{
  "best_metric": 1.9985228776931763,
  "best_model_checkpoint": "output/checkpoint-800",
  "epoch": 0.5469471907531741,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.9999999999999997e-06,
      "loss": 1.8876,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.999999999999999e-06,
      "loss": 2.0725,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-06,
      "loss": 2.0423,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 2.0022,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.0503,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 2.0501,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1e-05,
      "loss": 2.0322,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 2.0892,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 2.0786,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.0111,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 1.9539,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 2.0585,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9e-05,
      "loss": 2.0,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 1.9882,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 1.8964,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 2.0331,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.1e-05,
      "loss": 2.0569,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.399999999999999e-05,
      "loss": 1.9941,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 1.9494,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.0266,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.299999999999999e-05,
      "loss": 1.9042,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.599999999999999e-05,
      "loss": 2.009,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.9e-05,
      "loss": 1.9669,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.199999999999999e-05,
      "loss": 2.0222,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-05,
      "loss": 1.8443,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.8e-05,
      "loss": 1.9351,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.1e-05,
      "loss": 1.9858,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.4e-05,
      "loss": 2.0311,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.699999999999999e-05,
      "loss": 1.9912,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.0,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.3e-05,
      "loss": 2.0135,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.599999999999999e-05,
      "loss": 1.9629,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.9e-05,
      "loss": 1.9932,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000102,
      "loss": 2.0303,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010499999999999999,
      "loss": 1.9356,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010799999999999998,
      "loss": 1.9696,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011099999999999999,
      "loss": 1.9832,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.9901,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000117,
      "loss": 2.017,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.0139,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012299999999999998,
      "loss": 1.9377,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012599999999999997,
      "loss": 1.8405,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000129,
      "loss": 1.9986,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013199999999999998,
      "loss": 2.0137,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000135,
      "loss": 2.0437,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000138,
      "loss": 2.0392,
      "step": 46
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014099999999999998,
      "loss": 1.964,
      "step": 47
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014399999999999998,
      "loss": 1.9871,
      "step": 48
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000147,
      "loss": 1.9833,
      "step": 49
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015,
      "loss": 2.0132,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015299999999999998,
      "loss": 2.0262,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000156,
      "loss": 1.9727,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000159,
      "loss": 1.9904,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000162,
      "loss": 1.955,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000165,
      "loss": 1.9937,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000168,
      "loss": 2.0414,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017099999999999998,
      "loss": 1.9754,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017399999999999997,
      "loss": 1.9559,
      "step": 58
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017699999999999997,
      "loss": 1.971,
      "step": 59
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.959,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018299999999999998,
      "loss": 1.973,
      "step": 61
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000186,
      "loss": 1.9736,
      "step": 62
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018899999999999999,
      "loss": 2.01,
      "step": 63
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019199999999999998,
      "loss": 1.9916,
      "step": 64
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000195,
      "loss": 1.8412,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000198,
      "loss": 1.9188,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000201,
      "loss": 1.9836,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000204,
      "loss": 1.9659,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020699999999999996,
      "loss": 1.8651,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.8155,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021299999999999997,
      "loss": 1.9043,
      "step": 71
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021599999999999996,
      "loss": 1.9087,
      "step": 72
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021899999999999998,
      "loss": 2.0042,
      "step": 73
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022199999999999998,
      "loss": 1.9537,
      "step": 74
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000225,
      "loss": 1.9211,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022799999999999999,
      "loss": 1.9345,
      "step": 76
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023099999999999998,
      "loss": 1.84,
      "step": 77
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000234,
      "loss": 1.9432,
      "step": 78
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000237,
      "loss": 1.9381,
      "step": 79
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.9052,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000243,
      "loss": 1.9634,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00024599999999999996,
      "loss": 1.9323,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000249,
      "loss": 2.0616,
      "step": 83
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025199999999999995,
      "loss": 1.971,
      "step": 84
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025499999999999996,
      "loss": 1.9197,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000258,
      "loss": 1.9734,
      "step": 86
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000261,
      "loss": 1.8279,
      "step": 87
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00026399999999999997,
      "loss": 1.8787,
      "step": 88
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000267,
      "loss": 1.9271,
      "step": 89
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027,
      "loss": 1.8918,
      "step": 90
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027299999999999997,
      "loss": 1.9327,
      "step": 91
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000276,
      "loss": 1.8631,
      "step": 92
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000279,
      "loss": 1.8385,
      "step": 93
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00028199999999999997,
      "loss": 1.9437,
      "step": 94
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000285,
      "loss": 1.8879,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00028799999999999995,
      "loss": 1.9186,
      "step": 96
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029099999999999997,
      "loss": 1.9182,
      "step": 97
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000294,
      "loss": 1.8664,
      "step": 98
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029699999999999996,
      "loss": 1.9239,
      "step": 99
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 1.9942,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000303,
      "loss": 1.8882,
      "step": 101
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00030599999999999996,
      "loss": 1.9568,
      "step": 102
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000309,
      "loss": 1.9213,
      "step": 103
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000312,
      "loss": 1.8019,
      "step": 104
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00031499999999999996,
      "loss": 1.8682,
      "step": 105
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000318,
      "loss": 1.8517,
      "step": 106
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000321,
      "loss": 1.8922,
      "step": 107
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000324,
      "loss": 1.9581,
      "step": 108
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000327,
      "loss": 1.9073,
      "step": 109
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033,
      "loss": 1.8199,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000333,
      "loss": 1.933,
      "step": 111
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000336,
      "loss": 1.8907,
      "step": 112
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033899999999999995,
      "loss": 1.9093,
      "step": 113
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034199999999999996,
      "loss": 1.8501,
      "step": 114
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034499999999999993,
      "loss": 1.968,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034799999999999995,
      "loss": 1.8998,
      "step": 116
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035099999999999997,
      "loss": 1.9588,
      "step": 117
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035399999999999993,
      "loss": 1.8592,
      "step": 118
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035699999999999995,
      "loss": 1.9135,
      "step": 119
