{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0001996,
      "loss": 2.4683,
      "step": 1
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019920000000000002,
      "loss": 2.2023,
      "step": 2
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001988,
      "loss": 2.3039,
      "step": 3
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001984,
      "loss": 2.1855,
      "step": 4
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019800000000000002,
      "loss": 2.328,
      "step": 5
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001976,
      "loss": 2.3407,
      "step": 6
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001972,
      "loss": 2.3432,
      "step": 7
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001968,
      "loss": 2.2333,
      "step": 8
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001964,
      "loss": 2.1761,
      "step": 9
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000196,
      "loss": 2.1473,
      "step": 10
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001956,
      "loss": 2.2076,
      "step": 11
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001952,
      "loss": 2.1925,
      "step": 12
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001948,
      "loss": 2.1694,
      "step": 13
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001944,
      "loss": 2.1056,
      "step": 14
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000194,
      "loss": 2.2426,
      "step": 15
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019360000000000002,
      "loss": 2.2635,
      "step": 16
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001932,
      "loss": 2.251,
      "step": 17
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001928,
      "loss": 2.224,
      "step": 18
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019240000000000001,
      "loss": 2.1848,
      "step": 19
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000192,
      "loss": 2.1341,
      "step": 20
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001916,
      "loss": 2.126,
      "step": 21
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001912,
      "loss": 2.0959,
      "step": 22
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001908,
      "loss": 2.2446,
      "step": 23
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001904,
      "loss": 1.9448,
      "step": 24
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019,
      "loss": 2.0939,
      "step": 25
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001896,
      "loss": 2.1247,
      "step": 26
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001892,
      "loss": 1.9417,
      "step": 27
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001888,
      "loss": 2.105,
      "step": 28
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001884,
      "loss": 2.1595,
      "step": 29
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.000188,
      "loss": 2.2009,
      "step": 30
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001876,
      "loss": 2.0784,
      "step": 31
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00018720000000000002,
      "loss": 2.2173,
      "step": 32
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00018680000000000001,
      "loss": 2.1185,
      "step": 33
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00018640000000000003,
      "loss": 1.988,
      "step": 34
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.9493,
      "step": 35
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001856,
      "loss": 1.9947,
      "step": 36
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00018520000000000003,
      "loss": 2.0506,
      "step": 37
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00018480000000000002,
      "loss": 2.0829,
      "step": 38
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001844,
      "loss": 2.1455,
      "step": 39
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.0304,
      "step": 40
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00018360000000000002,
      "loss": 2.006,
      "step": 41
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001832,
      "loss": 2.1759,
      "step": 42
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00018280000000000003,
      "loss": 2.0093,
      "step": 43
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00018240000000000002,
      "loss": 2.0683,
      "step": 44
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.000182,
      "loss": 2.1352,
      "step": 45
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018160000000000002,
      "loss": 1.9736,
      "step": 46
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001812,
      "loss": 1.9631,
      "step": 47
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001808,
      "loss": 2.1024,
      "step": 48
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00018040000000000002,
      "loss": 1.9895,
      "step": 49
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018,
      "loss": 2.0067,
      "step": 50
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001796,
      "loss": 2.0509,
      "step": 51
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00017920000000000002,
      "loss": 1.8795,
      "step": 52
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001788,
      "loss": 2.0633,
      "step": 53
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001784,
      "loss": 1.9998,
      "step": 54
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00017800000000000002,
      "loss": 2.0675,
      "step": 55
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001776,
      "loss": 2.0129,
      "step": 56
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001772,
      "loss": 1.9302,
      "step": 57
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00017680000000000001,
      "loss": 2.0472,
      "step": 58
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001764,
      "loss": 2.0031,
      "step": 59
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.0231,
      "step": 60
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001756,
      "loss": 2.0192,
      "step": 61
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001752,
      "loss": 2.1336,
      "step": 62
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00017480000000000002,
      "loss": 1.7753,
      "step": 63
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001744,
      "loss": 2.0274,
      "step": 64
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.000174,
      "loss": 1.8893,
      "step": 65
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00017360000000000002,
      "loss": 2.0341,
      "step": 66
