{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 25.875,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.6915,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 11.0625,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.4256,
      "step": 20
    },
    {
      "epoch": 0.06,
      "grad_norm": 5.0,
      "learning_rate": 5.8e-06,
      "loss": 1.0232,
      "step": 30
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.515625,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.7479,
      "step": 40
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.8515625,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.6715,
      "step": 50
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0546875,
      "learning_rate": 1.18e-05,
      "loss": 0.6127,
      "step": 60
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.0859375,
      "learning_rate": 1.38e-05,
      "loss": 0.5316,
      "step": 70
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.71875,
      "learning_rate": 1.58e-05,
      "loss": 0.4557,
      "step": 80
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.50390625,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 0.4324,
      "step": 90
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.58203125,
      "learning_rate": 1.98e-05,
      "loss": 0.4665,
      "step": 100
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.4296875,
      "learning_rate": 1.9871428571428573e-05,
      "loss": 0.445,
      "step": 110
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.4921875,
      "learning_rate": 1.972857142857143e-05,
      "loss": 0.4252,
      "step": 120
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.41796875,
      "learning_rate": 1.958571428571429e-05,
      "loss": 0.4533,
      "step": 130
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.396484375,
      "learning_rate": 1.9442857142857147e-05,
      "loss": 0.455,
      "step": 140
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.4140625,
      "learning_rate": 1.93e-05,
      "loss": 0.414,
      "step": 150
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.392578125,
      "learning_rate": 1.915714285714286e-05,
      "loss": 0.4568,
      "step": 160
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.4609375,
      "learning_rate": 1.9014285714285718e-05,
      "loss": 0.4024,
      "step": 170
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.37890625,
      "learning_rate": 1.8871428571428572e-05,
      "loss": 0.4402,
      "step": 180
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.46484375,
      "learning_rate": 1.872857142857143e-05,
      "loss": 0.4407,
      "step": 190
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.388671875,
      "learning_rate": 1.858571428571429e-05,
      "loss": 0.419,
      "step": 200
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.384765625,
      "learning_rate": 1.8442857142857143e-05,
      "loss": 0.4146,
      "step": 210
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.375,
      "learning_rate": 1.83e-05,
      "loss": 0.4322,
      "step": 220
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.484375,
      "learning_rate": 1.815714285714286e-05,
      "loss": 0.4608,
      "step": 230
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.36328125,
      "learning_rate": 1.8014285714285714e-05,
      "loss": 0.4307,
      "step": 240
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.455078125,
      "learning_rate": 1.787142857142857e-05,
      "loss": 0.4447,
      "step": 250
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4375,
      "learning_rate": 1.772857142857143e-05,
      "loss": 0.4383,
      "step": 260
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.40234375,
      "learning_rate": 1.7585714285714288e-05,
      "loss": 0.439,
      "step": 270
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.35546875,
      "learning_rate": 1.7442857142857142e-05,
      "loss": 0.4059,
      "step": 280
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.46484375,
      "learning_rate": 1.73e-05,
      "loss": 0.4178,
      "step": 290
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.42578125,
      "learning_rate": 1.715714285714286e-05,
      "loss": 0.458,
      "step": 300
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.46484375,
      "learning_rate": 1.7014285714285716e-05,
      "loss": 0.4455,
      "step": 310
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.40234375,
      "learning_rate": 1.687142857142857e-05,
      "loss": 0.3664,
      "step": 320
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.498046875,
      "learning_rate": 1.672857142857143e-05,
      "loss": 0.4721,
      "step": 330
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.404296875,
      "learning_rate": 1.6585714285714287e-05,
      "loss": 0.3944,
      "step": 340
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.470703125,
      "learning_rate": 1.6442857142857145e-05,
      "loss": 0.4538,
      "step": 350
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.37890625,
      "learning_rate": 1.63e-05,
      "loss": 0.4037,
      "step": 360
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.42578125,
      "learning_rate": 1.6157142857142858e-05,
      "loss": 0.4065,
      "step": 370
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.412109375,
      "learning_rate": 1.6014285714285716e-05,
      "loss": 0.3996,
      "step": 380
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.439453125,
      "learning_rate": 1.5871428571428574e-05,
