{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "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": 0.0004995,
      "loss": 2.0736,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000499,
      "loss": 2.165,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004985,
      "loss": 2.084,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000498,
      "loss": 2.1784,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004975,
      "loss": 2.0932,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000497,
      "loss": 2.056,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004965,
      "loss": 2.0944,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000496,
      "loss": 2.1092,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004955,
      "loss": 2.1146,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000495,
      "loss": 2.1368,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004945,
      "loss": 2.0964,
      "step": 55
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000494,
      "loss": 2.0192,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004935,
      "loss": 2.0938,
      "step": 65
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004930000000000001,
      "loss": 2.0871,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004925,
      "loss": 2.0773,
      "step": 75
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000492,
      "loss": 2.0618,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004915,
      "loss": 2.0788,
      "step": 85
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000491,
      "loss": 2.1009,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004905,
      "loss": 2.0138,
      "step": 95
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00049,
      "loss": 2.0689,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004895,
      "loss": 2.0381,
      "step": 105
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000489,
      "loss": 2.1174,
      "step": 110
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004885,
      "loss": 2.0315,
      "step": 115
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000488,
      "loss": 2.0351,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004875,
      "loss": 2.1047,
      "step": 125
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000487,
      "loss": 2.0413,
      "step": 130
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004865,
      "loss": 2.0978,
      "step": 135
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000486,
      "loss": 2.1018,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004855,
      "loss": 2.0679,
      "step": 145
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00048499999999999997,
      "loss": 1.974,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0004845,
      "loss": 2.0155,
      "step": 155
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000484,
      "loss": 2.0396,
      "step": 160
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0004835,
      "loss": 2.0207,
      "step": 165
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000483,
      "loss": 2.017,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0004825,
      "loss": 2.0844,
      "step": 175
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000482,
      "loss": 2.0593,
      "step": 180
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0004815,
      "loss": 2.0018,
      "step": 185
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000481,
      "loss": 1.9544,
      "step": 190
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00048049999999999997,
      "loss": 2.063,
      "step": 195
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00048,
      "loss": 2.0345,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004795,
      "loss": 2.0164,
      "step": 205
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000479,
      "loss": 1.9801,
      "step": 210
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0004785,
      "loss": 2.038,
      "step": 215
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00047799999999999996,
      "loss": 2.0919,
      "step": 220
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004775,
      "loss": 2.0151,
      "step": 225
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000477,
      "loss": 1.9425,
      "step": 230
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004765,
      "loss": 2.0252,
      "step": 235
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00047599999999999997,
      "loss": 1.965,
      "step": 240
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0004755,
      "loss": 1.9773,
      "step": 245
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000475,
      "loss": 1.9828,
      "step": 250
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0004745,
      "loss": 1.9247,
      "step": 255
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000474,
      "loss": 1.9878,
      "step": 260
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00047349999999999996,
      "loss": 2.0097,
      "step": 265
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000473,
      "loss": 2.0276,
      "step": 270
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0004725,
      "loss": 1.949,
      "step": 275
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000472,
      "loss": 2.0144,
      "step": 280
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00047149999999999997,
      "loss": 1.9787,
      "step": 285
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000471,
      "loss": 2.0019,
      "step": 290
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0004705,
      "loss": 2.0421,
      "step": 295
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00047,
      "loss": 1.9843,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0004695,
      "loss": 1.9604,
      "step": 305
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00046899999999999996,
      "loss": 1.9696,
      "step": 310
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00046850000000000006,
      "loss": 1.988,
      "step": 315
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00046800000000000005,
      "loss": 1.9925,
      "step": 320
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00046750000000000003,
      "loss": 1.9881,
      "step": 325
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000467,
      "loss": 1.9817,
      "step": 330
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0004665,
      "loss": 1.9384,
      "step": 335
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00046600000000000005,
      "loss": 1.9971,
      "step": 340
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00046550000000000004,
      "loss": 2.0022,
      "step": 345
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000465,
      "loss": 1.9593,
      "step": 350