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035999999999999997,
      "loss": 1.8535,
      "step": 120
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036299999999999993,
      "loss": 1.8781,
      "step": 121
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036599999999999995,
      "loss": 1.8987,
      "step": 122
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036899999999999997,
      "loss": 1.8756,
      "step": 123
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000372,
      "loss": 1.8677,
      "step": 124
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037499999999999995,
      "loss": 1.8222,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037799999999999997,
      "loss": 1.9473,
      "step": 126
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000381,
      "loss": 1.8606,
      "step": 127
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00038399999999999996,
      "loss": 1.9605,
      "step": 128
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000387,
      "loss": 1.9135,
      "step": 129
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039,
      "loss": 1.9203,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039299999999999996,
      "loss": 1.9645,
      "step": 131
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000396,
      "loss": 1.8207,
      "step": 132
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000399,
      "loss": 1.9054,
      "step": 133
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000402,
      "loss": 1.8238,
      "step": 134
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000405,
      "loss": 1.9795,
      "step": 135
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000408,
      "loss": 1.923,
      "step": 136
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000411,
      "loss": 1.8111,
      "step": 137
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004139999999999999,
      "loss": 1.8022,
      "step": 138
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041699999999999994,
      "loss": 1.8601,
      "step": 139
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041999999999999996,
      "loss": 1.9157,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042299999999999993,
      "loss": 1.8795,
      "step": 141
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042599999999999995,
      "loss": 1.8175,
      "step": 142
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042899999999999997,
      "loss": 1.9633,
      "step": 143
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043199999999999993,
      "loss": 1.7384,
      "step": 144
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043499999999999995,
      "loss": 1.862,
      "step": 145
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043799999999999997,
      "loss": 1.8612,
      "step": 146
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044099999999999993,
      "loss": 1.8592,
      "step": 147
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044399999999999995,
      "loss": 1.8175,
      "step": 148
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044699999999999997,
      "loss": 1.8907,
      "step": 149
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045,
      "loss": 1.9142,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045299999999999995,
      "loss": 1.8859,
      "step": 151
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045599999999999997,
      "loss": 1.8369,
      "step": 152
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000459,
      "loss": 1.914,
      "step": 153
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046199999999999995,
      "loss": 1.8381,
      "step": 154
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046499999999999997,
      "loss": 1.96,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000468,
      "loss": 1.7527,
      "step": 156
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047099999999999996,
      "loss": 1.8762,
      "step": 157
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000474,
      "loss": 1.9295,
      "step": 158
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000477,
      "loss": 1.8433,
      "step": 159
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047999999999999996,
      "loss": 1.7407,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000483,
      "loss": 1.9237,
      "step": 161
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000486,
      "loss": 1.8505,
      "step": 162
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000489,
      "loss": 1.8386,
      "step": 163
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004919999999999999,
      "loss": 1.8489,
      "step": 164
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004949999999999999,
      "loss": 1.8447,
      "step": 165
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000498,
      "loss": 1.8709,
      "step": 166
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005009999999999999,
      "loss": 1.7427,
      "step": 167
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005039999999999999,
      "loss": 1.7115,
      "step": 168
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000507,
      "loss": 1.8692,
      "step": 169
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005099999999999999,
      "loss": 1.8863,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005129999999999999,
      "loss": 1.7856,
      "step": 171
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000516,
      "loss": 1.8338,
      "step": 172
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005189999999999999,
      "loss": 1.9064,
      "step": 173
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000522,
      "loss": 1.7566,
      "step": 174
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000525,
      "loss": 1.7792,
      "step": 175
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005279999999999999,
      "loss": 1.7444,
      "step": 176
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000531,
      "loss": 1.8172,
      "step": 177
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000534,
      "loss": 1.8232,
      "step": 178
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005369999999999999,
      "loss": 1.808,
      "step": 179
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00054,
      "loss": 1.7316,
      "step": 180
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000543,
      "loss": 1.7889,
      "step": 181
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005459999999999999,
      "loss": 1.8263,
      "step": 182
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000549,
      "loss": 1.8702,
      "step": 183
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000552,
      "loss": 1.8295,
      "step": 184
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005549999999999999,
      "loss": 1.7151,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000558,
      "loss": 1.7877,
      "step": 186
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000561,
      "loss": 1.7469,
      "step": 187
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005639999999999999,
      "loss": 1.8627,
      "step": 188
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005669999999999999,
      "loss": 1.6922,
      "step": 189
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00057,
      "loss": 1.8159,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005729999999999999,
      "loss": 1.7839,
      "step": 191
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005759999999999999,
      "loss": 1.8165,
      "step": 192
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000579,
      "loss": 1.8228,
      "step": 193
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005819999999999999,
      "loss": 1.8615,
      "step": 194
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005849999999999999,
      "loss": 1.8149,
      "step": 195
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000588,
      "loss": 1.8531,
      "step": 196
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005909999999999999,
      "loss": 1.7961,
      "step": 197
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005939999999999999,
      "loss": 1.7878,
      "step": 198
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000597,
      "loss": 1.7078,
      "step": 199
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0006,
      "loss": 1.77,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005998937677053823,
      "loss": 1.7704,
      "step": 201
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005997875354107648,
      "loss": 1.8041,
      "step": 202
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005996813031161472,
      "loss": 1.791,
      "step": 203
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005995750708215297,
      "loss": 1.8864,
      "step": 204
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005994688385269121,
      "loss": 1.8871,
      "step": 205
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005993626062322946,
      "loss": 1.781,
      "step": 206
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000599256373937677,
      "loss": 1.8129,
      "step": 207
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005991501416430595,
      "loss": 1.8208,
      "step": 208
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005990439093484419,
      "loss": 1.6943,
      "step": 209
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005989376770538244,
      "loss": 1.8093,
      "step": 210
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005988314447592068,
      "loss": 1.8158,
      "step": 211
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005987252124645891,
      "loss": 1.7879,
      "step": 212
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005986189801699716,
      "loss": 1.7495,
      "step": 213
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000598512747875354,
      "loss": 1.8075,
      "step": 214
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005984065155807364,
      "loss": 1.897,
      "step": 215
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005983002832861189,
      "loss": 1.7493,
      "step": 216
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005981940509915014,
      "loss": 1.7134,
      "step": 217
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005980878186968838,
      "loss": 1.7252,
      "step": 218
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005979815864022663,
      "loss": 1.8076,
      "step": 219
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005978753541076487,
      "loss": 1.7753,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005977691218130311,
      "loss": 1.7346,
      "step": 221
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005976628895184136,
      "loss": 1.7701,
      "step": 222
