{
  "best_metric": 1.9827316999435425,
  "best_model_checkpoint": "output/checkpoint-2200",
  "epoch": 1.5041047745712288,
  "global_step": 2200,
  "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": 2.1853,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.999999999999999e-06,
      "loss": 2.3789,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-06,
      "loss": 2.3312,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.1999999999999999e-05,
      "loss": 2.2895,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.3325,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 2.3354,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1e-05,
      "loss": 2.3068,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3999999999999997e-05,
      "loss": 2.3766,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 2.3448,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.2754,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 2.2119,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 2.3228,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9e-05,
      "loss": 2.2545,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 2.2331,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.1402,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.7999999999999994e-05,
      "loss": 2.2808,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.1e-05,
      "loss": 2.3187,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.399999999999999e-05,
      "loss": 2.2397,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 2.1723,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.2569,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.299999999999999e-05,
      "loss": 2.1196,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.599999999999999e-05,
      "loss": 2.2139,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.9e-05,
      "loss": 2.1917,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.199999999999999e-05,
      "loss": 2.2482,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-05,
      "loss": 2.099,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.8e-05,
      "loss": 2.1668,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.1e-05,
      "loss": 2.2079,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.4e-05,
      "loss": 2.2618,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.699999999999999e-05,
      "loss": 2.2295,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.2095,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.3e-05,
      "loss": 2.219,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.599999999999999e-05,
      "loss": 2.172,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.9e-05,
      "loss": 2.2062,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000102,
      "loss": 2.2535,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010499999999999999,
      "loss": 2.164,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010799999999999998,
      "loss": 2.2069,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011099999999999999,
      "loss": 2.1966,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011399999999999999,
      "loss": 2.1929,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000117,
      "loss": 2.2215,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.2541,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012299999999999998,
      "loss": 2.1316,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012599999999999997,
      "loss": 2.0486,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000129,
      "loss": 2.2175,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013199999999999998,
      "loss": 2.2277,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000135,
      "loss": 2.2629,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000138,
      "loss": 2.2549,
      "step": 46
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014099999999999998,
      "loss": 2.1836,
      "step": 47
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014399999999999998,
      "loss": 2.1772,
      "step": 48
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000147,
      "loss": 2.2013,
      "step": 49
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015,
      "loss": 2.2103,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015299999999999998,
      "loss": 2.244,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000156,
      "loss": 2.178,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000159,
      "loss": 2.1942,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000162,
      "loss": 2.171,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000165,
      "loss": 2.2166,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000168,
      "loss": 2.2737,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017099999999999998,
      "loss": 2.179,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017399999999999997,
      "loss": 2.173,
      "step": 58
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017699999999999997,
      "loss": 2.1753,
      "step": 59
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.1591,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018299999999999998,
      "loss": 2.1936,
      "step": 61
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000186,
      "loss": 2.1971,
      "step": 62
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00018899999999999999,
      "loss": 2.209,
      "step": 63
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019199999999999998,
      "loss": 2.2032,
      "step": 64
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000195,
      "loss": 2.0609,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000198,
      "loss": 2.1394,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000201,
      "loss": 2.1906,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000204,
      "loss": 2.1658,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020699999999999996,
      "loss": 2.0702,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00020999999999999998,
      "loss": 2.0302,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021299999999999997,
      "loss": 2.1205,
      "step": 71
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021599999999999996,
      "loss": 2.1048,
      "step": 72
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00021899999999999998,
      "loss": 2.2125,
      "step": 73
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022199999999999998,
      "loss": 2.1554,
      "step": 74
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000225,
      "loss": 2.1242,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00022799999999999999,
      "loss": 2.1383,
      "step": 76
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023099999999999998,
      "loss": 2.0299,
      "step": 77
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000234,
      "loss": 2.1578,
      "step": 78
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000237,
      "loss": 2.1432,
      "step": 79
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.1129,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000243,
      "loss": 2.1672,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00024599999999999996,
      "loss": 2.1425,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000249,
      "loss": 2.2758,
      "step": 83
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025199999999999995,
      "loss": 2.173,
      "step": 84
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00025499999999999996,
      "loss": 2.1262,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000258,
      "loss": 2.1657,
      "step": 86
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000261,
      "loss": 2.0322,
      "step": 87
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00026399999999999997,
      "loss": 2.0887,
      "step": 88
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000267,
      "loss": 2.135,
      "step": 89
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027,
      "loss": 2.1048,
      "step": 90
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00027299999999999997,
      "loss": 2.1313,
      "step": 91
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000276,
      "loss": 2.0808,
      "step": 92
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000279,
      "loss": 2.0489,
      "step": 93
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00028199999999999997,
      "loss": 2.1537,
      "step": 94
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000285,
      "loss": 2.1017,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00028799999999999995,
      "loss": 2.1312,
      "step": 96
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029099999999999997,
      "loss": 2.1248,
      "step": 97
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000294,
      "loss": 2.0856,
      "step": 98
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00029699999999999996,
      "loss": 2.1286,
      "step": 99
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 2.202,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000303,
      "loss": 2.0967,
      "step": 101
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00030599999999999996,
      "loss": 2.1731,
      "step": 102
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000309,
      "loss": 2.1321,
      "step": 103
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000312,
      "loss": 2.0159,
      "step": 104
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00031499999999999996,
      "loss": 2.071,
      "step": 105
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000318,
      "loss": 2.0542,
      "step": 106
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000321,
      "loss": 2.1085,
      "step": 107
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000324,
      "loss": 2.1758,
      "step": 108
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000327,
      "loss": 2.1243,
      "step": 109
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033,
      "loss": 2.0375,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000333,
      "loss": 2.1409,
      "step": 111
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000336,
      "loss": 2.1071,
      "step": 112
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00033899999999999995,
      "loss": 2.1259,
      "step": 113
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034199999999999996,
      "loss": 2.0782,
      "step": 114
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034499999999999993,
      "loss": 2.2005,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00034799999999999995,
      "loss": 2.1199,
      "step": 116
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035099999999999997,
      "loss": 2.1757,
      "step": 117
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035399999999999993,
      "loss": 2.0705,
      "step": 118
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035699999999999995,
      "loss": 2.1261,
      "step": 119
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00035999999999999997,
      "loss": 2.0633,
      "step": 120
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036299999999999993,
      "loss": 2.1012,
      "step": 121
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036599999999999995,
      "loss": 2.1077,
      "step": 122
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00036899999999999997,
      "loss": 2.0978,
      "step": 123
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000372,
      "loss": 2.0924,
      "step": 124
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037499999999999995,
      "loss": 2.0565,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00037799999999999997,
      "loss": 2.1612,
      "step": 126
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000381,
      "loss": 2.0699,
      "step": 127
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00038399999999999996,
      "loss": 2.1886,
      "step": 128
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000387,
      "loss": 2.1232,
      "step": 129
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039,
      "loss": 2.1499,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00039299999999999996,
      "loss": 2.1805,
      "step": 131
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000396,
      "loss": 2.0487,
      "step": 132
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000399,
      "loss": 2.1278,
      "step": 133
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000402,
      "loss": 2.0348,
      "step": 134
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000405,
      "loss": 2.1963,
      "step": 135
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000408,
      "loss": 2.1453,
      "step": 136
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000411,
      "loss": 2.035,
      "step": 137
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004139999999999999,
      "loss": 2.0129,
      "step": 138
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041699999999999994,
      "loss": 2.0832,
      "step": 139
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00041999999999999996,
      "loss": 2.1616,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042299999999999993,
      "loss": 2.1153,
      "step": 141
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042599999999999995,
      "loss": 2.0437,
      "step": 142
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00042899999999999997,
      "loss": 2.1931,
      "step": 143
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043199999999999993,
      "loss": 1.9648,
      "step": 144
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043499999999999995,
      "loss": 2.0986,
      "step": 145
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00043799999999999997,
      "loss": 2.0978,
      "step": 146
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044099999999999993,
      "loss": 2.0683,
      "step": 147
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044399999999999995,
      "loss": 2.0536,
      "step": 148
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00044699999999999997,
      "loss": 2.1095,
      "step": 149
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045,
      "loss": 2.154,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045299999999999995,
      "loss": 2.1351,
      "step": 151
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00045599999999999997,
      "loss": 2.0517,
      "step": 152
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000459,
      "loss": 2.1572,
      "step": 153
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046199999999999995,
      "loss": 2.0666,
      "step": 154
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00046499999999999997,
      "loss": 2.195,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000468,
      "loss": 1.9685,
      "step": 156
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047099999999999996,
      "loss": 2.11,
      "step": 157
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000474,
      "loss": 2.1476,
      "step": 158
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000477,
      "loss": 2.0957,
      "step": 159
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00047999999999999996,
      "loss": 1.9753,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000483,
      "loss": 2.1659,
      "step": 161
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000486,
      "loss": 2.0978,
      "step": 162
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000489,
      "loss": 2.0742,
      "step": 163
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004919999999999999,
      "loss": 2.0865,
      "step": 164
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004949999999999999,
      "loss": 2.0911,
      "step": 165
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000498,
      "loss": 2.1147,
      "step": 166
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005009999999999999,
      "loss": 1.9884,
      "step": 167
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0005039999999999999,
      "loss": 1.9497,
      "step": 168
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000507,
      "loss": 2.1134,
      "step": 169
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005099999999999999,
      "loss": 2.1097,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005129999999999999,
      "loss": 2.0186,
      "step": 171
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000516,
      "loss": 2.0772,
      "step": 172
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005189999999999999,
      "loss": 2.1284,
      "step": 173
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000522,
      "loss": 1.9895,
      "step": 174
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000525,
      "loss": 2.0206,
      "step": 175
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005279999999999999,
      "loss": 1.9765,
      "step": 176
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000531,
      "loss": 2.0687,
      "step": 177
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000534,
      "loss": 2.079,
      "step": 178
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005369999999999999,
      "loss": 2.0544,
      "step": 179
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00054,
      "loss": 1.9787,
      "step": 180
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000543,
      "loss": 2.0328,
      "step": 181
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0005459999999999999,
      "loss": 2.0692,
      "step": 182
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000549,
      "loss": 2.1062,
      "step": 183
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000552,
      "loss": 2.0996,
      "step": 184
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005549999999999999,
      "loss": 1.9696,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000558,
      "loss": 2.0402,
      "step": 186
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000561,
      "loss": 2.0141,
      "step": 187
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005639999999999999,
      "loss": 2.1041,
      "step": 188
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005669999999999999,
      "loss": 1.9539,
      "step": 189
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00057,
      "loss": 2.0689,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005729999999999999,
      "loss": 2.047,
      "step": 191
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005759999999999999,
      "loss": 2.0751,
      "step": 192
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000579,
      "loss": 2.0649,
      "step": 193
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005819999999999999,
      "loss": 2.1111,
      "step": 194
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005849999999999999,
      "loss": 2.0669,
      "step": 195
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000588,
      "loss": 2.1075,
      "step": 196
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0005909999999999999,
      "loss": 2.0398,
      "step": 197
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005939999999999999,
      "loss": 2.0357,
      "step": 198
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000597,
      "loss": 1.953,
      "step": 199
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0006,
      "loss": 2.026,
      "step": 200
    },
    {
      "epoch": 0.14,
      "eval_loss": 2.0633840560913086,
      "eval_runtime": 1727.3111,
      "eval_samples_per_second": 5.789,
      "eval_steps_per_second": 5.789,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005998566650740563,
      "loss": 2.0193,
      "step": 201
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005997133301481127,
      "loss": 2.0543,
      "step": 202
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005995699952221691,
      "loss": 2.0542,
      "step": 203
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005994266602962255,
      "loss": 2.1345,
      "step": 204
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005992833253702819,
      "loss": 2.1243,
      "step": 205
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005991399904443383,
      "loss": 2.0224,
      "step": 206
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005989966555183946,
      "loss": 2.0536,
      "step": 207
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005988533205924509,
      "loss": 2.073,
      "step": 208
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005987099856665074,
      "loss": 1.9553,
      "step": 209
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005985666507405637,
      "loss": 2.0866,
      "step": 210
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005984233158146202,
      "loss": 2.0656,
      "step": 211
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0005982799808886764,
      "loss": 2.0459,
      "step": 212
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005981366459627329,
      "loss": 1.9813,
      "step": 213
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005979933110367892,
      "loss": 2.0579,
      "step": 214
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005978499761108456,
      "loss": 2.1568,
      "step": 215
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000597706641184902,
      "loss": 2.0049,
      "step": 216
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005975633062589584,
      "loss": 1.9582,
      "step": 217
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005974199713330147,
      "loss": 1.9647,
      "step": 218
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005972766364070711,
      "loss": 2.0564,
      "step": 219
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005971333014811275,
      "loss": 2.0314,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005969899665551839,
      "loss": 1.9784,
      "step": 221
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005968466316292403,
      "loss": 2.015,
      "step": 222
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005967032967032967,
      "loss": 1.9988,
      "step": 223
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000596559961777353,
      "loss": 2.1571,
      "step": 224
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005964166268514094,
      "loss": 2.0942,
      "step": 225
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0005962732919254658,
      "loss": 2.0249,
      "step": 226
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005961299569995222,
      "loss": 2.0765,
      "step": 227
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005959866220735786,
      "loss": 2.0339,
      "step": 228
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005958432871476349,
      "loss": 1.9932,
      "step": 229
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005956999522216914,
      "loss": 2.0667,
      "step": 230
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005955566172957476,
      "loss": 1.9975,
      "step": 231
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005954132823698041,
      "loss": 2.1712,
      "step": 232
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005952699474438604,
      "loss": 2.0982,
      "step": 233
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005951266125179169,
      "loss": 2.0666,
      "step": 234
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005949832775919732,
      "loss": 2.0398,
      "step": 235
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005948399426660295,
      "loss": 2.148,
      "step": 236
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005946966077400859,
      "loss": 2.129,
      "step": 237
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005945532728141423,
      "loss": 1.9516,
      "step": 238
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005944099378881987,
      "loss": 2.1107,
      "step": 239
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005942666029622551,
      "loss": 2.0135,
      "step": 240
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0005941232680363115,
      "loss": 2.1016,
      "step": 241
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005939799331103678,
      "loss": 2.1468,
      "step": 242
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005938365981844242,
      "loss": 1.9971,
      "step": 243
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005936932632584806,
      "loss": 1.9989,
      "step": 244
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000593549928332537,
      "loss": 2.0357,
      "step": 245
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005934065934065934,
      "loss": 2.0284,
      "step": 246
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005932632584806498,
      "loss": 1.9888,
      "step": 247
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005931199235547062,
      "loss": 1.9282,
      "step": 248
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005929765886287625,
      "loss": 2.1674,
      "step": 249
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005928332537028188,
      "loss": 2.1181,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005926899187768753,
      "loss": 2.0121,
      "step": 251
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005925465838509316,
      "loss": 2.0473,
      "step": 252
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005924032489249881,
      "loss": 2.1176,
      "step": 253
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005922599139990443,
      "loss": 2.0193,
      "step": 254
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005921165790731007,
      "loss": 2.1572,
      "step": 255
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005919732441471571,
      "loss": 2.0089,
      "step": 256
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005918299092212135,
      "loss": 2.0258,
      "step": 257
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005916865742952699,
      "loss": 2.1088,
      "step": 258
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005915432393693263,
      "loss": 2.0018,
      "step": 259
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005913999044433826,
      "loss": 2.0369,
      "step": 260
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000591256569517439,
      "loss": 2.119,
      "step": 261
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005911132345914954,
      "loss": 2.1527,
      "step": 262
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005909698996655518,
      "loss": 2.0851,
      "step": 263
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005908265647396082,
      "loss": 2.1476,
      "step": 264
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005906832298136646,
      "loss": 2.1613,
      "step": 265
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000590539894887721,
      "loss": 2.2171,
      "step": 266
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005903965599617773,
      "loss": 2.1749,
      "step": 267
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005902532250358337,
      "loss": 2.0579,
      "step": 268
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00059010989010989,
      "loss": 2.0551,
      "step": 269
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0005899665551839465,
      "loss": 2.0846,
      "step": 270
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005898232202580028,
      "loss": 2.03,
      "step": 271
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005896798853320593,
      "loss": 1.9923,
      "step": 272
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005895365504061155,
      "loss": 2.0308,
      "step": 273
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000589393215480172,
      "loss": 1.9601,
      "step": 274
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005892498805542283,
      "loss": 2.0328,
      "step": 275
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005891065456282847,
      "loss": 2.0893,
      "step": 276
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005889632107023411,
      "loss": 2.1038,
      "step": 277
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005888198757763974,
      "loss": 2.0607,
      "step": 278
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005886765408504538,
      "loss": 2.054,
      "step": 279
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005885332059245102,
      "loss": 2.151,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005883898709985666,
      "loss": 2.1348,
      "step": 281
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000588246536072623,
      "loss": 2.0293,
      "step": 282
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005881032011466794,
      "loss": 2.1417,
      "step": 283
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005879598662207358,
      "loss": 1.9914,
      "step": 284
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0005878165312947921,
      "loss": 2.0846,
      "step": 285
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005876731963688485,
      "loss": 2.1063,
      "step": 286
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005875298614429049,
      "loss": 2.0454,
      "step": 287
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005873865265169613,
      "loss": 2.0268,
      "step": 288
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005872431915910177,
      "loss": 2.0762,
      "step": 289
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005870998566650739,
      "loss": 2.0691,
      "step": 290
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005869565217391304,
      "loss": 2.0831,
      "step": 291
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005868131868131867,
      "loss": 2.0361,
      "step": 292
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005866698518872432,
      "loss": 2.041,
      "step": 293
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005865265169612995,
      "loss": 2.0438,
      "step": 294
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000586383182035356,
      "loss": 2.0392,
      "step": 295
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005862398471094122,
      "loss": 2.0769,
      "step": 296
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005860965121834686,
      "loss": 2.0878,
      "step": 297
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000585953177257525,
      "loss": 2.1053,
      "step": 298
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0005858098423315814,
      "loss": 2.1494,
      "step": 299
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005856665074056378,
      "loss": 2.0596,
      "step": 300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005855231724796942,