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0004645,
      "loss": 1.9979,
      "step": 355
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00046400000000000006,
      "loss": 1.9264,
      "step": 360
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00046350000000000004,
      "loss": 1.9665,
      "step": 365
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00046300000000000003,
      "loss": 1.9307,
      "step": 370
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0004625,
      "loss": 1.9584,
      "step": 375
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000462,
      "loss": 2.0025,
      "step": 380
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00046150000000000005,
      "loss": 1.98,
      "step": 385
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00046100000000000004,
      "loss": 1.9673,
      "step": 390
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0004605,
      "loss": 1.9598,
      "step": 395
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00046,
      "loss": 2.0057,
      "step": 400
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00045950000000000006,
      "loss": 1.9537,
      "step": 405
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00045900000000000004,
      "loss": 1.9726,
      "step": 410
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00045850000000000003,
      "loss": 1.9011,
      "step": 415
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000458,
      "loss": 1.9988,
      "step": 420
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0004575,
      "loss": 1.9626,
      "step": 425
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00045700000000000005,
      "loss": 1.9083,
      "step": 430
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00045650000000000004,
      "loss": 1.9429,
      "step": 435
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000456,
      "loss": 1.9819,
      "step": 440
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0004555,
      "loss": 1.9259,
      "step": 445
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000455,
      "loss": 1.9024,
      "step": 450
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00045450000000000004,
      "loss": 1.983,
      "step": 455
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00045400000000000003,
      "loss": 1.9776,
      "step": 460
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0004535,
      "loss": 1.9816,
      "step": 465
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000453,
      "loss": 1.9402,
      "step": 470
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00045250000000000005,
      "loss": 1.9931,
      "step": 475
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00045200000000000004,
      "loss": 1.9528,
      "step": 480
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0004515,
      "loss": 1.9392,
      "step": 485
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000451,
      "loss": 1.9249,
      "step": 490
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0004505,
      "loss": 1.9711,
      "step": 495
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00045000000000000004,
      "loss": 1.8939,
      "step": 500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00044950000000000003,
      "loss": 1.96,
      "step": 505
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000449,
      "loss": 1.9014,
      "step": 510
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0004485,
      "loss": 1.9354,
      "step": 515
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000448,
      "loss": 1.9597,
      "step": 520
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00044750000000000004,
      "loss": 1.9367,
      "step": 525
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000447,
      "loss": 1.9698,
      "step": 530
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0004465,
      "loss": 1.8743,
      "step": 535
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000446,
      "loss": 1.9083,
      "step": 540
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00044550000000000004,
      "loss": 1.9096,
      "step": 545
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00044500000000000003,
      "loss": 2.0429,
      "step": 550
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0004445,
      "loss": 1.9972,
      "step": 555
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000444,
      "loss": 1.8974,
      "step": 560
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0004435,
      "loss": 1.9467,
      "step": 565
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00044300000000000003,
      "loss": 1.9382,
      "step": 570
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0004425,
      "loss": 1.8893,
      "step": 575
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000442,
      "loss": 1.9392,
      "step": 580
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004415,
      "loss": 1.9229,
      "step": 585
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000441,
      "loss": 1.9042,
      "step": 590
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00044050000000000003,
      "loss": 1.9104,
      "step": 595
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00044,
      "loss": 1.9541,
      "step": 600
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0004395,
      "loss": 1.8948,
      "step": 605
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000439,
      "loss": 1.8849,
      "step": 610
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00043850000000000003,
      "loss": 1.9097,
      "step": 615
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000438,
      "loss": 1.9457,
      "step": 620
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004375,
      "loss": 1.9231,
      "step": 625
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000437,
      "loss": 1.9228,
      "step": 630
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004365,
      "loss": 1.9258,
      "step": 635
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000436,
      "loss": 1.8884,
      "step": 640
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004355,
      "loss": 1.8693,
      "step": 645
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000435,
      "loss": 1.8635,
      "step": 650
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004345,
      "loss": 1.9319,
      "step": 655
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00043400000000000003,
      "loss": 1.9116,
      "step": 660
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004335,
      "loss": 1.9299,
      "step": 665
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000433,
      "loss": 1.8971,
      "step": 670
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004325,
      "loss": 1.9317,
      "step": 675