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000597556657223796,
      "loss": 1.7343,
      "step": 223
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005974504249291785,
      "loss": 1.9214,
      "step": 224
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005973441926345608,
      "loss": 1.8475,
      "step": 225
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005972379603399432,
      "loss": 1.7976,
      "step": 226
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005971317280453257,
      "loss": 1.8312,
      "step": 227
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005970254957507082,
      "loss": 1.7942,
      "step": 228
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005969192634560906,
      "loss": 1.7478,
      "step": 229
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005968130311614731,
      "loss": 1.8265,
      "step": 230
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005967067988668555,
      "loss": 1.743,
      "step": 231
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005966005665722379,
      "loss": 1.924,
      "step": 232
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005964943342776204,
      "loss": 1.8448,
      "step": 233
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005963881019830028,
      "loss": 1.8081,
      "step": 234
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005962818696883852,
      "loss": 1.7978,
      "step": 235
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005961756373937677,
      "loss": 1.9161,
      "step": 236
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00059606940509915,
      "loss": 1.8836,
      "step": 237
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005959631728045325,
      "loss": 1.6924,
      "step": 238
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000595856940509915,
      "loss": 1.8725,
      "step": 239
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005957507082152974,
      "loss": 1.7645,
      "step": 240
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005956444759206798,
      "loss": 1.8543,
      "step": 241
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005955382436260623,
      "loss": 1.8915,
      "step": 242
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005954320113314447,
      "loss": 1.7467,
      "step": 243
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005953257790368272,
      "loss": 1.7581,
      "step": 244
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005952195467422096,
      "loss": 1.7859,
      "step": 245
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000595113314447592,
      "loss": 1.7575,
      "step": 246
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005950070821529745,
      "loss": 1.7291,
      "step": 247
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005949008498583569,
      "loss": 1.692,
      "step": 248
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005947946175637393,
      "loss": 1.9056,
      "step": 249
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005946883852691218,
      "loss": 1.8572,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005945821529745042,
      "loss": 1.7458,
      "step": 251
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005944759206798866,
      "loss": 1.8021,
      "step": 252
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005943696883852691,
      "loss": 1.8534,
      "step": 253
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005942634560906515,
      "loss": 1.7671,
      "step": 254
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005941572237960339,
      "loss": 1.9101,
      "step": 255
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005940509915014164,
      "loss": 1.7567,
      "step": 256
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005939447592067988,
      "loss": 1.7771,
      "step": 257
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005938385269121813,
      "loss": 1.8691,
      "step": 258
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005937322946175637,
      "loss": 1.764,
      "step": 259
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000593626062322946,
      "loss": 1.7978,
      "step": 260
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005935198300283285,
      "loss": 1.8609,
      "step": 261
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000593413597733711,
      "loss": 1.9074,
      "step": 262
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005933073654390934,
      "loss": 1.8182,
      "step": 263
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005932011331444759,
      "loss": 1.9095,
      "step": 264
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005930949008498583,
      "loss": 1.9103,
      "step": 265
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005929886685552407,
      "loss": 1.969,
      "step": 266
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005928824362606232,
      "loss": 1.9142,
      "step": 267
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005927762039660056,
      "loss": 1.8281,
      "step": 268
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005926699716713881,
      "loss": 1.8105,
      "step": 269
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005925637393767705,
      "loss": 1.854,
      "step": 270
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005924575070821529,
      "loss": 1.7758,
      "step": 271
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005923512747875354,
      "loss": 1.7467,
      "step": 272
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005922450424929179,
      "loss": 1.8032,
      "step": 273
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005921388101983002,
      "loss": 1.7267,
      "step": 274
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005920325779036826,
      "loss": 1.7873,
      "step": 275
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005919263456090651,
      "loss": 1.8578,
      "step": 276
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005918201133144475,
      "loss": 1.8684,
      "step": 277
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00059171388101983,
      "loss": 1.8266,
      "step": 278
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005916076487252124,
      "loss": 1.7916,
      "step": 279
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005915014164305948,
      "loss": 1.9168,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005913951841359773,
      "loss": 1.8837,
      "step": 281
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005912889518413597,
      "loss": 1.7875,
      "step": 282
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005911827195467422,
      "loss": 1.9046,
      "step": 283
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005910764872521247,
      "loss": 1.7552,
      "step": 284
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000590970254957507,
      "loss": 1.8291,
      "step": 285
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005908640226628894,
      "loss": 1.8531,
      "step": 286
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005907577903682719,
      "loss": 1.7991,
      "step": 287
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005906515580736543,
      "loss": 1.7896,
      "step": 288
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005905453257790368,
      "loss": 1.8406,
      "step": 289
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005904390934844192,
      "loss": 1.8222,
      "step": 290
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005903328611898016,
      "loss": 1.8473,
      "step": 291
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005902266288951841,
      "loss": 1.7958,
      "step": 292
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005901203966005665,
      "loss": 1.7879,
      "step": 293
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000590014164305949,
      "loss": 1.8077,
      "step": 294
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005899079320113314,
      "loss": 1.7829,
      "step": 295
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005898016997167139,
      "loss": 1.8282,
      "step": 296
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005896954674220963,
      "loss": 1.8525,
      "step": 297
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005895892351274787,
      "loss": 1.8552,
      "step": 298
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005894830028328611,
      "loss": 1.9035,
      "step": 299
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005893767705382435,
      "loss": 1.8043,
      "step": 300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000589270538243626,
      "loss": 1.7884,
      "step": 301
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005891643059490084,
      "loss": 1.9804,
      "step": 302
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005890580736543909,
      "loss": 1.9464,
      "step": 303
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005889518413597733,
      "loss": 1.7684,
      "step": 304
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005888456090651558,
      "loss": 1.8019,
      "step": 305
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005887393767705382,
      "loss": 1.8127,
      "step": 306
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005886331444759207,
      "loss": 1.7938,
      "step": 307
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005885269121813031,
      "loss": 1.8452,
      "step": 308
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005884206798866856,
      "loss": 1.7761,
      "step": 309
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000588314447592068,
      "loss": 1.8166,
      "step": 310
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005882082152974503,
      "loss": 1.9685,
      "step": 311
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005881019830028328,
      "loss": 1.7582,
      "step": 312
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005879957507082152,
      "loss": 1.8127,
      "step": 313
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005878895184135976,
      "loss": 1.875,
      "step": 314
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005877832861189801,
      "loss": 1.7606,
      "step": 315
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005876770538243626,
      "loss": 1.8047,
      "step": 316
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000587570821529745,
      "loss": 1.8821,
      "step": 317
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005874645892351275,
      "loss": 1.9359,
      "step": 318
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005873583569405099,
      "loss": 1.9346,
      "step": 319
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005872521246458923,
