{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9987389659520807,
  "global_step": 594,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 4.8182,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-07,
      "loss": 5.0028,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-06,
      "loss": 4.8689,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-06,
      "loss": 4.8344,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-06,
      "loss": 4.7712,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 4.7584,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.6e-06,
      "loss": 4.8249,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-06,
      "loss": 4.6967,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-06,
      "loss": 4.7905,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.399999999999999e-06,
      "loss": 4.6558,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999999999999999e-06,
      "loss": 4.6367,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.599999999999999e-06,
      "loss": 4.646,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.2e-06,
      "loss": 4.543,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.799999999999998e-06,
      "loss": 4.4923,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.4e-06,
      "loss": 4.3786,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.999999999999999e-06,
      "loss": 4.5164,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.6e-06,
      "loss": 4.5063,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.02e-05,
      "loss": 4.5819,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.0799999999999998e-05,
      "loss": 4.3233,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.14e-05,
      "loss": 4.5417,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 4.4638,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.26e-05,
      "loss": 4.4333,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.3199999999999997e-05,
      "loss": 4.4354,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.3799999999999998e-05,
      "loss": 4.4696,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.44e-05,
      "loss": 4.2463,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 4.6625,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.5599999999999996e-05,
      "loss": 4.3226,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.6199999999999997e-05,
      "loss": 4.2108,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.68e-05,
      "loss": 4.2346,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.74e-05,
      "loss": 4.3936,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 4.4266,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.8599999999999998e-05,
      "loss": 4.2831,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.92e-05,
      "loss": 4.2859,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.98e-05,
      "loss": 4.2428,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.04e-05,
      "loss": 4.295,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1e-05,
      "loss": 4.452,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1599999999999996e-05,
      "loss": 4.2423,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.2199999999999998e-05,
      "loss": 4.4074,
      "step": 38
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.28e-05,
      "loss": 4.556,
      "step": 39
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.34e-05,
      "loss": 4.2127,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 4.2372,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.4599999999999998e-05,
      "loss": 4.4704,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.52e-05,
      "loss": 4.1838,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.5799999999999997e-05,
      "loss": 4.3398,
      "step": 44
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.6399999999999995e-05,
      "loss": 4.4231,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 4.4815,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.7599999999999997e-05,
      "loss": 4.3865,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 4.7313,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 4.7684,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.88e-05,
      "loss": 4.4833,
      "step": 50
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.94e-05,
      "loss": 4.193,
      "step": 51
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 4.2105,
      "step": 52
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.06e-05,
      "loss": 4.2301,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.119999999999999e-05,
      "loss": 4.3011,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.1799999999999994e-05,
      "loss": 4.1692,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.2399999999999995e-05,
      "loss": 4.3675,
      "step": 56
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 4.1814,
      "step": 57
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.36e-05,
      "loss": 4.4746,
      "step": 58
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.42e-05,
      "loss": 4.2425,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.48e-05,
      "loss": 4.0318,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.539999999999999e-05,
      "loss": 4.2939,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 4.3447,
      "step": 62
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.6599999999999995e-05,
      "loss": 4.2286,
      "step": 63
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.7199999999999996e-05,
      "loss": 4.2042,
      "step": 64
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.78e-05,
      "loss": 4.236,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.84e-05,
      "loss": 4.1772,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.9e-05,
      "loss": 4.142,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.96e-05,
      "loss": 4.1345,
      "step": 68
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.02e-05,
      "loss": 4.2305,
      "step": 69
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.08e-05,
      "loss": 4.2083,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.14e-05,
      "loss": 4.3085,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.2e-05,
      "loss": 4.2821,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.259999999999999e-05,
      "loss": 4.0847,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.319999999999999e-05,
      "loss": 4.2869,
      "step": 74
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.3799999999999994e-05,
      "loss": 4.2665,
      "step": 75
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.4399999999999995e-05,
      "loss": 4.24,
      "step": 76
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 4.219,
      "step": 77
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.56e-05,
      "loss": 4.1975,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.62e-05,
      "loss": 4.1354,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.68e-05,
      "loss": 4.3206,
      "step": 80
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7399999999999993e-05,
      "loss": 4.2772,
      "step": 81
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 4.2269,
      "step": 82
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.8599999999999995e-05,
      "loss": 4.3281,
      "step": 83
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9199999999999997e-05,
      "loss": 4.291,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.98e-05,
      "loss": 4.2093,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.04e-05,
      "loss": 4.1592,
      "step": 86
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.1e-05,
      "loss": 4.4026,
      "step": 87
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.1599999999999994e-05,
      "loss": 4.2414,
      "step": 88
