{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 34.628019323671495,
  "eval_steps": 500,
  "global_step": 2240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 2.2092,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.4086,
      "step": 10
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.1906,
      "step": 15
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.1447,
      "step": 20
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.1125,
      "step": 25
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.1011,
      "step": 30
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.0439,
      "step": 35
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.0341,
      "step": 40
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.0454,
      "step": 45
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.0261,
      "step": 50
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 1.0393,
      "step": 55
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 1.0407,
      "step": 60
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 0.9819,
      "step": 65
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 0.7776,
      "step": 70
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 0.742,
      "step": 75
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001,
      "loss": 0.7434,
      "step": 80
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001,
      "loss": 0.7963,
      "step": 85
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 0.7459,
      "step": 90
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 0.7714,
      "step": 95
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 0.7663,
      "step": 100
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001,
      "loss": 0.7458,
      "step": 105
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001,
      "loss": 0.7591,
      "step": 110
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 0.7567,
      "step": 115
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001,
      "loss": 0.7394,
      "step": 120
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001,
      "loss": 0.7631,
      "step": 125
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001,
      "loss": 0.7383,
      "step": 130
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 0.5741,
      "step": 135
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 0.5493,
      "step": 140
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001,
      "loss": 0.5863,
      "step": 145
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 0.5505,
      "step": 150
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001,
      "loss": 0.545,
      "step": 155
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 0.5583,
      "step": 160
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0001,
      "loss": 0.5454,
      "step": 165
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0001,
      "loss": 0.551,
      "step": 170
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001,
      "loss": 0.5609,
      "step": 175
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001,
      "loss": 0.5414,
      "step": 180
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001,
      "loss": 0.6485,
      "step": 185
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001,
      "loss": 0.5638,
      "step": 190
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0001,
      "loss": 0.5406,
      "step": 195
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001,
      "loss": 0.4256,
      "step": 200
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0001,
      "loss": 0.3931,
      "step": 205
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 0.4069,
      "step": 210
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0001,
      "loss": 0.4141,
      "step": 215
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001,
      "loss": 0.4716,
      "step": 220
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001,
      "loss": 0.4219,
      "step": 225
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001,
      "loss": 0.4143,
      "step": 230
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001,
      "loss": 0.4139,
      "step": 235
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0001,
      "loss": 0.4412,
      "step": 240
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0001,
      "loss": 0.4283,
      "step": 245
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0001,
      "loss": 0.4261,
      "step": 250
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0001,
      "loss": 0.4304,
      "step": 255
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001,
      "loss": 0.4093,
      "step": 260
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0001,
      "loss": 0.3088,
      "step": 265
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0001,
      "loss": 0.3017,
      "step": 270
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001,
      "loss": 0.3169,
      "step": 275
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0001,
      "loss": 0.3077,
      "step": 280
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001,
      "loss": 0.3131,
      "step": 285
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001,
      "loss": 0.3239,
      "step": 290
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001,
      "loss": 0.3428,
      "step": 295
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 0.3267,
      "step": 300
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0001,
      "loss": 0.3194,
      "step": 305
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001,
      "loss": 0.3276,
      "step": 310
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0001,
      "loss": 0.3314,
      "step": 315