      "loss": 0.3915,
      "step": 390
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.466796875,
      "learning_rate": 1.5728571428571432e-05,
      "loss": 0.4315,
      "step": 400
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.357421875,
      "learning_rate": 1.5585714285714287e-05,
      "loss": 0.4789,
      "step": 410
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.40625,
      "learning_rate": 1.5442857142857145e-05,
      "loss": 0.425,
      "step": 420
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.41015625,
      "learning_rate": 1.5300000000000003e-05,
      "loss": 0.4166,
      "step": 430
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.39453125,
      "learning_rate": 1.5157142857142859e-05,
      "loss": 0.4224,
      "step": 440
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.400390625,
      "learning_rate": 1.5014285714285715e-05,
      "loss": 0.431,
      "step": 450
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.3671875,
      "learning_rate": 1.4871428571428572e-05,
      "loss": 0.4009,
      "step": 460
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.421875,
      "learning_rate": 1.472857142857143e-05,
      "loss": 0.3984,
      "step": 470
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.384765625,
      "learning_rate": 1.4585714285714288e-05,
      "loss": 0.4361,
      "step": 480
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.326171875,
      "learning_rate": 1.4442857142857146e-05,
      "loss": 0.4102,
      "step": 490
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3359375,
      "learning_rate": 1.43e-05,
      "loss": 0.3869,
      "step": 500
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.443359375,
      "learning_rate": 1.4157142857142858e-05,
      "loss": 0.4152,
      "step": 510
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.46484375,
      "learning_rate": 1.4014285714285716e-05,
      "loss": 0.4159,
      "step": 520
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.357421875,
      "learning_rate": 1.3871428571428573e-05,
      "loss": 0.4004,
      "step": 530
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.455078125,
      "learning_rate": 1.3728571428571429e-05,
      "loss": 0.4167,
      "step": 540
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.4453125,
      "learning_rate": 1.3585714285714287e-05,
      "loss": 0.4035,
      "step": 550
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.40625,
      "learning_rate": 1.3442857142857143e-05,
      "loss": 0.3879,
      "step": 560
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.431640625,
      "learning_rate": 1.3300000000000001e-05,
      "loss": 0.3716,
      "step": 570
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.4140625,
      "learning_rate": 1.3157142857142858e-05,
      "loss": 0.4223,
      "step": 580
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.451171875,
      "learning_rate": 1.3014285714285714e-05,
      "loss": 0.4324,
      "step": 590
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.365234375,
      "learning_rate": 1.2871428571428572e-05,
      "loss": 0.3891,
      "step": 600
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.400390625,
      "learning_rate": 1.272857142857143e-05,
      "loss": 0.4211,
      "step": 610
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.419921875,
      "learning_rate": 1.2585714285714288e-05,
      "loss": 0.432,
      "step": 620
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.337890625,
      "learning_rate": 1.2442857142857143e-05,
      "loss": 0.4046,
      "step": 630
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.404296875,
      "learning_rate": 1.23e-05,
      "loss": 0.4152,
      "step": 640
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.404296875,
      "learning_rate": 1.2157142857142859e-05,
      "loss": 0.424,
      "step": 650
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.36328125,
      "learning_rate": 1.2014285714285717e-05,
      "loss": 0.4191,
      "step": 660
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.435546875,
      "learning_rate": 1.1871428571428572e-05,
      "loss": 0.4346,
      "step": 670
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.421875,
      "learning_rate": 1.172857142857143e-05,
      "loss": 0.4233,
      "step": 680
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.408203125,
      "learning_rate": 1.1585714285714288e-05,
      "loss": 0.4355,
      "step": 690
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.400390625,
      "learning_rate": 1.1442857142857144e-05,
      "loss": 0.4217,
      "step": 700
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.46875,
      "learning_rate": 1.13e-05,
      "loss": 0.4098,
      "step": 710
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.40234375,
      "learning_rate": 1.1157142857142858e-05,
      "loss": 0.3989,
      "step": 720
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.40234375,
      "learning_rate": 1.1014285714285715e-05,
      "loss": 0.4153,
      "step": 730
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.36328125,
      "learning_rate": 1.0871428571428573e-05,
      "loss": 0.3708,
      "step": 740
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.40234375,
      "learning_rate": 1.072857142857143e-05,
      "loss": 0.4314,
      "step": 750
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.4609375,
      "learning_rate": 1.0585714285714285e-05,
      "loss": 0.4025,
