{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 9.058,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 8.7613,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-06,
      "loss": 8.9401,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-06,
      "loss": 8.9321,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-06,
      "loss": 8.8155,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 8.4795,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 8e-06,
      "loss": 8.1861,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 7.9638,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2e-05,
      "loss": 7.7096,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4e-05,
      "loss": 7.8138,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6e-05,
      "loss": 7.6533,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8e-05,
      "loss": 7.4974,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 7.4995,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-05,
      "loss": 7.4919,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4e-05,
      "loss": 7.2911,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.6e-05,
      "loss": 7.3818,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.8e-05,
      "loss": 7.289,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 3e-05,
      "loss": 7.2732,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2e-05,
      "loss": 7.1699,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 7.2997,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.6e-05,
      "loss": 7.2654,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.8e-05,
      "loss": 7.2562,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 7.2341,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 7.1936,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.4e-05,
      "loss": 7.087,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.6e-05,
      "loss": 7.2481,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.8e-05,
      "loss": 7.1482,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 7.0234,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.2e-05,
      "loss": 7.1107,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.4e-05,
      "loss": 7.1312,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.6e-05,
      "loss": 7.1319,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.800000000000001e-05,
      "loss": 7.0867,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-05,
      "loss": 7.1029,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.2e-05,
      "loss": 6.9942,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.4e-05,
      "loss": 7.0135,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.6e-05,
      "loss": 7.0468,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.800000000000001e-05,
      "loss": 7.1351,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.000000000000001e-05,
      "loss": 7.0239,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.2e-05,
      "loss": 7.1055,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.4e-05,
      "loss": 7.0529,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.6e-05,
      "loss": 7.0928,
      "step": 41
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.8e-05,
      "loss": 7.0995,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 8e-05,
      "loss": 6.868,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.2e-05,
      "loss": 7.0389,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.400000000000001e-05,
      "loss": 7.0978,
      "step": 45
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.599999999999999e-05,
      "loss": 7.0015,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.8e-05,
      "loss": 6.9493,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.999999999999999e-05,
      "loss": 6.9514,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.2e-05,
      "loss": 6.7024,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.400000000000001e-05,
      "loss": 6.4352,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.6e-05,
      "loss": 7.2917,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.800000000000001e-05,
      "loss": 7.1611,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 7.1632,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000102,
      "loss": 7.0577,
      "step": 54
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000104,
      "loss": 6.9254,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000106,
      "loss": 7.0441,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000108,
      "loss": 7.104,
      "step": 57
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00011,
      "loss": 7.1653,
      "step": 58
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000112,
      "loss": 7.0212,
      "step": 59
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000114,
      "loss": 7.041,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00011600000000000001,
      "loss": 7.0323,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000118,
      "loss": 7.03,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00012,
      "loss": 6.9586,
      "step": 63
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000122,
      "loss": 7.0752,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000124,
      "loss": 6.9839,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000126,
      "loss": 6.9496,
      "step": 66
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000128,
      "loss": 6.9913,
      "step": 67
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00013000000000000002,
      "loss": 7.0036,
      "step": 68
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000132,
      "loss": 7.0529,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000134,
      "loss": 6.9548,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00013600000000000003,
      "loss": 7.0742,
      "step": 71
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00013800000000000002,
      "loss": 7.0652,
      "step": 72
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00014000000000000001,
      "loss": 7.1607,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00014199999999999998,
      "loss": 7.0535,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000144,
      "loss": 7.0252,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000146,
      "loss": 7.0717,
      "step": 76
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000148,
      "loss": 7.0656,
      "step": 77
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00015,
      "loss": 7.0663,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000152,
      "loss": 6.9699,
      "step": 79
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000154,
      "loss": 7.0587,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000156,
      "loss": 7.0515,
      "step": 81
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000158,
      "loss": 7.0416,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016,
      "loss": 7.0491,
      "step": 83
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000162,
      "loss": 7.0139,
      "step": 84
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000164,
      "loss": 7.0157,
      "step": 85
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016600000000000002,
