{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 74.17746759720838,
  "eval_steps": 500,
  "global_step": 2325,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 2.4292,
      "step": 5
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.6311,
      "step": 10
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.4364,
      "step": 15
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.3208,
      "step": 20
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.2781,
      "step": 25
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 1.2784,
      "step": 30
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001,
      "loss": 1.1591,
      "step": 35
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 1.1193,
      "step": 40
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001,
      "loss": 1.1173,
      "step": 45
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001,
      "loss": 1.0948,
      "step": 50
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001,
      "loss": 1.0937,
      "step": 55
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001,
      "loss": 1.0643,
      "step": 60
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001,
      "loss": 1.0252,
      "step": 65
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 0.9701,
      "step": 70
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001,
      "loss": 0.9773,
      "step": 75
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0001,
      "loss": 0.9364,
      "step": 80
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001,
      "loss": 0.955,
      "step": 85
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0001,
      "loss": 0.9752,
      "step": 90
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0001,
      "loss": 0.9614,
      "step": 95
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001,
      "loss": 0.8711,
      "step": 100
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001,
      "loss": 0.8728,
      "step": 105
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001,
      "loss": 0.8734,
      "step": 110
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0001,
      "loss": 0.8769,
      "step": 115
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001,
      "loss": 0.8714,
      "step": 120
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.0001,
      "loss": 0.8694,
      "step": 125
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.0001,
      "loss": 0.8008,
      "step": 130
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0001,
      "loss": 0.8044,
      "step": 135
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0001,
      "loss": 0.7945,
      "step": 140
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0001,
      "loss": 0.7927,
      "step": 145
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001,
      "loss": 0.7982,
      "step": 150
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0001,
      "loss": 0.7921,
      "step": 155
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.0001,
      "loss": 0.7751,
      "step": 160
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001,
      "loss": 0.7197,
      "step": 165
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0001,
      "loss": 0.7381,
      "step": 170
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.0001,
      "loss": 0.7328,
      "step": 175
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.0001,
      "loss": 0.7325,
      "step": 180
    },
    {
      "epoch": 5.9,
      "learning_rate": 0.0001,
      "loss": 0.7492,
      "step": 185
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.0001,
      "loss": 0.7042,
      "step": 190
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0001,
      "loss": 0.6687,
      "step": 195
    },
    {
      "epoch": 6.38,
      "learning_rate": 0.0001,
      "loss": 0.6617,
      "step": 200
    },
    {
      "epoch": 6.54,
      "learning_rate": 0.0001,
      "loss": 0.6895,
      "step": 205
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.0001,
      "loss": 0.6763,
      "step": 210
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.0001,
      "loss": 0.6825,
      "step": 215
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.0001,
      "loss": 0.6862,
      "step": 220
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.0001,
      "loss": 0.6176,
      "step": 225
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.0001,
      "loss": 0.6072,
      "step": 230
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.0001,
      "loss": 0.6289,
      "step": 235
    },
    {
      "epoch": 7.66,
      "learning_rate": 0.0001,
      "loss": 0.6223,
      "step": 240
    },
    {
      "epoch": 7.82,
      "learning_rate": 0.0001,
      "loss": 0.6358,
      "step": 245
    },
    {
      "epoch": 7.98,
      "learning_rate": 0.0001,
      "loss": 0.6365,
      "step": 250
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0001,
      "loss": 0.5835,
      "step": 255
    },
    {
      "epoch": 8.3,
      "learning_rate": 0.0001,
      "loss": 0.5829,
      "step": 260
    },
    {
      "epoch": 8.45,
      "learning_rate": 0.0001,
      "loss": 0.5816,
      "step": 265
    },
    {
      "epoch": 8.61,
      "learning_rate": 0.0001,
      "loss": 0.5595,
      "step": 270
    },
    {
      "epoch": 8.77,
      "learning_rate": 0.0001,
      "loss": 0.5902,
      "step": 275
    },
    {
      "epoch": 8.93,
      "learning_rate": 0.0001,
      "loss": 0.5717,
      "step": 280
    },
    {
      "epoch": 9.09,
      "learning_rate": 0.0001,
      "loss": 0.5584,
      "step": 285
    },
    {
      "epoch": 9.25,
      "learning_rate": 0.0001,
      "loss": 0.538,
      "step": 290
    },
    {
      "epoch": 9.41,
      "learning_rate": 0.0001,
      "loss": 0.5172,
      "step": 295
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.0001,
      "loss": 0.5378,
      "step": 300
    },
    {
      "epoch": 9.73,
      "learning_rate": 0.0001,
      "loss": 0.5319,
      "step": 305
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.0001,
      "loss": 0.529,
      "step": 310