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001732,
      "loss": 2.1081,
      "step": 67
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001728,
      "loss": 1.9463,
      "step": 68
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00017240000000000002,
      "loss": 2.0607,
      "step": 69
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.000172,
      "loss": 1.9803,
      "step": 70
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001716,
      "loss": 1.7663,
      "step": 71
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00017120000000000001,
      "loss": 2.1116,
      "step": 72
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001708,
      "loss": 1.9039,
      "step": 73
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001704,
      "loss": 2.049,
      "step": 74
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00017,
      "loss": 1.991,
      "step": 75
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001696,
      "loss": 1.8755,
      "step": 76
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001692,
      "loss": 2.0367,
      "step": 77
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001688,
      "loss": 1.9959,
      "step": 78
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0001684,
      "loss": 1.8051,
      "step": 79
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.000168,
      "loss": 2.0446,
      "step": 80
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001676,
      "loss": 1.7873,
      "step": 81
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0001672,
      "loss": 1.9264,
      "step": 82
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0001668,
      "loss": 1.8595,
      "step": 83
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0001664,
      "loss": 1.9992,
      "step": 84
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.000166,
      "loss": 1.8783,
      "step": 85
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0001656,
      "loss": 2.0216,
      "step": 86
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001652,
      "loss": 1.947,
      "step": 87
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001648,
      "loss": 1.9554,
      "step": 88
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001644,
      "loss": 1.8563,
      "step": 89
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.000164,
      "loss": 1.7795,
      "step": 90
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0001636,
      "loss": 1.9347,
      "step": 91
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0001632,
      "loss": 2.0078,
      "step": 92
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0001628,
      "loss": 1.9964,
      "step": 93
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.00016240000000000002,
      "loss": 1.9004,
      "step": 94
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.000162,
      "loss": 1.9446,
      "step": 95
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00016160000000000002,
      "loss": 1.8857,
      "step": 96
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.00016120000000000002,
      "loss": 1.8797,
      "step": 97
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0001608,
      "loss": 1.7643,
      "step": 98
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.00016040000000000002,
      "loss": 1.9724,
      "step": 99
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00016,
      "loss": 1.9058,
      "step": 100
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.0001596,
      "loss": 1.8663,
      "step": 101
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00015920000000000002,
      "loss": 1.8457,
      "step": 102
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001588,
      "loss": 1.8394,
      "step": 103
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.00015840000000000003,
      "loss": 1.8941,
      "step": 104
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.8601,
      "step": 105
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0001576,
      "loss": 1.7365,
      "step": 106
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00015720000000000003,
      "loss": 1.8809,
      "step": 107
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00015680000000000002,
      "loss": 2.0206,
      "step": 108
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0001564,
      "loss": 1.7776,
      "step": 109
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.9089,
      "step": 110
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.00015560000000000001,
      "loss": 1.8464,
      "step": 111
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001552,
      "loss": 1.7943,
      "step": 112
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.00015480000000000002,
      "loss": 1.8081,
      "step": 113
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001544,
      "loss": 1.734,
      "step": 114
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.000154,
      "loss": 1.8379,
      "step": 115
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.00015360000000000002,
      "loss": 1.6841,
      "step": 116
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001532,
      "loss": 1.8253,
      "step": 117
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0001528,
      "loss": 1.7607,
      "step": 118
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.00015240000000000002,
      "loss": 1.8205,
      "step": 119
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.000152,
      "loss": 1.8443,
      "step": 120
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0001516,
      "loss": 1.8824,
      "step": 121
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.00015120000000000002,
      "loss": 1.8369,
      "step": 122
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0001508,
      "loss": 1.8017,
      "step": 123
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0001504,
      "loss": 1.7858,
      "step": 124
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.8366,
      "step": 125
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0001496,
      "loss": 1.7353,
      "step": 126
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0001492,
      "loss": 1.6017,
      "step": 127
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.0001488,
      "loss": 1.6645,
      "step": 128
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.0001484,
      "loss": 1.8663,
      "step": 129
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.000148,
      "loss": 1.7009,
      "step": 130
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001476,
      "loss": 1.7371,
      "step": 131
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.0001472,
      "loss": 1.8555,