      "loss": 7.0541,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016800000000000002,
      "loss": 7.0067,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00017,
      "loss": 6.9629,
      "step": 88
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00017199999999999998,
      "loss": 6.9218,
      "step": 89
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000174,
      "loss": 7.0658,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000176,
      "loss": 6.9446,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000178,
      "loss": 7.1844,
      "step": 92
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00017999999999999998,
      "loss": 7.0148,
      "step": 93
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000182,
      "loss": 6.8312,
      "step": 94
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000184,
      "loss": 6.7648,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000186,
      "loss": 7.0495,
      "step": 96
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018800000000000002,
      "loss": 6.8445,
      "step": 97
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019,
      "loss": 6.586,
      "step": 98
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000192,
      "loss": 6.8264,
      "step": 99
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000194,
      "loss": 6.2679,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019600000000000002,
      "loss": 7.232,
      "step": 101
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019800000000000002,
      "loss": 7.1135,
      "step": 102
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 7.3081,
      "step": 103
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000202,
      "loss": 7.1059,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000204,
      "loss": 7.0181,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000206,
      "loss": 7.042,
      "step": 106
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000208,
      "loss": 6.9934,
      "step": 107
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00021,
      "loss": 7.0081,
      "step": 108
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000212,
      "loss": 6.9232,
      "step": 109
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000214,
      "loss": 6.9753,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000216,
      "loss": 6.8964,
      "step": 111
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000218,
      "loss": 6.8813,
      "step": 112
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00022,
      "loss": 6.9205,
      "step": 113
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000222,
      "loss": 6.972,
      "step": 114
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000224,
      "loss": 6.9011,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00022600000000000002,
      "loss": 7.0466,
      "step": 116
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000228,
      "loss": 6.9956,
      "step": 117
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00023,
      "loss": 6.9582,
      "step": 118
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00023200000000000003,
      "loss": 6.8957,
      "step": 119
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00023400000000000002,
      "loss": 6.9889,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000236,
      "loss": 6.8994,
      "step": 121
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00023799999999999998,
      "loss": 6.8518,
      "step": 122
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00024,
      "loss": 6.9078,
      "step": 123
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000242,
      "loss": 6.8499,
      "step": 124
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000244,
      "loss": 6.9592,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000246,
      "loss": 6.9507,
      "step": 126
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000248,
      "loss": 6.9285,
      "step": 127
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00025,
      "loss": 6.9252,
      "step": 128
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000252,
      "loss": 6.975,
      "step": 129
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000254,
      "loss": 7.0424,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000256,
      "loss": 6.8453,
      "step": 131
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00025800000000000004,
      "loss": 7.0332,
      "step": 132
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00026000000000000003,
      "loss": 6.8761,
      "step": 133
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000262,
      "loss": 6.9125,
      "step": 134
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000264,
      "loss": 7.0235,
      "step": 135
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000266,
      "loss": 6.8194,
      "step": 136
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000268,
      "loss": 6.9921,
      "step": 137
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027,
      "loss": 6.91,
      "step": 138
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027200000000000005,
      "loss": 6.8729,
      "step": 139
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00027400000000000005,
      "loss": 6.9956,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00027600000000000004,
      "loss": 7.0116,
      "step": 141
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00027800000000000004,
      "loss": 6.9834,
      "step": 142
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028000000000000003,
      "loss": 6.8219,
      "step": 143
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00028199999999999997,
      "loss": 6.81,
      "step": 144
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00028399999999999996,
      "loss": 6.769,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00028599999999999996,
      "loss": 6.7932,
      "step": 146
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000288,
      "loss": 6.8492,
      "step": 147
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029,
      "loss": 6.8182,
      "step": 148
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000292,
      "loss": 6.6264,
      "step": 149
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000294,
      "loss": 6.5046,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000296,
      "loss": 7.0365,
      "step": 151
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000298,
      "loss": 7.1078,
      "step": 152
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 7.0393,
      "step": 153
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000302,
      "loss": 6.9125,
      "step": 154
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000304,
      "loss": 6.901,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000306,
      "loss": 6.9173,
      "step": 156
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000308,
      "loss": 7.0307,
      "step": 157
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00031,
      "loss": 6.9548,
      "step": 158
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000312,
      "loss": 6.9309,
      "step": 159
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000314,
