{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.28,
  "eval_steps": 500,
  "global_step": 400,
  "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": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 245
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 305
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 325
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 345
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 355
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 385
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 936,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 1.0372744472297472e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}