      "loss": 2.0303,
      "step": 301
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005853798375537506,
      "loss": 2.0842,
      "step": 302
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005852365026278069,
      "loss": 2.1627,
      "step": 303
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005850931677018633,
      "loss": 2.0082,
      "step": 304
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005849498327759197,
      "loss": 2.062,
      "step": 305
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005848064978499761,
      "loss": 2.0595,
      "step": 306
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005846631629240325,
      "loss": 2.0231,
      "step": 307
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005845198279980889,
      "loss": 2.0741,
      "step": 308
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005843764930721452,
      "loss": 2.032,
      "step": 309
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005842331581462016,
      "loss": 2.0719,
      "step": 310
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005840898232202579,
      "loss": 2.2077,
      "step": 311
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005839464882943144,
      "loss": 2.0157,
      "step": 312
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005838031533683707,
      "loss": 2.0623,
      "step": 313
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0005836598184424272,
      "loss": 2.109,
      "step": 314
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005835164835164834,
      "loss": 1.9956,
      "step": 315
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005833731485905399,
      "loss": 2.037,
      "step": 316
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005832298136645962,
      "loss": 2.1446,
      "step": 317
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005830864787386526,
      "loss": 2.1719,
      "step": 318
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000582943143812709,
      "loss": 2.1727,
      "step": 319
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005827998088867654,
      "loss": 2.1275,
      "step": 320
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005826564739608217,
      "loss": 2.0181,
      "step": 321
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005825131390348781,
      "loss": 2.0416,
      "step": 322
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005823698041089345,
      "loss": 2.1615,
      "step": 323
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005822264691829909,
      "loss": 2.1476,
      "step": 324
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005820831342570473,
      "loss": 2.0338,
      "step": 325
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005819397993311037,
      "loss": 2.1117,
      "step": 326
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00058179646440516,
      "loss": 2.0487,
      "step": 327
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005816531294792164,
      "loss": 2.03,
      "step": 328
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0005815097945532728,
      "loss": 2.06,
      "step": 329
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005813664596273292,
      "loss": 2.0517,
      "step": 330
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005812231247013856,
      "loss": 2.1105,
      "step": 331
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005810797897754418,
      "loss": 2.0244,
      "step": 332
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005809364548494983,
      "loss": 2.1025,
      "step": 333
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005807931199235546,
      "loss": 2.0371,
      "step": 334
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005806497849976111,
      "loss": 2.083,
      "step": 335
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005805064500716674,
      "loss": 1.9636,
      "step": 336
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005803631151457239,
      "loss": 2.1417,
      "step": 337
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005802197802197801,
      "loss": 2.0717,
      "step": 338
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005800764452938365,
      "loss": 2.0832,
      "step": 339
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005799331103678929,
      "loss": 2.0748,
      "step": 340
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005797897754419493,
      "loss": 2.086,
      "step": 341
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005796464405160057,
      "loss": 2.075,
      "step": 342
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0005795031055900621,
      "loss": 2.1223,
      "step": 343
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005793597706641185,
      "loss": 2.0627,
      "step": 344
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005792164357381748,
      "loss": 2.069,
      "step": 345
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005790731008122312,
      "loss": 2.1574,
      "step": 346
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005789297658862876,
      "loss": 2.0647,
      "step": 347
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000578786430960344,
      "loss": 2.1713,
      "step": 348
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005786430960344004,
      "loss": 2.0984,
      "step": 349
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005784997611084568,
      "loss": 2.1219,
      "step": 350
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000578356426182513,
      "loss": 1.9956,
      "step": 351
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005782130912565695,
      "loss": 2.1522,
      "step": 352
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005780697563306258,
      "loss": 2.0521,
      "step": 353
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005779264214046823,
      "loss": 1.9579,
      "step": 354
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005777830864787386,
      "loss": 2.0615,
      "step": 355
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005776397515527951,
      "loss": 2.0337,
      "step": 356
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005774964166268513,
      "loss": 2.043,
      "step": 357
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0005773530817009077,
      "loss": 2.0453,
      "step": 358
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005772097467749641,
      "loss": 2.0554,
      "step": 359
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005770664118490205,
      "loss": 2.0509,
      "step": 360
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005769230769230769,
      "loss": 1.9859,
      "step": 361
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005767797419971333,
      "loss": 2.0209,
      "step": 362
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005766364070711896,
      "loss": 1.9763,
      "step": 363
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000576493072145246,
      "loss": 2.1231,
      "step": 364
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005763497372193024,
      "loss": 2.0418,
      "step": 365
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005762064022933588,
      "loss": 1.9824,
      "step": 366
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005760630673674152,
      "loss": 2.1536,
      "step": 367
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005759197324414716,
      "loss": 2.0565,
      "step": 368
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005757763975155279,
      "loss": 2.0413,
      "step": 369
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005756330625895843,
      "loss": 2.0659,
      "step": 370
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0005754897276636407,
      "loss": 2.018,
      "step": 371
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000575346392737697,
      "loss": 2.0262,
      "step": 372
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005752030578117535,
      "loss": 2.1005,
      "step": 373
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005750597228858097,
      "loss": 2.0796,
      "step": 374
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005749163879598662,
      "loss": 2.1344,
      "step": 375
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005747730530339225,
      "loss": 1.9448,
      "step": 376
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005746297181079789,
      "loss": 2.0658,
      "step": 377
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005744863831820353,
      "loss": 2.0931,
      "step": 378
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005743430482560917,
      "loss": 2.1048,
      "step": 379
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000574199713330148,
      "loss": 2.0263,
      "step": 380
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005740563784042044,
      "loss": 2.1217,
      "step": 381
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005739130434782608,
      "loss": 2.1169,
      "step": 382
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005737697085523172,
      "loss": 2.1247,
      "step": 383
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005736263736263736,
      "loss": 2.0325,
      "step": 384
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00057348303870043,
      "loss": 2.0885,
      "step": 385
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005733397037744864,
      "loss": 1.9968,
      "step": 386
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0005731963688485427,
      "loss": 2.0911,
      "step": 387
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005730530339225991,
      "loss": 2.0654,
      "step": 388
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005729096989966555,
      "loss": 2.1938,
      "step": 389
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005727663640707119,
      "loss": 2.1723,
      "step": 390
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005726230291447683,
      "loss": 2.0289,
      "step": 391
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005724796942188245,
      "loss": 2.1383,
      "step": 392
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005723363592928809,
      "loss": 2.1457,
      "step": 393
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005721930243669373,
      "loss": 2.0625,
      "step": 394
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005720496894409937,
      "loss": 2.0906,
      "step": 395
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005719063545150501,
      "loss": 2.0087,
      "step": 396
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005717630195891065,
      "loss": 2.1128,
      "step": 397
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005716196846631629,
      "loss": 2.1217,
      "step": 398
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005714763497372192,
      "loss": 2.1162,
      "step": 399
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005713330148112756,
      "loss": 2.1342,
      "step": 400
    },
    {
      "epoch": 0.27,
      "eval_loss": 2.0627405643463135,
      "eval_runtime": 1739.0775,
      "eval_samples_per_second": 5.75,
      "eval_steps_per_second": 5.75,
      "step": 400
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000571189679885332,
      "loss": 2.1854,
      "step": 401
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0005710463449593884,
      "loss": 2.1751,
      "step": 402
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005709030100334448,
      "loss": 2.2177,
      "step": 403
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005707596751075012,
      "loss": 2.1151,
      "step": 404
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005706163401815575,
      "loss": 2.1397,
      "step": 405
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005704730052556139,
      "loss": 2.1307,
      "step": 406
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005703296703296703,
      "loss": 2.1163,
      "step": 407
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005701863354037267,
      "loss": 2.2228,
      "step": 408
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000570043000477783,
      "loss": 2.0841,
      "step": 409
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005698996655518395,
      "loss": 2.2314,
      "step": 410
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005697563306258957,
      "loss": 2.2701,
      "step": 411
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005696129956999522,
      "loss": 2.1293,
      "step": 412
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005694696607740085,
      "loss": 2.1884,
      "step": 413
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005693263258480649,
      "loss": 2.1422,
      "step": 414
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005691829909221213,
      "loss": 2.1939,
      "step": 415
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0005690396559961777,
      "loss": 2.1862,
      "step": 416
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000568896321070234,
      "loss": 2.2965,
      "step": 417
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005687529861442904,
      "loss": 2.2042,
      "step": 418
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005686096512183468,
      "loss": 2.1242,
      "step": 419
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005684663162924032,
      "loss": 2.1837,
      "step": 420
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005683229813664596,
      "loss": 2.1068,
      "step": 421
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000568179646440516,
      "loss": 2.2236,
      "step": 422
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005680363115145723,
      "loss": 2.1684,
      "step": 423
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005678929765886287,
      "loss": 2.1441,
      "step": 424
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005677496416626851,
      "loss": 2.1091,
      "step": 425
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005676063067367415,
      "loss": 2.2047,
      "step": 426
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005674629718107979,
      "loss": 2.1858,
      "step": 427
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005673196368848541,
      "loss": 2.141,
      "step": 428
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005671763019589106,
      "loss": 2.1447,
      "step": 429
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005670329670329669,
      "loss": 2.1216,
      "step": 430
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0005668896321070234,
      "loss": 2.1843,
      "step": 431
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005667462971810797,
      "loss": 2.3159,
      "step": 432
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005666029622551362,
      "loss": 2.2143,
      "step": 433
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005664596273291925,
      "loss": 2.1456,
      "step": 434
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005663162924032488,
      "loss": 2.1061,
      "step": 435
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005661729574773052,
      "loss": 2.2449,
      "step": 436
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005660296225513616,
      "loss": 2.1625,
      "step": 437
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000565886287625418,
      "loss": 2.1141,
      "step": 438
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005657429526994744,
      "loss": 2.1314,
      "step": 439
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005655996177735308,
      "loss": 2.1726,
      "step": 440
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005654562828475871,
      "loss": 2.1889,
      "step": 441
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005653129479216435,
      "loss": 2.2172,
      "step": 442
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005651696129956999,
      "loss": 2.1766,
      "step": 443
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005650262780697563,
      "loss": 2.0534,
      "step": 444
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005648829431438127,
      "loss": 2.1665,
      "step": 445
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0005647396082178691,
      "loss": 2.1383,
      "step": 446
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005645962732919254,
      "loss": 2.1737,
      "step": 447
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005644529383659818,
      "loss": 2.1792,
      "step": 448
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005643096034400381,
      "loss": 2.2596,
      "step": 449
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005641662685140946,
      "loss": 2.1804,
      "step": 450
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005640229335881509,
      "loss": 2.0674,
      "step": 451
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005638795986622074,
      "loss": 2.0845,
      "step": 452
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005637362637362636,
      "loss": 2.0754,
      "step": 453
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00056359292881032,
      "loss": 2.1973,
      "step": 454
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005634495938843764,
      "loss": 2.1183,
      "step": 455
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005633062589584328,
      "loss": 2.1111,
      "step": 456
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005631629240324892,
      "loss": 2.1094,
      "step": 457
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005630195891065456,
      "loss": 2.0889,
      "step": 458
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005628762541806019,
      "loss": 2.2136,
      "step": 459
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0005627329192546583,
      "loss": 2.1521,
      "step": 460
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005625895843287147,
      "loss": 2.1277,
      "step": 461
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005624462494027711,
      "loss": 2.2086,
      "step": 462
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005623029144768275,
      "loss": 2.139,
      "step": 463
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005621595795508839,
      "loss": 2.0627,
      "step": 464
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005620162446249402,
      "loss": 2.2356,
      "step": 465
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005618729096989966,
      "loss": 2.2947,
      "step": 466
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000561729574773053,
      "loss": 2.1619,
      "step": 467
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005615862398471093,
      "loss": 2.2515,
      "step": 468
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005614429049211658,
      "loss": 2.1746,
      "step": 469
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000561299569995222,
      "loss": 2.259,
      "step": 470
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005611562350692785,
      "loss": 2.2093,
      "step": 471
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005610129001433348,
      "loss": 2.2077,
      "step": 472
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005608695652173913,
      "loss": 2.2464,
      "step": 473
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0005607262302914476,
      "loss": 2.0556,
      "step": 474
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000560582895365504,
      "loss": 2.135,
      "step": 475
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005604395604395604,
      "loss": 2.1812,
      "step": 476
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005602962255136167,
      "loss": 2.1082,
      "step": 477
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005601528905876731,
      "loss": 2.0997,
      "step": 478
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005600095556617295,
      "loss": 2.1532,
      "step": 479
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005598662207357859,
      "loss": 2.1389,
      "step": 480
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005597228858098423,
      "loss": 2.1122,
      "step": 481
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005595795508838987,
      "loss": 2.1091,
      "step": 482
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000559436215957955,
      "loss": 2.1699,
      "step": 483
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005592928810320114,
      "loss": 2.1043,
      "step": 484
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005591495461060678,
      "loss": 2.143,
      "step": 485
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005590062111801242,
      "loss": 2.1184,
      "step": 486
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005588628762541806,
      "loss": 2.0185,
      "step": 487
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000558719541328237,
      "loss": 2.2015,
      "step": 488
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0005585762064022932,
      "loss": 2.2501,
      "step": 489
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005584328714763497,
      "loss": 2.1088,
      "step": 490
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000558289536550406,
      "loss": 2.0932,
      "step": 491
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005581462016244625,
      "loss": 2.1717,
      "step": 492
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005580028666985188,
      "loss": 2.1509,
      "step": 493
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005578595317725753,
      "loss": 2.1354,
      "step": 494
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005577161968466315,
      "loss": 2.2007,
      "step": 495
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005575728619206879,
      "loss": 2.0769,
      "step": 496
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005574295269947443,
      "loss": 2.1375,
      "step": 497
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005572861920688007,
      "loss": 2.1743,
      "step": 498
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005571428571428571,
      "loss": 2.1998,
      "step": 499
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005569995222169135,
      "loss": 2.2041,
      "step": 500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005568561872909698,
      "loss": 2.1778,
      "step": 501
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005567128523650262,
      "loss": 2.2309,
      "step": 502
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0005565695174390826,
      "loss": 2.1322,
      "step": 503
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000556426182513139,
      "loss": 2.1951,
      "step": 504
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005562828475871954,
      "loss": 2.2756,
      "step": 505
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005561395126612518,
      "loss": 2.0972,
      "step": 506
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005559961777353081,
      "loss": 2.138,
      "step": 507
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005558528428093645,
      "loss": 2.1627,
      "step": 508
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005557095078834209,
      "loss": 2.1876,
      "step": 509
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005555661729574772,
      "loss": 2.1359,
      "step": 510
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005554228380315337,
      "loss": 2.2495,
      "step": 511
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00055527950310559,
      "loss": 2.1951,
      "step": 512
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005551361681796464,
      "loss": 2.1939,
      "step": 513
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005549928332537027,
      "loss": 2.12,
      "step": 514
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005548494983277592,
      "loss": 2.1258,
      "step": 515
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005547061634018155,
      "loss": 2.2273,
      "step": 516
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005545628284758719,
      "loss": 2.1856,
      "step": 517
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005544194935499283,
      "loss": 2.0875,
      "step": 518
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0005542761586239846,
      "loss": 2.0916,
      "step": 519
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000554132823698041,
      "loss": 2.094,
      "step": 520
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005539894887720974,
      "loss": 2.1244,
      "step": 521
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005538461538461538,
      "loss": 2.1668,
      "step": 522
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005537028189202102,
      "loss": 2.1785,
      "step": 523
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005535594839942666,
      "loss": 2.1497,
      "step": 524
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005534161490683229,
      "loss": 2.2136,
      "step": 525
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005532728141423793,
      "loss": 2.1554,
      "step": 526
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005531294792164357,
      "loss": 2.1288,
      "step": 527
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005529861442904921,
      "loss": 2.1221,
      "step": 528
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005528428093645485,
      "loss": 2.1583,
      "step": 529
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005526994744386049,
      "loss": 2.1514,
      "step": 530
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005525561395126611,
      "loss": 2.2256,
      "step": 531
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005524128045867176,
      "loss": 2.1435,
      "step": 532
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0005522694696607739,
      "loss": 2.169,
      "step": 533
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005521261347348304,
      "loss": 2.1734,
      "step": 534
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005519827998088867,
      "loss": 2.0882,
      "step": 535
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005518394648829432,
      "loss": 2.1364,
      "step": 536
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005516961299569994,
      "loss": 2.1544,
      "step": 537
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005515527950310558,
      "loss": 2.1356,
      "step": 538
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005514094601051122,
      "loss": 2.019,
      "step": 539
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005512661251791686,
      "loss": 2.1198,
      "step": 540
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000551122790253225,
      "loss": 2.1896,
      "step": 541
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005509794553272814,
      "loss": 2.1615,
      "step": 542
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005508361204013377,
      "loss": 2.1163,
      "step": 543
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005506927854753941,
      "loss": 2.2056,
      "step": 544
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005505494505494505,
      "loss": 2.2128,
      "step": 545
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005504061156235069,
      "loss": 2.195,
      "step": 546
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005502627806975633,
      "loss": 2.0768,
      "step": 547
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0005501194457716197,
      "loss": 2.1667,
      "step": 548
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000549976110845676,
      "loss": 2.1035,
      "step": 549
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005498327759197323,
      "loss": 2.1628,
      "step": 550
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005496894409937888,
      "loss": 2.1491,
      "step": 551
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005495461060678451,
      "loss": 2.0676,
      "step": 552
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005494027711419016,
      "loss": 2.3462,
      "step": 553
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005492594362159579,
      "loss": 2.107,
      "step": 554
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005491161012900143,
      "loss": 2.1844,
      "step": 555
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005489727663640706,
      "loss": 2.1328,
      "step": 556
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000548829431438127,
      "loss": 2.1467,
      "step": 557
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005486860965121834,
      "loss": 2.1706,
      "step": 558
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005485427615862398,
      "loss": 2.1649,
      "step": 559
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005483994266602962,
      "loss": 2.154,
      "step": 560
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005482560917343525,
      "loss": 2.1095,
      "step": 561
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005481127568084089,
      "loss": 2.1706,
      "step": 562
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0005479694218824653,
      "loss": 2.2179,
      "step": 563
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005478260869565217,
      "loss": 2.2188,
      "step": 564
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005476827520305781,
      "loss": 2.1167,
      "step": 565
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005475394171046345,
      "loss": 2.1275,
      "step": 566
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005473960821786908,
      "loss": 2.0766,
      "step": 567
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005472527472527472,
      "loss": 2.1719,
      "step": 568
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005471094123268036,
      "loss": 2.2378,
      "step": 569
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00054696607740086,
      "loss": 2.1612,
      "step": 570
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005468227424749163,
      "loss": 2.0903,
      "step": 571
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005466794075489728,
      "loss": 2.2279,
      "step": 572
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000546536072623029,
      "loss": 2.1084,
      "step": 573
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005463927376970855,
      "loss": 2.1652,
      "step": 574
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005462494027711418,
      "loss": 2.1035,