      "step": 132
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00014680000000000002,
      "loss": 1.6373,
      "step": 133
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0001464,
      "loss": 1.7211,
      "step": 134
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.000146,
      "loss": 1.614,
      "step": 135
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.00014560000000000002,
      "loss": 1.8736,
      "step": 136
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.0001452,
      "loss": 1.7229,
      "step": 137
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0001448,
      "loss": 1.7315,
      "step": 138
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0001444,
      "loss": 1.7259,
      "step": 139
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.000144,
      "loss": 1.7032,
      "step": 140
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.0001436,
      "loss": 1.9237,
      "step": 141
    },
    {
      "epoch": 5.68,
      "learning_rate": 0.0001432,
      "loss": 1.7821,
      "step": 142
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.0001428,
      "loss": 1.6081,
      "step": 143
    },
    {
      "epoch": 5.76,
      "learning_rate": 0.0001424,
      "loss": 1.7979,
      "step": 144
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.000142,
      "loss": 1.6675,
      "step": 145
    },
    {
      "epoch": 5.84,
      "learning_rate": 0.0001416,
      "loss": 1.6758,
      "step": 146
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.0001412,
      "loss": 1.7783,
      "step": 147
    },
    {
      "epoch": 5.92,
      "learning_rate": 0.0001408,
      "loss": 1.5935,
      "step": 148
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.0001404,
      "loss": 1.7372,
      "step": 149
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00014,
      "loss": 1.6308,
      "step": 150
    },
    {
      "epoch": 6.04,
      "learning_rate": 0.0001396,
      "loss": 1.5829,
      "step": 151
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.0001392,
      "loss": 1.6538,
      "step": 152
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.00013879999999999999,
      "loss": 1.7624,
      "step": 153
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.0001384,
      "loss": 1.4968,
      "step": 154
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.000138,
      "loss": 1.7305,
      "step": 155
    },
    {
      "epoch": 6.24,
      "learning_rate": 0.00013759999999999998,
      "loss": 1.6536,
      "step": 156
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00013720000000000003,
      "loss": 1.654,
      "step": 157
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.00013680000000000002,
      "loss": 1.7163,
      "step": 158
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.0001364,
      "loss": 1.6599,
      "step": 159
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.5729,
      "step": 160
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.00013560000000000002,
      "loss": 1.5291,
      "step": 161
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.0001352,
      "loss": 1.5666,
      "step": 162
    },
    {
      "epoch": 6.52,
      "learning_rate": 0.00013480000000000002,
      "loss": 1.7576,
      "step": 163
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.00013440000000000001,
      "loss": 1.4462,
      "step": 164
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.000134,
      "loss": 1.5659,
      "step": 165
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.00013360000000000002,
      "loss": 1.6234,
      "step": 166
    },
    {
      "epoch": 6.68,
      "learning_rate": 0.0001332,
      "loss": 1.5176,
      "step": 167
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.0001328,
      "loss": 1.667,
      "step": 168
    },
    {
      "epoch": 6.76,
      "learning_rate": 0.00013240000000000002,
      "loss": 1.6514,
      "step": 169
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.000132,
      "loss": 1.7179,
      "step": 170
    },
    {
      "epoch": 6.84,
      "learning_rate": 0.0001316,
      "loss": 1.4373,
      "step": 171
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.00013120000000000002,
      "loss": 1.7044,
      "step": 172
    },
    {
      "epoch": 6.92,
      "learning_rate": 0.0001308,
      "loss": 1.5673,
      "step": 173
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.0001304,
      "loss": 1.6303,
      "step": 174
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.4828,
      "step": 175
    },
    {
      "epoch": 7.04,
      "learning_rate": 0.0001296,
      "loss": 1.6204,
      "step": 176
    },
    {
      "epoch": 7.08,
      "learning_rate": 0.00012920000000000002,
      "loss": 1.4955,
      "step": 177
    },
    {
      "epoch": 7.12,
      "learning_rate": 0.00012880000000000001,
      "loss": 1.6109,
      "step": 178
    },
    {
      "epoch": 7.16,
      "learning_rate": 0.0001284,
      "loss": 1.5318,
      "step": 179
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.5702,
      "step": 180
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.0001276,
      "loss": 1.4598,
      "step": 181
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.0001272,
      "loss": 1.6145,
      "step": 182
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.00012680000000000002,
      "loss": 1.3628,
      "step": 183
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.0001264,
      "loss": 1.4578,
      "step": 184
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.000126,
      "loss": 1.7094,
      "step": 185
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.00012560000000000002,
      "loss": 1.4376,
      "step": 186
    },
    {
      "epoch": 7.48,
      "learning_rate": 0.0001252,
      "loss": 1.3393,
      "step": 187
    },
    {
      "epoch": 7.52,
      "learning_rate": 0.0001248,
      "loss": 1.4273,
      "step": 188
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.00012440000000000002,
      "loss": 1.5506,
      "step": 189
    },
    {
      "epoch": 7.6,
      "learning_rate": 0.000124,
      "loss": 1.4774,
      "step": 190
    },
    {
      "epoch": 7.64,
      "learning_rate": 0.0001236,
      "loss": 1.4632,
      "step": 191
    },
    {
      "epoch": 7.68,
      "learning_rate": 0.0001232,
      "loss": 1.4568,
      "step": 192
    },
    {
      "epoch": 7.72,
      "learning_rate": 0.0001228,
      "loss": 1.6106,
      "step": 193
    },
    {
      "epoch": 7.76,
      "learning_rate": 0.0001224,
      "loss": 1.577,
      "step": 194
    },
    {
      "epoch": 7.8,
      "learning_rate": 0.000122,
      "loss": 1.4805,
      "step": 195
    },
    {
      "epoch": 7.84,