      "step": 760
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.4453125,
      "learning_rate": 1.0442857142857143e-05,
      "loss": 0.4286,
      "step": 770
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.40625,
      "learning_rate": 1.0300000000000001e-05,
      "loss": 0.3973,
      "step": 780
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.3515625,
      "learning_rate": 1.015714285714286e-05,
      "loss": 0.4366,
      "step": 790
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.359375,
      "learning_rate": 1.0014285714285714e-05,
      "loss": 0.3933,
      "step": 800
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.431640625,
      "learning_rate": 9.871428571428572e-06,
      "loss": 0.4368,
      "step": 810
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.47265625,
      "learning_rate": 9.72857142857143e-06,
      "loss": 0.3967,
      "step": 820
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.3203125,
      "learning_rate": 9.585714285714286e-06,
      "loss": 0.408,
      "step": 830
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.42578125,
      "learning_rate": 9.442857142857144e-06,
      "loss": 0.4231,
      "step": 840
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.345703125,
      "learning_rate": 9.3e-06,
      "loss": 0.4004,
      "step": 850
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.396484375,
      "learning_rate": 9.157142857142857e-06,
      "loss": 0.431,
      "step": 860
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.427734375,
      "learning_rate": 9.014285714285715e-06,
      "loss": 0.4625,
      "step": 870
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.49609375,
      "learning_rate": 8.871428571428571e-06,
      "loss": 0.3664,
      "step": 880
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.423828125,
      "learning_rate": 8.72857142857143e-06,
      "loss": 0.4125,
      "step": 890
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.5,
      "learning_rate": 8.585714285714286e-06,
      "loss": 0.4678,
      "step": 900
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.408203125,
      "learning_rate": 8.442857142857144e-06,
      "loss": 0.4209,
      "step": 910
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.4140625,
      "learning_rate": 8.3e-06,
      "loss": 0.4592,
      "step": 920
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.32421875,
      "learning_rate": 8.157142857142858e-06,
      "loss": 0.3884,
      "step": 930
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.435546875,
      "learning_rate": 8.014285714285715e-06,
      "loss": 0.4343,
      "step": 940
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.388671875,
      "learning_rate": 7.871428571428573e-06,
      "loss": 0.4252,
      "step": 950
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.484375,
      "learning_rate": 7.72857142857143e-06,
      "loss": 0.4065,
      "step": 960
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.369140625,
      "learning_rate": 7.585714285714286e-06,
      "loss": 0.3999,
      "step": 970
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.53125,
      "learning_rate": 7.442857142857144e-06,
      "loss": 0.3812,
      "step": 980
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.380859375,
      "learning_rate": 7.3e-06,
      "loss": 0.4207,
      "step": 990
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.380859375,
      "learning_rate": 7.1571428571428584e-06,
      "loss": 0.4102,
      "step": 1000
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.462890625,
      "learning_rate": 7.014285714285715e-06,
      "loss": 0.4341,
      "step": 1010
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.4296875,
      "learning_rate": 6.871428571428572e-06,
      "loss": 0.4133,
      "step": 1020
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.478515625,
      "learning_rate": 6.728571428571429e-06,
      "loss": 0.42,
      "step": 1030
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.50390625,
      "learning_rate": 6.585714285714286e-06,
      "loss": 0.4259,
      "step": 1040
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.416015625,
      "learning_rate": 6.442857142857143e-06,
      "loss": 0.408,
      "step": 1050
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.353515625,
      "learning_rate": 6.300000000000001e-06,
      "loss": 0.3674,
      "step": 1060
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.46484375,
      "learning_rate": 6.157142857142858e-06,
      "loss": 0.4596,
      "step": 1070
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.462890625,
      "learning_rate": 6.014285714285715e-06,
      "loss": 0.4223,
      "step": 1080
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.39453125,
      "learning_rate": 5.871428571428572e-06,
      "loss": 0.4215,
      "step": 1090
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.35546875,
      "learning_rate": 5.7285714285714285e-06,
      "loss": 0.3983,
      "step": 1100
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.3671875,
      "learning_rate": 5.5857142857142866e-06,
      "loss": 0.37,
      "step": 1110
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.3671875,
      "learning_rate": 5.442857142857143e-06,
      "loss": 0.4269,
      "step": 1120
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.333984375,
      "learning_rate": 5.300000000000001e-06,
      "loss": 0.4239,
      "step": 1130
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.38671875,
