{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 24.607329842931936,
  "eval_steps": 500,
  "global_step": 1175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.7979,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.7693,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.7635,
      "step": 15
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.7587,
      "step": 20
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.7384,
      "step": 25
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.7832,
      "step": 30
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.7652,
      "step": 35
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 1.7417,
      "step": 40
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 1.7321,
      "step": 45
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 1.6915,
      "step": 50
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001,
      "loss": 1.6773,
      "step": 55
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 1.6713,
      "step": 60
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001,
      "loss": 1.6701,
      "step": 65
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 1.6941,
      "step": 70
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 1.6116,
      "step": 75
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001,
      "loss": 1.7088,
      "step": 80
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 1.661,
      "step": 85
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 1.7321,
      "step": 90
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 1.6995,
      "step": 95
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 1.6298,
      "step": 100
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 1.6231,
      "step": 105
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001,
      "loss": 1.6427,
      "step": 110
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001,
      "loss": 1.5985,
      "step": 115
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 1.6267,
      "step": 120
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001,
      "loss": 1.5373,
      "step": 125
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001,
      "loss": 1.6516,
      "step": 130
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001,
      "loss": 1.6861,
      "step": 135
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 1.6746,
      "step": 140
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001,
      "loss": 1.6478,
      "step": 145
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0001,
      "loss": 1.6206,
      "step": 150
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 1.5848,
      "step": 155
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001,
      "loss": 1.5988,
      "step": 160
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001,
      "loss": 1.6014,
      "step": 165
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001,
      "loss": 1.5327,
      "step": 170
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0001,
      "loss": 1.5811,
      "step": 175
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001,
      "loss": 1.6202,
      "step": 180
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0001,
      "loss": 1.5986,
      "step": 185
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0001,
      "loss": 1.6548,
      "step": 190
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0001,
      "loss": 1.5288,
      "step": 195
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001,
      "loss": 1.5604,
      "step": 200
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001,
      "loss": 1.5302,
      "step": 205
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0001,
      "loss": 1.5751,
      "step": 210
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001,
      "loss": 1.5865,
      "step": 215
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0001,
      "loss": 1.5476,
      "step": 220
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0001,
      "loss": 1.5636,