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.0001,
      "loss": 0.5236,
      "step": 315
    },
    {
      "epoch": 10.21,
      "learning_rate": 0.0001,
      "loss": 0.4818,
      "step": 320
    },
    {
      "epoch": 10.37,
      "learning_rate": 0.0001,
      "loss": 0.4856,
      "step": 325
    },
    {
      "epoch": 10.53,
      "learning_rate": 0.0001,
      "loss": 0.502,
      "step": 330
    },
    {
      "epoch": 10.69,
      "learning_rate": 0.0001,
      "loss": 0.482,
      "step": 335
    },
    {
      "epoch": 10.85,
      "learning_rate": 0.0001,
      "loss": 0.4957,
      "step": 340
    },
    {
      "epoch": 11.01,
      "learning_rate": 0.0001,
      "loss": 0.503,
      "step": 345
    },
    {
      "epoch": 11.17,
      "learning_rate": 0.0001,
      "loss": 0.4476,
      "step": 350
    },
    {
      "epoch": 11.33,
      "learning_rate": 0.0001,
      "loss": 0.4525,
      "step": 355
    },
    {
      "epoch": 11.49,
      "learning_rate": 0.0001,
      "loss": 0.4533,
      "step": 360
    },
    {
      "epoch": 11.65,
      "learning_rate": 0.0001,
      "loss": 0.4623,
      "step": 365
    },
    {
      "epoch": 11.8,
      "learning_rate": 0.0001,
      "loss": 0.459,
      "step": 370
    },
    {
      "epoch": 11.96,
      "learning_rate": 0.0001,
      "loss": 0.4563,
      "step": 375
    },
    {
      "epoch": 12.12,
      "learning_rate": 0.0001,
      "loss": 0.4408,
      "step": 380
    },
    {
      "epoch": 12.28,
      "learning_rate": 0.0001,
      "loss": 0.4123,
      "step": 385
    },
    {
      "epoch": 12.44,
      "learning_rate": 0.0001,
      "loss": 0.4203,
      "step": 390
    },
    {
      "epoch": 12.6,
      "learning_rate": 0.0001,
      "loss": 0.4283,
      "step": 395
    },
    {
      "epoch": 12.76,
      "learning_rate": 0.0001,
      "loss": 0.4144,
      "step": 400
    },
    {
      "epoch": 12.92,
      "learning_rate": 0.0001,
      "loss": 0.4282,
      "step": 405
    },
    {
      "epoch": 13.08,
      "learning_rate": 0.0001,
      "loss": 0.4062,
      "step": 410
    },
    {
      "epoch": 13.24,
      "learning_rate": 0.0001,
      "loss": 0.393,
      "step": 415
    },
    {
      "epoch": 13.4,
      "learning_rate": 0.0001,
      "loss": 0.3828,
      "step": 420
    },
    {
      "epoch": 13.56,
      "learning_rate": 0.0001,
      "loss": 0.3871,
      "step": 425
    },
    {
      "epoch": 13.72,
      "learning_rate": 0.0001,
      "loss": 0.3957,
      "step": 430
    },
    {
      "epoch": 13.88,
      "learning_rate": 0.0001,
      "loss": 0.3931,
      "step": 435
    },
    {
      "epoch": 14.04,
      "learning_rate": 0.0001,
      "loss": 0.389,
      "step": 440
    },
    {
      "epoch": 14.2,
      "learning_rate": 0.0001,
      "loss": 0.3529,
      "step": 445
    },
    {
      "epoch": 14.36,
      "learning_rate": 0.0001,
      "loss": 0.3639,
      "step": 450
    },
    {
      "epoch": 14.52,
      "learning_rate": 0.0001,
      "loss": 0.3665,
      "step": 455
    },
    {
      "epoch": 14.68,
      "learning_rate": 0.0001,
      "loss": 0.3609,
      "step": 460
    },
    {
      "epoch": 14.84,
      "learning_rate": 0.0001,
      "loss": 0.3642,
      "step": 465
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.0001,
      "loss": 0.3693,
      "step": 470
    },
    {
      "epoch": 15.15,
      "learning_rate": 0.0001,
      "loss": 0.3382,
      "step": 475
    },
    {
      "epoch": 15.31,
      "learning_rate": 0.0001,
      "loss": 0.3344,
      "step": 480
    },
    {
      "epoch": 15.47,
      "learning_rate": 0.0001,
      "loss": 0.3379,
      "step": 485
    },
    {
      "epoch": 15.63,
      "learning_rate": 0.0001,
      "loss": 0.3307,
      "step": 490
    },
    {
      "epoch": 15.79,
      "learning_rate": 0.0001,
      "loss": 0.3474,
      "step": 495
    },
    {
      "epoch": 15.95,
      "learning_rate": 0.0001,
      "loss": 0.3348,
      "step": 500
    },
    {
      "epoch": 16.11,
      "learning_rate": 0.0001,
      "loss": 0.3228,
      "step": 505
    },
    {
      "epoch": 16.27,
      "learning_rate": 0.0001,
      "loss": 0.3164,
      "step": 510
    },
    {
      "epoch": 16.43,
      "learning_rate": 0.0001,
      "loss": 0.3078,
      "step": 515
    },
    {
      "epoch": 16.59,
      "learning_rate": 0.0001,
      "loss": 0.3135,
      "step": 520
    },
    {
      "epoch": 16.75,
      "learning_rate": 0.0001,
      "loss": 0.3091,
      "step": 525
    },
    {
      "epoch": 16.91,
      "learning_rate": 0.0001,
      "loss": 0.3229,
      "step": 530
    },
    {
      "epoch": 17.07,
      "learning_rate": 0.0001,
      "loss": 0.3003,
      "step": 535
    },
    {
      "epoch": 17.23,
      "learning_rate": 0.0001,
      "loss": 0.2832,
      "step": 540
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.0001,
      "loss": 0.2936,
      "step": 545
    },
    {
      "epoch": 17.55,
      "learning_rate": 0.0001,
      "loss": 0.2881,
      "step": 550
    },
    {
      "epoch": 17.71,
      "learning_rate": 0.0001,
      "loss": 0.2858,
      "step": 555
    },
    {
      "epoch": 17.87,
      "learning_rate": 0.0001,
      "loss": 0.2987,
      "step": 560
    },
    {
      "epoch": 18.03,
      "learning_rate": 0.0001,
      "loss": 0.2986,
      "step": 565
    },
    {
      "epoch": 18.19,
      "learning_rate": 0.0001,
      "loss": 0.2624,
      "step": 570
    },
    {
      "epoch": 18.34,
      "learning_rate": 0.0001,
      "loss": 0.2668,
      "step": 575
    },
    {
      "epoch": 18.5,
      "learning_rate": 0.0001,
      "loss": 0.2701,
      "step": 580
    },
    {
      "epoch": 18.66,
      "learning_rate": 0.0001,
      "loss": 0.2759,
      "step": 585
    },
    {
      "epoch": 18.82,
      "learning_rate": 0.0001,
      "loss": 0.273,
      "step": 590
    },
    {
      "epoch": 18.98,
      "learning_rate": 0.0001,
      "loss": 0.2776,
      "step": 595
    },
    {
      "epoch": 19.14,
      "learning_rate": 0.0001,
      "loss": 0.256,
      "step": 600
    },
    {
      "epoch": 19.3,
      "learning_rate": 0.0001,
      "loss": 0.2494,