      "step": 575
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005461060678451983,
      "loss": 2.2028,
      "step": 576
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0005459627329192546,
      "loss": 2.2347,
      "step": 577
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000545819397993311,
      "loss": 2.1609,
      "step": 578
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005456760630673673,
      "loss": 2.0815,
      "step": 579
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005455327281414237,
      "loss": 2.0575,
      "step": 580
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005453893932154801,
      "loss": 2.1104,
      "step": 581
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005452460582895365,
      "loss": 2.1784,
      "step": 582
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005451027233635929,
      "loss": 2.117,
      "step": 583
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005449593884376493,
      "loss": 2.0947,
      "step": 584
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005448160535117056,
      "loss": 2.1204,
      "step": 585
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000544672718585762,
      "loss": 2.0614,
      "step": 586
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005445293836598184,
      "loss": 2.1227,
      "step": 587
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005443860487338748,
      "loss": 2.1831,
      "step": 588
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005442427138079312,
      "loss": 2.2267,
      "step": 589
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005440993788819876,
      "loss": 2.1008,
      "step": 590
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005439560439560439,
      "loss": 2.1126,
      "step": 591
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0005438127090301002,
      "loss": 2.2081,
      "step": 592
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005436693741041567,
      "loss": 2.2372,
      "step": 593
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000543526039178213,
      "loss": 2.1783,
      "step": 594
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005433827042522695,
      "loss": 2.1631,
      "step": 595
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005432393693263258,
      "loss": 2.2263,
      "step": 596
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005430960344003822,
      "loss": 2.2438,
      "step": 597
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005429526994744385,
      "loss": 2.125,
      "step": 598
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005428093645484949,
      "loss": 2.1655,
      "step": 599
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005426660296225513,
      "loss": 2.241,
      "step": 600
    },
    {
      "epoch": 0.41,
      "eval_loss": 2.047600030899048,
      "eval_runtime": 1736.5603,
      "eval_samples_per_second": 5.759,
      "eval_steps_per_second": 5.759,
      "step": 600
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005425226946966077,
      "loss": 2.0728,
      "step": 601
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005423793597706641,
      "loss": 2.051,
      "step": 602
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005422360248447204,
      "loss": 2.1657,
      "step": 603
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005420926899187768,
      "loss": 2.1084,
      "step": 604
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005419493549928332,
      "loss": 2.1312,
      "step": 605
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005418060200668896,
      "loss": 2.0724,
      "step": 606
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000541662685140946,
      "loss": 2.0999,
      "step": 607
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005415193502150024,
      "loss": 2.1649,
      "step": 608
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005413760152890587,
      "loss": 2.1458,
      "step": 609
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005412326803631151,
      "loss": 2.071,
      "step": 610
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005410893454371715,
      "loss": 2.1931,
      "step": 611
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005409460105112279,
      "loss": 2.1968,
      "step": 612
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005408026755852842,
      "loss": 2.105,
      "step": 613
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005406593406593407,
      "loss": 2.1429,
      "step": 614
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005405160057333969,
      "loss": 2.0812,
      "step": 615
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005403726708074534,
      "loss": 2.1389,
      "step": 616
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005402293358815097,
      "loss": 2.1685,
      "step": 617
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005400860009555662,
      "loss": 2.2248,
      "step": 618
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005399426660296225,
      "loss": 2.1771,
      "step": 619
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005397993311036789,
      "loss": 2.1094,
      "step": 620
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005396559961777352,
      "loss": 2.141,
      "step": 621
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005395126612517916,
      "loss": 2.2442,
      "step": 622
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000539369326325848,
      "loss": 2.1703,
      "step": 623
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005392259913999044,
      "loss": 2.1351,
      "step": 624
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005390826564739608,
      "loss": 2.2008,
      "step": 625
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005389393215480172,
      "loss": 2.2114,
      "step": 626
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005387959866220735,
      "loss": 2.1368,
      "step": 627
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005386526516961299,
      "loss": 2.2127,
      "step": 628
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005385093167701863,
      "loss": 2.2554,
      "step": 629
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005383659818442427,
      "loss": 2.143,
      "step": 630
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005382226469182991,
      "loss": 2.1306,
      "step": 631
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005380793119923555,
      "loss": 2.1257,
      "step": 632
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005379359770664118,
      "loss": 2.2013,
      "step": 633
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005377926421404681,
      "loss": 2.1856,
      "step": 634
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005376493072145246,
      "loss": 2.1917,
      "step": 635
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0005375059722885809,
      "loss": 2.1044,
      "step": 636
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005373626373626374,
      "loss": 2.1909,
      "step": 637
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005372193024366937,
      "loss": 2.0706,
      "step": 638
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005370759675107501,
      "loss": 2.142,
      "step": 639
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005369326325848064,
      "loss": 2.1813,
      "step": 640
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005367892976588628,
      "loss": 2.1802,
      "step": 641
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005366459627329192,
      "loss": 2.1461,
      "step": 642
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005365026278069756,
      "loss": 2.045,
      "step": 643
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000536359292881032,
      "loss": 2.1449,
      "step": 644
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005362159579550883,
      "loss": 2.0893,
      "step": 645
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005360726230291447,
      "loss": 2.1477,
      "step": 646
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005359292881032011,
      "loss": 2.172,
      "step": 647
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005357859531772575,
      "loss": 2.2154,
      "step": 648
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005356426182513139,
      "loss": 2.0651,
      "step": 649
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0005354992833253703,
      "loss": 2.2091,
      "step": 650
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005353559483994266,
      "loss": 2.1892,
      "step": 651
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000535212613473483,
      "loss": 2.1727,
      "step": 652
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005350692785475393,
      "loss": 2.1532,
      "step": 653
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005349259436215958,
      "loss": 2.0929,
      "step": 654
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005347826086956521,
      "loss": 2.1364,
      "step": 655
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005346392737697086,
      "loss": 2.1704,
      "step": 656
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005344959388437648,
      "loss": 2.116,
      "step": 657
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005343526039178213,
      "loss": 2.2498,
      "step": 658
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005342092689918776,
      "loss": 2.2484,
      "step": 659
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000534065934065934,
      "loss": 2.0954,
      "step": 660
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005339225991399904,
      "loss": 2.1747,
      "step": 661
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005337792642140468,
      "loss": 2.1775,
      "step": 662
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005336359292881031,
      "loss": 2.2085,
      "step": 663
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005334925943621595,
      "loss": 2.1576,
      "step": 664
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0005333492594362159,
      "loss": 2.1618,
      "step": 665
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005332059245102723,
      "loss": 2.1005,
      "step": 666
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005330625895843287,
      "loss": 2.1803,
      "step": 667
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005329192546583851,
      "loss": 2.036,
      "step": 668
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005327759197324414,
      "loss": 2.1275,
      "step": 669
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005326325848064978,
      "loss": 2.1677,
      "step": 670
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005324892498805542,
      "loss": 2.1649,
      "step": 671
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005323459149546106,
      "loss": 2.1187,
      "step": 672
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000532202580028667,
      "loss": 2.0904,
      "step": 673
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005320592451027233,
      "loss": 2.1749,
      "step": 674
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005319159101767797,
      "loss": 2.1062,
      "step": 675
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000531772575250836,
      "loss": 2.1854,
      "step": 676
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005316292403248925,
      "loss": 2.1493,
      "step": 677
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005314859053989488,
      "loss": 2.2119,
      "step": 678
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005313425704730053,
      "loss": 2.104,
      "step": 679
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005311992355470616,
      "loss": 2.2132,
      "step": 680
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005310559006211179,
      "loss": 2.2275,
      "step": 681
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005309125656951743,
      "loss": 2.146,
      "step": 682
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005307692307692307,
      "loss": 2.2401,
      "step": 683
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005306258958432871,
      "loss": 2.1453,
      "step": 684
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005304825609173435,
      "loss": 2.1154,
      "step": 685
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005303392259913999,
      "loss": 2.2073,
      "step": 686
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005301958910654562,
      "loss": 2.3166,
      "step": 687
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005300525561395126,
      "loss": 2.1223,
      "step": 688
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000529909221213569,
      "loss": 2.1857,
      "step": 689
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005297658862876254,
      "loss": 2.1932,
      "step": 690
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005296225513616818,
      "loss": 2.1361,
      "step": 691
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005294792164357382,
      "loss": 2.1133,
      "step": 692
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005293358815097945,
      "loss": 2.137,
      "step": 693
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0005291925465838509,
      "loss": 2.1077,
      "step": 694
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005290492116579072,
      "loss": 2.2026,
      "step": 695
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005289058767319637,
      "loss": 2.1443,
      "step": 696
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00052876254180602,
      "loss": 2.0933,
      "step": 697
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005286192068800765,
      "loss": 2.1728,
      "step": 698
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005284758719541327,
      "loss": 2.1026,
      "step": 699
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005283325370281892,
      "loss": 2.1373,
      "step": 700
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005281892021022455,
      "loss": 2.0439,
      "step": 701
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005280458671763019,
      "loss": 2.1893,
      "step": 702
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005279025322503583,
      "loss": 2.2672,
      "step": 703
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005277591973244147,
      "loss": 2.176,
      "step": 704
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000527615862398471,
      "loss": 2.1351,
      "step": 705
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005274725274725274,
      "loss": 2.0995,
      "step": 706
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005273291925465838,
      "loss": 2.1155,
      "step": 707
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005271858576206402,
      "loss": 2.1424,
      "step": 708
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0005270425226946966,
      "loss": 2.2112,
      "step": 709
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000526899187768753,
      "loss": 2.1792,
      "step": 710
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005267558528428093,
      "loss": 2.133,
      "step": 711
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005266125179168657,
      "loss": 2.1542,
      "step": 712
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005264691829909221,
      "loss": 2.1184,
      "step": 713
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005263258480649785,
      "loss": 2.0157,
      "step": 714
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005261825131390349,
      "loss": 2.1661,
      "step": 715
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005260391782130912,
      "loss": 2.2518,
      "step": 716
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005258958432871477,
      "loss": 2.0832,
      "step": 717
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005257525083612039,
      "loss": 2.2078,
      "step": 718
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005256091734352604,
      "loss": 2.085,
      "step": 719
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005254658385093167,
      "loss": 2.1,
      "step": 720
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005253225035833732,
      "loss": 2.0984,
      "step": 721
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005251791686574295,
      "loss": 2.1313,
      "step": 722
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005250358337314858,
      "loss": 2.0344,
      "step": 723
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0005248924988055422,
      "loss": 2.2206,
      "step": 724
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005247491638795986,
      "loss": 2.2121,
      "step": 725
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000524605828953655,
      "loss": 2.1267,
      "step": 726
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005244624940277114,
      "loss": 2.0358,
      "step": 727
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005243191591017678,
      "loss": 2.1301,
      "step": 728
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005241758241758241,
      "loss": 2.1678,
      "step": 729
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005240324892498805,
      "loss": 2.0717,
      "step": 730
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005238891543239369,
      "loss": 2.1041,
      "step": 731
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005237458193979933,
      "loss": 2.1661,
      "step": 732
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005236024844720497,
      "loss": 2.2038,
      "step": 733
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005234591495461061,
      "loss": 2.0797,
      "step": 734
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005233158146201624,
      "loss": 1.9513,
      "step": 735
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005231724796942188,
      "loss": 2.0952,
      "step": 736
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005230291447682751,
      "loss": 2.0112,
      "step": 737
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0005228858098423316,
      "loss": 2.1552,
      "step": 738
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005227424749163879,
      "loss": 2.1163,
      "step": 739
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005225991399904444,
      "loss": 2.1879,
      "step": 740
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005224558050645006,
      "loss": 2.1494,
      "step": 741
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000522312470138557,
      "loss": 2.1554,
      "step": 742
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005221691352126134,
      "loss": 2.1672,
      "step": 743
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005220258002866698,
      "loss": 2.1297,
      "step": 744
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005218824653607262,
      "loss": 2.1553,
      "step": 745
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005217391304347826,
      "loss": 2.1184,
      "step": 746
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000521595795508839,
      "loss": 2.1945,
      "step": 747
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005214524605828953,
      "loss": 2.1973,
      "step": 748
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005213091256569517,
      "loss": 2.076,
      "step": 749
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005211657907310081,
      "loss": 2.1019,
      "step": 750
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005210224558050645,
      "loss": 2.1234,
      "step": 751
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005208791208791209,
      "loss": 2.221,
      "step": 752
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0005207357859531772,
      "loss": 2.0994,
      "step": 753
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005205924510272336,
      "loss": 2.0699,
      "step": 754
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00052044911610129,
      "loss": 2.1554,
      "step": 755
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005203057811753463,
      "loss": 2.1254,
      "step": 756
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005201624462494028,
      "loss": 2.2119,
      "step": 757
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005200191113234591,
      "loss": 2.0509,
      "step": 758
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005198757763975154,
      "loss": 2.2616,
      "step": 759
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005197324414715718,
      "loss": 2.0417,
      "step": 760
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005195891065456282,
      "loss": 2.1356,
      "step": 761
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005194457716196846,
      "loss": 2.0701,
      "step": 762
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000519302436693741,
      "loss": 2.1677,
      "step": 763
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005191591017677974,
      "loss": 2.0766,
      "step": 764
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005190157668418537,
      "loss": 2.1733,
      "step": 765
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005188724319159101,
      "loss": 2.1307,
      "step": 766
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0005187290969899665,
      "loss": 2.0885,
      "step": 767
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005185857620640229,
      "loss": 2.1836,
      "step": 768
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005184424271380793,
      "loss": 2.1477,
      "step": 769
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005182990922121357,
      "loss": 2.1539,
      "step": 770
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000518155757286192,
      "loss": 2.1302,
      "step": 771
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005180124223602484,
      "loss": 2.1686,
      "step": 772
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005178690874343048,
      "loss": 2.1822,
      "step": 773
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005177257525083612,
      "loss": 2.1349,
      "step": 774
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005175824175824176,
      "loss": 2.1254,
      "step": 775
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005174390826564739,
      "loss": 2.1617,
      "step": 776
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005172957477305302,
      "loss": 2.0366,
      "step": 777
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005171524128045866,
      "loss": 2.1776,
      "step": 778
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000517009077878643,
      "loss": 2.0636,
      "step": 779
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005168657429526994,
      "loss": 2.0966,
      "step": 780
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005167224080267558,
      "loss": 2.0935,
      "step": 781
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0005165790731008122,
      "loss": 2.0194,
      "step": 782
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005164357381748685,
      "loss": 2.1995,
      "step": 783
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005162924032489249,
      "loss": 2.0758,
      "step": 784
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005161490683229813,
      "loss": 2.134,
      "step": 785
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005160057333970377,
      "loss": 2.1708,
      "step": 786
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005158623984710941,
      "loss": 2.155,
      "step": 787
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005157190635451505,
      "loss": 2.2275,
      "step": 788
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005155757286192068,
      "loss": 2.151,
      "step": 789
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005154323936932632,
      "loss": 2.1853,
      "step": 790
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005152890587673196,
      "loss": 2.1455,
      "step": 791
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000515145723841376,
      "loss": 2.1934,
      "step": 792
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005150023889154323,
      "loss": 2.0501,
      "step": 793
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005148590539894888,
      "loss": 2.197,
      "step": 794
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000514715719063545,
      "loss": 2.0713,
      "step": 795
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005145723841376015,
      "loss": 2.1562,
      "step": 796
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0005144290492116578,
      "loss": 2.158,
      "step": 797
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005142857142857142,
      "loss": 2.0456,
      "step": 798
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005141423793597706,
      "loss": 2.157,
      "step": 799
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000513999044433827,
      "loss": 2.0934,
      "step": 800
    },
    {
      "epoch": 0.55,
      "eval_loss": 2.0316452980041504,
      "eval_runtime": 1689.8048,
      "eval_samples_per_second": 5.918,
      "eval_steps_per_second": 5.918,
      "step": 800
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005138557095078833,
      "loss": 2.1501,
      "step": 801
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005137123745819397,
      "loss": 2.0977,
      "step": 802
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005135690396559961,
      "loss": 2.2608,
      "step": 803
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005134257047300525,
      "loss": 2.0765,
      "step": 804
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005132823698041089,
      "loss": 2.1414,
      "step": 805
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005131390348781653,
      "loss": 2.2186,
      "step": 806
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005129956999522216,
      "loss": 2.1596,
      "step": 807
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000512852365026278,
      "loss": 2.1241,
      "step": 808
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005127090301003344,
      "loss": 2.0742,
      "step": 809
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005125656951743908,
      "loss": 2.0797,
      "step": 810
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0005124223602484472,
      "loss": 2.1866,
      "step": 811
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005122790253225035,
      "loss": 2.1895,
      "step": 812
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00051213569039656,
      "loss": 2.0698,
      "step": 813
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005119923554706162,
      "loss": 2.1982,
      "step": 814
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005118490205446727,
      "loss": 2.1768,
      "step": 815
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.000511705685618729,
      "loss": 2.0943,
      "step": 816
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005115623506927855,
      "loss": 2.067,
      "step": 817
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005114190157668418,
      "loss": 2.0416,
      "step": 818
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005112756808408981,
      "loss": 2.1266,
      "step": 819
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005111323459149545,
      "loss": 2.1835,
      "step": 820
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005109890109890109,
      "loss": 2.1033,
      "step": 821
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005108456760630673,
      "loss": 2.1953,
      "step": 822
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005107023411371237,
      "loss": 2.2002,
      "step": 823
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005105590062111801,
      "loss": 2.0887,
      "step": 824
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005104156712852364,
      "loss": 2.1419,
      "step": 825
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0005102723363592928,
      "loss": 2.0993,
      "step": 826
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005101290014333492,
      "loss": 2.1632,
      "step": 827
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005099856665074056,
      "loss": 2.11,
      "step": 828
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000509842331581462,
      "loss": 2.1375,
      "step": 829
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005096989966555184,
      "loss": 2.0241,
      "step": 830
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005095556617295748,
      "loss": 1.9997,
      "step": 831
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005094123268036311,
      "loss": 2.095,
      "step": 832
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005092689918776874,
      "loss": 2.114,
      "step": 833
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005091256569517439,
      "loss": 2.0887,
      "step": 834
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005089823220258002,
      "loss": 2.1666,
      "step": 835
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005088389870998567,
      "loss": 2.1407,
      "step": 836
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005086956521739129,
      "loss": 2.2634,
      "step": 837
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005085523172479694,
      "loss": 2.2145,
      "step": 838
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005084089823220257,
      "loss": 2.0569,
      "step": 839
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005082656473960821,
      "loss": 2.1156,
      "step": 840
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0005081223124701385,
      "loss": 2.1948,
      "step": 841
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005079789775441949,
      "loss": 2.1315,
      "step": 842
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005078356426182512,
      "loss": 2.1392,
      "step": 843
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005076923076923076,
      "loss": 2.1225,
      "step": 844
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000507548972766364,
      "loss": 2.1076,
      "step": 845
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005074056378404204,
      "loss": 2.0865,
      "step": 846
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005072623029144768,
      "loss": 2.159,
      "step": 847
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005071189679885332,