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0001,
      "loss": 0.4401,
      "step": 320
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0001,
      "loss": 0.3017,
      "step": 325
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.0001,
      "loss": 0.2653,
      "step": 330
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0001,
      "loss": 0.293,
      "step": 335
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001,
      "loss": 0.2381,
      "step": 340
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0001,
      "loss": 0.245,
      "step": 345
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.0001,
      "loss": 0.2307,
      "step": 350
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0001,
      "loss": 0.2469,
      "step": 355
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001,
      "loss": 0.241,
      "step": 360
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.0001,
      "loss": 0.2494,
      "step": 365
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.0001,
      "loss": 0.2509,
      "step": 370
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0001,
      "loss": 0.2459,
      "step": 375
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.0001,
      "loss": 0.2524,
      "step": 380
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.0001,
      "loss": 0.2613,
      "step": 385
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.0001,
      "loss": 0.2321,
      "step": 390
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.0001,
      "loss": 0.1857,
      "step": 395
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.0001,
      "loss": 0.1834,
      "step": 400
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.0001,
      "loss": 0.1888,
      "step": 405
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.0001,
      "loss": 0.1857,
      "step": 410
    },
    {
      "epoch": 6.42,
      "learning_rate": 0.0001,
      "loss": 0.1901,
      "step": 415
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.0001,
      "loss": 0.2473,
      "step": 420
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.0001,
      "loss": 0.1957,
      "step": 425
    },
    {
      "epoch": 6.65,
      "learning_rate": 0.0001,
      "loss": 0.1991,
      "step": 430
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.0001,
      "loss": 0.2053,
      "step": 435
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.0001,
      "loss": 0.196,
      "step": 440
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.0001,
      "loss": 0.2074,
      "step": 445
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.0001,
      "loss": 0.2103,
      "step": 450
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.0001,
      "loss": 0.2051,
      "step": 455
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0001,
      "loss": 0.1453,
      "step": 460
    },
    {
      "epoch": 7.19,
      "learning_rate": 0.0001,
      "loss": 0.1502,
      "step": 465
    },
    {
      "epoch": 7.27,
      "learning_rate": 0.0001,
      "loss": 0.1432,
      "step": 470
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.0001,
      "loss": 0.1494,
      "step": 475
    },
    {
      "epoch": 7.42,
      "learning_rate": 0.0001,
      "loss": 0.1475,
      "step": 480
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.0001,
      "loss": 0.153,
      "step": 485
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.0001,
      "loss": 0.1525,
      "step": 490
    },
    {
      "epoch": 7.65,
      "learning_rate": 0.0001,
      "loss": 0.1604,
      "step": 495
    },
    {
      "epoch": 7.73,
      "learning_rate": 0.0001,
      "loss": 0.206,
      "step": 500
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.0001,
      "loss": 0.1656,
      "step": 505
    },
    {
      "epoch": 7.88,
      "learning_rate": 0.0001,
      "loss": 0.2155,
      "step": 510
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.0001,
      "loss": 0.1727,
      "step": 515
    },
    {
      "epoch": 8.04,
      "learning_rate": 0.0001,
      "loss": 0.1458,
      "step": 520
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.0001,
      "loss": 0.1598,
      "step": 525
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0001,
      "loss": 0.1173,
      "step": 530
    },
    {
      "epoch": 8.27,
      "learning_rate": 0.0001,
      "loss": 0.12,
      "step": 535
    },
    {
      "epoch": 8.35,
      "learning_rate": 0.0001,
      "loss": 0.1216,
      "step": 540
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.0001,
      "loss": 0.1242,
      "step": 545
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.0001,
      "loss": 0.126,
      "step": 550
    },
    {
      "epoch": 8.58,
      "learning_rate": 0.0001,
      "loss": 0.1706,
      "step": 555
    },
    {
      "epoch": 8.66,
      "learning_rate": 0.0001,
      "loss": 0.1386,
      "step": 560
    },
    {
      "epoch": 8.73,
      "learning_rate": 0.0001,
      "loss": 0.1341,
      "step": 565
    },
    {
      "epoch": 8.81,
      "learning_rate": 0.0001,
      "loss": 0.1466,
      "step": 570
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.0001,
      "loss": 0.1395,
      "step": 575
    },
    {
      "epoch": 8.97,
      "learning_rate": 0.0001,
      "loss": 0.1403,
      "step": 580
    },
    {
      "epoch": 9.04,
      "learning_rate": 0.0001,
      "loss": 0.1172,
      "step": 585
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.0001,
      "loss": 0.0994,
      "step": 590
    },
    {
      "epoch": 9.2,
      "learning_rate": 0.0001,
      "loss": 0.1263,
      "step": 595
    },
    {
      "epoch": 9.28,
      "learning_rate": 0.0001,
      "loss": 0.1073,
      "step": 600
    },
    {
      "epoch": 9.35,
      "learning_rate": 0.0001,
      "loss": 0.1062,