      "step": 605
    },
    {
      "epoch": 19.46,
      "learning_rate": 0.0001,
      "loss": 0.2507,
      "step": 610
    },
    {
      "epoch": 19.62,
      "learning_rate": 0.0001,
      "loss": 0.2541,
      "step": 615
    },
    {
      "epoch": 19.78,
      "learning_rate": 0.0001,
      "loss": 0.2513,
      "step": 620
    },
    {
      "epoch": 19.94,
      "learning_rate": 0.0001,
      "loss": 0.2579,
      "step": 625
    },
    {
      "epoch": 20.1,
      "learning_rate": 0.0001,
      "loss": 0.2421,
      "step": 630
    },
    {
      "epoch": 20.26,
      "learning_rate": 0.0001,
      "loss": 0.2348,
      "step": 635
    },
    {
      "epoch": 20.42,
      "learning_rate": 0.0001,
      "loss": 0.2366,
      "step": 640
    },
    {
      "epoch": 20.58,
      "learning_rate": 0.0001,
      "loss": 0.2306,
      "step": 645
    },
    {
      "epoch": 20.74,
      "learning_rate": 0.0001,
      "loss": 0.2356,
      "step": 650
    },
    {
      "epoch": 20.9,
      "learning_rate": 0.0001,
      "loss": 0.2407,
      "step": 655
    },
    {
      "epoch": 21.06,
      "learning_rate": 0.0001,
      "loss": 0.2328,
      "step": 660
    },
    {
      "epoch": 21.22,
      "learning_rate": 0.0001,
      "loss": 0.2183,
      "step": 665
    },
    {
      "epoch": 21.38,
      "learning_rate": 0.0001,
      "loss": 0.2121,
      "step": 670
    },
    {
      "epoch": 21.54,
      "learning_rate": 0.0001,
      "loss": 0.2186,
      "step": 675
    },
    {
      "epoch": 21.69,
      "learning_rate": 0.0001,
      "loss": 0.22,
      "step": 680
    },
    {
      "epoch": 21.85,
      "learning_rate": 0.0001,
      "loss": 0.2266,
      "step": 685
    },
    {
      "epoch": 22.01,
      "learning_rate": 0.0001,
      "loss": 0.2245,
      "step": 690
    },
    {
      "epoch": 22.17,
      "learning_rate": 0.0001,
      "loss": 0.202,
      "step": 695
    },
    {
      "epoch": 22.33,
      "learning_rate": 0.0001,
      "loss": 0.1993,
      "step": 700
    },
    {
      "epoch": 22.49,
      "learning_rate": 0.0001,
      "loss": 0.2056,
      "step": 705
    },
    {
      "epoch": 22.65,
      "learning_rate": 0.0001,
      "loss": 0.2076,
      "step": 710
    },
    {
      "epoch": 22.81,
      "learning_rate": 0.0001,
      "loss": 0.208,
      "step": 715
    },
    {
      "epoch": 22.97,
      "learning_rate": 0.0001,
      "loss": 0.2134,
      "step": 720
    },
    {
      "epoch": 23.13,
      "learning_rate": 0.0001,
      "loss": 0.1929,
      "step": 725
    },
    {
      "epoch": 23.29,
      "learning_rate": 0.0001,
      "loss": 0.19,
      "step": 730
    },
    {
      "epoch": 23.45,
      "learning_rate": 0.0001,
      "loss": 0.191,
      "step": 735
    },
    {
      "epoch": 23.61,
      "learning_rate": 0.0001,
      "loss": 0.1923,
      "step": 740
    },
    {
      "epoch": 23.77,
      "learning_rate": 0.0001,
      "loss": 0.193,
      "step": 745
    },
    {
      "epoch": 23.93,
      "learning_rate": 0.0001,
      "loss": 0.1978,
      "step": 750
    },
    {
      "epoch": 24.09,
      "learning_rate": 0.0001,
      "loss": 0.1898,
      "step": 755
    },
    {
      "epoch": 24.25,
      "learning_rate": 0.0001,
      "loss": 0.1785,
      "step": 760
    },
    {
      "epoch": 24.41,
      "learning_rate": 0.0001,
      "loss": 0.1815,
      "step": 765
    },
    {
      "epoch": 24.57,
      "learning_rate": 0.0001,
      "loss": 0.1854,
      "step": 770
    },
    {
      "epoch": 24.73,
      "learning_rate": 0.0001,
      "loss": 0.1796,
      "step": 775
    },
    {
      "epoch": 24.89,
      "learning_rate": 0.0001,
      "loss": 0.1797,
      "step": 780
    },
    {
      "epoch": 25.04,
      "learning_rate": 0.0001,
      "loss": 0.1779,
      "step": 785
    },
    {
      "epoch": 25.2,
      "learning_rate": 0.0001,
      "loss": 0.1689,
      "step": 790
    },
    {
      "epoch": 25.36,
      "learning_rate": 0.0001,
      "loss": 0.1642,
      "step": 795
    },
    {
      "epoch": 25.52,
      "learning_rate": 0.0001,
      "loss": 0.1697,
      "step": 800
    },
    {
      "epoch": 25.68,
      "learning_rate": 0.0001,
      "loss": 0.1713,
      "step": 805
    },
    {
      "epoch": 25.84,
      "learning_rate": 0.0001,
      "loss": 0.175,
      "step": 810
    },
    {
      "epoch": 26.0,
      "learning_rate": 0.0001,
      "loss": 0.1736,
      "step": 815
    },
    {
      "epoch": 26.16,
      "learning_rate": 0.0001,
      "loss": 0.1598,
      "step": 820
    },
    {
      "epoch": 26.32,
      "learning_rate": 0.0001,
      "loss": 0.156,
      "step": 825
    },
    {
      "epoch": 26.48,
      "learning_rate": 0.0001,
      "loss": 0.1605,
      "step": 830
    },
    {
      "epoch": 26.64,
      "learning_rate": 0.0001,
      "loss": 0.1595,
      "step": 835
    },
    {
      "epoch": 26.8,
      "learning_rate": 0.0001,
      "loss": 0.1613,
      "step": 840
    },
    {
      "epoch": 26.96,
      "learning_rate": 0.0001,
      "loss": 0.1636,
      "step": 845
    },
    {
      "epoch": 27.12,
      "learning_rate": 0.0001,
      "loss": 0.1526,
      "step": 850
    },
    {
      "epoch": 27.28,
      "learning_rate": 0.0001,
      "loss": 0.1506,
      "step": 855
    },
    {
      "epoch": 27.44,
      "learning_rate": 0.0001,
      "loss": 0.1492,
      "step": 860
    },
    {
      "epoch": 27.6,
      "learning_rate": 0.0001,
      "loss": 0.1486,
      "step": 865
    },
    {
      "epoch": 27.76,
      "learning_rate": 0.0001,
      "loss": 0.1524,
      "step": 870
    },
    {
      "epoch": 27.92,
      "learning_rate": 0.0001,
      "loss": 0.1538,
      "step": 875
    },
    {
      "epoch": 28.08,
      "learning_rate": 0.0001,
      "loss": 0.1495,
      "step": 880
    },
    {
      "epoch": 28.24,
      "learning_rate": 0.0001,
      "loss": 0.1436,
      "step": 885
    },
    {
      "epoch": 28.39,
      "learning_rate": 0.0001,
      "loss": 0.1387,
      "step": 890
    },
    {
      "epoch": 28.55,
      "learning_rate": 0.0001,
      "loss": 0.1419,
      "step": 895
    },
    {
      "epoch": 28.71,