      "learning_rate": 0.0001216,
      "loss": 1.4546,
      "step": 196
    },
    {
      "epoch": 7.88,
      "learning_rate": 0.0001212,
      "loss": 1.5164,
      "step": 197
    },
    {
      "epoch": 7.92,
      "learning_rate": 0.0001208,
      "loss": 1.5061,
      "step": 198
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.0001204,
      "loss": 1.5312,
      "step": 199
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.00012,
      "loss": 1.4463,
      "step": 200
    },
    {
      "epoch": 8.04,
      "learning_rate": 0.00011960000000000001,
      "loss": 1.4207,
      "step": 201
    },
    {
      "epoch": 8.08,
      "learning_rate": 0.0001192,
      "loss": 1.4688,
      "step": 202
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.0001188,
      "loss": 1.4445,
      "step": 203
    },
    {
      "epoch": 8.16,
      "learning_rate": 0.0001184,
      "loss": 1.4158,
      "step": 204
    },
    {
      "epoch": 8.2,
      "learning_rate": 0.000118,
      "loss": 1.3483,
      "step": 205
    },
    {
      "epoch": 8.24,
      "learning_rate": 0.0001176,
      "loss": 1.4117,
      "step": 206
    },
    {
      "epoch": 8.28,
      "learning_rate": 0.0001172,
      "loss": 1.4267,
      "step": 207
    },
    {
      "epoch": 8.32,
      "learning_rate": 0.00011679999999999999,
      "loss": 1.5547,
      "step": 208
    },
    {
      "epoch": 8.36,
      "learning_rate": 0.0001164,
      "loss": 1.4883,
      "step": 209
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.000116,
      "loss": 1.414,
      "step": 210
    },
    {
      "epoch": 8.44,
      "learning_rate": 0.00011559999999999999,
      "loss": 1.3254,
      "step": 211
    },
    {
      "epoch": 8.48,
      "learning_rate": 0.0001152,
      "loss": 1.22,
      "step": 212
    },
    {
      "epoch": 8.52,
      "learning_rate": 0.0001148,
      "loss": 1.3224,
      "step": 213
    },
    {
      "epoch": 8.56,
      "learning_rate": 0.0001144,
      "loss": 1.6158,
      "step": 214
    },
    {
      "epoch": 8.6,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.2817,
      "step": 215
    },
    {
      "epoch": 8.64,
      "learning_rate": 0.0001136,
      "loss": 1.4077,
      "step": 216
    },
    {
      "epoch": 8.68,
      "learning_rate": 0.0001132,
      "loss": 1.5311,
      "step": 217
    },
    {
      "epoch": 8.72,
      "learning_rate": 0.00011279999999999999,
      "loss": 1.5289,
      "step": 218
    },
    {
      "epoch": 8.76,
      "learning_rate": 0.00011240000000000002,
      "loss": 1.4576,
      "step": 219
    },
    {
      "epoch": 8.8,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.2063,
      "step": 220
    },
    {
      "epoch": 8.84,
      "learning_rate": 0.00011160000000000002,
      "loss": 1.3543,
      "step": 221
    },
    {
      "epoch": 8.88,
      "learning_rate": 0.00011120000000000002,
      "loss": 1.4352,
      "step": 222
    },
    {
      "epoch": 8.92,
      "learning_rate": 0.00011080000000000001,
      "loss": 1.3058,
      "step": 223
    },
    {
      "epoch": 8.96,
      "learning_rate": 0.00011040000000000001,
      "loss": 1.3475,
      "step": 224
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.1293,
      "step": 225
    },
    {
      "epoch": 9.04,
      "learning_rate": 0.00010960000000000001,
      "loss": 1.1671,
      "step": 226
    },
    {
      "epoch": 9.08,
      "learning_rate": 0.00010920000000000001,
      "loss": 1.4726,
      "step": 227
    },
    {
      "epoch": 9.12,
      "learning_rate": 0.00010880000000000002,
      "loss": 1.3986,
      "step": 228
    },
    {
      "epoch": 9.16,
      "learning_rate": 0.00010840000000000002,
      "loss": 1.2731,
      "step": 229
    },
    {
      "epoch": 9.2,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.2212,
      "step": 230
    },
    {
      "epoch": 9.24,
      "learning_rate": 0.00010760000000000001,
      "loss": 1.3067,
      "step": 231
    },
    {
      "epoch": 9.28,
      "learning_rate": 0.00010720000000000002,
      "loss": 1.278,
      "step": 232
    },
    {
      "epoch": 9.32,
      "learning_rate": 0.00010680000000000001,
      "loss": 1.4141,
      "step": 233
    },
    {
      "epoch": 9.36,
      "learning_rate": 0.00010640000000000001,
      "loss": 1.2885,
      "step": 234
    },
    {
      "epoch": 9.4,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.466,
      "step": 235
    },
    {
      "epoch": 9.44,
      "learning_rate": 0.0001056,
      "loss": 1.2979,
      "step": 236
    },
    {
      "epoch": 9.48,
      "learning_rate": 0.00010520000000000001,
      "loss": 1.1622,
      "step": 237
    },
    {
      "epoch": 9.52,
      "learning_rate": 0.00010480000000000001,
      "loss": 1.2504,
      "step": 238
    },
    {
      "epoch": 9.56,
      "learning_rate": 0.0001044,
      "loss": 1.228,
      "step": 239
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.3607,
      "step": 240
    },
    {
      "epoch": 9.64,
      "learning_rate": 0.00010360000000000001,
      "loss": 1.1921,
      "step": 241
    },
    {
      "epoch": 9.68,
      "learning_rate": 0.0001032,
      "loss": 1.2114,
      "step": 242
    },
    {
      "epoch": 9.72,
      "learning_rate": 0.0001028,
      "loss": 1.2385,
      "step": 243
    },
    {
      "epoch": 9.76,
      "learning_rate": 0.00010240000000000001,
      "loss": 1.3227,
      "step": 244
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.3935,
      "step": 245
    },
    {
      "epoch": 9.84,
      "learning_rate": 0.0001016,
      "loss": 1.2209,
      "step": 246
    },
    {
      "epoch": 9.88,
      "learning_rate": 0.00010120000000000001,
      "loss": 1.1541,
      "step": 247
    },
    {
      "epoch": 9.92,
      "learning_rate": 0.00010080000000000001,
      "loss": 1.4049,
      "step": 248
    },
    {
      "epoch": 9.96,
      "learning_rate": 0.0001004,
      "loss": 1.13,
      "step": 249
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001,
      "loss": 1.3783,
      "step": 250
    },
    {
      "epoch": 10.04,
      "learning_rate": 9.960000000000001e-05,
      "loss": 1.3207,
      "step": 251
    },
    {
      "epoch": 10.08,
      "learning_rate": 9.92e-05,
      "loss": 1.2697,
      "step": 252
    },
    {
      "epoch": 10.12,
      "learning_rate": 9.88e-05,
      "loss": 1.091,
      "step": 253
    },
    {
      "epoch": 10.16,
      "learning_rate": 9.84e-05,
      "loss": 1.0463,
      "step": 254
    },
    {
      "epoch": 10.2,
      "learning_rate": 9.8e-05,
      "loss": 1.3686,
      "step": 255
    },
    {
      "epoch": 10.24,
      "learning_rate": 9.76e-05,
      "loss": 1.3109,
      "step": 256
    },
    {
      "epoch": 10.28,
      "learning_rate": 9.72e-05,
