{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995796553173603,
  "global_step": 1189,
  "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": 4.8511,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 5.0392,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-06,
      "loss": 5.0449,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-06,
      "loss": 4.8611,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 4.5775,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-06,
      "loss": 4.895,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 4.619,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 4.5561,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 4.7099,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4e-05,
      "loss": 4.5353,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6e-05,
      "loss": 4.5746,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 4.4166,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.6183,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2e-05,
      "loss": 4.3869,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 4.2778,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6e-05,
      "loss": 4.4726,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8e-05,
      "loss": 4.4224,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 3e-05,
      "loss": 4.5754,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2e-05,
      "loss": 4.2828,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 4.4854,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 4.4592,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8e-05,
      "loss": 4.336,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 4.4397,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 4.4482,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4e-05,
      "loss": 4.2657,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.6e-05,
      "loss": 4.4489,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 4.3049,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 4.1245,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2e-05,
      "loss": 4.1784,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.4e-05,
      "loss": 4.2998,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6e-05,
      "loss": 4.4284,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.800000000000001e-05,
      "loss": 4.2353,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 4.3895,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.2e-05,
      "loss": 4.0501,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.4e-05,
      "loss": 4.2444,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.6e-05,
      "loss": 4.5839,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.3782,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.000000000000001e-05,
      "loss": 4.2556,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 4.7111,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.4e-05,
      "loss": 4.4187,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.6e-05,
      "loss": 4.1914,
      "step": 41
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.8e-05,
      "loss": 4.2891,
      "step": 42
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 4.2439,
      "step": 43
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.2e-05,
      "loss": 4.2867,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.400000000000001e-05,
      "loss": 4.4894,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.599999999999999e-05,
      "loss": 4.4172,
      "step": 46
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.8e-05,
      "loss": 4.6963,
      "step": 47
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.7471,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.2e-05,
      "loss": 4.9014,
      "step": 49
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.400000000000001e-05,
      "loss": 4.7686,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.6e-05,
      "loss": 4.368,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.800000000000001e-05,
      "loss": 4.3822,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 4.2264,
      "step": 53
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000102,
      "loss": 4.2716,
      "step": 54
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000104,
      "loss": 4.4112,
      "step": 55
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000106,
      "loss": 4.191,
      "step": 56
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000108,
      "loss": 4.4509,
      "step": 57
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011,
      "loss": 4.4127,
      "step": 58
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000112,
      "loss": 4.2537,
      "step": 59
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000114,
      "loss": 4.4896,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011600000000000001,
      "loss": 4.2308,
      "step": 61
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000118,
      "loss": 4.4071,
      "step": 62
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00012,
      "loss": 4.2868,
      "step": 63
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000122,
      "loss": 4.1752,
      "step": 64
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000124,
      "loss": 4.1496,
      "step": 65
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000126,
      "loss": 4.2547,
      "step": 66
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000128,
      "loss": 4.3735,
      "step": 67
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013000000000000002,
      "loss": 4.243,
      "step": 68
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000132,
      "loss": 4.2763,
      "step": 69
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000134,
      "loss": 4.3281,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013600000000000003,
      "loss": 4.5117,
      "step": 71
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013800000000000002,
      "loss": 4.4156,
      "step": 72
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00014000000000000001,
      "loss": 4.2873,
      "step": 73
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00014199999999999998,
      "loss": 4.4208,
      "step": 74
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000144,
      "loss": 4.2238,
      "step": 75
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000146,
      "loss": 4.5864,
      "step": 76
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000148,
      "loss": 4.4607,
      "step": 77
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015,
      "loss": 4.2875,
      "step": 78
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000152,
      "loss": 4.2922,
      "step": 79
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000154,
      "loss": 4.4421,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000156,
      "loss": 4.433,
      "step": 81
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000158,
      "loss": 4.3725,
      "step": 82
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016,
      "loss": 4.3333,
      "step": 83
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000162,
      "loss": 4.4473,
      "step": 84
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000164,
      "loss": 4.4238,
      "step": 85
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016600000000000002,
      "loss": 4.3154,
      "step": 86
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016800000000000002,
      "loss": 4.2695,
      "step": 87
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00017,
      "loss": 4.4924,
      "step": 88
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00017199999999999998,
      "loss": 4.5737,
      "step": 89
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000174,
      "loss": 4.457,
      "step": 90
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000176,
      "loss": 4.5949,
      "step": 91
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000178,
      "loss": 4.5588,
      "step": 92
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.1973,
      "step": 93
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000182,
      "loss": 4.5561,
      "step": 94
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000184,
      "loss": 4.7577,
      "step": 95
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000186,
      "loss": 4.6404,
      "step": 96
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018800000000000002,
      "loss": 4.6471,
      "step": 97
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019,
      "loss": 4.7406,
      "step": 98
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000192,
      "loss": 4.6403,
      "step": 99
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000194,
      "loss": 4.444,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019600000000000002,
      "loss": 4.3784,
      "step": 101
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019800000000000002,
      "loss": 4.6657,
      "step": 102
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 4.4524,
      "step": 103
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000202,
      "loss": 4.6985,
      "step": 104
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000204,
      "loss": 4.6463,
      "step": 105
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000206,
      "loss": 4.5927,
      "step": 106
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000208,
      "loss": 4.6364,
      "step": 107
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00021,
      "loss": 4.6561,
      "step": 108
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000212,
      "loss": 4.8036,
      "step": 109
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000214,
      "loss": 4.4123,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000216,
      "loss": 4.6414,
      "step": 111
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000218,
      "loss": 4.7836,
      "step": 112
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00022,
      "loss": 4.412,
      "step": 113
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000222,
      "loss": 4.6303,
      "step": 114
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000224,
      "loss": 4.5641,
      "step": 115
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00022600000000000002,
      "loss": 4.7007,
      "step": 116
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000228,
      "loss": 4.4402,
      "step": 117
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00023,
      "loss": 4.2599,
      "step": 118
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00023200000000000003,
      "loss": 4.3835,
      "step": 119
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00023400000000000002,
      "loss": 4.3983,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000236,
      "loss": 4.8916,
      "step": 121
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00023799999999999998,
      "loss": 4.5147,
      "step": 122
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00024,
      "loss": 4.555,
      "step": 123
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000242,
      "loss": 4.6935,
      "step": 124
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000244,
      "loss": 4.3677,
      "step": 125
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000246,
      "loss": 4.515,
      "step": 126
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000248,
      "loss": 4.6372,
      "step": 127
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00025,
      "loss": 4.4019,
      "step": 128
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000252,
      "loss": 4.3392,
      "step": 129
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000254,
      "loss": 4.5796,
      "step": 130
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000256,
      "loss": 4.5943,
      "step": 131
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00025800000000000004,
      "loss": 4.4655,
      "step": 132
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00026000000000000003,
      "loss": 4.8017,
      "step": 133
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000262,
      "loss": 4.5575,
      "step": 134
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000264,
      "loss": 4.6614,
      "step": 135
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000266,
      "loss": 4.4765,
      "step": 136
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000268,
      "loss": 4.5643,
      "step": 137
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00027,
      "loss": 4.666,
      "step": 138
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00027200000000000005,
      "loss": 4.6639,
      "step": 139
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00027400000000000005,
      "loss": 4.6461,
      "step": 140
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00027600000000000004,
      "loss": 4.8226,
      "step": 141
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00027800000000000004,
      "loss": 4.5566,
      "step": 142
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028000000000000003,
      "loss": 4.4941,
      "step": 143
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028199999999999997,
      "loss": 4.8677,
      "step": 144
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028399999999999996,
      "loss": 5.048,
      "step": 145
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028599999999999996,
      "loss": 4.8524,
      "step": 146
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000288,
      "loss": 4.9183,
      "step": 147
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00029,
      "loss": 4.4394,
      "step": 148
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000292,
      "loss": 5.5298,
      "step": 149
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000294,
      "loss": 4.7055,
      "step": 150
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000296,
      "loss": 4.8902,
      "step": 151
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000298,
      "loss": 4.8158,
      "step": 152
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 4.7027,
      "step": 153
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000302,
      "loss": 4.7774,
      "step": 154
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000304,
      "loss": 4.7513,
      "step": 155
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000306,
      "loss": 4.5636,
      "step": 156
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000308,
      "loss": 4.6546,
      "step": 157
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00031,
      "loss": 5.6404,
      "step": 158
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000312,
      "loss": 4.6338,
      "step": 159
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000314,
      "loss": 4.6164,
      "step": 160
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000316,
      "loss": 7.2017,
      "step": 161
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00031800000000000003,
      "loss": 5.0695,
      "step": 162
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00032,
      "loss": 5.8149,
      "step": 163
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000322,
      "loss": 5.784,
      "step": 164
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000324,
      "loss": 5.1999,
      "step": 165
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000326,
      "loss": 5.1967,
      "step": 166
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000328,
      "loss": 6.9382,
      "step": 167
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00033,
      "loss": 5.4285,
      "step": 168
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00033200000000000005,
      "loss": 5.1949,
      "step": 169
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00033400000000000004,
      "loss": 4.737,
      "step": 170
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00033600000000000004,