      "loss": 1.8984,
      "step": 320
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005871458923512748,
      "loss": 1.7759,
      "step": 321
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005870396600566571,
      "loss": 1.7961,
      "step": 322
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005869334277620396,
      "loss": 1.9148,
      "step": 323
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000586827195467422,
      "loss": 1.898,
      "step": 324
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005867209631728044,
      "loss": 1.7916,
      "step": 325
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005866147308781869,
      "loss": 1.8758,
      "step": 326
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005865084985835694,
      "loss": 1.8184,
      "step": 327
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005864022662889518,
      "loss": 1.7792,
      "step": 328
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005862960339943343,
      "loss": 1.8199,
      "step": 329
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005861898016997167,
      "loss": 1.8013,
      "step": 330
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005860835694050991,
      "loss": 1.8723,
      "step": 331
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005859773371104816,
      "loss": 1.7972,
      "step": 332
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000585871104815864,
      "loss": 1.8765,
      "step": 333
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005857648725212463,
      "loss": 1.8028,
      "step": 334
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005856586402266288,
      "loss": 1.8377,
      "step": 335
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005855524079320112,
      "loss": 1.7413,
      "step": 336
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005854461756373937,
      "loss": 1.8906,
      "step": 337
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005853399433427762,
      "loss": 1.8192,
      "step": 338
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005852337110481586,
      "loss": 1.8595,
      "step": 339
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000585127478753541,
      "loss": 1.8473,
      "step": 340
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005850212464589235,
      "loss": 1.861,
      "step": 341
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005849150141643059,
      "loss": 1.8337,
      "step": 342
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005848087818696884,
      "loss": 1.8747,
      "step": 343
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005847025495750708,
      "loss": 1.8202,
      "step": 344
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005845963172804532,
      "loss": 1.8235,
      "step": 345
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005844900849858357,
      "loss": 1.915,
      "step": 346
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000584383852691218,
      "loss": 1.8257,
      "step": 347
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005842776203966005,
      "loss": 1.9219,
      "step": 348
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000584171388101983,
      "loss": 1.8675,
      "step": 349
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005840651558073654,
      "loss": 1.8938,
      "step": 350
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005839589235127478,
      "loss": 1.7652,
      "step": 351
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005838526912181303,
      "loss": 1.9201,
      "step": 352
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005837464589235127,
      "loss": 1.8092,
      "step": 353
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005836402266288951,
      "loss": 1.7251,
      "step": 354
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005835339943342776,
      "loss": 1.8227,
      "step": 355
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00058342776203966,
      "loss": 1.7901,
      "step": 356
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005833215297450425,
      "loss": 1.7998,
      "step": 357
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005832152974504249,
      "loss": 1.8229,
      "step": 358
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005831090651558072,
      "loss": 1.8179,
      "step": 359
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005830028328611897,
      "loss": 1.8142,
      "step": 360
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005828966005665722,
      "loss": 1.7447,
      "step": 361
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005827903682719546,
      "loss": 1.7978,
      "step": 362
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005826841359773371,
      "loss": 1.7471,
      "step": 363
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005825779036827195,
      "loss": 1.9006,
      "step": 364
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005824716713881019,
      "loss": 1.8023,
      "step": 365
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005823654390934844,
      "loss": 1.7522,
      "step": 366
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005822592067988668,
      "loss": 1.8935,
      "step": 367
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005821529745042493,
      "loss": 1.8137,
      "step": 368
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005820467422096317,
      "loss": 1.8023,
      "step": 369
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000581940509915014,
      "loss": 1.8378,
      "step": 370
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005818342776203965,
      "loss": 1.7871,
      "step": 371
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000581728045325779,
      "loss": 1.793,
      "step": 372
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005816218130311614,
      "loss": 1.8656,
      "step": 373
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005815155807365438,
      "loss": 1.8213,
      "step": 374
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005814093484419263,
      "loss": 1.8686,
      "step": 375
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005813031161473087,
      "loss": 1.7107,
      "step": 376
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005811968838526912,
      "loss": 1.8303,
      "step": 377
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005810906515580736,
      "loss": 1.8433,
      "step": 378
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000580984419263456,
      "loss": 1.8635,
      "step": 379
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005808781869688385,
      "loss": 1.8097,
      "step": 380
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005807719546742209,
      "loss": 1.8751,
      "step": 381
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005806657223796034,
      "loss": 1.8784,
      "step": 382
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005805594900849859,
      "loss": 1.8826,
      "step": 383
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005804532577903682,
      "loss": 1.7963,
      "step": 384
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005803470254957506,
      "loss": 1.8452,
      "step": 385
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005802407932011331,
      "loss": 1.7549,
      "step": 386
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005801345609065155,
      "loss": 1.851,
      "step": 387
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000580028328611898,
      "loss": 1.8198,
      "step": 388
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005799220963172804,
      "loss": 1.956,
      "step": 389
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005798158640226628,
      "loss": 1.9291,
      "step": 390
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005797096317280453,
      "loss": 1.784,
      "step": 391
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005796033994334277,
      "loss": 1.894,
      "step": 392
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005794971671388101,
      "loss": 1.886,
      "step": 393
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005793909348441927,
      "loss": 1.826,
      "step": 394
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000579284702549575,
      "loss": 1.8398,
      "step": 395
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005791784702549574,
      "loss": 1.7506,
      "step": 396
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005790722379603399,
      "loss": 1.8669,
      "step": 397
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005789660056657223,
      "loss": 1.8566,
      "step": 398
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005788597733711047,
      "loss": 1.8618,
      "step": 399
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005787535410764872,
      "loss": 1.8632,
      "step": 400
    },
    {
      "epoch": 0.27,
      "eval_loss": 2.021120071411133,
      "eval_runtime": 1471.972,
      "eval_samples_per_second": 9.879,
      "eval_steps_per_second": 9.879,
      "step": 400
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005786473087818696,
      "loss": 1.9149,
      "step": 401
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005785410764872521,
      "loss": 1.9261,
      "step": 402
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005784348441926345,
      "loss": 1.9515,
      "step": 403
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005783286118980169,
      "loss": 1.8682,
      "step": 404
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005782223796033994,
      "loss": 1.8787,
      "step": 405
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005781161473087819,
      "loss": 1.8882,
      "step": 406
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005780099150141643,
      "loss": 1.8623,
      "step": 407
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005779036827195467,
      "loss": 1.9533,
      "step": 408
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005777974504249291,
      "loss": 1.8139,
      "step": 409
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005776912181303115,
      "loss": 1.9436,
      "step": 410
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000577584985835694,
      "loss": 2.012,
      "step": 411
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005774787535410764,
      "loss": 1.8593,
      "step": 412
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005773725212464589,
      "loss": 1.9534,
      "step": 413
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005772662889518413,
      "loss": 1.8901,
      "step": 414
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005771600566572237,
