{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 135.59322033898306,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.71,
      "learning_rate": 0.0196,
      "loss": 4.115,
      "step": 10
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0192,
      "loss": 4.0422,
      "step": 20
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0188,
      "loss": 3.7797,
      "step": 30
    },
    {
      "epoch": 10.85,
      "learning_rate": 0.0184,
      "loss": 3.204,
      "step": 40
    },
    {
      "epoch": 13.56,
      "learning_rate": 0.018000000000000002,
      "loss": 2.7285,
      "step": 50
    },
    {
      "epoch": 16.27,
      "learning_rate": 0.0176,
      "loss": 2.1524,
      "step": 60
    },
    {
      "epoch": 18.98,
      "learning_rate": 0.0172,
      "loss": 1.6875,
      "step": 70
    },
    {
      "epoch": 21.69,
      "learning_rate": 0.0168,
      "loss": 1.2613,
      "step": 80
    },
    {
      "epoch": 24.41,
      "learning_rate": 0.016399999999999998,
      "loss": 0.9464,
      "step": 90
    },
    {
      "epoch": 27.12,
      "learning_rate": 0.016,
      "loss": 0.734,
      "step": 100
    },
    {
      "epoch": 29.83,
      "learning_rate": 0.015600000000000001,
      "loss": 0.5502,
      "step": 110
    },
    {
      "epoch": 32.54,
      "learning_rate": 0.0152,
      "loss": 0.4353,
      "step": 120
    },
    {
      "epoch": 35.25,
      "learning_rate": 0.0148,
      "loss": 0.3286,
      "step": 130
    },
    {
      "epoch": 37.97,
      "learning_rate": 0.0144,
      "loss": 0.2814,
      "step": 140
    },
    {
      "epoch": 40.68,
      "learning_rate": 0.013999999999999999,
      "loss": 0.2337,
      "step": 150
    },
    {
      "epoch": 43.39,
      "learning_rate": 0.013600000000000001,
      "loss": 0.1949,
      "step": 160
    },
    {
      "epoch": 46.1,
      "learning_rate": 0.013200000000000002,
      "loss": 0.1482,
      "step": 170
    },
    {
      "epoch": 48.81,
      "learning_rate": 0.0128,
      "loss": 0.136,
      "step": 180
    },
    {
      "epoch": 51.53,
      "learning_rate": 0.0124,
      "loss": 0.1175,
      "step": 190
    },
    {
      "epoch": 54.24,
      "learning_rate": 0.012,
      "loss": 0.0995,
      "step": 200
    },
    {
      "epoch": 56.95,
      "learning_rate": 0.0116,
      "loss": 0.0841,
      "step": 210
    },
    {
      "epoch": 59.66,
      "learning_rate": 0.011200000000000002,
      "loss": 0.07,
      "step": 220
    },
    {
      "epoch": 62.37,
      "learning_rate": 0.0108,
      "loss": 0.0672,
      "step": 230
    },
    {
      "epoch": 65.08,
      "learning_rate": 0.010400000000000001,
      "loss": 0.058,
      "step": 240
    },
    {
      "epoch": 67.8,
      "learning_rate": 0.01,
      "loss": 0.0546,
      "step": 250
    },
    {
      "epoch": 70.51,
      "learning_rate": 0.0096,
      "loss": 0.0503,
      "step": 260
    },
    {
      "epoch": 73.22,
      "learning_rate": 0.0092,
      "loss": 0.0471,
      "step": 270
    },
    {
      "epoch": 75.93,
      "learning_rate": 0.0088,
      "loss": 0.0422,
      "step": 280
    },
    {
      "epoch": 78.64,
      "learning_rate": 0.0084,
      "loss": 0.0352,
      "step": 290
    },
    {
      "epoch": 81.36,
      "learning_rate": 0.008,
      "loss": 0.0374,
      "step": 300
    },
    {
      "epoch": 84.07,
      "learning_rate": 0.0076,
      "loss": 0.033,
      "step": 310
    },
    {
      "epoch": 86.78,
      "learning_rate": 0.0072,
      "loss": 0.0332,
      "step": 320
    },
    {
      "epoch": 89.49,
      "learning_rate": 0.0068000000000000005,
      "loss": 0.0292,
      "step": 330
    },
    {
      "epoch": 92.2,
      "learning_rate": 0.0064,
      "loss": 0.0298,
      "step": 340
    },
    {
      "epoch": 94.92,
      "learning_rate": 0.006,
      "loss": 0.0258,
      "step": 350
    },
    {
      "epoch": 97.63,
      "learning_rate": 0.005600000000000001,
      "loss": 0.0263,
      "step": 360
    },
    {
      "epoch": 100.34,
      "learning_rate": 0.005200000000000001,
      "loss": 0.0252,
      "step": 370
    },
    {
      "epoch": 103.05,
      "learning_rate": 0.0048,
      "loss": 0.0249,
      "step": 380
    },
    {
      "epoch": 105.76,
      "learning_rate": 0.0044,
      "loss": 0.0225,
      "step": 390
    },
    {
      "epoch": 108.47,
      "learning_rate": 0.004,
      "loss": 0.0219,
      "step": 400
    },
    {
      "epoch": 111.19,
      "learning_rate": 0.0036,
      "loss": 0.0224,
      "step": 410
    },
    {
      "epoch": 113.9,
      "learning_rate": 0.0032,
      "loss": 0.0238,
      "step": 420
    },
    {
      "epoch": 116.61,
      "learning_rate": 0.0028000000000000004,
      "loss": 0.0196,
      "step": 430
    },
    {
      "epoch": 119.32,
      "learning_rate": 0.0024,
      "loss": 0.0207,
      "step": 440
    },
    {
      "epoch": 122.03,
      "learning_rate": 0.002,
      "loss": 0.0208,
      "step": 450
    },
    {
      "epoch": 124.75,
      "learning_rate": 0.0016,
      "loss": 0.0204,
      "step": 460
    },
    {
      "epoch": 127.46,
      "learning_rate": 0.0012,
      "loss": 0.0207,
      "step": 470
    },
    {
      "epoch": 130.17,
      "learning_rate": 0.0008,
      "loss": 0.0206,
      "step": 480
    },
    {
      "epoch": 132.88,
      "learning_rate": 0.0004,
      "loss": 0.0203,
      "step": 490
    },
    {
      "epoch": 135.59,
      "learning_rate": 0.0,
      "loss": 0.021,
      "step": 500
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 167,
  "total_flos": 6.9331442466816e+16,
  "trial_name": null,
  "trial_params": null
}