{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 892,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 4.7965,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 5.0502,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-06,
      "loss": 4.9118,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-06,
      "loss": 4.8924,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 4.713,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-06,
      "loss": 4.7862,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 4.7066,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 4.5681,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4e-05,
      "loss": 4.6685,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6e-05,
      "loss": 4.4888,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 4.566,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.4834,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2e-05,
      "loss": 4.4308,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.4e-05,
      "loss": 4.3983,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.6e-05,
      "loss": 4.3274,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.8e-05,
      "loss": 4.4187,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 3e-05,
      "loss": 4.4051,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2e-05,
      "loss": 4.5591,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 4.2522,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 4.4396,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8e-05,
      "loss": 4.341,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 4.3206,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 4.3652,
      "step": 23
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.4e-05,
      "loss": 4.4403,
      "step": 24
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.6e-05,
      "loss": 4.3302,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.8e-05,
      "loss": 4.5044,
      "step": 26
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 4.2454,
      "step": 27
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2e-05,
      "loss": 4.1507,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.4e-05,
      "loss": 4.1699,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6e-05,
      "loss": 4.3846,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.800000000000001e-05,
      "loss": 4.3922,
      "step": 31
    },
    {
      "epoch": 0.04,
      "learning_rate": 6e-05,
      "loss": 4.1628,
      "step": 32
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.2e-05,
      "loss": 4.2404,
      "step": 33
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.4e-05,
      "loss": 4.1711,
      "step": 34
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.6e-05,
      "loss": 4.3801,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.3257,
      "step": 36
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.000000000000001e-05,
      "loss": 4.3421,
      "step": 37
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.2e-05,
      "loss": 4.3652,
      "step": 38
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.4e-05,
      "loss": 4.5053,
      "step": 39
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 4.3429,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.8e-05,
      "loss": 4.2031,
      "step": 41
    },
    {
      "epoch": 0.05,
      "learning_rate": 8e-05,
      "loss": 4.3582,
      "step": 42
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.2e-05,
      "loss": 4.1308,
      "step": 43
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.400000000000001e-05,
      "loss": 4.3577,
      "step": 44
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.599999999999999e-05,
      "loss": 4.3479,
      "step": 45
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.8e-05,
      "loss": 4.552,
      "step": 46
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.3865,
      "step": 47
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.2e-05,
      "loss": 4.7344,
      "step": 48
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.400000000000001e-05,
      "loss": 4.8671,
      "step": 49
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.6e-05,
      "loss": 4.6237,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.800000000000001e-05,
      "loss": 4.2275,
      "step": 51
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 4.4134,
      "step": 52
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000102,
      "loss": 4.2124,
      "step": 53
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000104,
      "loss": 4.2647,
      "step": 54
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000106,
      "loss": 4.2844,
      "step": 55
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000108,
      "loss": 4.3499,
      "step": 56
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011,
      "loss": 4.3192,
      "step": 57
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000112,
      "loss": 4.5597,
      "step": 58
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000114,
      "loss": 4.3034,
      "step": 59
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00011600000000000001,
      "loss": 4.2302,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000118,
      "loss": 4.4397,
      "step": 61
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00012,
      "loss": 4.4027,
      "step": 62
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000122,
      "loss": 4.2169,
      "step": 63
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000124,
      "loss": 4.3468,
      "step": 64
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000126,
      "loss": 4.1751,
      "step": 65
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000128,
      "loss": 4.3815,
      "step": 66
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013000000000000002,
      "loss": 4.1777,
      "step": 67
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000132,
      "loss": 4.2333,
      "step": 68
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000134,
      "loss": 4.1581,
      "step": 69
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013600000000000003,
      "loss": 4.3495,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013800000000000002,
      "loss": 4.5026,
      "step": 71
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00014000000000000001,
      "loss": 4.4102,
      "step": 72
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00014199999999999998,
      "loss": 4.3022,
      "step": 73
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000144,
      "loss": 4.3463,
      "step": 74
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000146,
      "loss": 4.2018,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000148,
      "loss": 4.4457,
      "step": 76
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00015,
      "loss": 4.3321,
      "step": 77
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000152,
      "loss": 4.3216,
      "step": 78
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000154,
      "loss": 4.1577,
      "step": 79
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000156,
      "loss": 4.4279,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000158,
      "loss": 4.4479,
      "step": 81
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00016,
      "loss": 4.2937,
      "step": 82
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000162,
      "loss": 4.8258,
      "step": 83
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000164,
      "loss": 4.4215,
      "step": 84
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00016600000000000002,
      "loss": 4.4092,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00016800000000000002,
      "loss": 4.3837,
      "step": 86
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017,
      "loss": 4.3505,
      "step": 87
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017199999999999998,
      "loss": 4.3491,
      "step": 88
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000174,
      "loss": 4.4475,
      "step": 89
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000176,
      "loss": 4.3947,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000178,
      "loss": 4.7094,
      "step": 91
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.5694,
      "step": 92
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000182,
      "loss": 4.2909,
      "step": 93
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000184,
      "loss": 4.4371,
      "step": 94
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000186,
      "loss": 4.7291,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018800000000000002,
      "loss": 4.6914,
      "step": 96
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019,
      "loss": 4.5874,
      "step": 97
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000192,
      "loss": 4.7773,
      "step": 98
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000194,
      "loss": 4.4424,
      "step": 99
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019600000000000002,
      "loss": 4.7924,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019800000000000002,
      "loss": 4.5736,
      "step": 101
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 4.6228,
      "step": 102
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000202,
      "loss": 4.4887,
      "step": 103
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000204,
      "loss": 4.4669,
      "step": 104
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000206,
      "loss": 4.485,
      "step": 105
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000208,
      "loss": 4.4893,
      "step": 106
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00021,
      "loss": 4.5879,
      "step": 107
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000212,
      "loss": 4.6778,
      "step": 108
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000214,
      "loss": 4.2605,
      "step": 109
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000216,
      "loss": 4.431,
      "step": 110
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000218,
      "loss": 4.52,
      "step": 111
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00022,
      "loss": 4.5446,
      "step": 112
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000222,
      "loss": 4.4884,
      "step": 113
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000224,
      "loss": 4.3684,
      "step": 114
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00022600000000000002,
      "loss": 4.5161,
      "step": 115
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000228,
      "loss": 4.1576,
      "step": 116
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00023,
      "loss": 4.4825,
      "step": 117
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00023200000000000003,
      "loss": 4.3964,
      "step": 118
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00023400000000000002,
      "loss": 4.5091,
      "step": 119
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000236,
      "loss": 4.5291,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00023799999999999998,
      "loss": 4.4232,
      "step": 121
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00024,
      "loss": 4.4717,
      "step": 122
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000242,
      "loss": 4.274,
      "step": 123
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000244,
      "loss": 4.4989,
      "step": 124
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000246,
      "loss": 4.55,
      "step": 125
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000248,
      "loss": 4.5464,
      "step": 126
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00025,
      "loss": 4.5534,