      "loss": 1.9311,
      "step": 415
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005770538243626062,
      "loss": 1.9357,
      "step": 416
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005769475920679887,
      "loss": 2.0402,
      "step": 417
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005768413597733711,
      "loss": 1.9272,
      "step": 418
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005767351274787535,
      "loss": 1.8699,
      "step": 419
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000576628895184136,
      "loss": 1.9146,
      "step": 420
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005765226628895183,
      "loss": 1.8632,
      "step": 421
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005764164305949008,
      "loss": 1.9577,
      "step": 422
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005763101983002832,
      "loss": 1.9124,
      "step": 423
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005762039660056656,
      "loss": 1.8922,
      "step": 424
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005760977337110481,
      "loss": 1.8515,
      "step": 425
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005759915014164305,
      "loss": 1.9232,
      "step": 426
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000575885269121813,
      "loss": 1.9402,
      "step": 427
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005757790368271955,
      "loss": 1.885,
      "step": 428
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005756728045325779,
      "loss": 1.8847,
      "step": 429
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005755665722379603,
      "loss": 1.8776,
      "step": 430
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005754603399433428,
      "loss": 1.9292,
      "step": 431
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005753541076487251,
      "loss": 2.037,
      "step": 432
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005752478753541076,
      "loss": 1.9526,
      "step": 433
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00057514164305949,
      "loss": 1.8857,
      "step": 434
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005750354107648724,
      "loss": 1.8571,
      "step": 435
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005749291784702549,
      "loss": 1.99,
      "step": 436
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005748229461756373,
      "loss": 1.9094,
      "step": 437
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005747167138810198,
      "loss": 1.8634,
      "step": 438
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005746104815864022,
      "loss": 1.85,
      "step": 439
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005745042492917847,
      "loss": 1.9329,
      "step": 440
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005743980169971671,
      "loss": 1.9566,
      "step": 441
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005742917847025496,
      "loss": 1.9756,
      "step": 442
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000574185552407932,
      "loss": 1.9327,
      "step": 443
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005740793201133143,
      "loss": 1.8133,
      "step": 444
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005739730878186968,
      "loss": 1.9292,
      "step": 445
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005738668555240792,
      "loss": 1.8839,
      "step": 446
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005737606232294617,
      "loss": 1.9216,
      "step": 447
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005736543909348441,
      "loss": 1.9303,
      "step": 448
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005735481586402266,
      "loss": 2.0129,
      "step": 449
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000573441926345609,
      "loss": 1.9233,
      "step": 450
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005733356940509915,
      "loss": 1.809,
      "step": 451
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005732294617563739,
      "loss": 1.822,
      "step": 452
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005731232294617564,
      "loss": 1.829,
      "step": 453
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005730169971671388,
      "loss": 1.9524,
      "step": 454
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005729107648725212,
      "loss": 1.8695,
      "step": 455
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005728045325779037,
      "loss": 1.8614,
      "step": 456
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000572698300283286,
      "loss": 1.8697,
      "step": 457
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005725920679886684,
      "loss": 1.8378,
      "step": 458
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005724858356940509,
      "loss": 1.9554,
      "step": 459
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005723796033994334,
      "loss": 1.9066,
      "step": 460
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005722733711048158,
      "loss": 1.8836,
      "step": 461
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005721671388101983,
      "loss": 1.9541,
      "step": 462
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005720609065155807,
      "loss": 1.8879,
      "step": 463
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005719546742209631,
      "loss": 1.8126,
      "step": 464
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005718484419263456,
      "loss": 1.9861,
      "step": 465
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000571742209631728,
      "loss": 2.0253,
      "step": 466
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005716359773371105,
      "loss": 1.9213,
      "step": 467
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005715297450424929,
      "loss": 1.9988,
      "step": 468
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005714235127478752,
      "loss": 1.9285,
      "step": 469
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005713172804532577,
      "loss": 1.9973,
      "step": 470
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005712110481586402,
      "loss": 1.945,
      "step": 471
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005711048158640226,
      "loss": 1.9327,
      "step": 472
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005709985835694051,
      "loss": 2.0014,
      "step": 473
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005708923512747875,
      "loss": 1.8221,
      "step": 474
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005707861189801699,
      "loss": 1.8905,
      "step": 475
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005706798866855524,
      "loss": 1.9236,
      "step": 476
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005705736543909348,
      "loss": 1.8436,
      "step": 477
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005704674220963172,
      "loss": 1.8545,
      "step": 478
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005703611898016997,
      "loss": 1.8886,
      "step": 479
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000570254957507082,
      "loss": 1.873,
      "step": 480
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005701487252124645,
      "loss": 1.8624,
      "step": 481
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000570042492917847,
      "loss": 1.8614,
      "step": 482
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005699362606232294,
      "loss": 1.9153,
      "step": 483
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005698300283286118,
      "loss": 1.8524,
      "step": 484
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005697237960339943,
      "loss": 1.9039,
      "step": 485
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005696175637393767,
      "loss": 1.8866,
      "step": 486
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005695113314447592,
      "loss": 1.7717,
      "step": 487
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005694050991501416,
      "loss": 1.9695,
      "step": 488
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000569298866855524,
      "loss": 1.9931,
      "step": 489
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005691926345609065,
      "loss": 1.8473,
      "step": 490
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005690864022662889,
      "loss": 1.8366,
      "step": 491
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005689801699716714,
      "loss": 1.9242,
      "step": 492
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005688739376770539,
      "loss": 1.9081,
      "step": 493
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005687677053824362,
      "loss": 1.8658,
      "step": 494
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005686614730878186,
      "loss": 1.9603,
      "step": 495
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005685552407932011,
      "loss": 1.8292,
      "step": 496
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005684490084985835,
      "loss": 1.8917,
      "step": 497
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005683427762039659,
      "loss": 1.9171,
      "step": 498
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005682365439093484,
      "loss": 1.9373,
      "step": 499
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005681303116147308,
      "loss": 1.9529,
      "step": 500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005680240793201133,
      "loss": 1.9459,
      "step": 501
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005679178470254957,
      "loss": 1.9941,
      "step": 502
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005678116147308781,
      "loss": 1.8738,
      "step": 503
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005677053824362606,
      "loss": 1.9666,
      "step": 504
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000567599150141643,
      "loss": 2.0352,
      "step": 505
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005674929178470254,
      "loss": 1.8621,
      "step": 506
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005673866855524079,
      "loss": 1.8733,
      "step": 507
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005672804532577903,
      "loss": 1.9414,
      "step": 508
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005671742209631727,
      "loss": 1.9515,
      "step": 509
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005670679886685552,
      "loss": 1.891,
      "step": 510
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005669617563739376,
      "loss": 2.0231,
      "step": 511
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005668555240793201,
