{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7548209366391183,
  "global_step": 500,
  "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": 1.6739,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4695,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.3698,
      "step": 15
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.31,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.1747,
      "step": 25
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.1566,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.102,
      "step": 35
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.2996,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.284,
      "step": 45
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.1008,
      "step": 50
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.8815,
      "step": 55
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.8306,
      "step": 60
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.0265,
      "step": 65
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.9281,
      "step": 70
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.9321,
      "step": 75
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.8366,
      "step": 80
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.1115,
      "step": 85
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.0392,
      "step": 90
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.0288,
      "step": 95
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.7581,
      "step": 100
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.8078,
      "step": 105
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.8296,
      "step": 110
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.9053,
      "step": 115
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.9,
      "step": 120
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.8384,
      "step": 125
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.9651,
      "step": 130
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.0384,
      "step": 135
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.9916,
      "step": 140
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.7081,
      "step": 145
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.7966,
      "step": 150
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.8907,
      "step": 155
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.8284,
      "step": 160
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.7204,
      "step": 165
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.8712,
      "step": 170
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.9699,
      "step": 175
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.9726,
      "step": 180
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.9618,
      "step": 185
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 0.6762,
      "step": 190
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.7073,
      "step": 195
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.8257,
      "step": 200
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.8218,
      "step": 205
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 0.879,
      "step": 210
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.7279,
      "step": 215
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.8078,
      "step": 220
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.9659,
      "step": 225
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 0.9077,
      "step": 230
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.8432,
      "step": 235
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.6376,
      "step": 240
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.6578,
      "step": 245
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.7712,
      "step": 250
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.7946,
      "step": 255
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.714,
      "step": 260
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.9,
      "step": 265
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.8877,
      "step": 270
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.8492,
      "step": 275
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.7307,
      "step": 280
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.6746,
      "step": 285
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.7466,
      "step": 290
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.6683,
      "step": 295
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 0.8136,
      "step": 300
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.6348,
      "step": 305
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.8073,
      "step": 310
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.9171,
      "step": 315
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.9165,
      "step": 320
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.7211,
      "step": 325
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 0.5587,
      "step": 330
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 0.7583,
      "step": 335
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 0.7004,
      "step": 340
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 0.7815,
      "step": 345
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 0.6479,
      "step": 350
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.8537,
      "step": 355
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 0.862,
      "step": 360
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002,
      "loss": 0.8366,
      "step": 365
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002,
      "loss": 0.7606,
      "step": 370
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0002,
      "loss": 0.5288,
      "step": 375
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0002,
      "loss": 0.5945,
      "step": 380
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0002,
      "loss": 0.6433,
      "step": 385
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 0.6962,
      "step": 390
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 0.5828,
      "step": 395
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 0.68,
      "step": 400
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 0.7801,
      "step": 405
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002,
      "loss": 0.7877,
      "step": 410
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.8949,
      "step": 415
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 0.4878,
      "step": 420
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0002,
      "loss": 0.5364,
      "step": 425
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.667,
      "step": 430
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.7271,
      "step": 435
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.6242,
      "step": 440
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.5735,
      "step": 445
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.7495,
      "step": 450
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 0.7836,
      "step": 455
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 0.785,
      "step": 460
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.5057,
      "step": 465
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.5685,
      "step": 470
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 0.6507,
      "step": 475
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0002,
      "loss": 0.6217,
      "step": 480
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.6732,
      "step": 485
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0002,
      "loss": 0.7112,
      "step": 490
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0002,
      "loss": 0.6993,
      "step": 495
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0002,
      "loss": 0.7456,
      "step": 500
    }
  ],
  "max_steps": 543,
  "num_train_epochs": 3,
  "total_flos": 941285658353664.0,
  "trial_name": null,
  "trial_params": null
}