      "loss": 6.988,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000316,
      "loss": 6.9284,
      "step": 161
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00031800000000000003,
      "loss": 6.9905,
      "step": 162
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00032,
      "loss": 6.9599,
      "step": 163
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000322,
      "loss": 6.9554,
      "step": 164
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000324,
      "loss": 6.9063,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000326,
      "loss": 6.9603,
      "step": 166
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000328,
      "loss": 6.892,
      "step": 167
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033,
      "loss": 6.82,
      "step": 168
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033200000000000005,
      "loss": 6.843,
      "step": 169
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033400000000000004,
      "loss": 6.9878,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00033600000000000004,
      "loss": 6.9122,
      "step": 171
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00033800000000000003,
      "loss": 6.9609,
      "step": 172
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00034,
      "loss": 6.9128,
      "step": 173
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000342,
      "loss": 6.9686,
      "step": 174
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00034399999999999996,
      "loss": 6.9677,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000346,
      "loss": 6.8522,
      "step": 176
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000348,
      "loss": 6.8334,
      "step": 177
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00035,
      "loss": 6.9131,
      "step": 178
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000352,
      "loss": 6.9267,
      "step": 179
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000354,
      "loss": 6.9799,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000356,
      "loss": 6.9508,
      "step": 181
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000358,
      "loss": 6.8477,
      "step": 182
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00035999999999999997,
      "loss": 6.9096,
      "step": 183
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000362,
      "loss": 6.9855,
      "step": 184
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000364,
      "loss": 6.9124,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000366,
      "loss": 6.8208,
      "step": 186
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000368,
      "loss": 6.8933,
      "step": 187
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00037,
      "loss": 6.8645,
      "step": 188
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000372,
      "loss": 6.9765,
      "step": 189
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000374,
      "loss": 6.9949,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00037600000000000003,
      "loss": 6.9836,
      "step": 191
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000378,
      "loss": 6.8604,
      "step": 192
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00038,
      "loss": 6.8956,
      "step": 193
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000382,
      "loss": 6.8332,
      "step": 194
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000384,
      "loss": 6.8282,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000386,
      "loss": 6.7299,
      "step": 196
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000388,
      "loss": 6.6981,
      "step": 197
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039000000000000005,
      "loss": 6.7954,
      "step": 198
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039200000000000004,
      "loss": 6.6457,
      "step": 199
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039400000000000004,
      "loss": 6.5128,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039600000000000003,
      "loss": 7.1254,
      "step": 201
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000398,
      "loss": 7.0731,
      "step": 202
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0004,
      "loss": 7.0289,
      "step": 203
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000402,
      "loss": 6.9703,
      "step": 204
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000404,
      "loss": 7.0268,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00040600000000000006,
      "loss": 6.9987,
      "step": 206
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000408,
      "loss": 6.9034,
      "step": 207
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00041,
      "loss": 7.0335,
      "step": 208
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000412,
      "loss": 6.9846,
      "step": 209
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000414,
      "loss": 7.0235,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000416,
      "loss": 6.9098,
      "step": 211
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00041799999999999997,
      "loss": 6.9513,
      "step": 212
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00042,
      "loss": 6.8177,
      "step": 213
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000422,
      "loss": 6.9137,
      "step": 214
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000424,
      "loss": 6.8912,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000426,
      "loss": 6.9322,
      "step": 216
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000428,
      "loss": 6.8724,
      "step": 217
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00043,
      "loss": 6.9227,
      "step": 218
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000432,
      "loss": 6.9208,
      "step": 219
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00043400000000000003,
      "loss": 6.9525,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000436,
      "loss": 6.9423,
      "step": 221
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000438,
      "loss": 6.9664,
      "step": 222
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00044,
      "loss": 6.8986,
      "step": 223
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000442,
      "loss": 6.8933,
      "step": 224
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000444,
      "loss": 7.0104,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000446,
      "loss": 6.893,
      "step": 226
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000448,
      "loss": 7.0228,
      "step": 227
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00045000000000000004,
      "loss": 6.9624,
      "step": 228
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00045200000000000004,
      "loss": 6.8561,
      "step": 229
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00045400000000000003,
      "loss": 6.9604,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000456,
      "loss": 6.9243,
      "step": 231
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000458,
      "loss": 6.8045,
      "step": 232
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00046,
