{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 2181,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00015151515151515152,
      "loss": 4.3789,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00030303030303030303,
      "loss": 4.4883,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00045454545454545455,
      "loss": 4.4062,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0006060606060606061,
      "loss": 4.375,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0007575757575757576,
      "loss": 4.2012,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0009090909090909091,
      "loss": 4.1875,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0010606060606060607,
      "loss": 4.2383,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0012121212121212121,
      "loss": 3.9727,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0013636363636363635,
      "loss": 4.0527,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0015151515151515152,
      "loss": 4.1172,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0016666666666666666,
      "loss": 4.0137,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0018181818181818182,
      "loss": 3.8691,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00196969696969697,
      "loss": 3.9531,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0021212121212121214,
      "loss": 3.7031,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0022727272727272726,
      "loss": 3.7305,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0024242424242424242,
      "loss": 3.6289,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.002575757575757576,
      "loss": 3.6777,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.002727272727272727,
      "loss": 3.6719,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.002878787878787879,
      "loss": 3.5215,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0030303030303030303,
      "loss": 3.5234,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.003181818181818182,
      "loss": 3.4414,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.003333333333333333,
      "loss": 3.4141,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.003484848484848485,
      "loss": 3.373,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0036363636363636364,
      "loss": 3.502,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.003787878787878788,
      "loss": 3.4727,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00393939393939394,
      "loss": 3.3711,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.004090909090909091,
      "loss": 3.5098,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.004242424242424243,
      "loss": 3.5332,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.004393939393939394,
      "loss": 3.3242,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.004545454545454545,
      "loss": 3.5137,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.004696969696969698,
      "loss": 3.3711,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0048484848484848485,
      "loss": 3.4316,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.005,
      "loss": 3.3398,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.005151515151515152,
      "loss": 3.3145,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0053030303030303025,
      "loss": 3.3281,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.005454545454545454,
      "loss": 3.3164,
      "step": 36
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.005606060606060606,
      "loss": 3.4941,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.005757575757575758,
      "loss": 3.4043,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00590909090909091,
      "loss": 3.4512,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.006060606060606061,
      "loss": 3.5156,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.006212121212121212,
      "loss": 3.2754,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.006363636363636364,
      "loss": 3.4316,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0065151515151515155,
      "loss": 3.3555,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.006666666666666666,
      "loss": 3.248,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.006818181818181818,
      "loss": 3.1289,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00696969696969697,
      "loss": 3.4102,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.007121212121212122,
      "loss": 3.2949,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.007272727272727273,
      "loss": 3.3789,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.007424242424242424,
      "loss": 3.2969,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.007575757575757576,
      "loss": 3.3555,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.007727272727272728,
      "loss": 3.3848,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00787878787878788,
      "loss": 3.3789,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00803030303030303,
      "loss": 3.1992,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.008181818181818182,
      "loss": 3.2363,
      "step": 54
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.008333333333333333,
      "loss": 3.2988,
      "step": 55
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.008484848484848486,
      "loss": 3.3828,
      "step": 56
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.008636363636363636,
      "loss": 3.2988,
      "step": 57
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.008787878787878787,
      "loss": 3.2695,
      "step": 58
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00893939393939394,
      "loss": 3.3262,
      "step": 59
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00909090909090909,
      "loss": 3.2051,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009242424242424243,
      "loss": 3.3047,
      "step": 61
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009393939393939395,
      "loss": 3.332,
      "step": 62
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009545454545454546,
      "loss": 3.2812,
      "step": 63
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009696969696969697,
      "loss": 3.207,
      "step": 64
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00984848484848485,
      "loss": 3.2949,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.01,
      "loss": 3.2305,
      "step": 66
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999994484067656,
      "loss": 3.2422,
      "step": 67
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00999997793628279,
      "loss": 3.2305,
      "step": 68
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999950356681912,
      "loss": 3.1914,
      "step": 69
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999911745325876,
      "loss": 3.3066,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999862102299873,
      "loss": 3.2188,
      "step": 71
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999801427713432,
      "loss": 3.3027,
      "step": 72
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999729721700424,
      "loss": 3.0938,
      "step": 73
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999646984419061,
      "loss": 3.2324,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999553216051891,
      "loss": 3.1992,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.009999448416805801,
      "loss": 3.2676,
      "step": 76
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009999332586912019,
      "loss": 3.3105,
      "step": 77
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009999205726626109,
      "loss": 3.1875,
      "step": 78
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999906783622797,
      "loss": 3.1152,
      "step": 79
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999891891602184,
      "loss": 3.2227,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009998758966336296,
      "loss": 3.2656,
      "step": 81
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009998587987524243,
      "loss": 3.1719,
      "step": 82
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009998405979962925,
      "loss": 3.1699,
      "step": 83
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999821294405392,
      "loss": 3.0996,
      "step": 84
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009998008880223133,
      "loss": 3.2246,
      "step": 85
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999779378892081,
      "loss": 3.1387,
      "step": 86
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999756767062152,
      "loss": 3.1953,
      "step": 87
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009997330525824166,
      "loss": 3.1465,
      "step": 88
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009997082355051977,
      "loss": 3.1582,
      "step": 89
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009996823158852508,
      "loss": 3.1914,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009996552937797646,
      "loss": 3.1602,
      "step": 91
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009996271692483596,
      "loss": 3.0469,
      "step": 92
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009995979423530891,
      "loss": 3.1055,
      "step": 93
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00999567613158439,
      "loss": 3.1016,
      "step": 94
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009995361817313262,
      "loss": 3.0977,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009995036481411004,
      "loss": 3.0996,
      "step": 96
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009994700124595428,
      "loss": 3.1777,
      "step": 97
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.009994352747608662,
      "loss": 3.0957,
      "step": 98
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009993994351217152,
      "loss": 2.9609,
      "step": 99
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009993624936211651,
      "loss": 3.0293,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009993244503407226,
      "loss": 3.1348,
      "step": 101
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009992853053643258,
      "loss": 3.1641,
      "step": 102
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009992450587783426,
      "loss": 3.0801,
      "step": 103
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009992037106715722,
      "loss": 3.0293,
      "step": 104
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009991612611352438,
      "loss": 3.043,
      "step": 105
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009991177102630174,
      "loss": 3.002,
      "step": 106
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009990730581509817,
      "loss": 3.0469,
      "step": 107
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009990273048976565,
      "loss": 2.9492,
      "step": 108
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009989804506039904,
      "loss": 2.9609,
      "step": 109
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009989324953733614,
      "loss": 3.0527,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009988834393115766,
      "loss": 2.8887,
      "step": 111
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00998833282526872,
      "loss": 3.0879,
      "step": 112
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009987820251299122,
      "loss": 2.998,
      "step": 113
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0099872966723379,
      "loss": 3.0215,
      "step": 114
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009986762089540267,
      "loss": 2.9668,
      "step": 115
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009986216504085708,
      "loss": 2.9746,
      "step": 116
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009985659917177992,
      "loss": 2.9395,
      "step": 117
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009985092330045155,
      "loss": 3.0898,
      "step": 118
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.009984513743939508,
      "loss": 3.0938,
      "step": 119
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009983924160137625,
      "loss": 3.0215,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009983323579940351,
      "loss": 2.9727,
      "step": 121
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009982712004672788,
      "loss": 3.0391,
      "step": 122
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009982089435684295,
      "loss": 3.0,
      "step": 123
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0099814558743485,
      "loss": 3.1055,
      "step": 124
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009980811322063268,
      "loss": 2.9551,
      "step": 125
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009980155780250728,
      "loss": 2.9785,
      "step": 126
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009979489250357243,
      "loss": 3.0039,
      "step": 127
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009978811733853432,
      "loss": 2.9785,
      "step": 128
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009978123232234147,
      "loss": 3.0078,
      "step": 129
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00997742374701848,
      "loss": 2.9648,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009976713279749755,
      "loss": 2.9609,
      "step": 131
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009975991831995528,
      "loss": 2.9355,
      "step": 132
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009975259405347582,
      "loss": 2.9355,
      "step": 133
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009974516001421924,
      "loss": 2.9023,
      "step": 134
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009973761621858781,
      "loss": 2.957,
      "step": 135
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009972996268322593,
      "loss": 2.9824,
      "step": 136
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009972219942502017,
      "loss": 2.9414,
      "step": 137
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009971432646109918,
      "loss": 2.8555,
      "step": 138
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009970634380883364,
      "loss": 2.9102,
      "step": 139
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009969825148583626,
      "loss": 2.9414,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.009969004950996174,
      "loss": 2.8887,
      "step": 141
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009968173789930668,
      "loss": 2.8555,
      "step": 142
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009967331667220958,
      "loss": 2.9062,
      "step": 143
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009966478584725085,
      "loss": 2.8594,
      "step": 144
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009965614544325263,
      "loss": 2.8457,
      "step": 145
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00996473954792789,
      "loss": 2.9844,
      "step": 146
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009963853597463532,
      "loss": 2.8828,
      "step": 147
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00996295669488693,
      "loss": 2.8809,
      "step": 148
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00996204884217698,
      "loss": 2.8809,
      "step": 149
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009961130041336749,
      "loss": 2.8145,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00996020029439345,
      "loss": 2.7793,
      "step": 151
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009959259603398453,
      "loss": 2.7715,
      "step": 152
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009958307970427275,
      "loss": 2.8926,
      "step": 153
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009957345397579571,
      "loss": 2.9062,
      "step": 154
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009956371886979138,
      "loss": 2.8066,
      "step": 155
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009955387440773901,
      "loss": 2.7969,
      "step": 156
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009954392061135917,
      "loss": 2.8633,
      "step": 157
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009953385750261364,
      "loss": 2.7773,
      "step": 158
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009952368510370537,
      "loss": 2.8828,
      "step": 159
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009951340343707852,
      "loss": 2.752,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009950301252541824,
      "loss": 2.7617,
      "step": 161
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.009949251239165076,
      "loss": 2.7637,
      "step": 162
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00994819030589433,
      "loss": 2.707,
      "step": 163
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0099471184550704,
      "loss": 2.709,
      "step": 164
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009946035689058188,
      "loss": 2.7207,
      "step": 165
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00994494201024668,
      "loss": 2.7734,
      "step": 166
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009943837421048941,
      "loss": 2.8105,
      "step": 167
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009942721923902106,
      "loss": 2.7305,
      "step": 168
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009941595521267376,
      "loss": 2.8125,
      "step": 169
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009940458215630017,
      "loss": 2.7461,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009939310009499347,
      "loss": 2.791,
      "step": 171
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00993815090540874,
      "loss": 2.8301,
      "step": 172
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009936980905915611,
      "loss": 2.75,
      "step": 173
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009935800013601415,
      "loss": 2.6738,
      "step": 174
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00993460823107164,
      "loss": 2.8047,
      "step": 175
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009933405560955804,
      "loss": 2.8203,
      "step": 176
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009932192005907446,
      "loss": 2.752,
      "step": 177
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009930967568604118,
      "loss": 2.7754,
      "step": 178
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009929732251747389,
      "loss": 2.834,
      "step": 179
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009928486058062827,
      "loss": 2.748,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0099272289903,
      "loss": 2.6816,
      "step": 181
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009925961051232468,
      "loss": 2.7441,
      "step": 182
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009924682243657779,
      "loss": 2.7363,
      "step": 183
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009923392570397458,
      "loss": 2.6406,
      "step": 184
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.009922092034297005,
      "loss": 2.7793,
      "step": 185
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009920780638225891,
      "loss": 2.6621,
      "step": 186
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009919458385077538,
      "loss": 2.7246,
      "step": 187
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009918125277769337,
      "loss": 2.6797,
      "step": 188
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009916781319242614,
      "loss": 2.8262,
      "step": 189
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009915426512462647,
      "loss": 2.6836,
      "step": 190
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009914060860418643,
      "loss": 2.6523,
      "step": 191
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00991268436612374,
      "loss": 2.6758,
      "step": 192
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009911297032614997,
      "loss": 2.666,
      "step": 193
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00990989886295339,
      "loss": 2.7402,
      "step": 194
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009908489860223803,
      "loss": 2.6582,
      "step": 195
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009907070027535022,
      "loss": 2.7031,
      "step": 196
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009905639368019725,
      "loss": 2.6211,
      "step": 197
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009904197884834482,
      "loss": 2.6562,
      "step": 198
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009902745581159743,
      "loss": 2.6953,
      "step": 199
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00990128246019983,
      "loss": 2.7266,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009899808525182933,
      "loss": 2.7285,
      "step": 201
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009898323779361107,
      "loss": 2.6562,
      "step": 202
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00989682822601025,
      "loss": 2.6543,
      "step": 203
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009895321868430113,
      "loss": 2.5488,
      "step": 204
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009893804709944281,
      "loss": 2.7383,
      "step": 205
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009892276753900173,
      "loss": 2.7168,
      "step": 206
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.009890738003669028,
      "loss": 2.6816,
      "step": 207
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009889188462645904,
      "loss": 2.6621,
      "step": 208
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009887628134249668,
      "loss": 2.6367,
      "step": 209
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009886057021922983,
      "loss": 2.6934,
      "step": 210
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009884475129132311,
      "loss": 2.7168,
      "step": 211
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009882882459367897,
      "loss": 2.5977,
      "step": 212
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009881279016143765,
      "loss": 2.6289,
      "step": 213
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009879664802997706,
      "loss": 2.7188,
      "step": 214
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00987803982349128,
      "loss": 2.6406,
      "step": 215
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009876404081209796,
      "loss": 2.584,
      "step": 216
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00987475757976231,
      "loss": 2.6035,
      "step": 217
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00987310032278162,
      "loss": 2.6504,
      "step": 218
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009871432313924254,
      "loss": 2.7539,
      "step": 219
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00986975355687046,
      "loss": 2.6113,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009868064055324203,
      "loss": 2.6777,
      "step": 221
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009866363813013153,
      "loss": 2.6426,
      "step": 222
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009864652833688677,
      "loss": 2.6816,
      "step": 223
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009862931121125835,
      "loss": 2.752,
      "step": 224
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009861198679123368,
      "loss": 2.5977,
      "step": 225
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00985945551150369,
      "loss": 2.6406,
      "step": 226
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009857701622112875,
      "loss": 2.7344,
      "step": 227
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009855937014820659,
      "loss": 2.6094,
      "step": 228
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.009854161693520425,
      "loss": 2.6738,
      "step": 229
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009852375662129194,
      "loss": 2.5996,
      "step": 230
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009850578924587614,
      "loss": 2.7227,
      "step": 231
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00984877148485996,
      "loss": 2.6152,
      "step": 232
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009846953346934119,
      "loss": 2.5762,
      "step": 233
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009845124514821581,
      "loss": 2.6133,
      "step": 234
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009843284992557431,
      "loss": 2.5234,
      "step": 235
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009841434784200341,
      "loss": 2.584,
      "step": 236
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009839573893832563,
      "loss": 2.6016,
      "step": 237
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009837702325559913,
      "loss": 2.5996,
      "step": 238
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009835820083511766,
      "loss": 2.5977,
      "step": 239
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009833927171841055,
      "loss": 2.6035,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009832023594724246,
      "loss": 2.625,
      "step": 241
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009830109356361343,
      "loss": 2.6406,
      "step": 242
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009828184460975867,
      "loss": 2.6074,
      "step": 243
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009826248912814854,
      "loss": 2.6035,
      "step": 244
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009824302716148847,
      "loss": 2.6465,
      "step": 245
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009822345875271882,
      "loss": 2.5039,
      "step": 246
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009820378394501481,
      "loss": 2.6699,
      "step": 247
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009818400278178636,
      "loss": 2.6094,
      "step": 248
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.009816411530667814,
      "loss": 2.6289,
      "step": 249
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00981441215635693,
      "loss": 2.5547,
      "step": 250
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009812402159657353,
      "loss": 2.5625,
      "step": 251
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00981038154500388,
      "loss": 2.4863,
      "step": 252
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009808350316854746,
      "loss": 2.5254,
      "step": 253
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009806308479691595,
      "loss": 2.5215,
      "step": 254
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00980425603801948,
      "loss": 2.6309,
      "step": 255
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009802192996366858,
      "loss": 2.5645,
      "step": 256
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009800119359285563,
      "loss": 2.5723,
      "step": 257
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009798035131350814,
      "loss": 2.5645,
      "step": 258
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009795940317161194,
      "loss": 2.6445,
      "step": 259
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009793834921338647,
      "loss": 2.5742,
      "step": 260
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009791718948528457,
      "loss": 2.5254,
      "step": 261
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009789592403399253,
      "loss": 2.5586,
      "step": 262
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009787455290642984,
      "loss": 2.5957,
      "step": 263
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009785307614974922,
      "loss": 2.6562,
      "step": 264
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009783149381133633,
      "loss": 2.584,
      "step": 265
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009780980593880993,
      "loss": 2.5938,
      "step": 266
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009778801258002153,
      "loss": 2.4375,
      "step": 267
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009776611378305539,
      "loss": 2.5195,
      "step": 268
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009774410959622844,
      "loss": 2.5176,
      "step": 269
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009772200006809012,
      "loss": 2.5098,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00976997852474223,
      "loss": 2.5391,
      "step": 271
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.009767746518323914,
      "loss": 2.4688,
      "step": 272
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009765503992478703,
      "loss": 2.4824,
      "step": 273
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009763250952154448,
      "loss": 2.5293,
      "step": 274
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009760987402322195,
      "loss": 2.4805,
      "step": 275
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009758713347976178,
      "loss": 2.5254,
      "step": 276
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00975642879413381,
      "loss": 2.584,
      "step": 277
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009754133745835666,
      "loss": 2.5879,
      "step": 278
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00975182820814548,
      "loss": 2.584,
      "step": 279
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009749512186150132,
      "loss": 2.4785,
      "step": 280
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009747185684959626,
      "loss": 2.6094,
      "step": 281
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00974484870970709,
      "loss": 2.5332,
      "step": 282
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009742501265548766,
      "loss": 2.498,
      "step": 283
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009740143357663994,
      "loss": 2.5293,
      "step": 284
