{
  "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": 1.717,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.5844,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.6147,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.6272,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.4652,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.3925,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.2981,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.2549,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.1734,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.0787,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.0597,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.0002,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.9364,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9021,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.9024,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.8829,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.881,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.907,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.908,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.8973,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.927,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.9174,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.85,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.8331,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.8393,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.9184,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8506,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8487,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.8352,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8581,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8843,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.858,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8927,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8385,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8775,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.8506,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.846,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8599,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8277,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8776,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.8536,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8411,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8515,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8253,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.8666,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8353,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.841,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8512,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.8768,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8201,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8264,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8303,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.8334,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8514,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8443,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8866,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.8196,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8133,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8366,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8313,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.8401,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8324,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8395,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8468,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.8332,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8415,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8882,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8104,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.8485,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8475,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.7839,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.841,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8401,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8442,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8336,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8371,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.8391,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8245,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8196,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.7927,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.8374,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8349,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8271,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8134,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.8481,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.8259,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.8447,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.839,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.8413,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8168,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8362,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8595,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8247,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.8122,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8282,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8326,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8086,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8564,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8377,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8456,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.7863,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.8117,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8347,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8155,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.8434,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.835,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8437,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8051,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8197,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.8337,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.8442,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.8277,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.7963,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.7699,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8266,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.7808,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8247,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8174,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8338,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8273,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8258,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.8368,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8133,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8457,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8479,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.8141,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8147,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8125,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8066,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.8781,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.858,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.7778,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.7964,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.836,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8205,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.7889,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8597,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.8203,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8256,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8284,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.8457,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.7978,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.7882,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8211,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8464,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.8007,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8526,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.7931,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.8185,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.802,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8354,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8124,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8436,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.8159,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8255,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.7855,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.802,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8207,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.7981,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.818,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.8684,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.7987,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8009,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.7902,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8244,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.8476,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8506,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8357,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8073,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.8377,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.7911,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8392,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8261,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8175,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.82,
      "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": 0.8176,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8211,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.7787,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8119,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8361,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8496,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8501,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.834,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.8241,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8458,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8439,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.7946,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.8297,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8388,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.842,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8286,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.8126,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8392,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.779,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8178,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.7796,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8119,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.7988,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8195,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.8413,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.849,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8184,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8572,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.8146,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8045,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8128,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.7768,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8289,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8173,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8749,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8143,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.8287,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.804,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8153,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.7883,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8065,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8538,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8239,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8615,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.8097,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8191,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8105,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.8228,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.7983,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8382,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8134,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.8338,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.826,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8145,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8139,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.7867,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8064,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8282,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8448,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8281,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.8608,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8041,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8092,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8166,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.8047,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8236,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.821,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8409,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.8129,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.806,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.7602,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8244,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8279,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8273,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8229,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.816,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.8284,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.7923,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8008,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.825,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.7781,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.7963,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8652,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8112,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.8307,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.7696,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.804,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.7744,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.806,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8223,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8517,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.7775,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.7867,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.7762,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8187,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.814,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8146,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.7844,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8237,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8364,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8035,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.807,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8138,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8015,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.7838,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8062,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.803,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8124,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.8318,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.7836,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8017,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.7574,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.7959,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8077,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.7988,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8183,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.7909,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8241,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.7927,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8215,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.8243,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.7996,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.7886,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8271,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.7985,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.7996,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8274,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8091,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8352,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.8365,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8241,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8125,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.7694,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8051,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.825,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8051,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8149,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.8483,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8013,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.7661,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.7741,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8237,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8298,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8414,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8061,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.8104,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8064,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8202,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.7952,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.7901,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7949,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7887,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8413,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.7949,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8184,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.7874,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8264,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.7812,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8128,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.8061,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.831,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.797,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8133,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8221,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.8287,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.811,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8321,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8095,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8114,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.8042,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8012,
      "step": 350
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 3.9310521413861376e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}