      "loss": 6.8398,
      "step": 233
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000462,
      "loss": 6.8647,
      "step": 234
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00046400000000000006,
      "loss": 6.9927,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00046600000000000005,
      "loss": 6.8641,
      "step": 236
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00046800000000000005,
      "loss": 6.9991,
      "step": 237
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00047,
      "loss": 6.8918,
      "step": 238
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000472,
      "loss": 6.8122,
      "step": 239
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000474,
      "loss": 7.0181,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00047599999999999997,
      "loss": 6.8649,
      "step": 241
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00047799999999999996,
      "loss": 6.8825,
      "step": 242
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00048,
      "loss": 6.9997,
      "step": 243
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000482,
      "loss": 6.7921,
      "step": 244
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000484,
      "loss": 6.8225,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000486,
      "loss": 6.7595,
      "step": 246
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000488,
      "loss": 6.5411,
      "step": 247
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00049,
      "loss": 6.821,
      "step": 248
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000492,
      "loss": 6.727,
      "step": 249
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000494,
      "loss": 6.4409,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000496,
      "loss": 7.1683,
      "step": 251
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000498,
      "loss": 7.0668,
      "step": 252
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005,
      "loss": 7.0276,
      "step": 253
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005020000000000001,
      "loss": 7.0282,
      "step": 254
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000504,
      "loss": 7.0416,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000506,
      "loss": 7.0002,
      "step": 256
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000508,
      "loss": 7.0033,
      "step": 257
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00051,
      "loss": 7.0092,
      "step": 258
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000512,
      "loss": 6.928,
      "step": 259
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000514,
      "loss": 6.9736,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005160000000000001,
      "loss": 6.9636,
      "step": 261
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000518,
      "loss": 6.9479,
      "step": 262
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005200000000000001,
      "loss": 7.0043,
      "step": 263
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000522,
      "loss": 6.9903,
      "step": 264
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000524,
      "loss": 7.0038,
      "step": 265
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000526,
      "loss": 6.7783,
      "step": 266
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000528,
      "loss": 7.0107,
      "step": 267
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005300000000000001,
      "loss": 6.8296,
      "step": 268
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000532,
      "loss": 6.9727,
      "step": 269
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005340000000000001,
      "loss": 6.9827,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000536,
      "loss": 6.8958,
      "step": 271
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005380000000000001,
      "loss": 6.8921,
      "step": 272
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00054,
      "loss": 6.8098,
      "step": 273
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005420000000000001,
      "loss": 6.7358,
      "step": 274
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0005440000000000001,
      "loss": 7.0087,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000546,
      "loss": 6.8763,
      "step": 276
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0005480000000000001,
      "loss": 6.8399,
      "step": 277
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00055,
      "loss": 6.934,
      "step": 278
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005520000000000001,
      "loss": 6.9767,
      "step": 279
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000554,
      "loss": 7.0013,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005560000000000001,
      "loss": 6.9378,
      "step": 281
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000558,
      "loss": 6.8736,
      "step": 282
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0005600000000000001,
      "loss": 6.8258,
      "step": 283
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005620000000000001,
      "loss": 6.881,
      "step": 284
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005639999999999999,
      "loss": 6.877,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000566,
      "loss": 6.964,
      "step": 286
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0005679999999999999,
      "loss": 6.924,
      "step": 287
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00057,
      "loss": 6.9248,
      "step": 288
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005719999999999999,
      "loss": 6.8809,
      "step": 289
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000574,
      "loss": 6.9341,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000576,
      "loss": 6.9908,
      "step": 291
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000578,
      "loss": 6.9272,
      "step": 292
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00058,
      "loss": 6.8068,
      "step": 293
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005819999999999999,
      "loss": 6.7484,
      "step": 294
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000584,
      "loss": 6.7442,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0005859999999999999,
      "loss": 6.7326,
      "step": 296
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000588,
      "loss": 6.7709,
      "step": 297
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00059,
      "loss": 6.7711,
      "step": 298
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000592,
      "loss": 6.4007,
      "step": 299
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000594,
      "loss": 6.4146,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000596,
      "loss": 7.1881,
      "step": 301
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000598,
      "loss": 7.0946,
      "step": 302
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0006,
      "loss": 7.0366,
      "step": 303
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000602,
      "loss": 6.9271,
      "step": 304
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000604,
      "loss": 7.0897,
      "step": 305