      "learning_rate": 0.0001,
      "loss": 0.144,
      "step": 900
    },
    {
      "epoch": 28.87,
      "learning_rate": 0.0001,
      "loss": 0.1421,
      "step": 905
    },
    {
      "epoch": 29.03,
      "learning_rate": 0.0001,
      "loss": 0.144,
      "step": 910
    },
    {
      "epoch": 29.19,
      "learning_rate": 0.0001,
      "loss": 0.1336,
      "step": 915
    },
    {
      "epoch": 29.35,
      "learning_rate": 0.0001,
      "loss": 0.1342,
      "step": 920
    },
    {
      "epoch": 29.51,
      "learning_rate": 0.0001,
      "loss": 0.1315,
      "step": 925
    },
    {
      "epoch": 29.67,
      "learning_rate": 0.0001,
      "loss": 0.134,
      "step": 930
    },
    {
      "epoch": 29.83,
      "learning_rate": 0.0001,
      "loss": 0.1385,
      "step": 935
    },
    {
      "epoch": 29.99,
      "learning_rate": 0.0001,
      "loss": 0.1396,
      "step": 940
    },
    {
      "epoch": 30.15,
      "learning_rate": 0.0001,
      "loss": 0.1261,
      "step": 945
    },
    {
      "epoch": 30.31,
      "learning_rate": 0.0001,
      "loss": 0.1254,
      "step": 950
    },
    {
      "epoch": 30.47,
      "learning_rate": 0.0001,
      "loss": 0.1274,
      "step": 955
    },
    {
      "epoch": 30.63,
      "learning_rate": 0.0001,
      "loss": 0.1273,
      "step": 960
    },
    {
      "epoch": 30.79,
      "learning_rate": 0.0001,
      "loss": 0.1328,
      "step": 965
    },
    {
      "epoch": 30.95,
      "learning_rate": 0.0001,
      "loss": 0.1305,
      "step": 970
    },
    {
      "epoch": 31.11,
      "learning_rate": 0.0001,
      "loss": 0.1215,
      "step": 975
    },
    {
      "epoch": 31.27,
      "learning_rate": 0.0001,
      "loss": 0.1196,
      "step": 980
    },
    {
      "epoch": 31.43,
      "learning_rate": 0.0001,
      "loss": 0.1209,
      "step": 985
    },
    {
      "epoch": 31.59,
      "learning_rate": 0.0001,
      "loss": 0.1211,
      "step": 990
    },
    {
      "epoch": 31.74,
      "learning_rate": 0.0001,
      "loss": 0.125,
      "step": 995
    },
    {
      "epoch": 31.9,
      "learning_rate": 0.0001,
      "loss": 0.1262,
      "step": 1000
    },
    {
      "epoch": 32.06,
      "learning_rate": 0.0001,
      "loss": 0.1185,
      "step": 1005
    },
    {
      "epoch": 32.22,
      "learning_rate": 0.0001,
      "loss": 0.113,
      "step": 1010
    },
    {
      "epoch": 32.38,
      "learning_rate": 0.0001,
      "loss": 0.1136,
      "step": 1015
    },
    {
      "epoch": 32.54,
      "learning_rate": 0.0001,
      "loss": 0.1144,
      "step": 1020
    },
    {
      "epoch": 32.7,
      "learning_rate": 0.0001,
      "loss": 0.1147,
      "step": 1025
    },
    {
      "epoch": 32.86,
      "learning_rate": 0.0001,
      "loss": 0.1168,
      "step": 1030
    },
    {
      "epoch": 33.02,
      "learning_rate": 0.0001,
      "loss": 0.1179,
      "step": 1035
    },
    {
      "epoch": 33.18,
      "learning_rate": 0.0001,
      "loss": 0.1073,
      "step": 1040
    },
    {
      "epoch": 33.34,
      "learning_rate": 0.0001,
      "loss": 0.1091,
      "step": 1045
    },
    {
      "epoch": 33.5,
      "learning_rate": 0.0001,
      "loss": 0.1116,
      "step": 1050
    },
    {
      "epoch": 33.66,
      "learning_rate": 0.0001,
      "loss": 0.1092,
      "step": 1055
    },
    {
      "epoch": 33.82,
      "learning_rate": 0.0001,
      "loss": 0.1107,
      "step": 1060
    },
    {
      "epoch": 33.98,
      "learning_rate": 0.0001,
      "loss": 0.1094,
      "step": 1065
    },
    {
      "epoch": 34.14,
      "learning_rate": 0.0001,
      "loss": 0.1033,
      "step": 1070
    },
    {
      "epoch": 34.3,
      "learning_rate": 0.0001,
      "loss": 0.1027,
      "step": 1075
    },
    {
      "epoch": 34.46,
      "learning_rate": 0.0001,
      "loss": 0.1021,
      "step": 1080
    },
    {
      "epoch": 34.62,
      "learning_rate": 0.0001,
      "loss": 0.1045,
      "step": 1085
    },
    {
      "epoch": 34.78,
      "learning_rate": 0.0001,
      "loss": 0.1044,
      "step": 1090
    },
    {
      "epoch": 34.94,
      "learning_rate": 0.0001,
      "loss": 0.1081,
      "step": 1095
    },
    {
      "epoch": 35.09,
      "learning_rate": 0.0001,
      "loss": 0.1028,
      "step": 1100
    },
    {
      "epoch": 35.25,
      "learning_rate": 0.0001,
      "loss": 0.0967,
      "step": 1105
    },
    {
      "epoch": 35.41,
      "learning_rate": 0.0001,
      "loss": 0.0967,
      "step": 1110
    },
    {
      "epoch": 35.57,
      "learning_rate": 0.0001,
      "loss": 0.1019,
      "step": 1115
    },
    {
      "epoch": 35.73,
      "learning_rate": 0.0001,
      "loss": 0.1005,
      "step": 1120
    },
    {
      "epoch": 35.89,
      "learning_rate": 0.0001,
      "loss": 0.1031,
      "step": 1125
    },
    {
      "epoch": 36.05,
      "learning_rate": 0.0001,
      "loss": 0.0981,
      "step": 1130
    },
    {
      "epoch": 36.21,
      "learning_rate": 0.0001,
      "loss": 0.0945,
      "step": 1135
    },
    {
      "epoch": 36.37,
      "learning_rate": 0.0001,
      "loss": 0.0954,
      "step": 1140
    },
    {
      "epoch": 36.53,
      "learning_rate": 0.0001,
      "loss": 0.0936,
      "step": 1145
    },
    {
      "epoch": 36.69,
      "learning_rate": 0.0001,
      "loss": 0.0972,
      "step": 1150
    },
    {
      "epoch": 36.85,
      "learning_rate": 0.0001,
      "loss": 0.0951,
      "step": 1155
    },
    {
      "epoch": 37.01,
      "learning_rate": 0.0001,
      "loss": 0.0974,
      "step": 1160
    },
    {
      "epoch": 37.17,
      "learning_rate": 0.0001,
      "loss": 0.0902,
      "step": 1165
    },
    {
      "epoch": 37.33,
      "learning_rate": 0.0001,
      "loss": 0.0909,
      "step": 1170
    },
    {
      "epoch": 37.49,
      "learning_rate": 0.0001,
      "loss": 0.0918,
      "step": 1175
    },
    {
      "epoch": 37.65,
      "learning_rate": 0.0001,
      "loss": 0.0913,
      "step": 1180
    },
    {
      "epoch": 37.81,
      "learning_rate": 0.0001,
      "loss": 0.0926,
      "step": 1185
    },
    {
      "epoch": 37.97,
