{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5690430314707773,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 4.3076,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 4.339,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 4.3359,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 4.2636,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 4.2206,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 4.3574,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 4.1852,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 4.2531,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 4.2387,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 4.3561,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 4.4244,
      "step": 55
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 4.4225,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 4.2115,
      "step": 65
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 4.288,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 4.2438,
      "step": 75
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 4.432,
      "step": 80
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 4.2755,
      "step": 85
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 4.313,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 4.3451,
      "step": 95
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 4.4527,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 4.2953,
      "step": 105
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 4.3346,
      "step": 110
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 4.1679,
      "step": 115
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 4.3397,
      "step": 120
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 4.2316,
      "step": 125
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 4.3543,
      "step": 130
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 4.1932,
      "step": 135
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 4.2699,
      "step": 140
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 4.3391,
      "step": 145
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 4.3462,
      "step": 150
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 4.2927,
      "step": 155
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 4.4016,
      "step": 160
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 4.3103,
      "step": 165
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 4.3131,
      "step": 170
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 4.4033,
      "step": 175
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 4.348,
      "step": 180
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 4.3298,
      "step": 185
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 4.1981,
      "step": 190
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 4.2476,
      "step": 195
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 4.3398,
      "step": 200
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 4.2935,
      "step": 205
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 4.2564,
      "step": 210
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 4.3345,
      "step": 215
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 4.3348,
      "step": 220
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 4.3484,
      "step": 225
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 4.3095,
      "step": 230
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 4.2634,
      "step": 235
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 4.4082,
      "step": 240
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 4.3323,
      "step": 245
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 4.3519,
      "step": 250
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 4.2884,
      "step": 255
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 4.1666,
      "step": 260
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 4.2651,
      "step": 265
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 4.3882,
      "step": 270
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 4.1804,
      "step": 275
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 4.3786,
      "step": 280
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 4.4226,
      "step": 285
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 4.386,
      "step": 290
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 4.4914,
      "step": 295
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 4.2797,
      "step": 300
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 4.1578,
      "step": 305
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 4.3835,
      "step": 310
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 4.1252,
      "step": 315
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001,
      "loss": 4.3937,
      "step": 320
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001,
      "loss": 4.2939,
      "step": 325
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 4.3824,
      "step": 330
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001,
      "loss": 4.3216,
      "step": 335
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 4.2493,
      "step": 340
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 4.2701,
      "step": 345
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 4.378,
      "step": 350
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 4.287,
      "step": 355
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001,
      "loss": 4.4676,
      "step": 360
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 4.3444,
      "step": 365
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001,
      "loss": 4.3595,
      "step": 370
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 4.3376,
      "step": 375
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 4.3348,
      "step": 380
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 4.5059,
      "step": 385
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 4.3621,
      "step": 390
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 4.1886,
      "step": 395
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 4.1752,
      "step": 400
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 4.2483,
      "step": 405
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 4.2046,
      "step": 410
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 4.2465,
      "step": 415
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 4.2682,
      "step": 420
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001,
      "loss": 4.1526,
      "step": 425
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 4.344,
      "step": 430
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001,
      "loss": 4.2489,
      "step": 435
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001,
      "loss": 4.3117,
      "step": 440
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001,
      "loss": 4.3635,
      "step": 445
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 4.3703,
      "step": 450
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 4.3134,
      "step": 455
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001,
      "loss": 4.2065,
      "step": 460
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 4.3101,
      "step": 465
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001,
      "loss": 4.224,
      "step": 470
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 4.2506,
      "step": 475
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 4.2744,
      "step": 480
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 3.9679,
      "step": 485
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 4.3277,
      "step": 490
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001,
      "loss": 4.0874,
      "step": 495
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 4.2368,
      "step": 500
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 4.13,
      "step": 505
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001,
      "loss": 4.2603,
      "step": 510
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 4.2935,
      "step": 515
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 4.2203,
      "step": 520
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001,
      "loss": 4.3598,
      "step": 525
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001,
      "loss": 4.2383,
      "step": 530
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001,
      "loss": 4.2613,
      "step": 535
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 4.3348,
      "step": 540