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00973777499125519,
      "loss": 2.5137,
      "step": 285
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00973539617154786,
      "loss": 2.5605,
      "step": 286
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009733006903790564,
      "loss": 2.5137,
      "step": 287
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009730607193254921,
      "loss": 2.4902,
      "step": 288
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009728197045235585,
      "loss": 2.4883,
      "step": 289
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009725776465050242,
      "loss": 2.4551,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009723345458039594,
      "loss": 2.5273,
      "step": 291
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00972090402956735,
      "loss": 2.4824,
      "step": 292
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009718452185020212,
      "loss": 2.4141,
      "step": 293
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.009715989929807862,
      "loss": 2.5137,
      "step": 294
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009713517269362955,
      "loss": 2.5293,
      "step": 295
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0097110342091411,
      "loss": 2.502,
      "step": 296
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009708540754620855,
      "loss": 2.4414,
      "step": 297
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009706036911303713,
      "loss": 2.5527,
      "step": 298
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009703522684714081,
      "loss": 2.5254,
      "step": 299
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009700998080399285,
      "loss": 2.4492,
      "step": 300
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009698463103929543,
      "loss": 2.4434,
      "step": 301
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009695917760897954,
      "loss": 2.4082,
      "step": 302
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0096933620569205,
      "loss": 2.3809,
      "step": 303
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009690795997636016,
      "loss": 2.4746,
      "step": 304
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009688219588706179,
      "loss": 2.4805,
      "step": 305
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009685632835815517,
      "loss": 2.4277,
      "step": 306
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009683035744671368,
      "loss": 2.4355,
      "step": 307
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009680428321003883,
      "loss": 2.4434,
      "step": 308
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00967781057056601,
      "loss": 2.4668,
      "step": 309
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009675182499133485,
      "loss": 2.4336,
      "step": 310
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009672544112504813,
      "loss": 2.4668,
      "step": 311
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009669895416501258,
      "loss": 2.457,
      "step": 312
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009667236416966832,
      "loss": 2.4453,
      "step": 313
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009664567119768281,
      "loss": 2.4277,
      "step": 314
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009661887530795067,
      "loss": 2.4375,
      "step": 315
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.009659197655959365,
      "loss": 2.2949,
      "step": 316
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00965649750119604,
      "loss": 2.4512,
      "step": 317
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009653787072462642,
      "loss": 2.5,
      "step": 318
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009651066375739387,
      "loss": 2.5078,
      "step": 319
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00964833541702915,
      "loss": 2.4746,
      "step": 320
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009645594202357438,
      "loss": 2.4688,
      "step": 321
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009642842737772397,
      "loss": 2.3379,
      "step": 322
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009640081029344784,
      "loss": 2.5332,
      "step": 323
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009637309083167955,
      "loss": 2.3594,
      "step": 324
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00963452690535786,
      "loss": 2.5078,
      "step": 325
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00963173450205302,
      "loss": 2.4512,
      "step": 326
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009628931879414517,
      "loss": 2.4336,
      "step": 327
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009626119043625982,
      "loss": 2.5039,
      "step": 328
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009623296000893582,
      "loss": 2.4648,
      "step": 329
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009620462757446,
      "loss": 2.457,
      "step": 330
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009617619319534428,
      "loss": 2.5059,
      "step": 331
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00961476569343255,
      "loss": 2.5273,
      "step": 332
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009611901885436529,
      "loss": 2.4707,
      "step": 333
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009609027901864997,
      "loss": 2.5176,
      "step": 334
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00960614374905903,
      "loss": 2.4492,
      "step": 335
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009603249433382144,
      "loss": 2.4141,
      "step": 336
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009600344961220282,
      "loss": 2.4766,
      "step": 337
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.009597430338981791,
      "loss": 2.4785,
      "step": 338
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009594505573097415,
      "loss": 2.4004,
      "step": 339
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009591570670020278,
      "loss": 2.416,
      "step": 340
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00958862563622587,
      "loss": 2.4121,
      "step": 341
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009585670478212037,
      "loss": 2.377,
      "step": 342
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009582705202498955,
      "loss": 2.4297,
      "step": 343
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009579729815629132,
      "loss": 2.4199,
      "step": 344
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009576744324167379,
      "loss": 2.4336,
      "step": 345
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009573748734700805,
      "loss": 2.4277,
      "step": 346
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009570743053838796,
      "loss": 2.4941,
      "step": 347
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009567727288213004,
      "loss": 2.3359,
      "step": 348
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009564701444477337,
      "loss": 2.4785,
      "step": 349
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00956166552930793,
      "loss": 2.5176,
      "step": 350
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009558619549403147,
      "loss": 2.4121,
      "step": 351
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009555563511483555,
      "loss": 2.415,
      "step": 352
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009552497422291913,
      "loss": 2.4473,
      "step": 353
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009549421288593157,
      "loss": 2.4648,
      "step": 354
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009546335117174384,
      "loss": 2.4043,
      "step": 355
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009543238914844843,
      "loss": 2.4277,
      "step": 356
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009540132688435907,
      "loss": 2.4375,
      "step": 357
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009537016444801073,
      "loss": 2.375,
      "step": 358
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.009533890190815934,
      "loss": 2.3066,
      "step": 359
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009530753933378173,
      "loss": 2.5137,
      "step": 360
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009527607679407545,
      "loss": 2.3926,
      "step": 361
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009524451435845857,
      "loss": 2.3828,
      "step": 362
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009521285209656963,
      "loss": 2.4531,
      "step": 363
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009518109007826734,
      "loss": 2.4082,
      "step": 364
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00951492283736306,
      "loss": 2.4434,
      "step": 365
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009511726705295818,
      "loss": 2.377,
      "step": 366
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00950852061867687,
      "loss": 2.4336,
      "step": 367
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009505304584580038,
      "loss": 2.4316,
      "step": 368
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009502078610101092,
      "loss": 2.4824,
      "step": 369
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009498842702357735,
      "loss": 2.4023,
      "step": 370
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009495596868489586,
      "loss": 2.3906,
      "step": 371
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009492341115658167,
      "loss": 2.4043,
      "step": 372
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009489075451046878,
      "loss": 2.3867,
      "step": 373
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009485799881860999,
      "loss": 2.4355,
      "step": 374
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009482514415327655,
      "loss": 2.4102,
      "step": 375
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00947921905869581,
      "loss": 2.3926,
      "step": 376
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009475913819236249,
      "loss": 2.2676,
      "step": 377
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009472598704241561,
      "loss": 2.4043,
      "step": 378
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009469273721026131,
      "loss": 2.4395,
      "step": 379
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00946593887692611,
      "loss": 2.3887,
      "step": 380
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.009462594179299406,
      "loss": 2.2852,
      "step": 381
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009459239635525672,
      "loss": 2.3828,
      "step": 382
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009455875253006282,
      "loss": 2.5332,
      "step": 383
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009452501039164314,
      "loss": 2.3652,
      "step": 384
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00944911700144455,
      "loss": 2.3828,
      "step": 385
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009445723147313434,
      "loss": 2.373,
      "step": 386
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009442319484259075,
      "loss": 2.3281,
      "step": 387
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009438906019791223,
      "loss": 2.3945,
      "step": 388
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009435482761441252,
      "loss": 2.4648,
      "step": 389
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00943204971676215,
      "loss": 2.3555,
      "step": 390
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009428606893328494,
      "loss": 2.373,
      "step": 391
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009425154298736431,
      "loss": 2.4473,
      "step": 392
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009421691940603678,
      "loss": 2.4746,
      "step": 393
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009418219826569487,
      "loss": 2.3359,
      "step": 394
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009414737964294635,
      "loss": 2.4688,
      "step": 395
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00941124636146141,
      "loss": 2.3906,
      "step": 396
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009407745025773588,
      "loss": 2.3203,
      "step": 397
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009404233964956423,
      "loss": 2.3828,
      "step": 398
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009400713186756624,
      "loss": 2.2539,
      "step": 399
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009397182698942342,
      "loss": 2.4062,
      "step": 400
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009393642509303149,
      "loss": 2.4102,
      "step": 401
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009390092625650022,
      "loss": 2.3145,
      "step": 402
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.009386533055815332,
      "loss": 2.377,
      "step": 403
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009382963807652814,
      "loss": 2.3301,
      "step": 404
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009379384889037562,
      "loss": 2.4219,
      "step": 405
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009375796307866002,
      "loss": 2.3555,
      "step": 406
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009372198072055889,
      "loss": 2.3223,
      "step": 407
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009368590189546267,
      "loss": 2.4531,
      "step": 408
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009364972668297474,
      "loss": 2.4199,
      "step": 409
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00936134551629111,
      "loss": 2.375,
      "step": 410
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009357708741530024,
      "loss": 2.3848,
      "step": 411
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0093540623520383,
      "loss": 2.3594,
      "step": 412
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00935040635586123,
      "loss": 2.3984,
      "step": 413
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009346740761065305,
      "loss": 2.4199,
      "step": 414
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009343065575738196,
      "loss": 2.2754,
      "step": 415
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009339380807988733,
      "loss": 2.3672,
      "step": 416
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009335686465946886,
      "loss": 2.4609,
      "step": 417
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009331982557763754,
      "loss": 2.3555,
      "step": 418
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009328269091611536,
      "loss": 2.4453,
      "step": 419
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009324546075683525,
      "loss": 2.3848,
      "step": 420
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009320813518194084,
      "loss": 2.2324,
      "step": 421
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009317071427378623,
      "loss": 2.3066,
      "step": 422
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.009313319811493595,
      "loss": 2.4531,
      "step": 423
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00930955867881646,
      "loss": 2.334,
      "step": 424
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00930578803764568,
      "loss": 2.375,
      "step": 425
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009302007896300698,
      "loss": 2.3418,
      "step": 426
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009298218263121912,
      "loss": 2.3848,
      "step": 427
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009294419146470667,
      "loss": 2.377,
      "step": 428
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009290610554729234,
      "loss": 2.3906,
      "step": 429
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009286792496300784,
      "loss": 2.3477,
      "step": 430
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00928296497960938,
      "loss": 2.3984,
      "step": 431
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009279128013099948,
      "loss": 2.3594,
      "step": 432
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009275281605238269,
      "loss": 2.3633,
      "step": 433
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009271425764510953,
      "loss": 2.4023,
      "step": 434
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009267560499425424,
      "loss": 2.3613,
      "step": 435
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009263685818509894,
      "loss": 2.3477,
      "step": 436
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00925980173031336,
      "loss": 2.3672,
      "step": 437
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009255908243405567,
      "loss": 2.3887,
      "step": 438
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009252005366376997,
      "loss": 2.4297,
      "step": 439
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009248093107838851,
      "loss": 2.373,
      "step": 440
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009244171476423037,
      "loss": 2.3975,
      "step": 441
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00924024048078213,
      "loss": 2.2969,
      "step": 442
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009236300129589375,
      "loss": 2.4844,
      "step": 443
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009232350431538656,
      "loss": 2.3203,
      "step": 444
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009228391395344482,
      "loss": 2.4297,
      "step": 445
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00922442302974196,
      "loss": 2.3848,
      "step": 446
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009220445343486785,
      "loss": 2.334,
      "step": 447
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009216458345355217,
      "loss": 2.4102,
      "step": 448
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009212462044144061,
      "loss": 2.2793,
      "step": 449
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009208456448670648,
      "loss": 2.2676,
      "step": 450
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009204441567772816,
      "loss": 2.3828,
      "step": 451
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009200417410308888,
      "loss": 2.3965,
      "step": 452
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009196383985157656,
      "loss": 2.3418,
      "step": 453
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00919234130121836,
      "loss": 2.4551,
      "step": 454
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009188289367410672,
      "loss": 2.2793,
      "step": 455
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009184228192674667,
      "loss": 2.3027,
      "step": 456
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009180157785970807,
      "loss": 2.3359,
      "step": 457
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009176078156279932,
      "loss": 2.2617,
      "step": 458
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009171989312603226,
      "loss": 2.3613,
      "step": 459
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009167891263962202,
      "loss": 2.293,
      "step": 460
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009163784019398684,
      "loss": 2.4355,
      "step": 461
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009159667587974785,
      "loss": 2.3164,
      "step": 462
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009155541978772887,
      "loss": 2.2832,
      "step": 463
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009151407200895625,
      "loss": 2.3867,
      "step": 464
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00914726326346586,
      "loss": 2.2949,
      "step": 465
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00914311017562666,
      "loss": 2.3301,
      "step": 466
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.009138947946541291,
      "loss": 2.3711,
      "step": 467
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00913477658539318,
      "loss": 2.2344,
      "step": 468
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009130596101385906,
      "loss": 2.3848,
      "step": 469
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009126406503743174,
      "loss": 2.4395,
      "step": 470
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009122207801708802,
      "loss": 2.3203,
      "step": 471
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009118000004546689,
      "loss": 2.3477,
      "step": 472
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009113783121540807,
      "loss": 2.373,
      "step": 473
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009109557161995172,
      "loss": 2.3594,
      "step": 474
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009105322135233828,
      "loss": 2.3125,
      "step": 475
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009101078050600822,
      "loss": 2.3281,
      "step": 476
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009096824917460186,
      "loss": 2.4297,
      "step": 477
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00909256274519592,
      "loss": 2.4395,
      "step": 478
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009088291543211967,
      "loss": 2.3027,
      "step": 479
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009084011320932188,
      "loss": 2.3359,
      "step": 480
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009079722087800352,
      "loss": 2.3535,
      "step": 481
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009075423853280105,
      "loss": 2.3242,
      "step": 482
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00907111662685496,
      "loss": 2.3535,
      "step": 483
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009066800418028256,
      "loss": 2.3164,
      "step": 484
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009062475236323168,
      "loss": 2.3555,
      "step": 485
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009058141091282656,
      "loss": 2.3379,
      "step": 486
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00905379799246946,
      "loss": 2.4062,
      "step": 487
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009049445949466077,
      "loss": 2.3457,
      "step": 488
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009045084971874737,
      "loss": 2.2988,
      "step": 489
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.009040715069317383,
      "loss": 2.2197,
      "step": 490
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009036336251435647,
      "loss": 2.291,
      "step": 491
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009031948527890838,
      "loss": 2.375,
      "step": 492
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009027551908363908,
      "loss": 2.3398,
      "step": 493
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009023146402555441,
      "loss": 2.3828,
      "step": 494
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009018732020185626,
      "loss": 2.375,
      "step": 495
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009014308770994236,
      "loss": 2.2793,
      "step": 496
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009009876664740605,
      "loss": 2.2988,
      "step": 497
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.009005435711203618,
      "loss": 2.3457,
      "step": 498
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00900098592018167,
      "loss": 2.2246,
      "step": 499
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008996527301492663,
      "loss": 2.3359,
      "step": 500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008992059864973971,
      "loss": 2.2754,
      "step": 501
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008987583620482426,
      "loss": 2.3311,
      "step": 502
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008983098577894292,
      "loss": 2.3711,
      "step": 503
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008978604747105245,
      "loss": 2.2637,
      "step": 504
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008974102138030354,
      "loss": 2.2871,
      "step": 505
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00896959076060405,
      "loss": 2.3223,
      "step": 506
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008965070624780117,
      "loss": 2.2051,
      "step": 507
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008960541740531658,
      "loss": 2.4316,
      "step": 508
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008956004117851083,
      "loss": 2.3867,
      "step": 509
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00895145776675008,
      "loss": 2.3164,
      "step": 510
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008946902697259593,
      "loss": 2.293,
      "step": 511
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.008942338919429806,
      "loss": 2.2559,
      "step": 512
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008937766443330114,
      "loss": 2.2324,
      "step": 513
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008933185279049103,
      "loss": 2.3477,
      "step": 514
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008928595436694532,
      "loss": 2.3145,
      "step": 515
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008923996926393306,
      "loss": 2.2715,
      "step": 516
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00891938975829145,
      "loss": 2.3691,
      "step": 517
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008914773942554098,
      "loss": 2.2959,
      "step": 518
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00891014948936546,
      "loss": 2.3418,
      "step": 519
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008905516408928804,
      "loss": 2.3379,
      "step": 520
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008900874711466434,
      "loss": 2.2871,
      "step": 521
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008896224407219667,
      "loss": 2.3086,
      "step": 522
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008891565506448804,
      "loss": 2.3359,
      "step": 523
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008886898019433122,
      "loss": 2.1797,
      "step": 524
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008882221956470836,
      "loss": 2.373,
      "step": 525
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008877537327879086,
      "loss": 2.3516,
      "step": 526
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008872844143993908,
      "loss": 2.2031,
      "step": 527
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008868142415170217,
      "loss": 2.3574,
      "step": 528
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00886343215178178,
      "loss": 2.3828,
      "step": 529
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008858713364221196,
      "loss": 2.3311,
      "step": 530
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008853986062899869,
      "loss": 2.2764,
      "step": 531
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008849250258247987,
      "loss": 2.3633,
      "step": 532
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008844505960714504,
      "loss": 2.2812,
      "step": 533
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.008839753180767107,
      "loss": 2.2656,
      "step": 534
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008834991928892205,
      "loss": 2.3809,
      "step": 535
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00883022221559489,
      "loss": 2.3457,
      "step": 536
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008825444051398934,
      "loss": 2.3613,
      "step": 537
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008820657446846744,
      "loss": 2.3555,
      "step": 538
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00881586241249936,
      "loss": 2.3867,
      "step": 539
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008811058958936411,
      "loss": 2.3613,
      "step": 540
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00880624709675611,
      "loss": 2.3594,
      "step": 541
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00880142683657522,
      "loss": 2.3164,
      "step": 542
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00879659818902903,
      "loss": 2.3145,
      "step": 543
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008791761164771338,
      "loss": 2.3672,
      "step": 544
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008786915774474425,
      "loss": 2.3027,
      "step": 545
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008782062028829028,
      "loss": 2.3477,
      "step": 546
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008777199938544318,
      "loss": 2.3516,
      "step": 547
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008772329514347883,
      "loss": 2.2461,
      "step": 548
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008767450766985693,
      "loss": 2.3242,
      "step": 549
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008762563707222086,
      "loss": 2.3672,
      "step": 550
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008757668345839738,
      "loss": 2.4902,
      "step": 551
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008752764693639638,
      "loss": 2.3574,
      "step": 552
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008747852761441077,
      "loss": 2.209,
      "step": 553
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008742932560081606,
      "loss": 2.2773,
      "step": 554
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008738004100417026,
      "loss": 2.3047,
      "step": 555
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.008733067393321355,
      "loss": 2.3711,
      "step": 556
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00872812244968681,