      "loss": 1.9534,
      "step": 512
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005667492917847025,
      "loss": 1.9437,
      "step": 513
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005666430594900849,
      "loss": 1.8914,
      "step": 514
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005665368271954674,
      "loss": 1.8711,
      "step": 515
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005664305949008499,
      "loss": 1.9708,
      "step": 516
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005663243626062323,
      "loss": 1.9462,
      "step": 517
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005662181303116146,
      "loss": 1.8547,
      "step": 518
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005661118980169971,
      "loss": 1.842,
      "step": 519
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005660056657223795,
      "loss": 1.8544,
      "step": 520
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000565899433427762,
      "loss": 1.8744,
      "step": 521
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005657932011331444,
      "loss": 1.9211,
      "step": 522
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005656869688385268,
      "loss": 1.9399,
      "step": 523
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005655807365439093,
      "loss": 1.9049,
      "step": 524
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005654745042492917,
      "loss": 1.9623,
      "step": 525
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005653682719546742,
      "loss": 1.9142,
      "step": 526
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005652620396600567,
      "loss": 1.8899,
      "step": 527
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005651558073654391,
      "loss": 1.8878,
      "step": 528
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005650495750708215,
      "loss": 1.924,
      "step": 529
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000564943342776204,
      "loss": 1.9087,
      "step": 530
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005648371104815863,
      "loss": 1.9945,
      "step": 531
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005647308781869688,
      "loss": 1.8945,
      "step": 532
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005646246458923512,
      "loss": 1.9209,
      "step": 533
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005645184135977336,
      "loss": 1.9301,
      "step": 534
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005644121813031161,
      "loss": 1.8516,
      "step": 535
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005643059490084985,
      "loss": 1.906,
      "step": 536
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000564199716713881,
      "loss": 1.91,
      "step": 537
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005640934844192634,
      "loss": 1.9069,
      "step": 538
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005639872521246459,
      "loss": 1.7911,
      "step": 539
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005638810198300283,
      "loss": 1.8925,
      "step": 540
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005637747875354108,
      "loss": 1.9526,
      "step": 541
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005636685552407931,
      "loss": 1.9279,
      "step": 542
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005635623229461755,
      "loss": 1.8829,
      "step": 543
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000563456090651558,
      "loss": 1.9501,
      "step": 544
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005633498583569404,
      "loss": 1.9602,
      "step": 545
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005632436260623229,
      "loss": 1.9497,
      "step": 546
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005631373937677053,
      "loss": 1.84,
      "step": 547
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005630311614730878,
      "loss": 1.9337,
      "step": 548
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005629249291784702,
      "loss": 1.8709,
      "step": 549
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005628186968838527,
      "loss": 1.9231,
      "step": 550
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005627124645892351,
      "loss": 1.9035,
      "step": 551
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005626062322946176,
      "loss": 1.8365,
      "step": 552
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005625,
      "loss": 2.1028,
      "step": 553
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005623937677053823,
      "loss": 1.8692,
      "step": 554
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005622875354107648,
      "loss": 1.9452,
      "step": 555
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005621813031161472,
      "loss": 1.883,
      "step": 556
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005620750708215296,
      "loss": 1.8987,
      "step": 557
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005619688385269121,
      "loss": 1.9188,
      "step": 558
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005618626062322946,
      "loss": 1.9373,
      "step": 559
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000561756373937677,
      "loss": 1.9167,
      "step": 560
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005616501416430595,
      "loss": 1.8628,
      "step": 561
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005615439093484419,
      "loss": 1.9258,
      "step": 562
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005614376770538243,
      "loss": 1.9783,
      "step": 563
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005613314447592068,
      "loss": 1.9738,
      "step": 564
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005612252124645892,
      "loss": 1.9351,
      "step": 565
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005611189801699717,
      "loss": 1.9109,
      "step": 566
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000561012747875354,
      "loss": 1.832,
      "step": 567
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005609065155807364,
      "loss": 1.9258,
      "step": 568
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005608002832861189,
      "loss": 1.9888,
      "step": 569
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005606940509915014,
      "loss": 1.9195,
      "step": 570
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005605878186968838,
      "loss": 1.8607,
      "step": 571
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005604815864022663,
      "loss": 1.9868,
      "step": 572
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005603753541076487,
      "loss": 1.885,
      "step": 573
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005602691218130311,
      "loss": 1.9379,
      "step": 574
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005601628895184136,
      "loss": 1.8685,
      "step": 575
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000560056657223796,
      "loss": 1.9636,
      "step": 576
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005599504249291784,
      "loss": 1.9925,
      "step": 577
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005598441926345609,
      "loss": 1.9332,
      "step": 578
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005597379603399432,
      "loss": 1.8458,
      "step": 579
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005596317280453257,
      "loss": 1.8204,
      "step": 580
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005595254957507082,
      "loss": 1.8656,
      "step": 581
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005594192634560906,
      "loss": 1.9399,
      "step": 582
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000559313031161473,
      "loss": 1.891,
      "step": 583
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005592067988668555,
      "loss": 1.8595,
      "step": 584
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005591005665722379,
      "loss": 1.8989,
      "step": 585
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005589943342776204,
      "loss": 1.8275,
      "step": 586
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005588881019830028,
      "loss": 1.8716,
      "step": 587
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005587818696883852,
      "loss": 1.933,
      "step": 588
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005586756373937677,
      "loss": 1.982,
      "step": 589
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00055856940509915,
      "loss": 1.8773,
      "step": 590
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005584631728045325,
      "loss": 1.8793,
      "step": 591
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000558356940509915,
      "loss": 1.9778,
      "step": 592
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005582507082152974,
      "loss": 1.9904,
      "step": 593
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005581444759206798,
      "loss": 1.9301,
      "step": 594
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005580382436260623,
      "loss": 1.9367,
      "step": 595
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005579320113314447,
      "loss": 1.9853,
      "step": 596
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005578257790368272,
      "loss": 1.9987,
      "step": 597
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005577195467422096,
      "loss": 1.88,
      "step": 598
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000557613314447592,
      "loss": 1.9391,
      "step": 599
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005575070821529745,
      "loss": 2.0134,
      "step": 600
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005574008498583569,
      "loss": 1.8383,
      "step": 601
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005572946175637392,
      "loss": 1.8189,
      "step": 602
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005571883852691217,
      "loss": 1.9324,
      "step": 603
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005570821529745042,
      "loss": 1.8702,
      "step": 604
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005569759206798866,
      "loss": 1.8803,
      "step": 605
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005568696883852691,
      "loss": 1.8409,
      "step": 606
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005567634560906515,
      "loss": 1.8715,
      "step": 607
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005566572237960339,
      "loss": 1.9359,
      "step": 608
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005565509915014164,
      "loss": 1.922,