      "step": 127
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000252,
      "loss": 4.4587,
      "step": 128
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000254,
      "loss": 4.3396,
      "step": 129
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000256,
      "loss": 4.6201,
      "step": 130
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00025800000000000004,
      "loss": 4.4956,
      "step": 131
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00026000000000000003,
      "loss": 4.6595,
      "step": 132
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000262,
      "loss": 4.5596,
      "step": 133
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000264,
      "loss": 4.6203,
      "step": 134
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000266,
      "loss": 4.3535,
      "step": 135
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000268,
      "loss": 4.4372,
      "step": 136
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00027,
      "loss": 4.684,
      "step": 137
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00027200000000000005,
      "loss": 5.0621,
      "step": 138
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00027400000000000005,
      "loss": 4.5093,
      "step": 139
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00027600000000000004,
      "loss": 4.4214,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00027800000000000004,
      "loss": 4.7394,
      "step": 141
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00028000000000000003,
      "loss": 4.7751,
      "step": 142
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00028199999999999997,
      "loss": 4.6543,
      "step": 143
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00028399999999999996,
      "loss": 4.5343,
      "step": 144
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00028599999999999996,
      "loss": 5.3579,
      "step": 145
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000288,
      "loss": 4.9072,
      "step": 146
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00029,
      "loss": 4.7826,
      "step": 147
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000292,
      "loss": 4.6273,
      "step": 148
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000294,
      "loss": 5.0711,
      "step": 149
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000296,
      "loss": 4.6724,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000298,
      "loss": 4.8402,
      "step": 151
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 4.9597,
      "step": 152
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000302,
      "loss": 4.8801,
      "step": 153
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000304,
      "loss": 4.5698,
      "step": 154
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000306,
      "loss": 4.5396,
      "step": 155
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000308,
      "loss": 4.7222,
      "step": 156
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00031,
      "loss": 5.0516,
      "step": 157
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000312,
      "loss": 4.8873,
      "step": 158
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000314,
      "loss": 4.9982,
      "step": 159
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000316,
      "loss": 4.7088,
      "step": 160
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00031800000000000003,
      "loss": 4.6326,
      "step": 161
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00032,
      "loss": 4.636,
      "step": 162
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000322,
      "loss": 4.6224,
      "step": 163
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000324,
      "loss": 4.8179,
      "step": 164
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000326,
      "loss": 4.6294,
      "step": 165
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000328,
      "loss": 4.7156,
      "step": 166
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00033,
      "loss": 4.6405,
      "step": 167
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00033200000000000005,
      "loss": 4.5294,
      "step": 168
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00033400000000000004,
      "loss": 5.4458,
      "step": 169
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00033600000000000004,
      "loss": 4.7599,
      "step": 170
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00033800000000000003,
      "loss": 4.8152,
      "step": 171
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00034,
      "loss": 4.9118,
      "step": 172
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000342,
      "loss": 4.6432,
      "step": 173
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00034399999999999996,
      "loss": 4.5836,
      "step": 174
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000346,
      "loss": 4.5978,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000348,
      "loss": 4.6663,
      "step": 176
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00035,
      "loss": 4.7834,
      "step": 177
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000352,
      "loss": 4.6238,
      "step": 178
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000354,
      "loss": 4.6915,
      "step": 179
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000356,
      "loss": 4.7074,
      "step": 180
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000358,
      "loss": 4.6754,
      "step": 181
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00035999999999999997,
      "loss": 4.751,
      "step": 182
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000362,
      "loss": 4.653,
      "step": 183
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000364,
      "loss": 4.9619,
      "step": 184
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000366,
      "loss": 4.8057,
      "step": 185
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000368,
      "loss": 4.6844,
      "step": 186
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00037,
      "loss": 4.8071,
      "step": 187
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000372,
      "loss": 4.5574,
      "step": 188
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000374,
      "loss": 4.65,
      "step": 189
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00037600000000000003,
      "loss": 4.6756,
      "step": 190
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000378,
      "loss": 4.7344,
      "step": 191
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00038,
      "loss": 4.8258,
      "step": 192
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000382,
      "loss": 4.8066,
      "step": 193
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000384,
      "loss": 4.6763,
      "step": 194
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000386,
      "loss": 5.9026,
      "step": 195
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000388,
      "loss": 5.2934,
      "step": 196
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039000000000000005,
      "loss": 5.1461,
      "step": 197
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039200000000000004,
      "loss": 7.1754,
      "step": 198
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039400000000000004,
      "loss": 5.788,
      "step": 199
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039600000000000003,
      "loss": 5.1586,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000398,
      "loss": 4.9359,
      "step": 201
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004,
      "loss": 5.1274,
      "step": 202
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000402,
      "loss": 5.4457,
      "step": 203
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000404,
      "loss": 4.8784,
      "step": 204
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00040600000000000006,
      "loss": 4.7054,
      "step": 205
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000408,
      "loss": 4.8631,
      "step": 206
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00041,
      "loss": 4.7219,
      "step": 207
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000412,
      "loss": 4.5005,
      "step": 208
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000414,
      "loss": 4.7144,
      "step": 209
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000416,
      "loss": 4.8477,
      "step": 210
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00041799999999999997,
      "loss": 4.9471,
      "step": 211
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00042,
      "loss": 4.8034,
      "step": 212
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000422,
      "loss": 4.9817,
      "step": 213
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000424,
      "loss": 4.8543,
      "step": 214
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000426,
      "loss": 4.5916,
      "step": 215
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000428,
      "loss": 4.8308,
      "step": 216
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00043,
      "loss": 5.0146,
      "step": 217
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000432,
      "loss": 4.7929,
      "step": 218
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00043400000000000003,
      "loss": 4.7524,
      "step": 219
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000436,
      "loss": 4.9242,
      "step": 220
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000438,
      "loss": 4.6412,
      "step": 221
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00044,
      "loss": 4.7249,
      "step": 222
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000442,
      "loss": 4.9072,
      "step": 223
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000444,
      "loss": 4.7815,
      "step": 224
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000446,
      "loss": 4.9337,
      "step": 225
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000448,
      "loss": 4.988,
      "step": 226
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00045000000000000004,
      "loss": 4.9625,
      "step": 227
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00045200000000000004,
      "loss": 5.0409,
      "step": 228
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00045400000000000003,
      "loss": 5.2279,
      "step": 229
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000456,
      "loss": 5.0434,
      "step": 230
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000458,
      "loss": 5.5576,
      "step": 231
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00046,
      "loss": 4.9453,
      "step": 232
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000462,
      "loss": 4.8898,
      "step": 233
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00046400000000000006,
      "loss": 4.9863,
      "step": 234
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00046600000000000005,
      "loss": 5.1805,
      "step": 235
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00046800000000000005,
      "loss": 4.7755,
      "step": 236
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00047,
      "loss": 4.703,
      "step": 237
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000472,
      "loss": 5.0463,
      "step": 238
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000474,
      "loss": 4.7303,
      "step": 239
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00047599999999999997,
      "loss": 4.8589,
      "step": 240
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00047799999999999996,
      "loss": 4.9848,
      "step": 241
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00048,
      "loss": 5.3981,
      "step": 242