      "loss": 1.2338,
      "step": 257
    },
    {
      "epoch": 10.32,
      "learning_rate": 9.680000000000001e-05,
      "loss": 1.12,
      "step": 258
    },
    {
      "epoch": 10.36,
      "learning_rate": 9.64e-05,
      "loss": 1.1864,
      "step": 259
    },
    {
      "epoch": 10.4,
      "learning_rate": 9.6e-05,
      "loss": 1.1062,
      "step": 260
    },
    {
      "epoch": 10.44,
      "learning_rate": 9.56e-05,
      "loss": 1.2924,
      "step": 261
    },
    {
      "epoch": 10.48,
      "learning_rate": 9.52e-05,
      "loss": 1.1931,
      "step": 262
    },
    {
      "epoch": 10.52,
      "learning_rate": 9.48e-05,
      "loss": 1.2366,
      "step": 263
    },
    {
      "epoch": 10.56,
      "learning_rate": 9.44e-05,
      "loss": 1.1589,
      "step": 264
    },
    {
      "epoch": 10.6,
      "learning_rate": 9.4e-05,
      "loss": 1.1197,
      "step": 265
    },
    {
      "epoch": 10.64,
      "learning_rate": 9.360000000000001e-05,
      "loss": 1.3072,
      "step": 266
    },
    {
      "epoch": 10.68,
      "learning_rate": 9.320000000000002e-05,
      "loss": 1.1173,
      "step": 267
    },
    {
      "epoch": 10.72,
      "learning_rate": 9.28e-05,
      "loss": 1.0378,
      "step": 268
    },
    {
      "epoch": 10.76,
      "learning_rate": 9.240000000000001e-05,
      "loss": 1.1746,
      "step": 269
    },
    {
      "epoch": 10.8,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.1144,
      "step": 270
    },
    {
      "epoch": 10.84,
      "learning_rate": 9.16e-05,
      "loss": 1.1862,
      "step": 271
    },
    {
      "epoch": 10.88,
      "learning_rate": 9.120000000000001e-05,
      "loss": 1.0816,
      "step": 272
    },
    {
      "epoch": 10.92,
      "learning_rate": 9.080000000000001e-05,
      "loss": 1.2288,
      "step": 273
    },
    {
      "epoch": 10.96,
      "learning_rate": 9.04e-05,
      "loss": 1.3031,
      "step": 274
    },
    {
      "epoch": 11.0,
      "learning_rate": 9e-05,
      "loss": 1.1646,
      "step": 275
    },
    {
      "epoch": 11.04,
      "learning_rate": 8.960000000000001e-05,
      "loss": 1.2088,
      "step": 276
    },
    {
      "epoch": 11.08,
      "learning_rate": 8.92e-05,
      "loss": 1.1465,
      "step": 277
    },
    {
      "epoch": 11.12,
      "learning_rate": 8.88e-05,
      "loss": 1.0313,
      "step": 278
    },
    {
      "epoch": 11.16,
      "learning_rate": 8.840000000000001e-05,
      "loss": 0.9662,
      "step": 279
    },
    {
      "epoch": 11.2,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.051,
      "step": 280
    },
    {
      "epoch": 11.24,
      "learning_rate": 8.76e-05,
      "loss": 1.1708,
      "step": 281
    },
    {
      "epoch": 11.28,
      "learning_rate": 8.72e-05,
      "loss": 1.0236,
      "step": 282
    },
    {
      "epoch": 11.32,
      "learning_rate": 8.680000000000001e-05,
      "loss": 1.1359,
      "step": 283
    },
    {
      "epoch": 11.36,
      "learning_rate": 8.64e-05,
      "loss": 1.1398,
      "step": 284
    },
    {
      "epoch": 11.4,
      "learning_rate": 8.6e-05,
      "loss": 1.0213,
      "step": 285
    },
    {
      "epoch": 11.44,
      "learning_rate": 8.560000000000001e-05,
      "loss": 1.1788,
      "step": 286
    },
    {
      "epoch": 11.48,
      "learning_rate": 8.52e-05,
      "loss": 1.0387,
      "step": 287
    },
    {
      "epoch": 11.52,
      "learning_rate": 8.48e-05,
      "loss": 0.9476,
      "step": 288
    },
    {
      "epoch": 11.56,
      "learning_rate": 8.44e-05,
      "loss": 1.1954,
      "step": 289
    },
    {
      "epoch": 11.6,
      "learning_rate": 8.4e-05,
      "loss": 1.0309,
      "step": 290
    },
    {
      "epoch": 11.64,
      "learning_rate": 8.36e-05,
      "loss": 1.1321,
      "step": 291
    },
    {
      "epoch": 11.68,
      "learning_rate": 8.32e-05,
      "loss": 1.0914,
      "step": 292
    },
    {
      "epoch": 11.72,
      "learning_rate": 8.28e-05,
      "loss": 1.222,
      "step": 293
    },
    {
      "epoch": 11.76,
      "learning_rate": 8.24e-05,
      "loss": 1.0127,
      "step": 294
    },
    {
      "epoch": 11.8,
      "learning_rate": 8.2e-05,
      "loss": 1.1977,
      "step": 295
    },
    {
      "epoch": 11.84,
      "learning_rate": 8.16e-05,
      "loss": 1.122,
      "step": 296
    },
    {
      "epoch": 11.88,
      "learning_rate": 8.120000000000001e-05,
      "loss": 1.1543,
      "step": 297
    },
    {
      "epoch": 11.92,
      "learning_rate": 8.080000000000001e-05,
      "loss": 1.1767,
      "step": 298
    },
    {
      "epoch": 11.96,
      "learning_rate": 8.04e-05,
      "loss": 1.1341,
      "step": 299
    },
    {
      "epoch": 12.0,
      "learning_rate": 8e-05,
      "loss": 1.0107,
      "step": 300
    },
    {
      "epoch": 12.04,
      "learning_rate": 7.960000000000001e-05,
      "loss": 1.1455,
      "step": 301
    },
    {
      "epoch": 12.08,
      "learning_rate": 7.920000000000001e-05,
      "loss": 1.0091,
      "step": 302
    },
    {
      "epoch": 12.12,
      "learning_rate": 7.88e-05,
      "loss": 0.9888,
      "step": 303
    },
    {
      "epoch": 12.16,
      "learning_rate": 7.840000000000001e-05,
      "loss": 0.9894,
      "step": 304
    },
    {
      "epoch": 12.2,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.0095,
      "step": 305
    },
    {
      "epoch": 12.24,
      "learning_rate": 7.76e-05,
      "loss": 1.1163,
      "step": 306
    },
    {
      "epoch": 12.28,
      "learning_rate": 7.72e-05,
      "loss": 1.0345,
      "step": 307
    },
    {
      "epoch": 12.32,
      "learning_rate": 7.680000000000001e-05,
      "loss": 0.9662,
      "step": 308
    },
    {
      "epoch": 12.36,
      "learning_rate": 7.64e-05,
      "loss": 0.9064,
      "step": 309
    },
    {
      "epoch": 12.4,
      "learning_rate": 7.6e-05,
      "loss": 0.9448,
      "step": 310
    },
    {
      "epoch": 12.44,
      "learning_rate": 7.560000000000001e-05,
      "loss": 0.9509,
      "step": 311
    },
    {
      "epoch": 12.48,
      "learning_rate": 7.52e-05,
      "loss": 1.123,
      "step": 312
    },
    {
      "epoch": 12.52,
      "learning_rate": 7.48e-05,
      "loss": 1.1011,
      "step": 313
    },
    {
      "epoch": 12.56,
      "learning_rate": 7.44e-05,
      "loss": 0.9398,
      "step": 314
    },
    {
      "epoch": 12.6,
      "learning_rate": 7.4e-05,
      "loss": 1.0498,
      "step": 315
    },
    {
      "epoch": 12.64,
      "learning_rate": 7.36e-05,
      "loss": 1.0442,
      "step": 316
    },
    {
      "epoch": 12.68,
      "learning_rate": 7.32e-05,
      "loss": 0.9599,
      "step": 317
    },
    {
      "epoch": 12.72,
