{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990726429675425,
  "eval_steps": 500,
  "global_step": 404,
  "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": 1.8153,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 1.7133,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.7943,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.8679,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.743,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 1.7498,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.7059,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.7679,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.766,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 1.6386,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.6084,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.5079,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.477,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 1.4787,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.4444,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.3219,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.248,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 1.3126,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.3276,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.3058,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.2129,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 1.2437,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.2289,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.1685,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.1254,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.1017,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.1708,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.0979,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.1026,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.0739,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.0892,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.1071,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.0821,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 1.108,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0547,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0601,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0343,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 1.0246,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0322,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0041,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0414,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 1.0022,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.0043,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9882,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.9793,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 1.0137,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9759,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9763,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9655,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.9991,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9387,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9557,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9513,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.9489,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9634,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9624,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 1.0105,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.9438,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.937,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9585,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9539,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.9575,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9435,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9534,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9611,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.9435,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9618,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 1.0131,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9302,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.9669,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9628,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.8996,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9581,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.9558,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9596,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9492,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9586,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.9557,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9386,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9409,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9029,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.9574,
      "step": 82
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9476,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9395,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.933,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.9553,
      "step": 86
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.932,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9627,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9506,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.9503,
      "step": 90
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9244,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.951,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9745,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9378,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.9346,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9411,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9496,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9283,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.9705,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9518,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9559,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9015,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.9204,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9479,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9416,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9589,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.9533,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9576,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9226,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9277,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.9567,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9657,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9377,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.9139,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.8807,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9388,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.8991,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.941,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.9319,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9562,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9324,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9263,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.9562,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9247,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9501,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9559,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.9141,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9235,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9294,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9176,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.9899,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9662,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.8998,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9093,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.9409,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9344,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9116,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9674,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.9362,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9402,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9424,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9564,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.9079,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9046,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9312,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9613,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.9099,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9687,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9067,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.9294,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.909,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9467,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9254,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9626,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.9222,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9263,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.8876,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9114,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.9343,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9109,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9318,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9794,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.9126,
      "step": 163
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9112,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9049,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9324,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.9613,
      "step": 167
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9528,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.951,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9245,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.9451,
      "step": 171
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.8994,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9411,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9403,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.9227,
      "step": 175
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9334,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9537,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9512,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.9203,
      "step": 179
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.936,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.8822,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9182,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.9461,
      "step": 183
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9664,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9652,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9366,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.927,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.9261,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9535,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9551,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.906,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.9333,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9461,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9512,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9355,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.9241,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.9478,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8873,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.9277,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.8928,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9214,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9048,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.926,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.9501,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9589,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9245,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.9592,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.923,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.9065,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.919,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.8851,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.9383,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9097,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9823,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9218,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.9316,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.9206,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.9184,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.8897,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.9107,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9511,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9262,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9688,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.9135,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9303,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9285,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9295,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.9125,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9357,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.921,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.9462,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.941,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9153,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9217,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.8929,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.9096,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.932,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9436,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9287,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.9745,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.9079,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.9196,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.922,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.9179,
      "step": 244
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9296,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9342,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9499,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.9228,
      "step": 248
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9217,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.8609,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9292,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.9324,
      "step": 252
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9311,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9183,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9189,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.9362,
      "step": 256
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.894,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.9114,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.9273,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.8803,
      "step": 260
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9053,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9661,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9161,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.9417,
      "step": 264
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.8808,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.9102,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.881,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.9093,
      "step": 268
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9285,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.9584,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8922,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.8916,
      "step": 272
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.8917,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9304,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9246,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.9176,
      "step": 276
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.8875,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9329,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9441,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9102,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.9089,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9219,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9091,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.8922,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.9165,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9154,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9196,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9407,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.9003,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.9108,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.861,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.8999,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.91,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8946,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.9214,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.8941,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.9277,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9061,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.935,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9307,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.9067,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.8951,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.926,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9005,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.9057,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9317,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9103,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9358,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.9339,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9238,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9142,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.8853,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.9174,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9292,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.917,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9185,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.9527,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.913,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8754,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.8769,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.931,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9378,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.949,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9037,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.9235,
      "step": 325
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9138,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9278,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.9039,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.8871,
      "step": 329
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9032,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9003,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.9533,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.8981,
      "step": 333
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9259,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8932,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.9287,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.8863,
      "step": 337
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.923,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9139,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9233,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.9002,
      "step": 341
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9168,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9216,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9326,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.9196,
      "step": 345
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.935,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9129,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9208,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.9123,
      "step": 349
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.9116,
      "step": 350
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.9085,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.8974,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.909,
      "step": 353
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9199,
      "step": 354
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9275,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9166,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.9616,
      "step": 357
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.9027,
      "step": 358
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.901,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.8895,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.9615,
      "step": 361
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.9083,
      "step": 362
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.8846,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.9059,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.9214,
      "step": 365
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.9095,
      "step": 366
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.9065,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.9303,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.9458,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.9131,
      "step": 370
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.9125,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8816,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.8974,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.9094,
      "step": 374
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.8936,
      "step": 375
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.9047,
      "step": 376
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.9408,
      "step": 377
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.8835,
      "step": 378
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9066,
      "step": 379
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9232,
      "step": 380
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9265,
      "step": 381
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.9261,
      "step": 382
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.9253,
      "step": 383
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.9141,
      "step": 384
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.9123,
      "step": 385
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.9243,
      "step": 386
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8901,
      "step": 387
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8764,
      "step": 388
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.8897,
      "step": 389
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.957,
      "step": 390
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.9092,
      "step": 391
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.9303,
      "step": 392
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.9023,
      "step": 393
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.9249,
      "step": 394
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.8807,
      "step": 395
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.9281,
      "step": 396
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.9171,
      "step": 397
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.9222,
      "step": 398
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.9181,
      "step": 399
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.8884,
      "step": 400
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.9034,
      "step": 401
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.8957,
      "step": 402
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.9266,
      "step": 403
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.9021,
      "step": 404
    },
    {
      "epoch": 1.0,
      "step": 404,
      "total_flos": 4.5406536857338675e+17,
      "train_loss": 0.9692713016330605,
      "train_runtime": 17158.3904,
      "train_samples_per_second": 3.017,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 1,
  "max_steps": 404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4.5406536857338675e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}