      "loss": 2.3242,
      "step": 557
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008723169280423784,
      "loss": 2.3965,
      "step": 558
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008718207896460812,
      "loss": 2.3555,
      "step": 559
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008713238308744558,
      "loss": 2.4004,
      "step": 560
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00870826052823979,
      "loss": 2.334,
      "step": 561
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00870327456592934,
      "loss": 2.3242,
      "step": 562
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008698280432814107,
      "loss": 2.3691,
      "step": 563
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00869327813991301,
      "loss": 2.3691,
      "step": 564
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008688267698262971,
      "loss": 2.3496,
      "step": 565
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008683249118918894,
      "loss": 2.2969,
      "step": 566
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008678222412953638,
      "loss": 2.3867,
      "step": 567
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008673187591457987,
      "loss": 2.4727,
      "step": 568
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008668144665540637,
      "loss": 2.3203,
      "step": 569
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008663093646328167,
      "loss": 2.334,
      "step": 570
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008658034544965004,
      "loss": 2.3047,
      "step": 571
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008652967372613412,
      "loss": 2.2852,
      "step": 572
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008647892140453466,
      "loss": 2.3438,
      "step": 573
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008642808859683021,
      "loss": 2.3086,
      "step": 574
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00863771754151769,
      "loss": 2.3691,
      "step": 575
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008632618197190816,
      "loss": 2.377,
      "step": 576
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.008627510837953458,
      "loss": 2.3633,
      "step": 577
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008622395475074355,
      "loss": 2.3184,
      "step": 578
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008617272119839902,
      "loss": 2.2686,
      "step": 579
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008612140783554137,
      "loss": 2.2441,
      "step": 580
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008607001477538696,
      "loss": 2.2988,
      "step": 581
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008601854213132807,
      "loss": 2.4629,
      "step": 582
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008596699001693256,
      "loss": 2.2969,
      "step": 583
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00859153585459436,
      "loss": 2.3848,
      "step": 584
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008586364783227949,
      "loss": 2.2988,
      "step": 585
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008581185799003332,
      "loss": 2.3145,
      "step": 586
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008575998913347283,
      "loss": 2.3145,
      "step": 587
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008570804137704004,
      "loss": 2.2715,
      "step": 588
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008565601483535109,
      "loss": 2.2188,
      "step": 589
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008560390962319591,
      "loss": 2.2148,
      "step": 590
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008555172585553805,
      "loss": 2.2598,
      "step": 591
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008549946364751435,
      "loss": 2.2812,
      "step": 592
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008544712311443475,
      "loss": 2.2852,
      "step": 593
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008539470437178197,
      "loss": 2.3457,
      "step": 594
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00853422075352113,
      "loss": 2.293,
      "step": 595
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008528963272055035,
      "loss": 2.3047,
      "step": 596
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008523698004379876,
      "loss": 2.2734,
      "step": 597
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0085184249621128,
      "loss": 2.3564,
      "step": 598
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.008513144156888102,
      "loss": 2.373,
      "step": 599
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008507855600357207,
      "loss": 2.3555,
      "step": 600
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008502559304188645,
      "loss": 2.3457,
      "step": 601
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00849725528006802,
      "loss": 2.3848,
      "step": 602
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008491943539697986,
      "loss": 2.2344,
      "step": 603
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008486624094798225,
      "loss": 2.2539,
      "step": 604
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008481296957105417,
      "loss": 2.3574,
      "step": 605
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008475962138373212,
      "loss": 2.2773,
      "step": 606
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008470619650372211,
      "loss": 2.3125,
      "step": 607
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008465269504889935,
      "loss": 2.3906,
      "step": 608
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008459911713730799,
      "loss": 2.2871,
      "step": 609
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00845454628871609,
      "loss": 2.332,
      "step": 610
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008449173241683934,
      "loss": 2.2793,
      "step": 611
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00844379258448928,
      "loss": 2.248,
      "step": 612
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008438404329003864,
      "loss": 2.375,
      "step": 613
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008433008487116183,
      "loss": 2.3398,
      "step": 614
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008427605070731481,
      "loss": 2.252,
      "step": 615
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00842219409177171,
      "loss": 2.3477,
      "step": 616
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008416775562175502,
      "loss": 2.2812,
      "step": 617
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00841134949389816,
      "loss": 2.3145,
      "step": 618
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008405915898911612,
      "loss": 2.293,
      "step": 619
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008400474789204396,
      "loss": 2.2139,
      "step": 620
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.008395026176781626,
      "loss": 2.291,
      "step": 621
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008389570073664976,
      "loss": 2.373,
      "step": 622
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008384106491892642,
      "loss": 2.2812,
      "step": 623
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008378635443519326,
      "loss": 2.2988,
      "step": 624
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0083731569406162,
      "loss": 2.3613,
      "step": 625
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008367670995270882,
      "loss": 2.4238,
      "step": 626
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008362177619587416,
      "loss": 2.2637,
      "step": 627
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008356676825686239,
      "loss": 2.2539,
      "step": 628
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008351168625704147,
      "loss": 2.377,
      "step": 629
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008345653031794291,
      "loss": 2.3477,
      "step": 630
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008340130056126126,
      "loss": 2.3203,
      "step": 631
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008334599710885394,
      "loss": 2.2188,
      "step": 632
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008329062008274098,
      "loss": 2.207,
      "step": 633
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00832351696051048,
      "loss": 2.3613,
      "step": 634
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00831796457982898,
      "loss": 2.377,
      "step": 635
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008312404878480222,
      "loss": 2.3672,
      "step": 636
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008306837868730979,
      "loss": 2.3672,
      "step": 637
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008301263562864153,
      "loss": 2.3066,
      "step": 638
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008295681973178736,
      "loss": 2.3008,
      "step": 639
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008290093111989805,
      "loss": 2.375,
      "step": 640
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008284496991628466,
      "loss": 2.3408,
      "step": 641
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.008278893624441848,
      "loss": 2.2793,
      "step": 642
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00827328302279307,
      "loss": 2.375,
      "step": 643
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008267665199061212,
      "loss": 2.1699,
      "step": 644
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008262040165641287,
      "loss": 2.3223,
      "step": 645
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00825640793494422,
      "loss": 2.3633,
      "step": 646
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008250768519396807,
      "loss": 2.2773,
      "step": 647
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008245121931441706,
      "loss": 2.2197,
      "step": 648
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008239468183537393,
      "loss": 2.3105,
      "step": 649
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008233807288158146,
      "loss": 2.3379,
      "step": 650
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008228139257794012,
      "loss": 2.2227,
      "step": 651
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00822246410495078,
      "loss": 2.2539,
      "step": 652
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00821678184214995,
      "loss": 2.2402,
      "step": 653
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008211092481928715,
      "loss": 2.3359,
      "step": 654
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008205396036839927,
      "loss": 2.3125,
      "step": 655
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00819969251945207,
      "loss": 2.3105,
      "step": 656
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008193981942349224,
      "loss": 2.293,
      "step": 657
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008188264318131055,
      "loss": 2.3281,
      "step": 658
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008182539659412777,
      "loss": 2.2637,
      "step": 659
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008176807978825118,
      "loss": 2.1709,
      "step": 660
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008171069289014305,
      "loss": 2.3242,
      "step": 661
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008165323602642029,
      "loss": 2.3555,
      "step": 662
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008159570932385413,
      "loss": 2.2119,
      "step": 663
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008153811290936999,
      "loss": 2.2363,
      "step": 664
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.008148044691004698,
      "loss": 2.2617,
      "step": 665
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008142271145311783,
      "loss": 2.3438,
      "step": 666
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00813649066659685,
      "loss": 2.3184,
      "step": 667
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008130703267613787,
      "loss": 2.2656,
      "step": 668
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008124908961131758,
      "loss": 2.2305,
      "step": 669
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008119107759935162,
      "loss": 2.1982,
      "step": 670
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008113299676823614,
      "loss": 2.2188,
      "step": 671
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00810748472461191,
      "loss": 2.2686,
      "step": 672
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008101662916130006,
      "loss": 2.2578,
      "step": 673
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008095834264222978,
      "loss": 2.2012,
      "step": 674
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008089998781751009,
      "loss": 2.3848,
      "step": 675
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008084156481589349,
      "loss": 2.2988,
      "step": 676
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008078307376628291,
      "loss": 2.2812,
      "step": 677
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008072451479773143,
      "loss": 2.2432,
      "step": 678
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008066588803944195,
      "loss": 2.3047,
      "step": 679
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008060719362076696,
      "loss": 2.3125,
      "step": 680
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008054843167120827,
      "loss": 2.3184,
      "step": 681
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008048960232041663,
      "loss": 2.2578,
      "step": 682
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008043070569819153,
      "loss": 2.2109,
      "step": 683
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008037174193448089,
      "loss": 2.3867,
      "step": 684
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008031271115938076,
      "loss": 2.2617,
      "step": 685
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008025361350313506,
      "loss": 2.2314,
      "step": 686
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.008019444909613522,
      "loss": 2.3877,
      "step": 687
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.008013521806892004,
      "loss": 2.3867,
      "step": 688
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00800759205521752,
      "loss": 2.2441,
      "step": 689
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.008001655667673318,
      "loss": 2.332,
      "step": 690
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007995712657357278,
      "loss": 2.3301,
      "step": 691
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007989763037381904,
      "loss": 2.25,
      "step": 692
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007983806820874271,
      "loss": 2.2598,
      "step": 693
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007977844020976016,
      "loss": 2.3438,
      "step": 694
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0079718746508433,
      "loss": 2.2646,
      "step": 695
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007965898723646777,
      "loss": 2.2959,
      "step": 696
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007959916252571572,
      "loss": 2.2451,
      "step": 697
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00795392725081725,
      "loss": 2.2852,
      "step": 698
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007947931731597779,
      "loss": 2.3535,
      "step": 699
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007941929708141513,
      "loss": 2.3613,
      "step": 700
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007935921193691152,
      "loss": 2.2656,
      "step": 701
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007929906201503722,
      "loss": 2.3242,
      "step": 702
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007923884744850536,
      "loss": 2.1826,
      "step": 703
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007917856837017175,
      "loss": 2.3066,
      "step": 704
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007911822491303452,
      "loss": 2.1387,
      "step": 705
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007905781721023382,
      "loss": 2.1465,
      "step": 706
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00789973453950516,
      "loss": 2.3477,
      "step": 707
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.007893680960091121,
      "loss": 2.3262,
      "step": 708
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00788762099613772,
      "loss": 2.3105,
      "step": 709
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007881554661015498,
      "loss": 2.4004,
      "step": 710
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007875481968109051,
      "loss": 2.335,
      "step": 711
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007869402930817006,
      "loss": 2.293,
      "step": 712
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007863317562551988,
      "loss": 2.2441,
      "step": 713
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007857225876740584,
      "loss": 2.209,
      "step": 714
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007851127886823328,
      "loss": 2.3291,
      "step": 715
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007845023606254657,
      "loss": 2.2773,
      "step": 716
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007838913048502896,
      "loss": 2.2969,
      "step": 717
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007832796227050208,
      "loss": 2.291,
      "step": 718
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007826673155392587,
      "loss": 2.2656,
      "step": 719
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00782054384703981,
      "loss": 2.209,
      "step": 720
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007814408315515418,
      "loss": 2.252,
      "step": 721
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007808266574356682,
      "loss": 2.3105,
      "step": 722
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007802118637114574,
      "loss": 2.3398,
      "step": 723
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007795964517353734,
      "loss": 2.2217,
      "step": 724
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0077898042286524485,
      "loss": 2.2793,
      "step": 725
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007783637784602609,
      "loss": 2.3066,
      "step": 726
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007777465198809691,
      "loss": 2.3027,
      "step": 727
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007771286484892722,
      "loss": 2.332,
      "step": 728
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007765101656484251,
      "loss": 2.2578,
      "step": 729
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.007758910727230311,
      "loss": 2.3047,
      "step": 730
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0077527137107904045,
      "loss": 2.3574,
      "step": 731
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007746510620837459,
      "loss": 2.2188,
      "step": 732
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007740301471057807,
      "loss": 2.2598,
      "step": 733
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007734086275151145,
      "loss": 2.2637,
      "step": 734
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0077278650468305165,
      "loss": 2.291,
      "step": 735
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007721637799822268,
      "loss": 2.2148,
      "step": 736
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0077154045478660315,
      "loss": 2.3379,
      "step": 737
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0077091653047146845,
      "loss": 2.207,
      "step": 738
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007702920084134324,
      "loss": 2.2051,
      "step": 739
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007696668899904236,
      "loss": 2.3418,
      "step": 740
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007690411765816863,
      "loss": 2.4004,
      "step": 741
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007684148695677778,
      "loss": 2.2402,
      "step": 742
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007677879703305649,
      "loss": 2.3203,
      "step": 743
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00767160480253221,
      "loss": 2.2734,
      "step": 744
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007665324007202235,
      "loss": 2.3926,
      "step": 745
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007659037331173497,
      "loss": 2.2422,
      "step": 746
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0076527447883167525,
      "loss": 2.1719,
      "step": 747
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007646446392515692,
      "loss": 2.2773,
      "step": 748
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00764014215766693,
      "loss": 2.3242,
      "step": 749
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007633832097679958,
      "loss": 2.2383,
      "step": 750
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007627516226477123,
      "loss": 2.2129,
      "step": 751
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.007621194557993589,
      "loss": 2.3574,
      "step": 752
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007614867106177319,
      "loss": 2.3281,
      "step": 753
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007608533884989028,
      "loss": 2.2793,
      "step": 754
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007602194908402166,
      "loss": 2.3027,
      "step": 755
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007595850190402876,
      "loss": 2.2402,
      "step": 756
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007589499744989976,
      "loss": 2.3086,
      "step": 757
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0075831435861749156,
      "loss": 2.3789,
      "step": 758
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00757678172798175,
      "loss": 2.2891,
      "step": 759
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007570414184447112,
      "loss": 2.2715,
      "step": 760
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007564040969620179,
      "loss": 2.2539,
      "step": 761
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0075576620975626365,
      "loss": 2.3027,
      "step": 762
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007551277582348658,
      "loss": 2.2588,
      "step": 763
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007544887438064862,
      "loss": 2.334,
      "step": 764
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007538491678810294,
      "loss": 2.3145,
      "step": 765
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007532090318696382,
      "loss": 2.2344,
      "step": 766
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0075256833718469135,
      "loss": 2.2637,
      "step": 767
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007519270852398002,
      "loss": 2.3184,
      "step": 768
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00751285277449806,
      "loss": 2.2969,
      "step": 769
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.007506429152307757,
      "loss": 2.3145,
      "step": 770
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0075,
      "loss": 2.2891,
      "step": 771
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0074935653317599,
      "loss": 2.291,
      "step": 772
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0074871251617847304,
      "loss": 2.2422,
      "step": 773
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00748067950428391,
      "loss": 2.3223,
      "step": 774
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007474228373478964,
      "loss": 2.2461,
      "step": 775
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007467771783603492,
      "loss": 2.3691,
      "step": 776
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007461309748903138,
      "loss": 2.2988,
      "step": 777
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007454842283635563,
      "loss": 2.2285,
      "step": 778
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007448369402070404,
      "loss": 2.2471,
      "step": 779
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007441891118489255,
      "loss": 2.3867,
      "step": 780
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0074354074471856225,
      "loss": 2.2529,
      "step": 781
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007428918402464908,
      "loss": 2.2637,
      "step": 782
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007422423998644359,
      "loss": 2.3086,
      "step": 783
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007415924250053055,
      "loss": 2.2656,
      "step": 784
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0074094191710318644,
      "loss": 2.2373,
      "step": 785
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007402908775933419,
      "loss": 2.2871,
      "step": 786
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007396393079122077,
      "loss": 2.2461,
      "step": 787
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007389872094973896,
      "loss": 2.3418,
      "step": 788
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007383345837876601,
      "loss": 2.3242,
      "step": 789
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007376814322229544,
      "loss": 2.2236,
      "step": 790
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007370277562443688,
      "loss": 2.2969,
      "step": 791
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007363735572941564,
      "loss": 2.2891,
      "step": 792
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007357188368157236,
      "loss": 2.2559,
      "step": 793
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007350635962536284,
      "loss": 2.2666,
      "step": 794
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007344078370535756,
      "loss": 2.2188,
      "step": 795
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.007337515606624148,
      "loss": 2.3379,
      "step": 796
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007330947685281362,
      "loss": 2.3008,
      "step": 797
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007324374620998682,
      "loss": 2.1719,
      "step": 798
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00731779642827874,
      "loss": 2.2344,
      "step": 799
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0073112131216354825,
      "loss": 2.2812,
      "step": 800
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0073046247155941395,
      "loss": 2.3281,
      "step": 801
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007298031224691193,
      "loss": 2.3848,
      "step": 802
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0072914326634743384,
      "loss": 2.2324,
      "step": 803
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007284829046502467,
      "loss": 2.3379,
      "step": 804
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007278220388345619,
      "loss": 2.3281,
      "step": 805
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007271606703584958,
      "loss": 2.2129,
      "step": 806
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0072649880068127405,
      "loss": 2.1562,
      "step": 807
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007258364312632279,
      "loss": 2.2188,
      "step": 808
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007251735635657916,
      "loss": 2.2637,
      "step": 809
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007245101990514979,
      "loss": 2.2852,
      "step": 810
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0072384633918397695,
      "loss": 2.3066,
      "step": 811
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007231819854279508,
      "loss": 2.2988,
      "step": 812
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007225171392492315,
      "loss": 2.248,
      "step": 813
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007218518021147182,
      "loss": 2.2021,
      "step": 814
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007211859754923923,
      "loss": 2.3555,
      "step": 815
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007205196608513158,
      "loss": 2.2285,
      "step": 816
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.007198528596616273,
      "loss": 2.252,
      "step": 817
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007191855733945388,
      "loss": 2.1494,
      "step": 818
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007185178035223326,
      "loss": 2.2168,
      "step": 819
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007178495515183583,
      "loss": 2.167,
      "step": 820
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071718081885702905,
      "loss": 2.2266,
      "step": 821
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007165116070138183,
      "loss": 2.2324,
      "step": 822
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007158419174652569,
      "loss": 2.1562,
      "step": 823
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071517175168893,
      "loss": 2.2227,
      "step": 824
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071450111116347316,
      "loss": 2.2305,
      "step": 825
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071382999736856936,
      "loss": 2.3438,
      "step": 826
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007131584117849459,
      "loss": 2.252,
      "step": 827
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007124863558943713,
      "loss": 2.3594,
      "step": 828
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071181383117965135,