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000606,
      "loss": 6.8866,
      "step": 306
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000608,
      "loss": 6.9124,
      "step": 307
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00061,
      "loss": 7.0546,
      "step": 308
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000612,
      "loss": 6.8526,
      "step": 309
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000614,
      "loss": 6.9688,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000616,
      "loss": 6.9559,
      "step": 311
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006180000000000001,
      "loss": 6.9221,
      "step": 312
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00062,
      "loss": 6.8472,
      "step": 313
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000622,
      "loss": 6.8412,
      "step": 314
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000624,
      "loss": 6.997,
      "step": 315
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000626,
      "loss": 6.8871,
      "step": 316
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000628,
      "loss": 6.856,
      "step": 317
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00063,
      "loss": 6.7757,
      "step": 318
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000632,
      "loss": 6.8653,
      "step": 319
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000634,
      "loss": 6.8784,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006360000000000001,
      "loss": 6.8707,
      "step": 321
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000638,
      "loss": 6.826,
      "step": 322
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00064,
      "loss": 6.9139,
      "step": 323
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000642,
      "loss": 6.8378,
      "step": 324
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000644,
      "loss": 6.8941,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000646,
      "loss": 6.9395,
      "step": 326
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000648,
      "loss": 6.8839,
      "step": 327
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006500000000000001,
      "loss": 6.825,
      "step": 328
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000652,
      "loss": 6.9028,
      "step": 329
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006540000000000001,
      "loss": 6.9174,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000656,
      "loss": 6.8735,
      "step": 331
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0006580000000000001,
      "loss": 6.7823,
      "step": 332
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00066,
      "loss": 6.9539,
      "step": 333
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000662,
      "loss": 6.8746,
      "step": 334
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0006640000000000001,
      "loss": 6.9545,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000666,
      "loss": 6.8598,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006680000000000001,
      "loss": 6.731,
      "step": 337
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00067,
      "loss": 6.9194,
      "step": 338
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006720000000000001,
      "loss": 6.8805,
      "step": 339
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000674,
      "loss": 6.9178,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0006760000000000001,
      "loss": 6.7853,
      "step": 341
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006780000000000001,
      "loss": 6.9158,
      "step": 342
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00068,
      "loss": 6.7655,
      "step": 343
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006820000000000001,
      "loss": 6.7349,
      "step": 344
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000684,
      "loss": 6.7429,
      "step": 345
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0006860000000000001,
      "loss": 6.821,
      "step": 346
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0006879999999999999,
      "loss": 6.6749,
      "step": 347
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00069,
      "loss": 6.5191,
      "step": 348
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000692,
      "loss": 6.613,
      "step": 349
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000694,
      "loss": 6.3143,
      "step": 350
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000696,
      "loss": 7.042,
      "step": 351
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0006979999999999999,
      "loss": 7.0495,
      "step": 352
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0007,
      "loss": 6.9122,
      "step": 353
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0007019999999999999,
      "loss": 6.8473,
      "step": 354
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000704,
      "loss": 6.9169,
      "step": 355
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0007059999999999999,
      "loss": 7.0432,
      "step": 356
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000708,
      "loss": 6.9105,
      "step": 357
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00071,
      "loss": 6.9928,
      "step": 358
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000712,
      "loss": 6.8983,
      "step": 359
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000714,
      "loss": 6.8808,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000716,
      "loss": 6.8656,
      "step": 361
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000718,
      "loss": 6.7979,
      "step": 362
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0007199999999999999,
      "loss": 6.754,
      "step": 363
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000722,
      "loss": 6.8061,
      "step": 364
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000724,
      "loss": 6.9021,
      "step": 365
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000726,
      "loss": 6.8486,
      "step": 366
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000728,
      "loss": 6.9699,
      "step": 367
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00073,
      "loss": 6.9067,
      "step": 368
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000732,
      "loss": 6.7865,
      "step": 369
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000734,
      "loss": 6.8306,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000736,
      "loss": 6.8887,
      "step": 371
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000738,
      "loss": 6.9094,
      "step": 372
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00074,
      "loss": 6.8319,
      "step": 373
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000742,
      "loss": 6.7177,
      "step": 374
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000744,
      "loss": 6.8512,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000746,
      "loss": 6.7854,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000748,
      "loss": 6.8627,
      "step": 377
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00075,
      "loss": 6.8255,