      "step": 605
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.0001,
      "loss": 0.1072,
      "step": 610
    },
    {
      "epoch": 9.51,
      "learning_rate": 0.0001,
      "loss": 0.129,
      "step": 615
    },
    {
      "epoch": 9.58,
      "learning_rate": 0.0001,
      "loss": 0.1103,
      "step": 620
    },
    {
      "epoch": 9.66,
      "learning_rate": 0.0001,
      "loss": 0.14,
      "step": 625
    },
    {
      "epoch": 9.74,
      "learning_rate": 0.0001,
      "loss": 0.1138,
      "step": 630
    },
    {
      "epoch": 9.82,
      "learning_rate": 0.0001,
      "loss": 0.1136,
      "step": 635
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.0001,
      "loss": 0.1161,
      "step": 640
    },
    {
      "epoch": 9.97,
      "learning_rate": 0.0001,
      "loss": 0.1126,
      "step": 645
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.0001,
      "loss": 0.0942,
      "step": 650
    },
    {
      "epoch": 10.13,
      "learning_rate": 0.0001,
      "loss": 0.1245,
      "step": 655
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.0001,
      "loss": 0.0892,
      "step": 660
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.0001,
      "loss": 0.1198,
      "step": 665
    },
    {
      "epoch": 10.36,
      "learning_rate": 0.0001,
      "loss": 0.0929,
      "step": 670
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.0001,
      "loss": 0.0923,
      "step": 675
    },
    {
      "epoch": 10.51,
      "learning_rate": 0.0001,
      "loss": 0.0962,
      "step": 680
    },
    {
      "epoch": 10.59,
      "learning_rate": 0.0001,
      "loss": 0.0945,
      "step": 685
    },
    {
      "epoch": 10.67,
      "learning_rate": 0.0001,
      "loss": 0.0986,
      "step": 690
    },
    {
      "epoch": 10.74,
      "learning_rate": 0.0001,
      "loss": 0.0982,
      "step": 695
    },
    {
      "epoch": 10.82,
      "learning_rate": 0.0001,
      "loss": 0.0982,
      "step": 700
    },
    {
      "epoch": 10.9,
      "learning_rate": 0.0001,
      "loss": 0.1011,
      "step": 705
    },
    {
      "epoch": 10.98,
      "learning_rate": 0.0001,
      "loss": 0.1037,
      "step": 710
    },
    {
      "epoch": 11.05,
      "learning_rate": 0.0001,
      "loss": 0.0817,
      "step": 715
    },
    {
      "epoch": 11.13,
      "learning_rate": 0.0001,
      "loss": 0.0979,
      "step": 720
    },
    {
      "epoch": 11.21,
      "learning_rate": 0.0001,
      "loss": 0.0738,
      "step": 725
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.0001,
      "loss": 0.0757,
      "step": 730
    },
    {
      "epoch": 11.36,
      "learning_rate": 0.0001,
      "loss": 0.0795,
      "step": 735
    },
    {
      "epoch": 11.44,
      "learning_rate": 0.0001,
      "loss": 0.0762,
      "step": 740
    },
    {
      "epoch": 11.52,
      "learning_rate": 0.0001,
      "loss": 0.0863,
      "step": 745
    },
    {
      "epoch": 11.59,
      "learning_rate": 0.0001,
      "loss": 0.0784,
      "step": 750
    },
    {
      "epoch": 11.67,
      "learning_rate": 0.0001,
      "loss": 0.0828,
      "step": 755
    },
    {
      "epoch": 11.75,
      "learning_rate": 0.0001,
      "loss": 0.0812,
      "step": 760
    },
    {
      "epoch": 11.83,
      "learning_rate": 0.0001,
      "loss": 0.0838,
      "step": 765
    },
    {
      "epoch": 11.9,
      "learning_rate": 0.0001,
      "loss": 0.089,
      "step": 770
    },
    {
      "epoch": 11.98,
      "learning_rate": 0.0001,
      "loss": 0.1106,
      "step": 775
    },
    {
      "epoch": 12.06,
      "learning_rate": 0.0001,
      "loss": 0.0737,
      "step": 780
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.0001,
      "loss": 0.0666,
      "step": 785
    },
    {
      "epoch": 12.21,
      "learning_rate": 0.0001,
      "loss": 0.0675,
      "step": 790
    },
    {
      "epoch": 12.29,
      "learning_rate": 0.0001,
      "loss": 0.0851,
      "step": 795
    },
    {
      "epoch": 12.37,
      "learning_rate": 0.0001,
      "loss": 0.0681,
      "step": 800
    },
    {
      "epoch": 12.44,
      "learning_rate": 0.0001,
      "loss": 0.0708,
      "step": 805
    },
    {
      "epoch": 12.52,
      "learning_rate": 0.0001,
      "loss": 0.0693,
      "step": 810
    },
    {
      "epoch": 12.6,
      "learning_rate": 0.0001,
      "loss": 0.0693,
      "step": 815
    },
    {
      "epoch": 12.68,
      "learning_rate": 0.0001,
      "loss": 0.1068,
      "step": 820
    },
    {
      "epoch": 12.75,
      "learning_rate": 0.0001,
      "loss": 0.07,
      "step": 825
    },
    {
      "epoch": 12.83,
      "learning_rate": 0.0001,
      "loss": 0.0871,
      "step": 830
    },
    {
      "epoch": 12.91,
      "learning_rate": 0.0001,
      "loss": 0.0743,
      "step": 835
    },
    {
      "epoch": 12.99,
      "learning_rate": 0.0001,
      "loss": 0.0722,
      "step": 840
    },
    {
      "epoch": 13.06,
      "learning_rate": 0.0001,
      "loss": 0.0593,
      "step": 845
    },
    {
      "epoch": 13.14,
      "learning_rate": 0.0001,
      "loss": 0.0549,
      "step": 850
    },
    {
      "epoch": 13.22,
      "learning_rate": 0.0001,
      "loss": 0.0548,
      "step": 855
    },
    {
      "epoch": 13.29,
      "learning_rate": 0.0001,
      "loss": 0.0582,
      "step": 860
    },
    {
      "epoch": 13.37,
      "learning_rate": 0.0001,
      "loss": 0.0579,
      "step": 865
    },
    {
      "epoch": 13.45,
      "learning_rate": 0.0001,
      "loss": 0.0601,
      "step": 870
    },
    {
      "epoch": 13.53,
      "learning_rate": 0.0001,
      "loss": 0.0576,
      "step": 875
    },
    {
      "epoch": 13.6,
      "learning_rate": 0.0001,
      "loss": 0.0594,
      "step": 880
    },
    {
      "epoch": 13.68,