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.2199999999999995e-05,
      "loss": 4.245,
      "step": 89
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.279999999999999e-05,
      "loss": 4.2845,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.339999999999999e-05,
      "loss": 4.247,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.399999999999999e-05,
      "loss": 4.3707,
      "step": 92
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.459999999999999e-05,
      "loss": 4.2318,
      "step": 93
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.519999999999999e-05,
      "loss": 4.4576,
      "step": 94
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.5799999999999994e-05,
      "loss": 4.3531,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.6399999999999995e-05,
      "loss": 4.409,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 4.3879,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.76e-05,
      "loss": 4.309,
      "step": 98
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.82e-05,
      "loss": 4.5432,
      "step": 99
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.88e-05,
      "loss": 4.205,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.94e-05,
      "loss": 4.3588,
      "step": 101
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.1904,
      "step": 102
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 4.2077,
      "step": 103
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.12e-05,
      "loss": 4.13,
      "step": 104
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.18e-05,
      "loss": 4.1796,
      "step": 105
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.239999999999999e-05,
      "loss": 4.1452,
      "step": 106
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.299999999999999e-05,
      "loss": 4.2699,
      "step": 107
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.359999999999999e-05,
      "loss": 4.3016,
      "step": 108
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.419999999999999e-05,
      "loss": 4.4238,
      "step": 109
    },
    {
      "epoch": 0.18,
      "learning_rate": 6.479999999999999e-05,
      "loss": 4.2019,
      "step": 110
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.539999999999999e-05,
      "loss": 4.2325,
      "step": 111
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.599999999999999e-05,
      "loss": 4.2623,
      "step": 112
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.659999999999999e-05,
      "loss": 4.2221,
      "step": 113
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.72e-05,
      "loss": 4.2787,
      "step": 114
    },
    {
      "epoch": 0.19,
      "learning_rate": 6.78e-05,
      "loss": 4.2717,
      "step": 115
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.84e-05,
      "loss": 4.2513,
      "step": 116
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.9e-05,
      "loss": 4.3379,
      "step": 117
    },
    {
      "epoch": 0.2,
      "learning_rate": 6.96e-05,
      "loss": 4.1303,
      "step": 118
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.02e-05,
      "loss": 4.1263,
      "step": 119
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.079999999999999e-05,
      "loss": 4.1342,
      "step": 120
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.139999999999999e-05,
      "loss": 4.3001,
      "step": 121
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.199999999999999e-05,
      "loss": 4.4657,
      "step": 122
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.259999999999999e-05,
      "loss": 4.194,
      "step": 123
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.319999999999999e-05,
      "loss": 4.2687,
      "step": 124
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.379999999999999e-05,
      "loss": 4.2877,
      "step": 125
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.439999999999999e-05,
      "loss": 4.1317,
      "step": 126
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.5e-05,
      "loss": 4.145,
      "step": 127
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.56e-05,
      "loss": 4.1317,
      "step": 128
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.62e-05,
      "loss": 4.2327,
      "step": 129
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.68e-05,
      "loss": 4.2944,
      "step": 130
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.74e-05,
      "loss": 4.254,
      "step": 131
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.8e-05,
      "loss": 4.2138,
      "step": 132
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.86e-05,
      "loss": 4.2627,
      "step": 133
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.92e-05,
      "loss": 4.3398,
      "step": 134
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.98e-05,
      "loss": 4.3485,
      "step": 135
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.04e-05,
      "loss": 4.2115,
      "step": 136
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.1e-05,
      "loss": 4.1802,
      "step": 137
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.16e-05,
      "loss": 4.24,
      "step": 138
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.22e-05,
      "loss": 4.2233,
      "step": 139
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.28e-05,
      "loss": 4.3909,
      "step": 140
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.34e-05,
      "loss": 4.2786,
      "step": 141
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.4e-05,
      "loss": 4.3874,
      "step": 142
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.459999999999998e-05,
      "loss": 4.4902,
      "step": 143
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.519999999999998e-05,
      "loss": 4.3232,
      "step": 144
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.579999999999998e-05,
      "loss": 4.3679,
      "step": 145
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.639999999999999e-05,
      "loss": 4.6866,
      "step": 146
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.699999999999999e-05,
      "loss": 4.6394,
      "step": 147
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.759999999999999e-05,
      "loss": 4.5798,
      "step": 148
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.819999999999999e-05,
      "loss": 4.6793,
      "step": 149
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.879999999999999e-05,
      "loss": 4.5903,
      "step": 150
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.939999999999999e-05,
      "loss": 4.2962,
      "step": 151
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.2278,
      "step": 152
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.059999999999999e-05,
      "loss": 4.2305,
      "step": 153
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.12e-05,
      "loss": 4.145,
      "step": 154
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.18e-05,
      "loss": 4.1925,
      "step": 155
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.24e-05,
      "loss": 4.1712,
      "step": 156
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.3e-05,
      "loss": 4.301,
      "step": 157
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.36e-05,
      "loss": 4.1469,
      "step": 158
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.419999999999999e-05,
      "loss": 4.0775,
      "step": 159
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.479999999999999e-05,
      "loss": 4.2078,
      "step": 160
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.539999999999999e-05,
      "loss": 4.2729,
      "step": 161
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.599999999999999e-05,
      "loss": 4.1514,
      "step": 162
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.659999999999999e-05,