      "step": 225
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.0001,
      "loss": 1.5472,
      "step": 230
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0001,
      "loss": 1.598,
      "step": 235
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.0001,
      "loss": 1.6288,
      "step": 240
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0001,
      "loss": 1.4983,
      "step": 245
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001,
      "loss": 1.5407,
      "step": 250
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001,
      "loss": 1.486,
      "step": 255
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.0001,
      "loss": 1.575,
      "step": 260
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.0001,
      "loss": 1.4745,
      "step": 265
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.0001,
      "loss": 1.5294,
      "step": 270
    },
    {
      "epoch": 5.76,
      "learning_rate": 0.0001,
      "loss": 1.5501,
      "step": 275
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.0001,
      "loss": 1.5791,
      "step": 280
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.0001,
      "loss": 1.5737,
      "step": 285
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.0001,
      "loss": 1.5181,
      "step": 290
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.0001,
      "loss": 1.4805,
      "step": 295
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.0001,
      "loss": 1.5105,
      "step": 300
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.0001,
      "loss": 1.5258,
      "step": 305
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.0001,
      "loss": 1.5081,
      "step": 310
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.0001,
      "loss": 1.4754,
      "step": 315
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.0001,
      "loss": 1.5619,
      "step": 320
    },
    {
      "epoch": 6.81,
      "learning_rate": 0.0001,
      "loss": 1.5239,
      "step": 325
    },
    {
      "epoch": 6.91,
      "learning_rate": 0.0001,
      "loss": 1.4911,
      "step": 330
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.0001,
      "loss": 1.5315,
      "step": 335
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.0001,
      "loss": 1.477,
      "step": 340
    },
    {
      "epoch": 7.23,
      "learning_rate": 0.0001,
      "loss": 1.4767,
      "step": 345
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0001,
      "loss": 1.4628,
      "step": 350
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0001,
      "loss": 1.4545,
      "step": 355
    },
    {
      "epoch": 7.54,
      "learning_rate": 0.0001,
      "loss": 1.4682,
      "step": 360
    },
    {
      "epoch": 7.64,
      "learning_rate": 0.0001,
      "loss": 1.4623,
      "step": 365
    },
    {
      "epoch": 7.75,
      "learning_rate": 0.0001,
      "loss": 1.5164,
      "step": 370
    },
    {
      "epoch": 7.85,
      "learning_rate": 0.0001,
      "loss": 1.5296,
      "step": 375
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.0001,
      "loss": 1.4896,
      "step": 380
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.0001,
      "loss": 1.4365,
      "step": 385
    },
    {
      "epoch": 8.17,
      "learning_rate": 0.0001,
      "loss": 1.4186,
      "step": 390
    },
    {
      "epoch": 8.27,
      "learning_rate": 0.0001,
      "loss": 1.4972,
      "step": 395
    },
    {
      "epoch": 8.38,
      "learning_rate": 0.0001,
      "loss": 1.4749,
      "step": 400
    },
    {
      "epoch": 8.48,
      "learning_rate": 0.0001,
      "loss": 1.4914,
      "step": 405
    },
    {
      "epoch": 8.59,
      "learning_rate": 0.0001,
      "loss": 1.4091,
      "step": 410
    },
    {
      "epoch": 8.69,
      "learning_rate": 0.0001,
      "loss": 1.4599,
      "step": 415
    },
    {
      "epoch": 8.8,
      "learning_rate": 0.0001,
      "loss": 1.4714,
      "step": 420
    },
    {
      "epoch": 8.9,
      "learning_rate": 0.0001,
      "loss": 1.4636,
      "step": 425
