{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 337,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 0.0214,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.0638,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.0084,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.0865,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 0.1704,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 0.0269,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 0.0027,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.1024,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.0043,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.1436,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.0381,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.037,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.1025,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.0779,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.0136,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.1107,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.1521,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.0201,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.0142,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.01,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.0255,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.0049,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.0693,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.26,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.0174,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.0269,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.5464,
      "step": 29
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.0194,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.0074,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.2089,
      "step": 32
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.0061,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.0017,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.0207,
      "step": 35
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.3662,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0464,
      "step": 39
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0051,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0008,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0744,
      "step": 42
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.009,
      "step": 43
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.1138,
      "step": 45
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.0016,
      "step": 46
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.0643,
      "step": 47
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.1696,
      "step": 48
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.0726,
      "step": 49
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.0412,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.0008,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 52
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.0573,
      "step": 53
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.0265,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 55
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.0012,
      "step": 56
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.0013,
      "step": 57
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.2062,
      "step": 58
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.1355,
      "step": 59
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.0085,
      "step": 60
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.1681,
      "step": 61
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.0005,
      "step": 63
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.0679,
      "step": 64
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.1091,
      "step": 65
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 66
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.0626,
      "step": 67
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 68
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.0194,
      "step": 69
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 70
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.0515,
      "step": 71
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.002,
      "step": 72
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.0028,
      "step": 73
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.0481,
      "step": 74
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.0742,
      "step": 75
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0296,
      "step": 76
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0548,
      "step": 77
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0066,
      "step": 79
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.0861,
      "step": 80
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.1836,
      "step": 81
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.071,
      "step": 82
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.3071,
      "step": 83
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.0113,
      "step": 84
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.0426,
      "step": 85
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.0034,
      "step": 86
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.1055,
      "step": 87
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.1451,
      "step": 89
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.0219,
      "step": 90
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.0272,
      "step": 91
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.0012,
      "step": 92
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.0122,
      "step": 93
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.1084,
      "step": 95
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.029,
      "step": 96
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 97
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.0582,
      "step": 98
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.0903,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 101
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.0284,
      "step": 102
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 103
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.0204,
      "step": 104
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.0623,
      "step": 105
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.103,
      "step": 106
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.0637,
      "step": 107
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.0026,
      "step": 108
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 109
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.0056,
      "step": 110
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.0022,
      "step": 111
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.0781,
      "step": 112
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0483,
      "step": 113
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0023,
      "step": 114
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 116
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.0061,
      "step": 117
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.0931,
      "step": 118
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 119
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.26,
      "step": 120
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.0312,
      "step": 121
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 122
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.014,
      "step": 123
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.1177,
      "step": 124
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 125
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 126
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.0024,
      "step": 127
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.0107,
      "step": 128
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 129
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 130
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.0986,
      "step": 131
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.0258,
      "step": 132
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 133
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.0722,
      "step": 134
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.0013,
      "step": 135
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.004,
      "step": 136
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 137
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.0009,
      "step": 138
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.0041,
      "step": 139
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.014,
      "step": 140
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.0018,
      "step": 141
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.008,
      "step": 142
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.0126,
      "step": 143
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 144
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.0988,
      "step": 147
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.036,
      "step": 148
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.0506,
      "step": 149
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0327,
      "step": 150
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0302,
      "step": 151
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0035,
      "step": 152
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0363,
      "step": 153
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 154
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 155
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 156
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.001,
      "step": 157
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.0008,
      "step": 159
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.0015,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.0074,
      "step": 161
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.0079,
      "step": 162
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.0184,
      "step": 163
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.0757,
      "step": 164
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.0331,
      "step": 165
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.0016,
      "step": 166
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.0067,
      "step": 167
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.1215,
      "step": 168
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.0454,
      "step": 169
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 170
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.0055,
      "step": 171
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.0212,
      "step": 172
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 173
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.0555,
      "step": 174
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 175
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 177