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000482,
      "loss": 5.5512,
      "step": 243
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000484,
      "loss": 4.8617,
      "step": 244
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000486,
      "loss": 5.081,
      "step": 245
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000488,
      "loss": 4.9583,
      "step": 246
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00049,
      "loss": 5.7793,
      "step": 247
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000492,
      "loss": 5.4057,
      "step": 248
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000494,
      "loss": 5.7089,
      "step": 249
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000496,
      "loss": 4.8237,
      "step": 250
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000498,
      "loss": 5.4087,
      "step": 251
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005,
      "loss": 5.0223,
      "step": 252
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005020000000000001,
      "loss": 5.0797,
      "step": 253
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000504,
      "loss": 4.8901,
      "step": 254
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000506,
      "loss": 5.1356,
      "step": 255
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000508,
      "loss": 5.0586,
      "step": 256
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00051,
      "loss": 5.1246,
      "step": 257
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000512,
      "loss": 4.8986,
      "step": 258
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000514,
      "loss": 4.8121,
      "step": 259
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005160000000000001,
      "loss": 4.8494,
      "step": 260
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000518,
      "loss": 4.8734,
      "step": 261
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005200000000000001,
      "loss": 4.9371,
      "step": 262
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000522,
      "loss": 4.7398,
      "step": 263
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000524,
      "loss": 4.8513,
      "step": 264
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000526,
      "loss": 5.242,
      "step": 265
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000528,
      "loss": 5.0909,
      "step": 266
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005300000000000001,
      "loss": 5.0276,
      "step": 267
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000532,
      "loss": 5.2137,
      "step": 268
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005340000000000001,
      "loss": 4.7544,
      "step": 269
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000536,
      "loss": 5.0531,
      "step": 270
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005380000000000001,
      "loss": 4.7155,
      "step": 271
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00054,
      "loss": 4.9672,
      "step": 272
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005420000000000001,
      "loss": 5.1118,
      "step": 273
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005440000000000001,
      "loss": 4.766,
      "step": 274
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000546,
      "loss": 5.2889,
      "step": 275
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005480000000000001,
      "loss": 5.2023,
      "step": 276
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00055,
      "loss": 4.9661,
      "step": 277
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005520000000000001,
      "loss": 4.6719,
      "step": 278
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000554,
      "loss": 4.9073,
      "step": 279
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005560000000000001,
      "loss": 5.0293,
      "step": 280
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000558,
      "loss": 4.7573,
      "step": 281
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005600000000000001,
      "loss": 4.7975,
      "step": 282
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005620000000000001,
      "loss": 4.7992,
      "step": 283
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005639999999999999,
      "loss": 5.0759,
      "step": 284
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000566,
      "loss": 5.1917,
      "step": 285
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005679999999999999,
      "loss": 4.9202,
      "step": 286
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00057,
      "loss": 5.34,
      "step": 287
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005719999999999999,
      "loss": 4.9242,
      "step": 288
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000574,
      "loss": 5.155,
      "step": 289
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000576,
      "loss": 5.1764,
      "step": 290
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000578,
      "loss": 4.9208,
      "step": 291
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00058,
      "loss": 4.7409,
      "step": 292
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005819999999999999,
      "loss": 6.5954,
      "step": 293
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000584,
      "loss": 5.0484,
      "step": 294
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005859999999999999,
      "loss": 4.7468,
      "step": 295
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000588,
      "loss": 5.7964,
      "step": 296
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00059,
      "loss": 5.9083,
      "step": 297
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000592,
      "loss": 5.1705,
      "step": 298
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000594,
      "loss": 5.4384,
      "step": 299
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000596,
      "loss": 5.4224,
      "step": 300
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000598,
      "loss": 5.329,
      "step": 301
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0006,
      "loss": 4.9936,
      "step": 302
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000602,
      "loss": 4.911,
      "step": 303
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000604,
      "loss": 4.9691,
      "step": 304
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000606,
      "loss": 5.0028,
      "step": 305
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000608,
      "loss": 4.8037,
      "step": 306
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00061,
      "loss": 4.8418,
      "step": 307
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000612,
      "loss": 5.2496,
      "step": 308
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000614,
      "loss": 5.2615,
      "step": 309
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000616,
      "loss": 5.1208,
      "step": 310
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0006180000000000001,
      "loss": 5.1199,
      "step": 311
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00062,
      "loss": 4.9914,
      "step": 312
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000622,
      "loss": 5.042,
      "step": 313
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000624,
      "loss": 4.9409,
      "step": 314
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000626,
      "loss": 4.8236,
      "step": 315
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000628,
      "loss": 5.1062,
      "step": 316
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00063,
      "loss": 4.823,
      "step": 317
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000632,
      "loss": 4.9081,
      "step": 318
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000634,
      "loss": 4.8754,
      "step": 319
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0006360000000000001,
      "loss": 4.8727,
      "step": 320
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000638,
      "loss": 5.2652,
      "step": 321
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00064,
      "loss": 4.7925,
      "step": 322
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000642,
      "loss": 4.7254,
      "step": 323
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000644,
      "loss": 5.2596,
      "step": 324
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000646,
      "loss": 5.1065,
      "step": 325
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000648,
      "loss": 5.0236,
      "step": 326
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0006500000000000001,
      "loss": 4.7007,
      "step": 327
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000652,
      "loss": 4.9706,
      "step": 328
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0006540000000000001,
      "loss": 5.3651,
      "step": 329
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000656,
      "loss": 5.3813,
      "step": 330
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0006580000000000001,
      "loss": 4.9263,
      "step": 331
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00066,
      "loss": 4.8357,
      "step": 332
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000662,
      "loss": 5.0999,
      "step": 333
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0006640000000000001,
      "loss": 5.017,
      "step": 334
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000666,
      "loss": 5.0555,
      "step": 335
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006680000000000001,
      "loss": 5.0284,
      "step": 336
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00067,
      "loss": 4.7011,
      "step": 337
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006720000000000001,
      "loss": 4.9937,
      "step": 338
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000674,
      "loss": 4.9687,
      "step": 339
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006760000000000001,
      "loss": 4.8688,
      "step": 340
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006780000000000001,
      "loss": 5.2171,
      "step": 341
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00068,
      "loss": 4.9272,
      "step": 342
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0006820000000000001,
      "loss": 5.4399,
      "step": 343
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000684,
      "loss": 5.0394,
      "step": 344
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0006860000000000001,
      "loss": 4.89,
      "step": 345
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0006879999999999999,
      "loss": 5.3467,
      "step": 346
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00069,
      "loss": 6.7675,
      "step": 347
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000692,
      "loss": 5.0929,
      "step": 348
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000694,
      "loss": 5.1975,
      "step": 349
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000696,
      "loss": 5.1623,
      "step": 350
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0006979999999999999,
      "loss": 5.7402,
      "step": 351
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0007,
      "loss": 5.0554,
      "step": 352
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0007019999999999999,
      "loss": 5.1392,
      "step": 353
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000704,
      "loss": 5.3242,
      "step": 354
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0007059999999999999,
      "loss": 6.0127,
      "step": 355
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000708,
      "loss": 5.3057,
      "step": 356
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00071,