    },
    {
      "epoch": 9.01,
      "learning_rate": 0.0001,
      "loss": 1.4848,
      "step": 430
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0001,
      "loss": 1.4412,
      "step": 435
    },
    {
      "epoch": 9.21,
      "learning_rate": 0.0001,
      "loss": 1.4057,
      "step": 440
    },
    {
      "epoch": 9.32,
      "learning_rate": 0.0001,
      "loss": 1.4464,
      "step": 445
    },
    {
      "epoch": 9.42,
      "learning_rate": 0.0001,
      "loss": 1.4228,
      "step": 450
    },
    {
      "epoch": 9.53,
      "learning_rate": 0.0001,
      "loss": 1.4315,
      "step": 455
    },
    {
      "epoch": 9.63,
      "learning_rate": 0.0001,
      "loss": 1.442,
      "step": 460
    },
    {
      "epoch": 9.74,
      "learning_rate": 0.0001,
      "loss": 1.4008,
      "step": 465
    },
    {
      "epoch": 9.84,
      "learning_rate": 0.0001,
      "loss": 1.4473,
      "step": 470
    },
    {
      "epoch": 9.95,
      "learning_rate": 0.0001,
      "loss": 1.4487,
      "step": 475
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.0001,
      "loss": 1.476,
      "step": 480
    },
    {
      "epoch": 10.16,
      "learning_rate": 0.0001,
      "loss": 1.3862,
      "step": 485
    },
    {
      "epoch": 10.26,
      "learning_rate": 0.0001,
      "loss": 1.4721,
      "step": 490
    },
    {
      "epoch": 10.37,
      "learning_rate": 0.0001,
      "loss": 1.3839,
      "step": 495
    },
    {
      "epoch": 10.47,
      "learning_rate": 0.0001,
      "loss": 1.3948,
      "step": 500
    },
    {
      "epoch": 10.58,
      "learning_rate": 0.0001,
      "loss": 1.4057,
      "step": 505
    },
    {
      "epoch": 10.68,
      "learning_rate": 0.0001,
      "loss": 1.4158,
      "step": 510
    },
    {
      "epoch": 10.79,
      "learning_rate": 0.0001,
      "loss": 1.4162,
      "step": 515
    },
    {
      "epoch": 10.89,
      "learning_rate": 0.0001,
      "loss": 1.468,
      "step": 520
    },
    {
      "epoch": 10.99,
      "learning_rate": 0.0001,
      "loss": 1.3958,
      "step": 525
    },
    {
      "epoch": 11.1,
      "learning_rate": 0.0001,
      "loss": 1.4011,
      "step": 530
    },
    {
      "epoch": 11.2,
      "learning_rate": 0.0001,
      "loss": 1.3536,
      "step": 535
    },
    {
      "epoch": 11.31,
      "learning_rate": 0.0001,
      "loss": 1.4058,
      "step": 540
    },
    {
      "epoch": 11.41,
      "learning_rate": 0.0001,
      "loss": 1.4246,
      "step": 545
    },
    {
      "epoch": 11.52,
      "learning_rate": 0.0001,
      "loss": 1.3732,
      "step": 550
    },
    {
      "epoch": 11.62,
      "learning_rate": 0.0001,
      "loss": 1.4389,
      "step": 555
    },
    {
      "epoch": 11.73,
      "learning_rate": 0.0001,
      "loss": 1.3583,
      "step": 560
    },
    {
      "epoch": 11.83,
      "learning_rate": 0.0001,
      "loss": 1.383,
      "step": 565
    },
    {
      "epoch": 11.94,
      "learning_rate": 0.0001,
      "loss": 1.3902,
      "step": 570
    },
    {
      "epoch": 12.04,
      "learning_rate": 0.0001,
      "loss": 1.3814,
      "step": 575
    },
    {
      "epoch": 12.15,
      "learning_rate": 0.0001,
      "loss": 1.3598,
      "step": 580
    },
    {
      "epoch": 12.25,
      "learning_rate": 0.0001,
      "loss": 1.3826,
      "step": 585
    },
    {
      "epoch": 12.36,
      "learning_rate": 0.0001,
      "loss": 1.3724,
      "step": 590
    },
    {
      "epoch": 12.46,
      "learning_rate": 0.0001,
      "loss": 1.3413,
      "step": 595
    },
    {
      "epoch": 12.57,
      "learning_rate": 0.0001,
      "loss": 1.3661,
      "step": 600
    },
    {
      "epoch": 12.67,
      "learning_rate": 0.0001,
      "loss": 1.3633,
      "step": 605
    },
    {
      "epoch": 12.77,
      "learning_rate": 0.0001,
      "loss": 1.3524,
      "step": 610
    },
    {
      "epoch": 12.88,
      "learning_rate": 0.0001,
      "loss": 1.4059,
      "step": 615
    },
    {
      "epoch": 12.98,
      "learning_rate": 0.0001,
