{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-06,
      "loss": 4.7448,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-06,
      "loss": 4.8883,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 4.8436,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-06,
      "loss": 4.7855,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 4.6616,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 4.6613,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4e-05,
      "loss": 4.5803,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6e-05,
      "loss": 4.5786,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.8e-05,
      "loss": 4.5486,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 4.3926,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 4.4643,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-05,
      "loss": 4.4572,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4e-05,
      "loss": 4.373,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.6e-05,
      "loss": 4.3855,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.8e-05,
      "loss": 4.2546,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 3e-05,
      "loss": 4.395,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2e-05,
      "loss": 4.2986,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 4.4178,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.6e-05,
      "loss": 4.222,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.8e-05,
      "loss": 4.3886,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 4.359,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 4.3137,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.4e-05,
      "loss": 4.3939,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.6e-05,
      "loss": 4.354,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.8e-05,
      "loss": 4.1825,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 4.413,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.2e-05,
      "loss": 4.2932,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.4e-05,
      "loss": 4.155,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.6e-05,
      "loss": 4.1171,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.800000000000001e-05,
      "loss": 4.3741,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-05,
      "loss": 4.3261,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.2e-05,
      "loss": 4.1959,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 6.4e-05,
      "loss": 4.2738,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.6e-05,
      "loss": 4.2401,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.2822,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 7.000000000000001e-05,
      "loss": 4.2956,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 7.2e-05,
      "loss": 4.3229,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.4e-05,
      "loss": 4.2568,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.6e-05,
      "loss": 4.373,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.8e-05,
      "loss": 4.2255,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 8e-05,
      "loss": 4.2638,
      "step": 41
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.2e-05,
      "loss": 4.3446,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.400000000000001e-05,
      "loss": 4.1355,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.599999999999999e-05,
      "loss": 4.3231,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.8e-05,
      "loss": 4.4,
      "step": 45
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.4553,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.2e-05,
      "loss": 4.3854,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.400000000000001e-05,
      "loss": 4.6031,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.6e-05,
      "loss": 4.629,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.800000000000001e-05,
      "loss": 4.3993,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 4.3064,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000102,
      "loss": 4.1792,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000104,
      "loss": 4.338,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000106,
      "loss": 4.2367,
      "step": 54
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000108,
      "loss": 4.0805,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00011,
      "loss": 4.2757,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000112,
      "loss": 4.2968,
      "step": 57
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000114,
      "loss": 4.414,
      "step": 58
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00011600000000000001,
      "loss": 4.2925,
      "step": 59
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000118,
      "loss": 4.1971,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00012,
      "loss": 4.2551,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000122,
      "loss": 4.2037,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000124,
      "loss": 4.1967,
      "step": 63
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000126,
      "loss": 4.3095,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000128,
      "loss": 4.2633,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00013000000000000002,
      "loss": 4.144,
      "step": 66
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000132,
      "loss": 4.2906,
      "step": 67
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000134,
      "loss": 4.1689,
      "step": 68
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00013600000000000003,
      "loss": 4.2172,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00013800000000000002,
      "loss": 4.1874,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014000000000000001,
      "loss": 4.3269,
      "step": 71
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014199999999999998,
      "loss": 4.3836,
      "step": 72
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000144,
      "loss": 4.1776,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000146,
      "loss": 4.2561,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000148,
      "loss": 4.2782,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00015,
      "loss": 4.2432,
      "step": 76
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000152,
      "loss": 4.2544,
      "step": 77
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000154,
      "loss": 4.2034,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000156,
      "loss": 4.2487,
      "step": 79
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000158,
      "loss": 4.3555,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016,
      "loss": 4.3519,
      "step": 81
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000162,
      "loss": 4.2654,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000164,
      "loss": 4.3638,
      "step": 83
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016600000000000002,
      "loss": 4.3315,
      "step": 84
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016800000000000002,
      "loss": 4.3381,
      "step": 85
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00017,