      "loss": 4.1282,
      "step": 163
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.719999999999999e-05,
      "loss": 4.1626,
      "step": 164
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.779999999999999e-05,
      "loss": 4.3451,
      "step": 165
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.839999999999999e-05,
      "loss": 4.3345,
      "step": 166
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.9e-05,
      "loss": 4.1537,
      "step": 167
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.96e-05,
      "loss": 4.3872,
      "step": 168
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001002,
      "loss": 4.2078,
      "step": 169
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001008,
      "loss": 4.2435,
      "step": 170
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001014,
      "loss": 4.1005,
      "step": 171
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000102,
      "loss": 4.1444,
      "step": 172
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001026,
      "loss": 4.1539,
      "step": 173
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00010319999999999999,
      "loss": 4.2127,
      "step": 174
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00010379999999999999,
      "loss": 4.3975,
      "step": 175
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010439999999999999,
      "loss": 4.3712,
      "step": 176
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010499999999999999,
      "loss": 4.3348,
      "step": 177
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010559999999999998,
      "loss": 4.1479,
      "step": 178
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010619999999999998,
      "loss": 4.2947,
      "step": 179
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010679999999999998,
      "loss": 4.1779,
      "step": 180
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010739999999999998,
      "loss": 4.3328,
      "step": 181
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010799999999999998,
      "loss": 4.2,
      "step": 182
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010859999999999998,
      "loss": 4.2252,
      "step": 183
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010919999999999998,
      "loss": 4.1258,
      "step": 184
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00010979999999999999,
      "loss": 4.4858,
      "step": 185
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00011039999999999999,
      "loss": 4.2418,
      "step": 186
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00011099999999999999,
      "loss": 4.2566,
      "step": 187
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00011159999999999999,
      "loss": 4.3974,
      "step": 188
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00011219999999999999,
      "loss": 4.4813,
      "step": 189
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00011279999999999999,
      "loss": 4.1671,
      "step": 190
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00011339999999999999,
      "loss": 4.4851,
      "step": 191
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00011399999999999999,
      "loss": 4.3957,
      "step": 192
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001146,
      "loss": 4.6878,
      "step": 193
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001152,
      "loss": 4.3941,
      "step": 194
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001158,
      "loss": 4.3453,
      "step": 195
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001164,
      "loss": 4.4555,
      "step": 196
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000117,
      "loss": 4.7167,
      "step": 197
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001176,
      "loss": 4.538,
      "step": 198
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001182,
      "loss": 4.5329,
      "step": 199
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001188,
      "loss": 4.5335,
      "step": 200
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001194,
      "loss": 4.1187,
      "step": 201
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00011999999999999999,
      "loss": 4.2866,
      "step": 202
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00012059999999999999,
      "loss": 4.3993,
      "step": 203
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00012119999999999999,
      "loss": 4.1615,
      "step": 204
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00012179999999999999,
      "loss": 4.226,
      "step": 205
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001224,
      "loss": 4.1952,
      "step": 206
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012299999999999998,
      "loss": 4.2312,
      "step": 207
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001236,
      "loss": 4.3538,
      "step": 208
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012419999999999998,
      "loss": 4.265,
      "step": 209
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012479999999999997,
      "loss": 4.3468,
      "step": 210
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00012539999999999999,
      "loss": 4.3613,
      "step": 211
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012599999999999997,
      "loss": 4.2659,
      "step": 212
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001266,
      "loss": 4.2808,
      "step": 213
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012719999999999997,
      "loss": 4.3405,
      "step": 214
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001278,
      "loss": 4.2305,
      "step": 215
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00012839999999999998,
      "loss": 4.277,
      "step": 216
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000129,
      "loss": 4.1606,
      "step": 217
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012959999999999998,
      "loss": 4.3264,
      "step": 218
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001302,
      "loss": 4.4251,
      "step": 219
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00013079999999999998,
      "loss": 4.4401,
      "step": 220
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001314,
      "loss": 4.2936,
      "step": 221
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00013199999999999998,
      "loss": 4.3649,
      "step": 222
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001326,
      "loss": 4.3694,
      "step": 223
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00013319999999999999,
      "loss": 4.3328,
      "step": 224
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001338,
      "loss": 4.5794,
      "step": 225
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001344,
      "loss": 4.2256,
      "step": 226
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000135,
      "loss": 4.1422,
      "step": 227
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001356,
      "loss": 4.2117,
      "step": 228
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001362,
      "loss": 4.4223,
      "step": 229
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001368,
      "loss": 4.384,
      "step": 230
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001374,
      "loss": 4.1981,
      "step": 231
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000138,
      "loss": 4.2797,
      "step": 232
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001386,
      "loss": 4.5837,
      "step": 233
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001392,
      "loss": 4.2845,
      "step": 234
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013979999999999998,
      "loss": 4.4128,
      "step": 235
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001404,
      "loss": 4.1982,
      "step": 236