      "loss": 2.0958,
      "step": 848
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005069756330625896,
      "loss": 2.1292,
      "step": 849
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005068322981366459,
      "loss": 2.1155,
      "step": 850
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005066889632107023,
      "loss": 2.0926,
      "step": 851
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005065456282847586,
      "loss": 2.1385,
      "step": 852
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005064022933588151,
      "loss": 2.1187,
      "step": 853
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005062589584328714,
      "loss": 2.0747,
      "step": 854
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0005061156235069279,
      "loss": 2.147,
      "step": 855
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005059722885809841,
      "loss": 2.2023,
      "step": 856
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005058289536550406,
      "loss": 2.0863,
      "step": 857
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005056856187290969,
      "loss": 2.1402,
      "step": 858
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005055422838031533,
      "loss": 2.1758,
      "step": 859
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005053989488772097,
      "loss": 2.1767,
      "step": 860
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000505255613951266,
      "loss": 2.2041,
      "step": 861
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005051122790253224,
      "loss": 2.1227,
      "step": 862
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005049689440993788,
      "loss": 2.1992,
      "step": 863
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005048256091734352,
      "loss": 2.0532,
      "step": 864
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005046822742474916,
      "loss": 2.1845,
      "step": 865
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000504538939321548,
      "loss": 2.1466,
      "step": 866
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005043956043956043,
      "loss": 2.0371,
      "step": 867
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005042522694696607,
      "loss": 2.0987,
      "step": 868
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005041089345437171,
      "loss": 2.1345,
      "step": 869
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0005039655996177735,
      "loss": 2.2204,
      "step": 870
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005038222646918299,
      "loss": 2.1403,
      "step": 871
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005036789297658863,
      "loss": 2.0582,
      "step": 872
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005035355948399425,
      "loss": 2.1603,
      "step": 873
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000503392259913999,
      "loss": 2.0686,
      "step": 874
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005032489249880553,
      "loss": 2.0596,
      "step": 875
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005031055900621118,
      "loss": 2.1168,
      "step": 876
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005029622551361681,
      "loss": 2.19,
      "step": 877
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005028189202102246,
      "loss": 2.2216,
      "step": 878
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005026755852842808,
      "loss": 2.1723,
      "step": 879
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005025322503583372,
      "loss": 2.1189,
      "step": 880
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005023889154323936,
      "loss": 2.1425,
      "step": 881
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00050224558050645,
      "loss": 2.2003,
      "step": 882
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005021022455805064,
      "loss": 2.211,
      "step": 883
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0005019589106545628,
      "loss": 2.1302,
      "step": 884
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005018155757286191,
      "loss": 2.1729,
      "step": 885
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005016722408026755,
      "loss": 2.1203,
      "step": 886
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005015289058767319,
      "loss": 2.0511,
      "step": 887
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005013855709507883,
      "loss": 1.9758,
      "step": 888
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005012422360248447,
      "loss": 2.1151,
      "step": 889
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005010989010989011,
      "loss": 2.0998,
      "step": 890
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005009555661729575,
      "loss": 2.0739,
      "step": 891
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005008122312470138,
      "loss": 2.0421,
      "step": 892
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005006688963210702,
      "loss": 2.0808,
      "step": 893
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005005255613951265,
      "loss": 2.1301,
      "step": 894
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000500382226469183,
      "loss": 2.1207,
      "step": 895
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005002388915432393,
      "loss": 2.1089,
      "step": 896
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0005000955566172958,
      "loss": 2.1796,
      "step": 897
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000499952221691352,
      "loss": 2.1123,
      "step": 898
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0004998088867654085,
      "loss": 2.1304,
      "step": 899
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004996655518394648,
      "loss": 2.0691,
      "step": 900
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004995222169135212,
      "loss": 2.215,
      "step": 901
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004993788819875776,
      "loss": 2.1303,
      "step": 902
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000499235547061634,
      "loss": 2.0983,
      "step": 903
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004990922121356903,
      "loss": 2.0761,
      "step": 904
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004989488772097467,
      "loss": 2.1889,
      "step": 905
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004988055422838031,
      "loss": 2.0557,
      "step": 906
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004986622073578595,
      "loss": 2.1591,
      "step": 907
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004985188724319159,
      "loss": 2.1217,
      "step": 908
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004983755375059723,
      "loss": 2.0165,
      "step": 909
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004982322025800286,
      "loss": 2.2102,
      "step": 910
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000498088867654085,
      "loss": 2.187,
      "step": 911
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004979455327281414,
      "loss": 2.0758,
      "step": 912
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004978021978021978,
      "loss": 2.2606,
      "step": 913
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0004976588628762542,
      "loss": 1.9795,
      "step": 914
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004975155279503104,
      "loss": 2.1235,
      "step": 915
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004973721930243669,
      "loss": 2.2042,
      "step": 916
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004972288580984232,
      "loss": 2.1169,
      "step": 917
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004970855231724797,
      "loss": 2.082,
      "step": 918
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000496942188246536,
      "loss": 2.0924,
      "step": 919
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004967988533205925,
      "loss": 2.1969,
      "step": 920
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004966555183946487,
      "loss": 2.1238,
      "step": 921
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004965121834687051,
      "loss": 2.1776,
      "step": 922
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004963688485427615,
      "loss": 2.1328,
      "step": 923
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004962255136168179,
      "loss": 2.0723,
      "step": 924
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004960821786908743,
      "loss": 2.2225,
      "step": 925
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004959388437649307,
      "loss": 2.1698,
      "step": 926
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000495795508838987,
      "loss": 2.1764,
      "step": 927
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0004956521739130434,
      "loss": 2.2167,
      "step": 928
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004955088389870998,
      "loss": 2.2408,
      "step": 929
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004953655040611562,
      "loss": 2.049,
      "step": 930
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004952221691352126,
      "loss": 2.0461,
      "step": 931
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000495078834209269,
      "loss": 2.1895,
      "step": 932
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004949354992833254,
      "loss": 2.1358,
      "step": 933
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004947921643573817,
      "loss": 2.1586,
      "step": 934
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004946488294314381,
      "loss": 2.0463,
      "step": 935
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004945054945054944,
      "loss": 2.006,
      "step": 936
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004943621595795509,
      "loss": 2.0742,
      "step": 937
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004942188246536072,
      "loss": 2.2008,
      "step": 938
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004940754897276637,
      "loss": 2.1771,
      "step": 939
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004939321548017199,
      "loss": 2.1418,
      "step": 940
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004937888198757764,
      "loss": 2.1089,
      "step": 941
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004936454849498327,
      "loss": 2.1641,
      "step": 942
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0004935021500238891,
      "loss": 2.2123,
      "step": 943
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004933588150979455,
      "loss": 2.083,
      "step": 944
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004932154801720019,
      "loss": 2.0856,
      "step": 945
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004930721452460582,
      "loss": 2.0576,
      "step": 946
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004929288103201146,
      "loss": 1.9976,
      "step": 947
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000492785475394171,
      "loss": 2.1001,
      "step": 948
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004926421404682274,
      "loss": 2.1942,
      "step": 949
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004924988055422838,
      "loss": 2.0722,
      "step": 950
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004923554706163402,
      "loss": 2.1542,
      "step": 951
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004922121356903965,
      "loss": 2.1446,
      "step": 952
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004920688007644529,
      "loss": 2.1166,
      "step": 953
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004919254658385093,
      "loss": 2.1406,
      "step": 954
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004917821309125656,
      "loss": 2.1346,
      "step": 955
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004916387959866221,
      "loss": 2.063,
      "step": 956
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004914954610606783,
      "loss": 2.0332,
      "step": 957
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0004913521261347348,
      "loss": 2.0845,
      "step": 958
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004912087912087911,
      "loss": 2.2177,
      "step": 959
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004910654562828476,
      "loss": 2.1375,
      "step": 960
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004909221213569039,
      "loss": 2.1171,
      "step": 961
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004907787864309603,
      "loss": 2.0483,
      "step": 962
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004906354515050167,
      "loss": 2.1325,
      "step": 963
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000490492116579073,
      "loss": 2.0789,
      "step": 964
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004903487816531294,
      "loss": 2.1548,
      "step": 965
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004902054467271858,
      "loss": 2.2216,
      "step": 966
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004900621118012422,
      "loss": 2.0969,
      "step": 967
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004899187768752986,
      "loss": 2.025,
      "step": 968
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000489775441949355,
      "loss": 2.2016,
      "step": 969
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004896321070234113,
      "loss": 2.1138,
      "step": 970
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004894887720974677,
      "loss": 2.0992,
      "step": 971
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0004893454371715241,
      "loss": 2.1381,
      "step": 972
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004892021022455805,
      "loss": 2.0633,
      "step": 973
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004890587673196369,
      "loss": 2.1169,
      "step": 974
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004889154323936933,
      "loss": 2.0574,
      "step": 975
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004887720974677495,
      "loss": 2.1371,
      "step": 976
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000488628762541806,
      "loss": 2.178,
      "step": 977
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004884854276158623,
      "loss": 2.1797,
      "step": 978
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004883420926899188,
      "loss": 2.0527,
      "step": 979
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004881987577639751,
      "loss": 2.2112,
      "step": 980
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004880554228380315,
      "loss": 2.1351,
      "step": 981
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004879120879120879,
      "loss": 2.0178,
      "step": 982
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004877687529861442,
      "loss": 2.1084,
      "step": 983
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00048762541806020066,
      "loss": 2.0922,
      "step": 984
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000487482083134257,
      "loss": 2.027,
      "step": 985
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0004873387482083134,
      "loss": 2.1061,
      "step": 986
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00048719541328236975,
      "loss": 2.0671,
      "step": 987
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004870520783564262,
      "loss": 2.112,
      "step": 988
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004869087434304825,
      "loss": 2.1656,
      "step": 989
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048676540850453885,
      "loss": 2.0472,
      "step": 990
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004866220735785953,
      "loss": 2.0411,
      "step": 991
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004864787386526516,
      "loss": 2.0884,
      "step": 992
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048633540372670806,
      "loss": 2.1037,
      "step": 993
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004861920688007644,
      "loss": 2.1009,
      "step": 994
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004860487338748208,
      "loss": 2.1671,
      "step": 995
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048590539894887715,
      "loss": 2.0654,
      "step": 996
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048576206402293354,
      "loss": 2.0784,
      "step": 997
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004856187290969899,
      "loss": 2.1642,
      "step": 998
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004854753941710463,
      "loss": 2.1117,
      "step": 999
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004853320592451027,
      "loss": 2.0927,
      "step": 1000
    },
    {
      "epoch": 0.68,
      "eval_loss": 2.0208685398101807,
      "eval_runtime": 1688.1492,
      "eval_samples_per_second": 5.924,
      "eval_steps_per_second": 5.924,
      "step": 1000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00048518872431915907,
      "loss": 2.1515,
      "step": 1001
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048504538939321545,
      "loss": 2.0814,
      "step": 1002
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048490205446727184,
      "loss": 2.0079,
      "step": 1003
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048475871954132817,
      "loss": 2.1011,
      "step": 1004
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004846153846153846,
      "loss": 2.1068,
      "step": 1005
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048447204968944094,
      "loss": 1.9542,
      "step": 1006
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004843287147634974,
      "loss": 2.0243,
      "step": 1007
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004841853798375537,
      "loss": 2.0099,
      "step": 1008
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048404204491161014,
      "loss": 2.0935,
      "step": 1009
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048389870998566647,
      "loss": 2.1306,
      "step": 1010
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004837553750597228,
      "loss": 2.1464,
      "step": 1011
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048361204013377924,
      "loss": 2.1239,
      "step": 1012
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048346870520783557,
      "loss": 2.0952,
      "step": 1013
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000483325370281892,
      "loss": 2.1171,
      "step": 1014
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00048318203535594834,
      "loss": 2.1482,
      "step": 1015
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0004830387004300048,
      "loss": 2.1371,
      "step": 1016
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004828953655040611,
      "loss": 2.0772,
      "step": 1017
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004827520305781175,
      "loss": 2.2531,
      "step": 1018
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048260869565217387,
      "loss": 2.157,
      "step": 1019
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048246536072623025,
      "loss": 2.105,
      "step": 1020
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048232202580028664,
      "loss": 2.1585,
      "step": 1021
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000482178690874343,
      "loss": 2.1916,
      "step": 1022
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004820353559483994,
      "loss": 2.0452,
      "step": 1023
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004818920210224558,
      "loss": 2.0769,
      "step": 1024
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004817486860965121,
      "loss": 2.2082,
      "step": 1025
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048160535117056856,
      "loss": 2.1002,
      "step": 1026
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004814620162446249,
      "loss": 2.1154,
      "step": 1027
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004813186813186813,
      "loss": 1.9913,
      "step": 1028
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048117534639273765,
      "loss": 2.1603,
      "step": 1029
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00048103201146679404,
      "loss": 2.0342,
      "step": 1030
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0004808886765408504,
      "loss": 2.1135,
      "step": 1031
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00048074534161490675,
      "loss": 2.0988,
      "step": 1032
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004806020066889632,
      "loss": 2.093,
      "step": 1033
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004804586717630195,
      "loss": 2.1204,
      "step": 1034
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00048031533683707596,
      "loss": 2.1183,
      "step": 1035
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004801720019111323,
      "loss": 2.101,
      "step": 1036
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004800286669851887,
      "loss": 2.1722,
      "step": 1037
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00047988533205924505,
      "loss": 2.122,
      "step": 1038
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00047974199713330144,
      "loss": 2.1153,
      "step": 1039
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004795986622073578,
      "loss": 2.0863,
      "step": 1040
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004794553272814142,
      "loss": 2.0038,
      "step": 1041
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0004793119923554706,
      "loss": 2.1352,
      "step": 1042
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000479168657429527,
      "loss": 2.0381,
      "step": 1043
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00047902532250358336,
      "loss": 2.1007,
      "step": 1044
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00047888198757763974,
      "loss": 2.0599,
      "step": 1045
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047873865265169607,
      "loss": 2.0975,
      "step": 1046
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047859531772575245,
      "loss": 2.1381,
      "step": 1047
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047845198279980884,
      "loss": 2.145,
      "step": 1048
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004783086478738652,
      "loss": 2.1833,
      "step": 1049
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004781653129479216,
      "loss": 2.0726,
      "step": 1050
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047802197802197793,
      "loss": 2.1836,
      "step": 1051
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047787864309603437,
      "loss": 2.128,
      "step": 1052
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004777353081700907,
      "loss": 2.0933,
      "step": 1053
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047759197324414714,
      "loss": 2.0189,
      "step": 1054
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047744863831820347,
      "loss": 2.0973,
      "step": 1055
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004773053033922599,
      "loss": 2.0629,
      "step": 1056
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00047716196846631624,
      "loss": 2.1493,
      "step": 1057
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004770186335403726,
      "loss": 2.0983,
      "step": 1058
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000476875298614429,
      "loss": 2.0396,
      "step": 1059
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0004767319636884854,
      "loss": 2.1371,
      "step": 1060
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047658862876254177,
      "loss": 2.0203,
      "step": 1061
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047644529383659816,
      "loss": 2.0575,
      "step": 1062
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047630195891065454,
      "loss": 2.1714,
      "step": 1063
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047615862398471087,
      "loss": 2.0467,
      "step": 1064
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047601528905876725,
      "loss": 2.1803,
      "step": 1065
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047587195413282364,
      "loss": 2.0905,
      "step": 1066
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047572861920688,
      "loss": 2.1515,
      "step": 1067
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004755852842809364,
      "loss": 2.052,
      "step": 1068
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004754419493549928,
      "loss": 2.0514,
      "step": 1069
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047529861442904917,
      "loss": 2.2441,
      "step": 1070
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047515527950310556,
      "loss": 2.1311,
      "step": 1071
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004750119445771619,
      "loss": 2.0485,
      "step": 1072
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004748686096512183,
      "loss": 2.0591,
      "step": 1073
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00047472527472527465,
      "loss": 2.1058,
      "step": 1074
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0004745819397993311,
      "loss": 2.1968,
      "step": 1075
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004744386048733874,
      "loss": 2.1501,
      "step": 1076
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047429526994744386,
      "loss": 2.0594,
      "step": 1077
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004741519350215002,
      "loss": 2.1584,
      "step": 1078
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047400860009555657,
      "loss": 2.1617,
      "step": 1079
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047386526516961296,
      "loss": 2.1563,
      "step": 1080
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004737219302436693,
      "loss": 2.1209,
      "step": 1081
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004735785953177257,
      "loss": 2.0942,
      "step": 1082
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047343526039178205,
      "loss": 2.0905,
      "step": 1083
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004732919254658385,
      "loss": 2.1083,
      "step": 1084
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004731485905398948,
      "loss": 2.1352,
      "step": 1085
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004730052556139512,
      "loss": 2.1182,
      "step": 1086
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0004728619206880076,
      "loss": 2.0542,
      "step": 1087
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047271858576206397,
      "loss": 2.0865,
      "step": 1088
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00047257525083612036,
      "loss": 2.0584,
      "step": 1089
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047243191591017674,
      "loss": 2.079,
      "step": 1090
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004722885809842331,
      "loss": 2.0989,
      "step": 1091
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004721452460582895,
      "loss": 2.0882,
      "step": 1092
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047200191113234584,
      "loss": 2.1022,
      "step": 1093
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004718585762064023,
      "loss": 2.1201,
      "step": 1094
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004717152412804586,
      "loss": 2.1393,
      "step": 1095
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047157190635451504,
      "loss": 2.0398,
      "step": 1096
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047142857142857137,
      "loss": 2.1704,
      "step": 1097
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004712852365026278,
      "loss": 2.057,
      "step": 1098
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047114190157668414,
      "loss": 2.0615,
      "step": 1099
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047099856665074047,
      "loss": 2.0887,
      "step": 1100
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004708552317247969,
      "loss": 2.1307,
      "step": 1101
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00047071189679885324,
      "loss": 2.0054,
      "step": 1102
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0004705685618729097,
      "loss": 2.1443,
      "step": 1103
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000470425226946966,
      "loss": 2.0008,
      "step": 1104
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00047028189202102244,
      "loss": 2.0476,
      "step": 1105
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00047013855709507877,
      "loss": 2.0807,
      "step": 1106
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00046999522216913516,
      "loss": 2.0908,
      "step": 1107
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00046985188724319154,
      "loss": 2.1526,
      "step": 1108
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004697085523172479,
      "loss": 2.0984,
      "step": 1109
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004695652173913043,
      "loss": 2.173,
      "step": 1110
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004694218824653607,
      "loss": 2.1548,
      "step": 1111
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004692785475394171,
      "loss": 2.1361,
      "step": 1112
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00046913521261347346,
      "loss": 2.1679,
      "step": 1113
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004689918776875298,
      "loss": 2.0432,
      "step": 1114
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004688485427615862,
      "loss": 2.1054,
      "step": 1115
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00046870520783564256,
      "loss": 2.1144,
      "step": 1116
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000468561872909699,
      "loss": 2.1629,
      "step": 1117
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0004684185379837553,
      "loss": 2.1008,
      "step": 1118
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00046827520305781176,
      "loss": 2.2149,
      "step": 1119
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004681318681318681,
      "loss": 2.1446,
      "step": 1120