      "step": 609
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005564447592067988,
      "loss": 1.8341,
      "step": 610
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005563385269121813,
      "loss": 1.9494,
      "step": 611
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005562322946175637,
      "loss": 1.9585,
      "step": 612
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005561260623229461,
      "loss": 1.8668,
      "step": 613
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005560198300283286,
      "loss": 1.9067,
      "step": 614
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000555913597733711,
      "loss": 1.8475,
      "step": 615
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005558073654390934,
      "loss": 1.9009,
      "step": 616
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005557011331444759,
      "loss": 1.941,
      "step": 617
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005555949008498583,
      "loss": 1.9756,
      "step": 618
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005554886685552407,
      "loss": 1.9568,
      "step": 619
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005553824362606232,
      "loss": 1.8794,
      "step": 620
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005552762039660056,
      "loss": 1.9152,
      "step": 621
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000555169971671388,
      "loss": 2.0171,
      "step": 622
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005550637393767705,
      "loss": 1.9388,
      "step": 623
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005549575070821529,
      "loss": 1.9048,
      "step": 624
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005548512747875354,
      "loss": 1.9667,
      "step": 625
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005547450424929179,
      "loss": 1.9878,
      "step": 626
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005546388101983003,
      "loss": 1.9145,
      "step": 627
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005545325779036826,
      "loss": 1.9873,
      "step": 628
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005544263456090651,
      "loss": 2.015,
      "step": 629
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005543201133144475,
      "loss": 1.9204,
      "step": 630
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00055421388101983,
      "loss": 1.8899,
      "step": 631
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005541076487252124,
      "loss": 1.9057,
      "step": 632
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005540014164305948,
      "loss": 1.9663,
      "step": 633
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005538951841359773,
      "loss": 1.9447,
      "step": 634
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005537889518413597,
      "loss": 1.957,
      "step": 635
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005536827195467422,
      "loss": 1.8772,
      "step": 636
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005535764872521247,
      "loss": 1.9601,
      "step": 637
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005534702549575071,
      "loss": 1.8354,
      "step": 638
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005533640226628895,
      "loss": 1.9107,
      "step": 639
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000553257790368272,
      "loss": 1.9511,
      "step": 640
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005531515580736543,
      "loss": 1.9354,
      "step": 641
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005530453257790367,
      "loss": 1.9189,
      "step": 642
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005529390934844192,
      "loss": 1.803,
      "step": 643
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005528328611898016,
      "loss": 1.9278,
      "step": 644
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005527266288951841,
      "loss": 1.8629,
      "step": 645
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005526203966005665,
      "loss": 1.9348,
      "step": 646
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000552514164305949,
      "loss": 1.9472,
      "step": 647
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005524079320113314,
      "loss": 1.9808,
      "step": 648
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005523016997167139,
      "loss": 1.8421,
      "step": 649
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005521954674220963,
      "loss": 1.9773,
      "step": 650
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005520892351274788,
      "loss": 1.9566,
      "step": 651
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005519830028328611,
      "loss": 1.9461,
      "step": 652
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005518767705382435,
      "loss": 1.9117,
      "step": 653
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000551770538243626,
      "loss": 1.8791,
      "step": 654
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005516643059490084,
      "loss": 1.9065,
      "step": 655
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005515580736543909,
      "loss": 1.9535,
      "step": 656
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005514518413597733,
      "loss": 1.8854,
      "step": 657
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005513456090651558,
      "loss": 2.023,
      "step": 658
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005512393767705382,
      "loss": 2.0061,
      "step": 659
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005511331444759207,
      "loss": 1.8768,
      "step": 660
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005510269121813031,
      "loss": 1.948,
      "step": 661
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005509206798866855,
      "loss": 1.9478,
      "step": 662
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000550814447592068,
      "loss": 1.977,
      "step": 663
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005507082152974503,
      "loss": 1.9208,
      "step": 664
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005506019830028328,
      "loss": 1.9287,
      "step": 665
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005504957507082152,
      "loss": 1.8817,
      "step": 666
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005503895184135976,
      "loss": 1.9567,
      "step": 667
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005502832861189801,
      "loss": 1.8139,
      "step": 668
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005501770538243626,
      "loss": 1.913,
      "step": 669
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000550070821529745,
      "loss": 1.9434,
      "step": 670
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005499645892351275,
      "loss": 1.9377,
      "step": 671
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005498583569405099,
      "loss": 1.8781,
      "step": 672
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005497521246458923,
      "loss": 1.8837,
      "step": 673
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005496458923512748,
      "loss": 1.9478,
      "step": 674
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005495396600566572,
      "loss": 1.8756,
      "step": 675
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005494334277620397,
      "loss": 1.9507,
      "step": 676
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000549327195467422,
      "loss": 1.9027,
      "step": 677
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005492209631728044,
      "loss": 1.9749,
      "step": 678
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005491147308781869,
      "loss": 1.8564,
      "step": 679
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005490084985835694,
      "loss": 1.9649,
      "step": 680
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005489022662889518,
      "loss": 2.0128,
      "step": 681
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005487960339943342,
      "loss": 1.9041,
      "step": 682
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005486898016997167,
      "loss": 2.0121,
      "step": 683
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005485835694050991,
      "loss": 1.9203,
      "step": 684
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005484773371104816,
      "loss": 1.9,
      "step": 685
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000548371104815864,
      "loss": 1.9857,
      "step": 686
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005482648725212464,
      "loss": 2.0838,
      "step": 687
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005481586402266289,
      "loss": 1.8973,
      "step": 688
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005480524079320112,
      "loss": 1.9636,
      "step": 689
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005479461756373937,
      "loss": 1.9726,
      "step": 690
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005478399433427762,
      "loss": 1.9062,
      "step": 691
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005477337110481586,
      "loss": 1.8709,
      "step": 692
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000547627478753541,
      "loss": 1.9234,
      "step": 693
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005475212464589235,
      "loss": 1.8859,
      "step": 694
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005474150141643059,
      "loss": 1.9746,
      "step": 695
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005473087818696884,
      "loss": 1.9229,
      "step": 696
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005472025495750708,
      "loss": 1.8827,
      "step": 697
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005470963172804532,
      "loss": 1.9455,
      "step": 698
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005469900849858357,
      "loss": 1.8779,
      "step": 699
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000546883852691218,
      "loss": 1.9151,
      "step": 700
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005467776203966004,
      "loss": 1.8283,
      "step": 701
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005466713881019829,
      "loss": 1.9657,
      "step": 702
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005465651558073654,
      "loss": 2.0174,
      "step": 703
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005464589235127478,
      "loss": 1.9462,
      "step": 704
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005463526912181303,
      "loss": 1.9257,
      "step": 705
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005462464589235127,
      "loss": 1.8828,
      "step": 706
