{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9273570324574961,
  "eval_steps": 500,
  "global_step": 375,
  "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": 1.7194,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.5944,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.6244,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.6388,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.4784,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.4072,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.3096,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.266,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.1784,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0751,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.0596,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.004,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.9479,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.9473,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9147,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9056,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.8843,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.8848,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.9098,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.911,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.8982,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.9278,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.9191,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.8514,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.8358,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.8404,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9196,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8522,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8501,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8363,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8594,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8857,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8596,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8931,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8385,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8781,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8512,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.846,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8606,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8274,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8779,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8537,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8417,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8517,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8258,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8664,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8347,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8417,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8508,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8779,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8202,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8262,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8302,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8339,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8518,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8445,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.887,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8198,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8141,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8372,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8319,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8405,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8324,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8396,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8472,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8338,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8421,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8881,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8112,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8495,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8486,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.7843,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.841,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8398,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8436,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.834,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8375,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8396,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8245,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.82,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.7925,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8371,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8348,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8274,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8134,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8477,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.826,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.8436,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.84,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.8416,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8166,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8366,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8597,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8247,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8125,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8287,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.832,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8082,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8562,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.837,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8457,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.7864,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8111,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8356,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8156,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.843,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8349,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8443,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8051,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8192,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8336,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.845,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.827,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.7963,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.7696,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8263,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.7804,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8246,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8163,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8346,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.828,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8252,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8365,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8129,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8458,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8475,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8142,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8152,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8122,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8071,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.878,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.8578,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.7773,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.7965,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.8366,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8205,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.7888,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8595,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.821,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8261,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8285,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8449,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.7975,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.7891,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8208,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8465,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8015,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8525,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.7932,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8023,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8352,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8121,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8434,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8156,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8254,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.7854,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.802,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8204,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.7987,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.8176,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.8679,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.799,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8012,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.7898,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.824,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8477,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8505,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8363,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8065,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.838,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.7906,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8393,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8262,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8175,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.8206,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.8448,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.8449,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.8175,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.822,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.7787,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.812,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8371,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8494,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8505,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8343,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8238,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8454,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8437,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.7944,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.83,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8394,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8426,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8295,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8121,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8391,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.7788,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8173,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.7804,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.812,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.7989,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8408,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8496,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8191,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8571,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.815,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8047,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8127,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.7772,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.829,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8182,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8745,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8145,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8294,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8044,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.816,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.788,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8063,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8532,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8241,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.861,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8099,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8192,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8102,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8231,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.7988,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.838,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8132,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8339,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8266,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8144,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8139,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.7863,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8063,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8283,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8453,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8282,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8608,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8043,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8095,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8169,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8049,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8243,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8215,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8411,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8136,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.807,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.7606,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8247,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8286,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8277,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8224,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8157,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8284,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.7926,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8017,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8248,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.7779,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.7972,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8653,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8111,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.831,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.77,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8038,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.7753,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8059,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8224,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8524,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.7774,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.7878,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.7764,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8188,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8137,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.815,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.7844,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8242,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8371,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8046,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8069,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8134,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8016,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.7842,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8066,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8028,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8118,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8321,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.7843,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8025,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.7579,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.7955,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8085,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.7992,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.818,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.7916,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8237,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.793,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8212,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8246,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.7994,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.789,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8274,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.7982,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.7997,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8273,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8089,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8359,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8362,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8242,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8131,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.7697,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8059,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8258,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8057,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8145,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8476,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8004,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.7657,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.7745,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8246,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8294,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8412,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8061,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8107,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8066,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8207,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.7957,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.7907,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7953,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7889,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8413,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7957,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8182,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.7869,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8262,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.7813,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8131,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8071,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8316,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.7976,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8128,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8219,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8285,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8109,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8323,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8103,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8112,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8043,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8018,
      "step": 350
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8015,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.7845,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8079,
      "step": 353
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.8144,
      "step": 354
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.8235,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.8158,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.8549,
      "step": 357
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.7984,
      "step": 358
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.789,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.7867,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.8552,
      "step": 361
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.801,
      "step": 362
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.7742,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.7987,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 365
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.808,
      "step": 366
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8054,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8257,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8442,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.8152,
      "step": 370
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.81,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.7818,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.796,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8045,
      "step": 374
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.7957,
      "step": 375
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4.214459938342994e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}