      "loss": 4.2955,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00017199999999999998,
      "loss": 4.3315,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000174,
      "loss": 4.2362,
      "step": 88
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000176,
      "loss": 4.4432,
      "step": 89
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000178,
      "loss": 4.4031,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.2638,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000182,
      "loss": 4.5215,
      "step": 92
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000184,
      "loss": 4.4342,
      "step": 93
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000186,
      "loss": 4.6104,
      "step": 94
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018800000000000002,
      "loss": 4.321,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019,
      "loss": 4.6963,
      "step": 96
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000192,
      "loss": 4.4766,
      "step": 97
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000194,
      "loss": 4.6106,
      "step": 98
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019600000000000002,
      "loss": 4.7505,
      "step": 99
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019800000000000002,
      "loss": 4.5221,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 4.4953,
      "step": 101
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000202,
      "loss": 4.5015,
      "step": 102
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000204,
      "loss": 4.2782,
      "step": 103
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000206,
      "loss": 4.3432,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000208,
      "loss": 4.2491,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00021,
      "loss": 4.343,
      "step": 106
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000212,
      "loss": 4.3491,
      "step": 107
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000214,
      "loss": 4.2156,
      "step": 108
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000216,
      "loss": 4.2983,
      "step": 109
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000218,
      "loss": 4.315,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00022,
      "loss": 4.4117,
      "step": 111
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000222,
      "loss": 4.3823,
      "step": 112
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000224,
      "loss": 4.3341,
      "step": 113
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00022600000000000002,
      "loss": 4.2731,
      "step": 114
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000228,
      "loss": 4.3656,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00023,
      "loss": 4.4402,
      "step": 116
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00023200000000000003,
      "loss": 4.3582,
      "step": 117
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00023400000000000002,
      "loss": 4.4894,
      "step": 118
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000236,
      "loss": 4.4289,
      "step": 119
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00023799999999999998,
      "loss": 4.4637,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00024,
      "loss": 4.2816,
      "step": 121
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000242,
      "loss": 4.3416,
      "step": 122
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000244,
      "loss": 4.3645,
      "step": 123
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000246,
      "loss": 4.3001,
      "step": 124
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000248,
      "loss": 4.4611,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00025,
      "loss": 4.5181,
      "step": 126
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000252,
      "loss": 4.4458,
      "step": 127
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000254,
      "loss": 4.3131,
      "step": 128
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000256,
      "loss": 4.27,
      "step": 129
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00025800000000000004,
      "loss": 4.6221,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00026000000000000003,
      "loss": 4.3875,
      "step": 131
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000262,
      "loss": 4.406,
      "step": 132
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000264,
      "loss": 4.2984,
      "step": 133
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000266,
      "loss": 4.4539,
      "step": 134
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000268,
      "loss": 4.5082,
      "step": 135
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00027,
      "loss": 4.3125,
      "step": 136
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027200000000000005,
      "loss": 4.4509,
      "step": 137
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027400000000000005,
      "loss": 4.5328,
      "step": 138
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027600000000000004,
      "loss": 4.4671,
      "step": 139
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027800000000000004,
      "loss": 4.478,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028000000000000003,
      "loss": 4.5525,
      "step": 141
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028199999999999997,
      "loss": 4.7511,
      "step": 142
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028399999999999996,
      "loss": 5.0134,
      "step": 143
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028599999999999996,
      "loss": 4.7465,
      "step": 144
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000288,
      "loss": 4.4685,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029,
      "loss": 4.6673,
      "step": 146
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000292,
      "loss": 5.0644,
      "step": 147
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000294,
      "loss": 4.8156,
      "step": 148
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000296,
      "loss": 4.6348,
      "step": 149
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000298,
      "loss": 4.905,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 4.5051,
      "step": 151
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000302,
      "loss": 4.4782,
      "step": 152
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000304,
      "loss": 4.563,
      "step": 153
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000306,
      "loss": 4.3117,
      "step": 154
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000308,
      "loss": 4.4834,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00031,
      "loss": 4.3141,
      "step": 156
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000312,
      "loss": 4.4631,
      "step": 157
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000314,
      "loss": 4.5245,
      "step": 158
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000316,
      "loss": 4.5088,
      "step": 159
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00031800000000000003,
      "loss": 4.5542,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00032,