      "loss": 2.2676,
      "step": 829
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0071114083912462624,
      "loss": 2.248,
      "step": 830
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007104673812141676,
      "loss": 2.2129,
      "step": 831
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007097934589341746,
      "loss": 2.2441,
      "step": 832
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007091190737715711,
      "loss": 2.2773,
      "step": 833
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007084442272143026,
      "loss": 2.25,
      "step": 834
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007077689207513319,
      "loss": 2.2969,
      "step": 835
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007070931558726372,
      "loss": 2.3242,
      "step": 836
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007064169340692076,
      "loss": 2.3047,
      "step": 837
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007057402568330407,
      "loss": 2.21,
      "step": 838
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.007050631256571389,
      "loss": 2.291,
      "step": 839
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00704385542035506,
      "loss": 2.3633,
      "step": 840
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00703707507463144,
      "loss": 2.3018,
      "step": 841
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.007030290234360505,
      "loss": 2.292,
      "step": 842
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.007023500914512139,
      "loss": 2.2715,
      "step": 843
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0070167071300661155,
      "loss": 2.3242,
      "step": 844
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.007009908896012055,
      "loss": 2.2793,
      "step": 845
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.007003106227349398,
      "loss": 2.2012,
      "step": 846
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00699629913908737,
      "loss": 2.1992,
      "step": 847
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006989487646244943,
      "loss": 2.2715,
      "step": 848
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006982671763850814,
      "loss": 2.2227,
      "step": 849
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00697585150694336,
      "loss": 2.3066,
      "step": 850
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006969026890570611,
      "loss": 2.2324,
      "step": 851
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006962197929790216,
      "loss": 2.1416,
      "step": 852
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006955364639669409,
      "loss": 2.1719,
      "step": 853
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0069485270352849775,
      "loss": 2.2207,
      "step": 854
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006941685131723225,
      "loss": 2.2695,
      "step": 855
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006934838944079943,
      "loss": 2.2559,
      "step": 856
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006927988487460377,
      "loss": 2.2715,
      "step": 857
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006921133776979186,
      "loss": 2.2363,
      "step": 858
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006914274827760418,
      "loss": 2.2871,
      "step": 859
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006907411654937475,
      "loss": 2.1709,
      "step": 860
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.006900544273653074,
      "loss": 2.2695,
      "step": 861
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00689367269905922,
      "loss": 2.0889,
      "step": 862
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0068867969463171684,
      "loss": 2.1562,
      "step": 863
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006879917030597397,
      "loss": 2.249,
      "step": 864
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006873032967079561,
      "loss": 2.2871,
      "step": 865
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006866144770952474,
      "loss": 2.2344,
      "step": 866
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006859252457414067,
      "loss": 2.2178,
      "step": 867
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006852356041671352,
      "loss": 2.2383,
      "step": 868
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0068454555389403935,
      "loss": 2.293,
      "step": 869
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006838550964446276,
      "loss": 2.2461,
      "step": 870
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006831642333423067,
      "loss": 2.1836,
      "step": 871
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00682472966111378,
      "loss": 2.2031,
      "step": 872
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006817812962770348,
      "loss": 2.2715,
      "step": 873
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006810892253653589,
      "loss": 2.3613,
      "step": 874
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006803967549033167,
      "loss": 2.3066,
      "step": 875
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0067970388641875636,
      "loss": 2.1855,
      "step": 876
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006790106214404043,
      "loss": 2.3223,
      "step": 877
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0067831696149786135,
      "loss": 2.3555,
      "step": 878
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006776229081216001,
      "loss": 2.2783,
      "step": 879
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006769284628429612,
      "loss": 2.332,
      "step": 880
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.006762336271941498,
      "loss": 2.2031,
      "step": 881
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0067553840270823265,
      "loss": 2.2266,
      "step": 882
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0067484279091913416,
      "loss": 2.1289,
      "step": 883
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0067414679336163345,
      "loss": 2.2051,
      "step": 884
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006734504115713603,
      "loss": 2.2236,
      "step": 885
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006727536470847931,
      "loss": 2.3359,
      "step": 886
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0067205650143925405,
      "loss": 2.2227,
      "step": 887
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006713589761729063,
      "loss": 2.2383,
      "step": 888
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006706610728247508,
      "loss": 2.2637,
      "step": 889
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006699627929346227,
      "loss": 2.3242,
      "step": 890
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006692641380431879,
      "loss": 2.3057,
      "step": 891
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006685651096919393,
      "loss": 2.3105,
      "step": 892
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006678657094231944,
      "loss": 2.2773,
      "step": 893
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006671659387800909,
      "loss": 2.3301,
      "step": 894
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0066646579930658405,
      "loss": 2.2852,
      "step": 895
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006657652925474424,
      "loss": 2.2852,
      "step": 896
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006650644200482451,
      "loss": 2.1855,
      "step": 897
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006643631833553785,
      "loss": 2.2158,
      "step": 898
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006636615840160321,
      "loss": 2.3262,
      "step": 899
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006629596235781956,
      "loss": 2.3457,
      "step": 900
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006622573035906556,
      "loss": 2.2051,
      "step": 901
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00661554625602992,
      "loss": 2.2031,
      "step": 902
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006608515911655744,
      "loss": 2.2598,
      "step": 903
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00660148201829559,
      "loss": 2.291,
      "step": 904
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.006594444591468851,
      "loss": 2.1729,
      "step": 905
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0065874036467027134,
      "loss": 2.1729,
      "step": 906
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006580359199532127,
      "loss": 2.2148,
      "step": 907
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006573311265499771,
      "loss": 2.21,
      "step": 908
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006566259860156014,
      "loss": 2.2656,
      "step": 909
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006559204999058888,
      "loss": 2.2832,
      "step": 910
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006552146697774049,
      "loss": 2.2969,
      "step": 911
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006545084971874737,
      "loss": 2.2021,
      "step": 912
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006538019836941758,
      "loss": 2.1787,
      "step": 913
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006530951308563431,
      "loss": 2.2402,
      "step": 914
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006523879402335567,
      "loss": 2.3203,
      "step": 915
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006516804133861429,
      "loss": 2.2842,
      "step": 916
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006509725518751698,
      "loss": 2.3418,
      "step": 917
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006502643572624438,
      "loss": 2.3145,
      "step": 918
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006495558311105064,
      "loss": 2.1465,
      "step": 919
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0064884697498263045,
      "loss": 2.3105,
      "step": 920
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00648137790442817,
      "loss": 2.2744,
      "step": 921
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006474282790557916,
      "loss": 2.1934,
      "step": 922
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006467184423870009,
      "loss": 2.2852,
      "step": 923
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006460082820026095,
      "loss": 2.3281,
      "step": 924
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.006452977994694959,
      "loss": 2.2383,
      "step": 925
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0064458699635524955,
      "loss": 2.3779,
      "step": 926
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006438758742281672,
      "loss": 2.2461,
      "step": 927
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006431644346572495,
      "loss": 2.2031,
      "step": 928
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006424526792121974,
      "loss": 2.2559,
      "step": 929
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006417406094634089,
      "loss": 2.2725,
      "step": 930
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006410282269819756,
      "loss": 2.2188,
      "step": 931
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0064031553333967865,
      "loss": 2.2412,
      "step": 932
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006396025301089863,
      "loss": 2.2344,
      "step": 933
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006388892188630493,
      "loss": 2.2598,
      "step": 934
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006381756011756983,
      "loss": 2.3574,
      "step": 935
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006374616786214402,
      "loss": 2.2969,
      "step": 936
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006367474527754545,
      "loss": 2.2363,
      "step": 937
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006360329252135893,
      "loss": 2.1523,
      "step": 938
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006353180975123595,
      "loss": 2.1895,
      "step": 939
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0063460297124894125,
      "loss": 2.249,
      "step": 940
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006338875480011698,
      "loss": 2.2637,
      "step": 941
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006331718293475357,
      "loss": 2.209,
      "step": 942
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006324558168671811,
      "loss": 2.2031,
      "step": 943
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006317395121398968,
      "loss": 2.2695,
      "step": 944
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006310229167461179,
      "loss": 2.2148,
      "step": 945
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006303060322669214,
      "loss": 2.2148,
      "step": 946
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006295888602840214,
      "loss": 2.2246,
      "step": 947
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.006288714023797671,
      "loss": 2.1201,
      "step": 948
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0062815366013713805,
      "loss": 2.2031,
      "step": 949
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006274356351397413,
      "loss": 2.2832,
      "step": 950
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0062671732897180785,
      "loss": 2.2715,
      "step": 951
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006259987432181891,
      "loss": 2.2891,
      "step": 952
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006252798794643529,
      "loss": 2.2334,
      "step": 953
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00624560739296381,
      "loss": 2.2188,
      "step": 954
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006238413243009647,
      "loss": 2.1973,
      "step": 955
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006231216360654019,
      "loss": 2.2578,
      "step": 956
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006224016761775933,
      "loss": 2.2402,
      "step": 957
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006216814462260385,
      "loss": 2.292,
      "step": 958
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0062096094779983384,
      "loss": 2.2861,
      "step": 959
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006202401824886674,
      "loss": 2.2949,
      "step": 960
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006195191518828163,
      "loss": 2.2061,
      "step": 961
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006187978575731428,
      "loss": 2.2422,
      "step": 962
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006180763011510912,
      "loss": 2.2969,
      "step": 963
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00617354484208684,
      "loss": 2.1338,
      "step": 964
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0061663240833851884,
      "loss": 2.2988,
      "step": 965
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006159100751337642,
      "loss": 2.2305,
      "step": 966
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006151874861881564,
      "loss": 2.2891,
      "step": 967
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006144646430959964,
      "loss": 2.3281,
      "step": 968
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006137415474521454,
      "loss": 2.3105,
      "step": 969
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.006130182008520222,
      "loss": 2.2598,
      "step": 970
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006122946048915991,
      "loss": 2.1729,
      "step": 971
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006115707611673986,
      "loss": 2.2773,
      "step": 972
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006108466712764902,
      "loss": 2.2832,
      "step": 973
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006101223368164857,
      "loss": 2.3457,
      "step": 974
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006093977593855375,
      "loss": 2.1895,
      "step": 975
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006086729405823335,
      "loss": 2.1992,
      "step": 976
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006079478820060943,
      "loss": 2.2617,
      "step": 977
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006072225852565695,
      "loss": 2.2061,
      "step": 978
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006064970519340342,
      "loss": 2.1523,
      "step": 979
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006057712836392856,
      "loss": 2.1855,
      "step": 980
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0060504528197363894,
      "loss": 2.2715,
      "step": 981
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006043190485389251,
      "loss": 2.2793,
      "step": 982
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0060359258493748544,
      "loss": 2.2891,
      "step": 983
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006028658927721697,
      "loss": 2.2949,
      "step": 984
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006021389736463321,
      "loss": 2.1992,
      "step": 985
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0060141182916382705,
      "loss": 2.1797,
      "step": 986
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.006006844609290065,
      "loss": 2.2715,
      "step": 987
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.005999568705467161,
      "loss": 2.2559,
      "step": 988
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.005992290596222916,
      "loss": 2.3652,
      "step": 989
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.005985010297615551,
      "loss": 2.2734,
      "step": 990
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.005977727825708122,
      "loss": 2.2471,
      "step": 991
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.005970443196568478,
      "loss": 2.168,
      "step": 992
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005963156426269227,
      "loss": 2.1631,
      "step": 993
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005955867530887702,
      "loss": 2.2754,
      "step": 994
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005948576526505924,
      "loss": 2.1768,
      "step": 995
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005941283429210568,
      "loss": 2.2227,
      "step": 996
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005933988255092926,
      "loss": 2.3027,
      "step": 997
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005926691020248874,
      "loss": 2.1504,
      "step": 998
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005919391740778832,
      "loss": 2.2422,
      "step": 999
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005912090432787735,
      "loss": 2.2559,
      "step": 1000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005904787112384991,
      "loss": 2.2598,
      "step": 1001
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005897481795684446,
      "loss": 2.2422,
      "step": 1002
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005890174498804355,
      "loss": 2.2773,
      "step": 1003
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005882865237867339,
      "loss": 2.2627,
      "step": 1004
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005875554029000353,
      "loss": 2.2227,
      "step": 1005
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005868240888334653,
      "loss": 2.251,
      "step": 1006
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005860925832005752,
      "loss": 2.1982,
      "step": 1007
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005853608876153394,
      "loss": 2.1914,
      "step": 1008
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005846290036921512,
      "loss": 2.248,
      "step": 1009
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005838969330458195,
      "loss": 2.3164,
      "step": 1010
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005831646772915651,
      "loss": 2.252,
      "step": 1011
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005824322380450173,
      "loss": 2.3711,
      "step": 1012
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005816996169222102,
      "loss": 2.3145,
      "step": 1013
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.005809668155395793,
      "loss": 2.2383,
      "step": 1014
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005802338355139578,
      "loss": 2.1924,
      "step": 1015
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005795006784625728,
      "loss": 2.2285,
      "step": 1016
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005787673460030423,
      "loss": 2.2207,
      "step": 1017
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005780338397533711,
      "loss": 2.2354,
      "step": 1018
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005773001613319477,
      "loss": 2.2695,
      "step": 1019
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005765663123575401,
      "loss": 2.1992,
      "step": 1020
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00575832294449293,
      "loss": 2.2793,
      "step": 1021
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005750981092267237,
      "loss": 2.2803,
      "step": 1022
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005743637583097184,
      "loss": 2.2383,
      "step": 1023
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005736292433185292,
      "loss": 2.1621,
      "step": 1024
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0057289456587377,
      "loss": 2.2402,
      "step": 1025
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005721597275964134,
      "loss": 2.2852,
      "step": 1026
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005714247301077865,
      "loss": 2.3027,
      "step": 1027
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005706895750295682,
      "loss": 2.2061,
      "step": 1028
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0056995426398378434,
      "loss": 2.1426,
      "step": 1029
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005692187985928056,
      "loss": 2.3252,
      "step": 1030
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005684831804793427,
      "loss": 2.209,
      "step": 1031
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005677474112664438,
      "loss": 2.2754,
      "step": 1032
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0056701149257749,
      "loss": 2.1553,
      "step": 1033
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005662754260361925,
      "loss": 2.2891,
      "step": 1034
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.005655392132665884,
      "loss": 2.167,
      "step": 1035
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00564802855893038,
      "loss": 2.2227,
      "step": 1036
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005640663555402198,
      "loss": 2.2832,
      "step": 1037
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005633297138331285,
      "loss": 2.1973,
      "step": 1038
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005625929323970704,
      "loss": 2.2949,
      "step": 1039
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005618560128576603,
      "loss": 2.1992,
      "step": 1040
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005611189568408173,
      "loss": 2.2578,
      "step": 1041
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005603817659727619,
      "loss": 2.2754,
      "step": 1042
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00559644441880012,
      "loss": 2.2793,
      "step": 1043
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005589069861893799,
      "loss": 2.291,
      "step": 1044
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005581694005279672,
      "loss": 2.2559,
      "step": 1045
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0055743168652316365,
      "loss": 2.1729,
      "step": 1046
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005566938458026411,
      "loss": 2.2051,
      "step": 1047
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005559558799943513,
      "loss": 2.2568,
      "step": 1048
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005552177907265223,
      "loss": 2.2246,
      "step": 1049
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00554479579627654,
      "loss": 2.2891,
      "step": 1050
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005537412483265156,
      "loss": 2.3281,
      "step": 1051
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005530027984521413,
      "loss": 2.2305,
      "step": 1052
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0055226423163382676,
      "loss": 2.1338,
      "step": 1053
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005515255495011259,
      "loss": 2.2197,
      "step": 1054
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005507867536838471,
      "loss": 2.291,
      "step": 1055
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0055004784581204925,
      "loss": 2.2637,
      "step": 1056
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.005493088275160387,
      "loss": 2.252,
      "step": 1057
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005485697004263657,
      "loss": 2.2578,
      "step": 1058
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0054783046617382,
      "loss": 2.2891,
      "step": 1059
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005470911263894279,
      "loss": 2.1914,
      "step": 1060
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005463516827044491,
      "loss": 2.2422,
      "step": 1061
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005456121367503721,
      "loss": 2.293,
      "step": 1062
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0054487249015891075,
      "loss": 2.1855,
      "step": 1063
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005441327445620013,
      "loss": 2.2285,
      "step": 1064
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005433929015917988,
      "loss": 2.3203,
      "step": 1065
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005426529628806723,
      "loss": 2.2402,
      "step": 1066
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005419129300612029,
      "loss": 2.2188,
      "step": 1067
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005411728047661789,
      "loss": 2.2656,
      "step": 1068
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005404325886285927,
      "loss": 2.1855,
      "step": 1069
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00539692283281637,
      "loss": 2.2588,
      "step": 1070
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005389518903587016,
      "loss": 2.2422,
      "step": 1071
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005382114114933695,
      "loss": 2.2695,
      "step": 1072
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005374708483194132,
      "loss": 2.1348,
      "step": 1073
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005367302024707911,
      "loss": 2.1816,
      "step": 1074
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005359894755816444,
      "loss": 2.2773,
      "step": 1075
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005352486692862926,
      "loss": 2.2354,
      "step": 1076
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005345077852192307,
      "loss": 2.3379,
      "step": 1077
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005337668250151254,
      "loss": 2.2012,
      "step": 1078
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.005330257903088112,
      "loss": 2.2578,
      "step": 1079
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005322846827352869,
      "loss": 2.1582,
      "step": 1080
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005315435039297124,
      "loss": 2.2656,
      "step": 1081
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005308022555274045,
      "loss": 2.1855,
      "step": 1082
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005300609391638336,
      "loss": 2.2139,
      "step": 1083
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005293195564746201,
      "loss": 2.2422,
      "step": 1084
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005285781090955304,
      "loss": 2.2695,
      "step": 1085
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005278365986624742,
      "loss": 2.2266,
      "step": 1086
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005270950268115,
      "loss": 2.1768,
      "step": 1087
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00526353395178792,
      "loss": 2.1455,
      "step": 1088
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00525611705400666,
      "loss": 2.209,
      "step": 1089
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005248699591135664,
      "loss": 2.1895,
      "step": 1090
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005241281579540619,
      "loss": 2.2266,
      "step": 1091
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005233863035588426,
      "loss": 2.1533,
      "step": 1092
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005226443975647162,
      "loss": 2.1934,
      "step": 1093
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0052190244160860355,
      "loss": 2.2656,
      "step": 1094
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005211604373275366,
      "loss": 2.2148,
      "step": 1095
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005204183863586533,
      "loss": 2.2646,
      "step": 1096
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005196762903391951,
      "loss": 2.2969,
      "step": 1097
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005189341509065023,
      "loss": 2.2139,
      "step": 1098
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005181919696980112,
      "loss": 2.2627,