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014099999999999998,
      "loss": 4.158,
      "step": 237
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014159999999999997,
      "loss": 4.2719,
      "step": 238
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001422,
      "loss": 4.3127,
      "step": 239
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014279999999999997,
      "loss": 4.3545,
      "step": 240
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001434,
      "loss": 4.5494,
      "step": 241
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014399999999999998,
      "loss": 4.4465,
      "step": 242
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001446,
      "loss": 4.2999,
      "step": 243
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014519999999999998,
      "loss": 4.4911,
      "step": 244
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001458,
      "loss": 4.7491,
      "step": 245
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014639999999999998,
      "loss": 4.5465,
      "step": 246
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000147,
      "loss": 4.9226,
      "step": 247
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014759999999999998,
      "loss": 4.895,
      "step": 248
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001482,
      "loss": 4.4854,
      "step": 249
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014879999999999998,
      "loss": 4.6152,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001494,
      "loss": 4.4272,
      "step": 251
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00015,
      "loss": 4.582,
      "step": 252
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015059999999999997,
      "loss": 4.7457,
      "step": 253
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001512,
      "loss": 4.4816,
      "step": 254
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015179999999999998,
      "loss": 4.8845,
      "step": 255
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001524,
      "loss": 4.8351,
      "step": 256
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015299999999999998,
      "loss": 4.5857,
      "step": 257
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001536,
      "loss": 4.389,
      "step": 258
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015419999999999998,
      "loss": 4.4282,
      "step": 259
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001548,
      "loss": 4.647,
      "step": 260
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015539999999999998,
      "loss": 4.6697,
      "step": 261
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000156,
      "loss": 4.5029,
      "step": 262
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00015659999999999998,
      "loss": 4.8514,
      "step": 263
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001572,
      "loss": 4.1349,
      "step": 264
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001578,
      "loss": 4.3635,
      "step": 265
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001584,
      "loss": 4.5442,
      "step": 266
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000159,
      "loss": 5.1162,
      "step": 267
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001596,
      "loss": 4.4451,
      "step": 268
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001602,
      "loss": 4.5503,
      "step": 269
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001608,
      "loss": 4.4475,
      "step": 270
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001614,
      "loss": 4.3478,
      "step": 271
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000162,
      "loss": 4.6113,
      "step": 272
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001626,
      "loss": 4.7242,
      "step": 273
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001632,
      "loss": 4.6371,
      "step": 274
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001638,
      "loss": 4.4794,
      "step": 275
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001644,
      "loss": 4.3902,
      "step": 276
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000165,
      "loss": 4.5252,
      "step": 277
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001656,
      "loss": 4.5436,
      "step": 278
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001662,
      "loss": 4.4553,
      "step": 279
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001668,
      "loss": 4.5571,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001674,
      "loss": 4.5108,
      "step": 281
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000168,
      "loss": 4.5576,
      "step": 282
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001686,
      "loss": 4.4762,
      "step": 283
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016919999999999997,
      "loss": 4.2964,
      "step": 284
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016979999999999998,
      "loss": 4.5742,
      "step": 285
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017039999999999997,
      "loss": 4.2314,
      "step": 286
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017099999999999998,
      "loss": 4.7449,
      "step": 287
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017159999999999997,
      "loss": 4.3179,
      "step": 288
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017219999999999998,
      "loss": 4.3885,
      "step": 289
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017279999999999997,
      "loss": 4.6569,
      "step": 290
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017339999999999996,
      "loss": 4.5262,
      "step": 291
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017399999999999997,
      "loss": 4.3064,
      "step": 292
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017459999999999996,
      "loss": 4.6379,
      "step": 293
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00017519999999999998,
      "loss": 4.6143,
      "step": 294
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017579999999999996,
      "loss": 4.4993,
      "step": 295
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017639999999999998,
      "loss": 4.348,
      "step": 296
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017699999999999997,
      "loss": 5.2729,
      "step": 297
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017759999999999998,
      "loss": 5.2359,
      "step": 298
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017819999999999997,
      "loss": 4.8578,
      "step": 299
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017879999999999998,
      "loss": 5.5686,
      "step": 300
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017939999999999997,
      "loss": 4.6844,
      "step": 301
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.5929,
      "step": 302
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018059999999999997,
      "loss": 4.7074,
      "step": 303
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018119999999999999,
      "loss": 4.4101,
      "step": 304
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018179999999999997,
      "loss": 4.5093,
      "step": 305
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001824,
      "loss": 4.725,
      "step": 306
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018299999999999998,
      "loss": 4.6516,
      "step": 307
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001836,
      "loss": 4.7071,
      "step": 308
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018419999999999998,
      "loss": 4.4795,
      "step": 309
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001848,
      "loss": 4.4157,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018539999999999998,
