{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.134471718249733,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0001996,
      "loss": 0.5949,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019920000000000002,
      "loss": 0.5845,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001988,
      "loss": 0.5783,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001984,
      "loss": 0.5964,
      "step": 40
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.573,
      "step": 50
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001976,
      "loss": 0.5882,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001972,
      "loss": 0.556,
      "step": 70
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001968,
      "loss": 0.5508,
      "step": 80
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001964,
      "loss": 0.5507,
      "step": 90
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000196,
      "loss": 0.58,
      "step": 100
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001956,
      "loss": 0.5605,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001952,
      "loss": 0.5685,
      "step": 120
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001948,
      "loss": 0.5521,
      "step": 130
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001944,
      "loss": 0.5447,
      "step": 140
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000194,
      "loss": 0.5508,
      "step": 150
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019360000000000002,
      "loss": 0.5437,
      "step": 160
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001932,
      "loss": 0.5505,
      "step": 170
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001928,
      "loss": 0.5456,
      "step": 180
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019240000000000001,
      "loss": 0.5337,
      "step": 190
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000192,
      "loss": 0.5662,
      "step": 200
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001916,
      "loss": 0.5527,
      "step": 210
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001912,
      "loss": 0.5695,
      "step": 220
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001908,
      "loss": 0.5561,
      "step": 230
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001904,
      "loss": 0.5435,
      "step": 240
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019,
      "loss": 0.5403,
      "step": 250
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001896,
      "loss": 0.5468,
      "step": 260
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001892,
      "loss": 0.556,
      "step": 270
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001888,
      "loss": 0.547,
      "step": 280
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001884,
      "loss": 0.5372,
      "step": 290
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.000188,
      "loss": 0.5541,
      "step": 300
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001876,
      "loss": 0.5367,
      "step": 310
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00018720000000000002,
      "loss": 0.542,
      "step": 320
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00018680000000000001,
      "loss": 0.541,
      "step": 330
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00018640000000000003,
      "loss": 0.5277,
      "step": 340
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.5368,
      "step": 350
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001856,
      "loss": 0.5297,
      "step": 360
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00018520000000000003,
      "loss": 0.5224,
      "step": 370
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00018480000000000002,
      "loss": 0.5484,
      "step": 380
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001844,
      "loss": 0.5406,
      "step": 390
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.524,
      "step": 400
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00018360000000000002,
      "loss": 0.5284,
      "step": 410
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001832,
      "loss": 0.5211,
      "step": 420
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018280000000000003,
      "loss": 0.5303,
      "step": 430
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018240000000000002,
      "loss": 0.5284,
      "step": 440
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.000182,
      "loss": 0.5245,
      "step": 450
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00018160000000000002,
      "loss": 0.5442,
      "step": 460
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001812,
      "loss": 0.5408,
      "step": 470
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001808,
      "loss": 0.5268,
      "step": 480
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00018040000000000002,
      "loss": 0.536,
      "step": 490
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00018,
      "loss": 0.522,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_train_epochs": 22,
  "save_steps": 500,
  "total_flos": 1.315055398331351e+18,
  "trial_name": null,
  "trial_params": null
}