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004679885332059244,
      "loss": 2.1551,
      "step": 1121
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00046784519827998086,
      "loss": 2.1443,
      "step": 1122
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004677018633540372,
      "loss": 2.1708,
      "step": 1123
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004675585284280936,
      "loss": 2.0796,
      "step": 1124
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00046741519350214995,
      "loss": 2.1689,
      "step": 1125
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004672718585762064,
      "loss": 2.0454,
      "step": 1126
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004671285236502627,
      "loss": 2.1714,
      "step": 1127
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004669851887243191,
      "loss": 2.0867,
      "step": 1128
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004668418537983755,
      "loss": 2.0246,
      "step": 1129
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0004666985188724319,
      "loss": 2.1147,
      "step": 1130
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00046655518394648826,
      "loss": 2.1384,
      "step": 1131
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00046641184902054464,
      "loss": 2.035,
      "step": 1132
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000466268514094601,
      "loss": 2.1166,
      "step": 1133
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004661251791686574,
      "loss": 2.0252,
      "step": 1134
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046598184424271374,
      "loss": 2.0221,
      "step": 1135
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004658385093167702,
      "loss": 2.1787,
      "step": 1136
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004656951743908265,
      "loss": 2.1729,
      "step": 1137
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046555183946488294,
      "loss": 2.1452,
      "step": 1138
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004654085045389393,
      "loss": 2.0615,
      "step": 1139
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004652651696129957,
      "loss": 2.0503,
      "step": 1140
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046512183468705204,
      "loss": 2.048,
      "step": 1141
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046497849976110837,
      "loss": 2.043,
      "step": 1142
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004648351648351648,
      "loss": 2.18,
      "step": 1143
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046469182990922114,
      "loss": 2.128,
      "step": 1144
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004645484949832776,
      "loss": 2.1708,
      "step": 1145
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004644051600573339,
      "loss": 2.0475,
      "step": 1146
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004642618251313903,
      "loss": 2.0693,
      "step": 1147
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0004641184902054467,
      "loss": 2.1685,
      "step": 1148
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046397515527950306,
      "loss": 2.1782,
      "step": 1149
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046383182035355944,
      "loss": 2.0848,
      "step": 1150
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004636884854276158,
      "loss": 2.1424,
      "step": 1151
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004635451505016722,
      "loss": 2.0642,
      "step": 1152
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004634018155757286,
      "loss": 1.9898,
      "step": 1153
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004632584806497849,
      "loss": 2.0492,
      "step": 1154
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046311514572384136,
      "loss": 2.1056,
      "step": 1155
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004629718107978977,
      "loss": 2.1412,
      "step": 1156
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046282847587195413,
      "loss": 2.0486,
      "step": 1157
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046268514094601046,
      "loss": 2.1234,
      "step": 1158
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004625418060200669,
      "loss": 2.1705,
      "step": 1159
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0004623984710941232,
      "loss": 2.122,
      "step": 1160
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046225513616817955,
      "loss": 2.0406,
      "step": 1161
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000462111801242236,
      "loss": 2.1442,
      "step": 1162
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004619684663162923,
      "loss": 2.052,
      "step": 1163
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046182513139034876,
      "loss": 2.0891,
      "step": 1164
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004616817964644051,
      "loss": 2.0678,
      "step": 1165
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046153846153846153,
      "loss": 2.1483,
      "step": 1166
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046139512661251786,
      "loss": 2.0679,
      "step": 1167
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046125179168657424,
      "loss": 2.1211,
      "step": 1168
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004611084567606306,
      "loss": 2.1161,
      "step": 1169
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000460965121834687,
      "loss": 2.1112,
      "step": 1170
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004608217869087434,
      "loss": 2.1506,
      "step": 1171
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004606784519827998,
      "loss": 2.0986,
      "step": 1172
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046053511705685616,
      "loss": 2.0766,
      "step": 1173
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046039178213091254,
      "loss": 2.115,
      "step": 1174
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00046024844720496887,
      "loss": 2.1063,
      "step": 1175
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0004601051122790253,
      "loss": 2.0088,
      "step": 1176
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00045996177735308164,
      "loss": 2.0694,
      "step": 1177
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004598184424271381,
      "loss": 2.1738,
      "step": 1178
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004596751075011944,
      "loss": 2.0662,
      "step": 1179
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045953177257525085,
      "loss": 2.1288,
      "step": 1180
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004593884376493072,
      "loss": 2.1382,
      "step": 1181
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004592451027233635,
      "loss": 2.1263,
      "step": 1182
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045910176779741994,
      "loss": 1.9623,
      "step": 1183
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045895843287147627,
      "loss": 2.2013,
      "step": 1184
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004588150979455327,
      "loss": 2.2295,
      "step": 1185
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045867176301958904,
      "loss": 2.1698,
      "step": 1186
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004585284280936455,
      "loss": 2.1143,
      "step": 1187
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004583850931677018,
      "loss": 2.0956,
      "step": 1188
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004582417582417582,
      "loss": 2.0658,
      "step": 1189
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0004580984233158146,
      "loss": 2.1017,
      "step": 1190
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045795508838987096,
      "loss": 2.1492,
      "step": 1191
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00045781175346392734,
      "loss": 2.2528,
      "step": 1192
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004576684185379837,
      "loss": 2.0356,
      "step": 1193
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004575250836120401,
      "loss": 2.0912,
      "step": 1194
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004573817486860965,
      "loss": 2.1458,
      "step": 1195
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004572384137601528,
      "loss": 2.0456,
      "step": 1196
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00045709507883420926,
      "loss": 2.0842,
      "step": 1197
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004569517439082656,
      "loss": 2.1316,
      "step": 1198
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00045680840898232203,
      "loss": 2.1506,
      "step": 1199
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00045666507405637836,
      "loss": 2.1229,
      "step": 1200
    },
    {
      "epoch": 0.82,
      "eval_loss": 2.010464906692505,
      "eval_runtime": 1649.1596,
      "eval_samples_per_second": 6.064,
      "eval_steps_per_second": 6.064,
      "step": 1200
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004565217391304348,
      "loss": 2.0344,
      "step": 1201
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004563784042044911,
      "loss": 2.1438,
      "step": 1202
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00045623506927854746,
      "loss": 1.9869,
      "step": 1203
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004560917343526039,
      "loss": 2.2059,
      "step": 1204
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0004559483994266602,
      "loss": 1.9896,
      "step": 1205
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00045580506450071666,
      "loss": 2.0367,
      "step": 1206
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000455661729574773,
      "loss": 2.0457,
      "step": 1207
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045551839464882943,
      "loss": 1.9596,
      "step": 1208
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045537505972288576,
      "loss": 2.0869,
      "step": 1209
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045523172479694214,
      "loss": 2.1679,
      "step": 1210
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004550883898709985,
      "loss": 2.0897,
      "step": 1211
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004549450549450549,
      "loss": 2.0965,
      "step": 1212
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004548017200191113,
      "loss": 2.1179,
      "step": 1213
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004546583850931677,
      "loss": 2.1033,
      "step": 1214
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045451505016722406,
      "loss": 2.0576,
      "step": 1215
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045437171524128045,
      "loss": 2.1722,
      "step": 1216
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004542283803153368,
      "loss": 2.0906,
      "step": 1217
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004540850453893932,
      "loss": 2.07,
      "step": 1218
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00045394171046344954,
      "loss": 2.1588,
      "step": 1219
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000453798375537506,
      "loss": 2.1003,
      "step": 1220
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0004536550406115623,
      "loss": 2.1694,
      "step": 1221
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004535117056856187,
      "loss": 2.09,
      "step": 1222
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004533683707596751,
      "loss": 2.1133,
      "step": 1223
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004532250358337314,
      "loss": 2.1067,
      "step": 1224
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00045308170090778784,
      "loss": 2.1304,
      "step": 1225
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004529383659818442,
      "loss": 2.1474,
      "step": 1226
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004527950310559006,
      "loss": 2.0828,
      "step": 1227
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00045265169612995694,
      "loss": 2.1004,
      "step": 1228
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004525083612040134,
      "loss": 2.0719,
      "step": 1229
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004523650262780697,
      "loss": 2.0861,
      "step": 1230
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004522216913521261,
      "loss": 2.136,
      "step": 1231
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0004520783564261825,
      "loss": 2.1708,
      "step": 1232
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00045193502150023886,
      "loss": 2.0946,
      "step": 1233
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00045179168657429524,
      "loss": 2.1396,
      "step": 1234
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00045164835164835163,
      "loss": 2.1104,
      "step": 1235
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000451505016722408,
      "loss": 2.1906,
      "step": 1236
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004513616817964644,
      "loss": 2.1554,
      "step": 1237
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004512183468705207,
      "loss": 2.1313,
      "step": 1238
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004510750119445771,
      "loss": 2.1129,
      "step": 1239
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004509316770186335,
      "loss": 1.9433,
      "step": 1240
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004507883420926899,
      "loss": 2.0958,
      "step": 1241
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00045064500716674626,
      "loss": 2.0529,
      "step": 1242
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00045050167224080264,
      "loss": 2.1668,
      "step": 1243
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00045035833731485903,
      "loss": 2.1123,
      "step": 1244
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00045021500238891536,
      "loss": 1.9926,
      "step": 1245
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004500716674629718,
      "loss": 2.0264,
      "step": 1246
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004499283325370281,
      "loss": 2.0906,
      "step": 1247
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00044978499761108456,
      "loss": 2.066,
      "step": 1248
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004496416626851409,
      "loss": 2.0788,
      "step": 1249
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0004494983277591973,
      "loss": 2.0461,
      "step": 1250
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044935499283325366,
      "loss": 2.0026,
      "step": 1251
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044921165790731004,
      "loss": 2.0602,
      "step": 1252
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044906832298136643,
      "loss": 2.1321,
      "step": 1253
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004489249880554228,
      "loss": 2.0282,
      "step": 1254
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004487816531294792,
      "loss": 2.042,
      "step": 1255
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004486383182035355,
      "loss": 2.0985,
      "step": 1256
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004484949832775919,
      "loss": 2.0782,
      "step": 1257
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004483516483516483,
      "loss": 2.0993,
      "step": 1258
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004482083134257047,
      "loss": 2.0959,
      "step": 1259
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044806497849976106,
      "loss": 2.0444,
      "step": 1260
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044792164357381744,
      "loss": 2.0952,
      "step": 1261
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044777830864787383,
      "loss": 2.077,
      "step": 1262
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004476349737219302,
      "loss": 2.2078,
      "step": 1263
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00044749163879598654,
      "loss": 2.1267,
      "step": 1264
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000447348303870043,
      "loss": 2.0193,
      "step": 1265
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004472049689440993,
      "loss": 2.118,
      "step": 1266
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044706163401815575,
      "loss": 2.0803,
      "step": 1267
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004469182990922121,
      "loss": 2.1214,
      "step": 1268
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004467749641662685,
      "loss": 2.0874,
      "step": 1269
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044663162924032484,
      "loss": 2.1083,
      "step": 1270
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044648829431438123,
      "loss": 2.0644,
      "step": 1271
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004463449593884376,
      "loss": 1.9959,
      "step": 1272
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044620162446249394,
      "loss": 2.04,
      "step": 1273
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004460582895365504,
      "loss": 2.1078,
      "step": 1274
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004459149546106067,
      "loss": 2.0223,
      "step": 1275
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044577161968466315,
      "loss": 2.0671,
      "step": 1276
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004456282847587195,
      "loss": 2.1617,
      "step": 1277
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044548494983277586,
      "loss": 2.0564,
      "step": 1278
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044534161490683224,
      "loss": 2.121,
      "step": 1279
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044519827998088863,
      "loss": 2.0868,
      "step": 1280
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000445054945054945,
      "loss": 2.0621,
      "step": 1281
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004449116101290014,
      "loss": 2.0657,
      "step": 1282
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004447682752030578,
      "loss": 2.1032,
      "step": 1283
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044462494027711416,
      "loss": 2.142,
      "step": 1284
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004444816053511705,
      "loss": 2.1185,
      "step": 1285
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044433827042522693,
      "loss": 2.119,
      "step": 1286
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044419493549928326,
      "loss": 1.9116,
      "step": 1287
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004440516005733397,
      "loss": 2.112,
      "step": 1288
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044390826564739603,
      "loss": 2.0351,
      "step": 1289
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044376493072145247,
      "loss": 2.0875,
      "step": 1290
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004436215957955088,
      "loss": 2.1202,
      "step": 1291
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004434782608695651,
      "loss": 2.1295,
      "step": 1292
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00044333492594362156,
      "loss": 2.0939,
      "step": 1293
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004431915910176779,
      "loss": 1.9528,
      "step": 1294
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044304825609173433,
      "loss": 2.155,
      "step": 1295
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044290492116579066,
      "loss": 2.1111,
      "step": 1296
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004427615862398471,
      "loss": 2.1194,
      "step": 1297
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004426182513139034,
      "loss": 2.1306,
      "step": 1298
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004424749163879598,
      "loss": 2.0579,
      "step": 1299
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004423315814620162,
      "loss": 2.1123,
      "step": 1300
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004421882465360726,
      "loss": 2.0886,
      "step": 1301
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044204491161012896,
      "loss": 2.0761,
      "step": 1302
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044190157668418535,
      "loss": 2.0334,
      "step": 1303
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044175824175824173,
      "loss": 2.0314,
      "step": 1304
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004416149068322981,
      "loss": 2.173,
      "step": 1305
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044147157190635444,
      "loss": 2.0194,
      "step": 1306
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004413282369804109,
      "loss": 2.1108,
      "step": 1307
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004411849020544672,
      "loss": 2.0581,
      "step": 1308
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00044104156712852365,
      "loss": 1.9859,
      "step": 1309
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00044089823220258,
      "loss": 2.0621,
      "step": 1310
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004407548972766364,
      "loss": 2.1089,
      "step": 1311
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00044061156235069275,
      "loss": 2.1205,
      "step": 1312
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004404682274247491,
      "loss": 2.0944,
      "step": 1313
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004403248924988055,
      "loss": 2.0718,
      "step": 1314
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00044018155757286184,
      "loss": 2.0605,
      "step": 1315
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004400382226469183,
      "loss": 2.0731,
      "step": 1316
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004398948877209746,
      "loss": 2.017,
      "step": 1317
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00043975155279503105,
      "loss": 2.0787,
      "step": 1318
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004396082178690874,
      "loss": 2.1489,
      "step": 1319
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00043946488294314376,
      "loss": 2.0481,
      "step": 1320
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00043932154801720015,
      "loss": 2.1374,
      "step": 1321
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00043917821309125653,
      "loss": 2.1136,
      "step": 1322
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004390348781653129,
      "loss": 2.0005,
      "step": 1323
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004388915432393693,
      "loss": 1.9886,
      "step": 1324
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004387482083134257,
      "loss": 2.1114,
      "step": 1325
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043860487338748206,
      "loss": 2.0226,
      "step": 1326
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004384615384615384,
      "loss": 2.1214,
      "step": 1327
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043831820353559483,
      "loss": 2.2046,
      "step": 1328
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043817486860965116,
      "loss": 2.094,
      "step": 1329
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004380315336837076,
      "loss": 2.1184,
      "step": 1330
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043788819875776393,
      "loss": 2.0185,
      "step": 1331
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043774486383182037,
      "loss": 2.0475,
      "step": 1332
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004376015289058767,
      "loss": 2.102,
      "step": 1333
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000437458193979933,
      "loss": 2.0615,
      "step": 1334
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043731485905398946,
      "loss": 1.9326,
      "step": 1335
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0004371715241280458,
      "loss": 2.1058,
      "step": 1336
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043702818920210223,
      "loss": 2.0959,
      "step": 1337
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00043688485427615856,
      "loss": 2.0412,
      "step": 1338
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000436741519350215,
      "loss": 2.104,
      "step": 1339
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043659818442427133,
      "loss": 2.0625,
      "step": 1340
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004364548494983277,
      "loss": 2.1427,
      "step": 1341
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004363115145723841,
      "loss": 2.0692,
      "step": 1342
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004361681796464405,
      "loss": 2.1571,
      "step": 1343
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043602484472049686,
      "loss": 2.0097,
      "step": 1344
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043588150979455325,
      "loss": 2.0033,
      "step": 1345
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043573817486860963,
      "loss": 2.0994,
      "step": 1346
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000435594839942666,
      "loss": 2.0478,
      "step": 1347
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043545150501672234,
      "loss": 2.006,
      "step": 1348
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004353081700907788,
      "loss": 2.0641,
      "step": 1349
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004351648351648351,
      "loss": 2.079,
      "step": 1350
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00043502150023889155,
      "loss": 2.1691,
      "step": 1351
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004348781653129479,
      "loss": 2.0747,
      "step": 1352
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004347348303870042,
      "loss": 2.1697,
      "step": 1353
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043459149546106065,
      "loss": 2.0546,
      "step": 1354
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000434448160535117,
      "loss": 2.1145,
      "step": 1355
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004343048256091734,
      "loss": 2.0477,
      "step": 1356
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043416149068322974,
      "loss": 2.1252,
      "step": 1357
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004340181557572862,
      "loss": 2.0674,
      "step": 1358
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004338748208313425,
      "loss": 2.2159,
      "step": 1359
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004337314859053989,
      "loss": 2.0525,
      "step": 1360
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004335881509794553,
      "loss": 2.1488,
      "step": 1361
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043344481605351166,
      "loss": 2.0317,
      "step": 1362
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043330148112756805,
      "loss": 2.0714,
      "step": 1363
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043315814620162443,
      "loss": 2.1052,
      "step": 1364
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004330148112756808,
      "loss": 2.139,
      "step": 1365
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0004328714763497372,
      "loss": 2.1675,
      "step": 1366
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00043272814142379353,
      "loss": 2.1032,
      "step": 1367
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043258480649784997,
      "loss": 2.0958,
      "step": 1368
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0004324414715719063,
      "loss": 2.1408,
      "step": 1369
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043229813664596273,
      "loss": 2.0466,
      "step": 1370
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043215480172001906,
      "loss": 2.097,
      "step": 1371
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0004320114667940755,
      "loss": 2.1923,
      "step": 1372
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043186813186813183,
      "loss": 2.0855,
      "step": 1373
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043172479694218816,
      "loss": 2.1068,
      "step": 1374
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0004315814620162446,
      "loss": 2.1737,
      "step": 1375
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043143812709030093,
      "loss": 2.1328,
      "step": 1376
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043129479216435737,
      "loss": 2.1188,
      "step": 1377
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0004311514572384137,
      "loss": 2.1673,
      "step": 1378
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043100812231247013,
      "loss": 2.0582,
      "step": 1379
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043086478738652646,
      "loss": 2.1352,
      "step": 1380
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043072145246058285,
      "loss": 1.9892,
      "step": 1381
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00043057811753463923,
      "loss": 2.1073,
      "step": 1382
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004304347826086956,
      "loss": 1.9898,
      "step": 1383
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000430291447682752,
      "loss": 2.0761,
      "step": 1384
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004301481127568084,
      "loss": 2.0451,
      "step": 1385
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00043000477783086477,
      "loss": 2.1101,
      "step": 1386
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00042986144290492115,
      "loss": 2.089,
      "step": 1387
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004297181079789775,
      "loss": 2.1503,
      "step": 1388
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004295747730530339,
      "loss": 2.1124,
      "step": 1389
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00042943143812709025,
      "loss": 2.0814,
      "step": 1390
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004292881032011467,
      "loss": 2.0763,
      "step": 1391