      "loss": 4.5309,
      "step": 161
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000322,
      "loss": 4.448,
      "step": 162
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000324,
      "loss": 4.4301,
      "step": 163
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000326,
      "loss": 4.5063,
      "step": 164
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000328,
      "loss": 4.3681,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00033,
      "loss": 4.5243,
      "step": 166
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00033200000000000005,
      "loss": 4.3789,
      "step": 167
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033400000000000004,
      "loss": 4.457,
      "step": 168
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033600000000000004,
      "loss": 4.599,
      "step": 169
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033800000000000003,
      "loss": 4.4211,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00034,
      "loss": 4.4048,
      "step": 171
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000342,
      "loss": 4.5022,
      "step": 172
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00034399999999999996,
      "loss": 4.4207,
      "step": 173
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000346,
      "loss": 4.6248,
      "step": 174
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000348,
      "loss": 4.6288,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00035,
      "loss": 4.3465,
      "step": 176
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000352,
      "loss": 4.2846,
      "step": 177
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000354,
      "loss": 4.5639,
      "step": 178
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000356,
      "loss": 4.5932,
      "step": 179
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000358,
      "loss": 4.6008,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00035999999999999997,
      "loss": 4.5307,
      "step": 181
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000362,
      "loss": 4.5309,
      "step": 182
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000364,
      "loss": 5.0206,
      "step": 183
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000366,
      "loss": 4.5031,
      "step": 184
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000368,
      "loss": 4.5873,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00037,
      "loss": 4.4111,
      "step": 186
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000372,
      "loss": 4.419,
      "step": 187
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000374,
      "loss": 4.4443,
      "step": 188
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00037600000000000003,
      "loss": 4.6531,
      "step": 189
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000378,
      "loss": 4.6183,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00038,
      "loss": 4.8718,
      "step": 191
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000382,
      "loss": 4.7412,
      "step": 192
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000384,
      "loss": 4.4731,
      "step": 193
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000386,
      "loss": 4.8124,
      "step": 194
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000388,
      "loss": 5.2314,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039000000000000005,
      "loss": 4.739,
      "step": 196
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039200000000000004,
      "loss": 5.8253,
      "step": 197
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039400000000000004,
      "loss": 5.141,
      "step": 198
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039600000000000003,
      "loss": 4.8066,
      "step": 199
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000398,
      "loss": 5.3003,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0004,
      "loss": 4.8144,
      "step": 201
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000402,
      "loss": 4.759,
      "step": 202
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000404,
      "loss": 4.9561,
      "step": 203
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00040600000000000006,
      "loss": 4.8247,
      "step": 204
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000408,
      "loss": 4.6602,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00041,
      "loss": 4.7296,
      "step": 206
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000412,
      "loss": 4.4467,
      "step": 207
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000414,
      "loss": 4.7099,
      "step": 208
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000416,
      "loss": 4.6622,
      "step": 209
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00041799999999999997,
      "loss": 4.9508,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00042,
      "loss": 4.4373,
      "step": 211
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000422,
      "loss": 4.748,
      "step": 212
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000424,
      "loss": 4.623,
      "step": 213
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000426,
      "loss": 4.5733,
      "step": 214
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000428,
      "loss": 4.6245,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00043,
      "loss": 4.6892,
      "step": 216
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000432,
      "loss": 4.6396,
      "step": 217
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00043400000000000003,
      "loss": 4.6174,
      "step": 218
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000436,
      "loss": 4.7913,
      "step": 219
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000438,
      "loss": 4.6375,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00044,
      "loss": 4.5069,
      "step": 221
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000442,
      "loss": 4.7579,
      "step": 222
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000444,
      "loss": 4.7951,
      "step": 223
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000446,
      "loss": 4.9794,
      "step": 224
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000448,
      "loss": 4.8345,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00045000000000000004,
      "loss": 4.6178,
      "step": 226
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00045200000000000004,
      "loss": 4.9773,
      "step": 227
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00045400000000000003,
      "loss": 4.6117,
      "step": 228
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000456,
      "loss": 4.5106,
      "step": 229
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000458,
      "loss": 4.5805,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00046,
      "loss": 4.634,
      "step": 231
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000462,
      "loss": 4.4508,
      "step": 232
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00046400000000000006,
      "loss": 4.7686,
      "step": 233
