{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9972041006523766,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2028,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.8921,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.837,
      "step": 6
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.8034,
      "step": 8
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.531,
      "step": 10
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.7161,
      "step": 12
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.9213,
      "step": 14
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.8214,
      "step": 16
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.8503,
      "step": 18
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.7335,
      "step": 20
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.81,
      "step": 22
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.7934,
      "step": 24
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.7097,
      "step": 26
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.6223,
      "step": 28
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.8643,
      "step": 30
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.7201,
      "step": 32
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.6561,
      "step": 34
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.0588,
      "step": 36
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.6402,
      "step": 38
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.6665,
      "step": 40
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.4429,
      "step": 42
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.5136,
      "step": 44
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.7228,
      "step": 46
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.7019,
      "step": 48
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 2.2361,
      "step": 50
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.7823,
      "step": 52
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.7056,
      "step": 54
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.7234,
      "step": 56
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.4893,
      "step": 58
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.6342,
      "step": 60
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.7274,
      "step": 62
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.4569,
      "step": 64
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.4923,
      "step": 66
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 2.0466,
      "step": 68
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 2.034,
      "step": 70
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.5523,
      "step": 72
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 1.6654,
      "step": 74
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 1.5583,
      "step": 76
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.4325,
      "step": 78
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.5099,
      "step": 80
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 1.5582,
      "step": 82
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.6519,
      "step": 84
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.9358,
      "step": 86
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.6292,
      "step": 88
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.5512,
      "step": 90
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.3745,
      "step": 92
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.3224,
      "step": 94
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.4843,
      "step": 96
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 1.6006,
      "step": 98
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.6436,
      "step": 100
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 1.8413,
      "step": 102
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.6665,
      "step": 104
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 1.6881,
      "step": 106
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 1.6871,
      "step": 108
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.357,
      "step": 110
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.349,
      "step": 112
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.5072,
      "step": 114
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.8975,
      "step": 116
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 2.2641,
      "step": 118
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 1.7053,
      "step": 120
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 1.6115,
      "step": 122
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.5428,
      "step": 124
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.2018,
      "step": 126
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 1.3601,
      "step": 128
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 1.5072,
      "step": 130
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.4283,
      "step": 132
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.4977,
      "step": 134
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002,
      "loss": 2.1986,
      "step": 136
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 2.0282,
      "step": 138
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0002,
      "loss": 1.6776,
      "step": 140
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 1.5972,
      "step": 142
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 1.3801,
      "step": 144
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 1.2358,
      "step": 146
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 1.3283,
      "step": 148
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 1.1866,
      "step": 150
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 1.8487,
      "step": 152
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 1.8731,
      "step": 154
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 1.5395,
      "step": 156
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002,
      "loss": 1.4486,
      "step": 158
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0002,
      "loss": 1.2876,
      "step": 160
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 1.2185,
      "step": 162
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 1.3274,
      "step": 164
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 1.1431,
      "step": 166
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 2.1022,
      "step": 168
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 1.3974,
      "step": 170
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 1.5858,
      "step": 172
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 1.555,
      "step": 174
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 1.3075,
      "step": 176
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 1.1968,
      "step": 178
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0002,
      "loss": 1.2942,
      "step": 180
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002,
      "loss": 1.0941,
      "step": 182
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0002,
      "loss": 2.4209,
      "step": 184
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0002,
      "loss": 1.5967,
      "step": 186
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0002,
      "loss": 1.623,
      "step": 188
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0002,
      "loss": 1.5194,
      "step": 190
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002,
      "loss": 1.4854,
      "step": 192
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 1.3782,
      "step": 194
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0002,
      "loss": 1.3657,
      "step": 196
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0002,
      "loss": 1.1328,
      "step": 198
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0002,
      "loss": 1.8249,
      "step": 200
    }
  ],
  "logging_steps": 2,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 8935930385571840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}