{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5051142821063266,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3345,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.2163,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2388,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.1277,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0973,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.9222,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0471,
      "step": 70
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0486,
      "step": 80
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1051,
      "step": 90
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9196,
      "step": 100
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.8498,
      "step": 110
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.0382,
      "step": 120
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.0499,
      "step": 130
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.0022,
      "step": 140
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9139,
      "step": 150
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9687,
      "step": 160
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9068,
      "step": 170
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9836,
      "step": 180
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.8829,
      "step": 190
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.8207,
      "step": 200
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.8816,
      "step": 210
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.7799,
      "step": 220
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.807,
      "step": 230
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.0162,
      "step": 240
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.8598,
      "step": 250
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.8082,
      "step": 260
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.8333,
      "step": 270
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.854,
      "step": 280
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.053,
      "step": 290
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9061,
      "step": 300
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.8762,
      "step": 310
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.9073,
      "step": 320
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.9419,
      "step": 330
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.9186,
      "step": 340
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.9589,
      "step": 350
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.9204,
      "step": 360
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.9035,
      "step": 370
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.8377,
      "step": 380
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.8428,
      "step": 390
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9021,
      "step": 400
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.8038,
      "step": 410
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.9453,
      "step": 420
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.8901,
      "step": 430
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.9512,
      "step": 440
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.0095,
      "step": 450
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.9301,
      "step": 460
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.0128,
      "step": 470
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.9258,
      "step": 480
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.8467,
      "step": 490
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.9122,
      "step": 500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.9291,
      "step": 510
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.7981,
      "step": 520
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.8686,
      "step": 530
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.8434,
      "step": 540
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.853,
      "step": 550
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.9072,
      "step": 560
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.85,
      "step": 570
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.839,
      "step": 580
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.7939,
      "step": 590
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.841,
      "step": 600
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.8217,
      "step": 610
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.0448,
      "step": 620
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.9818,
      "step": 630
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.9739,
      "step": 640
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.8328,
      "step": 650
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.9255,
      "step": 660
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.8866,
      "step": 670
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.8239,
      "step": 680
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.8367,
      "step": 690
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.8279,
      "step": 700
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9398,
      "step": 710
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.8385,
      "step": 720
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.7533,
      "step": 730
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.8876,
      "step": 740
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.6983,
      "step": 750
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.9458,
      "step": 760
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.7637,
      "step": 770
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.6953,
      "step": 780
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.8983,
      "step": 790
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.8633,
      "step": 800
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.8276,
      "step": 810
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.8583,
      "step": 820
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.785,
      "step": 830
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.7379,
      "step": 840
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.6939,
      "step": 850
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.8756,
      "step": 860
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.8872,
      "step": 870
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.7073,
      "step": 880
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7099,
      "step": 890
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.9085,
      "step": 900
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.7907,
      "step": 910
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.8173,
      "step": 920
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.7822,
      "step": 930
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.9099,
      "step": 940
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.8,
      "step": 950
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.7713,
      "step": 960
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.8722,
      "step": 970
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.9413,
      "step": 980
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.8112,
      "step": 990
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.8461,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 8.1655308484608e+16,
  "trial_name": null,
  "trial_params": null
}