      "learning_rate": 7.280000000000001e-05,
      "loss": 0.8778,
      "step": 318
    },
    {
      "epoch": 12.76,
      "learning_rate": 7.24e-05,
      "loss": 0.8727,
      "step": 319
    },
    {
      "epoch": 12.8,
      "learning_rate": 7.2e-05,
      "loss": 1.0189,
      "step": 320
    },
    {
      "epoch": 12.84,
      "learning_rate": 7.16e-05,
      "loss": 1.0543,
      "step": 321
    },
    {
      "epoch": 12.88,
      "learning_rate": 7.12e-05,
      "loss": 1.1282,
      "step": 322
    },
    {
      "epoch": 12.92,
      "learning_rate": 7.08e-05,
      "loss": 1.1018,
      "step": 323
    },
    {
      "epoch": 12.96,
      "learning_rate": 7.04e-05,
      "loss": 1.1827,
      "step": 324
    },
    {
      "epoch": 13.0,
      "learning_rate": 7e-05,
      "loss": 1.108,
      "step": 325
    },
    {
      "epoch": 13.04,
      "learning_rate": 6.96e-05,
      "loss": 0.9618,
      "step": 326
    },
    {
      "epoch": 13.08,
      "learning_rate": 6.92e-05,
      "loss": 1.0666,
      "step": 327
    },
    {
      "epoch": 13.12,
      "learning_rate": 6.879999999999999e-05,
      "loss": 0.9973,
      "step": 328
    },
    {
      "epoch": 13.16,
      "learning_rate": 6.840000000000001e-05,
      "loss": 1.0103,
      "step": 329
    },
    {
      "epoch": 13.2,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.9974,
      "step": 330
    },
    {
      "epoch": 13.24,
      "learning_rate": 6.76e-05,
      "loss": 1.2283,
      "step": 331
    },
    {
      "epoch": 13.28,
      "learning_rate": 6.720000000000001e-05,
      "loss": 0.7485,
      "step": 332
    },
    {
      "epoch": 13.32,
      "learning_rate": 6.680000000000001e-05,
      "loss": 0.8072,
      "step": 333
    },
    {
      "epoch": 13.36,
      "learning_rate": 6.64e-05,
      "loss": 1.1106,
      "step": 334
    },
    {
      "epoch": 13.4,
      "learning_rate": 6.6e-05,
      "loss": 0.8216,
      "step": 335
    },
    {
      "epoch": 13.44,
      "learning_rate": 6.560000000000001e-05,
      "loss": 0.959,
      "step": 336
    },
    {
      "epoch": 13.48,
      "learning_rate": 6.52e-05,
      "loss": 1.0767,
      "step": 337
    },
    {
      "epoch": 13.52,
      "learning_rate": 6.48e-05,
      "loss": 1.0395,
      "step": 338
    },
    {
      "epoch": 13.56,
      "learning_rate": 6.440000000000001e-05,
      "loss": 0.9102,
      "step": 339
    },
    {
      "epoch": 13.6,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.8875,
      "step": 340
    },
    {
      "epoch": 13.64,
      "learning_rate": 6.36e-05,
      "loss": 1.0005,
      "step": 341
    },
    {
      "epoch": 13.68,
      "learning_rate": 6.32e-05,
      "loss": 0.9208,
      "step": 342
    },
    {
      "epoch": 13.72,
      "learning_rate": 6.280000000000001e-05,
      "loss": 0.8943,
      "step": 343
    },
    {
      "epoch": 13.76,
      "learning_rate": 6.24e-05,
      "loss": 0.8441,
      "step": 344
    },
    {
      "epoch": 13.8,
      "learning_rate": 6.2e-05,
      "loss": 0.9953,
      "step": 345
    },
    {
      "epoch": 13.84,
      "learning_rate": 6.16e-05,
      "loss": 0.796,
      "step": 346
    },
    {
      "epoch": 13.88,
      "learning_rate": 6.12e-05,
      "loss": 1.0745,
      "step": 347
    },
    {
      "epoch": 13.92,
      "learning_rate": 6.08e-05,
      "loss": 0.9898,
      "step": 348
    },
    {
      "epoch": 13.96,
      "learning_rate": 6.04e-05,
      "loss": 0.9559,
      "step": 349
    },
    {
      "epoch": 14.0,
      "learning_rate": 6e-05,
      "loss": 0.8236,
      "step": 350
    },
    {
      "epoch": 14.04,
      "learning_rate": 5.96e-05,
      "loss": 0.7318,
      "step": 351
    },
    {
      "epoch": 14.08,
      "learning_rate": 5.92e-05,
      "loss": 0.8994,
      "step": 352
    },
    {
      "epoch": 14.12,
      "learning_rate": 5.88e-05,
      "loss": 0.9707,
      "step": 353
    },
    {
      "epoch": 14.16,
      "learning_rate": 5.8399999999999997e-05,
      "loss": 0.806,
      "step": 354
    },
    {
      "epoch": 14.2,
      "learning_rate": 5.8e-05,
      "loss": 1.0525,
      "step": 355
    },
    {
      "epoch": 14.24,
      "learning_rate": 5.76e-05,
      "loss": 0.7589,
      "step": 356
    },
    {
      "epoch": 14.28,
      "learning_rate": 5.72e-05,
      "loss": 0.7703,
      "step": 357
    },
    {
      "epoch": 14.32,
      "learning_rate": 5.68e-05,
      "loss": 0.9869,
      "step": 358
    },
    {
      "epoch": 14.36,
      "learning_rate": 5.6399999999999995e-05,
      "loss": 0.9673,
      "step": 359
    },
    {
      "epoch": 14.4,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.9913,
      "step": 360
    },
    {
      "epoch": 14.44,
      "learning_rate": 5.560000000000001e-05,
      "loss": 1.0219,
      "step": 361
    },
    {
      "epoch": 14.48,
      "learning_rate": 5.520000000000001e-05,
      "loss": 0.8672,
      "step": 362
    },
    {
      "epoch": 14.52,
      "learning_rate": 5.4800000000000004e-05,
      "loss": 1.0464,
      "step": 363
    },
    {
      "epoch": 14.56,
      "learning_rate": 5.440000000000001e-05,
      "loss": 1.0109,
      "step": 364
    },
    {
      "epoch": 14.6,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.9913,
      "step": 365
    },
    {
      "epoch": 14.64,
      "learning_rate": 5.360000000000001e-05,
      "loss": 0.779,
      "step": 366
    },
    {
      "epoch": 14.68,
      "learning_rate": 5.3200000000000006e-05,
      "loss": 0.8675,
      "step": 367
    },
    {
      "epoch": 14.72,
      "learning_rate": 5.28e-05,
      "loss": 0.987,
      "step": 368
    },
    {
      "epoch": 14.76,
      "learning_rate": 5.2400000000000007e-05,
      "loss": 0.741,
      "step": 369
    },
    {
      "epoch": 14.8,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.9585,
      "step": 370
    },
    {
      "epoch": 14.84,
      "learning_rate": 5.16e-05,
      "loss": 0.8977,
      "step": 371
    },
    {
      "epoch": 14.88,
      "learning_rate": 5.1200000000000004e-05,
      "loss": 0.7836,
      "step": 372
    },
    {
      "epoch": 14.92,
      "learning_rate": 5.08e-05,
      "loss": 0.8461,
      "step": 373
    },
    {
      "epoch": 14.96,
      "learning_rate": 5.0400000000000005e-05,
      "loss": 0.7531,
      "step": 374
    },
    {
      "epoch": 15.0,
      "learning_rate": 5e-05,
      "loss": 0.8906,
      "step": 375
    },
    {
      "epoch": 15.04,
      "learning_rate": 4.96e-05,
      "loss": 0.8793,
      "step": 376
    },
    {
      "epoch": 15.08,
      "learning_rate": 4.92e-05,
      "loss": 0.8596,
      "step": 377
    },
    {
      "epoch": 15.12,
      "learning_rate": 4.88e-05,
      "loss": 0.7947,
      "step": 378
    },
    {