      "loss": 5.3195,
      "step": 357
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000712,
      "loss": 5.2799,
      "step": 358
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000714,
      "loss": 5.2069,
      "step": 359
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000716,
      "loss": 5.1036,
      "step": 360
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000718,
      "loss": 5.2433,
      "step": 361
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0007199999999999999,
      "loss": 5.0837,
      "step": 362
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000722,
      "loss": 4.8481,
      "step": 363
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000724,
      "loss": 5.1938,
      "step": 364
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000726,
      "loss": 4.8737,
      "step": 365
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000728,
      "loss": 5.2159,
      "step": 366
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00073,
      "loss": 5.0045,
      "step": 367
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000732,
      "loss": 5.1269,
      "step": 368
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000734,
      "loss": 5.185,
      "step": 369
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000736,
      "loss": 5.2436,
      "step": 370
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000738,
      "loss": 4.9266,
      "step": 371
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00074,
      "loss": 5.1939,
      "step": 372
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000742,
      "loss": 5.1638,
      "step": 373
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000744,
      "loss": 5.5325,
      "step": 374
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000746,
      "loss": 4.8427,
      "step": 375
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000748,
      "loss": 5.1271,
      "step": 376
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00075,
      "loss": 4.8144,
      "step": 377
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0007520000000000001,
      "loss": 5.1655,
      "step": 378
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000754,
      "loss": 4.9469,
      "step": 379
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000756,
      "loss": 5.1108,
      "step": 380
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000758,
      "loss": 4.9925,
      "step": 381
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00076,
      "loss": 5.1714,
      "step": 382
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000762,
      "loss": 6.4374,
      "step": 383
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000764,
      "loss": 5.0459,
      "step": 384
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0007660000000000001,
      "loss": 4.9586,
      "step": 385
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000768,
      "loss": 5.0668,
      "step": 386
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0007700000000000001,
      "loss": 5.0477,
      "step": 387
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000772,
      "loss": 4.9241,
      "step": 388
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0007740000000000001,
      "loss": 5.2005,
      "step": 389
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000776,
      "loss": 5.6056,
      "step": 390
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000778,
      "loss": 5.4428,
      "step": 391
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0007800000000000001,
      "loss": 5.4239,
      "step": 392
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000782,
      "loss": 5.3807,
      "step": 393
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0007840000000000001,
      "loss": 5.2934,
      "step": 394
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000786,
      "loss": 6.1639,
      "step": 395
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0007880000000000001,
      "loss": 5.2127,
      "step": 396
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00079,
      "loss": 6.2097,
      "step": 397
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0007920000000000001,
      "loss": 5.2827,
      "step": 398
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0007940000000000001,
      "loss": 5.1212,
      "step": 399
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000796,
      "loss": 5.472,
      "step": 400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0007980000000000001,
      "loss": 5.4401,
      "step": 401
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0008,
      "loss": 5.2793,
      "step": 402
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0008020000000000001,
      "loss": 5.4463,
      "step": 403
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000804,
      "loss": 5.0944,
      "step": 404
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0008060000000000001,
      "loss": 5.3147,
      "step": 405
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000808,
      "loss": 5.3533,
      "step": 406
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008100000000000001,
      "loss": 5.163,
      "step": 407
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008120000000000001,
      "loss": 5.0185,
      "step": 408
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008139999999999999,
      "loss": 5.3798,
      "step": 409
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000816,
      "loss": 5.3974,
      "step": 410
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008179999999999999,
      "loss": 5.0302,
      "step": 411
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00082,
      "loss": 5.1526,
      "step": 412
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008219999999999999,
      "loss": 5.8772,
      "step": 413
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000824,
      "loss": 4.8392,
      "step": 414
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000826,
      "loss": 5.1069,
      "step": 415
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000828,
      "loss": 5.1643,
      "step": 416
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00083,
      "loss": 4.9795,
      "step": 417
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000832,
      "loss": 5.216,
      "step": 418
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000834,
      "loss": 5.0386,
      "step": 419
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0008359999999999999,
      "loss": 5.0863,
      "step": 420
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000838,
      "loss": 4.9586,
      "step": 421
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00084,
      "loss": 5.2313,
      "step": 422
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000842,
      "loss": 6.1135,
      "step": 423
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000844,
      "loss": 5.0778,
      "step": 424
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000846,
      "loss": 5.1118,
      "step": 425
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000848,
      "loss": 5.2043,
      "step": 426
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00085,
      "loss": 4.9702,
      "step": 427
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000852,
      "loss": 5.3167,
      "step": 428
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000854,
      "loss": 4.9597,
      "step": 429
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000856,
      "loss": 5.115,
      "step": 430
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000858,
      "loss": 5.4418,
      "step": 431
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00086,
      "loss": 5.1764,
      "step": 432
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000862,
      "loss": 4.8251,
      "step": 433
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000864,
      "loss": 5.2088,
      "step": 434
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000866,
      "loss": 5.0211,
      "step": 435
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008680000000000001,
      "loss": 5.2176,
      "step": 436
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00087,
      "loss": 5.2249,
      "step": 437
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000872,
      "loss": 5.118,
      "step": 438
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000874,
      "loss": 5.1533,
      "step": 439
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000876,
      "loss": 5.0237,
      "step": 440
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000878,
      "loss": 5.3436,
      "step": 441
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00088,
      "loss": 4.9092,
      "step": 442
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000882,
      "loss": 5.0294,
      "step": 443
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000884,
      "loss": 5.5218,
      "step": 444
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008860000000000001,
      "loss": 4.9374,
      "step": 445
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000888,
      "loss": 4.821,
      "step": 446
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008900000000000001,
      "loss": 4.9246,
      "step": 447
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000892,
      "loss": 7.544,
      "step": 448
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000894,
      "loss": 6.0168,
      "step": 449
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000896,
      "loss": 7.3071,
      "step": 450
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000898,
      "loss": 5.3956,
      "step": 451
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009000000000000001,
      "loss": 5.48,
      "step": 452
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000902,
      "loss": 5.4334,
      "step": 453
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009040000000000001,
      "loss": 5.0337,
      "step": 454
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000906,
      "loss": 5.4256,
      "step": 455
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009080000000000001,
      "loss": 5.3247,
      "step": 456
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00091,
      "loss": 5.2336,
      "step": 457
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000912,
      "loss": 5.3589,
      "step": 458
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009140000000000001,
      "loss": 5.2095,
      "step": 459
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000916,
      "loss": 5.3384,
      "step": 460
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009180000000000001,
      "loss": 4.9632,
      "step": 461
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00092,
      "loss": 5.3328,
      "step": 462
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009220000000000001,
      "loss": 5.5567,
      "step": 463
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000924,
      "loss": 4.9068,
      "step": 464
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009260000000000001,
      "loss": 5.1143,
      "step": 465
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009280000000000001,
      "loss": 5.3116,
      "step": 466
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00093,
      "loss": 5.0797,
      "step": 467
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009320000000000001,
      "loss": 5.1186,
      "step": 468
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000934,
      "loss": 5.4416,
      "step": 469
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009360000000000001,
      "loss": 5.1664,
      "step": 470
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009379999999999999,
      "loss": 4.9481,
      "step": 471