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 4.261,
      "step": 545
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001,
      "loss": 4.2119,
      "step": 550
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001,
      "loss": 4.3145,
      "step": 555
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001,
      "loss": 4.2848,
      "step": 560
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001,
      "loss": 4.2455,
      "step": 565
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 4.3453,
      "step": 570
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001,
      "loss": 4.4049,
      "step": 575
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001,
      "loss": 4.338,
      "step": 580
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 4.1911,
      "step": 585
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001,
      "loss": 4.3331,
      "step": 590
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 4.2812,
      "step": 595
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001,
      "loss": 4.2958,
      "step": 600
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 4.1687,
      "step": 605
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 4.2474,
      "step": 610
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001,
      "loss": 4.2782,
      "step": 615
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 4.2148,
      "step": 620
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001,
      "loss": 4.2261,
      "step": 625
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001,
      "loss": 4.2337,
      "step": 630
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001,
      "loss": 4.2706,
      "step": 635
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001,
      "loss": 4.3507,
      "step": 640
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001,
      "loss": 4.3652,
      "step": 645
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 4.3377,
      "step": 650
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001,
      "loss": 4.2426,
      "step": 655
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001,
      "loss": 4.1461,
      "step": 660
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 4.2695,
      "step": 665
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001,
      "loss": 4.3503,
      "step": 670
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001,
      "loss": 4.3124,
      "step": 675
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001,
      "loss": 4.1831,
      "step": 680
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001,
      "loss": 4.1907,
      "step": 685
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 4.2385,
      "step": 690
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001,
      "loss": 4.2744,
      "step": 695
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001,
      "loss": 4.2176,
      "step": 700
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 4.1306,
      "step": 705
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001,
      "loss": 4.2305,
      "step": 710
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001,
      "loss": 4.1491,
      "step": 715
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001,
      "loss": 4.238,
      "step": 720
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001,
      "loss": 4.2414,
      "step": 725
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 4.2582,
      "step": 730
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 4.3286,
      "step": 735
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001,
      "loss": 4.17,
      "step": 740
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001,
      "loss": 4.2558,
      "step": 745
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001,
      "loss": 4.3346,
      "step": 750
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001,
      "loss": 4.2515,
      "step": 755
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 4.3608,
      "step": 760
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001,
      "loss": 4.0462,
      "step": 765
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001,
      "loss": 4.3009,
      "step": 770
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 4.0083,
      "step": 775
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 4.0542,
      "step": 780
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001,
      "loss": 4.0633,
      "step": 785
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001,
      "loss": 4.1706,
      "step": 790
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001,
      "loss": 4.1673,
      "step": 795
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0001,
      "loss": 4.1666,
      "step": 800
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001,
      "loss": 4.2268,
      "step": 805
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 4.289,
      "step": 810
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 4.1504,
      "step": 815
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001,
      "loss": 4.2414,
      "step": 820
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 4.1514,
      "step": 825
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001,
      "loss": 4.1361,
      "step": 830
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001,
      "loss": 4.2677,
      "step": 835
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 4.1762,
      "step": 840
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001,
      "loss": 4.1429,
      "step": 845
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001,
      "loss": 4.2751,
      "step": 850
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 4.2268,
      "step": 855
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001,
      "loss": 4.0249,
      "step": 860
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001,
      "loss": 4.2635,
      "step": 865
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001,
      "loss": 4.136,
      "step": 870
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001,
      "loss": 4.2796,
      "step": 875
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001,
      "loss": 4.1551,
      "step": 880
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001,
      "loss": 4.1054,
      "step": 885
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001,
      "loss": 4.216,
      "step": 890
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001,
      "loss": 4.2077,
      "step": 895
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001,
      "loss": 4.1909,
      "step": 900
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 4.1047,
      "step": 905
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 4.2881,
      "step": 910
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 4.1232,
      "step": 915
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001,
      "loss": 4.2072,
      "step": 920
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001,
      "loss": 4.2022,
      "step": 925
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001,
      "loss": 4.2288,
      "step": 930
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001,
      "loss": 4.168,
      "step": 935
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001,
      "loss": 4.1692,
      "step": 940
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0001,
      "loss": 4.2852,
      "step": 945
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001,
      "loss": 4.2829,
      "step": 950
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001,
      "loss": 4.1029,
      "step": 955
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 4.1946,
      "step": 960
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001,
      "loss": 4.3298,
      "step": 965
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001,
      "loss": 4.1995,
      "step": 970
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 4.1478,
      "step": 975
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001,
      "loss": 4.2623,
      "step": 980
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001,
      "loss": 4.2101,
      "step": 985
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001,
      "loss": 4.2458,
      "step": 990
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001,
      "loss": 4.3196,
      "step": 995
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0001,
      "loss": 4.1717,
      "step": 1000
    }
  ],
  "logging_steps": 5,
  "max_steps": 1945,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "total_flos": 1824768000000000.0,
  "trial_name": null,
  "trial_params": null
}