069,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9104,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9069,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9212,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9183,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9654,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9037,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8957,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9187,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9173,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9176,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9076,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9154,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9254,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.911,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9221,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9694,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8931,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9246,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.929,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8632,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9252,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9211,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9232,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9103,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9192,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9155,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9054,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9034,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8694,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9198,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9087,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9056,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8997,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9202,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9023,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.926,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9171,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9191,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8932,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9198,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9409,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9019,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9012,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9028,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9149,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8975,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9371,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9161,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9248,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8693,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8859,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9156,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9013,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9251,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9192,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9269,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8964,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8964,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.923,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9349,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9092,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.8816,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.854,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9045,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8698,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9118,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9029,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9167,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9049,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9006,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.924,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8962,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9183,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9282,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8887,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.904,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.896,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8918,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9601,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9374,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.8716,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.8812,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9133,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.904,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8841,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9362,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.906,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9075,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9147,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9252,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.882,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8745,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9002,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8854,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.939,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8779,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9006,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.88,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9151,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8955,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9311,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8937,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9064,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8635,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8815,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9087,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.8895,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9035,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9523,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.8868,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8852,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8775,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9037,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9312,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9293,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9224,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8982,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9208,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8754,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9174,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9118,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8944,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9049,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9313,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9281,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.8946,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9066,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8574,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8952,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9202,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9374,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9379,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9115,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8986,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9024,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9324,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8833,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.906,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9236,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9316,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9123,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8945,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.9249,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8629,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.9006,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.869,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8932,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8787,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9035,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9326,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9004,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9341,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8938,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8818,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8946,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8595,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.9122,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8881,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9539,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8966,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9073,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8932,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8936,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8727,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8865,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9321,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9009,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9469,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8896,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9062,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.901,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9092,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8896,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9154,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8983,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.921,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9145,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.891,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9003,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8721,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8876,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9105,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9201,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9053,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9513,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8787,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8944,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8983,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.902,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.908,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9229,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9004,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.897,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8403,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9086,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9118,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9074,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.898,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8989,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9126,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8753,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8892,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.9049,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8593,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8795,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9441,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8931,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9158,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8571,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8889,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8609,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9117,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9346,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8709,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8722,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.868,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9078,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.899,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8947,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8708,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9073,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9225,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8896,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8892,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9034,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8875,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8762,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8911,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8901,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8986,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9185,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8783,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8892,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8446,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8787,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8917,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8735,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8955,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8737,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.904,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8747,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9131,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9048,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8889,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8739,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9074,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8801,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8874,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9092,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8899,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9164,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9172,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9051,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8893,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8634,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8953,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9077,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8903,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8981,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9341,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8926,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8535,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8572,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.909,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9196,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.927,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8842,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8985,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8935,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9105,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8808,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.87,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8799,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8775,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9295,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8774,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9037,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8746,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9093,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8621,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8968,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9039,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8815,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8955,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9011,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9149,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8991,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.912,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8921,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8995,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8962,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8905,
      "step": 350
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8855,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8722,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 353
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9013,
      "step": 354
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9098,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.897,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9427,
      "step": 357
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.8835,
      "step": 358
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.8816,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.8685,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.9398,
      "step": 361
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.887,
      "step": 362
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.8596,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.8859,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.9052,
      "step": 365
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.89,
      "step": 366
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8873,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.912,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.927,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8934,
      "step": 370
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8936,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8642,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8807,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8937,
      "step": 374
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.8791,
      "step": 375
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.8841,
      "step": 376
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.9214,
      "step": 377
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.8629,
      "step": 378
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.8845,
      "step": 379
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9012,
      "step": 380
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.904,
      "step": 381
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9032,
      "step": 382
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.9014,
      "step": 383
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.893,
      "step": 384
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.8892,
      "step": 385
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.906,
      "step": 386
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8724,
      "step": 387
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8595,
      "step": 388
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8719,
      "step": 389
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.9345,
      "step": 390
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 391
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.9131,
      "step": 392
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.8829,
      "step": 393
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.904,
      "step": 394
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.8657,
      "step": 395
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.9058,
      "step": 396
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.8936,
      "step": 397
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.903,
      "step": 398
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.8983,
      "step": 399
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.8746,
      "step": 400
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.883,
      "step": 401
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.8815,
      "step": 402
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.9086,
      "step": 403
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.884,
      "step": 404
    },
    {
      "epoch": 1.0,
      "step": 404,
      "total_flos": 4.585316415920947e+17,
      "train_loss": 0.9135053458780346,
      "train_runtime": 17326.8805,
      "train_samples_per_second": 2.987,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4.585316415920947e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}