      "learning_rate": 0.0001,
      "loss": 0.0605,
      "step": 885
    },
    {
      "epoch": 13.76,
      "learning_rate": 0.0001,
      "loss": 0.0732,
      "step": 890
    },
    {
      "epoch": 13.84,
      "learning_rate": 0.0001,
      "loss": 0.0652,
      "step": 895
    },
    {
      "epoch": 13.91,
      "learning_rate": 0.0001,
      "loss": 0.0628,
      "step": 900
    },
    {
      "epoch": 13.99,
      "learning_rate": 0.0001,
      "loss": 0.09,
      "step": 905
    },
    {
      "epoch": 14.07,
      "learning_rate": 0.0001,
      "loss": 0.0564,
      "step": 910
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.0001,
      "loss": 0.0481,
      "step": 915
    },
    {
      "epoch": 14.22,
      "learning_rate": 0.0001,
      "loss": 0.048,
      "step": 920
    },
    {
      "epoch": 14.3,
      "learning_rate": 0.0001,
      "loss": 0.0468,
      "step": 925
    },
    {
      "epoch": 14.38,
      "learning_rate": 0.0001,
      "loss": 0.0989,
      "step": 930
    },
    {
      "epoch": 14.45,
      "learning_rate": 0.0001,
      "loss": 0.0497,
      "step": 935
    },
    {
      "epoch": 14.53,
      "learning_rate": 0.0001,
      "loss": 0.0495,
      "step": 940
    },
    {
      "epoch": 14.61,
      "learning_rate": 0.0001,
      "loss": 0.0499,
      "step": 945
    },
    {
      "epoch": 14.69,
      "learning_rate": 0.0001,
      "loss": 0.049,
      "step": 950
    },
    {
      "epoch": 14.76,
      "learning_rate": 0.0001,
      "loss": 0.0629,
      "step": 955
    },
    {
      "epoch": 14.84,
      "learning_rate": 0.0001,
      "loss": 0.0536,
      "step": 960
    },
    {
      "epoch": 14.92,
      "learning_rate": 0.0001,
      "loss": 0.0515,
      "step": 965
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.0001,
      "loss": 0.0679,
      "step": 970
    },
    {
      "epoch": 15.07,
      "learning_rate": 0.0001,
      "loss": 0.04,
      "step": 975
    },
    {
      "epoch": 15.15,
      "learning_rate": 0.0001,
      "loss": 0.0596,
      "step": 980
    },
    {
      "epoch": 15.23,
      "learning_rate": 0.0001,
      "loss": 0.0742,
      "step": 985
    },
    {
      "epoch": 15.3,
      "learning_rate": 0.0001,
      "loss": 0.0693,
      "step": 990
    },
    {
      "epoch": 15.38,
      "learning_rate": 0.0001,
      "loss": 0.0414,
      "step": 995
    },
    {
      "epoch": 15.46,
      "learning_rate": 0.0001,
      "loss": 0.0442,
      "step": 1000
    },
    {
      "epoch": 15.54,
      "learning_rate": 0.0001,
      "loss": 0.0409,
      "step": 1005
    },
    {
      "epoch": 15.61,
      "learning_rate": 0.0001,
      "loss": 0.04,
      "step": 1010
    },
    {
      "epoch": 15.69,
      "learning_rate": 0.0001,
      "loss": 0.0414,
      "step": 1015
    },
    {
      "epoch": 15.77,
      "learning_rate": 0.0001,
      "loss": 0.0393,
      "step": 1020
    },
    {
      "epoch": 15.85,
      "learning_rate": 0.0001,
      "loss": 0.0398,
      "step": 1025
    },
    {
      "epoch": 15.92,
      "learning_rate": 0.0001,
      "loss": 0.0411,
      "step": 1030
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0001,
      "loss": 0.0407,
      "step": 1035
    },
    {
      "epoch": 16.08,
      "learning_rate": 0.0001,
      "loss": 0.0305,
      "step": 1040
    },
    {
      "epoch": 16.15,
      "learning_rate": 0.0001,
      "loss": 0.0338,
      "step": 1045
    },
    {
      "epoch": 16.23,
      "learning_rate": 0.0001,
      "loss": 0.0324,
      "step": 1050
    },
    {
      "epoch": 16.31,
      "learning_rate": 0.0001,
      "loss": 0.0326,
      "step": 1055
    },
    {
      "epoch": 16.39,
      "learning_rate": 0.0001,
      "loss": 0.0314,
      "step": 1060
    },
    {
      "epoch": 16.46,
      "learning_rate": 0.0001,
      "loss": 0.0332,
      "step": 1065
    },
    {
      "epoch": 16.54,
      "learning_rate": 0.0001,
      "loss": 0.0329,
      "step": 1070
    },
    {
      "epoch": 16.62,
      "learning_rate": 0.0001,
      "loss": 0.0406,
      "step": 1075
    },
    {
      "epoch": 16.7,
      "learning_rate": 0.0001,
      "loss": 0.0324,
      "step": 1080
    },
    {
      "epoch": 16.77,
      "learning_rate": 0.0001,
      "loss": 0.0324,
      "step": 1085
    },
    {
      "epoch": 16.85,
      "learning_rate": 0.0001,
      "loss": 0.0721,
      "step": 1090
    },
    {
      "epoch": 16.93,
      "learning_rate": 0.0001,
      "loss": 0.0344,
      "step": 1095
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.0001,
      "loss": 0.0333,
      "step": 1100
    },
    {
      "epoch": 17.08,
      "learning_rate": 0.0001,
      "loss": 0.029,
      "step": 1105
    },
    {
      "epoch": 17.16,
      "learning_rate": 0.0001,
      "loss": 0.028,
      "step": 1110
    },
    {
      "epoch": 17.24,
      "learning_rate": 0.0001,
      "loss": 0.0288,
      "step": 1115
    },
    {
      "epoch": 17.31,
      "learning_rate": 0.0001,
      "loss": 0.0274,
      "step": 1120
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.0001,
      "loss": 0.0278,
      "step": 1125
    },
    {
      "epoch": 17.47,
      "learning_rate": 0.0001,
      "loss": 0.0288,
      "step": 1130
    },
    {
      "epoch": 17.55,
      "learning_rate": 0.0001,
      "loss": 0.0414,
      "step": 1135
    },
    {
      "epoch": 17.62,
      "learning_rate": 0.0001,
      "loss": 0.0322,
      "step": 1140
    },
    {
      "epoch": 17.7,
      "learning_rate": 0.0001,
      "loss": 0.0303,
      "step": 1145
    },
    {
      "epoch": 17.78,
      "learning_rate": 0.0001,
      "loss": 0.0291,
      "step": 1150
    },
    {
      "epoch": 17.86,
      "learning_rate": 0.0001,
      "loss": 0.0411,
      "step": 1155
    },
    {
      "epoch": 17.93,
