{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 35.08771929824562,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.0495,
      "step": 10
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.9419,
      "step": 20
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 1.6328,
      "step": 30
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 1.2627,
      "step": 40
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.1166,
      "step": 50
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.9466,
      "step": 60
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.4556,
      "step": 70
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0002,
      "loss": 0.4507,
      "step": 80
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0002,
      "loss": 0.3553,
      "step": 90
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0002,
      "loss": 0.1801,
      "step": 100
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0002,
      "loss": 0.2521,
      "step": 110
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0002,
      "loss": 0.1021,
      "step": 120
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0002,
      "loss": 0.0998,
      "step": 130
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0002,
      "loss": 0.0726,
      "step": 140
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0002,
      "loss": 0.0708,
      "step": 150
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.0002,
      "loss": 0.0327,
      "step": 160
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.0002,
      "loss": 0.0662,
      "step": 170
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.0002,
      "loss": 0.0258,
      "step": 180
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 0.0301,
      "step": 190
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.0002,
      "loss": 0.0412,
      "step": 200
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.0002,
      "loss": 0.0396,
      "step": 210
    },
    {
      "epoch": 7.72,
      "learning_rate": 0.0002,
      "loss": 0.0155,
      "step": 220
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.0002,
      "loss": 0.0295,
      "step": 230
    },
    {
      "epoch": 8.42,
      "learning_rate": 0.0002,
      "loss": 0.01,
      "step": 240
    },
    {
      "epoch": 8.77,
      "learning_rate": 0.0002,
      "loss": 0.0247,
      "step": 250
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.0002,
      "loss": 0.0183,
      "step": 260
    },
    {
      "epoch": 9.47,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 270
    },
    {
      "epoch": 9.82,
      "learning_rate": 0.0002,
      "loss": 0.0053,
      "step": 280
    },
    {
      "epoch": 10.18,
      "learning_rate": 0.0002,
      "loss": 0.0161,
      "step": 290
    },
    {
      "epoch": 10.53,
      "learning_rate": 0.0002,
      "loss": 0.0122,
      "step": 300
    },
    {
      "epoch": 10.88,
      "learning_rate": 0.0002,
      "loss": 0.0126,
      "step": 310
    },
    {
      "epoch": 11.23,
      "learning_rate": 0.0002,
      "loss": 0.0135,
      "step": 320
    },
    {
      "epoch": 11.58,
      "learning_rate": 0.0002,
      "loss": 0.0196,
      "step": 330
    },
    {
      "epoch": 11.93,
      "learning_rate": 0.0002,
      "loss": 0.014,
      "step": 340
    },
    {
      "epoch": 12.28,
      "learning_rate": 0.0002,
      "loss": 0.0056,
      "step": 350
    },
    {
      "epoch": 12.63,
      "learning_rate": 0.0002,
      "loss": 0.0078,
      "step": 360
    },
    {
      "epoch": 12.98,
      "learning_rate": 0.0002,
      "loss": 0.0151,
      "step": 370
    },
    {
      "epoch": 13.33,
      "learning_rate": 0.0002,
      "loss": 0.0155,
      "step": 380
    },
    {
      "epoch": 13.68,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 390
    },
    {
      "epoch": 14.04,
      "learning_rate": 0.0002,
      "loss": 0.0396,
      "step": 400
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.0002,
      "loss": 0.0262,
      "step": 410
    },
    {
      "epoch": 14.74,
      "learning_rate": 0.0002,
      "loss": 0.0209,
      "step": 420
    },
    {
      "epoch": 15.09,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 430
    },
    {
      "epoch": 15.44,
      "learning_rate": 0.0002,
      "loss": 0.0126,
      "step": 440
    },
    {
      "epoch": 15.79,
      "learning_rate": 0.0002,
      "loss": 0.0118,
      "step": 450
    },
    {
      "epoch": 16.14,
      "learning_rate": 0.0002,
      "loss": 0.0049,
      "step": 460
    },
    {
      "epoch": 16.49,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 470
    },
    {
      "epoch": 16.84,
      "learning_rate": 0.0002,
      "loss": 0.0097,
      "step": 480
    },
    {
      "epoch": 17.19,
      "learning_rate": 0.0002,
      "loss": 0.0115,
      "step": 490
    },
    {
      "epoch": 17.54,
      "learning_rate": 0.0002,
      "loss": 0.0033,
      "step": 500
    },
    {
      "epoch": 17.89,
      "learning_rate": 0.0002,
      "loss": 0.0122,
      "step": 510
    },
    {
      "epoch": 18.25,
      "learning_rate": 0.0002,
      "loss": 0.0083,
      "step": 520
    },