      "loss": 4.7707,
      "step": 171
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00033800000000000003,
      "loss": 4.817,
      "step": 172
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00034,
      "loss": 4.7532,
      "step": 173
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000342,
      "loss": 5.9552,
      "step": 174
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00034399999999999996,
      "loss": 4.8476,
      "step": 175
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000346,
      "loss": 5.7053,
      "step": 176
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000348,
      "loss": 4.8703,
      "step": 177
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00035,
      "loss": 4.7289,
      "step": 178
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000352,
      "loss": 4.628,
      "step": 179
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000354,
      "loss": 4.8781,
      "step": 180
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000356,
      "loss": 4.8125,
      "step": 181
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000358,
      "loss": 4.9407,
      "step": 182
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00035999999999999997,
      "loss": 4.7761,
      "step": 183
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000362,
      "loss": 5.049,
      "step": 184
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000364,
      "loss": 4.4187,
      "step": 185
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000366,
      "loss": 4.9644,
      "step": 186
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000368,
      "loss": 4.8425,
      "step": 187
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00037,
      "loss": 4.6558,
      "step": 188
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000372,
      "loss": 4.973,
      "step": 189
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000374,
      "loss": 5.0381,
      "step": 190
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00037600000000000003,
      "loss": 5.2445,
      "step": 191
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000378,
      "loss": 5.4255,
      "step": 192
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00038,
      "loss": 4.9689,
      "step": 193
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000382,
      "loss": 5.2518,
      "step": 194
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000384,
      "loss": 4.9659,
      "step": 195
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000386,
      "loss": 5.2984,
      "step": 196
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000388,
      "loss": 4.9212,
      "step": 197
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00039000000000000005,
      "loss": 5.186,
      "step": 198
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00039200000000000004,
      "loss": 5.0575,
      "step": 199
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00039400000000000004,
      "loss": 4.6557,
      "step": 200
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00039600000000000003,
      "loss": 5.1663,
      "step": 201
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000398,
      "loss": 5.0017,
      "step": 202
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0004,
      "loss": 5.2516,
      "step": 203
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000402,
      "loss": 4.8405,
      "step": 204
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000404,
      "loss": 5.2231,
      "step": 205
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00040600000000000006,
      "loss": 5.0627,
      "step": 206
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000408,
      "loss": 4.7863,
      "step": 207
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00041,
      "loss": 5.9023,
      "step": 208
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000412,
      "loss": 4.9873,
      "step": 209
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000414,
      "loss": 5.1966,
      "step": 210
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000416,
      "loss": 4.8328,
      "step": 211
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00041799999999999997,
      "loss": 5.0304,
      "step": 212
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00042,
      "loss": 4.7429,
      "step": 213
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000422,
      "loss": 4.9829,
      "step": 214
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000424,
      "loss": 4.8241,
      "step": 215
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000426,
      "loss": 4.8027,
      "step": 216
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000428,
      "loss": 5.1121,
      "step": 217
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00043,
      "loss": 4.8366,
      "step": 218
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000432,
      "loss": 4.623,
      "step": 219
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00043400000000000003,
      "loss": 5.8336,
      "step": 220
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000436,
      "loss": 4.9087,
      "step": 221
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000438,
      "loss": 5.4127,
      "step": 222
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00044,
      "loss": 5.0507,
      "step": 223
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000442,
      "loss": 5.0366,
      "step": 224
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000444,
      "loss": 4.8739,
      "step": 225
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000446,
      "loss": 4.6306,
      "step": 226
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000448,
      "loss": 4.9492,
      "step": 227
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00045000000000000004,
      "loss": 5.2392,
      "step": 228
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00045200000000000004,
      "loss": 5.1064,
      "step": 229
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00045400000000000003,
      "loss": 4.8969,
      "step": 230
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000456,
      "loss": 4.9746,
      "step": 231
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000458,
      "loss": 4.7355,
      "step": 232
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00046,
      "loss": 5.2297,
      "step": 233
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000462,
      "loss": 5.0465,
      "step": 234
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00046400000000000006,
      "loss": 5.0885,
      "step": 235
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00046600000000000005,
      "loss": 5.3038,
      "step": 236
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00046800000000000005,
      "loss": 4.8304,
      "step": 237
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00047,
      "loss": 4.8464,
      "step": 238
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000472,
      "loss": 4.8042,
      "step": 239
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000474,
      "loss": 4.8883,
      "step": 240
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00047599999999999997,
      "loss": 5.4181,
      "step": 241
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00047799999999999996,
      "loss": 5.1992,
      "step": 242
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00048,
      "loss": 5.1573,
      "step": 243
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000482,
      "loss": 4.9052,
      "step": 244
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000484,
      "loss": 5.9046,
      "step": 245
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000486,
      "loss": 4.7418,
      "step": 246
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000488,
      "loss": 6.3338,
      "step": 247
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00049,
      "loss": 5.2248,
      "step": 248
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000492,
      "loss": 8.206,
      "step": 249
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000494,
      "loss": 5.2911,
      "step": 250
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000496,
      "loss": 5.3111,
      "step": 251
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000498,
      "loss": 4.8883,
      "step": 252
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005,
      "loss": 5.0506,
      "step": 253
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005020000000000001,
      "loss": 4.7748,
      "step": 254
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000504,
      "loss": 4.9331,
      "step": 255
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000506,
      "loss": 5.2438,
      "step": 256
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000508,
      "loss": 4.6562,
      "step": 257
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00051,
      "loss": 5.5853,
      "step": 258
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000512,
      "loss": 5.2,
      "step": 259
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000514,
      "loss": 4.8476,
      "step": 260
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005160000000000001,
      "loss": 4.9591,
      "step": 261
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000518,
      "loss": 5.2288,
      "step": 262
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005200000000000001,
      "loss": 5.0392,
      "step": 263
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000522,
      "loss": 5.1153,
      "step": 264
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000524,
      "loss": 5.0144,
      "step": 265
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000526,
      "loss": 5.4205,
      "step": 266
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000528,
      "loss": 4.859,
      "step": 267
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005300000000000001,
      "loss": 5.0684,
      "step": 268
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000532,
      "loss": 5.0688,
      "step": 269
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005340000000000001,
      "loss": 4.842,
      "step": 270
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000536,
      "loss": 5.0882,
      "step": 271
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005380000000000001,
      "loss": 4.8919,
      "step": 272
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00054,
      "loss": 4.8645,
      "step": 273
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005420000000000001,
      "loss": 4.9041,
      "step": 274
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005440000000000001,
      "loss": 4.9276,
      "step": 275
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000546,
      "loss": 4.7217,
      "step": 276
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005480000000000001,
      "loss": 5.7271,
      "step": 277
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00055,
      "loss": 5.5031,
      "step": 278
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005520000000000001,
      "loss": 5.4163,
      "step": 279
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000554,
      "loss": 5.0355,
      "step": 280
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005560000000000001,
      "loss": 4.9209,
      "step": 281
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000558,
      "loss": 5.0386,
      "step": 282
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005600000000000001,
      "loss": 6.3469,
      "step": 283
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005620000000000001,
      "loss": 5.1925,
      "step": 284
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005639999999999999,
      "loss": 5.1816,
      "step": 285
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000566,
      "loss": 4.9083,
      "step": 286
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005679999999999999,
      "loss": 5.0828,
      "step": 287
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00057,
      "loss": 4.7952,
      "step": 288
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005719999999999999,
      "loss": 5.0554,
      "step": 289
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000574,
      "loss": 5.0934,
      "step": 290
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000576,
      "loss": 5.2574,
      "step": 291
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000578,
      "loss": 6.2128,
      "step": 292
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00058,
      "loss": 4.7037,
      "step": 293
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005819999999999999,
      "loss": 5.0873,
      "step": 294
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000584,
      "loss": 5.2764,
      "step": 295
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005859999999999999,
      "loss": 6.2514,
      "step": 296
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000588,
      "loss": 5.6582,
      "step": 297
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00059,
      "loss": 5.2889,
      "step": 298
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000592,
      "loss": 8.0798,
      "step": 299
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000594,
      "loss": 7.3563,
      "step": 300
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000596,
      "loss": 5.2756,
      "step": 301
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000598,
      "loss": 5.2133,
      "step": 302
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0006,
      "loss": 5.4376,
      "step": 303
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000602,
      "loss": 4.9474,
      "step": 304
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000604,
      "loss": 4.9552,
      "step": 305
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000606,
      "loss": 5.4167,
      "step": 306
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000608,
      "loss": 5.1688,
      "step": 307
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00061,
      "loss": 5.1933,
      "step": 308
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000612,
      "loss": 4.7817,
      "step": 309
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000614,
      "loss": 5.4313,
      "step": 310
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000616,
      "loss": 4.9793,
      "step": 311
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0006180000000000001,
      "loss": 4.8846,
      "step": 312
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00062,
      "loss": 4.8638,
      "step": 313
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000622,
      "loss": 5.2058,
      "step": 314
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000624,
      "loss": 4.7608,
      "step": 315
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000626,
      "loss": 5.1831,
      "step": 316
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000628,
      "loss": 5.3887,
      "step": 317
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00063,
      "loss": 5.0039,
      "step": 318
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000632,
      "loss": 4.9832,
      "step": 319
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000634,
      "loss": 5.0153,
      "step": 320
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0006360000000000001,
      "loss": 5.1506,
      "step": 321
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000638,
      "loss": 4.9482,
      "step": 322
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00064,
      "loss": 4.9163,
      "step": 323
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000642,
      "loss": 5.4786,
      "step": 324
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000644,
      "loss": 4.8748,
      "step": 325
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000646,
      "loss": 6.1923,
      "step": 326