      "loss": 4.2875,
      "step": 311
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000186,
      "loss": 4.5176,
      "step": 312
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018659999999999998,
      "loss": 4.4679,
      "step": 313
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001872,
      "loss": 4.6015,
      "step": 314
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018779999999999998,
      "loss": 4.338,
      "step": 315
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018839999999999997,
      "loss": 4.6336,
      "step": 316
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018899999999999999,
      "loss": 4.4357,
      "step": 317
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018959999999999997,
      "loss": 4.8962,
      "step": 318
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001902,
      "loss": 4.5626,
      "step": 319
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019079999999999998,
      "loss": 4.5467,
      "step": 320
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001914,
      "loss": 4.2766,
      "step": 321
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019199999999999998,
      "loss": 4.3254,
      "step": 322
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001926,
      "loss": 4.8041,
      "step": 323
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019319999999999998,
      "loss": 4.3947,
      "step": 324
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001938,
      "loss": 4.7643,
      "step": 325
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019439999999999998,
      "loss": 4.4117,
      "step": 326
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000195,
      "loss": 4.7301,
      "step": 327
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019559999999999998,
      "loss": 4.4717,
      "step": 328
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001962,
      "loss": 4.4449,
      "step": 329
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019679999999999999,
      "loss": 4.4055,
      "step": 330
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001974,
      "loss": 4.5839,
      "step": 331
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000198,
      "loss": 4.2595,
      "step": 332
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001986,
      "loss": 4.4989,
      "step": 333
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001992,
      "loss": 4.5707,
      "step": 334
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001998,
      "loss": 4.4243,
      "step": 335
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002004,
      "loss": 4.4127,
      "step": 336
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000201,
      "loss": 4.4754,
      "step": 337
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002016,
      "loss": 4.3751,
      "step": 338
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002022,
      "loss": 4.4543,
      "step": 339
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002028,
      "loss": 4.6159,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00020339999999999998,
      "loss": 4.4517,
      "step": 341
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000204,
      "loss": 4.7063,
      "step": 342
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00020459999999999999,
      "loss": 4.7711,
      "step": 343
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002052,
      "loss": 4.6853,
      "step": 344
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002058,
      "loss": 4.8209,
      "step": 345
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00020639999999999998,
      "loss": 4.3988,
      "step": 346
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00020699999999999996,
      "loss": 4.5112,
      "step": 347
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00020759999999999998,
      "loss": 4.6472,
      "step": 348
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00020819999999999996,
      "loss": 4.4794,
      "step": 349
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00020879999999999998,
      "loss": 5.2373,
      "step": 350
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00020939999999999997,
      "loss": 4.5732,
      "step": 351
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00020999999999999998,
      "loss": 4.5354,
      "step": 352
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00021059999999999997,
      "loss": 4.5812,
      "step": 353
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021119999999999996,
      "loss": 4.4975,
      "step": 354
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021179999999999997,
      "loss": 4.4032,
      "step": 355
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021239999999999996,
      "loss": 4.3613,
      "step": 356
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021299999999999997,
      "loss": 4.3984,
      "step": 357
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021359999999999996,
      "loss": 4.7058,
      "step": 358
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00021419999999999998,
      "loss": 4.3473,
      "step": 359
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021479999999999996,
      "loss": 4.6245,
      "step": 360
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021539999999999998,
      "loss": 4.6861,
      "step": 361
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021599999999999996,
      "loss": 4.4029,
      "step": 362
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021659999999999998,
      "loss": 4.7367,
      "step": 363
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021719999999999997,
      "loss": 4.4922,
      "step": 364
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00021779999999999998,
      "loss": 4.7612,
      "step": 365
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00021839999999999997,
      "loss": 4.447,
      "step": 366
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00021899999999999998,
      "loss": 4.5431,
      "step": 367
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00021959999999999997,
      "loss": 4.3665,
      "step": 368
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00022019999999999999,
      "loss": 4.4973,
      "step": 369
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00022079999999999997,
      "loss": 4.8256,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002214,
      "loss": 4.2738,
      "step": 371
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00022199999999999998,
      "loss": 4.4241,
      "step": 372
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002226,
      "loss": 4.3496,
      "step": 373
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00022319999999999998,
      "loss": 4.6338,
      "step": 374
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002238,
      "loss": 4.5995,
      "step": 375
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00022439999999999998,
      "loss": 4.5976,
      "step": 376
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000225,
      "loss": 4.572,
      "step": 377
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022559999999999998,
      "loss": 4.6357,
      "step": 378
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022619999999999997,
      "loss": 4.5382,
      "step": 379
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022679999999999998,
      "loss": 4.5339,
      "step": 380
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022739999999999997,
      "loss": 4.6268,
      "step": 381
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022799999999999999,
      "loss": 4.7323,
      "step": 382
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00022859999999999997,
      "loss": 4.7925,
      "step": 383
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002292,