    {
      "epoch": 18.6,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 530
    },
    {
      "epoch": 18.95,
      "learning_rate": 0.0002,
      "loss": 0.0136,
      "step": 540
    },
    {
      "epoch": 19.3,
      "learning_rate": 0.0002,
      "loss": 0.0127,
      "step": 550
    },
    {
      "epoch": 19.65,
      "learning_rate": 0.0002,
      "loss": 0.004,
      "step": 560
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0002,
      "loss": 0.0082,
      "step": 570
    },
    {
      "epoch": 20.35,
      "learning_rate": 0.0002,
      "loss": 0.0147,
      "step": 580
    },
    {
      "epoch": 20.7,
      "learning_rate": 0.0002,
      "loss": 0.0206,
      "step": 590
    },
    {
      "epoch": 21.05,
      "learning_rate": 0.0002,
      "loss": 0.0238,
      "step": 600
    },
    {
      "epoch": 21.4,
      "learning_rate": 0.0002,
      "loss": 0.0286,
      "step": 610
    },
    {
      "epoch": 21.75,
      "learning_rate": 0.0002,
      "loss": 0.0484,
      "step": 620
    },
    {
      "epoch": 22.11,
      "learning_rate": 0.0002,
      "loss": 0.0251,
      "step": 630
    },
    {
      "epoch": 22.46,
      "learning_rate": 0.0002,
      "loss": 0.0324,
      "step": 640
    },
    {
      "epoch": 22.81,
      "learning_rate": 0.0002,
      "loss": 0.024,
      "step": 650
    },
    {
      "epoch": 23.16,
      "learning_rate": 0.0002,
      "loss": 0.0166,
      "step": 660
    },
    {
      "epoch": 23.51,
      "learning_rate": 0.0002,
      "loss": 0.0298,
      "step": 670
    },
    {
      "epoch": 23.86,
      "learning_rate": 0.0002,
      "loss": 0.0383,
      "step": 680
    },
    {
      "epoch": 24.21,
      "learning_rate": 0.0002,
      "loss": 0.0309,
      "step": 690
    },
    {
      "epoch": 24.56,
      "learning_rate": 0.0002,
      "loss": 0.0164,
      "step": 700
    },
    {
      "epoch": 24.91,
      "learning_rate": 0.0002,
      "loss": 0.0281,
      "step": 710
    },
    {
      "epoch": 25.26,
      "learning_rate": 0.0002,
      "loss": 0.0146,
      "step": 720
    },
    {
      "epoch": 25.61,
      "learning_rate": 0.0002,
      "loss": 0.0433,
      "step": 730
    },
    {
      "epoch": 25.96,
      "learning_rate": 0.0002,
      "loss": 0.0543,
      "step": 740
    },
    {
      "epoch": 26.32,
      "learning_rate": 0.0002,
      "loss": 0.0786,
      "step": 750
    },
    {
      "epoch": 26.67,
      "learning_rate": 0.0002,
      "loss": 0.0248,
      "step": 760
    },
    {
      "epoch": 27.02,
      "learning_rate": 0.0002,
      "loss": 0.0249,
      "step": 770
    },
    {
      "epoch": 27.37,
      "learning_rate": 0.0002,
      "loss": 0.0253,
      "step": 780
    },
    {
      "epoch": 27.72,
      "learning_rate": 0.0002,
      "loss": 0.0111,
      "step": 790
    },
    {
      "epoch": 28.07,
      "learning_rate": 0.0002,
      "loss": 0.0356,
      "step": 800
    },
    {
      "epoch": 28.42,
      "learning_rate": 0.0002,
      "loss": 0.0597,
      "step": 810
    },
    {
      "epoch": 28.77,
      "learning_rate": 0.0002,
      "loss": 0.0473,
      "step": 820
    },
    {
      "epoch": 29.12,
      "learning_rate": 0.0002,
      "loss": 0.0233,
      "step": 830
    },
    {
      "epoch": 29.47,
      "learning_rate": 0.0002,
      "loss": 0.0085,
      "step": 840
    },
    {
      "epoch": 29.82,
      "learning_rate": 0.0002,
      "loss": 0.0114,
      "step": 850
    },
    {
      "epoch": 30.18,
      "learning_rate": 0.0002,
      "loss": 0.035,
      "step": 860
    },
    {
      "epoch": 30.53,
      "learning_rate": 0.0002,
      "loss": 0.017,
      "step": 870
    },
    {
      "epoch": 30.88,
      "learning_rate": 0.0002,
      "loss": 0.0398,
      "step": 880
    },
    {
      "epoch": 31.23,
      "learning_rate": 0.0002,
      "loss": 0.0101,
      "step": 890
    },
    {
      "epoch": 31.58,
      "learning_rate": 0.0002,
      "loss": 0.0163,
      "step": 900
    },
    {
      "epoch": 31.93,
      "learning_rate": 0.0002,
      "loss": 0.0425,
      "step": 910
    },
    {
      "epoch": 32.28,
      "learning_rate": 0.0002,
      "loss": 0.0319,
      "step": 920
    },
    {
      "epoch": 32.63,
      "learning_rate": 0.0002,
      "loss": 0.0163,
      "step": 930
    },
    {
      "epoch": 32.98,
      "learning_rate": 0.0002,
      "loss": 0.0236,
      "step": 940
    },
    {
      "epoch": 33.33,
      "learning_rate": 0.0002,
      "loss": 0.0255,
      "step": 950
    },
    {
      "epoch": 33.68,
      "learning_rate": 0.0002,
      "loss": 0.0261,
      "step": 960
    },
    {
      "epoch": 34.04,
      "learning_rate": 0.0002,
      "loss": 0.0197,
      "step": 970
    },
    {
      "epoch": 34.39,
      "learning_rate": 0.0002,
      "loss": 0.0323,
      "step": 980
    },
    {
      "epoch": 34.74,
      "learning_rate": 0.0002,
      "loss": 0.0456,
      "step": 990
    },
    {
      "epoch": 35.09,
      "learning_rate": 0.0002,
      "loss": 0.0149,
      "step": 1000
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 36,
  "total_flos": 8864472152586240.0,
  "trial_name": null,
  "trial_params": null
}