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00094,
      "loss": 4.9097,
      "step": 472
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000942,
      "loss": 5.6217,
      "step": 473
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000944,
      "loss": 5.1009,
      "step": 474
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000946,
      "loss": 5.3705,
      "step": 475
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000948,
      "loss": 5.418,
      "step": 476
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00095,
      "loss": 5.5494,
      "step": 477
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009519999999999999,
      "loss": 5.0258,
      "step": 478
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000954,
      "loss": 5.0919,
      "step": 479
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009559999999999999,
      "loss": 5.0294,
      "step": 480
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000958,
      "loss": 5.0032,
      "step": 481
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00096,
      "loss": 5.3622,
      "step": 482
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000962,
      "loss": 5.016,
      "step": 483
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000964,
      "loss": 5.3424,
      "step": 484
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000966,
      "loss": 5.3396,
      "step": 485
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000968,
      "loss": 4.9877,
      "step": 486
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009699999999999999,
      "loss": 5.0559,
      "step": 487
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000972,
      "loss": 4.8909,
      "step": 488
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000974,
      "loss": 5.3144,
      "step": 489
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000976,
      "loss": 5.2026,
      "step": 490
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000978,
      "loss": 4.904,
      "step": 491
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00098,
      "loss": 5.5084,
      "step": 492
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000982,
      "loss": 5.2827,
      "step": 493
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000984,
      "loss": 5.1398,
      "step": 494
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009860000000000001,
      "loss": 5.5595,
      "step": 495
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000988,
      "loss": 4.8808,
      "step": 496
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00099,
      "loss": 4.8302,
      "step": 497
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000992,
      "loss": 5.6899,
      "step": 498
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000994,
      "loss": 5.4486,
      "step": 499
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000996,
      "loss": 4.7246,
      "step": 500
    },
    {
      "epoch": 0.56,
      "eval_loss": 5.553798675537109,
      "eval_runtime": 947.3214,
      "eval_samples_per_second": 2.789,
      "eval_steps_per_second": 0.349,
      "eval_wer": 2.01330821102737,
      "step": 500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000998,
      "loss": 6.2615,
      "step": 501
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001,
      "loss": 4.9686,
      "step": 502
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0009974489795918369,
      "loss": 5.2496,
      "step": 503
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009948979591836735,
      "loss": 5.4162,
      "step": 504
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00099234693877551,
      "loss": 5.3041,
      "step": 505
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000989795918367347,
      "loss": 5.2386,
      "step": 506
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009872448979591838,
      "loss": 5.3472,
      "step": 507
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009846938775510204,
      "loss": 5.1626,
      "step": 508
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009821428571428572,
      "loss": 5.3774,
      "step": 509
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009795918367346938,
      "loss": 5.6755,
      "step": 510
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009770408163265307,
      "loss": 5.1559,
      "step": 511
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009744897959183674,
      "loss": 5.0161,
      "step": 512
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009719387755102041,
      "loss": 5.6675,
      "step": 513
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009693877551020408,
      "loss": 5.1173,
      "step": 514
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009668367346938776,
      "loss": 5.2748,
      "step": 515
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009642857142857143,
      "loss": 5.033,
      "step": 516
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009617346938775511,
      "loss": 5.2472,
      "step": 517
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009591836734693877,
      "loss": 5.1146,
      "step": 518
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009566326530612245,
      "loss": 5.4533,
      "step": 519
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009540816326530613,
      "loss": 5.4604,
      "step": 520
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000951530612244898,
      "loss": 5.3102,
      "step": 521
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009489795918367348,
      "loss": 5.0594,
      "step": 522
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009464285714285714,
      "loss": 5.3375,
      "step": 523
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009438775510204082,
      "loss": 5.2176,
      "step": 524
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009413265306122449,
      "loss": 5.9862,
      "step": 525
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009387755102040817,
      "loss": 5.0509,
      "step": 526
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009362244897959184,
      "loss": 5.1616,
      "step": 527
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009336734693877551,
      "loss": 5.1956,
      "step": 528
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009311224489795918,
      "loss": 5.795,
      "step": 529
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009285714285714287,
      "loss": 5.4817,
      "step": 530
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009260204081632653,
      "loss": 5.6069,
      "step": 531
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000923469387755102,
      "loss": 4.8953,
      "step": 532
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009209183673469387,
      "loss": 4.9381,
      "step": 533
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009183673469387756,
      "loss": 4.9541,
      "step": 534
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009158163265306123,
      "loss": 5.0257,
      "step": 535
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009132653061224489,
      "loss": 5.4078,
      "step": 536
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009107142857142857,
      "loss": 5.3974,
      "step": 537
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009081632653061225,
      "loss": 5.3991,
      "step": 538
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009056122448979592,
      "loss": 5.2251,
      "step": 539
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0009030612244897959,
      "loss": 5.3175,
      "step": 540
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0009005102040816327,
      "loss": 5.361,
      "step": 541
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008979591836734694,
      "loss": 5.3854,
      "step": 542
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008954081632653062,
      "loss": 5.2583,
      "step": 543
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008928571428571429,
      "loss": 5.4731,
      "step": 544
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008903061224489796,
      "loss": 6.1977,
      "step": 545
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008877551020408163,
      "loss": 5.2304,
      "step": 546
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008852040816326531,
      "loss": 5.8843,
      "step": 547
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0008826530612244898,
      "loss": 5.4071,
      "step": 548
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008801020408163265,
      "loss": 5.0849,
      "step": 549
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008775510204081633,
      "loss": 5.8482,
      "step": 550
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000875,
      "loss": 5.2635,
      "step": 551
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008724489795918367,
      "loss": 5.418,
      "step": 552
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008698979591836736,
      "loss": 5.2408,
      "step": 553
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008673469387755102,
      "loss": 5.0475,
      "step": 554
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008647959183673469,
      "loss": 5.0966,
      "step": 555
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008622448979591838,
      "loss": 5.0922,
      "step": 556
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0008596938775510205,
      "loss": 4.9667,
      "step": 557
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008571428571428571,
      "loss": 5.2674,
      "step": 558
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008545918367346938,
      "loss": 5.0393,
      "step": 559
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008520408163265307,
      "loss": 5.0971,
      "step": 560
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008494897959183674,
      "loss": 5.1893,
      "step": 561
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008469387755102041,
      "loss": 5.0583,
      "step": 562
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008443877551020408,
      "loss": 5.1257,
      "step": 563
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008418367346938776,
      "loss": 5.0834,
      "step": 564
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008392857142857143,
      "loss": 5.148,
      "step": 565
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0008367346938775511,
      "loss": 5.06,
      "step": 566
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008341836734693877,
      "loss": 5.0448,
      "step": 567
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008316326530612245,
      "loss": 4.8972,
      "step": 568
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008290816326530613,
      "loss": 4.9932,
      "step": 569
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000826530612244898,
      "loss": 5.1723,
      "step": 570
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008239795918367348,
      "loss": 4.9847,
      "step": 571
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008214285714285714,
      "loss": 5.0464,
      "step": 572
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008188775510204082,
      "loss": 5.0259,
      "step": 573
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008163265306122449,
      "loss": 5.5426,
      "step": 574
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0008137755102040817,
      "loss": 5.3417,
      "step": 575
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008112244897959184,
      "loss": 5.0017,
      "step": 576
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008086734693877551,
      "loss": 5.0695,
      "step": 577
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008061224489795918,
      "loss": 5.1576,
      "step": 578