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000648,
      "loss": 5.4042,
      "step": 327
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006500000000000001,
      "loss": 5.3992,
      "step": 328
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000652,
      "loss": 4.9699,
      "step": 329
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006540000000000001,
      "loss": 5.8082,
      "step": 330
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000656,
      "loss": 5.466,
      "step": 331
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006580000000000001,
      "loss": 6.293,
      "step": 332
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00066,
      "loss": 5.1304,
      "step": 333
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000662,
      "loss": 5.2604,
      "step": 334
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006640000000000001,
      "loss": 5.2558,
      "step": 335
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000666,
      "loss": 5.6875,
      "step": 336
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006680000000000001,
      "loss": 4.9292,
      "step": 337
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00067,
      "loss": 5.2356,
      "step": 338
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0006720000000000001,
      "loss": 5.2205,
      "step": 339
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000674,
      "loss": 5.3556,
      "step": 340
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0006760000000000001,
      "loss": 5.2928,
      "step": 341
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0006780000000000001,
      "loss": 5.553,
      "step": 342
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00068,
      "loss": 6.2782,
      "step": 343
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0006820000000000001,
      "loss": 5.6736,
      "step": 344
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000684,
      "loss": 4.9139,
      "step": 345
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0006860000000000001,
      "loss": 5.4002,
      "step": 346
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0006879999999999999,
      "loss": 5.517,
      "step": 347
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00069,
      "loss": 6.5166,
      "step": 348
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000692,
      "loss": 5.9373,
      "step": 349
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000694,
      "loss": 5.1641,
      "step": 350
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000696,
      "loss": 5.9066,
      "step": 351
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0006979999999999999,
      "loss": 5.2212,
      "step": 352
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0007,
      "loss": 6.0158,
      "step": 353
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0007019999999999999,
      "loss": 5.3464,
      "step": 354
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000704,
      "loss": 5.1174,
      "step": 355
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0007059999999999999,
      "loss": 5.2882,
      "step": 356
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000708,
      "loss": 5.352,
      "step": 357
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00071,
      "loss": 4.9085,
      "step": 358
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000712,
      "loss": 5.2592,
      "step": 359
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000714,
      "loss": 5.2981,
      "step": 360
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000716,
      "loss": 4.9637,
      "step": 361
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000718,
      "loss": 5.5029,
      "step": 362
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0007199999999999999,
      "loss": 5.0046,
      "step": 363
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000722,
      "loss": 5.0682,
      "step": 364
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000724,
      "loss": 5.8746,
      "step": 365
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000726,
      "loss": 5.8206,
      "step": 366
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000728,
      "loss": 5.1082,
      "step": 367
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00073,
      "loss": 5.3463,
      "step": 368
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000732,
      "loss": 5.7593,
      "step": 369
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000734,
      "loss": 5.5599,
      "step": 370
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000736,
      "loss": 5.4685,
      "step": 371
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000738,
      "loss": 5.5344,
      "step": 372
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00074,
      "loss": 5.1595,
      "step": 373
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000742,
      "loss": 5.197,
      "step": 374
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000744,
      "loss": 5.1699,
      "step": 375
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000746,
      "loss": 5.4809,
      "step": 376
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000748,
      "loss": 5.297,
      "step": 377
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00075,
      "loss": 5.2932,
      "step": 378
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0007520000000000001,
      "loss": 5.2886,
      "step": 379
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000754,
      "loss": 5.3678,
      "step": 380
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000756,
      "loss": 4.9895,
      "step": 381
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000758,
      "loss": 5.2246,
      "step": 382
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00076,
      "loss": 5.0254,
      "step": 383
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000762,
      "loss": 5.3305,
      "step": 384
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000764,
      "loss": 5.3363,
      "step": 385
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0007660000000000001,
      "loss": 5.0416,
      "step": 386
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000768,
      "loss": 5.2708,
      "step": 387
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0007700000000000001,
      "loss": 5.1443,
      "step": 388
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000772,
      "loss": 5.4075,
      "step": 389
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0007740000000000001,
      "loss": 5.3772,
      "step": 390
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000776,
      "loss": 5.3105,
      "step": 391
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000778,
      "loss": 6.8609,
      "step": 392
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0007800000000000001,
      "loss": 5.0175,
      "step": 393
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000782,
      "loss": 5.3111,
      "step": 394
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0007840000000000001,
      "loss": 4.9941,
      "step": 395
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000786,
      "loss": 5.9271,
      "step": 396
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0007880000000000001,
      "loss": 5.6516,
      "step": 397
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00079,
      "loss": 5.606,
      "step": 398
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0007920000000000001,
      "loss": 6.9485,
      "step": 399
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0007940000000000001,
      "loss": 8.2026,
      "step": 400
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000796,
      "loss": 5.7139,
      "step": 401
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0007980000000000001,
      "loss": 5.5075,
      "step": 402
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008,
      "loss": 5.4495,
      "step": 403
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008020000000000001,
      "loss": 5.4492,
      "step": 404
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000804,
      "loss": 5.4174,
      "step": 405
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008060000000000001,
      "loss": 5.1429,
      "step": 406
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000808,
      "loss": 5.228,
      "step": 407
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008100000000000001,
      "loss": 5.9743,
      "step": 408
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008120000000000001,
      "loss": 5.346,
      "step": 409
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008139999999999999,
      "loss": 5.4215,
      "step": 410
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000816,
      "loss": 5.534,
      "step": 411
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0008179999999999999,
      "loss": 5.3026,
      "step": 412
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00082,
      "loss": 5.4964,
      "step": 413
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0008219999999999999,
      "loss": 5.0144,
      "step": 414
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000824,
      "loss": 5.3684,
      "step": 415
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000826,
      "loss": 5.6391,
      "step": 416
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000828,
      "loss": 4.9192,
      "step": 417
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00083,
      "loss": 5.2417,
      "step": 418
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000832,
      "loss": 5.269,
      "step": 419
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000834,
      "loss": 5.4544,
      "step": 420
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0008359999999999999,
      "loss": 5.6599,
      "step": 421
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000838,
      "loss": 5.1408,
      "step": 422
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00084,
      "loss": 5.0571,
      "step": 423
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000842,
      "loss": 5.0662,
      "step": 424
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000844,
      "loss": 5.7209,
      "step": 425
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000846,
      "loss": 4.9936,
      "step": 426
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000848,
      "loss": 5.0084,
      "step": 427
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00085,
      "loss": 5.3047,
      "step": 428
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000852,
      "loss": 5.954,
      "step": 429
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000854,
      "loss": 5.6528,
      "step": 430
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000856,
      "loss": 5.3661,
      "step": 431
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000858,
      "loss": 5.3309,
      "step": 432
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00086,
      "loss": 5.4359,
      "step": 433
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000862,
      "loss": 5.2456,
      "step": 434
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000864,
      "loss": 5.368,
      "step": 435
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000866,
      "loss": 5.106,
      "step": 436
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0008680000000000001,
      "loss": 5.0062,
      "step": 437
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00087,
      "loss": 5.0479,
      "step": 438
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000872,
      "loss": 5.4351,
      "step": 439
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000874,
      "loss": 5.094,
      "step": 440
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000876,
      "loss": 5.372,
      "step": 441
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000878,
      "loss": 5.2698,
      "step": 442
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00088,
      "loss": 5.1859,
      "step": 443
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000882,
      "loss": 5.2186,
      "step": 444
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000884,
      "loss": 4.9551,
      "step": 445
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0008860000000000001,
      "loss": 5.2439,
      "step": 446
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000888,
      "loss": 8.0543,
      "step": 447
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0008900000000000001,
      "loss": 5.4051,
      "step": 448
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000892,
      "loss": 5.519,
      "step": 449
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000894,
      "loss": 5.5713,
      "step": 450
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000896,
      "loss": 5.3046,
      "step": 451
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000898,
      "loss": 5.1503,
      "step": 452
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009000000000000001,
      "loss": 5.2802,
      "step": 453
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000902,
      "loss": 5.415,
      "step": 454
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009040000000000001,
      "loss": 6.009,
      "step": 455
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000906,
      "loss": 5.8562,
      "step": 456
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009080000000000001,
      "loss": 5.4349,
      "step": 457
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00091,
      "loss": 7.5475,
      "step": 458
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000912,
      "loss": 5.4009,
      "step": 459
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009140000000000001,
      "loss": 5.4328,
      "step": 460
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000916,
      "loss": 5.5625,
      "step": 461
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009180000000000001,
      "loss": 5.3081,
      "step": 462
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00092,
      "loss": 5.2885,
      "step": 463
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009220000000000001,
      "loss": 5.7384,
      "step": 464
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000924,
      "loss": 5.3471,
      "step": 465
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009260000000000001,
      "loss": 5.5417,
      "step": 466
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009280000000000001,
      "loss": 5.2314,
      "step": 467
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00093,
      "loss": 5.2603,
      "step": 468
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009320000000000001,
      "loss": 5.1603,
      "step": 469
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000934,
      "loss": 5.4647,
      "step": 470
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009360000000000001,
      "loss": 5.2128,
      "step": 471
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009379999999999999,
      "loss": 5.3251,
      "step": 472
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00094,
      "loss": 5.2272,
      "step": 473
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000942,
      "loss": 5.37,
      "step": 474
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000944,
      "loss": 5.7458,
      "step": 475
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000946,
      "loss": 6.0803,
      "step": 476
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000948,
      "loss": 5.0569,
      "step": 477
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00095,
      "loss": 5.4589,
      "step": 478
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009519999999999999,
      "loss": 5.1716,
      "step": 479
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000954,
      "loss": 5.4422,
      "step": 480
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009559999999999999,
      "loss": 5.0668,
      "step": 481