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00046600000000000005,
      "loss": 4.6839,
      "step": 234
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00046800000000000005,
      "loss": 4.8609,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00047,
      "loss": 4.5689,
      "step": 236
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000472,
      "loss": 4.5626,
      "step": 237
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000474,
      "loss": 4.4552,
      "step": 238
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00047599999999999997,
      "loss": 4.6341,
      "step": 239
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00047799999999999996,
      "loss": 4.7347,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00048,
      "loss": 4.5554,
      "step": 241
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000482,
      "loss": 5.1093,
      "step": 242
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000484,
      "loss": 4.8549,
      "step": 243
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000486,
      "loss": 4.7953,
      "step": 244
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000488,
      "loss": 5.1484,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00049,
      "loss": 4.5329,
      "step": 246
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000492,
      "loss": 4.4645,
      "step": 247
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000494,
      "loss": 5.3223,
      "step": 248
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000496,
      "loss": 6.4257,
      "step": 249
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000498,
      "loss": 6.3633,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005,
      "loss": 6.1391,
      "step": 251
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005020000000000001,
      "loss": 5.3127,
      "step": 252
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000504,
      "loss": 4.912,
      "step": 253
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000506,
      "loss": 4.6873,
      "step": 254
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000508,
      "loss": 4.9215,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00051,
      "loss": 4.6735,
      "step": 256
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000512,
      "loss": 5.0567,
      "step": 257
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000514,
      "loss": 5.2453,
      "step": 258
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005160000000000001,
      "loss": 4.8018,
      "step": 259
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000518,
      "loss": 5.2815,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005200000000000001,
      "loss": 4.7621,
      "step": 261
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000522,
      "loss": 4.6185,
      "step": 262
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000524,
      "loss": 4.9622,
      "step": 263
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000526,
      "loss": 4.9574,
      "step": 264
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000528,
      "loss": 4.6961,
      "step": 265
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005300000000000001,
      "loss": 4.8911,
      "step": 266
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000532,
      "loss": 4.8782,
      "step": 267
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005340000000000001,
      "loss": 4.9493,
      "step": 268
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000536,
      "loss": 4.8858,
      "step": 269
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005380000000000001,
      "loss": 5.1246,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00054,
      "loss": 4.5835,
      "step": 271
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005420000000000001,
      "loss": 4.6087,
      "step": 272
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005440000000000001,
      "loss": 4.7457,
      "step": 273
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000546,
      "loss": 4.8951,
      "step": 274
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0005480000000000001,
      "loss": 5.3403,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00055,
      "loss": 4.6695,
      "step": 276
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0005520000000000001,
      "loss": 4.783,
      "step": 277
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000554,
      "loss": 4.7711,
      "step": 278
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005560000000000001,
      "loss": 5.0676,
      "step": 279
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000558,
      "loss": 4.8579,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005600000000000001,
      "loss": 5.0367,
      "step": 281
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005620000000000001,
      "loss": 4.9462,
      "step": 282
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005639999999999999,
      "loss": 4.7645,
      "step": 283
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000566,
      "loss": 4.6745,
      "step": 284
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005679999999999999,
      "loss": 4.9527,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00057,
      "loss": 4.9766,
      "step": 286
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005719999999999999,
      "loss": 5.3699,
      "step": 287
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000574,
      "loss": 4.7668,
      "step": 288
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000576,
      "loss": 4.6789,
      "step": 289
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000578,
      "loss": 5.0322,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00058,
      "loss": 5.2736,
      "step": 291
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005819999999999999,
      "loss": 5.0443,
      "step": 292
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000584,
      "loss": 4.8732,
      "step": 293
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005859999999999999,
      "loss": 5.166,
      "step": 294
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000588,
      "loss": 4.8355,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00059,
      "loss": 4.8877,
      "step": 296
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000592,
      "loss": 5.2269,
      "step": 297
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000594,
      "loss": 17.9702,
      "step": 298
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000596,
      "loss": 5.7343,
      "step": 299
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000598,
      "loss": 5.515,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0006,
      "loss": 5.3824,
      "step": 301
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000602,
      "loss": 5.148,
      "step": 302
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000604,
      "loss": 4.8959,
      "step": 303
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000606,
      "loss": 5.0647,
      "step": 304
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000608,
      "loss": 4.8941,
      "step": 305
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00061,
