{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7359781121751023,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2598,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.2292,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.1966,
      "step": 30
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.2014,
      "step": 40
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.1835,
      "step": 50
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.2463,
      "step": 60
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.2303,
      "step": 70
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.1892,
      "step": 80
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.1961,
      "step": 90
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.1219,
      "step": 100
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.1738,
      "step": 110
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.1226,
      "step": 120
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.1246,
      "step": 130
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.1479,
      "step": 140
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.2111,
      "step": 150
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.1836,
      "step": 160
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.1366,
      "step": 170
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.1682,
      "step": 180
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 1.1431,
      "step": 190
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 1.1472,
      "step": 200
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 1.0244,
      "step": 210
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.1281,
      "step": 220
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.0264,
      "step": 230
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 1.1049,
      "step": 240
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 1.1054,
      "step": 250
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.0381,
      "step": 260
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 1.0953,
      "step": 270
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 1.1273,
      "step": 280
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 1.0747,
      "step": 290
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 1.1288,
      "step": 300
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 1.0656,
      "step": 310
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.1188,
      "step": 320
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.0525,
      "step": 330
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 1.057,
      "step": 340
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 1.1001,
      "step": 350
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 1.1505,
      "step": 360
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 1.0715,
      "step": 370
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.9598,
      "step": 380
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 0.986,
      "step": 390
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 0.991,
      "step": 400
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 0.9805,
      "step": 410
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 0.9839,
      "step": 420
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.9978,
      "step": 430
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0002,
      "loss": 0.9476,
      "step": 440
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.9543,
      "step": 450
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0002,
      "loss": 0.9569,
      "step": 460
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002,
      "loss": 1.002,
      "step": 470
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0002,
      "loss": 1.012,
      "step": 480
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0002,
      "loss": 1.0095,
      "step": 490
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0002,
      "loss": 0.9938,
      "step": 500
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 3,
  "total_flos": 8.459308833806746e+16,
  "trial_name": null,
  "trial_params": null
}