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000958,
      "loss": 5.2654,
      "step": 482
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00096,
      "loss": 6.7736,
      "step": 483
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000962,
      "loss": 5.7394,
      "step": 484
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000964,
      "loss": 5.4959,
      "step": 485
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000966,
      "loss": 5.5867,
      "step": 486
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000968,
      "loss": 5.2123,
      "step": 487
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009699999999999999,
      "loss": 5.4199,
      "step": 488
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000972,
      "loss": 5.8817,
      "step": 489
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000974,
      "loss": 5.1656,
      "step": 490
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000976,
      "loss": 5.7833,
      "step": 491
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000978,
      "loss": 5.7503,
      "step": 492
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00098,
      "loss": 6.3054,
      "step": 493
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000982,
      "loss": 6.0516,
      "step": 494
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000984,
      "loss": 6.7448,
      "step": 495
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009860000000000001,
      "loss": 5.8998,
      "step": 496
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000988,
      "loss": 5.523,
      "step": 497
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00099,
      "loss": 5.4295,
      "step": 498
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000992,
      "loss": 5.2345,
      "step": 499
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000994,
      "loss": 5.6082,
      "step": 500
    },
    {
      "epoch": 0.42,
      "eval_loss": 5.971189498901367,
      "eval_runtime": 772.5606,
      "eval_samples_per_second": 3.42,
      "eval_steps_per_second": 0.286,
      "eval_wer": 1.9655890519635066,
      "step": 500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000996,
      "loss": 6.0055,
      "step": 501
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000998,
      "loss": 5.5965,
      "step": 502
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.001,
      "loss": 5.4823,
      "step": 503
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009985486211901307,
      "loss": 5.3086,
      "step": 504
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009970972423802612,
      "loss": 5.3724,
      "step": 505
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000995645863570392,
      "loss": 5.6485,
      "step": 506
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009941944847605226,
      "loss": 5.4129,
      "step": 507
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009927431059506531,
      "loss": 5.3835,
      "step": 508
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009912917271407838,
      "loss": 5.3629,
      "step": 509
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009898403483309143,
      "loss": 5.6084,
      "step": 510
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000988388969521045,
      "loss": 5.522,
      "step": 511
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009869375907111755,
      "loss": 5.1979,
      "step": 512
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009854862119013062,
      "loss": 5.5267,
      "step": 513
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000984034833091437,
      "loss": 5.0734,
      "step": 514
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009825834542815674,
      "loss": 5.1902,
      "step": 515
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009811320754716981,
      "loss": 5.2944,
      "step": 516
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009796806966618288,
      "loss": 5.5136,
      "step": 517
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009782293178519593,
      "loss": 5.4618,
      "step": 518
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00097677793904209,
      "loss": 5.7373,
      "step": 519
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009753265602322206,
      "loss": 5.0968,
      "step": 520
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009738751814223512,
      "loss": 5.3119,
      "step": 521
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009724238026124818,
      "loss": 5.2911,
      "step": 522
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009709724238026125,
      "loss": 6.3803,
      "step": 523
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000969521044992743,
      "loss": 5.6489,
      "step": 524
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009680696661828737,
      "loss": 5.6184,
      "step": 525
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009666182873730044,
      "loss": 5.0753,
      "step": 526
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000965166908563135,
      "loss": 5.3418,
      "step": 527
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009637155297532656,
      "loss": 5.7998,
      "step": 528
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009622641509433962,
      "loss": 5.3236,
      "step": 529
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009608127721335269,
      "loss": 5.3762,
      "step": 530
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009593613933236574,
      "loss": 5.4276,
      "step": 531
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009579100145137881,
      "loss": 5.3769,
      "step": 532
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009564586357039187,
      "loss": 5.2204,
      "step": 533
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009550072568940493,
      "loss": 5.3234,
      "step": 534
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009535558780841799,
      "loss": 5.2219,
      "step": 535
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009521044992743106,
      "loss": 5.2035,
      "step": 536
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009506531204644411,
      "loss": 5.6239,
      "step": 537
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009492017416545718,
      "loss": 5.3629,
      "step": 538
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009477503628447026,
      "loss": 5.3972,
      "step": 539
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009462989840348331,
      "loss": 5.709,
      "step": 540
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009448476052249637,
      "loss": 5.5734,
      "step": 541
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009433962264150943,
      "loss": 5.5395,
      "step": 542
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000941944847605225,
      "loss": 5.1856,
      "step": 543
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009404934687953555,
      "loss": 5.4564,
      "step": 544
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009390420899854863,
      "loss": 5.4666,
      "step": 545
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009375907111756169,
      "loss": 5.2829,
      "step": 546
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009361393323657474,
      "loss": 5.8558,
      "step": 547
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000934687953555878,
      "loss": 7.3071,
      "step": 548
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009332365747460088,
      "loss": 5.4414,
      "step": 549
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009317851959361394,
      "loss": 6.2957,
      "step": 550
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00093033381712627,
      "loss": 5.7204,
      "step": 551
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009288824383164007,
      "loss": 5.3751,
      "step": 552
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009274310595065311,
      "loss": 5.6019,
      "step": 553
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009259796806966619,
      "loss": 5.397,
      "step": 554
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009245283018867925,
      "loss": 5.7751,
      "step": 555
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009230769230769232,
      "loss": 5.6476,
      "step": 556
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009216255442670537,
      "loss": 5.2722,
      "step": 557
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009201741654571844,
      "loss": 5.7729,
      "step": 558
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000918722786647315,
      "loss": 5.6173,
      "step": 559
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009172714078374456,
      "loss": 5.51,
      "step": 560
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009158200290275763,
      "loss": 5.3482,
      "step": 561
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009143686502177069,
      "loss": 5.4823,
      "step": 562
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009129172714078375,
      "loss": 6.2471,
      "step": 563
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009114658925979681,
      "loss": 4.9672,
      "step": 564
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009100145137880988,
      "loss": 5.2456,
      "step": 565
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009085631349782293,
      "loss": 5.1968,
      "step": 566
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00090711175616836,
      "loss": 5.5594,
      "step": 567
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009056603773584906,
      "loss": 5.7127,
      "step": 568
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009042089985486213,
      "loss": 5.1732,
      "step": 569
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009027576197387518,
      "loss": 5.2284,
      "step": 570
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009013062409288825,
      "loss": 5.4143,
      "step": 571
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008998548621190132,
      "loss": 5.3897,
      "step": 572
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008984034833091437,
      "loss": 5.3026,
      "step": 573
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008969521044992744,
      "loss": 5.3856,
      "step": 574
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000895500725689405,
      "loss": 5.4547,
      "step": 575
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008940493468795356,
      "loss": 5.4656,
      "step": 576
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008925979680696662,
      "loss": 5.5619,
      "step": 577
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008911465892597969,
      "loss": 5.1546,
      "step": 578
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008896952104499274,
      "loss": 5.3612,
      "step": 579
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008882438316400581,
      "loss": 5.4632,
      "step": 580
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008867924528301887,
      "loss": 5.452,
      "step": 581
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008853410740203193,
      "loss": 5.2672,
      "step": 582
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00088388969521045,
      "loss": 5.3376,
      "step": 583
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008824383164005806,
      "loss": 5.2473,
      "step": 584
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008809869375907113,
      "loss": 5.5358,
      "step": 585
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008795355587808418,
      "loss": 5.5731,
      "step": 586
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008780841799709725,
      "loss": 5.5165,
      "step": 587
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0008766328011611031,
      "loss": 5.4301,
      "step": 588
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008751814223512337,
      "loss": 5.4791,
      "step": 589
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008737300435413643,
      "loss": 5.4197,
      "step": 590
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000872278664731495,
      "loss": 5.2328,
      "step": 591
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008708272859216255,
      "loss": 5.0995,
      "step": 592
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008693759071117562,
      "loss": 5.7272,
      "step": 593
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008679245283018869,
      "loss": 5.3319,
      "step": 594
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008664731494920174,
      "loss": 5.0899,
      "step": 595
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008650217706821481,
      "loss": 5.0355,
      "step": 596
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008635703918722787,
      "loss": 5.2191,
      "step": 597
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008621190130624093,
      "loss": 6.9456,
      "step": 598
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008606676342525399,
      "loss": 5.5227,
      "step": 599
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008592162554426706,
      "loss": 6.2959,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008577648766328012,
      "loss": 5.3511,
      "step": 601
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008563134978229318,
      "loss": 5.6864,
      "step": 602
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008548621190130624,
      "loss": 5.564,
      "step": 603
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008534107402031931,
      "loss": 5.2273,
      "step": 604
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008519593613933237,
      "loss": 5.4808,
      "step": 605
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008505079825834543,
      "loss": 5.5164,
      "step": 606
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000849056603773585,
      "loss": 5.3247,
      "step": 607
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008476052249637155,
      "loss": 5.4717,
      "step": 608
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008461538461538462,
      "loss": 5.2743,
      "step": 609
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008447024673439768,
      "loss": 5.3684,
      "step": 610
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008432510885341074,
      "loss": 5.5687,
      "step": 611
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000841799709724238,
      "loss": 5.1055,
      "step": 612
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008403483309143687,
      "loss": 5.9791,
      "step": 613
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008388969521044993,
      "loss": 5.0076,
      "step": 614
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008374455732946299,
      "loss": 5.1948,
      "step": 615
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008359941944847606,
      "loss": 5.2781,
      "step": 616
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008345428156748912,
      "loss": 5.2203,
      "step": 617
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008330914368650218,
      "loss": 7.2738,
      "step": 618
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008316400580551524,
      "loss": 5.4513,
      "step": 619
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008301886792452831,
      "loss": 5.383,
      "step": 620
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008287373004354136,
      "loss": 5.0347,
      "step": 621
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008272859216255443,
      "loss": 5.0027,
      "step": 622
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008258345428156749,
      "loss": 5.8913,
      "step": 623
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008243831640058055,
      "loss": 5.4649,
      "step": 624
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008229317851959361,