      "loss": 4.5124,
      "step": 384
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00022979999999999997,
      "loss": 4.706,
      "step": 385
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002304,
      "loss": 4.8178,
      "step": 386
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00023099999999999998,
      "loss": 4.981,
      "step": 387
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002316,
      "loss": 4.4796,
      "step": 388
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00023219999999999998,
      "loss": 4.4747,
      "step": 389
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002328,
      "loss": 4.5041,
      "step": 390
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00023339999999999998,
      "loss": 4.5166,
      "step": 391
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000234,
      "loss": 4.7084,
      "step": 392
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00023459999999999998,
      "loss": 4.9243,
      "step": 393
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002352,
      "loss": 4.4673,
      "step": 394
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00023579999999999999,
      "loss": 4.9729,
      "step": 395
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002364,
      "loss": 4.6977,
      "step": 396
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000237,
      "loss": 4.9387,
      "step": 397
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002376,
      "loss": 5.7888,
      "step": 398
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002382,
      "loss": 4.9183,
      "step": 399
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002388,
      "loss": 5.0151,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002394,
      "loss": 4.7088,
      "step": 401
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00023999999999999998,
      "loss": 4.644,
      "step": 402
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002406,
      "loss": 4.5208,
      "step": 403
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00024119999999999998,
      "loss": 4.4707,
      "step": 404
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002418,
      "loss": 4.4193,
      "step": 405
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00024239999999999998,
      "loss": 4.3914,
      "step": 406
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000243,
      "loss": 4.6832,
      "step": 407
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00024359999999999999,
      "loss": 4.3622,
      "step": 408
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00024419999999999997,
      "loss": 4.5366,
      "step": 409
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002448,
      "loss": 4.4287,
      "step": 410
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00024539999999999995,
      "loss": 4.3764,
      "step": 411
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00024599999999999996,
      "loss": 4.6033,
      "step": 412
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002466,
      "loss": 4.4157,
      "step": 413
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002472,
      "loss": 4.5498,
      "step": 414
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00024779999999999995,
      "loss": 4.4146,
      "step": 415
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00024839999999999997,
      "loss": 4.4638,
      "step": 416
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000249,
      "loss": 4.4486,
      "step": 417
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00024959999999999994,
      "loss": 4.1511,
      "step": 418
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00025019999999999996,
      "loss": 4.6831,
      "step": 419
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00025079999999999997,
      "loss": 4.502,
      "step": 420
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002514,
      "loss": 4.196,
      "step": 421
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00025199999999999995,
      "loss": 4.4275,
      "step": 422
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00025259999999999996,
      "loss": 4.5887,
      "step": 423
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002532,
      "loss": 4.4421,
      "step": 424
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002538,
      "loss": 4.4905,
      "step": 425
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025439999999999995,
      "loss": 4.4904,
      "step": 426
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025499999999999996,
      "loss": 4.2661,
      "step": 427
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002556,
      "loss": 4.2795,
      "step": 428
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002562,
      "loss": 4.8814,
      "step": 429
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025679999999999995,
      "loss": 4.5092,
      "step": 430
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00025739999999999997,
      "loss": 4.7066,
      "step": 431
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000258,
      "loss": 4.22,
      "step": 432
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002586,
      "loss": 4.4888,
      "step": 433
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00025919999999999996,
      "loss": 4.5165,
      "step": 434
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00025979999999999997,
      "loss": 4.6135,
      "step": 435
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002604,
      "loss": 4.4378,
      "step": 436
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000261,
      "loss": 4.6876,
      "step": 437
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00026159999999999996,
      "loss": 4.5232,
      "step": 438
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002622,
      "loss": 4.6054,
      "step": 439
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002628,
      "loss": 4.6991,
      "step": 440
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00026339999999999995,
      "loss": 4.7554,
      "step": 441
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00026399999999999997,
      "loss": 4.8751,
      "step": 442
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002646,
      "loss": 4.8587,
      "step": 443
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002652,
      "loss": 4.5289,
      "step": 444
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00026579999999999996,
      "loss": 4.3795,
      "step": 445
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00026639999999999997,
      "loss": 4.7699,
      "step": 446
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000267,
      "loss": 4.5368,
      "step": 447
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002676,
      "loss": 4.6414,
      "step": 448
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00026819999999999996,
      "loss": 5.1838,
      "step": 449
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002688,
      "loss": 4.3724,
      "step": 450
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002694,
      "loss": 4.4935,
      "step": 451
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00027,
      "loss": 4.6275,
      "step": 452
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00027059999999999996,
      "loss": 4.4756,
      "step": 453
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002712,
      "loss": 4.7369,
      "step": 454
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002718,
      "loss": 4.6098,
      "step": 455
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002724,
      "loss": 4.6067,
      "step": 456
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00027299999999999997,
      "loss": 4.8474,
      "step": 457