      "step": 1099
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005174497483512506,
      "loss": 2.1738,
      "step": 1100
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.005167074885038373,
      "loss": 2.2422,
      "step": 1101
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0051596519179347355,
      "loss": 2.2197,
      "step": 1102
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005152228598579428,
      "loss": 2.248,
      "step": 1103
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00514480494335106,
      "loss": 2.25,
      "step": 1104
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005137380968628983,
      "loss": 2.127,
      "step": 1105
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005129956690793255,
      "loss": 2.1475,
      "step": 1106
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0051225321262246,
      "loss": 2.1934,
      "step": 1107
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005115107291304378,
      "loss": 2.1494,
      "step": 1108
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005107682202414544,
      "loss": 2.2129,
      "step": 1109
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005100256875937613,
      "loss": 2.1621,
      "step": 1110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005092831328256625,
      "loss": 2.1543,
      "step": 1111
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005085405575755105,
      "loss": 2.2295,
      "step": 1112
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005077979634817034,
      "loss": 2.2148,
      "step": 1113
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005070553521826808,
      "loss": 2.3262,
      "step": 1114
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0050631272531692,
      "loss": 2.1377,
      "step": 1115
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005055700845229327,
      "loss": 2.1699,
      "step": 1116
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005048274314392621,
      "loss": 2.168,
      "step": 1117
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005040847677044771,
      "loss": 2.208,
      "step": 1118
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005033420949571712,
      "loss": 2.2754,
      "step": 1119
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0050259941483595735,
      "loss": 2.2812,
      "step": 1120
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005018567289794651,
      "loss": 2.2041,
      "step": 1121
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005011140390263362,
      "loss": 2.2383,
      "step": 1122
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.005003713466152217,
      "loss": 2.2637,
      "step": 1123
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004996286533847783,
      "loss": 2.2852,
      "step": 1124
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0049888596097366405,
      "loss": 2.167,
      "step": 1125
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004981432710205351,
      "loss": 2.3008,
      "step": 1126
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0049740058516404275,
      "loss": 2.2402,
      "step": 1127
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0049665790504282905,
      "loss": 2.1562,
      "step": 1128
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004959152322955232,
      "loss": 2.2012,
      "step": 1129
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004951725685607381,
      "loss": 2.1982,
      "step": 1130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004944299154770673,
      "loss": 2.2773,
      "step": 1131
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004936872746830803,
      "loss": 2.2461,
      "step": 1132
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004929446478173194,
      "loss": 2.1611,
      "step": 1133
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004922020365182967,
      "loss": 2.2363,
      "step": 1134
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004914594424244897,
      "loss": 2.2441,
      "step": 1135
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004907168671743377,
      "loss": 2.2715,
      "step": 1136
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004899743124062388,
      "loss": 2.2344,
      "step": 1137
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004892317797585456,
      "loss": 2.291,
      "step": 1138
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004884892708695623,
      "loss": 2.2363,
      "step": 1139
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004877467873775402,
      "loss": 2.2568,
      "step": 1140
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004870043309206747,
      "loss": 2.1641,
      "step": 1141
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004862619031371019,
      "loss": 2.1689,
      "step": 1142
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004855195056648941,
      "loss": 2.1895,
      "step": 1143
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004847771401420573,
      "loss": 2.2383,
      "step": 1144
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.004840348082065265,
      "loss": 2.1367,
      "step": 1145
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004832925114961629,
      "loss": 2.2695,
      "step": 1146
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004825502516487497,
      "loss": 2.2129,
      "step": 1147
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004818080303019889,
      "loss": 2.2461,
      "step": 1148
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004810658490934979,
      "loss": 2.2305,
      "step": 1149
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00480323709660805,
      "loss": 2.2393,
      "step": 1150
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004795816136413467,
      "loss": 2.2266,
      "step": 1151
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004788395626724636,
      "loss": 2.2012,
      "step": 1152
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004780975583913966,
      "loss": 2.2969,
      "step": 1153
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004773556024352841,
      "loss": 2.3789,
      "step": 1154
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004766136964411576,
      "loss": 2.2598,
      "step": 1155
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004758718420459383,
      "loss": 2.2871,
      "step": 1156
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004751300408864338,
      "loss": 2.2236,
      "step": 1157
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0047438829459933414,
      "loss": 2.1875,
      "step": 1158
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004736466048212082,
      "loss": 2.1162,
      "step": 1159
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004729049731885002,
      "loss": 2.1914,
      "step": 1160
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00472163401337526,
      "loss": 2.1572,
      "step": 1161
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004714218909044699,
      "loss": 2.1641,
      "step": 1162
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004706804435253802,
      "loss": 2.1807,
      "step": 1163
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004699390608361665,
      "loss": 2.1289,
      "step": 1164
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004691977444725955,
      "loss": 2.2061,
      "step": 1165
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.004684564960702877,
      "loss": 2.2754,
      "step": 1166
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004677153172647131,
      "loss": 2.1055,
      "step": 1167
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004669742096911889,
      "loss": 2.2627,
      "step": 1168
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004662331749848747,
      "loss": 2.1836,
      "step": 1169
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004654922147807695,
      "loss": 2.2803,
      "step": 1170
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004647513307137076,
      "loss": 2.3496,
      "step": 1171
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004640105244183557,
      "loss": 2.1045,
      "step": 1172
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00463269797529209,
      "loss": 2.1055,
      "step": 1173
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00462529151680587,
      "loss": 2.2305,
      "step": 1174
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004617885885066305,
      "loss": 2.1973,
      "step": 1175
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004610481096412984,
      "loss": 2.1201,
      "step": 1176
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00460307716718363,
      "loss": 2.2695,
      "step": 1177
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004595674113714074,
      "loss": 2.2734,
      "step": 1178
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004588271952338212,
      "loss": 2.1748,
      "step": 1179
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004580870699387971,
      "loss": 2.2832,
      "step": 1180
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004573470371193277,
      "loss": 2.1719,
      "step": 1181
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004566070984082013,
      "loss": 2.1943,
      "step": 1182
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004558672554379987,
      "loss": 2.1465,
      "step": 1183
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004551275098410894,
      "loss": 2.1826,
      "step": 1184
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00454387863249628,
      "loss": 2.2119,
      "step": 1185
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004536483172955509,
      "loss": 2.252,
      "step": 1186
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004529088736105721,
      "loss": 2.2461,
      "step": 1187
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.004521695338261802,
      "loss": 2.3477,
      "step": 1188
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0045143029957363445,
      "loss": 2.2832,
      "step": 1189
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004506911724839613,
      "loss": 2.2559,
      "step": 1190
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0044995215418795085,
      "loss": 2.1758,
      "step": 1191
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00449213246316153,
      "loss": 2.1201,
      "step": 1192
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004484744504988742,
      "loss": 2.2598,
      "step": 1193
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0044773576836617335,
      "loss": 2.1631,
      "step": 1194
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004469972015478588,
      "loss": 2.1992,
      "step": 1195
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004462587516734844,
      "loss": 2.3184,
      "step": 1196
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00445520420372346,
      "loss": 2.1553,
      "step": 1197
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004447822092734777,
      "loss": 2.2217,
      "step": 1198
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004440441200056488,
      "loss": 2.1836,
      "step": 1199
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00443306154197359,
      "loss": 2.2285,
      "step": 1200
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004425683134768365,
      "loss": 2.1816,
      "step": 1201
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004418305994720328,
      "loss": 2.1699,
      "step": 1202
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004410930138106203,
      "loss": 2.2891,
      "step": 1203
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00440355558119988,
      "loss": 2.1807,
      "step": 1204
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004396182340272382,
      "loss": 2.252,
      "step": 1205
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004388810431591829,
      "loss": 2.1465,
      "step": 1206
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004381439871423399,
      "loss": 2.1406,
      "step": 1207
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004374070676029297,
      "loss": 2.3125,
      "step": 1208
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004366702861668716,
      "loss": 2.1982,
      "step": 1209
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.004359336444597803,
      "loss": 2.1836,
      "step": 1210
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004351971441069622,
      "loss": 2.2344,
      "step": 1211
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004344607867334116,
      "loss": 2.2637,
      "step": 1212
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0043372457396380765,
      "loss": 2.1992,
      "step": 1213
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004329885074225101,
      "loss": 2.1416,
      "step": 1214
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004322525887335563,
      "loss": 2.3057,
      "step": 1215
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004315168195206573,
      "loss": 2.2188,
      "step": 1216
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004307812014071945,
      "loss": 2.248,
      "step": 1217
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004300457360162158,
      "loss": 2.2539,
      "step": 1218
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0042931042497043196,
      "loss": 2.1719,
      "step": 1219
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004285752698922136,
      "loss": 2.2422,
      "step": 1220
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0042784027240358674,
      "loss": 2.1768,
      "step": 1221
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004271054341262301,
      "loss": 2.1777,
      "step": 1222
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00426370756681471,
      "loss": 2.2793,
      "step": 1223
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004256362416902817,
      "loss": 2.1904,
      "step": 1224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004249018907732763,
      "loss": 2.1797,
      "step": 1225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00424167705550707,
      "loss": 2.1328,
      "step": 1226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0042343368764245996,
      "loss": 2.207,
      "step": 1227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004226998386680524,
      "loss": 2.2725,
      "step": 1228
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00421966160246629,
      "loss": 2.2812,
      "step": 1229
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004212326539969578,
      "loss": 2.2344,
      "step": 1230
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004204993215374273,
      "loss": 2.2246,
      "step": 1231
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.004197661644860423,
      "loss": 2.3164,
      "step": 1232
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004190331844604208,
      "loss": 2.2871,
      "step": 1233
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004183003830777898,
      "loss": 2.2344,
      "step": 1234
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004175677619549828,
      "loss": 2.1846,
      "step": 1235
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00416835322708435,
      "loss": 2.2207,
      "step": 1236
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004161030669541805,
      "loss": 2.2188,
      "step": 1237
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004153709963078488,
      "loss": 2.2285,
      "step": 1238
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004146391123846606,
      "loss": 2.2148,
      "step": 1239
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004139074167994249,
      "loss": 2.3125,
      "step": 1240
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0041317591116653484,
      "loss": 2.2832,
      "step": 1241
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004124445970999648,
      "loss": 2.207,
      "step": 1242
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004117134762132662,
      "loss": 2.2383,
      "step": 1243
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004109825501195647,
      "loss": 2.2383,
      "step": 1244
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004102518204315554,
      "loss": 2.1328,
      "step": 1245
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00409521288761501,
      "loss": 2.2041,
      "step": 1246
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004087909567212265,
      "loss": 2.2891,
      "step": 1247
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0040806082592211666,
      "loss": 2.1777,
      "step": 1248
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004073308979751126,
      "loss": 2.252,
      "step": 1249
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004066011744907074,
      "loss": 2.2012,
      "step": 1250
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004058716570789433,
      "loss": 2.2734,
      "step": 1251
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004051423473494076,
      "loss": 2.1338,
      "step": 1252
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004044132469112299,
      "loss": 2.1406,
      "step": 1253
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.004036843573730774,
      "loss": 2.1387,
      "step": 1254
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.004029556803431522,
      "loss": 2.2949,
      "step": 1255
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.004022272174291878,
      "loss": 2.2461,
      "step": 1256
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.004014989702384449,
      "loss": 2.2031,
      "step": 1257
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.004007709403777085,
      "loss": 2.1807,
      "step": 1258
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.004000431294532838,
      "loss": 2.2969,
      "step": 1259
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003993155390709935,
      "loss": 2.1191,
      "step": 1260
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00398588170836173,
      "loss": 2.3066,
      "step": 1261
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003978610263536678,
      "loss": 2.1738,
      "step": 1262
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003971341072278302,
      "loss": 2.1553,
      "step": 1263
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003964074150625146,
      "loss": 2.1895,
      "step": 1264
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003956809514610749,
      "loss": 2.2393,
      "step": 1265
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00394954718026361,
      "loss": 2.1484,
      "step": 1266
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003942287163607145,
      "loss": 2.2227,
      "step": 1267
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003935029480659658,
      "loss": 2.1904,
      "step": 1268
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003927774147434305,
      "loss": 2.1797,
      "step": 1269
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003920521179939057,
      "loss": 2.2148,
      "step": 1270
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.003913270594176664,
      "loss": 2.3066,
      "step": 1271
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0039060224061446243,
      "loss": 2.25,
      "step": 1272
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0038987766318351433,
      "loss": 2.2285,
      "step": 1273
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0038915332872350994,
      "loss": 2.2598,
      "step": 1274
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0038842923883260134,
      "loss": 2.2461,
      "step": 1275
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003877053951084009,
      "loss": 2.2451,
      "step": 1276
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038698179914797783,
      "loss": 2.1953,
      "step": 1277
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038625845254785453,
      "loss": 2.3086,
      "step": 1278
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038553535690400353,
      "loss": 2.2051,
      "step": 1279
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038481251381184355,
      "loss": 2.3105,
      "step": 1280
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038408992486623585,
      "loss": 2.1836,
      "step": 1281
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038336759166148118,
      "loss": 2.0674,
      "step": 1282
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003826455157913159,
      "loss": 2.3027,
      "step": 1283
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003819236988489089,
      "loss": 2.2471,
      "step": 1284
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038120214242685726,
      "loss": 2.165,
      "step": 1285
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0038048084811718374,
      "loss": 2.1436,
      "step": 1286
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003797598175113327,
      "loss": 2.1465,
      "step": 1287
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003790390522001662,
      "loss": 2.3486,
      "step": 1288
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003783185537739615,
      "loss": 2.1699,
      "step": 1289
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00377598323822407,
      "loss": 2.1055,
      "step": 1290
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0037687836393459823,
      "loss": 2.1758,
      "step": 1291
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003761586756990354,
      "loss": 2.1523,
      "step": 1292
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0037543926070361913,
      "loss": 2.2129,
      "step": 1293
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0037472012053564718,
      "loss": 2.0596,
      "step": 1294
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0037400125678181107,
      "loss": 2.1504,
      "step": 1295
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0037328267102819225,
      "loss": 2.1836,
      "step": 1296
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.003725643648602588,
      "loss": 2.1602,
      "step": 1297
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003718463398628621,
      "loss": 2.2773,
      "step": 1298
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003711285976202331,
      "loss": 2.1309,
      "step": 1299
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003704111397159787,
      "loss": 2.207,
      "step": 1300
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036969396773307885,
      "loss": 2.3027,
      "step": 1301
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003689770832538821,
      "loss": 2.1514,
      "step": 1302
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036826048786010343,
      "loss": 2.1807,
      "step": 1303
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00367544183132819,
      "loss": 2.2461,
      "step": 1304
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036682817065246454,
      "loss": 2.1016,
      "step": 1305
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036611245199883037,
      "loss": 2.2227,
      "step": 1306
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036539702875105894,
      "loss": 2.2852,
      "step": 1307
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003646819024876406,
      "loss": 2.1719,
      "step": 1308
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036396707478641072,
      "loss": 2.208,
      "step": 1309
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003632525472245458,
      "loss": 2.1133,
      "step": 1310
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036253832137855997,
      "loss": 2.2598,
      "step": 1311
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036182439882430184,
      "loss": 2.2363,
      "step": 1312
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0036111078113695095,
      "loss": 2.1602,
      "step": 1313
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003603974698910139,
      "loss": 2.2217,
      "step": 1314
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003596844666603214,
      "loss": 2.2559,
      "step": 1315
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0035897177301802453,
      "loss": 2.2031,
      "step": 1316
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.003582593905365912,
      "loss": 2.2949,
      "step": 1317
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0035754732078780273,
      "loss": 2.2432,
      "step": 1318
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0035683556534275075,
      "loss": 2.168,
      "step": 1319
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00356124125771833,
      "loss": 2.1953,
      "step": 1320
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035541300364475064,
      "loss": 2.2461,
      "step": 1321
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003547022005305043,
      "loss": 2.124,
      "step": 1322
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035399171799739074,
      "loss": 2.1855,
      "step": 1323
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035328155761299917,
      "loss": 2.1172,
      "step": 1324
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035257172094420855,
      "loss": 2.2109,
      "step": 1325
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035186220955718307,
      "loss": 2.1973,
      "step": 1326
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003511530250173696,
      "loss": 2.2764,
      "step": 1327
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0035044416888949364,
      "loss": 2.2031,
      "step": 1328
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003497356427375562,
      "loss": 2.2539,
      "step": 1329
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003490274481248303,
      "loss": 2.2031,
      "step": 1330
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034831958661385716,
      "loss": 2.1885,
      "step": 1331
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003476120597664434,
      "loss": 2.168,
      "step": 1332
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034690486914365705,
      "loss": 2.207,
      "step": 1333
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003461980163058244,
      "loss": 2.1855,
      "step": 1334
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003454915028125263,
      "loss": 2.1357,
      "step": 1335
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034478533022259525,
      "loss": 2.2168,
      "step": 1336
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034407950009411126,
      "loss": 2.1553,
      "step": 1337
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034337401398439873,
      "loss": 2.2383,
      "step": 1338
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.003426688734500231,
      "loss": 2.1484,
      "step": 1339
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034196408004678737,
      "loss": 2.1904,
      "step": 1340
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0034125963532972876,
      "loss": 2.127,
      "step": 1341
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0034055554085311492,
      "loss": 2.3066,
      "step": 1342
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033985179817044102,
      "loss": 2.1885,
      "step": 1343
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033914840883442566,
      "loss": 2.2578,
      "step": 1344
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003384453743970081,
      "loss": 2.1426,
      "step": 1345
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033774269640934446,
      "loss": 2.2041,
      "step": 1346
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033704037642180453,
      "loss": 2.1875,
      "step": 1347
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00336338415983968,
      "loss": 2.2012,
      "step": 1348
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033563681664462155,
      "loss": 2.1484,
      "step": 1349
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00334935579951755,
      "loss": 2.2139,
      "step": 1350
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003342347074525578,
      "loss": 2.2578,
      "step": 1351
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003335342006934161,
      "loss": 2.2148,
      "step": 1352
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033283406121990913,
      "loss": 2.2461,
      "step": 1353
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003321342905768057,
      "loss": 2.1152,
      "step": 1354
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033143489030806085,
      "loss": 2.2344,
      "step": 1355
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0033073586195681228,
      "loss": 2.2793,
      "step": 1356
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003300372070653774,
      "loss": 2.1611,
      "step": 1357
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0032933892717524923,
      "loss": 2.2012,
      "step": 1358
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0032864102382709377,
      "loss": 2.2031,
      "step": 1359
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00327943498560746,
      "loss": 2.167,
      "step": 1360
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003272463529152069,
      "loss": 2.2754,
      "step": 1361
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003265495884286397,
      "loss": 2.166,
      "step": 1362
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.003258532066383667,
      "loss": 2.2402,
      "step": 1363
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00325157209080866,
      "loss": 2.1211,
      "step": 1364
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032446159729176745,
      "loss": 2.1865,
      "step": 1365
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032376637280585024,
      "loss": 2.334,
      "step": 1366
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.003230715371570389,
      "loss": 2.208,
      "step": 1367
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032237709187839998,
      "loss": 2.1562,
      "step": 1368