      "loss": 5.7076,
      "step": 625
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008214804063860668,
      "loss": 5.7467,
      "step": 626
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008200290275761973,
      "loss": 5.3819,
      "step": 627
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000818577648766328,
      "loss": 4.9549,
      "step": 628
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008171262699564587,
      "loss": 5.2382,
      "step": 629
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008156748911465893,
      "loss": 5.5093,
      "step": 630
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008142235123367199,
      "loss": 5.3199,
      "step": 631
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008127721335268505,
      "loss": 5.271,
      "step": 632
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008113207547169812,
      "loss": 5.7689,
      "step": 633
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008098693759071117,
      "loss": 5.1918,
      "step": 634
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0008084179970972424,
      "loss": 5.5693,
      "step": 635
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000806966618287373,
      "loss": 5.2135,
      "step": 636
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008055152394775036,
      "loss": 4.9668,
      "step": 637
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008040638606676342,
      "loss": 5.0565,
      "step": 638
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008026124818577649,
      "loss": 5.2087,
      "step": 639
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008011611030478955,
      "loss": 5.3371,
      "step": 640
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007997097242380261,
      "loss": 5.1342,
      "step": 641
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007982583454281568,
      "loss": 5.8708,
      "step": 642
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007968069666182874,
      "loss": 5.8123,
      "step": 643
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000795355587808418,
      "loss": 5.3119,
      "step": 644
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007939042089985486,
      "loss": 5.3256,
      "step": 645
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007924528301886793,
      "loss": 5.4008,
      "step": 646
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007910014513788098,
      "loss": 4.8679,
      "step": 647
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0007895500725689405,
      "loss": 6.0724,
      "step": 648
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007880986937590711,
      "loss": 5.5273,
      "step": 649
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007866473149492017,
      "loss": 4.9108,
      "step": 650
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007851959361393324,
      "loss": 5.6022,
      "step": 651
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000783744557329463,
      "loss": 5.1818,
      "step": 652
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007822931785195936,
      "loss": 5.1802,
      "step": 653
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007808417997097242,
      "loss": 5.4167,
      "step": 654
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007793904208998549,
      "loss": 5.1972,
      "step": 655
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007779390420899854,
      "loss": 5.0685,
      "step": 656
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007764876632801161,
      "loss": 5.3508,
      "step": 657
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007750362844702467,
      "loss": 5.5123,
      "step": 658
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007735849056603774,
      "loss": 5.4158,
      "step": 659
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007721335268505079,
      "loss": 5.2287,
      "step": 660
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007706821480406386,
      "loss": 5.3385,
      "step": 661
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007692307692307693,
      "loss": 5.1604,
      "step": 662
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007677793904208998,
      "loss": 5.1538,
      "step": 663
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007663280116110305,
      "loss": 5.1191,
      "step": 664
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007648766328011611,
      "loss": 5.5619,
      "step": 665
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007634252539912917,
      "loss": 5.298,
      "step": 666
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007619738751814223,
      "loss": 5.2461,
      "step": 667
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000760522496371553,
      "loss": 5.0993,
      "step": 668
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007590711175616835,
      "loss": 5.5692,
      "step": 669
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007576197387518142,
      "loss": 5.6514,
      "step": 670
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007561683599419448,
      "loss": 5.6489,
      "step": 671
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0007547169811320755,
      "loss": 5.1456,
      "step": 672
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007532656023222061,
      "loss": 5.2761,
      "step": 673
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007518142235123367,
      "loss": 5.1052,
      "step": 674
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007503628447024674,
      "loss": 5.1917,
      "step": 675
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007489114658925979,
      "loss": 5.0055,
      "step": 676
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007474600870827286,
      "loss": 5.3781,
      "step": 677
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007460087082728592,
      "loss": 5.3236,
      "step": 678
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007445573294629898,
      "loss": 5.1835,
      "step": 679
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007431059506531204,
      "loss": 5.3368,
      "step": 680
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007416545718432511,
      "loss": 4.9094,
      "step": 681
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007402031930333816,
      "loss": 4.8995,
      "step": 682
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007387518142235123,
      "loss": 5.1664,
      "step": 683
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000737300435413643,
      "loss": 5.0402,
      "step": 684
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007358490566037735,
      "loss": 5.5918,
      "step": 685
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007343976777939043,
      "loss": 5.3654,
      "step": 686
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007329462989840348,
      "loss": 5.1001,
      "step": 687
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007314949201741656,
      "loss": 5.1216,
      "step": 688
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000730043541364296,
      "loss": 5.2851,
      "step": 689
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007285921625544268,
      "loss": 5.2563,
      "step": 690
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007271407837445574,
      "loss": 5.4761,
      "step": 691
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000725689404934688,
      "loss": 5.2268,
      "step": 692
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007242380261248185,
      "loss": 5.3059,
      "step": 693
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007227866473149493,
      "loss": 5.8417,
      "step": 694
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007213352685050797,
      "loss": 5.3375,
      "step": 695
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007198838896952105,
      "loss": 5.0948,
      "step": 696
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007184325108853412,
      "loss": 5.3722,
      "step": 697
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007169811320754717,
      "loss": 5.5119,
      "step": 698
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007155297532656024,
      "loss": 4.9806,
      "step": 699
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000714078374455733,
      "loss": 5.9573,
      "step": 700
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007126269956458637,
      "loss": 5.9752,
      "step": 701
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007111756168359942,
      "loss": 4.982,
      "step": 702
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007097242380261249,
      "loss": 5.3352,
      "step": 703
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007082728592162555,
      "loss": 5.1336,
      "step": 704
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007068214804063861,
      "loss": 5.1104,
      "step": 705
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007053701015965167,
      "loss": 5.1668,
      "step": 706
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007039187227866474,
      "loss": 5.2123,
      "step": 707
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000702467343976778,
      "loss": 5.4632,
      "step": 708
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007010159651669086,
      "loss": 5.2234,
      "step": 709
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006995645863570393,
      "loss": 6.1649,
      "step": 710
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006981132075471698,
      "loss": 4.9586,
      "step": 711
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006966618287373005,
      "loss": 5.3222,
      "step": 712
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006952104499274311,
      "loss": 5.4812,
      "step": 713
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006937590711175617,
      "loss": 5.0724,
      "step": 714
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006923076923076923,
      "loss": 5.1864,
      "step": 715
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000690856313497823,
      "loss": 5.0248,
      "step": 716
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006894049346879536,
      "loss": 5.0635,
      "step": 717
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006879535558780842,
      "loss": 5.3964,
      "step": 718
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0006865021770682149,
      "loss": 5.0607,
      "step": 719
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006850507982583455,
      "loss": 5.0457,
      "step": 720
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006835994194484761,
      "loss": 5.0219,
      "step": 721
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006821480406386067,
      "loss": 4.9143,
      "step": 722
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006806966618287374,
      "loss": 5.4245,
      "step": 723
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006792452830188679,
      "loss": 4.8856,
      "step": 724
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006777939042089986,
      "loss": 5.1959,
      "step": 725
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006763425253991292,
      "loss": 5.9459,
      "step": 726
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006748911465892598,
      "loss": 4.961,
      "step": 727
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006734397677793904,
      "loss": 5.1239,
      "step": 728
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006719883889695211,
      "loss": 4.8281,
      "step": 729
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006705370101596517,
      "loss": 5.3037,
      "step": 730
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0006690856313497823,
      "loss": 5.4818,
      "step": 731
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000667634252539913,
      "loss": 5.378,
      "step": 732
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006661828737300436,
      "loss": 4.9808,
      "step": 733
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006647314949201742,
      "loss": 5.0709,
      "step": 734
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006632801161103048,
      "loss": 5.2164,
      "step": 735
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006618287373004355,
      "loss": 4.9492,
      "step": 736
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000660377358490566,
      "loss": 5.4681,
      "step": 737
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006589259796806967,
      "loss": 5.511,
      "step": 738
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006574746008708273,
      "loss": 5.1693,
      "step": 739
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006560232220609579,
      "loss": 5.0552,
      "step": 740
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006545718432510886,
      "loss": 5.2149,
      "step": 741
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006531204644412192,
      "loss": 6.3403,
      "step": 742
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006516690856313498,
      "loss": 5.3862,
      "step": 743
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006502177068214804,
      "loss": 5.0721,
      "step": 744
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006487663280116111,
      "loss": 5.5026,
      "step": 745
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006473149492017417,
      "loss": 6.4226,
      "step": 746
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006458635703918723,
      "loss": 5.3436,
      "step": 747
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006444121915820029,
      "loss": 6.4222,
      "step": 748
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006429608127721336,
      "loss": 6.0071,
      "step": 749
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006415094339622641,
      "loss": 5.0389,
      "step": 750
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006400580551523948,
      "loss": 5.3047,
      "step": 751
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006386066763425255,
      "loss": 5.3622,
      "step": 752
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000637155297532656,
      "loss": 5.2451,
      "step": 753
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006357039187227867,
      "loss": 4.9362,
      "step": 754
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0006342525399129173,
      "loss": 5.3065,
      "step": 755
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006328011611030479,
      "loss": 5.0147,
      "step": 756
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006313497822931785,
      "loss": 5.0598,
      "step": 757
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006298984034833092,
      "loss": 5.2496,
      "step": 758
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006284470246734397,
      "loss": 4.8978,
      "step": 759
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006269956458635704,
      "loss": 5.4418,
      "step": 760
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000625544267053701,
      "loss": 4.8784,
      "step": 761
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006240928882438317,
      "loss": 5.0095,
      "step": 762
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006226415094339623,
      "loss": 5.0565,
      "step": 763
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006211901306240929,
      "loss": 5.0263,
      "step": 764
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006197387518142236,
      "loss": 5.1925,
      "step": 765
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006182873730043541,
      "loss": 4.9813,
      "step": 766
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0006168359941944848,
      "loss": 5.2589,
      "step": 767
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006153846153846154,
      "loss": 4.7593,