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008035714285714287,
      "loss": 4.7052,
      "step": 579
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008010204081632653,
      "loss": 5.4356,
      "step": 580
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000798469387755102,
      "loss": 5.1405,
      "step": 581
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0007959183673469387,
      "loss": 4.9729,
      "step": 582
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0007933673469387756,
      "loss": 5.4895,
      "step": 583
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0007908163265306123,
      "loss": 5.0296,
      "step": 584
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007882653061224489,
      "loss": 5.7285,
      "step": 585
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007857142857142857,
      "loss": 5.4251,
      "step": 586
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007831632653061225,
      "loss": 5.603,
      "step": 587
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007806122448979592,
      "loss": 4.9566,
      "step": 588
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007780612244897959,
      "loss": 4.9453,
      "step": 589
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007755102040816326,
      "loss": 5.4635,
      "step": 590
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007729591836734694,
      "loss": 5.0545,
      "step": 591
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007704081632653062,
      "loss": 5.6657,
      "step": 592
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0007678571428571429,
      "loss": 5.4611,
      "step": 593
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007653061224489796,
      "loss": 4.968,
      "step": 594
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007627551020408163,
      "loss": 5.477,
      "step": 595
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007602040816326531,
      "loss": 5.3628,
      "step": 596
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007576530612244898,
      "loss": 5.1578,
      "step": 597
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007551020408163265,
      "loss": 5.3148,
      "step": 598
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007525510204081633,
      "loss": 5.5493,
      "step": 599
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00075,
      "loss": 4.9865,
      "step": 600
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007474489795918367,
      "loss": 5.2224,
      "step": 601
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0007448979591836736,
      "loss": 5.1809,
      "step": 602
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007423469387755102,
      "loss": 5.2736,
      "step": 603
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007397959183673469,
      "loss": 5.1739,
      "step": 604
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007372448979591838,
      "loss": 5.0983,
      "step": 605
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007346938775510205,
      "loss": 4.9385,
      "step": 606
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007321428571428571,
      "loss": 5.867,
      "step": 607
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007295918367346938,
      "loss": 5.0564,
      "step": 608
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007270408163265307,
      "loss": 5.1008,
      "step": 609
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007244897959183674,
      "loss": 5.1949,
      "step": 610
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0007219387755102041,
      "loss": 4.9015,
      "step": 611
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007193877551020408,
      "loss": 5.1184,
      "step": 612
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007168367346938776,
      "loss": 5.2819,
      "step": 613
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007142857142857143,
      "loss": 5.0992,
      "step": 614
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007117346938775511,
      "loss": 5.1966,
      "step": 615
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007091836734693877,
      "loss": 4.9135,
      "step": 616
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007066326530612245,
      "loss": 5.1225,
      "step": 617
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007040816326530613,
      "loss": 4.8598,
      "step": 618
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000701530612244898,
      "loss": 4.8324,
      "step": 619
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006989795918367347,
      "loss": 5.01,
      "step": 620
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006964285714285714,
      "loss": 5.0319,
      "step": 621
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006938775510204082,
      "loss": 4.9734,
      "step": 622
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006913265306122449,
      "loss": 5.05,
      "step": 623
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006887755102040817,
      "loss": 5.0356,
      "step": 624
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006862244897959184,
      "loss": 5.3868,
      "step": 625
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006836734693877551,
      "loss": 5.0528,
      "step": 626
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006811224489795918,
      "loss": 5.0486,
      "step": 627
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006785714285714287,
      "loss": 4.9144,
      "step": 628
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006760204081632653,
      "loss": 4.923,
      "step": 629
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000673469387755102,
      "loss": 5.2818,
      "step": 630
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006709183673469387,
      "loss": 4.9389,
      "step": 631
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006683673469387756,
      "loss": 5.6102,
      "step": 632
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006658163265306123,
      "loss": 5.0466,
      "step": 633
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006632653061224489,
      "loss": 4.9354,
      "step": 634
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006607142857142857,
      "loss": 5.1228,
      "step": 635
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006581632653061225,
      "loss": 4.937,
      "step": 636
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0006556122448979592,
      "loss": 4.9867,
      "step": 637
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006530612244897959,
      "loss": 4.7481,
      "step": 638
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006505102040816326,
      "loss": 5.1057,
      "step": 639
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006479591836734694,
      "loss": 4.8321,
      "step": 640
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006454081632653062,
      "loss": 4.8926,
      "step": 641
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006428571428571429,
      "loss": 6.7244,
      "step": 642
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006403061224489795,
      "loss": 5.5171,
      "step": 643
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006377551020408163,
      "loss": 4.8591,
      "step": 644
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006352040816326531,
      "loss": 4.7389,
      "step": 645
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006326530612244898,
      "loss": 4.997,
      "step": 646
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006301020408163265,
      "loss": 4.9194,
      "step": 647
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006275510204081633,
      "loss": 5.0819,
      "step": 648
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000625,
      "loss": 5.2145,
      "step": 649
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006224489795918367,
      "loss": 4.8832,
      "step": 650
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006198979591836736,
      "loss": 5.3171,
      "step": 651
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006173469387755102,
      "loss": 5.2764,
      "step": 652
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006147959183673469,
      "loss": 5.0498,
      "step": 653
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006122448979591838,
      "loss": 5.2789,
      "step": 654
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0006096938775510205,
      "loss": 4.9983,
      "step": 655
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006071428571428571,
      "loss": 5.055,
      "step": 656
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006045918367346938,
      "loss": 4.9124,
      "step": 657
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006020408163265307,
      "loss": 5.1472,
      "step": 658
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005994897959183674,
      "loss": 4.9621,
      "step": 659
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005969387755102041,
      "loss": 5.1466,
      "step": 660
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005943877551020408,
      "loss": 4.7999,
      "step": 661
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005918367346938776,
      "loss": 4.7113,
      "step": 662
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005892857142857143,
      "loss": 5.2727,
      "step": 663
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0005867346938775511,
      "loss": 4.9338,
      "step": 664
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005841836734693877,
      "loss": 4.8416,
      "step": 665
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005816326530612245,
      "loss": 5.1135,
      "step": 666
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005790816326530613,
      "loss": 4.9375,
      "step": 667
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000576530612244898,
      "loss": 4.909,
      "step": 668
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005739795918367347,
      "loss": 5.1056,
      "step": 669
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005714285714285714,
      "loss": 5.0018,
      "step": 670
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005688775510204082,
      "loss": 4.7696,
      "step": 671
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005663265306122449,
      "loss": 4.9088,
      "step": 672
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0005637755102040816,
      "loss": 4.7722,
      "step": 673
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005612244897959184,
      "loss": 4.8107,
      "step": 674
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005586734693877551,
      "loss": 4.9513,
      "step": 675
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005561224489795918,
      "loss": 5.549,
      "step": 676
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005535714285714287,
      "loss": 4.8031,
      "step": 677
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005510204081632653,
      "loss": 4.6527,
      "step": 678
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000548469387755102,
      "loss": 4.8261,
      "step": 679
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005459183673469387,
      "loss": 4.8573,
      "step": 680
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005433673469387756,
      "loss": 5.1294,
      "step": 681
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0005408163265306123,
      "loss": 4.6851,
      "step": 682
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005382653061224489,
      "loss": 5.119,
      "step": 683
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005357142857142857,
      "loss": 5.217,
      "step": 684