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000432,
      "loss": 1.9523,
      "step": 680
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004315,
      "loss": 1.8683,
      "step": 685
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000431,
      "loss": 1.9321,
      "step": 690
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004305,
      "loss": 1.8971,
      "step": 695
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00043,
      "loss": 1.8666,
      "step": 700
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004295,
      "loss": 1.888,
      "step": 705
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000429,
      "loss": 1.8946,
      "step": 710
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004285,
      "loss": 1.9037,
      "step": 715
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000428,
      "loss": 1.8533,
      "step": 720
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004275,
      "loss": 1.9052,
      "step": 725
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000427,
      "loss": 1.8677,
      "step": 730
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004265,
      "loss": 1.9164,
      "step": 735
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000426,
      "loss": 1.8823,
      "step": 740
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004255,
      "loss": 1.9215,
      "step": 745
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000425,
      "loss": 1.8903,
      "step": 750
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004245,
      "loss": 1.8148,
      "step": 755
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000424,
      "loss": 1.8324,
      "step": 760
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004235,
      "loss": 1.9011,
      "step": 765
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000423,
      "loss": 1.9424,
      "step": 770
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00042249999999999997,
      "loss": 1.9028,
      "step": 775
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000422,
      "loss": 1.8789,
      "step": 780
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004215,
      "loss": 1.9016,
      "step": 785
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000421,
      "loss": 1.8837,
      "step": 790
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004205,
      "loss": 1.8651,
      "step": 795
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00042,
      "loss": 1.8212,
      "step": 800
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004195,
      "loss": 1.9073,
      "step": 805
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000419,
      "loss": 1.9267,
      "step": 810
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004185,
      "loss": 1.8311,
      "step": 815
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00041799999999999997,
      "loss": 1.8537,
      "step": 820
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004175,
      "loss": 1.8717,
      "step": 825
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000417,
      "loss": 1.8241,
      "step": 830
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004165,
      "loss": 1.8863,
      "step": 835
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000416,
      "loss": 1.9053,
      "step": 840
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00041549999999999996,
      "loss": 1.87,
      "step": 845
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000415,
      "loss": 1.837,
      "step": 850
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004145,
      "loss": 1.8941,
      "step": 855
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000414,
      "loss": 1.9237,
      "step": 860
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00041349999999999997,
      "loss": 1.8854,
      "step": 865
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000413,
      "loss": 1.8401,
      "step": 870
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004125,
      "loss": 1.8314,
      "step": 875
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000412,
      "loss": 1.858,
      "step": 880
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004115,
      "loss": 1.8806,
      "step": 885
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00041099999999999996,
      "loss": 1.8244,
      "step": 890
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004105,
      "loss": 1.8432,
      "step": 895
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00041,
      "loss": 1.8596,
      "step": 900
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004095,
      "loss": 1.8276,
      "step": 905
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00040899999999999997,
      "loss": 1.9486,
      "step": 910
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004085,
      "loss": 1.8382,
      "step": 915
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000408,
      "loss": 1.8735,
      "step": 920
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004075,
      "loss": 1.8203,
      "step": 925
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00040699999999999997,
      "loss": 1.8045,
      "step": 930
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00040649999999999996,
      "loss": 1.8732,
      "step": 935
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00040600000000000006,
      "loss": 1.8032,
      "step": 940
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00040550000000000004,
      "loss": 1.8079,
      "step": 945
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00040500000000000003,
      "loss": 1.8855,
      "step": 950
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004045,
      "loss": 1.8511,
      "step": 955
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000404,
      "loss": 1.8529,
      "step": 960
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00040350000000000005,
      "loss": 1.8482,
      "step": 965
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00040300000000000004,
      "loss": 1.8288,
      "step": 970
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004025,
      "loss": 1.8781,
      "step": 975
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000402,
      "loss": 1.8458,
      "step": 980
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00040150000000000006,
      "loss": 1.8426,
      "step": 985
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00040100000000000004,
      "loss": 1.8517,
      "step": 990
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00040050000000000003,
      "loss": 1.8426,
      "step": 995
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004,
      "loss": 1.7787,
      "step": 1000
    }
  ],
  "logging_steps": 5,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2.65273620205824e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}