      "step": 768
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000613933236574746,
      "loss": 5.015,
      "step": 769
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006124818577648766,
      "loss": 5.1436,
      "step": 770
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006110304789550073,
      "loss": 5.149,
      "step": 771
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006095791001451378,
      "loss": 5.1044,
      "step": 772
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006081277213352685,
      "loss": 4.9833,
      "step": 773
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006066763425253992,
      "loss": 5.2861,
      "step": 774
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006052249637155298,
      "loss": 5.3884,
      "step": 775
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006037735849056604,
      "loss": 4.8799,
      "step": 776
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000602322206095791,
      "loss": 5.0057,
      "step": 777
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0006008708272859217,
      "loss": 5.2477,
      "step": 778
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005994194484760522,
      "loss": 5.1023,
      "step": 779
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005979680696661829,
      "loss": 5.1842,
      "step": 780
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005965166908563135,
      "loss": 5.0125,
      "step": 781
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005950653120464441,
      "loss": 5.4608,
      "step": 782
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005936139332365747,
      "loss": 4.9112,
      "step": 783
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005921625544267054,
      "loss": 5.1474,
      "step": 784
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005907111756168359,
      "loss": 5.1718,
      "step": 785
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005892597968069666,
      "loss": 5.1529,
      "step": 786
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005878084179970973,
      "loss": 5.2616,
      "step": 787
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005863570391872278,
      "loss": 5.062,
      "step": 788
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005849056603773585,
      "loss": 5.0368,
      "step": 789
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005834542815674891,
      "loss": 5.0685,
      "step": 790
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005820029027576198,
      "loss": 5.2184,
      "step": 791
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005805515239477503,
      "loss": 5.2071,
      "step": 792
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000579100145137881,
      "loss": 5.3898,
      "step": 793
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005776487663280116,
      "loss": 5.2976,
      "step": 794
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005761973875181422,
      "loss": 5.167,
      "step": 795
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005747460087082728,
      "loss": 5.3693,
      "step": 796
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005732946298984035,
      "loss": 4.8185,
      "step": 797
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005718432510885341,
      "loss": 5.3253,
      "step": 798
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005703918722786647,
      "loss": 5.8208,
      "step": 799
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005689404934687954,
      "loss": 4.9468,
      "step": 800
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005674891146589259,
      "loss": 5.1776,
      "step": 801
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0005660377358490566,
      "loss": 4.9745,
      "step": 802
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005645863570391872,
      "loss": 5.0746,
      "step": 803
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005631349782293179,
      "loss": 5.2983,
      "step": 804
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005616835994194484,
      "loss": 4.86,
      "step": 805
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005602322206095791,
      "loss": 4.9945,
      "step": 806
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005587808417997097,
      "loss": 6.0606,
      "step": 807
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005573294629898403,
      "loss": 5.1517,
      "step": 808
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000555878084179971,
      "loss": 5.1314,
      "step": 809
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005544267053701016,
      "loss": 5.1679,
      "step": 810
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005529753265602322,
      "loss": 4.9893,
      "step": 811
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005515239477503628,
      "loss": 5.6067,
      "step": 812
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0005500725689404935,
      "loss": 4.9295,
      "step": 813
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000548621190130624,
      "loss": 5.3404,
      "step": 814
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005471698113207547,
      "loss": 5.0729,
      "step": 815
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005457184325108853,
      "loss": 5.0503,
      "step": 816
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005442670537010159,
      "loss": 5.0757,
      "step": 817
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005428156748911465,
      "loss": 4.7697,
      "step": 818
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005413642960812772,
      "loss": 4.819,
      "step": 819
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000539912917271408,
      "loss": 5.089,
      "step": 820
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005384615384615384,
      "loss": 5.1247,
      "step": 821
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005370101596516691,
      "loss": 4.8385,
      "step": 822
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005355587808417997,
      "loss": 5.1001,
      "step": 823
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005341074020319303,
      "loss": 5.4633,
      "step": 824
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005326560232220609,
      "loss": 4.9786,
      "step": 825
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0005312046444121916,
      "loss": 5.1771,
      "step": 826
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005297532656023221,
      "loss": 5.0881,
      "step": 827
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005283018867924528,
      "loss": 5.0811,
      "step": 828
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005268505079825834,
      "loss": 4.9207,
      "step": 829
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000525399129172714,
      "loss": 5.0726,
      "step": 830
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005239477503628448,
      "loss": 5.1162,
      "step": 831
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005224963715529754,
      "loss": 5.4175,
      "step": 832
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005210449927431061,
      "loss": 5.0988,
      "step": 833
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005195936139332365,
      "loss": 5.1395,
      "step": 834
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005181422351233673,
      "loss": 5.0437,
      "step": 835
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005166908563134979,
      "loss": 5.0964,
      "step": 836
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0005152394775036285,
      "loss": 5.0094,
      "step": 837
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000513788098693759,
      "loss": 4.5872,
      "step": 838
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005123367198838898,
      "loss": 5.1621,
      "step": 839
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005108853410740202,
      "loss": 5.2346,
      "step": 840
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000509433962264151,
      "loss": 5.0822,
      "step": 841
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005079825834542817,
      "loss": 5.3804,
      "step": 842
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005065312046444122,
      "loss": 5.6472,
      "step": 843
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005050798258345429,
      "loss": 5.3193,
      "step": 844
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005036284470246735,
      "loss": 4.9138,
      "step": 845
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005021770682148041,
      "loss": 4.9016,
      "step": 846
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0005007256894049347,
      "loss": 6.7137,
      "step": 847
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004992743105950654,
      "loss": 4.6902,
      "step": 848
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000497822931785196,
      "loss": 5.2458,
      "step": 849
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004963715529753266,
      "loss": 5.153,
      "step": 850
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004949201741654572,
      "loss": 5.5571,
      "step": 851
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004934687953555878,
      "loss": 5.0553,
      "step": 852
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004920174165457185,
      "loss": 5.0873,
      "step": 853
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004905660377358491,
      "loss": 5.0853,
      "step": 854
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004891146589259797,
      "loss": 5.098,
      "step": 855
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004876632801161103,
      "loss": 5.0839,
      "step": 856
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004862119013062409,
      "loss": 5.0078,
      "step": 857
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004847605224963715,
      "loss": 4.7948,
      "step": 858
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004833091436865022,
      "loss": 5.0643,
      "step": 859
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004818577648766328,
      "loss": 5.1501,
      "step": 860
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00048040638606676347,
      "loss": 4.67,
      "step": 861
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047895500725689407,
      "loss": 4.9893,
      "step": 862
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047750362844702467,
      "loss": 4.9115,
      "step": 863
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004760522496371553,
      "loss": 4.9451,
      "step": 864
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004746008708272859,
      "loss": 4.9671,
      "step": 865
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004731494920174166,
      "loss": 4.9126,
      "step": 866
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004716981132075472,
      "loss": 4.7534,
      "step": 867
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047024673439767777,
      "loss": 4.9833,
      "step": 868
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004687953555878084,
      "loss": 5.1847,
      "step": 869
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000467343976777939,
      "loss": 4.5659,
      "step": 870
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004658925979680697,
      "loss": 4.6605,
      "step": 871
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00046444121915820033,
      "loss": 4.7457,
      "step": 872
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00046298984034833093,
      "loss": 5.0637,
      "step": 873
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004615384615384616,
      "loss": 4.951,
      "step": 874
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004600870827285922,
      "loss": 4.9564,
      "step": 875
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004586357039187228,
      "loss": 4.7754,
      "step": 876
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00045718432510885343,
      "loss": 4.7696,
      "step": 877
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00045573294629898403,
      "loss": 5.3184,
      "step": 878
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00045428156748911463,
      "loss": 4.9474,
      "step": 879
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004528301886792453,
      "loss": 5.0461,
      "step": 880
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004513788098693759,
      "loss": 4.7707,
      "step": 881
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004499274310595066,
      "loss": 5.0858,
      "step": 882
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004484760522496372,
      "loss": 4.939,
      "step": 883
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004470246734397678,
      "loss": 4.9511,
      "step": 884
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00044557329462989844,
      "loss": 4.7977,
      "step": 885
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00044412191582002904,
      "loss": 5.0046,
      "step": 886
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00044267053701015964,
      "loss": 4.9981,
      "step": 887
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004412191582002903,
      "loss": 4.8977,
      "step": 888
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004397677793904209,
      "loss": 4.9723,
      "step": 889
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043831640058055154,
      "loss": 5.2849,
      "step": 890
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043686502177068214,
      "loss": 6.5805,
      "step": 891
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043541364296081274,
      "loss": 4.8901,
      "step": 892
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043396226415094345,
      "loss": 5.1268,
      "step": 893
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043251088534107404,
      "loss": 5.0544,
      "step": 894
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00043105950653120464,
      "loss": 4.8594,
      "step": 895
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004296081277213353,
      "loss": 5.0497,
      "step": 896
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004281567489114659,
      "loss": 4.9975,
      "step": 897
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00042670537010159655,
      "loss": 4.9852,
      "step": 898
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00042525399129172715,
      "loss": 5.1585,
      "step": 899
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00042380261248185774,
      "loss": 4.8233,
      "step": 900
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004223512336719884,
      "loss": 4.9715,
      "step": 901
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000420899854862119,
      "loss": 5.0533,
      "step": 902
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00041944847605224965,
      "loss": 5.0464,
      "step": 903
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004179970972423803,
      "loss": 5.0582,
      "step": 904
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004165457184325109,
      "loss": 4.9427,
      "step": 905
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00041509433962264155,
      "loss": 5.122,
      "step": 906
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00041364296081277215,
      "loss": 4.8487,
      "step": 907
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00041219158200290275,
      "loss": 5.4142,
      "step": 908
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004107402031930334,
      "loss": 5.0128,
      "step": 909
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000409288824383164,
      "loss": 5.1977,
      "step": 910
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00040783744557329466,
      "loss": 5.0896,
      "step": 911
