{
  "best_metric": 2.047600030899048,
  "best_model_checkpoint": "output/checkpoint-600",
  "epoch": 0.41021039306488055,
  "global_step": 600,
  "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
    }
  ],
  "max_steps": 4386,
  "num_train_epochs": 3,
  "total_flos": 7.368734337271511e+17,
  "trial_name": null,
  "trial_params": null
}