{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.88,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 205
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 215
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 235
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 245
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 265
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 275
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 295
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 305
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 325
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 345
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 355
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 365
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 385
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 395
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 415
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 425
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 435
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 445
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 455
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 465
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 475
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 485
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 505
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 510
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 515
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 520
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 525
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 530
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 535
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 540
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 545
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 555
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 560
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 565
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 570
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 575
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 580
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 585
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 590
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 595
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 605
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 610
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 615
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 620
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 625
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 630
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 635
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 640
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 645
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 655
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 660
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 665
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 670
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 675
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 680
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 685
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 690
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 695
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 705
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 710
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 715
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 720
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 725
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 730
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 735
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 740
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 745
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 755
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 760
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 765
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 770
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 775
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 780
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 785
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 790
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 795
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 805
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 810
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 815
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 820
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 825
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 830
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 835
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 840
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 845
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 850
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 855
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 860
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 865
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 870
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 875
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 880
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 885
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 890
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 895
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 900
    }
  ],
  "logging_steps": 5,
  "max_steps": 936,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.33087946031104e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}