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005461402266288951,
      "loss": 1.8831,
      "step": 707
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005460339943342776,
      "loss": 1.9266,
      "step": 708
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00054592776203966,
      "loss": 2.0017,
      "step": 709
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005458215297450425,
      "loss": 1.9537,
      "step": 710
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005457152974504249,
      "loss": 1.9141,
      "step": 711
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005456090651558072,
      "loss": 1.9393,
      "step": 712
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005455028328611897,
      "loss": 1.8896,
      "step": 713
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005453966005665722,
      "loss": 1.8186,
      "step": 714
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005452903682719546,
      "loss": 1.9527,
      "step": 715
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005451841359773371,
      "loss": 2.0319,
      "step": 716
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005450779036827195,
      "loss": 1.8668,
      "step": 717
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005449716713881019,
      "loss": 1.9775,
      "step": 718
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005448654390934844,
      "loss": 1.8624,
      "step": 719
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005447592067988668,
      "loss": 1.8725,
      "step": 720
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005446529745042492,
      "loss": 1.8682,
      "step": 721
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005445467422096317,
      "loss": 1.9078,
      "step": 722
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005444405099150141,
      "loss": 1.8206,
      "step": 723
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005443342776203966,
      "loss": 1.9923,
      "step": 724
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000544228045325779,
      "loss": 1.9765,
      "step": 725
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005441218130311614,
      "loss": 1.9154,
      "step": 726
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005440155807365438,
      "loss": 1.8111,
      "step": 727
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005439093484419263,
      "loss": 1.9149,
      "step": 728
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005438031161473087,
      "loss": 1.927,
      "step": 729
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005436968838526912,
      "loss": 1.855,
      "step": 730
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005435906515580736,
      "loss": 1.8842,
      "step": 731
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000543484419263456,
      "loss": 1.955,
      "step": 732
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005433781869688385,
      "loss": 1.9599,
      "step": 733
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005432719546742209,
      "loss": 1.8462,
      "step": 734
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005431657223796034,
      "loss": 1.7453,
      "step": 735
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005430594900849859,
      "loss": 1.8518,
      "step": 736
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005429532577903683,
      "loss": 1.7791,
      "step": 737
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005428470254957506,
      "loss": 1.918,
      "step": 738
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005427407932011331,
      "loss": 1.8775,
      "step": 739
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005426345609065155,
      "loss": 1.9502,
      "step": 740
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005425283286118979,
      "loss": 1.9256,
      "step": 741
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005424220963172804,
      "loss": 1.9275,
      "step": 742
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005423158640226628,
      "loss": 1.9383,
      "step": 743
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005422096317280453,
      "loss": 1.8964,
      "step": 744
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005421033994334277,
      "loss": 1.9313,
      "step": 745
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005419971671388101,
      "loss": 1.8931,
      "step": 746
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005418909348441926,
      "loss": 1.9748,
      "step": 747
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005417847025495751,
      "loss": 1.985,
      "step": 748
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005416784702549575,
      "loss": 1.8515,
      "step": 749
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00054157223796034,
      "loss": 1.8717,
      "step": 750
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005414660056657223,
      "loss": 1.9044,
      "step": 751
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005413597733711047,
      "loss": 1.9972,
      "step": 752
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005412535410764872,
      "loss": 1.8846,
      "step": 753
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005411473087818696,
      "loss": 1.8465,
      "step": 754
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005410410764872521,
      "loss": 1.9254,
      "step": 755
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005409348441926345,
      "loss": 1.89,
      "step": 756
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005408286118980169,
      "loss": 1.9923,
      "step": 757
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005407223796033994,
      "loss": 1.8325,
      "step": 758
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005406161473087819,
      "loss": 2.023,
      "step": 759
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005405099150141643,
      "loss": 1.8279,
      "step": 760
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005404036827195467,
      "loss": 1.9296,
      "step": 761
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005402974504249291,
      "loss": 1.8728,
      "step": 762
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005401912181303115,
      "loss": 1.9336,
      "step": 763
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000540084985835694,
      "loss": 1.8554,
      "step": 764
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005399787535410764,
      "loss": 1.9388,
      "step": 765
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005398725212464588,
      "loss": 1.9101,
      "step": 766
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005397662889518413,
      "loss": 1.866,
      "step": 767
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005396600566572237,
      "loss": 1.9731,
      "step": 768
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005395538243626062,
      "loss": 1.9263,
      "step": 769
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005394475920679887,
      "loss": 1.9337,
      "step": 770
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005393413597733711,
      "loss": 1.896,
      "step": 771
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005392351274787535,
      "loss": 1.9376,
      "step": 772
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000539128895184136,
      "loss": 1.9601,
      "step": 773
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005390226628895183,
      "loss": 1.9177,
      "step": 774
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005389164305949008,
      "loss": 1.9044,
      "step": 775
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005388101983002832,
      "loss": 1.9378,
      "step": 776
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005387039660056656,
      "loss": 1.8153,
      "step": 777
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005385977337110481,
      "loss": 1.9445,
      "step": 778
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005384915014164305,
      "loss": 1.8467,
      "step": 779
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000538385269121813,
      "loss": 1.8743,
      "step": 780
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005382790368271955,
      "loss": 1.8839,
      "step": 781
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005381728045325779,
      "loss": 1.8023,
      "step": 782
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005380665722379603,
      "loss": 1.9814,
      "step": 783
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005379603399433428,
      "loss": 1.8621,
      "step": 784
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005378541076487252,
      "loss": 1.9371,
      "step": 785
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005377478753541075,
      "loss": 1.9692,
      "step": 786
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00053764164305949,
      "loss": 1.9392,
      "step": 787
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005375354107648724,
      "loss": 2.0,
      "step": 788
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005374291784702549,
      "loss": 1.9281,
      "step": 789
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005373229461756373,
      "loss": 1.9512,
      "step": 790
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005372167138810198,
      "loss": 1.9222,
      "step": 791
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005371104815864022,
      "loss": 1.9698,
      "step": 792
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005370042492917847,
      "loss": 1.8392,
      "step": 793
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005368980169971671,
      "loss": 1.9714,
      "step": 794
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005367917847025496,
      "loss": 1.8521,
      "step": 795
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000536685552407932,
      "loss": 1.9495,
      "step": 796
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005365793201133144,
      "loss": 1.9401,
      "step": 797
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005364730878186969,
      "loss": 1.8449,
      "step": 798
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005363668555240792,
      "loss": 1.9425,
      "step": 799
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005362606232294617,
      "loss": 1.8826,
      "step": 800
    },
    {
      "epoch": 0.55,
      "eval_loss": 1.9985228776931763,
      "eval_runtime": 1468.32,
      "eval_samples_per_second": 9.904,
      "eval_steps_per_second": 9.904,
      "step": 800
    }
  ],
  "max_steps": 5848,
  "num_train_epochs": 4,
  "total_flos": 9.813169375148851e+17,
  "trial_name": null,
  "trial_params": null
}