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000429144768275203,
      "loss": 2.0478,
      "step": 1392
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00042900143334925945,
      "loss": 2.0456,
      "step": 1393
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004288580984233158,
      "loss": 1.9715,
      "step": 1394
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0004287147634973721,
      "loss": 2.1651,
      "step": 1395
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00042857142857142855,
      "loss": 2.0314,
      "step": 1396
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004284280936454849,
      "loss": 2.1104,
      "step": 1397
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004282847587195413,
      "loss": 2.068,
      "step": 1398
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042814142379359765,
      "loss": 2.013,
      "step": 1399
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004279980888676541,
      "loss": 2.058,
      "step": 1400
    },
    {
      "epoch": 0.96,
      "eval_loss": 2.0060460567474365,
      "eval_runtime": 1646.7958,
      "eval_samples_per_second": 6.072,
      "eval_steps_per_second": 6.072,
      "step": 1400
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004278547539417104,
      "loss": 2.0666,
      "step": 1401
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004277114190157668,
      "loss": 2.1469,
      "step": 1402
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004275680840898232,
      "loss": 2.0233,
      "step": 1403
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042742474916387957,
      "loss": 2.0452,
      "step": 1404
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042728141423793595,
      "loss": 2.0146,
      "step": 1405
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042713807931199233,
      "loss": 2.1285,
      "step": 1406
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004269947443860487,
      "loss": 2.0872,
      "step": 1407
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004268514094601051,
      "loss": 2.0824,
      "step": 1408
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042670807453416143,
      "loss": 2.1307,
      "step": 1409
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00042656473960821787,
      "loss": 2.0136,
      "step": 1410
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004264214046822742,
      "loss": 2.0709,
      "step": 1411
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042627806975633064,
      "loss": 2.0025,
      "step": 1412
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042613473483038697,
      "loss": 2.1293,
      "step": 1413
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042599139990444335,
      "loss": 2.1285,
      "step": 1414
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042584806497849973,
      "loss": 2.1601,
      "step": 1415
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042570473005255606,
      "loss": 2.0589,
      "step": 1416
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004255613951266125,
      "loss": 2.087,
      "step": 1417
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042541806020066883,
      "loss": 2.1115,
      "step": 1418
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042527472527472527,
      "loss": 2.0327,
      "step": 1419
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004251313903487816,
      "loss": 2.0255,
      "step": 1420
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042498805542283804,
      "loss": 2.0882,
      "step": 1421
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042484472049689436,
      "loss": 2.1193,
      "step": 1422
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042470138557095075,
      "loss": 2.0616,
      "step": 1423
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00042455805064500713,
      "loss": 2.088,
      "step": 1424
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004244147157190635,
      "loss": 2.1032,
      "step": 1425
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004242713807931199,
      "loss": 2.1068,
      "step": 1426
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004241280458671763,
      "loss": 2.0329,
      "step": 1427
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042398471094123267,
      "loss": 2.2018,
      "step": 1428
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042384137601528905,
      "loss": 2.107,
      "step": 1429
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004236980410893454,
      "loss": 2.0242,
      "step": 1430
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042355470616340176,
      "loss": 2.1247,
      "step": 1431
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042341137123745815,
      "loss": 2.0634,
      "step": 1432
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042326803631151453,
      "loss": 2.0362,
      "step": 1433
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004231247013855709,
      "loss": 2.1368,
      "step": 1434
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004229813664596273,
      "loss": 1.9856,
      "step": 1435
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004228380315336837,
      "loss": 2.0913,
      "step": 1436
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042269469660774,
      "loss": 2.1541,
      "step": 1437
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00042255136168179645,
      "loss": 2.1063,
      "step": 1438
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004224080267558528,
      "loss": 2.0437,
      "step": 1439
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0004222646918299092,
      "loss": 2.1481,
      "step": 1440
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042212135690396555,
      "loss": 2.2177,
      "step": 1441
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000421978021978022,
      "loss": 2.0707,
      "step": 1442
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004218346870520783,
      "loss": 2.1417,
      "step": 1443
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004216913521261347,
      "loss": 2.0127,
      "step": 1444
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004215480172001911,
      "loss": 2.0886,
      "step": 1445
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042140468227424747,
      "loss": 2.0717,
      "step": 1446
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042126134734830385,
      "loss": 2.1458,
      "step": 1447
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004211180124223602,
      "loss": 2.1917,
      "step": 1448
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042097467749641656,
      "loss": 2.0842,
      "step": 1449
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042083134257047295,
      "loss": 2.1187,
      "step": 1450
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042068800764452933,
      "loss": 2.141,
      "step": 1451
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004205446727185857,
      "loss": 2.079,
      "step": 1452
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004204013377926421,
      "loss": 2.1057,
      "step": 1453
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004202580028666985,
      "loss": 2.1162,
      "step": 1454
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00042011466794075487,
      "loss": 2.0668,
      "step": 1455
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004199713330148112,
      "loss": 2.1383,
      "step": 1456
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041982799808886763,
      "loss": 2.0792,
      "step": 1457
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041968466316292396,
      "loss": 2.1121,
      "step": 1458
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004195413282369804,
      "loss": 2.0756,
      "step": 1459
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041939799331103673,
      "loss": 1.9645,
      "step": 1460
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041925465838509317,
      "loss": 2.0766,
      "step": 1461
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004191113234591495,
      "loss": 2.0359,
      "step": 1462
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004189679885332059,
      "loss": 2.2025,
      "step": 1463
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041882465360726227,
      "loss": 1.9701,
      "step": 1464
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004186813186813186,
      "loss": 2.0596,
      "step": 1465
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041853798375537503,
      "loss": 2.0145,
      "step": 1466
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041839464882943136,
      "loss": 1.9526,
      "step": 1467
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0004182513139034878,
      "loss": 2.0803,
      "step": 1468
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00041810797897754413,
      "loss": 2.0068,
      "step": 1469
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004179646440516005,
      "loss": 2.013,
      "step": 1470
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004178213091256569,
      "loss": 2.0862,
      "step": 1471
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004176779741997133,
      "loss": 1.8934,
      "step": 1472
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041753463927376967,
      "loss": 2.0101,
      "step": 1473
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041739130434782605,
      "loss": 2.0879,
      "step": 1474
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041724796942188243,
      "loss": 2.0305,
      "step": 1475
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004171046344959388,
      "loss": 1.9277,
      "step": 1476
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041696129956999515,
      "loss": 2.0387,
      "step": 1477
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004168179646440516,
      "loss": 2.0777,
      "step": 1478
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004166746297181079,
      "loss": 2.0581,
      "step": 1479
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041653129479216435,
      "loss": 1.9738,
      "step": 1480
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004163879598662207,
      "loss": 2.0169,
      "step": 1481
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004162446249402771,
      "loss": 1.9716,
      "step": 1482
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00041610129001433345,
      "loss": 2.0244,
      "step": 1483
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004159579550883898,
      "loss": 2.0311,
      "step": 1484
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004158146201624462,
      "loss": 2.0443,
      "step": 1485
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041567128523650255,
      "loss": 1.9971,
      "step": 1486
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.000415527950310559,
      "loss": 2.0571,
      "step": 1487
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004153846153846153,
      "loss": 2.0578,
      "step": 1488
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041524128045867175,
      "loss": 2.0293,
      "step": 1489
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004150979455327281,
      "loss": 1.9722,
      "step": 1490
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041495461060678447,
      "loss": 2.076,
      "step": 1491
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041481127568084085,
      "loss": 2.0976,
      "step": 1492
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041466794075489723,
      "loss": 2.0126,
      "step": 1493
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004145246058289536,
      "loss": 1.9639,
      "step": 1494
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041438127090301,
      "loss": 2.0662,
      "step": 1495
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004142379359770664,
      "loss": 2.0507,
      "step": 1496
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041409460105112277,
      "loss": 1.9897,
      "step": 1497
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004139512661251791,
      "loss": 2.1243,
      "step": 1498
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00041380793119923554,
      "loss": 1.9646,
      "step": 1499
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041366459627329187,
      "loss": 2.0035,
      "step": 1500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004135212613473483,
      "loss": 2.0319,
      "step": 1501
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041337792642140463,
      "loss": 2.052,
      "step": 1502
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041323459149546107,
      "loss": 2.0439,
      "step": 1503
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004130912565695174,
      "loss": 2.0266,
      "step": 1504
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041294792164357373,
      "loss": 2.0671,
      "step": 1505
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041280458671763017,
      "loss": 1.9876,
      "step": 1506
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004126612517916865,
      "loss": 2.0493,
      "step": 1507
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041251791686574294,
      "loss": 2.1042,
      "step": 1508
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041237458193979927,
      "loss": 1.9368,
      "step": 1509
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004122312470138557,
      "loss": 2.0264,
      "step": 1510
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00041208791208791203,
      "loss": 2.0312,
      "step": 1511
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004119445771619684,
      "loss": 2.0225,
      "step": 1512
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004118012422360248,
      "loss": 2.0262,
      "step": 1513
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004116579073100812,
      "loss": 2.0185,
      "step": 1514
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041151457238413757,
      "loss": 1.9769,
      "step": 1515
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041137123745819395,
      "loss": 2.0439,
      "step": 1516
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041122790253225034,
      "loss": 2.0507,
      "step": 1517
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004110845676063067,
      "loss": 2.0452,
      "step": 1518
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041094123268036305,
      "loss": 2.1165,
      "step": 1519
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004107978977544195,
      "loss": 1.9441,
      "step": 1520
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004106545628284758,
      "loss": 1.9882,
      "step": 1521
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041051122790253225,
      "loss": 2.0254,
      "step": 1522
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004103678929765886,
      "loss": 1.978,
      "step": 1523
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.000410224558050645,
      "loss": 1.9725,
      "step": 1524
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00041008122312470135,
      "loss": 1.9926,
      "step": 1525
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004099378881987577,
      "loss": 1.9377,
      "step": 1526
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004097945532728141,
      "loss": 1.9989,
      "step": 1527
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00040965121834687045,
      "loss": 1.999,
      "step": 1528
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004095078834209269,
      "loss": 2.0974,
      "step": 1529
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004093645484949832,
      "loss": 1.9753,
      "step": 1530
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040922121356903965,
      "loss": 1.9776,
      "step": 1531
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000409077878643096,
      "loss": 2.004,
      "step": 1532
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040893454371715237,
      "loss": 1.9964,
      "step": 1533
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040879120879120875,
      "loss": 1.9928,
      "step": 1534
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040864787386526514,
      "loss": 2.0106,
      "step": 1535
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004085045389393215,
      "loss": 1.9374,
      "step": 1536
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004083612040133779,
      "loss": 1.9205,
      "step": 1537
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004082178690874343,
      "loss": 1.9928,
      "step": 1538
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040807453416149067,
      "loss": 2.0717,
      "step": 1539
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000407931199235547,
      "loss": 2.0671,
      "step": 1540
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040778786430960344,
      "loss": 1.955,
      "step": 1541
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00040764452938365977,
      "loss": 1.9376,
      "step": 1542
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0004075011944577162,
      "loss": 1.9598,
      "step": 1543
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040735785953177254,
      "loss": 1.981,
      "step": 1544
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.000407214524605829,
      "loss": 2.0193,
      "step": 1545
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004070711896798853,
      "loss": 1.9919,
      "step": 1546
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040692785475394163,
      "loss": 2.0287,
      "step": 1547
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040678451982799807,
      "loss": 2.0366,
      "step": 1548
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004066411849020544,
      "loss": 1.9564,
      "step": 1549
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040649784997611084,
      "loss": 2.0538,
      "step": 1550
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040635451505016717,
      "loss": 2.0049,
      "step": 1551
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040621118012422355,
      "loss": 2.0463,
      "step": 1552
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040606784519827994,
      "loss": 2.002,
      "step": 1553
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004059245102723363,
      "loss": 2.0292,
      "step": 1554
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004057811753463927,
      "loss": 2.0681,
      "step": 1555
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004056378404204491,
      "loss": 2.0833,
      "step": 1556
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00040549450549450547,
      "loss": 2.0966,
      "step": 1557
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00040535117056856185,
      "loss": 1.9594,
      "step": 1558
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004052078356426182,
      "loss": 1.9783,
      "step": 1559
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004050645007166746,
      "loss": 2.0691,
      "step": 1560
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00040492116579073095,
      "loss": 2.0509,
      "step": 1561
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004047778308647874,
      "loss": 2.0472,
      "step": 1562
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004046344959388437,
      "loss": 1.9536,
      "step": 1563
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00040449116101290016,
      "loss": 2.0033,
      "step": 1564
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004043478260869565,
      "loss": 2.0034,
      "step": 1565
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004042044911610128,
      "loss": 1.9905,
      "step": 1566
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00040406115623506925,
      "loss": 2.0264,
      "step": 1567
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004039178213091256,
      "loss": 1.982,
      "step": 1568
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000403774486383182,
      "loss": 2.0034,
      "step": 1569
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00040363115145723835,
      "loss": 1.994,
      "step": 1570
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004034878165312948,
      "loss": 1.9319,
      "step": 1571
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004033444816053511,
      "loss": 1.9808,
      "step": 1572
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004032011466794075,
      "loss": 2.057,
      "step": 1573
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004030578117534639,
      "loss": 1.9804,
      "step": 1574
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040291447682752027,
      "loss": 1.9346,
      "step": 1575
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040277114190157665,
      "loss": 1.9386,
      "step": 1576
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040262780697563304,
      "loss": 2.0997,
      "step": 1577
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004024844720496894,
      "loss": 1.9615,
      "step": 1578
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004023411371237458,
      "loss": 2.0695,
      "step": 1579
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040219780219780213,
      "loss": 2.0928,
      "step": 1580
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040205446727185857,
      "loss": 1.9805,
      "step": 1581
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004019111323459149,
      "loss": 1.9855,
      "step": 1582
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040176779741997134,
      "loss": 2.0609,
      "step": 1583
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040162446249402767,
      "loss": 2.0458,
      "step": 1584
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004014811275680841,
      "loss": 1.9908,
      "step": 1585
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00040133779264214044,
      "loss": 2.1244,
      "step": 1586
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040119445771619677,
      "loss": 2.0618,
      "step": 1587
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0004010511227902532,
      "loss": 1.9426,
      "step": 1588
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040090778786430953,
      "loss": 2.0683,
      "step": 1589
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040076445293836597,
      "loss": 1.9883,
      "step": 1590
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0004006211180124223,
      "loss": 2.081,
      "step": 1591
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040047778308647874,
      "loss": 1.9766,
      "step": 1592
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040033444816053507,
      "loss": 2.0358,
      "step": 1593
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040019111323459145,
      "loss": 2.0776,
      "step": 1594
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00040004777830864784,
      "loss": 2.065,
      "step": 1595
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003999044433827042,
      "loss": 2.0691,
      "step": 1596
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003997611084567606,
      "loss": 2.1403,
      "step": 1597
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000399617773530817,
      "loss": 1.9704,
      "step": 1598
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00039947443860487337,
      "loss": 2.0766,
      "step": 1599
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00039933110367892976,
      "loss": 2.005,
      "step": 1600
    },
    {
      "epoch": 1.09,
      "eval_loss": 2.000626564025879,
      "eval_runtime": 1644.0479,
      "eval_samples_per_second": 6.083,
      "eval_steps_per_second": 6.083,
      "step": 1600
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0003991877687529861,
      "loss": 1.9763,
      "step": 1601
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003990444338270425,
      "loss": 2.0162,
      "step": 1602
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00039890109890109885,
      "loss": 1.8628,
      "step": 1603
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003987577639751553,
      "loss": 2.0199,
      "step": 1604
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003986144290492116,
      "loss": 1.9488,
      "step": 1605
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000398471094123268,
      "loss": 2.0393,
      "step": 1606
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003983277591973244,
      "loss": 1.9423,
      "step": 1607
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003981844242713807,
      "loss": 2.1568,
      "step": 1608
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00039804108934543716,
      "loss": 2.0384,
      "step": 1609
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003978977544194935,
      "loss": 1.9644,
      "step": 1610
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003977544194935499,
      "loss": 2.0689,
      "step": 1611
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00039761108456760625,
      "loss": 2.0017,
      "step": 1612
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003974677496416627,
      "loss": 1.9427,
      "step": 1613
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000397324414715719,
      "loss": 1.9709,
      "step": 1614
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003971810797897754,
      "loss": 2.0033,
      "step": 1615
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003970377448638318,
      "loss": 1.9937,
      "step": 1616
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039689440993788817,
      "loss": 2.005,
      "step": 1617
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039675107501194456,
      "loss": 2.0023,
      "step": 1618
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039660774008600094,
      "loss": 2.0233,
      "step": 1619
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003964644051600573,
      "loss": 1.962,
      "step": 1620
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003963210702341137,
      "loss": 2.026,
      "step": 1621
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039617773530817004,
      "loss": 2.0934,
      "step": 1622
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003960344003822264,
      "loss": 2.0144,
      "step": 1623
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003958910654562828,
      "loss": 1.9919,
      "step": 1624
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003957477305303392,
      "loss": 1.9533,
      "step": 1625
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039560439560439557,
      "loss": 1.9303,
      "step": 1626
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039546106067845196,
      "loss": 1.9299,
      "step": 1627
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039531772575250834,
      "loss": 2.0134,
      "step": 1628
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00039517439082656467,
      "loss": 1.9218,
      "step": 1629
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003950310559006211,
      "loss": 2.0074,
      "step": 1630
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039488772097467744,
      "loss": 2.1142,
      "step": 1631
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003947443860487339,
      "loss": 2.0237,
      "step": 1632
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003946010511227902,
      "loss": 2.0208,
      "step": 1633
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039445771619684664,
      "loss": 1.9773,
      "step": 1634
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039431438127090297,
      "loss": 1.9945,
      "step": 1635
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039417104634495936,
      "loss": 1.9521,
      "step": 1636
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039402771141901574,
      "loss": 2.0321,
      "step": 1637
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003938843764930721,
      "loss": 2.0056,
      "step": 1638
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003937410415671285,
      "loss": 2.008,
      "step": 1639
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039359770664118484,
      "loss": 2.0351,
      "step": 1640
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003934543717152413,
      "loss": 2.0366,
      "step": 1641
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003933110367892976,
      "loss": 2.0498,
      "step": 1642
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.000393167701863354,
      "loss": 2.0764,
      "step": 1643
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039302436693741037,
      "loss": 1.9468,
      "step": 1644
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00039288103201146675,
      "loss": 2.0169,
      "step": 1645
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039273769708552314,
      "loss": 1.9899,
      "step": 1646
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003925943621595795,
      "loss": 2.0945,
      "step": 1647
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039245102723363585,
      "loss": 2.055,
      "step": 1648
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003923076923076923,
      "loss": 1.9816,
      "step": 1649
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003921643573817486,
      "loss": 1.9407,
      "step": 1650
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039202102245580506,
      "loss": 2.1146,
      "step": 1651
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003918776875298614,
      "loss": 2.096,
      "step": 1652
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003917343526039178,
      "loss": 2.0008,
      "step": 1653
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039159101767797415,
      "loss": 2.0295,
      "step": 1654
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039144768275203054,
      "loss": 1.9967,
      "step": 1655
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003913043478260869,
      "loss": 2.0425,
      "step": 1656
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039116101290014325,
      "loss": 2.062,
      "step": 1657
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0003910176779741997,
      "loss": 2.0158,
      "step": 1658
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.000390874343048256,
      "loss": 1.9327,
      "step": 1659
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00039073100812231246,
      "loss": 2.0324,
      "step": 1660
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003905876731963688,
      "loss": 1.9874,