      "epoch": 15.16,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 0.7976,
      "step": 379
    },
    {
      "epoch": 15.2,
      "learning_rate": 4.8e-05,
      "loss": 0.9037,
      "step": 380
    },
    {
      "epoch": 15.24,
      "learning_rate": 4.76e-05,
      "loss": 0.9863,
      "step": 381
    },
    {
      "epoch": 15.28,
      "learning_rate": 4.72e-05,
      "loss": 0.7735,
      "step": 382
    },
    {
      "epoch": 15.32,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 0.6723,
      "step": 383
    },
    {
      "epoch": 15.36,
      "learning_rate": 4.64e-05,
      "loss": 0.7002,
      "step": 384
    },
    {
      "epoch": 15.4,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9479,
      "step": 385
    },
    {
      "epoch": 15.44,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 0.8159,
      "step": 386
    },
    {
      "epoch": 15.48,
      "learning_rate": 4.52e-05,
      "loss": 0.7954,
      "step": 387
    },
    {
      "epoch": 15.52,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 0.8016,
      "step": 388
    },
    {
      "epoch": 15.56,
      "learning_rate": 4.44e-05,
      "loss": 0.7995,
      "step": 389
    },
    {
      "epoch": 15.6,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.8243,
      "step": 390
    },
    {
      "epoch": 15.64,
      "learning_rate": 4.36e-05,
      "loss": 0.8335,
      "step": 391
    },
    {
      "epoch": 15.68,
      "learning_rate": 4.32e-05,
      "loss": 1.001,
      "step": 392
    },
    {
      "epoch": 15.72,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 0.9385,
      "step": 393
    },
    {
      "epoch": 15.76,
      "learning_rate": 4.24e-05,
      "loss": 0.8796,
      "step": 394
    },
    {
      "epoch": 15.8,
      "learning_rate": 4.2e-05,
      "loss": 0.98,
      "step": 395
    },
    {
      "epoch": 15.84,
      "learning_rate": 4.16e-05,
      "loss": 0.7547,
      "step": 396
    },
    {
      "epoch": 15.88,
      "learning_rate": 4.12e-05,
      "loss": 0.7943,
      "step": 397
    },
    {
      "epoch": 15.92,
      "learning_rate": 4.08e-05,
      "loss": 0.8135,
      "step": 398
    },
    {
      "epoch": 15.96,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 0.87,
      "step": 399
    },
    {
      "epoch": 16.0,
      "learning_rate": 4e-05,
      "loss": 0.8818,
      "step": 400
    },
    {
      "epoch": 16.04,
      "learning_rate": 3.960000000000001e-05,
      "loss": 1.0793,
      "step": 401
    },
    {
      "epoch": 16.08,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 0.6816,
      "step": 402
    },
    {
      "epoch": 16.12,
      "learning_rate": 3.88e-05,
      "loss": 0.8138,
      "step": 403
    },
    {
      "epoch": 16.16,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.8002,
      "step": 404
    },
    {
      "epoch": 16.2,
      "learning_rate": 3.8e-05,
      "loss": 0.7104,
      "step": 405
    },
    {
      "epoch": 16.24,
      "learning_rate": 3.76e-05,
      "loss": 0.749,
      "step": 406
    },
    {
      "epoch": 16.28,
      "learning_rate": 3.72e-05,
      "loss": 0.9713,
      "step": 407
    },
    {
      "epoch": 16.32,
      "learning_rate": 3.68e-05,
      "loss": 0.9039,
      "step": 408
    },
    {
      "epoch": 16.36,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 0.7958,
      "step": 409
    },
    {
      "epoch": 16.4,
      "learning_rate": 3.6e-05,
      "loss": 0.9242,
      "step": 410
    },
    {
      "epoch": 16.44,
      "learning_rate": 3.56e-05,
      "loss": 0.7224,
      "step": 411
    },
    {
      "epoch": 16.48,
      "learning_rate": 3.52e-05,
      "loss": 0.8227,
      "step": 412
    },
    {
      "epoch": 16.52,
      "learning_rate": 3.48e-05,
      "loss": 0.7336,
      "step": 413
    },
    {
      "epoch": 16.56,
      "learning_rate": 3.4399999999999996e-05,
      "loss": 0.801,
      "step": 414
    },
    {
      "epoch": 16.6,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.7649,
      "step": 415
    },
    {
      "epoch": 16.64,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.859,
      "step": 416
    },
    {
      "epoch": 16.68,
      "learning_rate": 3.32e-05,
      "loss": 0.7702,
      "step": 417
    },
    {
      "epoch": 16.72,
      "learning_rate": 3.2800000000000004e-05,
      "loss": 0.7585,
      "step": 418
    },
    {
      "epoch": 16.76,
      "learning_rate": 3.24e-05,
      "loss": 0.6829,
      "step": 419
    },
    {
      "epoch": 16.8,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.8186,
      "step": 420
    },
    {
      "epoch": 16.84,
      "learning_rate": 3.16e-05,
      "loss": 0.7649,
      "step": 421
    },
    {
      "epoch": 16.88,
      "learning_rate": 3.12e-05,
      "loss": 0.8019,
      "step": 422
    },
    {
      "epoch": 16.92,
      "learning_rate": 3.08e-05,
      "loss": 0.82,
      "step": 423
    },
    {
      "epoch": 16.96,
      "learning_rate": 3.04e-05,
      "loss": 0.7077,
      "step": 424
    },
    {
      "epoch": 17.0,
      "learning_rate": 3e-05,
      "loss": 0.7803,
      "step": 425
    },
    {
      "epoch": 17.04,
      "learning_rate": 2.96e-05,
      "loss": 0.8311,
      "step": 426
    },
    {
      "epoch": 17.08,
      "learning_rate": 2.9199999999999998e-05,
      "loss": 0.8245,
      "step": 427
    },
    {
      "epoch": 17.12,
      "learning_rate": 2.88e-05,
      "loss": 0.6627,
      "step": 428
    },
    {
      "epoch": 17.16,
      "learning_rate": 2.84e-05,
      "loss": 0.6721,
      "step": 429
    },
    {
      "epoch": 17.2,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.9004,
      "step": 430
    },
    {
      "epoch": 17.24,
      "learning_rate": 2.7600000000000003e-05,
      "loss": 0.7606,
      "step": 431
    },
    {
      "epoch": 17.28,
      "learning_rate": 2.7200000000000004e-05,
      "loss": 0.7235,
      "step": 432
    },
    {
      "epoch": 17.32,
      "learning_rate": 2.6800000000000004e-05,
      "loss": 0.797,
      "step": 433
    },
    {
      "epoch": 17.36,
      "learning_rate": 2.64e-05,
      "loss": 0.6312,
      "step": 434
    },
    {
      "epoch": 17.4,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.869,
      "step": 435
    },
    {
      "epoch": 17.44,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 0.7968,
      "step": 436
    },
    {
      "epoch": 17.48,
      "learning_rate": 2.5200000000000003e-05,
      "loss": 0.6872,
      "step": 437
    },
    {
      "epoch": 17.52,
      "learning_rate": 2.48e-05,
      "loss": 0.7272,
      "step": 438
    },
    {
      "epoch": 17.56,
      "learning_rate": 2.44e-05,
      "loss": 0.7695,
      "step": 439
    },
    {
      "epoch": 17.6,