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005331632653061225,
      "loss": 4.9345,
      "step": 685
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005306122448979592,
      "loss": 5.0111,
      "step": 686
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005280612244897959,
      "loss": 4.9354,
      "step": 687
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005255102040816326,
      "loss": 4.9864,
      "step": 688
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005229591836734694,
      "loss": 4.9079,
      "step": 689
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005204081632653062,
      "loss": 5.2492,
      "step": 690
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0005178571428571429,
      "loss": 4.9012,
      "step": 691
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005153061224489795,
      "loss": 4.9484,
      "step": 692
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005127551020408163,
      "loss": 4.7525,
      "step": 693
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005102040816326531,
      "loss": 5.2413,
      "step": 694
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005076530612244898,
      "loss": 5.0768,
      "step": 695
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005051020408163265,
      "loss": 5.1833,
      "step": 696
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005025510204081633,
      "loss": 5.3869,
      "step": 697
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0005,
      "loss": 5.0354,
      "step": 698
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004974489795918367,
      "loss": 5.0789,
      "step": 699
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004948979591836735,
      "loss": 4.9279,
      "step": 700
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004923469387755102,
      "loss": 4.7946,
      "step": 701
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004897959183673469,
      "loss": 4.9595,
      "step": 702
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004872448979591837,
      "loss": 4.7994,
      "step": 703
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004846938775510204,
      "loss": 4.9163,
      "step": 704
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00048214285714285715,
      "loss": 4.9548,
      "step": 705
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00047959183673469387,
      "loss": 5.1581,
      "step": 706
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00047704081632653065,
      "loss": 4.9996,
      "step": 707
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004744897959183674,
      "loss": 5.1511,
      "step": 708
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004719387755102041,
      "loss": 4.9985,
      "step": 709
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046938775510204083,
      "loss": 5.0571,
      "step": 710
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046683673469387755,
      "loss": 5.1134,
      "step": 711
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046428571428571433,
      "loss": 4.7978,
      "step": 712
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000461734693877551,
      "loss": 4.6712,
      "step": 713
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004591836734693878,
      "loss": 4.9959,
      "step": 714
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00045663265306122446,
      "loss": 5.1947,
      "step": 715
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00045408163265306124,
      "loss": 4.8231,
      "step": 716
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00045153061224489796,
      "loss": 5.09,
      "step": 717
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004489795918367347,
      "loss": 4.7469,
      "step": 718
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00044642857142857147,
      "loss": 4.8668,
      "step": 719
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00044387755102040814,
      "loss": 4.841,
      "step": 720
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004413265306122449,
      "loss": 4.7433,
      "step": 721
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00043877551020408165,
      "loss": 4.7101,
      "step": 722
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00043622448979591837,
      "loss": 4.8642,
      "step": 723
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004336734693877551,
      "loss": 4.9878,
      "step": 724
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004311224489795919,
      "loss": 4.8054,
      "step": 725
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00042857142857142855,
      "loss": 5.0236,
      "step": 726
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00042602040816326533,
      "loss": 4.8533,
      "step": 727
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00042346938775510206,
      "loss": 4.6959,
      "step": 728
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004209183673469388,
      "loss": 4.6739,
      "step": 729
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00041836734693877556,
      "loss": 5.0312,
      "step": 730
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00041581632653061223,
      "loss": 5.2839,
      "step": 731
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000413265306122449,
      "loss": 4.9503,
      "step": 732
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004107142857142857,
      "loss": 4.8103,
      "step": 733
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00040816326530612246,
      "loss": 4.9057,
      "step": 734
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004056122448979592,
      "loss": 4.6994,
      "step": 735
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004030612244897959,
      "loss": 4.8075,
      "step": 736
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00040051020408163264,
      "loss": 4.8765,
      "step": 737
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00039795918367346937,
      "loss": 4.843,
      "step": 738
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00039540816326530615,
      "loss": 4.6777,
      "step": 739
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003928571428571429,
      "loss": 5.0097,
      "step": 740
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003903061224489796,
      "loss": 5.0502,
      "step": 741
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003877551020408163,
      "loss": 4.7957,
      "step": 742
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003852040816326531,
      "loss": 4.6631,
      "step": 743
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003826530612244898,
      "loss": 4.8876,
      "step": 744
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00038010204081632656,
      "loss": 4.6636,
      "step": 745
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00037755102040816323,
      "loss": 5.2342,
      "step": 746
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000375,
      "loss": 4.753,
      "step": 747
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003724489795918368,
      "loss": 4.8729,
      "step": 748
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00036989795918367346,
      "loss": 5.0168,
      "step": 749
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00036734693877551024,
      "loss": 4.9339,
      "step": 750
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003647959183673469,
      "loss": 4.9065,
      "step": 751
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003622448979591837,
      "loss": 4.8276,
      "step": 752
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003596938775510204,
      "loss": 4.8596,
      "step": 753
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00035714285714285714,
      "loss": 4.8511,
      "step": 754
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00035459183673469387,
      "loss": 4.8633,
      "step": 755
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00035204081632653065,
      "loss": 5.1471,
      "step": 756
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003494897959183674,
      "loss": 5.0629,
      "step": 757
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003469387755102041,
      "loss": 4.8626,
      "step": 758
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003443877551020408,
      "loss": 4.7699,
      "step": 759
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034183673469387755,
      "loss": 4.7787,
      "step": 760
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00033928571428571433,
      "loss": 4.8297,
      "step": 761
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000336734693877551,
      "loss": 4.6865,
      "step": 762
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003341836734693878,
      "loss": 4.691,
      "step": 763
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00033163265306122445,
      "loss": 4.5826,
      "step": 764
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00032908163265306123,
      "loss": 5.1117,
      "step": 765
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00032653061224489796,
      "loss": 5.0025,
      "step": 766
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003239795918367347,
      "loss": 4.6712,
      "step": 767
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00032142857142857147,
      "loss": 5.162,
      "step": 768
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00031887755102040814,
      "loss": 4.8693,
      "step": 769
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003163265306122449,
      "loss": 4.7581,
      "step": 770
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00031377551020408164,
      "loss": 4.7253,
      "step": 771
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00031122448979591837,
      "loss": 4.8999,
      "step": 772
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003086734693877551,
      "loss": 4.9918,
      "step": 773
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003061224489795919,
      "loss": 4.5347,
      "step": 774
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00030357142857142855,
      "loss": 4.4954,
      "step": 775
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003010204081632653,
      "loss": 5.0078,
      "step": 776
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029846938775510205,
      "loss": 4.6184,
      "step": 777
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002959183673469388,
      "loss": 4.9227,
      "step": 778
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029336734693877556,
      "loss": 4.667,
      "step": 779
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00029081632653061223,
      "loss": 4.7333,
      "step": 780
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000288265306122449,
      "loss": 4.6473,
      "step": 781
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002857142857142857,
      "loss": 4.7418,
      "step": 782
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00028316326530612246,
      "loss": 4.8777,
      "step": 783
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002806122448979592,
      "loss": 4.5377,
      "step": 784
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002780612244897959,
      "loss": 4.7229,
      "step": 785
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00027551020408163264,
      "loss": 4.6596,
      "step": 786
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00027295918367346936,
      "loss": 4.8652,
      "step": 787
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00027040816326530614,
      "loss": 4.8039,
      "step": 788
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00026785714285714287,
      "loss": 4.7242,
      "step": 789
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002653061224489796,