      "learning_rate": 0.0001,
      "loss": 0.0925,
      "step": 1190
    },
    {
      "epoch": 38.13,
      "learning_rate": 0.0001,
      "loss": 0.0882,
      "step": 1195
    },
    {
      "epoch": 38.29,
      "learning_rate": 0.0001,
      "loss": 0.0856,
      "step": 1200
    },
    {
      "epoch": 38.44,
      "learning_rate": 0.0001,
      "loss": 0.0881,
      "step": 1205
    },
    {
      "epoch": 38.6,
      "learning_rate": 0.0001,
      "loss": 0.0889,
      "step": 1210
    },
    {
      "epoch": 38.76,
      "learning_rate": 0.0001,
      "loss": 0.0863,
      "step": 1215
    },
    {
      "epoch": 38.92,
      "learning_rate": 0.0001,
      "loss": 0.087,
      "step": 1220
    },
    {
      "epoch": 39.08,
      "learning_rate": 0.0001,
      "loss": 0.0851,
      "step": 1225
    },
    {
      "epoch": 39.24,
      "learning_rate": 0.0001,
      "loss": 0.0819,
      "step": 1230
    },
    {
      "epoch": 39.4,
      "learning_rate": 0.0001,
      "loss": 0.0844,
      "step": 1235
    },
    {
      "epoch": 39.56,
      "learning_rate": 0.0001,
      "loss": 0.0826,
      "step": 1240
    },
    {
      "epoch": 39.72,
      "learning_rate": 0.0001,
      "loss": 0.0832,
      "step": 1245
    },
    {
      "epoch": 39.88,
      "learning_rate": 0.0001,
      "loss": 0.0838,
      "step": 1250
    },
    {
      "epoch": 40.04,
      "learning_rate": 0.0001,
      "loss": 0.087,
      "step": 1255
    },
    {
      "epoch": 40.2,
      "learning_rate": 0.0001,
      "loss": 0.0792,
      "step": 1260
    },
    {
      "epoch": 40.36,
      "learning_rate": 0.0001,
      "loss": 0.0802,
      "step": 1265
    },
    {
      "epoch": 40.52,
      "learning_rate": 0.0001,
      "loss": 0.0806,
      "step": 1270
    },
    {
      "epoch": 40.68,
      "learning_rate": 0.0001,
      "loss": 0.0768,
      "step": 1275
    },
    {
      "epoch": 40.84,
      "learning_rate": 0.0001,
      "loss": 0.0812,
      "step": 1280
    },
    {
      "epoch": 41.0,
      "learning_rate": 0.0001,
      "loss": 0.0849,
      "step": 1285
    },
    {
      "epoch": 41.16,
      "learning_rate": 0.0001,
      "loss": 0.0767,
      "step": 1290
    },
    {
      "epoch": 41.32,
      "learning_rate": 0.0001,
      "loss": 0.0766,
      "step": 1295
    },
    {
      "epoch": 41.48,
      "learning_rate": 0.0001,
      "loss": 0.0774,
      "step": 1300
    },
    {
      "epoch": 41.64,
      "learning_rate": 0.0001,
      "loss": 0.0789,
      "step": 1305
    },
    {
      "epoch": 41.79,
      "learning_rate": 0.0001,
      "loss": 0.0774,
      "step": 1310
    },
    {
      "epoch": 41.95,
      "learning_rate": 0.0001,
      "loss": 0.0795,
      "step": 1315
    },
    {
      "epoch": 42.11,
      "learning_rate": 0.0001,
      "loss": 0.0748,
      "step": 1320
    },
    {
      "epoch": 42.27,
      "learning_rate": 0.0001,
      "loss": 0.0728,
      "step": 1325
    },
    {
      "epoch": 42.43,
      "learning_rate": 0.0001,
      "loss": 0.0751,
      "step": 1330
    },
    {
      "epoch": 42.59,
      "learning_rate": 0.0001,
      "loss": 0.0765,
      "step": 1335
    },
    {
      "epoch": 42.75,
      "learning_rate": 0.0001,
      "loss": 0.0741,
      "step": 1340
    },
    {
      "epoch": 42.91,
      "learning_rate": 0.0001,
      "loss": 0.0761,
      "step": 1345
    },
    {
      "epoch": 43.07,
      "learning_rate": 0.0001,
      "loss": 0.0752,
      "step": 1350
    },
    {
      "epoch": 43.23,
      "learning_rate": 0.0001,
      "loss": 0.0715,
      "step": 1355
    },
    {
      "epoch": 43.39,
      "learning_rate": 0.0001,
      "loss": 0.0734,
      "step": 1360
    },
    {
      "epoch": 43.55,
      "learning_rate": 0.0001,
      "loss": 0.0727,
      "step": 1365
    },
    {
      "epoch": 43.71,
      "learning_rate": 0.0001,
      "loss": 0.0726,
      "step": 1370
    },
    {
      "epoch": 43.87,
      "learning_rate": 0.0001,
      "loss": 0.0731,
      "step": 1375
    },
    {
      "epoch": 44.03,
      "learning_rate": 0.0001,
      "loss": 0.0706,
      "step": 1380
    },
    {
      "epoch": 44.19,
      "learning_rate": 0.0001,
      "loss": 0.0684,
      "step": 1385
    },
    {
      "epoch": 44.35,
      "learning_rate": 0.0001,
      "loss": 0.0695,
      "step": 1390
    },
    {
      "epoch": 44.51,
      "learning_rate": 0.0001,
      "loss": 0.0691,
      "step": 1395
    },
    {
      "epoch": 44.67,
      "learning_rate": 0.0001,
      "loss": 0.0711,
      "step": 1400
    },
    {
      "epoch": 44.83,
      "learning_rate": 0.0001,
      "loss": 0.07,
      "step": 1405
    },
    {
      "epoch": 44.99,
      "learning_rate": 0.0001,
      "loss": 0.071,
      "step": 1410
    },
    {
      "epoch": 45.14,
      "learning_rate": 0.0001,
      "loss": 0.0663,
      "step": 1415
    },
    {
      "epoch": 45.3,
      "learning_rate": 0.0001,
      "loss": 0.0663,
      "step": 1420
    },
    {
      "epoch": 45.46,
      "learning_rate": 0.0001,
      "loss": 0.0667,
      "step": 1425
    },
    {
      "epoch": 45.62,
      "learning_rate": 0.0001,
      "loss": 0.0694,
      "step": 1430
    },
    {
      "epoch": 45.78,
      "learning_rate": 0.0001,
      "loss": 0.0677,
      "step": 1435
    },
    {
      "epoch": 45.94,
      "learning_rate": 0.0001,
      "loss": 0.0683,
      "step": 1440
    },
    {
      "epoch": 46.1,
      "learning_rate": 0.0001,
      "loss": 0.065,
      "step": 1445
    },
    {
      "epoch": 46.26,
      "learning_rate": 0.0001,
      "loss": 0.0642,
      "step": 1450
    },
    {
      "epoch": 46.42,
      "learning_rate": 0.0001,
      "loss": 0.066,
      "step": 1455
    },
    {
      "epoch": 46.58,
      "learning_rate": 0.0001,
      "loss": 0.0644,
      "step": 1460
    },
    {
      "epoch": 46.74,
      "learning_rate": 0.0001,
      "loss": 0.0657,
      "step": 1465
    },
    {
      "epoch": 46.9,
      "learning_rate": 0.0001,
      "loss": 0.066,
      "step": 1470
    },
    {
      "epoch": 47.06,
      "learning_rate": 0.0001,
      "loss": 0.0648,
      "step": 1475
    },
    {
      "epoch": 47.22,