      "learning_rate": 2.4e-05,
      "loss": 0.6806,
      "step": 440
    },
    {
      "epoch": 17.64,
      "learning_rate": 2.36e-05,
      "loss": 0.9562,
      "step": 441
    },
    {
      "epoch": 17.68,
      "learning_rate": 2.32e-05,
      "loss": 0.8659,
      "step": 442
    },
    {
      "epoch": 17.72,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 0.8259,
      "step": 443
    },
    {
      "epoch": 17.76,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.7056,
      "step": 444
    },
    {
      "epoch": 17.8,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.7251,
      "step": 445
    },
    {
      "epoch": 17.84,
      "learning_rate": 2.16e-05,
      "loss": 0.8674,
      "step": 446
    },
    {
      "epoch": 17.88,
      "learning_rate": 2.12e-05,
      "loss": 0.7127,
      "step": 447
    },
    {
      "epoch": 17.92,
      "learning_rate": 2.08e-05,
      "loss": 0.849,
      "step": 448
    },
    {
      "epoch": 17.96,
      "learning_rate": 2.04e-05,
      "loss": 0.7506,
      "step": 449
    },
    {
      "epoch": 18.0,
      "learning_rate": 2e-05,
      "loss": 0.7262,
      "step": 450
    },
    {
      "epoch": 18.04,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.8102,
      "step": 451
    },
    {
      "epoch": 18.08,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.7843,
      "step": 452
    },
    {
      "epoch": 18.12,
      "learning_rate": 1.88e-05,
      "loss": 0.6902,
      "step": 453
    },
    {
      "epoch": 18.16,
      "learning_rate": 1.84e-05,
      "loss": 0.749,
      "step": 454
    },
    {
      "epoch": 18.2,
      "learning_rate": 1.8e-05,
      "loss": 0.722,
      "step": 455
    },
    {
      "epoch": 18.24,
      "learning_rate": 1.76e-05,
      "loss": 0.7015,
      "step": 456
    },
    {
      "epoch": 18.28,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 0.7451,
      "step": 457
    },
    {
      "epoch": 18.32,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.8411,
      "step": 458
    },
    {
      "epoch": 18.36,
      "learning_rate": 1.6400000000000002e-05,
      "loss": 0.8594,
      "step": 459
    },
    {
      "epoch": 18.4,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7394,
      "step": 460
    },
    {
      "epoch": 18.44,
      "learning_rate": 1.56e-05,
      "loss": 0.8071,
      "step": 461
    },
    {
      "epoch": 18.48,
      "learning_rate": 1.52e-05,
      "loss": 0.5883,
      "step": 462
    },
    {
      "epoch": 18.52,
      "learning_rate": 1.48e-05,
      "loss": 0.5356,
      "step": 463
    },
    {
      "epoch": 18.56,
      "learning_rate": 1.44e-05,
      "loss": 0.6916,
      "step": 464
    },
    {
      "epoch": 18.6,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.7899,
      "step": 465
    },
    {
      "epoch": 18.64,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.7651,
      "step": 466
    },
    {
      "epoch": 18.68,
      "learning_rate": 1.32e-05,
      "loss": 0.7883,
      "step": 467
    },
    {
      "epoch": 18.72,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.8655,
      "step": 468
    },
    {
      "epoch": 18.76,
      "learning_rate": 1.24e-05,
      "loss": 0.6875,
      "step": 469
    },
    {
      "epoch": 18.8,
      "learning_rate": 1.2e-05,
      "loss": 0.7629,
      "step": 470
    },
    {
      "epoch": 18.84,
      "learning_rate": 1.16e-05,
      "loss": 0.5825,
      "step": 471
    },
    {
      "epoch": 18.88,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.6979,
      "step": 472
    },
    {
      "epoch": 18.92,
      "learning_rate": 1.08e-05,
      "loss": 0.8777,
      "step": 473
    },
    {
      "epoch": 18.96,
      "learning_rate": 1.04e-05,
      "loss": 0.7298,
      "step": 474
    },
    {
      "epoch": 19.0,
      "learning_rate": 1e-05,
      "loss": 0.8324,
      "step": 475
    },
    {
      "epoch": 19.04,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.6186,
      "step": 476
    },
    {
      "epoch": 19.08,
      "learning_rate": 9.2e-06,
      "loss": 0.7853,
      "step": 477
    },
    {
      "epoch": 19.12,
      "learning_rate": 8.8e-06,
      "loss": 0.5731,
      "step": 478
    },
    {
      "epoch": 19.16,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.7915,
      "step": 479
    },
    {
      "epoch": 19.2,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.83,
      "step": 480
    },
    {
      "epoch": 19.24,
      "learning_rate": 7.6e-06,
      "loss": 0.7768,
      "step": 481
    },
    {
      "epoch": 19.28,
      "learning_rate": 7.2e-06,
      "loss": 0.6634,
      "step": 482
    },
    {
      "epoch": 19.32,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.657,
      "step": 483
    },
    {
      "epoch": 19.36,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.8127,
      "step": 484
    },
    {
      "epoch": 19.4,
      "learning_rate": 6e-06,
      "loss": 0.7326,
      "step": 485
    },
    {
      "epoch": 19.44,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.6168,
      "step": 486
    },
    {
      "epoch": 19.48,
      "learning_rate": 5.2e-06,
      "loss": 0.7808,
      "step": 487
    },
    {
      "epoch": 19.52,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.7509,
      "step": 488
    },
    {
      "epoch": 19.56,
      "learning_rate": 4.4e-06,
      "loss": 0.7304,
      "step": 489
    },
    {
      "epoch": 19.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.77,
      "step": 490
    },
    {
      "epoch": 19.64,
      "learning_rate": 3.6e-06,
      "loss": 0.6577,
      "step": 491
    },
    {
      "epoch": 19.68,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.6797,
      "step": 492
    },
    {
      "epoch": 19.72,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.807,
      "step": 493
    },
    {
      "epoch": 19.76,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.7484,
      "step": 494
    },
    {
      "epoch": 19.8,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7582,
      "step": 495
    },
    {
      "epoch": 19.84,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.7102,
      "step": 496
    },
    {
      "epoch": 19.88,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.7078,
      "step": 497
    },
    {
      "epoch": 19.92,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.7877,
      "step": 498
    },
    {
      "epoch": 19.96,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.8055,
      "step": 499
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0,
      "loss": 0.6905,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 500,
  "num_train_epochs": 20,
  "save_steps": 100,
  "total_flos": 1.701892530444288e+17,
  "trial_name": null,
  "trial_params": null
}