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032168303850213876,
      "loss": 2.1104,
      "step": 1369
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032098937855959586,
      "loss": 2.1309,
      "step": 1370
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0032029611358124366,
      "loss": 2.0107,
      "step": 1371
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.003196032450966834,
      "loss": 2.2451,
      "step": 1372
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.003189107746346412,
      "loss": 2.2256,
      "step": 1373
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.003182187037229653,
      "loss": 2.2227,
      "step": 1374
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031752703388862216,
      "loss": 2.2324,
      "step": 1375
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031683576665769344,
      "loss": 2.2305,
      "step": 1376
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.003161449035553724,
      "loss": 2.2305,
      "step": 1377
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031545444610596076,
      "loss": 2.0889,
      "step": 1378
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00314764395832865,
      "loss": 2.2314,
      "step": 1379
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031407475425859342,
      "loss": 2.2285,
      "step": 1380
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031338552290475262,
      "loss": 2.248,
      "step": 1381
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00312696703292044,
      "loss": 2.248,
      "step": 1382
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031200829694026043,
      "loss": 2.1816,
      "step": 1383
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0031132030536828313,
      "loss": 2.2031,
      "step": 1384
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0031063273009407804,
      "loss": 2.123,
      "step": 1385
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030994557263469263,
      "loss": 2.2539,
      "step": 1386
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030925883450625257,
      "loss": 2.2383,
      "step": 1387
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030857251722395816,
      "loss": 2.1777,
      "step": 1388
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003078866223020815,
      "loss": 2.1416,
      "step": 1389
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030720115125396235,
      "loss": 2.2109,
      "step": 1390
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003065161055920057,
      "loss": 2.166,
      "step": 1391
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003058314868276776,
      "loss": 2.1914,
      "step": 1392
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003051472964715024,
      "loss": 2.25,
      "step": 1393
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003044635360330592,
      "loss": 2.1992,
      "step": 1394
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030378020702097846,
      "loss": 2.2725,
      "step": 1395
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030309731094293898,
      "loss": 2.1162,
      "step": 1396
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.003024148493056641,
      "loss": 2.2031,
      "step": 1397
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030173282361491867,
      "loss": 2.2773,
      "step": 1398
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030105123537550573,
      "loss": 2.2012,
      "step": 1399
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0030037008609126313,
      "loss": 2.1514,
      "step": 1400
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.002996893772650602,
      "loss": 2.1787,
      "step": 1401
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0029900911039879453,
      "loss": 2.2188,
      "step": 1402
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0029832928699338856,
      "loss": 2.2578,
      "step": 1403
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.002976499085487862,
      "loss": 2.1592,
      "step": 1404
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0029697097656394963,
      "loss": 2.083,
      "step": 1405
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0029629249253685596,
      "loss": 2.2109,
      "step": 1406
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029561445796449414,
      "loss": 2.1621,
      "step": 1407
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002949368743428612,
      "loss": 2.2178,
      "step": 1408
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029425974316695932,
      "loss": 2.1611,
      "step": 1409
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029358306593079237,
      "loss": 2.3086,
      "step": 1410
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002929068441273629,
      "loss": 2.2031,
      "step": 1411
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002922310792486681,
      "loss": 2.1855,
      "step": 1412
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029155577278569744,
      "loss": 2.1465,
      "step": 1413
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029088092622842894,
      "loss": 2.2676,
      "step": 1414
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0029020654106582545,
      "loss": 2.1201,
      "step": 1415
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002895326187858326,
      "loss": 2.1523,
      "step": 1416
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028885916087537378,
      "loss": 2.1387,
      "step": 1417
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028818616882034876,
      "loss": 2.1914,
      "step": 1418
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028751364410562865,
      "loss": 2.1699,
      "step": 1419
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00286841588215054,
      "loss": 2.1172,
      "step": 1420
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002861700026314308,
      "loss": 2.1807,
      "step": 1421
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028549888883652686,
      "loss": 2.3535,
      "step": 1422
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028482824831107,
      "loss": 2.2812,
      "step": 1423
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00284158082534743,
      "loss": 2.1777,
      "step": 1424
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002834883929861818,
      "loss": 2.2051,
      "step": 1425
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002828191811429709,
      "loss": 2.2178,
      "step": 1426
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.002821504484816416,
      "loss": 2.1982,
      "step": 1427
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0028148219647766747,
      "loss": 2.1924,
      "step": 1428
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0028081442660546126,
      "loss": 2.2002,
      "step": 1429
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0028014714033837286,
      "loss": 2.1182,
      "step": 1430
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027948033914868414,
      "loss": 2.1377,
      "step": 1431
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002788140245076077,
      "loss": 2.1318,
      "step": 1432
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027814819788528167,
      "loss": 2.21,
      "step": 1433
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027748286075076835,
      "loss": 2.1973,
      "step": 1434
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027681801457204937,
      "loss": 2.1641,
      "step": 1435
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027615366081602307,
      "loss": 2.2236,
      "step": 1436
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002754898009485021,
      "loss": 2.3086,
      "step": 1437
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027482643643420845,
      "loss": 2.1807,
      "step": 1438
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027416356873677205,
      "loss": 2.1719,
      "step": 1439
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002735011993187258,
      "loss": 2.2012,
      "step": 1440
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027283932964150413,
      "loss": 2.2617,
      "step": 1441
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027217796116543818,
      "loss": 2.2207,
      "step": 1442
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002715170953497532,
      "loss": 2.1973,
      "step": 1443
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027085673365256613,
      "loss": 2.1064,
      "step": 1444
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0027019687753088075,
      "loss": 2.1045,
      "step": 1445
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00269537528440586,
      "loss": 2.2529,
      "step": 1446
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002688786878364516,
      "loss": 2.2285,
      "step": 1447
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0026822035717212595,
      "loss": 2.1709,
      "step": 1448
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002675625379001319,
      "loss": 2.2617,
      "step": 1449
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.002669052314718641,
      "loss": 2.2539,
      "step": 1450
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026624843933758546,
      "loss": 2.1934,
      "step": 1451
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026559216294642445,
      "loss": 2.2119,
      "step": 1452
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002649364037463718,
      "loss": 2.2617,
      "step": 1453
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002642811631842764,
      "loss": 2.2051,
      "step": 1454
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002636264427058439,
      "loss": 2.1016,
      "step": 1455
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002629722437556312,
      "loss": 2.2109,
      "step": 1456
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026231856777704575,
      "loss": 2.1338,
      "step": 1457
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026166541621234023,
      "loss": 2.1035,
      "step": 1458
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026101279050261047,
      "loss": 2.1523,
      "step": 1459
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0026036069208779243,
      "loss": 2.2422,
      "step": 1460
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002597091224066581,
      "loss": 2.1855,
      "step": 1461
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025905808289681366,
      "loss": 2.1904,
      "step": 1462
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002584075749946946,
      "loss": 2.1416,
      "step": 1463
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025775760013556424,
      "loss": 2.1602,
      "step": 1464
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002571081597535095,
      "loss": 2.1777,
      "step": 1465
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025645925528143777,
      "loss": 2.1641,
      "step": 1466
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025581088815107467,
      "loss": 2.0947,
      "step": 1467
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002551630597929596,
      "loss": 2.2305,
      "step": 1468
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002545157716364439,
      "loss": 2.1699,
      "step": 1469
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.002538690251096862,
      "loss": 2.1465,
      "step": 1470
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025322282163965093,
      "loss": 2.1992,
      "step": 1471
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0025257716265210386,
      "loss": 2.2129,
      "step": 1472
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002519320495716091,
      "loss": 2.2852,
      "step": 1473
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0025128748382152715,
      "loss": 2.2207,
      "step": 1474
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002506434668240102,
      "loss": 2.2871,
      "step": 1475
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0025000000000000014,
      "loss": 2.1611,
      "step": 1476
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002493570847692246,
      "loss": 2.2168,
      "step": 1477
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002487147225501942,
      "loss": 2.2383,
      "step": 1478
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024807291476019993,
      "loss": 2.2559,
      "step": 1479
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024743166281530875,
      "loss": 2.0986,
      "step": 1480
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00246790968130362,
      "loss": 2.1855,
      "step": 1481
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002461508321189706,
      "loss": 2.0986,
      "step": 1482
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024551125619351384,
      "loss": 2.2109,
      "step": 1483
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002448722417651345,
      "loss": 2.1904,
      "step": 1484
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002442337902437365,
      "loss": 2.0967,
      "step": 1485
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024359590303798242,
      "loss": 2.3145,
      "step": 1486
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002429585815552889,
      "loss": 2.1582,
      "step": 1487
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002423218272018252,
      "loss": 2.2285,
      "step": 1488
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024168564138250855,
      "loss": 2.1895,
      "step": 1489
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024105002550100247,
      "loss": 2.2207,
      "step": 1490
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0024041498095971254,
      "loss": 2.1445,
      "step": 1491
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002397805091597835,
      "loss": 2.207,
      "step": 1492
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.002391466115010973,
      "loss": 2.2715,
      "step": 1493
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023851328938226807,
      "loss": 2.1729,
      "step": 1494
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002378805442006411,
      "loss": 2.1699,
      "step": 1495
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002372483773522877,
      "loss": 2.1826,
      "step": 1496
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023661679023200422,
      "loss": 2.0889,
      "step": 1497
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023598578423330713,
      "loss": 2.2031,
      "step": 1498
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023535536074843085,
      "loss": 2.1309,
      "step": 1499
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023472552116832503,
      "loss": 2.1348,
      "step": 1500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023409626688265027,
      "loss": 2.1572,
      "step": 1501
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0023346759927977663,
      "loss": 2.1982,
      "step": 1502
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002328395197467789,
      "loss": 2.2051,
      "step": 1503
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002322120296694352,
      "loss": 2.2109,
      "step": 1504
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002315851304322223,
      "loss": 2.2988,
      "step": 1505
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002309588234183137,
      "loss": 2.2344,
      "step": 1506
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002303331100095765,
      "loss": 2.0938,
      "step": 1507
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002297079915865676,
      "loss": 2.1768,
      "step": 1508
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002290834695285316,
      "loss": 2.2607,
      "step": 1509
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002284595452133968,
      "loss": 2.2422,
      "step": 1510
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002278362200177732,
      "loss": 2.1797,
      "step": 1511
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002272134953169485,
      "loss": 2.208,
      "step": 1512
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.002265913724848855,
      "loss": 2.2422,
      "step": 1513
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0022596985289421944,
      "loss": 2.1211,
      "step": 1514
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0022534893791625404,
      "loss": 2.1152,
      "step": 1515
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002247286289209597,
      "loss": 2.2061,
      "step": 1516
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0022410892727696896,
      "loss": 2.249,
      "step": 1517
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002234898343515751,
      "loss": 2.1562,
      "step": 1518
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002228713515107279,
      "loss": 2.1338,
      "step": 1519
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00222253480119031,
      "loss": 2.1807,
      "step": 1520
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002216362215397393,
      "loss": 2.2002,
      "step": 1521
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0022101957713475525,
      "loss": 2.1211,
      "step": 1522
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0022040354826462667,
      "loss": 2.25,
      "step": 1523
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002197881362885426,
      "loss": 2.2363,
      "step": 1524
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002191733425643318,
      "loss": 2.1367,
      "step": 1525
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0021855916844845825,
      "loss": 2.1426,
      "step": 1526
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00217945615296019,
      "loss": 2.1104,
      "step": 1527
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002173326844607414,
      "loss": 2.1328,
      "step": 1528
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0021672037729497918,
      "loss": 2.2578,
      "step": 1529
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002161086951497106,
      "loss": 2.2266,
      "step": 1530
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0021549763937453443,
      "loss": 2.2178,
      "step": 1531
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002148872113176674,
      "loss": 2.2949,
      "step": 1532
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0021427741232594184,
      "loss": 2.293,
      "step": 1533
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002136682437448013,
      "loss": 2.3379,
      "step": 1534
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002130597069182994,
      "loss": 2.2539,
      "step": 1535
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002124518031890948,
      "loss": 2.1543,
      "step": 1536
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.002118445338984502,
      "loss": 2.0781,
      "step": 1537
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002112379003862281,
      "loss": 2.1855,
      "step": 1538
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002106319039908879,
      "loss": 2.1748,
      "step": 1539
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002100265460494841,
      "loss": 2.1973,
      "step": 1540
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020942182789766175,
      "loss": 2.1729,
      "step": 1541
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020881775086965494,
      "loss": 2.1855,
      "step": 1542
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020821431629828246,
      "loss": 2.2363,
      "step": 1543
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020761152551494644,
      "loss": 2.2168,
      "step": 1544
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00207009379849628,
      "loss": 2.2344,
      "step": 1545
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002064078806308848,
      "loss": 2.1953,
      "step": 1546
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020580702918584883,
      "loss": 2.1299,
      "step": 1547
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020520682684022204,
      "loss": 2.166,
      "step": 1548
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002046072749182751,
      "loss": 2.2207,
      "step": 1549
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002040083747428427,
      "loss": 2.2246,
      "step": 1550
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002034101276353224,
      "loss": 2.1582,
      "step": 1551
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020281253491567027,
      "loss": 2.2305,
      "step": 1552
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002022155979023984,
      "loss": 2.1992,
      "step": 1553
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020161931791257298,
      "loss": 2.2773,
      "step": 1554
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0020102369626180962,
      "loss": 2.1641,
      "step": 1555
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.002004287342642721,
      "loss": 2.1504,
      "step": 1556
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0019983443323266827,
      "loss": 2.1396,
      "step": 1557
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0019924079447824804,
      "loss": 2.209,
      "step": 1558
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0019864781931079978,
      "loss": 2.1875,
      "step": 1559
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001980555090386477,
      "loss": 2.2969,
      "step": 1560
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001974638649686495,
      "loss": 2.0967,
      "step": 1561
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001968728884061923,
      "loss": 2.166,
      "step": 1562
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019628258065519113,
      "loss": 2.1172,
      "step": 1563
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001956929430180846,
      "loss": 2.1465,
      "step": 1564
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019510397679583374,
      "loss": 2.2383,
      "step": 1565
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001945156832879174,
      "loss": 2.2295,
      "step": 1566
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019392806379233036,
      "loss": 2.0605,
      "step": 1567
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019334111960558065,
      "loss": 2.123,
      "step": 1568
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019275485202268573,
      "loss": 2.2832,
      "step": 1569
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019216926233717087,
      "loss": 2.1885,
      "step": 1570
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019158435184106499,
      "loss": 2.1758,
      "step": 1571
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019100012182489906,
      "loss": 2.1924,
      "step": 1572
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0019041657357770226,
      "loss": 2.1309,
      "step": 1573
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018983370838699942,
      "loss": 2.1123,
      "step": 1574
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018925152753880893,
      "loss": 2.2393,
      "step": 1575
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018867003231763846,
      "loss": 2.2207,
      "step": 1576
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018808922400648377,
      "loss": 2.2754,
      "step": 1577
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001875091038868243,
      "loss": 2.2891,
      "step": 1578
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018692967323862125,
      "loss": 2.1709,
      "step": 1579
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018635093334031516,
      "loss": 2.2109,
      "step": 1580
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0018577288546882166,
      "loss": 2.1562,
      "step": 1581
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018519553089953022,
      "loss": 2.1895,
      "step": 1582
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001846188709063001,
      "loss": 2.1484,
      "step": 1583
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018404290676145858,
      "loss": 2.1592,
      "step": 1584
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018346763973579722,
      "loss": 2.165,
      "step": 1585
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001828930710985694,
      "loss": 2.2461,
      "step": 1586
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018231920211748821,
      "loss": 2.125,
      "step": 1587
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001817460340587223,
      "loss": 2.3164,
      "step": 1588
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018117356818689446,
      "loss": 2.2363,
      "step": 1589
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018060180576507756,
      "loss": 2.2168,
      "step": 1590
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0018003074805479314,
      "loss": 2.0469,
      "step": 1591
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017946039631600724,
      "loss": 2.1816,
      "step": 1592
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017889075180712837,
      "loss": 2.1875,
      "step": 1593
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017832181578500512,
      "loss": 2.1895,
      "step": 1594
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001777535895049221,
      "loss": 2.1387,
      "step": 1595
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001771860742205988,
      "loss": 2.2012,
      "step": 1596
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017661927118418526,
      "loss": 2.2539,
      "step": 1597
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017605318164626066,
      "loss": 2.2129,
      "step": 1598
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001754878068558295,
      "loss": 2.3066,
      "step": 1599
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017492314806031922,
      "loss": 2.2676,
      "step": 1600
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017435920650557806,
      "loss": 2.1582,
      "step": 1601
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001737959834358711,
      "loss": 2.1777,
      "step": 1602
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0017323348009387878,
      "loss": 2.1123,
      "step": 1603
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0017267169772069292,
      "loss": 2.1328,
      "step": 1604
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0017211063755581523,
      "loss": 2.1328,
      "step": 1605
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0017155030083715363,
      "loss": 2.123,
      "step": 1606
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001709906888010196,
      "loss": 2.1426,
      "step": 1607
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0017043180268212638,
      "loss": 2.2051,
      "step": 1608
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016987364371358483,
      "loss": 2.1699,
      "step": 1609
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016931621312690215,
      "loss": 2.1719,
      "step": 1610
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016875951215197776,
      "loss": 2.2012,
      "step": 1611
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016820354201710214,
      "loss": 2.2344,
      "step": 1612
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016764830394895203,
      "loss": 2.0322,
      "step": 1613
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016709379917259027,
      "loss": 2.1309,
      "step": 1614
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016654002891146092,
      "loss": 2.1807,
      "step": 1615
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016598699438738762,
      "loss": 2.1562,
      "step": 1616
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016543469682057106,
      "loss": 2.3096,
      "step": 1617
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016488313742958527,
      "loss": 2.2129,
      "step": 1618
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016433231743137645,
      "loss": 2.083,
      "step": 1619
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016378223804125842,
      "loss": 2.1914,
      "step": 1620
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0016323290047291195,
      "loss": 2.1592,
      "step": 1621
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001626843059383803,
      "loss": 2.1895,
      "step": 1622
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001621364556480675,
      "loss": 2.2295,
      "step": 1623
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.001615893508107359,
      "loss": 2.1875,
      "step": 1624
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0016104299263350252,
      "loss": 2.1543,
      "step": 1625
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0016049738232183758,
      "loss": 2.168,
      "step": 1626
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015995252107956059,
      "loss": 2.2441,
      "step": 1627
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001594084101088389,
      "loss": 2.1777,
      "step": 1628
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015886505061018415,
      "loss": 2.123,
      "step": 1629
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001583224437824498,
      "loss": 2.1768,
      "step": 1630
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001577805908228293,
      "loss": 2.1826,
      "step": 1631
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001572394929268519,
      "loss": 2.1455,
      "step": 1632
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001566991512883818,
      "loss": 2.1094,
      "step": 1633
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015615956709961376,
      "loss": 2.1484,
      "step": 1634
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015562074155107215,
      "loss": 2.1777,
      "step": 1635
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015508267583160679,
      "loss": 2.1211,
      "step": 1636
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015454537112839124,
      "loss": 2.1416,