      "learning_rate": 0.0001,
      "loss": 0.0282,
      "step": 1160
    },
    {
      "epoch": 18.01,
      "learning_rate": 0.0001,
      "loss": 0.0285,
      "step": 1165
    },
    {
      "epoch": 18.09,
      "learning_rate": 0.0001,
      "loss": 0.0227,
      "step": 1170
    },
    {
      "epoch": 18.16,
      "learning_rate": 0.0001,
      "loss": 0.0232,
      "step": 1175
    },
    {
      "epoch": 18.24,
      "learning_rate": 0.0001,
      "loss": 0.0228,
      "step": 1180
    },
    {
      "epoch": 18.32,
      "learning_rate": 0.0001,
      "loss": 0.0332,
      "step": 1185
    },
    {
      "epoch": 18.4,
      "learning_rate": 0.0001,
      "loss": 0.0226,
      "step": 1190
    },
    {
      "epoch": 18.47,
      "learning_rate": 0.0001,
      "loss": 0.0367,
      "step": 1195
    },
    {
      "epoch": 18.55,
      "learning_rate": 0.0001,
      "loss": 0.0255,
      "step": 1200
    },
    {
      "epoch": 18.63,
      "learning_rate": 0.0001,
      "loss": 0.0354,
      "step": 1205
    },
    {
      "epoch": 18.71,
      "learning_rate": 0.0001,
      "loss": 0.0238,
      "step": 1210
    },
    {
      "epoch": 18.78,
      "learning_rate": 0.0001,
      "loss": 0.0262,
      "step": 1215
    },
    {
      "epoch": 18.86,
      "learning_rate": 0.0001,
      "loss": 0.0243,
      "step": 1220
    },
    {
      "epoch": 18.94,
      "learning_rate": 0.0001,
      "loss": 0.0241,
      "step": 1225
    },
    {
      "epoch": 19.01,
      "learning_rate": 0.0001,
      "loss": 0.0237,
      "step": 1230
    },
    {
      "epoch": 19.09,
      "learning_rate": 0.0001,
      "loss": 0.0207,
      "step": 1235
    },
    {
      "epoch": 19.17,
      "learning_rate": 0.0001,
      "loss": 0.0223,
      "step": 1240
    },
    {
      "epoch": 19.25,
      "learning_rate": 0.0001,
      "loss": 0.02,
      "step": 1245
    },
    {
      "epoch": 19.32,
      "learning_rate": 0.0001,
      "loss": 0.0205,
      "step": 1250
    },
    {
      "epoch": 19.4,
      "learning_rate": 0.0001,
      "loss": 0.0204,
      "step": 1255
    },
    {
      "epoch": 19.48,
      "learning_rate": 0.0001,
      "loss": 0.0195,
      "step": 1260
    },
    {
      "epoch": 19.56,
      "learning_rate": 0.0001,
      "loss": 0.0205,
      "step": 1265
    },
    {
      "epoch": 19.63,
      "learning_rate": 0.0001,
      "loss": 0.0222,
      "step": 1270
    },
    {
      "epoch": 19.71,
      "learning_rate": 0.0001,
      "loss": 0.0473,
      "step": 1275
    },
    {
      "epoch": 19.79,
      "learning_rate": 0.0001,
      "loss": 0.0216,
      "step": 1280
    },
    {
      "epoch": 19.86,
      "learning_rate": 0.0001,
      "loss": 0.0242,
      "step": 1285
    },
    {
      "epoch": 19.94,
      "learning_rate": 0.0001,
      "loss": 0.0209,
      "step": 1290
    },
    {
      "epoch": 20.02,
      "learning_rate": 0.0001,
      "loss": 0.0212,
      "step": 1295
    },
    {
      "epoch": 20.1,
      "learning_rate": 0.0001,
      "loss": 0.0243,
      "step": 1300
    },
    {
      "epoch": 20.17,
      "learning_rate": 0.0001,
      "loss": 0.0205,
      "step": 1305
    },
    {
      "epoch": 20.25,
      "learning_rate": 0.0001,
      "loss": 0.0197,
      "step": 1310
    },
    {
      "epoch": 20.33,
      "learning_rate": 0.0001,
      "loss": 0.0191,
      "step": 1315
    },
    {
      "epoch": 20.41,
      "learning_rate": 0.0001,
      "loss": 0.0186,
      "step": 1320
    },
    {
      "epoch": 20.48,
      "learning_rate": 0.0001,
      "loss": 0.0264,
      "step": 1325
    },
    {
      "epoch": 20.56,
      "learning_rate": 0.0001,
      "loss": 0.0194,
      "step": 1330
    },
    {
      "epoch": 20.64,
      "learning_rate": 0.0001,
      "loss": 0.0206,
      "step": 1335
    },
    {
      "epoch": 20.71,
      "learning_rate": 0.0001,
      "loss": 0.0203,
      "step": 1340
    },
    {
      "epoch": 20.79,
      "learning_rate": 0.0001,
      "loss": 0.019,
      "step": 1345
    },
    {
      "epoch": 20.87,
      "learning_rate": 0.0001,
      "loss": 0.0191,
      "step": 1350
    },
    {
      "epoch": 20.95,
      "learning_rate": 0.0001,
      "loss": 0.0262,
      "step": 1355
    },
    {
      "epoch": 21.02,
      "learning_rate": 0.0001,
      "loss": 0.0293,
      "step": 1360
    },
    {
      "epoch": 21.1,
      "learning_rate": 0.0001,
      "loss": 0.0169,
      "step": 1365
    },
    {
      "epoch": 21.18,
      "learning_rate": 0.0001,
      "loss": 0.0175,
      "step": 1370
    },
    {
      "epoch": 21.26,
      "learning_rate": 0.0001,
      "loss": 0.0175,
      "step": 1375
    },
    {
      "epoch": 21.33,
      "learning_rate": 0.0001,
      "loss": 0.0179,
      "step": 1380
    },
    {
      "epoch": 21.41,
      "learning_rate": 0.0001,
      "loss": 0.017,
      "step": 1385
    },
    {
      "epoch": 21.49,
      "learning_rate": 0.0001,
      "loss": 0.0211,
      "step": 1390
    },
    {
      "epoch": 21.57,
      "learning_rate": 0.0001,
      "loss": 0.0169,
      "step": 1395
    },
    {
      "epoch": 21.64,
      "learning_rate": 0.0001,
      "loss": 0.0168,
      "step": 1400
    },
    {
      "epoch": 21.72,
      "learning_rate": 0.0001,
      "loss": 0.0164,
      "step": 1405
    },
    {
      "epoch": 21.8,
      "learning_rate": 0.0001,
      "loss": 0.0298,
      "step": 1410
    },
    {
      "epoch": 21.87,
      "learning_rate": 0.0001,
      "loss": 0.02,
      "step": 1415
    },
    {
      "epoch": 21.95,
      "learning_rate": 0.0001,
      "loss": 0.0235,
      "step": 1420
    },
    {
      "epoch": 22.03,
      "learning_rate": 0.0001,
      "loss": 0.018,
      "step": 1425
    },
    {
      "epoch": 22.11,
      "learning_rate": 0.0001,
      "loss": 0.0164,
      "step": 1430
