{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.48953616448415127,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.1809,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.515,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.3848,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2882,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2283,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1074,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.1195,
      "step": 70
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1942,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0617,
      "step": 90
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.2377,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1167,
      "step": 110
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.0454,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.0348,
      "step": 130
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.1334,
      "step": 140
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.1347,
      "step": 150
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9811,
      "step": 160
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.1339,
      "step": 170
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.1432,
      "step": 180
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9374,
      "step": 190
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.078,
      "step": 200
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.0077,
      "step": 210
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.1386,
      "step": 220
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.0728,
      "step": 230
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.058,
      "step": 240
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.1418,
      "step": 250
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.8572,
      "step": 260
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.0748,
      "step": 270
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.0684,
      "step": 280
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.9738,
      "step": 290
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.0983,
      "step": 300
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9303,
      "step": 310
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.0693,
      "step": 320
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.9826,
      "step": 330
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.0645,
      "step": 340
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.016,
      "step": 350
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.017,
      "step": 360
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.9784,
      "step": 370
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.0232,
      "step": 380
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.052,
      "step": 390
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.2058,
      "step": 400
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9714,
      "step": 410
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.9989,
      "step": 420
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.1847,
      "step": 430
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0508,
      "step": 440
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.1055,
      "step": 450
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.9516,
      "step": 460
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.0335,
      "step": 470
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.9142,
      "step": 480
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.9935,
      "step": 490
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.9775,
      "step": 500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.997,
      "step": 510
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.9757,
      "step": 520
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.039,
      "step": 530
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.9778,
      "step": 540
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.9335,
      "step": 550
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.1015,
      "step": 560
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.0541,
      "step": 570
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.992,
      "step": 580
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.8638,
      "step": 590
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.9015,
      "step": 600
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.9853,
      "step": 610
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.8795,
      "step": 620
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.998,
      "step": 630
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.9117,
      "step": 640
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.9385,
      "step": 650
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.9176,
      "step": 660
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.944,
      "step": 670
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.9806,
      "step": 680
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.9584,
      "step": 690
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.8142,
      "step": 700
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.1244,
      "step": 710
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.0237,
      "step": 720
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9156,
      "step": 730
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9587,
      "step": 740
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 2.0621,
      "step": 750
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.8895,
      "step": 760
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.9138,
      "step": 770
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.9483,
      "step": 780
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.9976,
      "step": 790
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.961,
      "step": 800
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.9718,
      "step": 810
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.9632,
      "step": 820
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.9603,
      "step": 830
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.9101,
      "step": 840
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.0021,
      "step": 850
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.9553,
      "step": 860
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.0327,
      "step": 870
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.8616,
      "step": 880
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.9514,
      "step": 890
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.0745,
      "step": 900
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 2.094,
      "step": 910
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7963,
      "step": 920
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.9299,
      "step": 930
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.9508,
      "step": 940
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.9966,
      "step": 950
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.9024,
      "step": 960
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.9214,
      "step": 970
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.9296,
      "step": 980
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.0227,
      "step": 990
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.9409,
      "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
}