      "learning_rate": 0.0001,
      "loss": 0.0614,
      "step": 1480
    },
    {
      "epoch": 47.38,
      "learning_rate": 0.0001,
      "loss": 0.063,
      "step": 1485
    },
    {
      "epoch": 47.54,
      "learning_rate": 0.0001,
      "loss": 0.0651,
      "step": 1490
    },
    {
      "epoch": 47.7,
      "learning_rate": 0.0001,
      "loss": 0.0635,
      "step": 1495
    },
    {
      "epoch": 47.86,
      "learning_rate": 0.0001,
      "loss": 0.0637,
      "step": 1500
    },
    {
      "epoch": 48.02,
      "learning_rate": 0.0001,
      "loss": 0.0627,
      "step": 1505
    },
    {
      "epoch": 48.18,
      "learning_rate": 0.0001,
      "loss": 0.0602,
      "step": 1510
    },
    {
      "epoch": 48.33,
      "learning_rate": 0.0001,
      "loss": 0.0598,
      "step": 1515
    },
    {
      "epoch": 48.49,
      "learning_rate": 0.0001,
      "loss": 0.06,
      "step": 1520
    },
    {
      "epoch": 48.65,
      "learning_rate": 0.0001,
      "loss": 0.0607,
      "step": 1525
    },
    {
      "epoch": 48.81,
      "learning_rate": 0.0001,
      "loss": 0.063,
      "step": 1530
    },
    {
      "epoch": 48.97,
      "learning_rate": 0.0001,
      "loss": 0.0628,
      "step": 1535
    },
    {
      "epoch": 49.13,
      "learning_rate": 0.0001,
      "loss": 0.0584,
      "step": 1540
    },
    {
      "epoch": 49.29,
      "learning_rate": 0.0001,
      "loss": 0.0585,
      "step": 1545
    },
    {
      "epoch": 49.45,
      "learning_rate": 0.0001,
      "loss": 0.0599,
      "step": 1550
    },
    {
      "epoch": 49.61,
      "learning_rate": 0.0001,
      "loss": 0.0583,
      "step": 1555
    },
    {
      "epoch": 49.77,
      "learning_rate": 0.0001,
      "loss": 0.0601,
      "step": 1560
    },
    {
      "epoch": 49.93,
      "learning_rate": 0.0001,
      "loss": 0.0596,
      "step": 1565
    },
    {
      "epoch": 50.09,
      "learning_rate": 0.0001,
      "loss": 0.0588,
      "step": 1570
    },
    {
      "epoch": 50.25,
      "learning_rate": 0.0001,
      "loss": 0.0576,
      "step": 1575
    },
    {
      "epoch": 50.41,
      "learning_rate": 0.0001,
      "loss": 0.0564,
      "step": 1580
    },
    {
      "epoch": 50.57,
      "learning_rate": 0.0001,
      "loss": 0.0581,
      "step": 1585
    },
    {
      "epoch": 50.73,
      "learning_rate": 0.0001,
      "loss": 0.0583,
      "step": 1590
    },
    {
      "epoch": 50.89,
      "learning_rate": 0.0001,
      "loss": 0.0568,
      "step": 1595
    },
    {
      "epoch": 51.05,
      "learning_rate": 0.0001,
      "loss": 0.0586,
      "step": 1600
    },
    {
      "epoch": 51.21,
      "learning_rate": 0.0001,
      "loss": 0.0544,
      "step": 1605
    },
    {
      "epoch": 51.37,
      "learning_rate": 0.0001,
      "loss": 0.0553,
      "step": 1610
    },
    {
      "epoch": 51.53,
      "learning_rate": 0.0001,
      "loss": 0.0559,
      "step": 1615
    },
    {
      "epoch": 51.68,
      "learning_rate": 0.0001,
      "loss": 0.0553,
      "step": 1620
    },
    {
      "epoch": 51.84,
      "learning_rate": 0.0001,
      "loss": 0.0566,
      "step": 1625
    },
    {
      "epoch": 52.0,
      "learning_rate": 0.0001,
      "loss": 0.0576,
      "step": 1630
    },
    {
      "epoch": 52.16,
      "learning_rate": 0.0001,
      "loss": 0.0545,
      "step": 1635
    },
    {
      "epoch": 52.32,
      "learning_rate": 0.0001,
      "loss": 0.0552,
      "step": 1640
    },
    {
      "epoch": 52.48,
      "learning_rate": 0.0001,
      "loss": 0.0534,
      "step": 1645
    },
    {
      "epoch": 52.64,
      "learning_rate": 0.0001,
      "loss": 0.0535,
      "step": 1650
    },
    {
      "epoch": 52.8,
      "learning_rate": 0.0001,
      "loss": 0.0545,
      "step": 1655
    },
    {
      "epoch": 52.96,
      "learning_rate": 0.0001,
      "loss": 0.055,
      "step": 1660
    },
    {
      "epoch": 53.12,
      "learning_rate": 0.0001,
      "loss": 0.0526,
      "step": 1665
    },
    {
      "epoch": 53.28,
      "learning_rate": 0.0001,
      "loss": 0.0527,
      "step": 1670
    },
    {
      "epoch": 53.44,
      "learning_rate": 0.0001,
      "loss": 0.0521,
      "step": 1675
    },
    {
      "epoch": 53.6,
      "learning_rate": 0.0001,
      "loss": 0.0529,
      "step": 1680
    },
    {
      "epoch": 53.76,
      "learning_rate": 0.0001,
      "loss": 0.0531,
      "step": 1685
    },
    {
      "epoch": 53.92,
      "learning_rate": 0.0001,
      "loss": 0.0532,
      "step": 1690
    },
    {
      "epoch": 54.08,
      "learning_rate": 0.0001,
      "loss": 0.0524,
      "step": 1695
    },
    {
      "epoch": 54.24,
      "learning_rate": 0.0001,
      "loss": 0.0516,
      "step": 1700
    },
    {
      "epoch": 54.4,
      "learning_rate": 0.0001,
      "loss": 0.0496,
      "step": 1705
    },
    {
      "epoch": 54.56,
      "learning_rate": 0.0001,
      "loss": 0.0517,
      "step": 1710
    },
    {
      "epoch": 54.72,
      "learning_rate": 0.0001,
      "loss": 0.0528,
      "step": 1715
    },
    {
      "epoch": 54.88,
      "learning_rate": 0.0001,
      "loss": 0.0509,
      "step": 1720
    },
    {
      "epoch": 55.03,
      "learning_rate": 0.0001,
      "loss": 0.0503,
      "step": 1725
    },
    {
      "epoch": 55.19,
      "learning_rate": 0.0001,
      "loss": 0.0493,
      "step": 1730
    },
    {
      "epoch": 55.35,
      "learning_rate": 0.0001,
      "loss": 0.0492,
      "step": 1735
    },
    {
      "epoch": 55.51,
      "learning_rate": 0.0001,
      "loss": 0.0495,
      "step": 1740
    },
    {
      "epoch": 55.67,
      "learning_rate": 0.0001,
      "loss": 0.0491,
      "step": 1745
    },
    {
      "epoch": 55.83,
      "learning_rate": 0.0001,
      "loss": 0.0503,
      "step": 1750
    },
    {
      "epoch": 55.99,
      "learning_rate": 0.0001,
      "loss": 0.0516,
      "step": 1755
    },
    {
      "epoch": 56.15,
      "learning_rate": 0.0001,
      "loss": 0.0475,
      "step": 1760
    },
    {
      "epoch": 56.31,
      "learning_rate": 0.0001,
      "loss": 0.0493,
      "step": 1765
    },
    {
      "epoch": 56.47,
