{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.116279069767442,
  "global_step": 490,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.496,
      "step": 10
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4045,
      "step": 20
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.3185,
      "step": 30
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.3501,
      "step": 40
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.2881,
      "step": 50
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.2783,
      "step": 60
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.2701,
      "step": 70
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.208,
      "step": 80
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.2175,
      "step": 90
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.2248,
      "step": 100
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0002,
      "loss": 0.1415,
      "step": 110
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 0.1788,
      "step": 120
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.1748,
      "step": 130
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 0.1839,
      "step": 140
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0002,
      "loss": 0.1778,
      "step": 150
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0002,
      "loss": 0.1986,
      "step": 160
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0002,
      "loss": 0.0977,
      "step": 170
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0002,
      "loss": 0.1209,
      "step": 180
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0002,
      "loss": 0.1328,
      "step": 190
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0002,
      "loss": 0.1503,
      "step": 200
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0002,
      "loss": 0.1649,
      "step": 210
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0002,
      "loss": 0.1284,
      "step": 220
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0002,
      "loss": 0.1156,
      "step": 230
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0002,
      "loss": 0.0689,
      "step": 240
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0002,
      "loss": 0.0885,
      "step": 250
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0002,
      "loss": 0.1168,
      "step": 260
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0002,
      "loss": 0.1102,
      "step": 270
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0002,
      "loss": 0.0619,
      "step": 280
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.0002,
      "loss": 0.0767,
      "step": 290
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.0002,
      "loss": 0.0922,
      "step": 300
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.0002,
      "loss": 0.0591,
      "step": 310
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.0002,
      "loss": 0.0893,
      "step": 320
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.0002,
      "loss": 0.0562,
      "step": 330
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.0002,
      "loss": 0.0541,
      "step": 340
    },
    {
      "epoch": 6.51,
      "learning_rate": 0.0002,
      "loss": 0.0629,
      "step": 350
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.0002,
      "loss": 0.0612,
      "step": 360
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.0002,
      "loss": 0.0526,
      "step": 370
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.0002,
      "loss": 0.044,
      "step": 380
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.0002,
      "loss": 0.0424,
      "step": 390
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.0002,
      "loss": 0.0459,
      "step": 400
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.0002,
      "loss": 0.0442,
      "step": 410
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.0002,
      "loss": 0.039,
      "step": 420
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0002,
      "loss": 0.0375,
      "step": 430
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0002,
      "loss": 0.0315,
      "step": 440
    },
    {
      "epoch": 8.37,
      "learning_rate": 0.0002,
      "loss": 0.0348,
      "step": 450
    },
    {
      "epoch": 8.56,
      "learning_rate": 0.0002,
      "loss": 0.0324,
      "step": 460
    },
    {
      "epoch": 8.74,
      "learning_rate": 0.0002,
      "loss": 0.0382,
      "step": 470
    },
    {
      "epoch": 8.93,
      "learning_rate": 0.0002,
      "loss": 0.0257,
      "step": 480
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.0002,
      "loss": 0.0361,
      "step": 490
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 10,
  "total_flos": 8.27522682566738e+16,
  "trial_name": null,
  "trial_params": null
}