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002736,
      "loss": 4.6679,
      "step": 458
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002742,
      "loss": 4.7952,
      "step": 459
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002748,
      "loss": 4.5183,
      "step": 460
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00027539999999999997,
      "loss": 4.8535,
      "step": 461
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000276,
      "loss": 4.4351,
      "step": 462
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002766,
      "loss": 4.7839,
      "step": 463
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002772,
      "loss": 4.6477,
      "step": 464
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002778,
      "loss": 4.8635,
      "step": 465
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002784,
      "loss": 4.4758,
      "step": 466
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000279,
      "loss": 4.5836,
      "step": 467
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00027959999999999997,
      "loss": 4.4608,
      "step": 468
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002802,
      "loss": 4.7147,
      "step": 469
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002808,
      "loss": 4.3855,
      "step": 470
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00028139999999999996,
      "loss": 4.5603,
      "step": 471
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00028199999999999997,
      "loss": 4.3725,
      "step": 472
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002826,
      "loss": 4.4598,
      "step": 473
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00028319999999999994,
      "loss": 4.6407,
      "step": 474
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00028379999999999996,
      "loss": 4.4258,
      "step": 475
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002844,
      "loss": 4.6098,
      "step": 476
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000285,
      "loss": 4.5606,
      "step": 477
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00028559999999999995,
      "loss": 4.5687,
      "step": 478
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00028619999999999996,
      "loss": 4.3645,
      "step": 479
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002868,
      "loss": 4.3326,
      "step": 480
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00028739999999999994,
      "loss": 4.9138,
      "step": 481
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00028799999999999995,
      "loss": 4.992,
      "step": 482
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00028859999999999997,
      "loss": 4.7403,
      "step": 483
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002892,
      "loss": 4.7293,
      "step": 484
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00028979999999999994,
      "loss": 4.5899,
      "step": 485
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029039999999999996,
      "loss": 4.4421,
      "step": 486
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029099999999999997,
      "loss": 4.6241,
      "step": 487
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002916,
      "loss": 4.4847,
      "step": 488
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029219999999999995,
      "loss": 4.5834,
      "step": 489
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00029279999999999996,
      "loss": 4.4479,
      "step": 490
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002934,
      "loss": 4.7391,
      "step": 491
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000294,
      "loss": 4.7008,
      "step": 492
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029459999999999995,
      "loss": 4.3374,
      "step": 493
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00029519999999999997,
      "loss": 4.378,
      "step": 494
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002958,
      "loss": 4.636,
      "step": 495
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002964,
      "loss": 4.8833,
      "step": 496
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00029699999999999996,
      "loss": 4.5708,
      "step": 497
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00029759999999999997,
      "loss": 4.6291,
      "step": 498
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002982,
      "loss": 5.1499,
      "step": 499
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002988,
      "loss": 4.7669,
      "step": 500
    },
    {
      "epoch": 0.84,
      "eval_loss": 4.873856067657471,
      "eval_runtime": 784.3492,
      "eval_samples_per_second": 3.368,
      "eval_steps_per_second": 0.282,
      "eval_wer": 1.9278262594208648,
      "step": 500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00029939999999999996,
      "loss": 4.5736,
      "step": 501
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 4.6392,
      "step": 502
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00029680851063829784,
      "loss": 4.7407,
      "step": 503
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002936170212765957,
      "loss": 4.9224,
      "step": 504
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002904255319148936,
      "loss": 4.7926,
      "step": 505
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002872340425531915,
      "loss": 5.0733,
      "step": 506
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00028404255319148934,
      "loss": 4.7467,
      "step": 507
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002808510638297872,
      "loss": 4.7175,
      "step": 508
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00027765957446808506,
      "loss": 4.6484,
      "step": 509
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000274468085106383,
      "loss": 4.7577,
      "step": 510
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00027127659574468084,
      "loss": 4.7992,
      "step": 511
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002680851063829787,
      "loss": 4.5604,
      "step": 512
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00026489361702127656,
      "loss": 4.5546,
      "step": 513
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002617021276595745,
      "loss": 4.9298,
      "step": 514
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002585106382978723,
      "loss": 4.6264,
      "step": 515
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002553191489361702,
      "loss": 4.6125,
      "step": 516
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00025212765957446806,
      "loss": 4.5963,
      "step": 517
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002489361702127659,
      "loss": 4.7157,
      "step": 518
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00024574468085106384,
      "loss": 4.5033,
      "step": 519
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00024255319148936167,
      "loss": 4.5918,
      "step": 520
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023936170212765956,
      "loss": 4.6696,
      "step": 521
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023617021276595742,
      "loss": 4.8345,
      "step": 522
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023297872340425529,
      "loss": 4.3613,
      "step": 523
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00022978723404255317,
      "loss": 4.1583,
      "step": 524
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00022659574468085106,
      "loss": 4.5778,
      "step": 525
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002234042553191489,
      "loss": 4.7744,
      "step": 526
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00022021276595744679,
      "loss": 4.6864,
      "step": 527
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00021702127659574468,