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00040638606676342525,
      "loss": 4.8231,
      "step": 912
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00040493468795355585,
      "loss": 4.9305,
      "step": 913
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004034833091436865,
      "loss": 4.9777,
      "step": 914
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004020319303338171,
      "loss": 5.1488,
      "step": 915
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00040058055152394776,
      "loss": 4.821,
      "step": 916
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003991291727140784,
      "loss": 4.8961,
      "step": 917
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000397677793904209,
      "loss": 4.9929,
      "step": 918
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00039622641509433966,
      "loss": 5.1567,
      "step": 919
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00039477503628447026,
      "loss": 5.0701,
      "step": 920
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00039332365747460086,
      "loss": 4.827,
      "step": 921
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003918722786647315,
      "loss": 5.2814,
      "step": 922
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003904208998548621,
      "loss": 4.7432,
      "step": 923
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003889695210449927,
      "loss": 4.9114,
      "step": 924
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00038751814223512336,
      "loss": 4.694,
      "step": 925
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00038606676342525396,
      "loss": 4.8725,
      "step": 926
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00038461538461538467,
      "loss": 5.5212,
      "step": 927
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00038316400580551527,
      "loss": 4.9127,
      "step": 928
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00038171262699564587,
      "loss": 4.7343,
      "step": 929
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003802612481857765,
      "loss": 4.799,
      "step": 930
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003788098693759071,
      "loss": 5.0624,
      "step": 931
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00037735849056603777,
      "loss": 5.5152,
      "step": 932
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00037590711175616837,
      "loss": 4.9362,
      "step": 933
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00037445573294629897,
      "loss": 4.8447,
      "step": 934
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003730043541364296,
      "loss": 5.0213,
      "step": 935
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003715529753265602,
      "loss": 4.9314,
      "step": 936
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003701015965166908,
      "loss": 5.0127,
      "step": 937
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003686502177068215,
      "loss": 5.0349,
      "step": 938
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003671988388969521,
      "loss": 4.9583,
      "step": 939
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003657474600870828,
      "loss": 4.9811,
      "step": 940
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003642960812772134,
      "loss": 4.8891,
      "step": 941
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000362844702467344,
      "loss": 4.9644,
      "step": 942
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00036139332365747463,
      "loss": 4.5369,
      "step": 943
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035994194484760523,
      "loss": 4.6659,
      "step": 944
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003584905660377358,
      "loss": 5.2977,
      "step": 945
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003570391872278665,
      "loss": 4.7141,
      "step": 946
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003555878084179971,
      "loss": 4.8314,
      "step": 947
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035413642960812773,
      "loss": 4.6193,
      "step": 948
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035268505079825833,
      "loss": 4.8419,
      "step": 949
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000351233671988389,
      "loss": 4.8189,
      "step": 950
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00034978229317851964,
      "loss": 4.8661,
      "step": 951
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00034833091436865023,
      "loss": 5.1865,
      "step": 952
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00034687953555878083,
      "loss": 4.8,
      "step": 953
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003454281567489115,
      "loss": 4.6069,
      "step": 954
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003439767779390421,
      "loss": 5.0117,
      "step": 955
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00034252539912917274,
      "loss": 5.0603,
      "step": 956
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00034107402031930334,
      "loss": 5.0904,
      "step": 957
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00033962264150943393,
      "loss": 4.9147,
      "step": 958
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003381712626995646,
      "loss": 5.0641,
      "step": 959
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003367198838896952,
      "loss": 4.8329,
      "step": 960
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00033526850507982584,
      "loss": 4.7659,
      "step": 961
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003338171262699565,
      "loss": 4.9337,
      "step": 962
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003323657474600871,
      "loss": 4.6835,
      "step": 963
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00033091436865021774,
      "loss": 5.1411,
      "step": 964
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00032946298984034834,
      "loss": 4.9891,
      "step": 965
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00032801161103047894,
      "loss": 4.7431,
      "step": 966
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003265602322206096,
      "loss": 5.0134,
      "step": 967
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003251088534107402,
      "loss": 4.9053,
      "step": 968
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00032365747460087085,
      "loss": 4.6344,
      "step": 969
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00032220609579100144,
      "loss": 4.8781,
      "step": 970
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00032075471698113204,
      "loss": 4.7326,
      "step": 971
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031930333817126275,
      "loss": 4.6855,
      "step": 972
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031785195936139335,
      "loss": 4.9818,
      "step": 973
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031640058055152395,
      "loss": 4.7883,
      "step": 974
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003149492017416546,
      "loss": 4.9197,
      "step": 975
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003134978229317852,
      "loss": 4.917,
      "step": 976
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031204644412191585,
      "loss": 4.8078,
      "step": 977
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00031059506531204645,
      "loss": 4.7798,
      "step": 978
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00030914368650217705,
      "loss": 4.6256,
      "step": 979
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003076923076923077,
      "loss": 4.9239,
      "step": 980
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003062409288824383,
      "loss": 5.1256,
      "step": 981
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003047895500725689,
      "loss": 5.2522,
      "step": 982
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003033381712626996,
      "loss": 4.7731,
      "step": 983
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003018867924528302,
      "loss": 4.9897,
      "step": 984
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00030043541364296086,
      "loss": 4.7127,
      "step": 985
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029898403483309146,
      "loss": 4.8191,
      "step": 986
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029753265602322206,
      "loss": 4.9202,
      "step": 987
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002960812772133527,
      "loss": 4.8658,
      "step": 988
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002946298984034833,
      "loss": 4.9547,
      "step": 989
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002931785195936139,
      "loss": 4.7892,
      "step": 990
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029172714078374456,
      "loss": 5.0276,
      "step": 991
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029027576197387516,
      "loss": 4.7144,
      "step": 992
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002888243831640058,
      "loss": 4.6585,
      "step": 993
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002873730043541364,
      "loss": 4.8446,
      "step": 994
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00028592162554426706,
      "loss": 4.8927,
      "step": 995
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002844702467343977,
      "loss": 5.8035,
      "step": 996
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002830188679245283,
      "loss": 5.0722,
      "step": 997
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00028156748911465897,
      "loss": 4.7843,
      "step": 998
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00028011611030478957,
      "loss": 4.9298,
      "step": 999
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00027866473149492017,
      "loss": 5.0039,
      "step": 1000
    },
    {
      "epoch": 0.84,
      "eval_loss": 5.048862457275391,
      "eval_runtime": 760.3008,
      "eval_samples_per_second": 3.475,
      "eval_steps_per_second": 0.291,
      "eval_wer": 1.9565251884172947,
      "step": 1000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002772133526850508,
      "loss": 4.8261,
      "step": 1001
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002757619738751814,
      "loss": 4.7969,
      "step": 1002
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000274310595065312,
      "loss": 4.7738,
      "step": 1003
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00027285921625544267,
      "loss": 4.9683,
      "step": 1004
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00027140783744557327,
      "loss": 4.9032,
      "step": 1005
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000269956458635704,
      "loss": 4.8847,
      "step": 1006
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002685050798258346,
      "loss": 4.7633,
      "step": 1007
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00026705370101596517,
      "loss": 4.7142,
      "step": 1008
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002656023222060958,
      "loss": 4.8657,
      "step": 1009
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002641509433962264,
      "loss": 4.7196,
      "step": 1010
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000262699564586357,
      "loss": 4.6712,
      "step": 1011
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002612481857764877,
      "loss": 4.6983,
      "step": 1012
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002597968069666183,
      "loss": 4.667,
      "step": 1013
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002583454281567489,
      "loss": 4.659,
      "step": 1014
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002568940493468795,
      "loss": 4.8124,
      "step": 1015
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002554426705370101,
      "loss": 5.1725,
      "step": 1016
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00025399129172714083,
      "loss": 4.6304,
      "step": 1017
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00025253991291727143,
      "loss": 4.9142,
      "step": 1018
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00025108853410740203,
      "loss": 5.0531,
      "step": 1019
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002496371552975327,
      "loss": 4.648,
      "step": 1020
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002481857764876633,
      "loss": 4.8026,
      "step": 1021
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002467343976777939,
      "loss": 4.9464,
      "step": 1022
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024528301886792453,
      "loss": 5.1749,
      "step": 1023
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024383164005805516,
      "loss": 4.6092,
      "step": 1024
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024238026124818576,
      "loss": 4.744,
      "step": 1025
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002409288824383164,
      "loss": 4.7657,
      "step": 1026
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00023947750362844704,
      "loss": 4.7509,
      "step": 1027
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00023802612481857766,
      "loss": 4.7388,
      "step": 1028
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002365747460087083,
      "loss": 4.6644,
      "step": 1029
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00023512336719883889,
      "loss": 4.5836,
      "step": 1030
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002336719883889695,
      "loss": 4.7619,
      "step": 1031
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00023222060957910016,
      "loss": 4.6205,
      "step": 1032
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002307692307692308,
      "loss": 5.0488,
      "step": 1033
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002293178519593614,
      "loss": 4.5679,
      "step": 1034
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00022786647314949202,
      "loss": 4.6562,
      "step": 1035
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00022641509433962264,
      "loss": 4.6732,
      "step": 1036
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002249637155297533,
      "loss": 4.6644,
      "step": 1037
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002235123367198839,
      "loss": 4.8933,
      "step": 1038
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00022206095791001452,
      "loss": 4.7343,
      "step": 1039
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00022060957910014514,
      "loss": 4.6194,
      "step": 1040
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021915820029027577,
      "loss": 4.8073,
      "step": 1041
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021770682148040637,
      "loss": 5.0539,
      "step": 1042
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021625544267053702,
      "loss": 4.7011,
      "step": 1043
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021480406386066765,
      "loss": 4.8361,
      "step": 1044
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021335268505079827,
      "loss": 5.0069,
      "step": 1045
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00021190130624092887,
      "loss": 4.6283,
      "step": 1046
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002104499274310595,
      "loss": 4.7217,
      "step": 1047
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00020899854862119015,
      "loss": 5.0962,
      "step": 1048
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00020754716981132078,
      "loss": 5.3154,
      "step": 1049
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00020609579100145138,
      "loss": 5.0557,
      "step": 1050
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000204644412191582,
      "loss": 4.9492,