    },
    {
      "epoch": 22.18,
      "learning_rate": 0.0001,
      "loss": 0.0225,
      "step": 1435
    },
    {
      "epoch": 22.26,
      "learning_rate": 0.0001,
      "loss": 0.0167,
      "step": 1440
    },
    {
      "epoch": 22.34,
      "learning_rate": 0.0001,
      "loss": 0.024,
      "step": 1445
    },
    {
      "epoch": 22.42,
      "learning_rate": 0.0001,
      "loss": 0.0161,
      "step": 1450
    },
    {
      "epoch": 22.49,
      "learning_rate": 0.0001,
      "loss": 0.0224,
      "step": 1455
    },
    {
      "epoch": 22.57,
      "learning_rate": 0.0001,
      "loss": 0.0203,
      "step": 1460
    },
    {
      "epoch": 22.65,
      "learning_rate": 0.0001,
      "loss": 0.0169,
      "step": 1465
    },
    {
      "epoch": 22.72,
      "learning_rate": 0.0001,
      "loss": 0.0166,
      "step": 1470
    },
    {
      "epoch": 22.8,
      "learning_rate": 0.0001,
      "loss": 0.0163,
      "step": 1475
    },
    {
      "epoch": 22.88,
      "learning_rate": 0.0001,
      "loss": 0.0165,
      "step": 1480
    },
    {
      "epoch": 22.96,
      "learning_rate": 0.0001,
      "loss": 0.0155,
      "step": 1485
    },
    {
      "epoch": 23.03,
      "learning_rate": 0.0001,
      "loss": 0.0164,
      "step": 1490
    },
    {
      "epoch": 23.11,
      "learning_rate": 0.0001,
      "loss": 0.0148,
      "step": 1495
    },
    {
      "epoch": 23.19,
      "learning_rate": 0.0001,
      "loss": 0.0151,
      "step": 1500
    },
    {
      "epoch": 23.27,
      "learning_rate": 0.0001,
      "loss": 0.0176,
      "step": 1505
    },
    {
      "epoch": 23.34,
      "learning_rate": 0.0001,
      "loss": 0.0418,
      "step": 1510
    },
    {
      "epoch": 23.42,
      "learning_rate": 0.0001,
      "loss": 0.0155,
      "step": 1515
    },
    {
      "epoch": 23.5,
      "learning_rate": 0.0001,
      "loss": 0.0163,
      "step": 1520
    },
    {
      "epoch": 23.57,
      "learning_rate": 0.0001,
      "loss": 0.0161,
      "step": 1525
    },
    {
      "epoch": 23.65,
      "learning_rate": 0.0001,
      "loss": 0.0157,
      "step": 1530
    },
    {
      "epoch": 23.73,
      "learning_rate": 0.0001,
      "loss": 0.0219,
      "step": 1535
    },
    {
      "epoch": 23.81,
      "learning_rate": 0.0001,
      "loss": 0.0154,
      "step": 1540
    },
    {
      "epoch": 23.88,
      "learning_rate": 0.0001,
      "loss": 0.0149,
      "step": 1545
    },
    {
      "epoch": 23.96,
      "learning_rate": 0.0001,
      "loss": 0.0151,
      "step": 1550
    },
    {
      "epoch": 24.04,
      "learning_rate": 0.0001,
      "loss": 0.0138,
      "step": 1555
    },
    {
      "epoch": 24.12,
      "learning_rate": 0.0001,
      "loss": 0.0134,
      "step": 1560
    },
    {
      "epoch": 24.19,
      "learning_rate": 0.0001,
      "loss": 0.0349,
      "step": 1565
    },
    {
      "epoch": 24.27,
      "learning_rate": 0.0001,
      "loss": 0.0139,
      "step": 1570
    },
    {
      "epoch": 24.35,
      "learning_rate": 0.0001,
      "loss": 0.0138,
      "step": 1575
    },
    {
      "epoch": 24.43,
      "learning_rate": 0.0001,
      "loss": 0.014,
      "step": 1580
    },
    {
      "epoch": 24.5,
      "learning_rate": 0.0001,
      "loss": 0.0139,
      "step": 1585
    },
    {
      "epoch": 24.58,
      "learning_rate": 0.0001,
      "loss": 0.0137,
      "step": 1590
    },
    {
      "epoch": 24.66,
      "learning_rate": 0.0001,
      "loss": 0.0132,
      "step": 1595
    },
    {
      "epoch": 24.73,
      "learning_rate": 0.0001,
      "loss": 0.0133,
      "step": 1600
    },
    {
      "epoch": 24.81,
      "learning_rate": 0.0001,
      "loss": 0.027,
      "step": 1605
    },
    {
      "epoch": 24.89,
      "learning_rate": 0.0001,
      "loss": 0.0135,
      "step": 1610
    },
    {
      "epoch": 24.97,
      "learning_rate": 0.0001,
      "loss": 0.0141,
      "step": 1615
    },
    {
      "epoch": 25.04,
      "learning_rate": 0.0001,
      "loss": 0.0135,
      "step": 1620
    },
    {
      "epoch": 25.12,
      "learning_rate": 0.0001,
      "loss": 0.0119,
      "step": 1625
    },
    {
      "epoch": 25.2,
      "learning_rate": 0.0001,
      "loss": 0.0197,
      "step": 1630
    },
    {
      "epoch": 25.28,
      "learning_rate": 0.0001,
      "loss": 0.012,
      "step": 1635
    },
    {
      "epoch": 25.35,
      "learning_rate": 0.0001,
      "loss": 0.0119,
      "step": 1640
    },
    {
      "epoch": 25.43,
      "learning_rate": 0.0001,
      "loss": 0.0124,
      "step": 1645
    },
    {
      "epoch": 25.51,
      "learning_rate": 0.0001,
      "loss": 0.0121,
      "step": 1650
    },
    {
      "epoch": 25.58,
      "learning_rate": 0.0001,
      "loss": 0.0173,
      "step": 1655
    },
    {
      "epoch": 25.66,
      "learning_rate": 0.0001,
      "loss": 0.0153,
      "step": 1660
    },
    {
      "epoch": 25.74,
      "learning_rate": 0.0001,
      "loss": 0.0127,
      "step": 1665
    },
    {
      "epoch": 25.82,
      "learning_rate": 0.0001,
      "loss": 0.0125,
      "step": 1670
    },
    {
      "epoch": 25.89,
      "learning_rate": 0.0001,
      "loss": 0.0124,
      "step": 1675
    },
    {
      "epoch": 25.97,
      "learning_rate": 0.0001,
      "loss": 0.0146,
      "step": 1680
    },
    {
      "epoch": 26.05,
      "learning_rate": 0.0001,
      "loss": 0.0169,
      "step": 1685
    },
    {
      "epoch": 26.13,
      "learning_rate": 0.0001,
      "loss": 0.0137,
      "step": 1690
    },
    {
      "epoch": 26.2,
      "learning_rate": 0.0001,
      "loss": 0.0147,
      "step": 1695
    },
    {
      "epoch": 26.28,
      "learning_rate": 0.0001,
      "loss": 0.0116,
      "step": 1700
    },
    {
      "epoch": 26.36,