      "step": 1637
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015400882862692034,
      "loss": 2.1523,
      "step": 1638
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015347304951100667,
      "loss": 2.1699,
      "step": 1639
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015293803496277908,
      "loss": 2.1855,
      "step": 1640
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015240378616267886,
      "loss": 2.1396,
      "step": 1641
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001518703042894584,
      "loss": 2.1133,
      "step": 1642
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001513375905201776,
      "loss": 2.1934,
      "step": 1643
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015080564603020142,
      "loss": 2.2148,
      "step": 1644
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0015027447199319822,
      "loss": 2.293,
      "step": 1645
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0014974406958113556,
      "loss": 2.2129,
      "step": 1646
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014921443996427947,
      "loss": 2.083,
      "step": 1647
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001486855843111901,
      "loss": 2.2441,
      "step": 1648
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014815750378872011,
      "loss": 2.1689,
      "step": 1649
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014763019956201251,
      "loss": 2.1182,
      "step": 1650
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001471036727944966,
      "loss": 2.1572,
      "step": 1651
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014657792464788722,
      "loss": 2.1582,
      "step": 1652
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014605295628218047,
      "loss": 2.1201,
      "step": 1653
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014552876885565269,
      "loss": 2.1895,
      "step": 1654
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001450053635248567,
      "loss": 2.2061,
      "step": 1655
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014448274144461964,
      "loss": 2.1289,
      "step": 1656
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001439609037680411,
      "loss": 2.2051,
      "step": 1657
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014343985164648927,
      "loss": 2.1328,
      "step": 1658
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014291958622959973,
      "loss": 2.1299,
      "step": 1659
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014240010866527176,
      "loss": 2.2148,
      "step": 1660
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014188142009966688,
      "loss": 2.1055,
      "step": 1661
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014136352167720529,
      "loss": 2.207,
      "step": 1662
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014084641454056401,
      "loss": 2.1504,
      "step": 1663
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0014033009983067451,
      "loss": 2.1602,
      "step": 1664
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0013981457868671927,
      "loss": 2.1328,
      "step": 1665
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001392998522461305,
      "loss": 2.2393,
      "step": 1666
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0013878592164458636,
      "loss": 2.1484,
      "step": 1667
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0013827278801600978,
      "loss": 2.1641,
      "step": 1668
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001377604524925647,
      "loss": 2.2891,
      "step": 1669
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013724891620465424,
      "loss": 2.1846,
      "step": 1670
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001367381802809185,
      "loss": 2.123,
      "step": 1671
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013622824584823112,
      "loss": 2.2041,
      "step": 1672
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013571911403169796,
      "loss": 2.2363,
      "step": 1673
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001352107859546533,
      "loss": 2.2148,
      "step": 1674
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013470326273865884,
      "loss": 2.2656,
      "step": 1675
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013419654550349985,
      "loss": 2.1855,
      "step": 1676
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013369063536718346,
      "loss": 2.1455,
      "step": 1677
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.001331855334459363,
      "loss": 2.2227,
      "step": 1678
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013268124085420135,
      "loss": 2.1865,
      "step": 1679
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013217775870463639,
      "loss": 2.2207,
      "step": 1680
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013167508810811056,
      "loss": 2.1992,
      "step": 1681
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013117323017370292,
      "loss": 2.2939,
      "step": 1682
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013067218600869913,
      "loss": 2.1621,
      "step": 1683
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0013017195671858929,
      "loss": 2.1504,
      "step": 1684
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012967254340706608,
      "loss": 2.2266,
      "step": 1685
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012917394717602121,
      "loss": 2.1865,
      "step": 1686
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012867616912554424,
      "loss": 2.1514,
      "step": 1687
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012817921035391882,
      "loss": 2.1777,
      "step": 1688
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012768307195762168,
      "loss": 2.1719,
      "step": 1689
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0012718775503131907,
      "loss": 2.1875,
      "step": 1690
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012669326066786458,
      "loss": 2.1826,
      "step": 1691
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012619958995829755,
      "loss": 2.2129,
      "step": 1692
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001257067439918394,
      "loss": 2.2109,
      "step": 1693
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012521472385589234,
      "loss": 2.1777,
      "step": 1694
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012472353063603626,
      "loss": 2.0742,
      "step": 1695
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001242331654160263,
      "loss": 2.1533,
      "step": 1696
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012374362927779143,
      "loss": 2.2402,
      "step": 1697
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012325492330143063,
      "loss": 2.168,
      "step": 1698
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012276704856521176,
      "loss": 2.1074,
      "step": 1699
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012228000614556817,
      "loss": 2.1865,
      "step": 1700
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012179379711709738,
      "loss": 2.2129,
      "step": 1701
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012130842255255769,
      "loss": 2.1777,
      "step": 1702
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012082388352286626,
      "loss": 2.2246,
      "step": 1703
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0012034018109709716,
      "loss": 2.2617,
      "step": 1704
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001198573163424781,
      "loss": 2.1455,
      "step": 1705
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011937529032438905,
      "loss": 2.1328,
      "step": 1706
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011889410410635887,
      "loss": 2.0742,
      "step": 1707
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001184137587500641,
      "loss": 2.1025,
      "step": 1708
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011793425531532564,
      "loss": 2.0967,
      "step": 1709
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011745559486010671,
      "loss": 2.2227,
      "step": 1710
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011697777844051104,
      "loss": 2.2832,
      "step": 1711
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0011650080711077964,
      "loss": 2.1348,
      "step": 1712
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011602468192328935,
      "loss": 2.2422,
      "step": 1713
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011554940392854973,
      "loss": 2.2412,
      "step": 1714
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011507497417520146,
      "loss": 2.1963,
      "step": 1715
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011460139371001338,
      "loss": 2.2012,
      "step": 1716
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011412866357788049,
      "loss": 2.1582,
      "step": 1717
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011365678482182207,
      "loss": 2.085,
      "step": 1718
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001131857584829783,
      "loss": 2.1309,
      "step": 1719
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001127155856006093,
      "loss": 2.1787,
      "step": 1720
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011224626721209141,
      "loss": 2.0049,
      "step": 1721
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001117778043529164,
      "loss": 2.2422,
      "step": 1722
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001113101980566879,
      "loss": 2.1035,
      "step": 1723
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001108434493551196,
      "loss": 2.1475,
      "step": 1724
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0011037755927803346,
      "loss": 2.2031,
      "step": 1725
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0010991252885335652,
      "loss": 2.1738,
      "step": 1726
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001094483591071196,
      "loss": 2.25,
      "step": 1727
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0010898505106345397,
      "loss": 2.2451,
      "step": 1728
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001085226057445902,
      "loss": 2.1768,
      "step": 1729
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0010806102417085513,
      "loss": 2.1689,
      "step": 1730
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001076003073606695,
      "loss": 2.1816,
      "step": 1731
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0010714045633054687,
      "loss": 2.2324,
      "step": 1732
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0010668147209508972,
      "loss": 2.1191,
      "step": 1733
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010622335566698876,
      "loss": 2.2168,
      "step": 1734
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001057661080570194,
      "loss": 2.2012,
      "step": 1735
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010530973027404072,
      "loss": 2.1768,
      "step": 1736
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001048542233249921,
      "loss": 2.1133,
      "step": 1737
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010439958821489165,
      "loss": 2.1533,
      "step": 1738
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010394582594683427,
      "loss": 2.1152,
      "step": 1739
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001034929375219884,
      "loss": 2.1182,
      "step": 1740
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010304092393959513,
      "loss": 2.0957,
      "step": 1741
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001025897861969647,
      "loss": 2.1641,
      "step": 1742
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.001021395252894755,
      "loss": 2.1934,
      "step": 1743
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010169014221057089,
      "loss": 2.04,
      "step": 1744
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010124163795175733,
      "loss": 2.2012,
      "step": 1745
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010079401350260287,
      "loss": 2.0908,
      "step": 1746
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0010034726985073362,
      "loss": 2.2871,
      "step": 1747
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00099901407981833,
      "loss": 2.2148,
      "step": 1748
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000994564288796384,
      "loss": 2.1611,
      "step": 1749
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009901233352593952,
      "loss": 2.1738,
      "step": 1750
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009856912290057667,
      "loss": 2.1504,
      "step": 1751
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009812679798143747,
      "loss": 2.1748,
      "step": 1752
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009768535974445586,
      "loss": 2.1816,
      "step": 1753
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009724480916360906,
      "loss": 2.1514,
      "step": 1754
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009680514721091621,
      "loss": 2.1406,
      "step": 1755
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009636637485643529,
      "loss": 2.1992,
      "step": 1756
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009592849306826174,
      "loss": 2.2715,
      "step": 1757
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009549150281252633,
      "loss": 2.2383,
      "step": 1758
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009505540505339221,
      "loss": 2.1582,
      "step": 1759
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009462020075305399,
      "loss": 2.1064,
      "step": 1760
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009418589087173441,
      "loss": 2.1475,
      "step": 1761
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009375247636768325,
      "loss": 2.1953,
      "step": 1762
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009331995819717442,
      "loss": 2.1572,
      "step": 1763
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009288833731450419,
      "loss": 2.1797,
      "step": 1764
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009245761467198949,
      "loss": 2.2109,
      "step": 1765
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000920277912199648,
      "loss": 2.1494,
      "step": 1766
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009159886790678124,
      "loss": 2.2861,
      "step": 1767
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000911708456788033,
      "loss": 2.2324,
      "step": 1768
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009074372548040794,
      "loss": 2.1582,
      "step": 1769
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009031750825398144,
      "loss": 2.1855,
      "step": 1770
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008989219493991791,
      "loss": 2.1016,
      "step": 1771
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008946778647661729,
      "loss": 2.1143,
      "step": 1772
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008904428380048269,
      "loss": 2.1777,
      "step": 1773
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008862168784591929,
      "loss": 2.207,
      "step": 1774
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008819999954533114,
      "loss": 2.2773,
      "step": 1775
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008777921982911996,
      "loss": 2.1309,
      "step": 1776
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0008735934962568253,
      "loss": 2.1709,
      "step": 1777
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008694038986140945,
      "loss": 2.1025,
      "step": 1778
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008652234146068205,
      "loss": 2.0742,
      "step": 1779
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008610520534587086,
      "loss": 2.2402,
      "step": 1780
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008568898243733398,
      "loss": 2.1865,
      "step": 1781
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000852736736534141,
      "loss": 2.1338,
      "step": 1782
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008485927991043757,
      "loss": 1.9893,
      "step": 1783
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008444580212271125,
      "loss": 2.1748,
      "step": 1784
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000840332412025216,
      "loss": 2.1953,
      "step": 1785
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008362159806013176,
      "loss": 2.1855,
      "step": 1786
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008321087360377988,
      "loss": 2.1865,
      "step": 1787
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008280106873967753,
      "loss": 2.1465,
      "step": 1788
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008239218437200679,
      "loss": 2.1104,
      "step": 1789
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008198422140291939,
      "loss": 2.1533,
      "step": 1790
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000815771807325335,
      "loss": 2.1738,
      "step": 1791
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008117106325893287,
      "loss": 2.1172,
      "step": 1792
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008076586987816404,
      "loss": 2.166,
      "step": 1793
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000803616014842345,
      "loss": 2.2871,
      "step": 1794
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000799582589691114,
      "loss": 2.042,
      "step": 1795
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0007955584322271853,
      "loss": 2.1318,
      "step": 1796
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0007915435513293523,
      "loss": 2.2158,
      "step": 1797
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0007875379558559387,
      "loss": 2.2305,
      "step": 1798
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0007835416546447838,
      "loss": 2.1855,
      "step": 1799
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007795546565132166,
      "loss": 2.1396,
      "step": 1800
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007755769702580412,
      "loss": 2.1016,
      "step": 1801
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007716086046555192,
      "loss": 2.1025,
      "step": 1802
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007676495684613432,
      "loss": 2.1396,
      "step": 1803
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007636998704106251,
      "loss": 2.1699,
      "step": 1804
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007597595192178702,
      "loss": 2.0908,
      "step": 1805
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007558285235769646,
      "loss": 2.1816,
      "step": 1806
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007519068921611494,
      "loss": 2.0977,
      "step": 1807
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007479946336230048,
      "loss": 2.166,
      "step": 1808
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000744091756594435,
      "loss": 2.1309,
      "step": 1809
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00074019826968664,
      "loss": 2.1572,
      "step": 1810
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007363141814901053,
      "loss": 2.207,
      "step": 1811
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007324395005745771,
      "loss": 2.2383,
      "step": 1812
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007285742354890474,
      "loss": 2.2246,
      "step": 1813
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007247183947617325,
      "loss": 2.0615,
      "step": 1814
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000720871986900053,
      "loss": 2.2559,
      "step": 1815
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007170350203906218,
      "loss": 2.1045,
      "step": 1816
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007132075036992158,
      "loss": 2.123,
      "step": 1817
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007093894452707667,
      "loss": 2.1582,
      "step": 1818
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007055808535293334,
      "loss": 2.1416,
      "step": 1819
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0007017817368780888,
      "loss": 2.1904,
      "step": 1820
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0006979921036993042,
      "loss": 2.123,
      "step": 1821
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006942119623543203,
      "loss": 2.1191,
      "step": 1822
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006904413211835414,
      "loss": 2.1299,
      "step": 1823
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006866801885064055,
      "loss": 2.1973,
      "step": 1824
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006829285726213768,
      "loss": 2.1289,
      "step": 1825
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006791864818059179,
      "loss": 2.1475,
      "step": 1826
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006754539243164754,
      "loss": 2.1836,
      "step": 1827
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006717309083884654,
      "loss": 2.2119,
      "step": 1828
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006680174422362467,
      "loss": 2.1738,
      "step": 1829
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006643135340531137,
      "loss": 2.2168,
      "step": 1830
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006606191920112665,
      "loss": 2.1787,
      "step": 1831
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006569344242618036,
      "loss": 2.2168,
      "step": 1832
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006532592389346958,
      "loss": 2.2832,
      "step": 1833
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006495936441387713,
      "loss": 2.2412,
      "step": 1834
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006459376479617013,
      "loss": 2.1689,
      "step": 1835
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006422912584699753,
      "loss": 2.0859,
      "step": 1836
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006386544837088903,
      "loss": 2.1172,
      "step": 1837
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006350273317025252,
      "loss": 2.2285,
      "step": 1838
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006314098104537324,
      "loss": 2.2012,
      "step": 1839
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006278019279441122,
      "loss": 2.0361,
      "step": 1840
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006242036921339972,
      "loss": 2.2285,
      "step": 1841
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0006206151109624402,
      "loss": 2.2246,
      "step": 1842
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0006170361923471867,
      "loss": 2.2275,
      "step": 1843
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000613466944184669,
      "loss": 2.209,
      "step": 1844
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0006099073743499773,
      "loss": 2.208,
      "step": 1845
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0006063574906968511,
      "loss": 2.2754,
      "step": 1846
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0006028173010576581,
      "loss": 2.1562,
      "step": 1847
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005992868132433754,
      "loss": 2.0664,
      "step": 1848
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005957660350435773,
      "loss": 2.1621,
      "step": 1849
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005922549742264122,
      "loss": 2.2852,
      "step": 1850
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005887536385385917,
      "loss": 2.1875,
      "step": 1851
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005852620357053651,
      "loss": 2.1758,
      "step": 1852
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005817801734305134,
      "loss": 2.085,
      "step": 1853
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005783080593963219,
      "loss": 2.1963,
      "step": 1854
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005748457012635683,
      "loss": 2.0869,
      "step": 1855
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005713931066715078,
      "loss": 2.123,
      "step": 1856
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005679502832378497,
      "loss": 2.2178,
      "step": 1857
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005645172385587482,
      "loss": 2.1279,
      "step": 1858
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005610939802087783,
      "loss": 2.1758,
      "step": 1859
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005576805157409265,
      "loss": 2.0752,
      "step": 1860
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005542768526865677,
      "loss": 2.0723,
      "step": 1861
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005508829985554508,
      "loss": 2.1426,
      "step": 1862
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005474989608356856,
      "loss": 2.1562,
      "step": 1863
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005441247469937194,
      "loss": 2.1777,
      "step": 1864
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005407603644743286,
      "loss": 2.1924,
      "step": 1865
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005374058207005944,
      "loss": 2.1152,
      "step": 1866
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005340611230738907,
      "loss": 2.1543,
      "step": 1867
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005307262789738693,
      "loss": 2.0918,
      "step": 1868
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005274012957584389,
      "loss": 2.2139,
      "step": 1869
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005240861807637531,
      "loss": 2.1738,
      "step": 1870
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005207809413041914,
      "loss": 2.1045,
      "step": 1871
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005174855846723458,
      "loss": 2.1846,
      "step": 1872
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000514200118139001,
      "loss": 2.1504,
      "step": 1873
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005109245489531211,
      "loss": 2.1758,
      "step": 1874
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005076588843418345,
      "loss": 2.1348,
      "step": 1875
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005044031315104136,
      "loss": 2.1934,
      "step": 1876
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0005011572976422657,
      "loss": 2.125,
      "step": 1877
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004979213898989082,
      "loss": 2.167,
      "step": 1878
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004946954154199623,
      "loss": 2.1533,
      "step": 1879
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004914793813231305,
      "loss": 2.2324,
      "step": 1880
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004882732947041818,
      "loss": 2.1768,
      "step": 1881
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00048507716263694156,
      "loss": 2.0439,
      "step": 1882
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00048189099217326614,
      "loss": 2.1953,
      "step": 1883
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00047871479034303834,
      "loss": 2.2051,
      "step": 1884
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004755485641541424,
      "loss": 2.2441,
      "step": 1885
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004723923205924557,
      "loss": 2.1318,
      "step": 1886
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00046924606662182734,
      "loss": 2.2422,
      "step": 1887
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000466109809184066,
      "loss": 2.166,
      "step": 1888
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00046298355519892756,
      "loss": 2.2109,
      "step": 1889
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004598673115640922,
      "loss": 2.1045,
      "step": 1890
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00045676108515515677,
      "loss": 2.1777,
      "step": 1891
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004536648828256146,
      "loss": 2.25,
      "step": 1892
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00045057871140684325,
      "loss": 2.3105,
      "step": 1893
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00044750257770808765,
      "loss": 2.0996,
      "step": 1894
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004444364885164448,
      "loss": 2.1621,
      "step": 1895
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004413804505968533,
      "loss": 2.1191,
      "step": 1896
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00043833447069206944,
      "loss": 2.1445,
      "step": 1897
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004352985555226635,
      "loss": 2.2168,
      "step": 1898
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004322727117869951,
      "loss": 2.2207,
      "step": 1899
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00042925694616120503,
      "loss": 2.0986,
      "step": 1900
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004262512652991968,
      "loss": 2.0986,
      "step": 1901
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00042325567583262113,
      "loss": 2.2168,
      "step": 1902
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004202701843708689,
      "loss": 2.1934,
      "step": 1903
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00041729479750104493,
      "loss": 2.127,
      "step": 1904
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00041432952178796446,
      "loss": 2.2246,
      "step": 1905
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00041137436377412963,