      "loss": 1.3891,
      "step": 620
    },
    {
      "epoch": 13.09,
      "learning_rate": 0.0001,
      "loss": 1.4142,
      "step": 625
    },
    {
      "epoch": 13.19,
      "learning_rate": 0.0001,
      "loss": 1.2695,
      "step": 630
    },
    {
      "epoch": 13.3,
      "learning_rate": 0.0001,
      "loss": 1.3521,
      "step": 635
    },
    {
      "epoch": 13.4,
      "learning_rate": 0.0001,
      "loss": 1.264,
      "step": 640
    },
    {
      "epoch": 13.51,
      "learning_rate": 0.0001,
      "loss": 1.3551,
      "step": 645
    },
    {
      "epoch": 13.61,
      "learning_rate": 0.0001,
      "loss": 1.4012,
      "step": 650
    },
    {
      "epoch": 13.72,
      "learning_rate": 0.0001,
      "loss": 1.3733,
      "step": 655
    },
    {
      "epoch": 13.82,
      "learning_rate": 0.0001,
      "loss": 1.3957,
      "step": 660
    },
    {
      "epoch": 13.93,
      "learning_rate": 0.0001,
      "loss": 1.3557,
      "step": 665
    },
    {
      "epoch": 14.03,
      "learning_rate": 0.0001,
      "loss": 1.3732,
      "step": 670
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.0001,
      "loss": 1.248,
      "step": 675
    },
    {
      "epoch": 14.24,
      "learning_rate": 0.0001,
      "loss": 1.352,
      "step": 680
    },
    {
      "epoch": 14.35,
      "learning_rate": 0.0001,
      "loss": 1.3024,
      "step": 685
    },
    {
      "epoch": 14.45,
      "learning_rate": 0.0001,
      "loss": 1.3343,
      "step": 690
    },
    {
      "epoch": 14.55,
      "learning_rate": 0.0001,
      "loss": 1.3487,
      "step": 695
    },
    {
      "epoch": 14.66,
      "learning_rate": 0.0001,
      "loss": 1.3051,
      "step": 700
    },
    {
      "epoch": 14.76,
      "learning_rate": 0.0001,
      "loss": 1.3331,
      "step": 705
    },
    {
      "epoch": 14.87,
      "learning_rate": 0.0001,
      "loss": 1.371,
      "step": 710
    },
    {
      "epoch": 14.97,
      "learning_rate": 0.0001,
      "loss": 1.3779,
      "step": 715
    },
    {
      "epoch": 15.08,
      "learning_rate": 0.0001,
      "loss": 1.3086,
      "step": 720
    },
    {
      "epoch": 15.18,
      "learning_rate": 0.0001,
      "loss": 1.2871,
      "step": 725
    },
    {
      "epoch": 15.29,
      "learning_rate": 0.0001,
      "loss": 1.2899,
      "step": 730
    },
    {
      "epoch": 15.39,
      "learning_rate": 0.0001,
      "loss": 1.3205,
      "step": 735
    },
    {
      "epoch": 15.5,
      "learning_rate": 0.0001,
      "loss": 1.3799,
      "step": 740
    },
    {
      "epoch": 15.6,
      "learning_rate": 0.0001,
      "loss": 1.3251,
      "step": 745
    },
    {
      "epoch": 15.71,
      "learning_rate": 0.0001,
      "loss": 1.3209,
      "step": 750
    },
    {
      "epoch": 15.81,
      "learning_rate": 0.0001,
      "loss": 1.3015,
      "step": 755
    },
    {
      "epoch": 15.92,
      "learning_rate": 0.0001,
      "loss": 1.2979,
      "step": 760
    },
    {
      "epoch": 16.02,
      "learning_rate": 0.0001,
      "loss": 1.3355,
      "step": 765
    },
    {
      "epoch": 16.13,
      "learning_rate": 0.0001,
      "loss": 1.2764,
      "step": 770
    },
    {
      "epoch": 16.23,
      "learning_rate": 0.0001,
      "loss": 1.319,
      "step": 775
    },
    {
      "epoch": 16.34,
      "learning_rate": 0.0001,
      "loss": 1.2541,
      "step": 780
    },
    {
      "epoch": 16.44,
      "learning_rate": 0.0001,
      "loss": 1.3251,
      "step": 785
    },
    {
      "epoch": 16.54,
      "learning_rate": 0.0001,
      "loss": 1.2479,
      "step": 790
    },
    {
      "epoch": 16.65,
      "learning_rate": 0.0001,
      "loss": 1.2912,
      "step": 795
    },
    {
      "epoch": 16.75,
      "learning_rate": 0.0001,
      "loss": 1.3064,
      "step": 800
    },
    {
      "epoch": 16.86,
      "learning_rate": 0.0001,
      "loss": 1.3029,
      "step": 805
    },
    {
      "epoch": 16.96,
      "learning_rate": 0.0001,
      "loss": 1.3103,
      "step": 810
    },
    {
      "epoch": 17.07,