      "loss": 4.8608,
      "step": 306
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000612,
      "loss": 5.2265,
      "step": 307
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000614,
      "loss": 5.0575,
      "step": 308
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000616,
      "loss": 4.9254,
      "step": 309
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006180000000000001,
      "loss": 4.9891,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00062,
      "loss": 4.5658,
      "step": 311
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000622,
      "loss": 4.9779,
      "step": 312
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000624,
      "loss": 5.3951,
      "step": 313
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000626,
      "loss": 4.796,
      "step": 314
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000628,
      "loss": 4.8412,
      "step": 315
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00063,
      "loss": 4.6783,
      "step": 316
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000632,
      "loss": 4.7405,
      "step": 317
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000634,
      "loss": 4.6025,
      "step": 318
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006360000000000001,
      "loss": 4.8142,
      "step": 319
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000638,
      "loss": 4.8876,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00064,
      "loss": 4.8069,
      "step": 321
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000642,
      "loss": 4.8133,
      "step": 322
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000644,
      "loss": 4.7322,
      "step": 323
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000646,
      "loss": 4.5794,
      "step": 324
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000648,
      "loss": 5.0187,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006500000000000001,
      "loss": 5.1333,
      "step": 326
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000652,
      "loss": 4.7612,
      "step": 327
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006540000000000001,
      "loss": 4.6401,
      "step": 328
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000656,
      "loss": 4.7183,
      "step": 329
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006580000000000001,
      "loss": 4.8948,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00066,
      "loss": 4.7955,
      "step": 331
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000662,
      "loss": 4.7045,
      "step": 332
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0006640000000000001,
      "loss": 4.9097,
      "step": 333
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000666,
      "loss": 4.924,
      "step": 334
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0006680000000000001,
      "loss": 4.8816,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00067,
      "loss": 4.6617,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006720000000000001,
      "loss": 4.8668,
      "step": 337
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000674,
      "loss": 4.813,
      "step": 338
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006760000000000001,
      "loss": 4.869,
      "step": 339
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006780000000000001,
      "loss": 4.9609,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00068,
      "loss": 4.735,
      "step": 341
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006820000000000001,
      "loss": 6.541,
      "step": 342
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000684,
      "loss": 5.0304,
      "step": 343
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006860000000000001,
      "loss": 4.9253,
      "step": 344
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006879999999999999,
      "loss": 4.7216,
      "step": 345
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00069,
      "loss": 4.8354,
      "step": 346
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000692,
      "loss": 4.8476,
      "step": 347
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000694,
      "loss": 4.8727,
      "step": 348
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000696,
      "loss": 5.0211,
      "step": 349
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0006979999999999999,
      "loss": 4.7231,
      "step": 350
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0007,
      "loss": 6.3094,
      "step": 351
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0007019999999999999,
      "loss": 5.0654,
      "step": 352
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000704,
      "loss": 4.8125,
      "step": 353
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0007059999999999999,
      "loss": 4.9841,
      "step": 354
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000708,
      "loss": 4.9406,
      "step": 355
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00071,
      "loss": 5.3482,
      "step": 356
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000712,
      "loss": 5.2098,
      "step": 357
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000714,
      "loss": 5.0179,
      "step": 358
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000716,
      "loss": 4.8699,
      "step": 359
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000718,
      "loss": 4.8703,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0007199999999999999,
      "loss": 4.8909,
      "step": 361
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000722,
      "loss": 4.8246,
      "step": 362
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000724,
      "loss": 4.6949,
      "step": 363
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000726,
      "loss": 5.0433,
      "step": 364
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000728,
      "loss": 5.055,
      "step": 365
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00073,
      "loss": 4.7938,
      "step": 366
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000732,
      "loss": 4.8905,
      "step": 367
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000734,
      "loss": 4.7919,
      "step": 368
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000736,
      "loss": 4.7992,
      "step": 369
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000738,
      "loss": 4.7454,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00074,
      "loss": 4.8729,
      "step": 371
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000742,
      "loss": 4.8837,
      "step": 372
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000744,
      "loss": 4.7922,
      "step": 373
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000746,
      "loss": 4.6167,
      "step": 374
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000748,
      "loss": 4.7867,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00075,
      "loss": 4.708,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0007520000000000001,
      "loss": 4.7856,
      "step": 377
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000754,
      "loss": 4.8291,
      "step": 378