      "step": 1051
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00020319303338171263,
      "loss": 4.7266,
      "step": 1052
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00020174165457184325,
      "loss": 4.742,
      "step": 1053
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00020029027576197388,
      "loss": 4.863,
      "step": 1054
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001988388969521045,
      "loss": 4.845,
      "step": 1055
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019738751814223513,
      "loss": 4.9859,
      "step": 1056
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019593613933236576,
      "loss": 4.7998,
      "step": 1057
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019448476052249636,
      "loss": 4.8476,
      "step": 1058
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019303338171262698,
      "loss": 4.7775,
      "step": 1059
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019158200290275763,
      "loss": 4.9301,
      "step": 1060
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019013062409288826,
      "loss": 4.8106,
      "step": 1061
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018867924528301889,
      "loss": 4.6737,
      "step": 1062
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018722786647314948,
      "loss": 4.9978,
      "step": 1063
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001857764876632801,
      "loss": 4.795,
      "step": 1064
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018432510885341076,
      "loss": 4.614,
      "step": 1065
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001828737300435414,
      "loss": 4.5133,
      "step": 1066
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000181422351233672,
      "loss": 4.705,
      "step": 1067
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017997097242380261,
      "loss": 4.6891,
      "step": 1068
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017851959361393324,
      "loss": 4.6569,
      "step": 1069
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017706821480406387,
      "loss": 4.8474,
      "step": 1070
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001756168359941945,
      "loss": 4.5824,
      "step": 1071
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017416545718432512,
      "loss": 4.7272,
      "step": 1072
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017271407837445574,
      "loss": 4.3551,
      "step": 1073
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00017126269956458637,
      "loss": 4.649,
      "step": 1074
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016981132075471697,
      "loss": 4.5383,
      "step": 1075
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001683599419448476,
      "loss": 4.871,
      "step": 1076
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016690856313497825,
      "loss": 5.0256,
      "step": 1077
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016545718432510887,
      "loss": 4.8263,
      "step": 1078
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016400580551523947,
      "loss": 4.7065,
      "step": 1079
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001625544267053701,
      "loss": 4.6886,
      "step": 1080
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016110304789550072,
      "loss": 4.8443,
      "step": 1081
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015965166908563138,
      "loss": 4.9113,
      "step": 1082
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015820029027576197,
      "loss": 4.7974,
      "step": 1083
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001567489114658926,
      "loss": 4.6697,
      "step": 1084
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015529753265602323,
      "loss": 4.6998,
      "step": 1085
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015384615384615385,
      "loss": 4.718,
      "step": 1086
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00015239477503628445,
      "loss": 4.655,
      "step": 1087
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001509433962264151,
      "loss": 4.9084,
      "step": 1088
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014949201741654573,
      "loss": 4.6914,
      "step": 1089
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014804063860667635,
      "loss": 4.7079,
      "step": 1090
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014658925979680695,
      "loss": 4.6175,
      "step": 1091
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014513788098693758,
      "loss": 4.4339,
      "step": 1092
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001436865021770682,
      "loss": 4.753,
      "step": 1093
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014223512336719886,
      "loss": 4.8632,
      "step": 1094
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014078374455732948,
      "loss": 4.9026,
      "step": 1095
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013933236574746008,
      "loss": 5.2352,
      "step": 1096
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001378809869375907,
      "loss": 4.7769,
      "step": 1097
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013642960812772133,
      "loss": 5.0062,
      "step": 1098
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000134978229317852,
      "loss": 5.2523,
      "step": 1099
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013352685050798259,
      "loss": 4.704,
      "step": 1100
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001320754716981132,
      "loss": 5.3307,
      "step": 1101
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013062409288824384,
      "loss": 4.716,
      "step": 1102
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012917271407837446,
      "loss": 4.8122,
      "step": 1103
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012772133526850506,
      "loss": 4.6091,
      "step": 1104
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012626995645863572,
      "loss": 4.6994,
      "step": 1105
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012481857764876634,
      "loss": 4.5174,
      "step": 1106
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012336719883889694,
      "loss": 5.0963,
      "step": 1107
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012191582002902758,
      "loss": 4.7831,
      "step": 1108
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001204644412191582,
      "loss": 4.75,
      "step": 1109
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011901306240928883,
      "loss": 4.5889,
      "step": 1110
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011756168359941944,
      "loss": 4.6618,
      "step": 1111
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011611030478955008,
      "loss": 4.959,
      "step": 1112
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001146589259796807,
      "loss": 4.6879,
      "step": 1113
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011320754716981132,
      "loss": 4.4547,
      "step": 1114
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011175616835994195,
      "loss": 4.7914,
      "step": 1115
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011030478955007257,
      "loss": 4.864,
      "step": 1116
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010885341074020318,
      "loss": 4.9186,
      "step": 1117
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010740203193033382,
      "loss": 4.6017,
      "step": 1118
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010595065312046444,
      "loss": 4.3441,
      "step": 1119
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010449927431059508,
      "loss": 4.8269,
      "step": 1120
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010304789550072569,
      "loss": 4.8003,
      "step": 1121
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010159651669085631,
      "loss": 4.908,
      "step": 1122
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010014513788098694,
      "loss": 4.597,
      "step": 1123
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.869375907111757e-05,
      "loss": 4.7209,
      "step": 1124
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.724238026124818e-05,
      "loss": 5.189,
      "step": 1125
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.579100145137882e-05,
      "loss": 4.6447,
      "step": 1126
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.433962264150944e-05,
      "loss": 4.7426,
      "step": 1127
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.288824383164006e-05,
      "loss": 4.6786,
      "step": 1128
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.14368650217707e-05,
      "loss": 4.7179,
      "step": 1129
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.998548621190131e-05,
      "loss": 4.8215,
      "step": 1130
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.853410740203193e-05,
      "loss": 4.4143,
      "step": 1131
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.708272859216256e-05,
      "loss": 4.4619,
      "step": 1132
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.563134978229318e-05,
      "loss": 4.763,
      "step": 1133
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.41799709724238e-05,
      "loss": 4.586,
      "step": 1134
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.272859216255444e-05,
      "loss": 4.9249,
      "step": 1135
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.127721335268505e-05,
      "loss": 4.5555,
      "step": 1136
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.982583454281569e-05,
      "loss": 4.6658,
      "step": 1137
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.83744557329463e-05,
      "loss": 4.6832,
      "step": 1138
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.692307692307693e-05,
      "loss": 4.5276,
      "step": 1139
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.547169811320755e-05,
      "loss": 4.512,
      "step": 1140
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.402031930333818e-05,
      "loss": 4.9081,
      "step": 1141
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.256894049346879e-05,
      "loss": 4.6692,
      "step": 1142
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.111756168359943e-05,
      "loss": 4.7582,
      "step": 1143
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.966618287373004e-05,
      "loss": 4.8991,
      "step": 1144
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.821480406386067e-05,
      "loss": 4.5162,
      "step": 1145
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.676342525399129e-05,
      "loss": 4.9342,
      "step": 1146
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.531204644412192e-05,
      "loss": 6.1205,
      "step": 1147
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.386066763425253e-05,
      "loss": 4.6055,
      "step": 1148
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.240928882438317e-05,
      "loss": 5.1268,
      "step": 1149
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.095791001451379e-05,
      "loss": 4.7341,
      "step": 1150
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.9506531204644415e-05,
      "loss": 4.5723,
      "step": 1151
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.805515239477504e-05,
      "loss": 4.4349,
      "step": 1152
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.660377358490566e-05,
      "loss": 4.6777,
      "step": 1153
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.5152394775036286e-05,
      "loss": 4.4656,
      "step": 1154
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.370101596516691e-05,
      "loss": 4.9724,
      "step": 1155
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.224963715529754e-05,
      "loss": 4.7204,
      "step": 1156
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.079825834542816e-05,
      "loss": 4.7556,
      "step": 1157
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.934687953555878e-05,
      "loss": 4.6727,
      "step": 1158
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.789550072568941e-05,
      "loss": 4.4809,
      "step": 1159
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.644412191582003e-05,
      "loss": 4.708,
      "step": 1160
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.4992743105950653e-05,
      "loss": 4.8091,
      "step": 1161
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.354136429608128e-05,
      "loss": 5.0111,
      "step": 1162
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.20899854862119e-05,
      "loss": 4.823,
      "step": 1163
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.0638606676342524e-05,
      "loss": 4.5235,
      "step": 1164
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.918722786647315e-05,
      "loss": 4.8935,
      "step": 1165
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.7735849056603776e-05,
      "loss": 4.8347,
      "step": 1166
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.6284470246734395e-05,
      "loss": 4.5507,
      "step": 1167
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.483309143686502e-05,
      "loss": 4.5014,
      "step": 1168
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.3381712626995646e-05,
      "loss": 4.6697,
      "step": 1169
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.1930333817126266e-05,
      "loss": 4.5949,
      "step": 1170
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.0478955007256895e-05,
      "loss": 4.6143,
      "step": 1171
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.902757619738752e-05,
      "loss": 4.4137,
      "step": 1172
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.7576197387518143e-05,
      "loss": 4.6779,
      "step": 1173
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.612481857764877e-05,
      "loss": 4.6309,
      "step": 1174
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.467343976777939e-05,
      "loss": 4.3231,
      "step": 1175
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.3222060957910014e-05,
      "loss": 4.5942,
      "step": 1176
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.177068214804064e-05,
      "loss": 4.5917,
      "step": 1177
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.0319303338171262e-05,
      "loss": 5.0845,
      "step": 1178
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.8867924528301888e-05,
      "loss": 4.4308,
      "step": 1179
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.741654571843251e-05,
      "loss": 4.7573,
      "step": 1180
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.5965166908563133e-05,
      "loss": 4.8455,
      "step": 1181
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.451378809869376e-05,
      "loss": 4.6741,
      "step": 1182
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.3062409288824384e-05,
      "loss": 4.5611,
      "step": 1183
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.1611030478955007e-05,
      "loss": 4.9078,
      "step": 1184
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0159651669085631e-05,
      "loss": 4.7998,
      "step": 1185
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.708272859216255e-06,
      "loss": 4.7906,
      "step": 1186
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.25689404934688e-06,
      "loss": 4.5753,
      "step": 1187
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.8055152394775034e-06,
      "loss": 4.7835,
      "step": 1188
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.354136429608128e-06,
      "loss": 4.9311,
      "step": 1189
    },
    {
      "epoch": 1.0,
      "step": 1189,
      "total_flos": 0.0,
      "train_loss": 5.084408325743936,
      "train_runtime": 6545.2766,
      "train_samples_per_second": 4.36,
      "train_steps_per_second": 0.182
    }
  ],
  "max_steps": 1189,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}