      "learning_rate": 0.0001,
      "loss": 0.0493,
      "step": 1770
    },
    {
      "epoch": 56.63,
      "learning_rate": 0.0001,
      "loss": 0.0484,
      "step": 1775
    },
    {
      "epoch": 56.79,
      "learning_rate": 0.0001,
      "loss": 0.0479,
      "step": 1780
    },
    {
      "epoch": 56.95,
      "learning_rate": 0.0001,
      "loss": 0.0488,
      "step": 1785
    },
    {
      "epoch": 57.11,
      "learning_rate": 0.0001,
      "loss": 0.0468,
      "step": 1790
    },
    {
      "epoch": 57.27,
      "learning_rate": 0.0001,
      "loss": 0.0479,
      "step": 1795
    },
    {
      "epoch": 57.43,
      "learning_rate": 0.0001,
      "loss": 0.0462,
      "step": 1800
    },
    {
      "epoch": 57.59,
      "learning_rate": 0.0001,
      "loss": 0.0488,
      "step": 1805
    },
    {
      "epoch": 57.75,
      "learning_rate": 0.0001,
      "loss": 0.0488,
      "step": 1810
    },
    {
      "epoch": 57.91,
      "learning_rate": 0.0001,
      "loss": 0.048,
      "step": 1815
    },
    {
      "epoch": 58.07,
      "learning_rate": 0.0001,
      "loss": 0.0474,
      "step": 1820
    },
    {
      "epoch": 58.23,
      "learning_rate": 0.0001,
      "loss": 0.0469,
      "step": 1825
    },
    {
      "epoch": 58.38,
      "learning_rate": 0.0001,
      "loss": 0.0456,
      "step": 1830
    },
    {
      "epoch": 58.54,
      "learning_rate": 0.0001,
      "loss": 0.0465,
      "step": 1835
    },
    {
      "epoch": 58.7,
      "learning_rate": 0.0001,
      "loss": 0.0475,
      "step": 1840
    },
    {
      "epoch": 58.86,
      "learning_rate": 0.0001,
      "loss": 0.0469,
      "step": 1845
    },
    {
      "epoch": 59.02,
      "learning_rate": 0.0001,
      "loss": 0.0472,
      "step": 1850
    },
    {
      "epoch": 59.18,
      "learning_rate": 0.0001,
      "loss": 0.0453,
      "step": 1855
    },
    {
      "epoch": 59.34,
      "learning_rate": 0.0001,
      "loss": 0.0464,
      "step": 1860
    },
    {
      "epoch": 59.5,
      "learning_rate": 0.0001,
      "loss": 0.0456,
      "step": 1865
    },
    {
      "epoch": 59.66,
      "learning_rate": 0.0001,
      "loss": 0.0463,
      "step": 1870
    },
    {
      "epoch": 59.82,
      "learning_rate": 0.0001,
      "loss": 0.0467,
      "step": 1875
    },
    {
      "epoch": 59.98,
      "learning_rate": 0.0001,
      "loss": 0.046,
      "step": 1880
    },
    {
      "epoch": 60.14,
      "learning_rate": 0.0001,
      "loss": 0.0444,
      "step": 1885
    },
    {
      "epoch": 60.3,
      "learning_rate": 0.0001,
      "loss": 0.0448,
      "step": 1890
    },
    {
      "epoch": 60.46,
      "learning_rate": 0.0001,
      "loss": 0.0441,
      "step": 1895
    },
    {
      "epoch": 60.62,
      "learning_rate": 0.0001,
      "loss": 0.0468,
      "step": 1900
    },
    {
      "epoch": 60.78,
      "learning_rate": 0.0001,
      "loss": 0.045,
      "step": 1905
    },
    {
      "epoch": 60.94,
      "learning_rate": 0.0001,
      "loss": 0.0454,
      "step": 1910
    },
    {
      "epoch": 61.1,
      "learning_rate": 0.0001,
      "loss": 0.0454,
      "step": 1915
    },
    {
      "epoch": 61.26,
      "learning_rate": 0.0001,
      "loss": 0.044,
      "step": 1920
    },
    {
      "epoch": 61.42,
      "learning_rate": 0.0001,
      "loss": 0.0451,
      "step": 1925
    },
    {
      "epoch": 61.58,
      "learning_rate": 0.0001,
      "loss": 0.0436,
      "step": 1930
    },
    {
      "epoch": 61.73,
      "learning_rate": 0.0001,
      "loss": 0.044,
      "step": 1935
    },
    {
      "epoch": 61.89,
      "learning_rate": 0.0001,
      "loss": 0.0444,
      "step": 1940
    },
    {
      "epoch": 62.05,
      "learning_rate": 0.0001,
      "loss": 0.043,
      "step": 1945
    },
    {
      "epoch": 62.21,
      "learning_rate": 0.0001,
      "loss": 0.0414,
      "step": 1950
    },
    {
      "epoch": 62.37,
      "learning_rate": 0.0001,
      "loss": 0.0417,
      "step": 1955
    },
    {
      "epoch": 62.53,
      "learning_rate": 0.0001,
      "loss": 0.0433,
      "step": 1960
    },
    {
      "epoch": 62.69,
      "learning_rate": 0.0001,
      "loss": 0.0437,
      "step": 1965
    },
    {
      "epoch": 62.85,
      "learning_rate": 0.0001,
      "loss": 0.0428,
      "step": 1970
    },
    {
      "epoch": 63.01,
      "learning_rate": 0.0001,
      "loss": 0.0437,
      "step": 1975
    },
    {
      "epoch": 63.17,
      "learning_rate": 0.0001,
      "loss": 0.042,
      "step": 1980
    },
    {
      "epoch": 63.33,
      "learning_rate": 0.0001,
      "loss": 0.0413,
      "step": 1985
    },
    {
      "epoch": 63.49,
      "learning_rate": 0.0001,
      "loss": 0.0426,
      "step": 1990
    },
    {
      "epoch": 63.65,
      "learning_rate": 0.0001,
      "loss": 0.042,
      "step": 1995
    },
    {
      "epoch": 63.81,
      "learning_rate": 0.0001,
      "loss": 0.0434,
      "step": 2000
    },
    {
      "epoch": 63.97,
      "learning_rate": 0.0001,
      "loss": 0.0429,
      "step": 2005
    },
    {
      "epoch": 64.13,
      "learning_rate": 0.0001,
      "loss": 0.0421,
      "step": 2010
    },
    {
      "epoch": 64.29,
      "learning_rate": 0.0001,
      "loss": 0.0411,
      "step": 2015
    },
    {
      "epoch": 64.45,
      "learning_rate": 0.0001,
      "loss": 0.0415,
      "step": 2020
    },
    {
      "epoch": 64.61,
      "learning_rate": 0.0001,
      "loss": 0.0401,
      "step": 2025
    },
    {
      "epoch": 64.77,
      "learning_rate": 0.0001,
      "loss": 0.0417,
      "step": 2030
    },
    {
      "epoch": 64.93,
      "learning_rate": 0.0001,
      "loss": 0.0418,
      "step": 2035
    },
    {
      "epoch": 65.08,
      "learning_rate": 0.0001,
      "loss": 0.0409,
      "step": 2040
    },
    {
      "epoch": 65.24,
      "learning_rate": 0.0001,
      "loss": 0.0404,
      "step": 2045
    },
    {
      "epoch": 65.4,
      "learning_rate": 0.0001,
      "loss": 0.0404,
      "step": 2050
    },
    {
      "epoch": 65.56,
      "learning_rate": 0.0001,
      "loss": 0.0403,
      "step": 2055
    },
    {
