{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.865533230293663,
  "eval_steps": 500,
  "global_step": 350,
  "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": 1.8146,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.7128,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.7934,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.8663,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.7405,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.7479,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.7056,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.7681,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.767,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.6407,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.6092,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.5077,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.4746,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.4743,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.4388,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.3198,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.2482,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.3124,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.3294,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.3068,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.2152,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.2475,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.2338,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.1761,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.1325,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.109,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.179,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.1049,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.1057,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.0743,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.0916,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.1079,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.0831,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.1066,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0571,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0616,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0372,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0247,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0285,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0031,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0416,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0013,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.0033,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9867,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9778,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.0149,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9756,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9752,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9662,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9988,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9385,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.955,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9509,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9478,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9628,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9629,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.0102,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9445,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.936,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9574,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9524,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9556,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9435,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9527,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9615,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9425,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9624,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.0114,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9294,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9667,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9618,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8984,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9577,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9536,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9596,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9491,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9574,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9554,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9381,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.941,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9034,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9558,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9472,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9395,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9331,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9549,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9331,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9612,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9505,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9498,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9245,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.95,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9742,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9365,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9345,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9397,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9501,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.928,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9696,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9519,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9555,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9016,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9206,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9483,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9389,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9579,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9526,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.958,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9212,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9269,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.956,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9657,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9381,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9142,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.8811,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9375,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8994,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9411,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9318,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.957,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9323,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9252,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9562,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9229,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9489,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9549,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9145,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9232,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9296,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9185,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9892,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9659,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9093,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9408,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9339,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9115,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9675,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9347,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.941,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9431,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.955,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9084,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9034,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9311,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9614,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9109,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9683,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9062,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9292,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9106,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9469,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9259,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9642,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9216,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.927,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8858,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9123,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.934,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9101,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9306,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9782,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9135,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9105,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9044,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9323,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9618,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9525,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9502,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9243,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9448,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8992,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9416,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9387,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9226,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9329,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9547,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9515,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.92,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9357,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.882,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9177,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9455,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9667,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9641,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9359,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9264,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9267,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9517,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9543,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9059,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9318,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.946,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.951,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9352,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9236,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.948,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8868,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.9284,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8917,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9202,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9048,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9258,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.95,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9596,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9235,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9581,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9215,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.905,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.9181,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8831,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.937,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9103,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9816,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9215,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9307,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.9206,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.918,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8884,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.9095,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9505,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9259,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9678,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9132,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9296,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9275,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9286,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9103,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.936,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9214,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.945,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9413,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9145,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9211,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8922,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9088,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9422,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9271,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.975,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.907,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.9195,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.923,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.9165,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9297,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9331,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9491,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9215,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9221,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8605,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.928,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9319,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9185,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9187,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9353,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8942,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.911,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.9271,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8801,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9044,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9646,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9156,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9405,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8802,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.9094,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8809,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.9083,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9282,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9579,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8929,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8925,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8898,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9295,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9242,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9169,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8876,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9315,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9429,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9089,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9069,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.92,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9081,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8913,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9158,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9156,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9192,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9404,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8985,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.91,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8605,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8989,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.9105,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8932,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.9199,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8941,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.9279,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9053,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9343,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9311,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9065,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8938,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9244,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9004,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9063,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9314,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9092,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9339,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9335,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9244,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9138,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8845,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9171,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9293,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9165,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9179,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9524,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.9123,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8732,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8759,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.9305,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.936,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9481,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9024,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9224,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.913,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9267,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9028,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8864,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9018,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8984,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9518,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8977,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9246,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8929,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9282,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8864,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9223,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9125,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9234,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8995,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9163,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9209,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9181,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9337,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9108,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9207,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9107,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.9108,
      "step": 350
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 3.932299450220544e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}