      "step": 1661
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00039044433827042517,
      "loss": 1.9798,
      "step": 1662
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00039030100334448155,
      "loss": 1.8957,
      "step": 1663
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00039015766841853794,
      "loss": 2.0757,
      "step": 1664
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003900143334925943,
      "loss": 2.0211,
      "step": 1665
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003898709985666507,
      "loss": 2.0094,
      "step": 1666
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003897276636407071,
      "loss": 2.0978,
      "step": 1667
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003895843287147635,
      "loss": 2.0842,
      "step": 1668
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003894409937888198,
      "loss": 2.1968,
      "step": 1669
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00038929765886287624,
      "loss": 2.0997,
      "step": 1670
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00038915432393693257,
      "loss": 1.9782,
      "step": 1671
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.000389010989010989,
      "loss": 2.0218,
      "step": 1672
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00038886765408504534,
      "loss": 2.038,
      "step": 1673
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003887243191591018,
      "loss": 2.049,
      "step": 1674
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003885809842331581,
      "loss": 2.1634,
      "step": 1675
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038843764930721444,
      "loss": 2.0358,
      "step": 1676
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003882943143812709,
      "loss": 2.0982,
      "step": 1677
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003881509794553272,
      "loss": 2.1026,
      "step": 1678
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038800764452938364,
      "loss": 1.9847,
      "step": 1679
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038786430960343997,
      "loss": 1.9671,
      "step": 1680
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003877209746774964,
      "loss": 2.0934,
      "step": 1681
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038757763975155274,
      "loss": 1.9865,
      "step": 1682
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003874343048256091,
      "loss": 2.0684,
      "step": 1683
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003872909698996655,
      "loss": 2.1101,
      "step": 1684
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003871476349737219,
      "loss": 1.9562,
      "step": 1685
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003870043000477783,
      "loss": 1.9814,
      "step": 1686
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038686096512183466,
      "loss": 2.0065,
      "step": 1687
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00038671763019589104,
      "loss": 2.1368,
      "step": 1688
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003865742952699474,
      "loss": 1.9981,
      "step": 1689
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038643096034400375,
      "loss": 1.993,
      "step": 1690
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003862876254180602,
      "loss": 2.0458,
      "step": 1691
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003861442904921165,
      "loss": 1.9745,
      "step": 1692
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038600095556617296,
      "loss": 1.932,
      "step": 1693
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003858576206402293,
      "loss": 2.0137,
      "step": 1694
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003857142857142857,
      "loss": 2.0512,
      "step": 1695
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038557095078834206,
      "loss": 1.9725,
      "step": 1696
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003854276158623984,
      "loss": 1.9678,
      "step": 1697
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003852842809364548,
      "loss": 1.9604,
      "step": 1698
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038514094601051115,
      "loss": 2.0289,
      "step": 1699
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003849976110845676,
      "loss": 1.9483,
      "step": 1700
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003848542761586239,
      "loss": 2.0639,
      "step": 1701
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038471094123268036,
      "loss": 2.0865,
      "step": 1702
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003845676063067367,
      "loss": 2.014,
      "step": 1703
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00038442427138079307,
      "loss": 2.0076,
      "step": 1704
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038428093645484946,
      "loss": 2.042,
      "step": 1705
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038413760152890584,
      "loss": 1.974,
      "step": 1706
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003839942666029622,
      "loss": 2.0785,
      "step": 1707
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003838509316770186,
      "loss": 1.971,
      "step": 1708
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000383707596751075,
      "loss": 2.0806,
      "step": 1709
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003835642618251314,
      "loss": 2.0394,
      "step": 1710
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003834209268991877,
      "loss": 2.0122,
      "step": 1711
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038327759197324414,
      "loss": 1.9853,
      "step": 1712
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038313425704730047,
      "loss": 1.9518,
      "step": 1713
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003829909221213569,
      "loss": 2.0134,
      "step": 1714
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038284758719541324,
      "loss": 2.0334,
      "step": 1715
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0003827042522694697,
      "loss": 2.0515,
      "step": 1716
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000382560917343526,
      "loss": 2.0012,
      "step": 1717
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00038241758241758234,
      "loss": 1.9745,
      "step": 1718
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003822742474916388,
      "loss": 2.0406,
      "step": 1719
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003821309125656951,
      "loss": 2.0851,
      "step": 1720
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038198757763975154,
      "loss": 1.991,
      "step": 1721
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038184424271380787,
      "loss": 1.9414,
      "step": 1722
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003817009077878643,
      "loss": 1.9876,
      "step": 1723
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038155757286192064,
      "loss": 1.9759,
      "step": 1724
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.000381414237935977,
      "loss": 2.0176,
      "step": 1725
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003812709030100334,
      "loss": 2.063,
      "step": 1726
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003811275680840898,
      "loss": 2.0379,
      "step": 1727
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003809842331581462,
      "loss": 2.0511,
      "step": 1728
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038084089823220256,
      "loss": 2.0851,
      "step": 1729
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038069756330625894,
      "loss": 2.0056,
      "step": 1730
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003805542283803153,
      "loss": 2.0117,
      "step": 1731
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00038041089345437166,
      "loss": 1.924,
      "step": 1732
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003802675585284281,
      "loss": 1.9935,
      "step": 1733
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003801242236024844,
      "loss": 1.9831,
      "step": 1734
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037998088867654086,
      "loss": 2.0066,
      "step": 1735
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003798375537505972,
      "loss": 1.9368,
      "step": 1736
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037969421882465363,
      "loss": 2.1333,
      "step": 1737
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037955088389870996,
      "loss": 2.0094,
      "step": 1738
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003794075489727663,
      "loss": 2.0104,
      "step": 1739
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003792642140468227,
      "loss": 2.1044,
      "step": 1740
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037912087912087906,
      "loss": 1.9823,
      "step": 1741
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003789775441949355,
      "loss": 2.0191,
      "step": 1742
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003788342092689918,
      "loss": 1.9903,
      "step": 1743
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037869087434304826,
      "loss": 2.0378,
      "step": 1744
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003785475394171046,
      "loss": 1.9787,
      "step": 1745
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.000378404204491161,
      "loss": 2.016,
      "step": 1746
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00037826086956521736,
      "loss": 2.0677,
      "step": 1747
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037811753463927374,
      "loss": 2.0095,
      "step": 1748
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003779741997133301,
      "loss": 2.0386,
      "step": 1749
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003778308647873865,
      "loss": 2.0146,
      "step": 1750
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037768752986144284,
      "loss": 2.0429,
      "step": 1751
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003775441949354993,
      "loss": 2.0113,
      "step": 1752
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003774008600095556,
      "loss": 2.0442,
      "step": 1753
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037725752508361204,
      "loss": 2.0165,
      "step": 1754
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003771141901576684,
      "loss": 2.0509,
      "step": 1755
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003769708552317248,
      "loss": 2.0619,
      "step": 1756
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037682752030578114,
      "loss": 1.9896,
      "step": 1757
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037668418537983747,
      "loss": 1.9639,
      "step": 1758
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003765408504538939,
      "loss": 1.9989,
      "step": 1759
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00037639751552795024,
      "loss": 1.9954,
      "step": 1760
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003762541806020067,
      "loss": 2.0313,
      "step": 1761
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.000376110845676063,
      "loss": 1.9543,
      "step": 1762
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037596751075011944,
      "loss": 1.982,
      "step": 1763
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003758241758241758,
      "loss": 2.0651,
      "step": 1764
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037568084089823216,
      "loss": 2.0458,
      "step": 1765
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037553750597228854,
      "loss": 2.0584,
      "step": 1766
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003753941710463449,
      "loss": 2.0646,
      "step": 1767
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003752508361204013,
      "loss": 1.9832,
      "step": 1768
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003751075011944577,
      "loss": 2.0284,
      "step": 1769
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003749641662685141,
      "loss": 2.002,
      "step": 1770
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037482083134257046,
      "loss": 2.0567,
      "step": 1771
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003746774964166268,
      "loss": 1.9435,
      "step": 1772
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037453416149068323,
      "loss": 2.0795,
      "step": 1773
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037439082656473956,
      "loss": 1.9883,
      "step": 1774
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.000374247491638796,
      "loss": 1.9813,
      "step": 1775
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0003741041567128523,
      "loss": 2.0155,
      "step": 1776
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00037396082178690876,
      "loss": 2.0065,
      "step": 1777
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003738174868609651,
      "loss": 1.9658,
      "step": 1778
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003736741519350214,
      "loss": 2.0513,
      "step": 1779
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037353081700907786,
      "loss": 2.1119,
      "step": 1780
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003733874820831342,
      "loss": 1.9894,
      "step": 1781
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037324414715719063,
      "loss": 2.0833,
      "step": 1782
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037310081223124696,
      "loss": 2.0896,
      "step": 1783
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003729574773053034,
      "loss": 1.9927,
      "step": 1784
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003728141423793597,
      "loss": 1.9954,
      "step": 1785
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003726708074534161,
      "loss": 2.0618,
      "step": 1786
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003725274725274725,
      "loss": 1.9595,
      "step": 1787
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003723841376015289,
      "loss": 2.0487,
      "step": 1788
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037224080267558526,
      "loss": 2.1212,
      "step": 1789
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037209746774964164,
      "loss": 1.976,
      "step": 1790
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00037195413282369803,
      "loss": 1.8774,
      "step": 1791
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003718107978977544,
      "loss": 2.0226,
      "step": 1792
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00037166746297181074,
      "loss": 1.9768,
      "step": 1793
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003715241280458672,
      "loss": 2.0637,
      "step": 1794
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003713807931199235,
      "loss": 2.0001,
      "step": 1795
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00037123745819397995,
      "loss": 2.0729,
      "step": 1796
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003710941232680363,
      "loss": 1.9483,
      "step": 1797
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00037095078834209266,
      "loss": 2.0153,
      "step": 1798
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00037080745341614904,
      "loss": 2.0948,
      "step": 1799
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003706641184902054,
      "loss": 2.0054,
      "step": 1800
    },
    {
      "epoch": 1.23,
      "eval_loss": 1.9992964267730713,
      "eval_runtime": 1649.7967,
      "eval_samples_per_second": 6.061,
      "eval_steps_per_second": 6.061,
      "step": 1800
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003705207835642618,
      "loss": 1.9406,
      "step": 1801
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00037037744863831814,
      "loss": 2.164,
      "step": 1802
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003702341137123746,
      "loss": 2.0001,
      "step": 1803
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003700907787864309,
      "loss": 1.9451,
      "step": 1804
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00036994744386048735,
      "loss": 2.003,
      "step": 1805
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003698041089345437,
      "loss": 2.0272,
      "step": 1806
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036966077400860006,
      "loss": 1.9824,
      "step": 1807
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036951743908265644,
      "loss": 2.0841,
      "step": 1808
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036937410415671283,
      "loss": 2.0329,
      "step": 1809
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003692307692307692,
      "loss": 2.0209,
      "step": 1810
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003690874343048256,
      "loss": 1.8782,
      "step": 1811
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000368944099378882,
      "loss": 1.9467,
      "step": 1812
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036880076445293836,
      "loss": 1.915,
      "step": 1813
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003686574295269947,
      "loss": 2.019,
      "step": 1814
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003685140946010511,
      "loss": 2.0315,
      "step": 1815
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036837075967510746,
      "loss": 2.0391,
      "step": 1816
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00036822742474916384,
      "loss": 1.9748,
      "step": 1817
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003680840898232202,
      "loss": 2.0068,
      "step": 1818
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003679407548972766,
      "loss": 1.9701,
      "step": 1819
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000367797419971333,
      "loss": 1.9574,
      "step": 1820
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003676540850453893,
      "loss": 2.0035,
      "step": 1821
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036751075011944576,
      "loss": 1.9546,
      "step": 1822
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003673674151935021,
      "loss": 1.9779,
      "step": 1823
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036722408026755853,
      "loss": 2.1025,
      "step": 1824
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036708074534161486,
      "loss": 2.028,
      "step": 1825
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003669374104156713,
      "loss": 1.9185,
      "step": 1826
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003667940754897276,
      "loss": 1.865,
      "step": 1827
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000366650740563784,
      "loss": 1.9609,
      "step": 1828
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003665074056378404,
      "loss": 1.9569,
      "step": 1829
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003663640707118968,
      "loss": 2.0257,
      "step": 1830
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036622073578595316,
      "loss": 2.0884,
      "step": 1831
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0003660774008600095,
      "loss": 2.0377,
      "step": 1832
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036593406593406593,
      "loss": 1.9751,
      "step": 1833
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036579073100812226,
      "loss": 2.0617,
      "step": 1834
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00036564739608217864,
      "loss": 2.0659,
      "step": 1835
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000365504061156235,
      "loss": 1.9916,
      "step": 1836
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003653607262302914,
      "loss": 2.0324,
      "step": 1837
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003652173913043478,
      "loss": 2.0329,
      "step": 1838
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003650740563784042,
      "loss": 1.9504,
      "step": 1839
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00036493072145246056,
      "loss": 1.8959,
      "step": 1840
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00036478738652651695,
      "loss": 2.0087,
      "step": 1841
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003646440516005733,
      "loss": 2.1006,
      "step": 1842
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003645007166746297,
      "loss": 2.0928,
      "step": 1843
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00036435738174868604,
      "loss": 2.0526,
      "step": 1844
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003642140468227425,
      "loss": 1.9657,
      "step": 1845
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003640707118967988,
      "loss": 1.9081,
      "step": 1846
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00036392737697085514,
      "loss": 2.007,
      "step": 1847
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003637840420449116,
      "loss": 2.0273,
      "step": 1848
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003636407071189679,
      "loss": 1.9917,
      "step": 1849
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00036349737219302435,
      "loss": 1.9588,
      "step": 1850
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003633540372670807,
      "loss": 1.9464,
      "step": 1851
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003632107023411371,
      "loss": 1.9609,
      "step": 1852
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036306736741519344,
      "loss": 1.9257,
      "step": 1853
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003629240324892498,
      "loss": 2.0676,
      "step": 1854
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003627806975633062,
      "loss": 2.0322,
      "step": 1855
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003626373626373626,
      "loss": 2.023,
      "step": 1856
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.000362494027711419,
      "loss": 1.9282,
      "step": 1857
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036235069278547536,
      "loss": 2.0074,
      "step": 1858
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036220735785953175,
      "loss": 2.037,
      "step": 1859
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036206402293358813,
      "loss": 1.9538,
      "step": 1860
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036192068800764446,
      "loss": 1.852,
      "step": 1861
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003617773530817009,
      "loss": 2.0184,
      "step": 1862
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003616340181557572,
      "loss": 2.0041,
      "step": 1863
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00036149068322981366,
      "loss": 1.988,
      "step": 1864
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036134734830387,
      "loss": 2.0504,
      "step": 1865
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036120401337792643,
      "loss": 2.0778,
      "step": 1866
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036106067845198276,
      "loss": 2.066,
      "step": 1867
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003609173435260391,
      "loss": 2.0418,
      "step": 1868
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036077400860009553,
      "loss": 2.0154,
      "step": 1869
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036063067367415186,
      "loss": 1.9723,
      "step": 1870
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003604873387482083,
      "loss": 1.9196,
      "step": 1871
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003603440038222646,
      "loss": 2.0374,
      "step": 1872
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00036020066889632106,
      "loss": 2.1146,
      "step": 1873
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003600573339703774,
      "loss": 2.0713,
      "step": 1874
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003599139990444338,
      "loss": 2.0524,
      "step": 1875
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00035977066411849016,
      "loss": 1.9778,
      "step": 1876
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00035962732919254654,
      "loss": 2.0138,
      "step": 1877
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00035948399426660293,
      "loss": 1.9767,
      "step": 1878
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003593406593406593,
      "loss": 1.9536,
      "step": 1879
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003591973244147157,
      "loss": 2.1092,
      "step": 1880
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003590539894887721,
      "loss": 1.9906,
      "step": 1881
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003589106545628284,
      "loss": 2.0383,
      "step": 1882
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00035876731963688485,
      "loss": 1.9626,
      "step": 1883
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003586239847109412,
      "loss": 2.0121,
      "step": 1884
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003584806497849976,
      "loss": 2.0007,
      "step": 1885
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00035833731485905394,
      "loss": 2.0846,
      "step": 1886
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003581939799331104,
      "loss": 2.1493,
      "step": 1887
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003580506450071667,
      "loss": 1.9866,
      "step": 1888
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00035790731008122304,
      "loss": 1.9876,
      "step": 1889
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003577639751552795,
      "loss": 2.0256,
      "step": 1890
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003576206402293358,
      "loss": 2.0551,
      "step": 1891
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00035747730530339225,
      "loss": 1.9491,
      "step": 1892
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0003573339703774486,
      "loss": 1.976,
      "step": 1893
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.000357190635451505,
      "loss": 2.0242,
      "step": 1894
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035704730052556134,
      "loss": 1.9942,
      "step": 1895
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035690396559961773,
      "loss": 1.9462,
      "step": 1896
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003567606306736741,
      "loss": 1.9941,
      "step": 1897
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003566172957477305,
      "loss": 1.987,
      "step": 1898
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003564739608217869,
      "loss": 1.9921,
      "step": 1899
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035633062589584326,
      "loss": 1.9913,
      "step": 1900
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035618729096989965,
      "loss": 2.0761,
      "step": 1901
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035604395604395603,
      "loss": 2.0225,
      "step": 1902
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035590062111801236,
      "loss": 2.1646,
      "step": 1903
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003557572861920688,
      "loss": 1.9713,
      "step": 1904
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035561395126612513,
      "loss": 2.0381,
      "step": 1905
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035547061634018157,
      "loss": 2.1288,
      "step": 1906
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003553272814142379,
      "loss": 1.9958,
      "step": 1907
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00035518394648829433,
      "loss": 2.0927,
      "step": 1908
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035504061156235066,
      "loss": 2.0493,
      "step": 1909
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.000354897276636407,
      "loss": 1.9751,
      "step": 1910
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035475394171046343,
      "loss": 1.9947,
      "step": 1911
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035461060678451976,
      "loss": 1.9878,
      "step": 1912
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003544672718585762,
      "loss": 2.0322,
      "step": 1913
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035432393693263253,
      "loss": 1.9825,
      "step": 1914
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035418060200668897,
      "loss": 2.0174,
      "step": 1915
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003540372670807453,
      "loss": 1.9631,
      "step": 1916
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003538939321548017,
      "loss": 1.9678,
      "step": 1917
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035375059722885806,
      "loss": 2.0006,
      "step": 1918
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035360726230291445,
      "loss": 1.9347,
      "step": 1919
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035346392737697083,
      "loss": 2.0409,
      "step": 1920
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003533205924510272,
      "loss": 2.0187,
      "step": 1921
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003531772575250836,
      "loss": 1.9847,
      "step": 1922
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00035303392259914,
      "loss": 2.0057,
      "step": 1923
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003528905876731963,
      "loss": 2.0196,
      "step": 1924
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035274725274725275,
      "loss": 1.8575,
      "step": 1925
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003526039178213091,
      "loss": 1.9818,
      "step": 1926
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003524605828953655,
      "loss": 2.0204,
      "step": 1927
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035231724796942185,
      "loss": 2.0446,
      "step": 1928
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003521739130434783,
      "loss": 2.0144,
      "step": 1929
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003520305781175346,
      "loss": 1.9512,
      "step": 1930
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035188724319159094,
      "loss": 1.9937,
      "step": 1931
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003517439082656474,
      "loss": 1.9763,
      "step": 1932