      "learning_rate": 5.157142857142857e-06,
      "loss": 0.4232,
      "step": 1140
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.373046875,
      "learning_rate": 5.014285714285715e-06,
      "loss": 0.4167,
      "step": 1150
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.46875,
      "learning_rate": 4.871428571428572e-06,
      "loss": 0.4019,
      "step": 1160
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.310546875,
      "learning_rate": 4.728571428571429e-06,
      "loss": 0.4047,
      "step": 1170
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.361328125,
      "learning_rate": 4.585714285714286e-06,
      "loss": 0.3912,
      "step": 1180
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.396484375,
      "learning_rate": 4.442857142857143e-06,
      "loss": 0.386,
      "step": 1190
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.3828125,
      "learning_rate": 4.3e-06,
      "loss": 0.407,
      "step": 1200
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.32421875,
      "learning_rate": 4.1571428571428575e-06,
      "loss": 0.4214,
      "step": 1210
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.447265625,
      "learning_rate": 4.014285714285715e-06,
      "loss": 0.4027,
      "step": 1220
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.35546875,
      "learning_rate": 3.871428571428572e-06,
      "loss": 0.4209,
      "step": 1230
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.3828125,
      "learning_rate": 3.7285714285714286e-06,
      "loss": 0.4339,
      "step": 1240
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.35546875,
      "learning_rate": 3.5857142857142862e-06,
      "loss": 0.4498,
      "step": 1250
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.4453125,
      "learning_rate": 3.4428571428571434e-06,
      "loss": 0.3927,
      "step": 1260
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.365234375,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.4186,
      "step": 1270
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.44140625,
      "learning_rate": 3.1571428571428573e-06,
      "loss": 0.4302,
      "step": 1280
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.38671875,
      "learning_rate": 3.0142857142857145e-06,
      "loss": 0.4069,
      "step": 1290
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.42578125,
      "learning_rate": 2.8714285714285717e-06,
      "loss": 0.4082,
      "step": 1300
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.423828125,
      "learning_rate": 2.728571428571429e-06,
      "loss": 0.4081,
      "step": 1310
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.51953125,
      "learning_rate": 2.5857142857142856e-06,
      "loss": 0.3754,
      "step": 1320
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.4453125,
      "learning_rate": 2.442857142857143e-06,
      "loss": 0.4181,
      "step": 1330
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.416015625,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.4055,
      "step": 1340
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.384765625,
      "learning_rate": 2.157142857142857e-06,
      "loss": 0.4136,
      "step": 1350
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.349609375,
      "learning_rate": 2.0142857142857144e-06,
      "loss": 0.4076,
      "step": 1360
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.421875,
      "learning_rate": 1.8714285714285715e-06,
      "loss": 0.3923,
      "step": 1370
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.408203125,
      "learning_rate": 1.7285714285714287e-06,
      "loss": 0.402,
      "step": 1380
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.37890625,
      "learning_rate": 1.5857142857142857e-06,
      "loss": 0.3868,
      "step": 1390
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.34375,
      "learning_rate": 1.442857142857143e-06,
      "loss": 0.4136,
      "step": 1400
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.47265625,
      "learning_rate": 1.3e-06,
      "loss": 0.3963,
      "step": 1410
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.408203125,
      "learning_rate": 1.1571428571428572e-06,
      "loss": 0.4165,
      "step": 1420
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.357421875,
      "learning_rate": 1.0142857142857144e-06,
      "loss": 0.4273,
      "step": 1430
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.419921875,
      "learning_rate": 8.714285714285716e-07,
      "loss": 0.4037,
      "step": 1440
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.380859375,
      "learning_rate": 7.285714285714287e-07,
      "loss": 0.4117,
      "step": 1450
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.419921875,
      "learning_rate": 5.857142857142857e-07,
      "loss": 0.396,
      "step": 1460
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.353515625,
      "learning_rate": 4.4285714285714286e-07,
      "loss": 0.424,
      "step": 1470
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.37109375,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 0.4359,
      "step": 1480
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.3671875,
      "learning_rate": 1.5714285714285717e-07,
      "loss": 0.3962,
      "step": 1490
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.384765625,
      "learning_rate": 1.4285714285714288e-08,
      "loss": 0.4008,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.286265088278528e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}