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000756,
      "loss": 4.8428,
      "step": 379
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000758,
      "loss": 4.7221,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00076,
      "loss": 5.227,
      "step": 381
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000762,
      "loss": 5.304,
      "step": 382
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000764,
      "loss": 4.8953,
      "step": 383
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0007660000000000001,
      "loss": 4.7784,
      "step": 384
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000768,
      "loss": 4.874,
      "step": 385
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0007700000000000001,
      "loss": 4.727,
      "step": 386
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000772,
      "loss": 4.9384,
      "step": 387
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0007740000000000001,
      "loss": 4.8338,
      "step": 388
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000776,
      "loss": 4.8328,
      "step": 389
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000778,
      "loss": 4.7213,
      "step": 390
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0007800000000000001,
      "loss": 4.9069,
      "step": 391
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000782,
      "loss": 4.97,
      "step": 392
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0007840000000000001,
      "loss": 4.7095,
      "step": 393
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000786,
      "loss": 4.7421,
      "step": 394
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007880000000000001,
      "loss": 4.8849,
      "step": 395
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00079,
      "loss": 5.2645,
      "step": 396
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007920000000000001,
      "loss": 5.1189,
      "step": 397
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007940000000000001,
      "loss": 4.8777,
      "step": 398
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000796,
      "loss": 5.253,
      "step": 399
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007980000000000001,
      "loss": 4.937,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0008,
      "loss": 5.2032,
      "step": 401
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0008020000000000001,
      "loss": 5.0266,
      "step": 402
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000804,
      "loss": 5.1012,
      "step": 403
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008060000000000001,
      "loss": 4.9038,
      "step": 404
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000808,
      "loss": 4.8848,
      "step": 405
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008100000000000001,
      "loss": 5.2038,
      "step": 406
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008120000000000001,
      "loss": 4.9554,
      "step": 407
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008139999999999999,
      "loss": 5.1101,
      "step": 408
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000816,
      "loss": 4.8516,
      "step": 409
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008179999999999999,
      "loss": 4.6971,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00082,
      "loss": 5.1527,
      "step": 411
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008219999999999999,
      "loss": 4.9715,
      "step": 412
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000824,
      "loss": 4.6715,
      "step": 413
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000826,
      "loss": 5.0357,
      "step": 414
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000828,
      "loss": 5.0545,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00083,
      "loss": 4.9108,
      "step": 416
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000832,
      "loss": 5.2884,
      "step": 417
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000834,
      "loss": 4.8856,
      "step": 418
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0008359999999999999,
      "loss": 5.253,
      "step": 419
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000838,
      "loss": 5.1539,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00084,
      "loss": 5.2202,
      "step": 421
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000842,
      "loss": 4.7612,
      "step": 422
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000844,
      "loss": 4.8588,
      "step": 423
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000846,
      "loss": 5.0295,
      "step": 424
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000848,
      "loss": 4.7428,
      "step": 425
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00085,
      "loss": 4.7598,
      "step": 426
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000852,
      "loss": 4.7621,
      "step": 427
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000854,
      "loss": 4.7438,
      "step": 428
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000856,
      "loss": 4.5182,
      "step": 429
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000858,
      "loss": 5.0404,
      "step": 430
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00086,
      "loss": 4.814,
      "step": 431
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000862,
      "loss": 5.1218,
      "step": 432
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000864,
      "loss": 4.7879,
      "step": 433
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000866,
      "loss": 4.8229,
      "step": 434
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0008680000000000001,
      "loss": 5.1322,
      "step": 435
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00087,
      "loss": 4.6759,
      "step": 436
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000872,
      "loss": 4.9387,
      "step": 437
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000874,
      "loss": 5.0383,
      "step": 438
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000876,
      "loss": 4.9599,
      "step": 439
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000878,
      "loss": 4.9917,
      "step": 440
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00088,
      "loss": 4.7285,
      "step": 441
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000882,
      "loss": 5.0258,
      "step": 442
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000884,
      "loss": 6.6035,
      "step": 443
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0008860000000000001,
      "loss": 5.1825,
      "step": 444
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000888,
      "loss": 5.0386,
      "step": 445
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0008900000000000001,
      "loss": 4.8899,
      "step": 446
    },
    {
      "epoch": 1.0,
      "step": 446,
      "total_flos": 0.0,
      "train_loss": 4.734800568610563,
      "train_runtime": 5167.9675,
      "train_samples_per_second": 5.522,
      "train_steps_per_second": 0.086
    }
  ],
  "max_steps": 446,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}