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003516005733397037,
      "loss": 2.0291,
      "step": 1933
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035145723841376015,
      "loss": 2.0598,
      "step": 1934
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003513139034878165,
      "loss": 2.0737,
      "step": 1935
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003511705685618729,
      "loss": 2.1272,
      "step": 1936
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035102723363592925,
      "loss": 2.0258,
      "step": 1937
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00035088389870998563,
      "loss": 2.0811,
      "step": 1938
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.000350740563784042,
      "loss": 1.9712,
      "step": 1939
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003505972288580984,
      "loss": 1.9419,
      "step": 1940
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003504538939321548,
      "loss": 2.0849,
      "step": 1941
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00035031055900621116,
      "loss": 2.0123,
      "step": 1942
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00035016722408026755,
      "loss": 1.9185,
      "step": 1943
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00035002388915432393,
      "loss": 2.0759,
      "step": 1944
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00034988055422838026,
      "loss": 2.0272,
      "step": 1945
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003497372193024367,
      "loss": 2.0296,
      "step": 1946
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00034959388437649303,
      "loss": 2.095,
      "step": 1947
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00034945054945054947,
      "loss": 2.1172,
      "step": 1948
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003493072145246058,
      "loss": 1.9911,
      "step": 1949
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003491638795986621,
      "loss": 1.9346,
      "step": 1950
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00034902054467271856,
      "loss": 2.0437,
      "step": 1951
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0003488772097467749,
      "loss": 1.9926,
      "step": 1952
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034873387482083133,
      "loss": 1.8601,
      "step": 1953
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034859053989488766,
      "loss": 2.0288,
      "step": 1954
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003484472049689441,
      "loss": 1.9644,
      "step": 1955
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034830387004300043,
      "loss": 2.0219,
      "step": 1956
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003481605351170568,
      "loss": 2.0288,
      "step": 1957
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003480172001911132,
      "loss": 2.0549,
      "step": 1958
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003478738652651696,
      "loss": 2.0246,
      "step": 1959
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034773053033922596,
      "loss": 2.0496,
      "step": 1960
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034758719541328235,
      "loss": 1.9183,
      "step": 1961
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034744386048733873,
      "loss": 2.0135,
      "step": 1962
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003473005255613951,
      "loss": 1.9164,
      "step": 1963
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034715719063545145,
      "loss": 2.0452,
      "step": 1964
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003470138557095079,
      "loss": 2.1023,
      "step": 1965
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003468705207835642,
      "loss": 1.9568,
      "step": 1966
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00034672718585762065,
      "loss": 2.0042,
      "step": 1967
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.000346583850931677,
      "loss": 1.9825,
      "step": 1968
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003464405160057334,
      "loss": 2.0362,
      "step": 1969
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034629718107978975,
      "loss": 1.9395,
      "step": 1970
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003461538461538461,
      "loss": 1.9586,
      "step": 1971
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003460105112279025,
      "loss": 2.0692,
      "step": 1972
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034586717630195885,
      "loss": 2.0178,
      "step": 1973
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003457238413760153,
      "loss": 1.9349,
      "step": 1974
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003455805064500716,
      "loss": 2.0868,
      "step": 1975
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034543717152412805,
      "loss": 1.9723,
      "step": 1976
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003452938365981844,
      "loss": 2.0752,
      "step": 1977
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034515050167224076,
      "loss": 1.9482,
      "step": 1978
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034500716674629715,
      "loss": 1.9869,
      "step": 1979
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00034486383182035353,
      "loss": 2.0023,
      "step": 1980
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003447204968944099,
      "loss": 2.0806,
      "step": 1981
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003445771619684663,
      "loss": 2.0252,
      "step": 1982
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003444338270425227,
      "loss": 1.9967,
      "step": 1983
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034429049211657907,
      "loss": 1.9377,
      "step": 1984
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003441471571906354,
      "loss": 1.9739,
      "step": 1985
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034400382226469183,
      "loss": 2.0232,
      "step": 1986
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034386048733874816,
      "loss": 1.9893,
      "step": 1987
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003437171524128046,
      "loss": 2.1028,
      "step": 1988
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034357381748686093,
      "loss": 2.0027,
      "step": 1989
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003434304825609173,
      "loss": 1.9481,
      "step": 1990
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003432871476349737,
      "loss": 2.0907,
      "step": 1991
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034314381270903003,
      "loss": 2.0744,
      "step": 1992
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034300047778308647,
      "loss": 2.0442,
      "step": 1993
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003428571428571428,
      "loss": 2.0232,
      "step": 1994
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034271380793119923,
      "loss": 2.0709,
      "step": 1995
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00034257047300525556,
      "loss": 1.9478,
      "step": 1996
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.000342427138079312,
      "loss": 1.9676,
      "step": 1997
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034228380315336833,
      "loss": 2.1258,
      "step": 1998
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003421404682274247,
      "loss": 1.9892,
      "step": 1999
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003419971333014811,
      "loss": 2.0512,
      "step": 2000
    },
    {
      "epoch": 1.37,
      "eval_loss": 1.9946362972259521,
      "eval_runtime": 1647.5347,
      "eval_samples_per_second": 6.07,
      "eval_steps_per_second": 6.07,
      "step": 2000
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003418537983755375,
      "loss": 2.0172,
      "step": 2001
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034171046344959387,
      "loss": 2.0405,
      "step": 2002
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034156712852365025,
      "loss": 1.9842,
      "step": 2003
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034142379359770663,
      "loss": 2.0294,
      "step": 2004
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.000341280458671763,
      "loss": 1.9872,
      "step": 2005
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034113712374581935,
      "loss": 1.9517,
      "step": 2006
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034099378881987573,
      "loss": 2.0903,
      "step": 2007
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003408504538939321,
      "loss": 2.0047,
      "step": 2008
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003407071189679885,
      "loss": 1.9116,
      "step": 2009
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0003405637840420449,
      "loss": 1.9933,
      "step": 2010
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00034042044911610127,
      "loss": 2.0691,
      "step": 2011
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00034027711419015765,
      "loss": 2.0249,
      "step": 2012
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.000340133779264214,
      "loss": 1.9914,
      "step": 2013
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003399904443382704,
      "loss": 2.0592,
      "step": 2014
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033984710941232675,
      "loss": 2.0658,
      "step": 2015
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003397037744863832,
      "loss": 1.9771,
      "step": 2016
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003395604395604395,
      "loss": 1.9868,
      "step": 2017
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033941710463449595,
      "loss": 1.943,
      "step": 2018
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003392737697085523,
      "loss": 2.0233,
      "step": 2019
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033913043478260867,
      "loss": 1.9217,
      "step": 2020
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033898709985666505,
      "loss": 2.05,
      "step": 2021
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033884376493072143,
      "loss": 1.9538,
      "step": 2022
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003387004300047778,
      "loss": 1.9666,
      "step": 2023
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00033855709507883415,
      "loss": 2.0349,
      "step": 2024
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003384137601528906,
      "loss": 2.0789,
      "step": 2025
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003382704252269469,
      "loss": 2.0193,
      "step": 2026
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003381270903010033,
      "loss": 2.0933,
      "step": 2027
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003379837553750597,
      "loss": 2.0623,
      "step": 2028
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033784042044911607,
      "loss": 2.044,
      "step": 2029
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033769708552317245,
      "loss": 2.0534,
      "step": 2030
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033755375059722883,
      "loss": 1.9295,
      "step": 2031
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003374104156712852,
      "loss": 2.141,
      "step": 2032
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003372670807453416,
      "loss": 2.0085,
      "step": 2033
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033712374581939793,
      "loss": 2.0188,
      "step": 2034
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033698041089345437,
      "loss": 2.0537,
      "step": 2035
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003368370759675107,
      "loss": 1.9598,
      "step": 2036
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033669374104156714,
      "loss": 2.004,
      "step": 2037
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033655040611562347,
      "loss": 2.0024,
      "step": 2038
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003364070711896799,
      "loss": 2.0414,
      "step": 2039
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00033626373626373623,
      "loss": 2.0245,
      "step": 2040
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033612040133779256,
      "loss": 1.9819,
      "step": 2041
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.000335977066411849,
      "loss": 2.0282,
      "step": 2042
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033583373148590533,
      "loss": 1.9962,
      "step": 2043
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033569039655996177,
      "loss": 1.9422,
      "step": 2044
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003355470616340181,
      "loss": 2.0411,
      "step": 2045
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003354037267080745,
      "loss": 1.9571,
      "step": 2046
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033526039178213087,
      "loss": 1.9993,
      "step": 2047
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033511705685618725,
      "loss": 2.0761,
      "step": 2048
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033497372193024363,
      "loss": 2.0052,
      "step": 2049
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003348303870043,
      "loss": 2.0984,
      "step": 2050
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003346870520783564,
      "loss": 2.0299,
      "step": 2051
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003345437171524128,
      "loss": 1.9776,
      "step": 2052
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003344003822264691,
      "loss": 2.0061,
      "step": 2053
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00033425704730052555,
      "loss": 2.0546,
      "step": 2054
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003341137123745819,
      "loss": 2.0127,
      "step": 2055
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003339703774486383,
      "loss": 2.0911,
      "step": 2056
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00033382704252269465,
      "loss": 1.9568,
      "step": 2057
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003336837075967511,
      "loss": 2.0353,
      "step": 2058
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003335403726708074,
      "loss": 1.9722,
      "step": 2059
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00033339703774486375,
      "loss": 2.0115,
      "step": 2060
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003332537028189202,
      "loss": 1.9517,
      "step": 2061
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003331103678929765,
      "loss": 1.9787,
      "step": 2062
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00033296703296703295,
      "loss": 2.0402,
      "step": 2063
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003328236980410893,
      "loss": 2.0362,
      "step": 2064
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003326803631151457,
      "loss": 2.0316,
      "step": 2065
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00033253702818920205,
      "loss": 1.9957,
      "step": 2066
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00033239369326325843,
      "loss": 2.076,
      "step": 2067
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003322503583373148,
      "loss": 1.9697,
      "step": 2068
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0003321070234113712,
      "loss": 2.063,
      "step": 2069
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003319636884854276,
      "loss": 2.0591,
      "step": 2070
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033182035355948397,
      "loss": 2.031,
      "step": 2071
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033167701863354035,
      "loss": 2.0116,
      "step": 2072
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033153368370759674,
      "loss": 2.0301,
      "step": 2073
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033139034878165306,
      "loss": 2.0387,
      "step": 2074
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003312470138557095,
      "loss": 2.0549,
      "step": 2075
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033110367892976583,
      "loss": 1.9861,
      "step": 2076
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033096034400382227,
      "loss": 1.918,
      "step": 2077
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003308170090778786,
      "loss": 1.9836,
      "step": 2078
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033067367415193504,
      "loss": 2.0345,
      "step": 2079
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033053033922599137,
      "loss": 1.9827,
      "step": 2080
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003303870043000477,
      "loss": 1.9904,
      "step": 2081
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033024366937410413,
      "loss": 1.9661,
      "step": 2082
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00033010033444816046,
      "loss": 2.0373,
      "step": 2083
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003299569995222169,
      "loss": 1.872,
      "step": 2084
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032981366459627323,
      "loss": 1.9871,
      "step": 2085
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032967032967032967,
      "loss": 1.9051,
      "step": 2086
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000329526994744386,
      "loss": 2.1045,
      "step": 2087
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003293836598184424,
      "loss": 1.9143,
      "step": 2088
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032924032489249877,
      "loss": 1.8973,
      "step": 2089
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032909698996655515,
      "loss": 1.9506,
      "step": 2090
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032895365504061153,
      "loss": 1.9271,
      "step": 2091
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003288103201146679,
      "loss": 1.9837,
      "step": 2092
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003286669851887243,
      "loss": 2.1084,
      "step": 2093
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003285236502627807,
      "loss": 1.9546,
      "step": 2094
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000328380315336837,
      "loss": 2.0735,
      "step": 2095
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00032823698041089345,
      "loss": 2.0231,
      "step": 2096
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003280936454849498,
      "loss": 2.0705,
      "step": 2097
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003279503105590062,
      "loss": 1.9939,
      "step": 2098
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032780697563306255,
      "loss": 1.9815,
      "step": 2099
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.000327663640707119,
      "loss": 1.9705,
      "step": 2100
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003275203057811753,
      "loss": 2.0562,
      "step": 2101
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032737697085523165,
      "loss": 2.014,
      "step": 2102
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003272336359292881,
      "loss": 2.0447,
      "step": 2103
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003270903010033444,
      "loss": 1.9627,
      "step": 2104
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032694696607740085,
      "loss": 1.9587,
      "step": 2105
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003268036311514572,
      "loss": 2.0637,
      "step": 2106
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003266602962255136,
      "loss": 1.9581,
      "step": 2107
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032651696129956995,
      "loss": 1.9609,
      "step": 2108
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032637362637362633,
      "loss": 1.9956,
      "step": 2109
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003262302914476827,
      "loss": 1.9885,
      "step": 2110
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003260869565217391,
      "loss": 1.9506,
      "step": 2111
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003259436215957955,
      "loss": 2.0175,
      "step": 2112
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00032580028666985187,
      "loss": 1.9666,
      "step": 2113
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032565695174390825,
      "loss": 2.0387,
      "step": 2114
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032551361681796464,
      "loss": 2.0288,
      "step": 2115
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032537028189202097,
      "loss": 2.0741,
      "step": 2116
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0003252269469660774,
      "loss": 2.0846,
      "step": 2117
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032508361204013373,
      "loss": 1.974,
      "step": 2118
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032494027711419017,
      "loss": 1.9899,
      "step": 2119
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0003247969421882465,
      "loss": 2.1513,
      "step": 2120
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032465360726230294,
      "loss": 1.9642,
      "step": 2121
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032451027233635927,
      "loss": 1.9595,
      "step": 2122
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0003243669374104156,
      "loss": 2.0706,
      "step": 2123
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032422360248447204,
      "loss": 2.0984,
      "step": 2124
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032408026755852837,
      "loss": 2.1254,
      "step": 2125
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0003239369326325848,
      "loss": 1.9552,
      "step": 2126
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032379359770664113,
      "loss": 1.9694,
      "step": 2127
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00032365026278069757,
      "loss": 2.0373,
      "step": 2128
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003235069278547539,
      "loss": 2.0331,
      "step": 2129
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003233635929288103,
      "loss": 2.0722,
      "step": 2130
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00032322025800286667,
      "loss": 2.0406,
      "step": 2131
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00032307692307692305,
      "loss": 1.8967,
      "step": 2132
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00032293358815097944,
      "loss": 1.9515,
      "step": 2133
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003227902532250358,
      "loss": 2.0313,
      "step": 2134
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003226469182990922,
      "loss": 2.0825,
      "step": 2135
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003225035833731486,
      "loss": 2.0743,
      "step": 2136
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003223602484472049,
      "loss": 2.0133,
      "step": 2137
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00032221691352126136,
      "loss": 1.9019,
      "step": 2138
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003220735785953177,
      "loss": 1.9543,
      "step": 2139
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003219302436693741,
      "loss": 1.999,
      "step": 2140
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00032178690874343045,
      "loss": 1.927,
      "step": 2141
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003216435738174869,
      "loss": 2.069,
      "step": 2142
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003215002388915432,
      "loss": 1.9393,
      "step": 2143
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00032135690396559955,
      "loss": 1.9443,
      "step": 2144
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.000321213569039656,
      "loss": 1.9659,
      "step": 2145
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003210702341137123,
      "loss": 2.0523,
      "step": 2146
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00032092689918776876,
      "loss": 2.0378,
      "step": 2147
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003207835642618251,
      "loss": 2.0093,
      "step": 2148
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00032064022933588147,
      "loss": 2.0546,
      "step": 2149
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00032049689440993785,
      "loss": 2.0351,
      "step": 2150
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00032035355948399424,
      "loss": 1.9175,
      "step": 2151
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003202102245580506,
      "loss": 1.9986,
      "step": 2152
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.000320066889632107,
      "loss": 1.9202,
      "step": 2153
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003199235547061634,
      "loss": 1.9855,
      "step": 2154
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00031978021978021977,
      "loss": 1.9847,
      "step": 2155
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003196368848542761,
      "loss": 2.096,
      "step": 2156
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00031949354992833254,
      "loss": 2.0109,
      "step": 2157
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031935021500238887,
      "loss": 1.8784,
      "step": 2158
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003192068800764453,
      "loss": 1.902,
      "step": 2159
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031906354515050164,
      "loss": 2.0265,
      "step": 2160
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003189202102245581,
      "loss": 1.9539,
      "step": 2161
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003187768752986144,
      "loss": 1.9743,
      "step": 2162
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031863354037267073,
      "loss": 2.0785,
      "step": 2163
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031849020544672717,
      "loss": 2.0334,
      "step": 2164
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003183468705207835,
      "loss": 1.8959,
      "step": 2165
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031820353559483994,
      "loss": 1.9354,
      "step": 2166
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031806020066889627,
      "loss": 2.1023,
      "step": 2167
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003179168657429527,
      "loss": 2.034,
      "step": 2168
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00031777353081700904,
      "loss": 1.9602,
      "step": 2169
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003176301958910654,
      "loss": 1.9826,
      "step": 2170
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003174868609651218,
      "loss": 1.9921,
      "step": 2171
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003173435260391782,
      "loss": 1.9476,
      "step": 2172
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031720019111323457,
      "loss": 2.0478,
      "step": 2173
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031705685618729095,
      "loss": 2.0748,
      "step": 2174
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031691352126134734,
      "loss": 1.9633,
      "step": 2175
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003167701863354037,
      "loss": 2.001,
      "step": 2176
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031662685140946005,
      "loss": 2.0642,
      "step": 2177
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003164835164835165,
      "loss": 1.9987,
      "step": 2178
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003163401815575728,
      "loss": 1.9435,
      "step": 2179
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031619684663162926,
      "loss": 1.9399,
      "step": 2180
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003160535117056856,
      "loss": 1.9618,
      "step": 2181
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031591017677974197,
      "loss": 1.9743,
      "step": 2182
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031576684185379835,
      "loss": 1.9511,
      "step": 2183
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003156235069278547,
      "loss": 2.0058,
      "step": 2184
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0003154801720019111,
      "loss": 2.0174,
      "step": 2185
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00031533683707596745,
      "loss": 2.0545,
      "step": 2186
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003151935021500239,
      "loss": 1.9771,
      "step": 2187
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003150501672240802,
      "loss": 1.9741,
      "step": 2188
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00031490683229813666,
      "loss": 1.9993,
      "step": 2189
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000314763497372193,
      "loss": 1.9776,
      "step": 2190
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00031462016244624937,
      "loss": 2.0027,
      "step": 2191
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00031447682752030575,
      "loss": 2.0119,
      "step": 2192
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00031433349259436214,
      "loss": 1.9371,
      "step": 2193
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003141901576684185,
      "loss": 2.0221,
      "step": 2194
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003140468227424749,
      "loss": 2.0126,
      "step": 2195
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003139034878165313,
      "loss": 2.066,
      "step": 2196
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003137601528905877,
      "loss": 1.9748,
      "step": 2197
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000313616817964644,
      "loss": 1.9549,
      "step": 2198
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003134734830387004,
      "loss": 2.0066,
      "step": 2199
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00031333014811275677,
      "loss": 2.0541,
      "step": 2200
    },
    {
      "epoch": 1.5,
      "eval_loss": 1.9827316999435425,
      "eval_runtime": 1651.9566,
      "eval_samples_per_second": 6.053,
      "eval_steps_per_second": 6.053,
      "step": 2200
    }
  ],
  "max_steps": 4386,
  "num_train_epochs": 3,
  "total_flos": 2.69384075772468e+18,
  "trial_name": null,
  "trial_params": null
}