      "learning_rate": 0.0001,
      "loss": 1.2733,
      "step": 815
    },
    {
      "epoch": 17.17,
      "learning_rate": 0.0001,
      "loss": 1.3373,
      "step": 820
    },
    {
      "epoch": 17.28,
      "learning_rate": 0.0001,
      "loss": 1.2371,
      "step": 825
    },
    {
      "epoch": 17.38,
      "learning_rate": 0.0001,
      "loss": 1.2919,
      "step": 830
    },
    {
      "epoch": 17.49,
      "learning_rate": 0.0001,
      "loss": 1.2806,
      "step": 835
    },
    {
      "epoch": 17.59,
      "learning_rate": 0.0001,
      "loss": 1.2925,
      "step": 840
    },
    {
      "epoch": 17.7,
      "learning_rate": 0.0001,
      "loss": 1.2465,
      "step": 845
    },
    {
      "epoch": 17.8,
      "learning_rate": 0.0001,
      "loss": 1.2417,
      "step": 850
    },
    {
      "epoch": 17.91,
      "learning_rate": 0.0001,
      "loss": 1.3069,
      "step": 855
    },
    {
      "epoch": 18.01,
      "learning_rate": 0.0001,
      "loss": 1.2598,
      "step": 860
    },
    {
      "epoch": 18.12,
      "learning_rate": 0.0001,
      "loss": 1.2807,
      "step": 865
    },
    {
      "epoch": 18.22,
      "learning_rate": 0.0001,
      "loss": 1.2548,
      "step": 870
    },
    {
      "epoch": 18.32,
      "learning_rate": 0.0001,
      "loss": 1.2531,
      "step": 875
    },
    {
      "epoch": 18.43,
      "learning_rate": 0.0001,
      "loss": 1.1707,
      "step": 880
    },
    {
      "epoch": 18.53,
      "learning_rate": 0.0001,
      "loss": 1.2652,
      "step": 885
    },
    {
      "epoch": 18.64,
      "learning_rate": 0.0001,
      "loss": 1.2448,
      "step": 890
    },
    {
      "epoch": 18.74,
      "learning_rate": 0.0001,
      "loss": 1.2969,
      "step": 895
    },
    {
      "epoch": 18.85,
      "learning_rate": 0.0001,
      "loss": 1.279,
      "step": 900
    },
    {
      "epoch": 18.95,
      "learning_rate": 0.0001,
      "loss": 1.2714,
      "step": 905
    },
    {
      "epoch": 19.06,
      "learning_rate": 0.0001,
      "loss": 1.277,
      "step": 910
    },
    {
      "epoch": 19.16,
      "learning_rate": 0.0001,
      "loss": 1.2272,
      "step": 915
    },
    {
      "epoch": 19.27,
      "learning_rate": 0.0001,
      "loss": 1.2387,
      "step": 920
    },
    {
      "epoch": 19.37,
      "learning_rate": 0.0001,
      "loss": 1.2494,
      "step": 925
    },
    {
      "epoch": 19.48,
      "learning_rate": 0.0001,
      "loss": 1.3238,
      "step": 930
    },
    {
      "epoch": 19.58,
      "learning_rate": 0.0001,
      "loss": 1.258,
      "step": 935
    },
    {
      "epoch": 19.69,
      "learning_rate": 0.0001,
      "loss": 1.2089,
      "step": 940
    },
    {
      "epoch": 19.79,
      "learning_rate": 0.0001,
      "loss": 1.2216,
      "step": 945
    },
    {
      "epoch": 19.9,
      "learning_rate": 0.0001,
      "loss": 1.2264,
      "step": 950
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0001,
      "loss": 1.2316,
      "step": 955
    },
    {
      "epoch": 20.1,
      "learning_rate": 0.0001,
      "loss": 1.2038,
      "step": 960
    },
    {
      "epoch": 20.21,
      "learning_rate": 0.0001,
      "loss": 1.2001,
      "step": 965
    },
    {
      "epoch": 20.31,
      "learning_rate": 0.0001,
      "loss": 1.2475,
      "step": 970
    },
    {
      "epoch": 20.42,
      "learning_rate": 0.0001,
      "loss": 1.2513,
      "step": 975
    },
    {
      "epoch": 20.52,
      "learning_rate": 0.0001,
      "loss": 1.2635,
      "step": 980
    },
    {
      "epoch": 20.63,
      "learning_rate": 0.0001,
      "loss": 1.1817,
      "step": 985
    },
    {
      "epoch": 20.73,
      "learning_rate": 0.0001,
      "loss": 1.2474,
      "step": 990
    },
    {
      "epoch": 20.84,
      "learning_rate": 0.0001,
      "loss": 1.2309,
      "step": 995
    },
    {
      "epoch": 20.94,
      "learning_rate": 0.0001,
      "loss": 1.1871,
      "step": 1000
    },
    {
      "epoch": 21.05,
      "learning_rate": 0.0001,
      "loss": 1.2312,
