{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7058823529411766,
  "eval_steps": 500,
  "global_step": 216,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8355,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8713,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8682,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.9393,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7962,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.812,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7402,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8024,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7745,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7962,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7168,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.7441,
      "step": 24
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7646,
      "step": 26
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.76,
      "step": 28
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.8013,
      "step": 30
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.7374,
      "step": 32
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.8013,
      "step": 34
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.7418,
      "step": 36
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.7707,
      "step": 38
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.8057,
      "step": 40
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7133,
      "step": 42
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7545,
      "step": 44
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6649,
      "step": 46
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6521,
      "step": 48
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.7292,
      "step": 50
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.6916,
      "step": 52
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.729,
      "step": 54
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.7188,
      "step": 56
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.8067,
      "step": 58
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.7742,
      "step": 60
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6993,
      "step": 62
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6729,
      "step": 64
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.7793,
      "step": 66
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.6627,
      "step": 68
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.7312,
      "step": 70
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6635,
      "step": 72
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.6613,
      "step": 74
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.746,
      "step": 76
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.6225,
      "step": 78
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 0.6959,
      "step": 80
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 82
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.7556,
      "step": 84
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.6855,
      "step": 86
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.6031,
      "step": 88
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.7095,
      "step": 90
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.7242,
      "step": 92
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.6949,
      "step": 94
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.6036,
      "step": 96
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.5898,
      "step": 98
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.6601,
      "step": 100
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.7339,
      "step": 102
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.6019,
      "step": 104
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.564,
      "step": 106
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.6074,
      "step": 108
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 0.5943,
      "step": 110
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.6432,
      "step": 112
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.7072,
      "step": 114
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.6307,
      "step": 116
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 0.6776,
      "step": 118
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.6353,
      "step": 120
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.5932,
      "step": 122
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 0.5897,
      "step": 124
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 0.688,
      "step": 126
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.6442,
      "step": 128
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.5699,
      "step": 130
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 0.7366,
      "step": 132
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.6914,
      "step": 134
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.7067,
      "step": 136
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 0.6865,
      "step": 138
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.6918,
      "step": 140
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 0.665,
      "step": 142
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.5812,
      "step": 144
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 0.6092,
      "step": 146
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002,
      "loss": 0.6446,
      "step": 148
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.6022,
      "step": 150
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.6215,
      "step": 152
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 0.705,
      "step": 154
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 0.5592,
      "step": 156
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.6238,
      "step": 158
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0002,
      "loss": 0.4967,
      "step": 160
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 0.6922,
      "step": 162
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 0.6024,
      "step": 164
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.6448,
      "step": 166
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 0.5405,
      "step": 168
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 0.6757,
      "step": 170
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.6052,
      "step": 172
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.6523,
      "step": 174
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.5521,
      "step": 176
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.6658,
      "step": 178
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.5512,
      "step": 180
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.6127,
      "step": 182
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0002,
      "loss": 0.6525,
      "step": 184
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0002,
      "loss": 0.6247,
      "step": 186
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.557,
      "step": 188
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.6364,
      "step": 190
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0002,
      "loss": 0.5925,
      "step": 192
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0002,
      "loss": 0.6482,
      "step": 194
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 0.5387,
      "step": 196
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 0.6056,
      "step": 198
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 0.5665,
      "step": 200
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002,
      "loss": 0.6772,
      "step": 202
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.6314,
      "step": 204
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002,
      "loss": 0.5302,
      "step": 206
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0002,
      "loss": 0.6412,
      "step": 208
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 0.5737,
      "step": 210
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.5281,
      "step": 212
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0002,
      "loss": 0.7309,
      "step": 214
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002,
      "loss": 0.5749,
      "step": 216
    }
  ],
  "logging_steps": 2,
  "max_steps": 306,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.51914469359616e+16,
  "trial_name": null,
  "trial_params": null
}