      "learning_rate": 0.0001,
      "loss": 0.0135,
      "step": 1705
    },
    {
      "epoch": 26.43,
      "learning_rate": 0.0001,
      "loss": 0.0129,
      "step": 1710
    },
    {
      "epoch": 26.51,
      "learning_rate": 0.0001,
      "loss": 0.0124,
      "step": 1715
    },
    {
      "epoch": 26.59,
      "learning_rate": 0.0001,
      "loss": 0.0115,
      "step": 1720
    },
    {
      "epoch": 26.67,
      "learning_rate": 0.0001,
      "loss": 0.0119,
      "step": 1725
    },
    {
      "epoch": 26.74,
      "learning_rate": 0.0001,
      "loss": 0.0118,
      "step": 1730
    },
    {
      "epoch": 26.82,
      "learning_rate": 0.0001,
      "loss": 0.0123,
      "step": 1735
    },
    {
      "epoch": 26.9,
      "learning_rate": 0.0001,
      "loss": 0.0114,
      "step": 1740
    },
    {
      "epoch": 26.98,
      "learning_rate": 0.0001,
      "loss": 0.0119,
      "step": 1745
    },
    {
      "epoch": 27.05,
      "learning_rate": 0.0001,
      "loss": 0.011,
      "step": 1750
    },
    {
      "epoch": 27.13,
      "learning_rate": 0.0001,
      "loss": 0.0122,
      "step": 1755
    },
    {
      "epoch": 27.21,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 1760
    },
    {
      "epoch": 27.29,
      "learning_rate": 0.0001,
      "loss": 0.011,
      "step": 1765
    },
    {
      "epoch": 27.36,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 1770
    },
    {
      "epoch": 27.44,
      "learning_rate": 0.0001,
      "loss": 0.0105,
      "step": 1775
    },
    {
      "epoch": 27.52,
      "learning_rate": 0.0001,
      "loss": 0.0106,
      "step": 1780
    },
    {
      "epoch": 27.59,
      "learning_rate": 0.0001,
      "loss": 0.0138,
      "step": 1785
    },
    {
      "epoch": 27.67,
      "learning_rate": 0.0001,
      "loss": 0.0129,
      "step": 1790
    },
    {
      "epoch": 27.75,
      "learning_rate": 0.0001,
      "loss": 0.0109,
      "step": 1795
    },
    {
      "epoch": 27.83,
      "learning_rate": 0.0001,
      "loss": 0.0108,
      "step": 1800
    },
    {
      "epoch": 27.9,
      "learning_rate": 0.0001,
      "loss": 0.0108,
      "step": 1805
    },
    {
      "epoch": 27.98,
      "learning_rate": 0.0001,
      "loss": 0.0109,
      "step": 1810
    },
    {
      "epoch": 28.06,
      "learning_rate": 0.0001,
      "loss": 0.0098,
      "step": 1815
    },
    {
      "epoch": 28.14,
      "learning_rate": 0.0001,
      "loss": 0.0127,
      "step": 1820
    },
    {
      "epoch": 28.21,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 1825
    },
    {
      "epoch": 28.29,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 1830
    },
    {
      "epoch": 28.37,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 1835
    },
    {
      "epoch": 28.44,
      "learning_rate": 0.0001,
      "loss": 0.0101,
      "step": 1840
    },
    {
      "epoch": 28.52,
      "learning_rate": 0.0001,
      "loss": 0.0105,
      "step": 1845
    },
    {
      "epoch": 28.6,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 1850
    },
    {
      "epoch": 28.68,
      "learning_rate": 0.0001,
      "loss": 0.0101,
      "step": 1855
    },
    {
      "epoch": 28.75,
      "learning_rate": 0.0001,
      "loss": 0.0103,
      "step": 1860
    },
    {
      "epoch": 28.83,
      "learning_rate": 0.0001,
      "loss": 0.0103,
      "step": 1865
    },
    {
      "epoch": 28.91,
      "learning_rate": 0.0001,
      "loss": 0.0139,
      "step": 1870
    },
    {
      "epoch": 28.99,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 1875
    },
    {
      "epoch": 29.06,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 1880
    },
    {
      "epoch": 29.14,
      "learning_rate": 0.0001,
      "loss": 0.01,
      "step": 1885
    },
    {
      "epoch": 29.22,
      "learning_rate": 0.0001,
      "loss": 0.009,
      "step": 1890
    },
    {
      "epoch": 29.29,
      "learning_rate": 0.0001,
      "loss": 0.0097,
      "step": 1895
    },
    {
      "epoch": 29.37,
      "learning_rate": 0.0001,
      "loss": 0.0094,
      "step": 1900
    },
    {
      "epoch": 29.45,
      "learning_rate": 0.0001,
      "loss": 0.0311,
      "step": 1905
    },
    {
      "epoch": 29.53,
      "learning_rate": 0.0001,
      "loss": 0.0101,
      "step": 1910
    },
    {
      "epoch": 29.6,
      "learning_rate": 0.0001,
      "loss": 0.0103,
      "step": 1915
    },
    {
      "epoch": 29.68,
      "learning_rate": 0.0001,
      "loss": 0.012,
      "step": 1920
    },
    {
      "epoch": 29.76,
      "learning_rate": 0.0001,
      "loss": 0.01,
      "step": 1925
    },
    {
      "epoch": 29.84,
      "learning_rate": 0.0001,
      "loss": 0.0112,
      "step": 1930
    },
    {
      "epoch": 29.91,
      "learning_rate": 0.0001,
      "loss": 0.0101,
      "step": 1935
    },
    {
      "epoch": 29.99,
      "learning_rate": 0.0001,
      "loss": 0.0105,
      "step": 1940
    },
    {
      "epoch": 30.07,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 1945
    },
    {
      "epoch": 30.14,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 1950
    },
    {
      "epoch": 30.22,
      "learning_rate": 0.0001,
      "loss": 0.0089,
      "step": 1955
    },
    {
      "epoch": 30.3,
      "learning_rate": 0.0001,
      "loss": 0.0101,
      "step": 1960
    },
    {
      "epoch": 30.38,
      "learning_rate": 0.0001,
      "loss": 0.0094,
      "step": 1965
    },
    {
      "epoch": 30.45,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 1970
    },
    {
      "epoch": 30.53,
      "learning_rate": 0.0001,
      "loss": 0.0094,
      "step": 1975
    },
    {
      "epoch": 30.61,
      "learning_rate": 0.0001,
      "loss": 0.0197,
      "step": 1980
    },
    {
      "epoch": 30.69,