      "loss": 4.7512,
      "step": 790
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002627551020408163,
      "loss": 4.75,
      "step": 791
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002602040816326531,
      "loss": 4.5709,
      "step": 792
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002576530612244898,
      "loss": 4.7332,
      "step": 793
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00025510204081632655,
      "loss": 4.8817,
      "step": 794
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002525510204081632,
      "loss": 4.9428,
      "step": 795
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00025,
      "loss": 4.5729,
      "step": 796
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024744897959183673,
      "loss": 4.8771,
      "step": 797
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024489795918367346,
      "loss": 4.8702,
      "step": 798
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002423469387755102,
      "loss": 5.4777,
      "step": 799
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023979591836734694,
      "loss": 5.01,
      "step": 800
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002372448979591837,
      "loss": 4.8871,
      "step": 801
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023469387755102041,
      "loss": 4.6433,
      "step": 802
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023214285714285717,
      "loss": 4.8369,
      "step": 803
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002295918367346939,
      "loss": 4.7214,
      "step": 804
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00022704081632653062,
      "loss": 4.5577,
      "step": 805
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00022448979591836734,
      "loss": 4.9597,
      "step": 806
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00022193877551020407,
      "loss": 4.6841,
      "step": 807
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021938775510204082,
      "loss": 4.6865,
      "step": 808
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021683673469387755,
      "loss": 4.9089,
      "step": 809
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021428571428571427,
      "loss": 4.4829,
      "step": 810
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021173469387755103,
      "loss": 4.8973,
      "step": 811
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020918367346938778,
      "loss": 4.8187,
      "step": 812
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002066326530612245,
      "loss": 4.5545,
      "step": 813
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020408163265306123,
      "loss": 4.7104,
      "step": 814
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020153061224489796,
      "loss": 4.5445,
      "step": 815
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019897959183673468,
      "loss": 4.6521,
      "step": 816
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019642857142857144,
      "loss": 4.762,
      "step": 817
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019387755102040816,
      "loss": 4.6711,
      "step": 818
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001913265306122449,
      "loss": 4.7525,
      "step": 819
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018877551020408161,
      "loss": 4.6909,
      "step": 820
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001862244897959184,
      "loss": 4.628,
      "step": 821
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018367346938775512,
      "loss": 4.4963,
      "step": 822
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018112244897959185,
      "loss": 4.6785,
      "step": 823
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017857142857142857,
      "loss": 4.6588,
      "step": 824
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017602040816326532,
      "loss": 5.0121,
      "step": 825
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00017346938775510205,
      "loss": 4.7394,
      "step": 826
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00017091836734693878,
      "loss": 4.6542,
      "step": 827
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001683673469387755,
      "loss": 4.5092,
      "step": 828
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016581632653061223,
      "loss": 4.5507,
      "step": 829
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016326530612244898,
      "loss": 4.8904,
      "step": 830
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016071428571428573,
      "loss": 4.4503,
      "step": 831
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00015816326530612246,
      "loss": 4.5233,
      "step": 832
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00015561224489795918,
      "loss": 4.7851,
      "step": 833
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00015306122448979594,
      "loss": 4.5912,
      "step": 834
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015051020408163266,
      "loss": 4.5898,
      "step": 835
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001479591836734694,
      "loss": 4.782,
      "step": 836
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00014540816326530611,
      "loss": 4.5167,
      "step": 837
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00014285714285714284,
      "loss": 4.8074,
      "step": 838
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001403061224489796,
      "loss": 4.5436,
      "step": 839
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013775510204081632,
      "loss": 4.7421,
      "step": 840
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013520408163265307,
      "loss": 4.833,
      "step": 841
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001326530612244898,
      "loss": 4.5748,
      "step": 842
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013010204081632655,
      "loss": 4.9057,
      "step": 843
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00012755102040816328,
      "loss": 4.7376,
      "step": 844
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000125,
      "loss": 4.9631,
      "step": 845
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00012244897959183673,
      "loss": 8.4938,
      "step": 846
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011989795918367347,
      "loss": 4.594,
      "step": 847
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011734693877551021,
      "loss": 5.1287,
      "step": 848
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011479591836734695,
      "loss": 4.8459,
      "step": 849
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011224489795918367,
      "loss": 4.7704,
      "step": 850
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010969387755102041,
      "loss": 4.6765,
      "step": 851
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010714285714285714,
      "loss": 4.9124,
      "step": 852
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010459183673469389,
      "loss": 4.7199,
      "step": 853
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00010204081632653062,
      "loss": 4.6014,
      "step": 854
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.948979591836734e-05,
      "loss": 4.6581,
      "step": 855
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.693877551020408e-05,
      "loss": 4.5992,
      "step": 856
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.438775510204081e-05,
      "loss": 4.873,
      "step": 857
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.183673469387756e-05,
      "loss": 4.6767,
      "step": 858
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.928571428571429e-05,
      "loss": 4.4785,
      "step": 859
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.673469387755102e-05,
      "loss": 4.6034,
      "step": 860
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.418367346938775e-05,
      "loss": 4.926,
      "step": 861
    },
    {
      "epoch": 0.97,
      "learning_rate": 8.163265306122449e-05,
      "loss": 4.6059,
      "step": 862
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.908163265306123e-05,
      "loss": 4.6713,
      "step": 863
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.653061224489797e-05,
      "loss": 4.9771,
      "step": 864
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.39795918367347e-05,
      "loss": 4.7271,
      "step": 865
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.142857142857142e-05,
      "loss": 4.7206,
      "step": 866
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.887755102040816e-05,
      "loss": 4.7444,
      "step": 867
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.63265306122449e-05,
      "loss": 4.6091,
      "step": 868
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.377551020408164e-05,
      "loss": 4.5961,
      "step": 869
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.122448979591836e-05,
      "loss": 4.6923,
      "step": 870
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.8673469387755104e-05,
      "loss": 4.5866,
      "step": 871
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.6122448979591836e-05,
      "loss": 4.6059,
      "step": 872
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.357142857142857e-05,
      "loss": 4.6245,
      "step": 873
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.102040816326531e-05,
      "loss": 4.592,
      "step": 874
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.846938775510204e-05,
      "loss": 4.7475,
      "step": 875
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.591836734693878e-05,
      "loss": 4.4702,
      "step": 876
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.336734693877551e-05,
      "loss": 4.4525,
      "step": 877
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.0816326530612245e-05,
      "loss": 4.6854,
      "step": 878
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.8265306122448984e-05,
      "loss": 4.6533,
      "step": 879
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.571428571428571e-05,
      "loss": 4.9238,
      "step": 880
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.316326530612245e-05,
      "loss": 4.4336,
      "step": 881
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.061224489795918e-05,
      "loss": 4.6463,
      "step": 882
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.8061224489795918e-05,
      "loss": 4.5835,
      "step": 883
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5510204081632654e-05,
      "loss": 4.5467,
      "step": 884
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.295918367346939e-05,
      "loss": 4.5758,
      "step": 885
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.0408163265306123e-05,
      "loss": 4.664,
      "step": 886
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.7857142857142855e-05,
      "loss": 4.5767,
      "step": 887
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.530612244897959e-05,
      "loss": 4.7443,
      "step": 888
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2755102040816327e-05,
      "loss": 4.7622,
      "step": 889
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0204081632653061e-05,
      "loss": 4.4401,
      "step": 890
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.653061224489796e-06,
      "loss": 4.8296,
      "step": 891
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.102040816326531e-06,
      "loss": 4.2487,
      "step": 892
    },
    {
      "epoch": 1.0,
      "step": 892,
      "total_flos": 0.0,
      "train_loss": 4.944881099221952,
      "train_runtime": 6324.9374,
      "train_samples_per_second": 4.512,
      "train_steps_per_second": 0.141
    }
  ],
  "max_steps": 892,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}