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.022,
      "step": 178
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.0105,
      "step": 180
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.1473,
      "step": 181
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 182
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.1501,
      "step": 183
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0053,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 185
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0046,
      "step": 186
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0079,
      "step": 187
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 188
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.0115,
      "step": 189
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.0789,
      "step": 190
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.0899,
      "step": 191
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 192
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.0192,
      "step": 193
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.0609,
      "step": 194
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 195
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.013,
      "step": 196
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.1091,
      "step": 197
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 198
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.0686,
      "step": 199
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.0117,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.0357,
      "step": 201
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 202
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.0273,
      "step": 203
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0635,
      "step": 204
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 205
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0447,
      "step": 206
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.0422,
      "step": 209
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.0302,
      "step": 210
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.0032,
      "step": 211
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 212
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 213
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.0339,
      "step": 214
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.0074,
      "step": 215
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.0443,
      "step": 216
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.0769,
      "step": 217
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 218
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0008,
      "step": 219
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0643,
      "step": 221
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 222
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0009,
      "step": 223
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 224
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.1344,
      "step": 225
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.0252,
      "step": 226
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 227
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.0059,
      "step": 228
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 229
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 230
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0069,
      "step": 231
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0046,
      "step": 233
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 234
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.0052,
      "step": 235
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 236
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 237
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 238
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.0021,
      "step": 239
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.1248,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0312,
      "step": 241
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0551,
      "step": 242
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0502,
      "step": 244
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 245
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.0689,
      "step": 246
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.0464,
      "step": 247
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.0093,
      "step": 248
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 249
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.0187,
      "step": 250
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 251
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0009,
      "step": 252
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0559,
      "step": 253
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0118,
      "step": 254
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.1187,
      "step": 255
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.091,
      "step": 256
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.03,
      "step": 257
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 258
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0648,
      "step": 259
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0601,
      "step": 260
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0009,
      "step": 261
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 262
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 263
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 264
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.1255,
      "step": 265
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.0022,
      "step": 266
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 267
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.0656,
      "step": 268
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.0612,
      "step": 269
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.1666,
      "step": 270
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.0109,
      "step": 271
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.0437,
      "step": 272
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.0043,
      "step": 273
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.0067,
      "step": 274
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 275
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 276
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 277
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0576,
      "step": 278
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.0418,
      "step": 279
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.0165,
      "step": 280
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.0055,
      "step": 281
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.002,
      "step": 282
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 283
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.0012,
      "step": 284
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 285
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.0092,
      "step": 286
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.0131,
      "step": 287
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 288
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.0059,
      "step": 289
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.0659,
      "step": 290
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.0037,
      "step": 291
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.0069,
      "step": 292
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 293
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.0194,
      "step": 294
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.0022,
      "step": 295
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 296
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 297
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 298
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.0059,
      "step": 299
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 300
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.0029,
      "step": 301
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.0017,
      "step": 302
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.0065,
      "step": 303
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.0223,
      "step": 304
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.0321,
      "step": 305
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.0265,
      "step": 306
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.0375,
      "step": 307
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.001,
      "step": 308
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.0018,
      "step": 309
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.0174,
      "step": 310
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 311
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 312
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0005,
      "step": 313
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 314
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0234,
      "step": 315
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 316
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.0386,
      "step": 317
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.0663,
      "step": 318
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 319
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.01,
      "step": 320
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.0026,
      "step": 321
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.0037,
      "step": 322
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.0169,
      "step": 323
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.0706,
      "step": 324
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.0202,
      "step": 325
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.0016,
      "step": 326
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.0001,
      "step": 327
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.1026,
      "step": 328
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 329
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.0753,
      "step": 330
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 331
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.0056,
      "step": 332
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 333
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.1039,
      "step": 334
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 335
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.0078,
      "step": 336
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.0373,
      "step": 337
    },
    {
      "epoch": 1.0,
      "step": 337,
      "total_flos": 1942138071859986.0,
      "train_loss": 0.03423183325136451,
      "train_runtime": 739.225,
      "train_samples_per_second": 14.565,
      "train_steps_per_second": 0.456
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 337,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1942138071859986.0,
  "trial_name": null,
  "trial_params": null
}