      "learning_rate": 0.0001,
      "loss": 0.0103,
      "step": 1985
    },
    {
      "epoch": 30.76,
      "learning_rate": 0.0001,
      "loss": 0.0107,
      "step": 1990
    },
    {
      "epoch": 30.84,
      "learning_rate": 0.0001,
      "loss": 0.01,
      "step": 1995
    },
    {
      "epoch": 30.92,
      "learning_rate": 0.0001,
      "loss": 0.0112,
      "step": 2000
    },
    {
      "epoch": 31.0,
      "learning_rate": 0.0001,
      "loss": 0.0104,
      "step": 2005
    },
    {
      "epoch": 31.07,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 2010
    },
    {
      "epoch": 31.15,
      "learning_rate": 0.0001,
      "loss": 0.0089,
      "step": 2015
    },
    {
      "epoch": 31.23,
      "learning_rate": 0.0001,
      "loss": 0.0085,
      "step": 2020
    },
    {
      "epoch": 31.3,
      "learning_rate": 0.0001,
      "loss": 0.0092,
      "step": 2025
    },
    {
      "epoch": 31.38,
      "learning_rate": 0.0001,
      "loss": 0.0087,
      "step": 2030
    },
    {
      "epoch": 31.46,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2035
    },
    {
      "epoch": 31.54,
      "learning_rate": 0.0001,
      "loss": 0.01,
      "step": 2040
    },
    {
      "epoch": 31.61,
      "learning_rate": 0.0001,
      "loss": 0.0088,
      "step": 2045
    },
    {
      "epoch": 31.69,
      "learning_rate": 0.0001,
      "loss": 0.0099,
      "step": 2050
    },
    {
      "epoch": 31.77,
      "learning_rate": 0.0001,
      "loss": 0.0211,
      "step": 2055
    },
    {
      "epoch": 31.85,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 2060
    },
    {
      "epoch": 31.92,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2065
    },
    {
      "epoch": 32.0,
      "learning_rate": 0.0001,
      "loss": 0.01,
      "step": 2070
    },
    {
      "epoch": 32.08,
      "learning_rate": 0.0001,
      "loss": 0.0089,
      "step": 2075
    },
    {
      "epoch": 32.15,
      "learning_rate": 0.0001,
      "loss": 0.0088,
      "step": 2080
    },
    {
      "epoch": 32.23,
      "learning_rate": 0.0001,
      "loss": 0.0082,
      "step": 2085
    },
    {
      "epoch": 32.31,
      "learning_rate": 0.0001,
      "loss": 0.0084,
      "step": 2090
    },
    {
      "epoch": 32.39,
      "learning_rate": 0.0001,
      "loss": 0.0084,
      "step": 2095
    },
    {
      "epoch": 32.46,
      "learning_rate": 0.0001,
      "loss": 0.0088,
      "step": 2100
    },
    {
      "epoch": 32.54,
      "learning_rate": 0.0001,
      "loss": 0.0103,
      "step": 2105
    },
    {
      "epoch": 32.62,
      "learning_rate": 0.0001,
      "loss": 0.0087,
      "step": 2110
    },
    {
      "epoch": 32.7,
      "learning_rate": 0.0001,
      "loss": 0.0154,
      "step": 2115
    },
    {
      "epoch": 32.77,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2120
    },
    {
      "epoch": 32.85,
      "learning_rate": 0.0001,
      "loss": 0.009,
      "step": 2125
    },
    {
      "epoch": 32.93,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 2130
    },
    {
      "epoch": 33.0,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2135
    },
    {
      "epoch": 33.08,
      "learning_rate": 0.0001,
      "loss": 0.0261,
      "step": 2140
    },
    {
      "epoch": 33.16,
      "learning_rate": 0.0001,
      "loss": 0.0095,
      "step": 2145
    },
    {
      "epoch": 33.24,
      "learning_rate": 0.0001,
      "loss": 0.0088,
      "step": 2150
    },
    {
      "epoch": 33.31,
      "learning_rate": 0.0001,
      "loss": 0.0091,
      "step": 2155
    },
    {
      "epoch": 33.39,
      "learning_rate": 0.0001,
      "loss": 0.0091,
      "step": 2160
    },
    {
      "epoch": 33.47,
      "learning_rate": 0.0001,
      "loss": 0.0092,
      "step": 2165
    },
    {
      "epoch": 33.55,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2170
    },
    {
      "epoch": 33.62,
      "learning_rate": 0.0001,
      "loss": 0.009,
      "step": 2175
    },
    {
      "epoch": 33.7,
      "learning_rate": 0.0001,
      "loss": 0.0093,
      "step": 2180
    },
    {
      "epoch": 33.78,
      "learning_rate": 0.0001,
      "loss": 0.0096,
      "step": 2185
    },
    {
      "epoch": 33.86,
      "learning_rate": 0.0001,
      "loss": 0.0089,
      "step": 2190
    },
    {
      "epoch": 33.93,
      "learning_rate": 0.0001,
      "loss": 0.0091,
      "step": 2195
    },
    {
      "epoch": 34.01,
      "learning_rate": 0.0001,
      "loss": 0.0098,
      "step": 2200
    },
    {
      "epoch": 34.09,
      "learning_rate": 0.0001,
      "loss": 0.0084,
      "step": 2205
    },
    {
      "epoch": 34.16,
      "learning_rate": 0.0001,
      "loss": 0.008,
      "step": 2210
    },
    {
      "epoch": 34.24,
      "learning_rate": 0.0001,
      "loss": 0.0085,
      "step": 2215
    },
    {
      "epoch": 34.32,
      "learning_rate": 0.0001,
      "loss": 0.0082,
      "step": 2220
    },
    {
      "epoch": 34.4,
      "learning_rate": 0.0001,
      "loss": 0.0077,
      "step": 2225
    },
    {
      "epoch": 34.47,
      "learning_rate": 0.0001,
      "loss": 0.0099,
      "step": 2230
    },
    {
      "epoch": 34.55,
      "learning_rate": 0.0001,
      "loss": 0.0192,
      "step": 2235
    },
    {
      "epoch": 34.63,
      "learning_rate": 0.0001,
      "loss": 0.0087,
      "step": 2240
    },
    {
      "epoch": 34.63,
      "step": 2240,
      "total_flos": 5.322709161266381e+17,
      "train_loss": 0.14071606248617172,
      "train_runtime": 19826.8664,
      "train_samples_per_second": 3.654,
      "train_steps_per_second": 0.113
    }
  ],
  "logging_steps": 5,
  "max_steps": 2240,
  "num_train_epochs": 35,
  "save_steps": -2240,
  "total_flos": 5.322709161266381e+17,
  "trial_name": null,
  "trial_params": null
}