      "loss": 4.4407,
      "step": 528
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00021382978723404254,
      "loss": 4.6176,
      "step": 529
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002106382978723404,
      "loss": 4.3369,
      "step": 530
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002074468085106383,
      "loss": 4.4068,
      "step": 531
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00020425531914893615,
      "loss": 4.7584,
      "step": 532
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00020106382978723404,
      "loss": 4.6745,
      "step": 533
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019787234042553187,
      "loss": 4.4945,
      "step": 534
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019468085106382976,
      "loss": 4.3341,
      "step": 535
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019148936170212765,
      "loss": 4.5124,
      "step": 536
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001882978723404255,
      "loss": 4.5719,
      "step": 537
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001851063829787234,
      "loss": 4.3806,
      "step": 538
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018191489361702126,
      "loss": 4.623,
      "step": 539
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00017872340425531912,
      "loss": 4.5661,
      "step": 540
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000175531914893617,
      "loss": 4.6673,
      "step": 541
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001723404255319149,
      "loss": 4.7293,
      "step": 542
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016914893617021274,
      "loss": 4.4276,
      "step": 543
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016595744680851062,
      "loss": 4.4851,
      "step": 544
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016276595744680849,
      "loss": 4.5706,
      "step": 545
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015957446808510637,
      "loss": 4.7982,
      "step": 546
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015638297872340426,
      "loss": 4.4439,
      "step": 547
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001531914893617021,
      "loss": 5.0839,
      "step": 548
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015,
      "loss": 5.1486,
      "step": 549
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014680851063829785,
      "loss": 4.481,
      "step": 550
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00014361702127659574,
      "loss": 4.5966,
      "step": 551
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001404255319148936,
      "loss": 4.7382,
      "step": 552
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001372340425531915,
      "loss": 4.5965,
      "step": 553
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013404255319148935,
      "loss": 4.3645,
      "step": 554
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013085106382978724,
      "loss": 4.4921,
      "step": 555
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001276595744680851,
      "loss": 4.547,
      "step": 556
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00012446808510638296,
      "loss": 4.6281,
      "step": 557
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00012127659574468084,
      "loss": 4.5267,
      "step": 558
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011808510638297871,
      "loss": 4.3407,
      "step": 559
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011489361702127659,
      "loss": 4.2849,
      "step": 560
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00011170212765957445,
      "loss": 4.7138,
      "step": 561
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010851063829787234,
      "loss": 4.3811,
      "step": 562
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001053191489361702,
      "loss": 4.4681,
      "step": 563
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00010212765957446807,
      "loss": 4.7141,
      "step": 564
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.893617021276594e-05,
      "loss": 4.5566,
      "step": 565
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.574468085106382e-05,
      "loss": 4.5957,
      "step": 566
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.25531914893617e-05,
      "loss": 4.4626,
      "step": 567
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.936170212765956e-05,
      "loss": 4.2414,
      "step": 568
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.617021276595745e-05,
      "loss": 4.3564,
      "step": 569
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.297872340425531e-05,
      "loss": 4.4139,
      "step": 570
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.978723404255319e-05,
      "loss": 4.5387,
      "step": 571
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.659574468085105e-05,
      "loss": 4.4192,
      "step": 572
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.340425531914892e-05,
      "loss": 4.5384,
      "step": 573
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.02127659574468e-05,
      "loss": 4.3597,
      "step": 574
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.702127659574467e-05,
      "loss": 4.3714,
      "step": 575
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.382978723404255e-05,
      "loss": 4.4526,
      "step": 576
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.063829787234042e-05,
      "loss": 4.4474,
      "step": 577
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.7446808510638294e-05,
      "loss": 4.188,
      "step": 578
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.425531914893617e-05,
      "loss": 4.3285,
      "step": 579
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.106382978723404e-05,
      "loss": 4.3842,
      "step": 580
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.787234042553191e-05,
      "loss": 4.5096,
      "step": 581
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.468085106382978e-05,
      "loss": 4.3595,
      "step": 582
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.1489361702127656e-05,
      "loss": 4.2159,
      "step": 583
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.8297872340425525e-05,
      "loss": 4.4105,
      "step": 584
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.51063829787234e-05,
      "loss": 4.3474,
      "step": 585
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.1914893617021275e-05,
      "loss": 4.2935,
      "step": 586
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.8723404255319147e-05,
      "loss": 4.5936,
      "step": 587
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.553191489361702e-05,
      "loss": 4.5503,
      "step": 588
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.234042553191489e-05,
      "loss": 4.4791,
      "step": 589
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9148936170212762e-05,
      "loss": 4.3574,
      "step": 590
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.5957446808510637e-05,
      "loss": 4.5734,
      "step": 591
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.276595744680851e-05,
      "loss": 5.0126,
      "step": 592
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.574468085106381e-06,
      "loss": 4.6574,
      "step": 593
    },
    {
      "epoch": 1.0,
      "learning_rate": 6.382978723404255e-06,
      "loss": 4.4898,
      "step": 594
    },
    {
      "epoch": 1.0,
      "step": 594,
      "total_flos": 0.0,
      "train_loss": 4.478918995520081,
      "train_runtime": 5719.3723,
      "train_samples_per_second": 4.99,
      "train_steps_per_second": 0.104
    }
  ],
  "max_steps": 594,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}