      "step": 1005
    },
    {
      "epoch": 21.15,
      "learning_rate": 0.0001,
      "loss": 1.2152,
      "step": 1010
    },
    {
      "epoch": 21.26,
      "learning_rate": 0.0001,
      "loss": 1.1812,
      "step": 1015
    },
    {
      "epoch": 21.36,
      "learning_rate": 0.0001,
      "loss": 1.2133,
      "step": 1020
    },
    {
      "epoch": 21.47,
      "learning_rate": 0.0001,
      "loss": 1.1851,
      "step": 1025
    },
    {
      "epoch": 21.57,
      "learning_rate": 0.0001,
      "loss": 1.1767,
      "step": 1030
    },
    {
      "epoch": 21.68,
      "learning_rate": 0.0001,
      "loss": 1.242,
      "step": 1035
    },
    {
      "epoch": 21.78,
      "learning_rate": 0.0001,
      "loss": 1.2135,
      "step": 1040
    },
    {
      "epoch": 21.88,
      "learning_rate": 0.0001,
      "loss": 1.1895,
      "step": 1045
    },
    {
      "epoch": 21.99,
      "learning_rate": 0.0001,
      "loss": 1.2546,
      "step": 1050
    },
    {
      "epoch": 22.09,
      "learning_rate": 0.0001,
      "loss": 1.198,
      "step": 1055
    },
    {
      "epoch": 22.2,
      "learning_rate": 0.0001,
      "loss": 1.1872,
      "step": 1060
    },
    {
      "epoch": 22.3,
      "learning_rate": 0.0001,
      "loss": 1.1824,
      "step": 1065
    },
    {
      "epoch": 22.41,
      "learning_rate": 0.0001,
      "loss": 1.1962,
      "step": 1070
    },
    {
      "epoch": 22.51,
      "learning_rate": 0.0001,
      "loss": 1.1711,
      "step": 1075
    },
    {
      "epoch": 22.62,
      "learning_rate": 0.0001,
      "loss": 1.1717,
      "step": 1080
    },
    {
      "epoch": 22.72,
      "learning_rate": 0.0001,
      "loss": 1.1856,
      "step": 1085
    },
    {
      "epoch": 22.83,
      "learning_rate": 0.0001,
      "loss": 1.2152,
      "step": 1090
    },
    {
      "epoch": 22.93,
      "learning_rate": 0.0001,
      "loss": 1.2333,
      "step": 1095
    },
    {
      "epoch": 23.04,
      "learning_rate": 0.0001,
      "loss": 1.1765,
      "step": 1100
    },
    {
      "epoch": 23.14,
      "learning_rate": 0.0001,
      "loss": 1.1416,
      "step": 1105
    },
    {
      "epoch": 23.25,
      "learning_rate": 0.0001,
      "loss": 1.1475,
      "step": 1110
    },
    {
      "epoch": 23.35,
      "learning_rate": 0.0001,
      "loss": 1.1745,
      "step": 1115
    },
    {
      "epoch": 23.46,
      "learning_rate": 0.0001,
      "loss": 1.1599,
      "step": 1120
    },
    {
      "epoch": 23.56,
      "learning_rate": 0.0001,
      "loss": 1.1557,
      "step": 1125
    },
    {
      "epoch": 23.66,
      "learning_rate": 0.0001,
      "loss": 1.21,
      "step": 1130
    },
    {
      "epoch": 23.77,
      "learning_rate": 0.0001,
      "loss": 1.196,
      "step": 1135
    },
    {
      "epoch": 23.87,
      "learning_rate": 0.0001,
      "loss": 1.1653,
      "step": 1140
    },
    {
      "epoch": 23.98,
      "learning_rate": 0.0001,
      "loss": 1.2687,
      "step": 1145
    },
    {
      "epoch": 24.08,
      "learning_rate": 0.0001,
      "loss": 1.1043,
      "step": 1150
    },
    {
      "epoch": 24.19,
      "learning_rate": 0.0001,
      "loss": 1.1802,
      "step": 1155
    },
    {
      "epoch": 24.29,
      "learning_rate": 0.0001,
      "loss": 1.158,
      "step": 1160
    },
    {
      "epoch": 24.4,
      "learning_rate": 0.0001,
      "loss": 1.1153,
      "step": 1165
    },
    {
      "epoch": 24.5,
      "learning_rate": 0.0001,
      "loss": 1.1722,
      "step": 1170
    },
    {
      "epoch": 24.61,
      "learning_rate": 0.0001,
      "loss": 1.2067,
      "step": 1175
    },
    {
      "epoch": 24.61,
      "step": 1175,
      "total_flos": 4391121715200000.0,
      "train_loss": 1.3988467488390335,
      "train_runtime": 1205.3351,
      "train_samples_per_second": 31.692,
      "train_steps_per_second": 0.975
    }
  ],
  "logging_steps": 5,
  "max_steps": 1175,
  "num_train_epochs": 25,
  "save_steps": 1000,
  "total_flos": 4391121715200000.0,
  "trial_name": null,
  "trial_params": null
}