{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 16.3471,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.4615,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.194,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.9551,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.2261,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 1.9869,
      "step": 85
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 1.6293,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 2.0245,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 1.8265,
      "step": 140
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.5536,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0,
      "loss": 2.0011,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.1846,
      "step": 175
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 2.3248,
      "step": 180
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 3.966,
      "step": 185
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 49.8341,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 4.7387,
      "step": 220
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 27.6091,
      "step": 225
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 0.7769,
      "step": 245
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 1.2832,
      "step": 250
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 28.6253,
      "step": 255
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0,
      "loss": 1.311,
      "step": 265
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0,
      "loss": 1.0543,
      "step": 290
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0,
      "loss": 4.1379,
      "step": 305
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0,
      "loss": 0.2084,
      "step": 315
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.0999,
      "step": 325
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.2186,
      "step": 345
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0,
      "loss": 0.6567,
      "step": 355
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0,
      "loss": 0.1897,
      "step": 360
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0,
      "loss": 1.1873,
      "step": 380
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 0.5393,
      "step": 385
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 415
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 435
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0,
      "loss": 0.6623,
      "step": 455
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0,
      "loss": 7.193,
      "step": 460
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0,
      "loss": 62.3001,
      "step": 465
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 1.6018,
      "step": 470
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.1079,
      "step": 485
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0,
      "loss": 1.2356,
      "step": 495
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 1250,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 4.0647058784256e+16,
  "trial_name": null,
  "trial_params": null
}