      "step": 378
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0007520000000000001,
      "loss": 6.8259,
      "step": 379
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000754,
      "loss": 6.8465,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000756,
      "loss": 6.9686,
      "step": 381
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000758,
      "loss": 6.8864,
      "step": 382
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00076,
      "loss": 6.8678,
      "step": 383
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000762,
      "loss": 6.8329,
      "step": 384
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000764,
      "loss": 6.9062,
      "step": 385
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0007660000000000001,
      "loss": 6.8693,
      "step": 386
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000768,
      "loss": 6.8085,
      "step": 387
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0007700000000000001,
      "loss": 6.8915,
      "step": 388
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000772,
      "loss": 6.8316,
      "step": 389
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0007740000000000001,
      "loss": 6.7548,
      "step": 390
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000776,
      "loss": 6.869,
      "step": 391
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000778,
      "loss": 6.8538,
      "step": 392
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0007800000000000001,
      "loss": 6.7857,
      "step": 393
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000782,
      "loss": 6.7821,
      "step": 394
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007840000000000001,
      "loss": 6.9268,
      "step": 395
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000786,
      "loss": 6.8703,
      "step": 396
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007880000000000001,
      "loss": 6.8004,
      "step": 397
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00079,
      "loss": 6.6531,
      "step": 398
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0007920000000000001,
      "loss": 6.6996,
      "step": 399
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007940000000000001,
      "loss": 6.371,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000796,
      "loss": 7.1791,
      "step": 401
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007980000000000001,
      "loss": 7.0062,
      "step": 402
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0008,
      "loss": 7.0965,
      "step": 403
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008020000000000001,
      "loss": 6.9202,
      "step": 404
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000804,
      "loss": 6.868,
      "step": 405
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008060000000000001,
      "loss": 6.9814,
      "step": 406
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000808,
      "loss": 7.017,
      "step": 407
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0008100000000000001,
      "loss": 6.8681,
      "step": 408
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008120000000000001,
      "loss": 6.8563,
      "step": 409
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008139999999999999,
      "loss": 6.8619,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000816,
      "loss": 6.951,
      "step": 411
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008179999999999999,
      "loss": 7.847,
      "step": 412
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00082,
      "loss": 6.9371,
      "step": 413
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0008219999999999999,
      "loss": 6.9672,
      "step": 414
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000824,
      "loss": 6.9922,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000826,
      "loss": 6.9618,
      "step": 416
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000828,
      "loss": 6.9311,
      "step": 417
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00083,
      "loss": 6.855,
      "step": 418
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000832,
      "loss": 6.8993,
      "step": 419
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000834,
      "loss": 7.1197,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0008359999999999999,
      "loss": 7.0555,
      "step": 421
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000838,
      "loss": 7.0712,
      "step": 422
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00084,
      "loss": 7.0318,
      "step": 423
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000842,
      "loss": 7.1324,
      "step": 424
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000844,
      "loss": 6.9384,
      "step": 425
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000846,
      "loss": 7.0145,
      "step": 426
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000848,
      "loss": 6.9932,
      "step": 427
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00085,
      "loss": 6.8553,
      "step": 428
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000852,
      "loss": 6.8817,
      "step": 429
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000854,
      "loss": 6.9164,
      "step": 430
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000856,
      "loss": 6.9114,
      "step": 431
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000858,
      "loss": 7.0238,
      "step": 432
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00086,
      "loss": 6.9004,
      "step": 433
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000862,
      "loss": 6.862,
      "step": 434
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000864,
      "loss": 7.0077,
      "step": 435
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000866,
      "loss": 6.8605,
      "step": 436
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0008680000000000001,
      "loss": 6.8455,
      "step": 437
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00087,
      "loss": 6.9177,
      "step": 438
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000872,
      "loss": 6.8778,
      "step": 439
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000874,
      "loss": 6.8986,
      "step": 440
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000876,
      "loss": 6.7385,
      "step": 441
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000878,
      "loss": 6.9416,
      "step": 442
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00088,
      "loss": 6.6524,
      "step": 443
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000882,
      "loss": 6.8695,
      "step": 444
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000884,
      "loss": 6.5954,
      "step": 445
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0008860000000000001,
      "loss": 6.4923,
      "step": 446
    },
    {
      "epoch": 1.0,
      "step": 446,
      "total_flos": 0.0,
      "train_loss": 6.968126589941871,
      "train_runtime": 4906.9209,
      "train_samples_per_second": 5.816,
      "train_steps_per_second": 0.091
    }
  ],
  "max_steps": 446,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}