      "epoch": 65.72,
      "learning_rate": 0.0001,
      "loss": 0.0399,
      "step": 2060
    },
    {
      "epoch": 65.88,
      "learning_rate": 0.0001,
      "loss": 0.042,
      "step": 2065
    },
    {
      "epoch": 66.04,
      "learning_rate": 0.0001,
      "loss": 0.0397,
      "step": 2070
    },
    {
      "epoch": 66.2,
      "learning_rate": 0.0001,
      "loss": 0.0396,
      "step": 2075
    },
    {
      "epoch": 66.36,
      "learning_rate": 0.0001,
      "loss": 0.0387,
      "step": 2080
    },
    {
      "epoch": 66.52,
      "learning_rate": 0.0001,
      "loss": 0.0392,
      "step": 2085
    },
    {
      "epoch": 66.68,
      "learning_rate": 0.0001,
      "loss": 0.0407,
      "step": 2090
    },
    {
      "epoch": 66.84,
      "learning_rate": 0.0001,
      "loss": 0.0414,
      "step": 2095
    },
    {
      "epoch": 67.0,
      "learning_rate": 0.0001,
      "loss": 0.0407,
      "step": 2100
    },
    {
      "epoch": 67.16,
      "learning_rate": 0.0001,
      "loss": 0.0404,
      "step": 2105
    },
    {
      "epoch": 67.32,
      "learning_rate": 0.0001,
      "loss": 0.0382,
      "step": 2110
    },
    {
      "epoch": 67.48,
      "learning_rate": 0.0001,
      "loss": 0.0397,
      "step": 2115
    },
    {
      "epoch": 67.64,
      "learning_rate": 0.0001,
      "loss": 0.0392,
      "step": 2120
    },
    {
      "epoch": 67.8,
      "learning_rate": 0.0001,
      "loss": 0.0383,
      "step": 2125
    },
    {
      "epoch": 67.96,
      "learning_rate": 0.0001,
      "loss": 0.0397,
      "step": 2130
    },
    {
      "epoch": 68.12,
      "learning_rate": 0.0001,
      "loss": 0.0384,
      "step": 2135
    },
    {
      "epoch": 68.28,
      "learning_rate": 0.0001,
      "loss": 0.0376,
      "step": 2140
    },
    {
      "epoch": 68.43,
      "learning_rate": 0.0001,
      "loss": 0.0383,
      "step": 2145
    },
    {
      "epoch": 68.59,
      "learning_rate": 0.0001,
      "loss": 0.0393,
      "step": 2150
    },
    {
      "epoch": 68.75,
      "learning_rate": 0.0001,
      "loss": 0.0387,
      "step": 2155
    },
    {
      "epoch": 68.91,
      "learning_rate": 0.0001,
      "loss": 0.0382,
      "step": 2160
    },
    {
      "epoch": 69.07,
      "learning_rate": 0.0001,
      "loss": 0.0382,
      "step": 2165
    },
    {
      "epoch": 69.23,
      "learning_rate": 0.0001,
      "loss": 0.0376,
      "step": 2170
    },
    {
      "epoch": 69.39,
      "learning_rate": 0.0001,
      "loss": 0.0375,
      "step": 2175
    },
    {
      "epoch": 69.55,
      "learning_rate": 0.0001,
      "loss": 0.0382,
      "step": 2180
    },
    {
      "epoch": 69.71,
      "learning_rate": 0.0001,
      "loss": 0.0386,
      "step": 2185
    },
    {
      "epoch": 69.87,
      "learning_rate": 0.0001,
      "loss": 0.0373,
      "step": 2190
    },
    {
      "epoch": 70.03,
      "learning_rate": 0.0001,
      "loss": 0.0376,
      "step": 2195
    },
    {
      "epoch": 70.19,
      "learning_rate": 0.0001,
      "loss": 0.037,
      "step": 2200
    },
    {
      "epoch": 70.35,
      "learning_rate": 0.0001,
      "loss": 0.0368,
      "step": 2205
    },
    {
      "epoch": 70.51,
      "learning_rate": 0.0001,
      "loss": 0.036,
      "step": 2210
    },
    {
      "epoch": 70.67,
      "learning_rate": 0.0001,
      "loss": 0.0375,
      "step": 2215
    },
    {
      "epoch": 70.83,
      "learning_rate": 0.0001,
      "loss": 0.0368,
      "step": 2220
    },
    {
      "epoch": 70.99,
      "learning_rate": 0.0001,
      "loss": 0.038,
      "step": 2225
    },
    {
      "epoch": 71.15,
      "learning_rate": 0.0001,
      "loss": 0.0368,
      "step": 2230
    },
    {
      "epoch": 71.31,
      "learning_rate": 0.0001,
      "loss": 0.036,
      "step": 2235
    },
    {
      "epoch": 71.47,
      "learning_rate": 0.0001,
      "loss": 0.0367,
      "step": 2240
    },
    {
      "epoch": 71.63,
      "learning_rate": 0.0001,
      "loss": 0.0358,
      "step": 2245
    },
    {
      "epoch": 71.78,
      "learning_rate": 0.0001,
      "loss": 0.0363,
      "step": 2250
    },
    {
      "epoch": 71.94,
      "learning_rate": 0.0001,
      "loss": 0.0366,
      "step": 2255
    },
    {
      "epoch": 72.1,
      "learning_rate": 0.0001,
      "loss": 0.0356,
      "step": 2260
    },
    {
      "epoch": 72.26,
      "learning_rate": 0.0001,
      "loss": 0.0344,
      "step": 2265
    },
    {
      "epoch": 72.42,
      "learning_rate": 0.0001,
      "loss": 0.0366,
      "step": 2270
    },
    {
      "epoch": 72.58,
      "learning_rate": 0.0001,
      "loss": 0.0362,
      "step": 2275
    },
    {
      "epoch": 72.74,
      "learning_rate": 0.0001,
      "loss": 0.0354,
      "step": 2280
    },
    {
      "epoch": 72.9,
      "learning_rate": 0.0001,
      "loss": 0.0362,
      "step": 2285
    },
    {
      "epoch": 73.06,
      "learning_rate": 0.0001,
      "loss": 0.0358,
      "step": 2290
    },
    {
      "epoch": 73.22,
      "learning_rate": 0.0001,
      "loss": 0.035,
      "step": 2295
    },
    {
      "epoch": 73.38,
      "learning_rate": 0.0001,
      "loss": 0.0354,
      "step": 2300
    },
    {
      "epoch": 73.54,
      "learning_rate": 0.0001,
      "loss": 0.0357,
      "step": 2305
    },
    {
      "epoch": 73.7,
      "learning_rate": 0.0001,
      "loss": 0.0344,
      "step": 2310
    },
    {
      "epoch": 73.86,
      "learning_rate": 0.0001,
      "loss": 0.0348,
      "step": 2315
    },
    {
      "epoch": 74.02,
      "learning_rate": 0.0001,
      "loss": 0.0351,
      "step": 2320
    },
    {
      "epoch": 74.18,
      "learning_rate": 0.0001,
      "loss": 0.0339,
      "step": 2325
    },
    {
      "epoch": 74.18,
      "step": 2325,
      "total_flos": 2.773380910546944e+17,
      "train_loss": 0.22404980731266802,
      "train_runtime": 24311.8759,
      "train_samples_per_second": 3.094,
      "train_steps_per_second": 0.096
    }
  ],
  "logging_steps": 5,
  "max_steps": 2325,
  "num_train_epochs": 75,
  "save_steps": -2325,
  "total_flos": 2.773380910546944e+17,
  "trial_name": null,
  "trial_params": null
}