      "loss": 2.2891,
      "step": 1906
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004084293299797226,
      "loss": 2.1719,
      "step": 1907
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0004054944269025862,
      "loss": 2.2275,
      "step": 1908
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004025696610182095,
      "loss": 2.1875,
      "step": 1909
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00039965503877971876,
      "loss": 2.1426,
      "step": 1910
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003967505666178556,
      "loss": 2.0869,
      "step": 1911
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00039385625094097155,
      "loss": 2.209,
      "step": 1912
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00039097209813500344,
      "loss": 2.2793,
      "step": 1913
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00038809811456347044,
      "loss": 2.2334,
      "step": 1914
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003852343065674507,
      "loss": 2.1973,
      "step": 1915
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003823806804655727,
      "loss": 2.2031,
      "step": 1916
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003795372425540006,
      "loss": 2.2402,
      "step": 1917
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003767039991064181,
      "loss": 2.0352,
      "step": 1918
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003738809563740175,
      "loss": 2.2676,
      "step": 1919
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00037106812058548377,
      "loss": 2.0996,
      "step": 1920
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00036826549794698074,
      "loss": 2.1572,
      "step": 1921
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003654730946421403,
      "loss": 2.1963,
      "step": 1922
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003626909168320447,
      "loss": 2.1943,
      "step": 1923
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00035991897065521693,
      "loss": 2.168,
      "step": 1924
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00035715726222760257,
      "loss": 2.2793,
      "step": 1925
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003544057976425619,
      "loss": 2.1943,
      "step": 1926
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00035166458297085146,
      "loss": 2.0664,
      "step": 1927
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00034893362426061114,
      "loss": 2.168,
      "step": 1928
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00034621292753735767,
      "loss": 2.125,
      "step": 1929
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003435024988039592,
      "loss": 2.3066,
      "step": 1930
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00034080234404063547,
      "loss": 2.1777,
      "step": 1931
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003381124692049331,
      "loss": 2.1719,
      "step": 1932
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003354328802317197,
      "loss": 2.1152,
      "step": 1933
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00033276358303316767,
      "loss": 2.1748,
      "step": 1934
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00033010458349874206,
      "loss": 2.0811,
      "step": 1935
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00032745588749518773,
      "loss": 2.126,
      "step": 1936
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00032481750086651605,
      "loss": 2.1904,
      "step": 1937
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003221894294339911,
      "loss": 2.2363,
      "step": 1938
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003195716789961184,
      "loss": 2.1699,
      "step": 1939
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003169642553286334,
      "loss": 2.1709,
      "step": 1940
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003143671641844831,
      "loss": 2.1152,
      "step": 1941
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003117804112938205,
      "loss": 2.1084,
      "step": 1942
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003092040023639869,
      "loss": 2.1533,
      "step": 1943
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003066379430795002,
      "loss": 2.1582,
      "step": 1944
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003040822391020459,
      "loss": 2.1064,
      "step": 1945
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00030153689607045843,
      "loss": 2.2041,
      "step": 1946
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002990019196007154,
      "loss": 2.0732,
      "step": 1947
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002964773152859185,
      "loss": 2.1279,
      "step": 1948
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00029396308869628795,
      "loss": 2.1719,
      "step": 1949
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00029145924537914483,
      "loss": 2.1143,
      "step": 1950
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002889657908589,
      "loss": 2.2402,
      "step": 1951
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000286482730637046,
      "loss": 2.1621,
      "step": 1952
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002840100701921383,
      "loss": 2.0938,
      "step": 1953
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000281547814979789,
      "loss": 2.2305,
      "step": 1954
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00027909597043265013,
      "loss": 2.1553,
      "step": 1955
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002766545419604066,
      "loss": 2.1094,
      "step": 1956
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00027422353494975906,
      "loss": 2.1787,
      "step": 1957
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002718029547644157,
      "loss": 2.2793,
      "step": 1958
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00026939280674508016,
      "loss": 2.2148,
      "step": 1959
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002669930962094358,
      "loss": 2.2422,
      "step": 1960
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002646038284521413,
      "loss": 2.1611,
      "step": 1961
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00026222500874481026,
      "loss": 2.2295,
      "step": 1962
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00025985664233600826,
      "loss": 2.1875,
      "step": 1963
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002574987344512336,
      "loss": 2.21,
      "step": 1964
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00025515129029290984,
      "loss": 2.1953,
      "step": 1965
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00025281431504037554,
      "loss": 2.2285,
      "step": 1966
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002504878138498684,
      "loss": 2.126,
      "step": 1967
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000248171791854519,
      "loss": 2.1348,
      "step": 1968
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00024586625416433473,
      "loss": 2.1104,
      "step": 1969
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00024357120586619208,
      "loss": 2.2402,
      "step": 1970
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00024128665202382326,
      "loss": 2.1924,
      "step": 1971
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023901259767780515,
      "loss": 2.0039,
      "step": 1972
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002367490478455514,
      "loss": 2.127,
      "step": 1973
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00023449600752129595,
      "loss": 2.2051,
      "step": 1974
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00023225348167608685,
      "loss": 2.3145,
      "step": 1975
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00023002147525777117,
      "loss": 2.2266,
      "step": 1976
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00022779999319098854,
      "loss": 2.2598,
      "step": 1977
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002255890403771571,
      "loss": 2.1152,
      "step": 1978
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00022338862169446138,
      "loss": 2.0605,
      "step": 1979
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002211987419978484,
      "loss": 2.1221,
      "step": 1980
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021901940611900706,
      "loss": 2.1396,
      "step": 1981
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021685061886636659,
      "loss": 2.1455,
      "step": 1982
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021469238502507925,
      "loss": 2.2207,
      "step": 1983
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021254470935701543,
      "loss": 2.1367,
      "step": 1984
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00021040759660074794,
      "loss": 2.0801,
      "step": 1985
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020828105147154276,
      "loss": 2.1133,
      "step": 1986
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020616507866135446,
      "loss": 2.1875,
      "step": 1987
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00020405968283880582,
      "loss": 2.1738,
      "step": 1988
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002019648686491865,
      "loss": 2.2246,
      "step": 1989
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019988064071443769,
      "loss": 2.1152,
      "step": 1990
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019780700363314252,
      "loss": 2.3018,
      "step": 1991
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001957439619805196,
      "loss": 2.125,
      "step": 1992
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019369152030840553,
      "loss": 2.2119,
      "step": 1993
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019164968314525522,
      "loss": 2.166,
      "step": 1994
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018961845499611995,
      "loss": 2.1758,
      "step": 1995
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018759784034264927,
      "loss": 2.1689,
      "step": 1996
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001855878436430708,
      "loss": 2.1201,
      "step": 1997
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001835884693321871,
      "loss": 2.1387,
      "step": 1998
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018159972182136386,
      "loss": 2.1357,
      "step": 1999
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017962160549851947,
      "loss": 2.1865,
      "step": 2000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017765412472811772,
      "loss": 2.0791,
      "step": 2001
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017569728385115224,
      "loss": 2.0713,
      "step": 2002
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017375108718514665,
      "loss": 2.1914,
      "step": 2003
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017181553902413438,
      "loss": 2.2021,
      "step": 2004
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016989064363865769,
      "loss": 2.1455,
      "step": 2005
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001679764052757532,
      "loss": 2.166,
      "step": 2006
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016607282815894465,
      "loss": 2.1338,
      "step": 2007
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016417991648823405,
      "loss": 2.2266,
      "step": 2008
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016229767444008835,
      "loss": 2.2168,
      "step": 2009
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001604261061674378,
      "loss": 2.1494,
      "step": 2010
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015856521579965866,
      "loss": 2.2012,
      "step": 2011
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015671500744256938,
      "loss": 2.0576,
      "step": 2012
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015487548517841953,
      "loss": 2.2246,
      "step": 2013
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001530466530658814,
      "loss": 2.1416,
      "step": 2014
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015122851514004054,
      "loss": 2.1113,
      "step": 2015
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014942107541238703,
      "loss": 2.0869,
      "step": 2016
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00014762433787080808,
      "loss": 2.124,
      "step": 2017
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001458383064795754,
      "loss": 2.2373,
      "step": 2018
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001440629851793407,
      "loss": 2.2568,
      "step": 2019
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00014229837788712563,
      "loss": 2.1621,
      "step": 2020
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00014054448849631085,
      "loss": 2.1641,
      "step": 2021
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013880132087663145,
      "loss": 2.1875,
      "step": 2022
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013706887887416418,
      "loss": 2.085,
      "step": 2023
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013534716631132316,
      "loss": 2.1074,
      "step": 2024
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013363618698684855,
      "loss": 2.1807,
      "step": 2025
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001319359446757973,
      "loss": 2.0605,
      "step": 2026
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013024644312954026,
      "loss": 2.0986,
      "step": 2027
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012856768607574564,
      "loss": 2.0508,
      "step": 2028
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012689967721837947,
      "loss": 2.0869,
      "step": 2029
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012524242023769007,
      "loss": 2.0645,
      "step": 2030
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012359591879020527,
      "loss": 2.1514,
      "step": 2031
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012196017650872082,
      "loss": 2.0938,
      "step": 2032
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00012033519700229367,
      "loss": 2.2422,
      "step": 2033
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011872098385623586,
      "loss": 2.1191,
      "step": 2034
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001171175406321029,
      "loss": 2.1143,
      "step": 2035
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001155248708676887,
      "loss": 2.0996,
      "step": 2036
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011394297807701737,
      "loss": 2.2832,
      "step": 2037
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011237186575033253,
      "loss": 2.1445,
      "step": 2038
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00011081153735409521,
      "loss": 2.2109,
      "step": 2039
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010926199633097155,
      "loss": 2.209,
      "step": 2040
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010772324609982787,
      "loss": 2.1221,
      "step": 2041
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010619529005571893,
      "loss": 2.0762,
      "step": 2042
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010467813156988747,
      "loss": 2.0547,
      "step": 2043
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010317177398975031,
      "loss": 2.1348,
      "step": 2044
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010167622063889326,
      "loss": 2.0996,
      "step": 2045
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010019147481706626,
      "loss": 2.1357,
      "step": 2046
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.87175398001705e-05,
      "loss": 2.1602,
      "step": 2047
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.725441884025854e-05,
      "loss": 2.0576,
      "step": 2048
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.580211516551862e-05,
      "loss": 2.2246,
      "step": 2049
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.436063198027589e-05,
      "loss": 2.0859,
      "step": 2050
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.292997246497959e-05,
      "loss": 2.0938,
      "step": 2051
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.151013977619693e-05,
      "loss": 2.2305,
      "step": 2052
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.010113704661038e-05,
      "loss": 2.0889,
      "step": 2053
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.870296738500316e-05,
      "loss": 2.2559,
      "step": 2054
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.731563387626096e-05,
      "loss": 2.2178,
      "step": 2055
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.593913958135691e-05,
      "loss": 2.0879,
      "step": 2056
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.457348753735328e-05,
      "loss": 2.207,
      "step": 2057
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.321868075738592e-05,
      "loss": 2.1504,
      "step": 2058
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.187472223066373e-05,
      "loss": 2.248,
      "step": 2059
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.054161492246137e-05,
      "loss": 2.1631,
      "step": 2060
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.92193617741105e-05,
      "loss": 2.2432,
      "step": 2061
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.790796570299463e-05,
      "loss": 2.1426,
      "step": 2062
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.660742960254208e-05,
      "loss": 2.2051,
      "step": 2063
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.531775634222138e-05,
      "loss": 2.0703,
      "step": 2064
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.403894876753192e-05,
      "loss": 2.1201,
      "step": 2065
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.277100970000061e-05,
      "loss": 2.1387,
      "step": 2066
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.151394193717408e-05,
      "loss": 2.1367,
      "step": 2067
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.02677482526115e-05,
      "loss": 2.1064,
      "step": 2068
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.903243139588234e-05,
      "loss": 2.1523,
      "step": 2069
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.780799409255523e-05,
      "loss": 2.0889,
      "step": 2070
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.659443904419638e-05,
      "loss": 2.2207,
      "step": 2071
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.539176892836007e-05,
      "loss": 2.167,
      "step": 2072
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.419998639858537e-05,
      "loss": 2.252,
      "step": 2073
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.301909408438888e-05,
      "loss": 2.1934,
      "step": 2074
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.18490945912592e-05,
      "loss": 2.1553,
      "step": 2075
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.0689990500652494e-05,
      "loss": 2.127,
      "step": 2076
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.954178436998359e-05,
      "loss": 2.1455,
      "step": 2077
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.8404478732624335e-05,
      "loss": 2.1416,
      "step": 2078
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.7278076097894705e-05,
      "loss": 2.0908,
      "step": 2079
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.6162578951058917e-05,
      "loss": 2.042,
      "step": 2080
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.5057989753319326e-05,
      "loss": 2.2324,
      "step": 2081
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.396431094181198e-05,
      "loss": 2.2539,
      "step": 2082
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.288154492960107e-05,
      "loss": 2.2324,
      "step": 2083
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.180969410567116e-05,
      "loss": 2.2891,
      "step": 2084
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.074876083492441e-05,
      "loss": 2.0488,
      "step": 2085
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.969874745817671e-05,
      "loss": 2.2109,
      "step": 2086
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.865965629214819e-05,
      "loss": 2.0791,
      "step": 2087
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.763148962946218e-05,
      "loss": 2.0996,
      "step": 2088
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.661424973863682e-05,
      "loss": 2.0918,
      "step": 2089
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.560793886408399e-05,
      "loss": 2.2188,
      "step": 2090
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.4612559226099855e-05,
      "loss": 2.1797,
      "step": 2091
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.362811302086267e-05,
      "loss": 2.2266,
      "step": 2092
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.2654602420428844e-05,
      "loss": 2.1094,
      "step": 2093
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.169202957272522e-05,
      "loss": 2.1426,
      "step": 2094
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.074039660154738e-05,
      "loss": 2.2324,
      "step": 2095
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.979970560655133e-05,
      "loss": 2.2266,
      "step": 2096
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.886995866325294e-05,
      "loss": 2.2021,
      "step": 2097
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.795115782302072e-05,
      "loss": 2.2061,
      "step": 2098
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.7043305113071965e-05,
      "loss": 2.1201,
      "step": 2099
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.614640253646828e-05,
      "loss": 2.1592,
      "step": 2100
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.526045207211059e-05,
      "loss": 2.2539,
      "step": 2101
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.4385455674737496e-05,
      "loss": 2.1104,
      "step": 2102
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.352141527491526e-05,
      "loss": 2.1465,
      "step": 2103
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.266833277904113e-05,
      "loss": 2.1641,
      "step": 2104
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.1826210069332836e-05,
      "loss": 2.1445,
      "step": 2105
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.0995049003826324e-05,
      "loss": 2.1621,
      "step": 2106
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.017485141637355e-05,
      "loss": 2.1289,
      "step": 2107
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.9365619116636377e-05,
      "loss": 2.127,
      "step": 2108
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.8567353890082694e-05,
      "loss": 2.1318,
      "step": 2109
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.7780057497983068e-05,
      "loss": 2.1328,
      "step": 2110
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.700373167740744e-05,
      "loss": 2.1055,
      "step": 2111
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.6238378141220097e-05,
      "loss": 2.1123,
      "step": 2112
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.5483998578076374e-05,
      "loss": 2.127,
      "step": 2113
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.4740594652418734e-05,
      "loss": 2.0703,
      "step": 2114
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.4008168004472917e-05,
      "loss": 2.1328,
      "step": 2115
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.328672025024625e-05,
      "loss": 2.084,
      "step": 2116
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.2576252981520994e-05,
      "loss": 2.0742,
      "step": 2117
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.1876767765853235e-05,
      "loss": 2.1113,
      "step": 2118
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.118826614656788e-05,
      "loss": 2.0566,
      "step": 2119
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.051074964275701e-05,
      "loss": 2.1738,
      "step": 2120
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.9844219749273752e-05,
      "loss": 2.1426,
      "step": 2121
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.9188677936731736e-05,
      "loss": 2.1299,
      "step": 2122
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.8544125651501208e-05,
      "loss": 2.0869,
      "step": 2123
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.7910564315704035e-05,
      "loss": 2.1494,
      "step": 2124
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.7287995327214256e-05,
      "loss": 2.1182,
      "step": 2125
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.6676420059649754e-05,
      "loss": 2.2344,
      "step": 2126
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6075839862374485e-05,
      "loss": 2.0996,
      "step": 2127
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5486256060492366e-05,
      "loss": 2.2334,
      "step": 2128
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4907669954844493e-05,
      "loss": 2.123,
      "step": 2129
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.434008282200805e-05,
      "loss": 2.0557,
      "step": 2130
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3783495914291843e-05,
      "loss": 2.1172,
      "step": 2131
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3237910459734103e-05,
      "loss": 2.2266,
      "step": 2132
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.270332766210025e-05,
      "loss": 2.1025,
      "step": 2133
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2179748700879012e-05,
      "loss": 2.1172,
      "step": 2134
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1667174731280206e-05,
      "loss": 2.1855,
      "step": 2135
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.116560688423418e-05,
      "loss": 2.21,
      "step": 2136
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0675046266386268e-05,
      "loss": 2.2246,
      "step": 2137
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0195493960095669e-05,
      "loss": 2.1592,
      "step": 2138
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.72695102343435e-06,
      "loss": 2.1807,
      "step": 2139
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.26941849018259e-06,
      "loss": 2.1572,
      "step": 2140
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.822897369827333e-06,
      "loss": 2.1455,
      "step": 2141
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.387388647561612e-06,
      "loss": 2.1104,
      "step": 2142
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.962893284279016e-06,
      "loss": 2.123,
      "step": 2143
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.549412216574791e-06,
      "loss": 2.1836,
      "step": 2144
    },
    {
      "epoch": 0.98,
      "learning_rate": 7.1469463567430674e-06,
      "loss": 2.1377,
      "step": 2145
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.755496592773524e-06,
      "loss": 2.1562,
      "step": 2146
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.375063788349733e-06,
      "loss": 2.1797,
      "step": 2147
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.005648782848594e-06,
      "loss": 2.3027,
      "step": 2148
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.647252391337565e-06,
      "loss": 2.082,
      "step": 2149
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.299875404572441e-06,
      "loss": 2.0898,
      "step": 2150
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.963518588996796e-06,
      "loss": 2.0898,
      "step": 2151
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.638182686738657e-06,
      "loss": 2.2373,
      "step": 2152
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.323868415611054e-06,
      "loss": 2.1514,
      "step": 2153
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.020576469108139e-06,
      "loss": 2.1602,
      "step": 2154
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.7283075164046277e-06,
      "loss": 2.126,
      "step": 2155
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.4470622023557995e-06,
      "loss": 2.1357,
      "step": 2156
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.176841147492504e-06,
      "loss": 2.0342,
      "step": 2157
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.9176449480244892e-06,
      "loss": 2.126,
      "step": 2158
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.6694741758342966e-06,
      "loss": 2.207,
      "step": 2159
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4323293784789256e-06,
      "loss": 2.1094,
      "step": 2160
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.20621107918928e-06,
      "loss": 2.3125,
      "step": 2161
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9911197768662793e-06,
      "loss": 2.1816,
      "step": 2162
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.7870559460814173e-06,
      "loss": 2.0957,
      "step": 2163
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.5940200370750946e-06,
      "loss": 2.2295,
      "step": 2164
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.412012475757729e-06,
      "loss": 2.2695,
      "step": 2165
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.2410336637047603e-06,
      "loss": 2.1367,
      "step": 2166
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.081083978159425e-06,
      "loss": 2.1768,
      "step": 2167
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.321637720310916e-07,
      "loss": 2.2207,
      "step": 2168
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.942733738924846e-07,
      "loss": 2.0977,
      "step": 2169
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.6741308798135e-07,
      "loss": 2.0625,
      "step": 2170
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.515831941993455e-07,
      "loss": 2.2227,
      "step": 2171
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.4678394810981905e-07,
      "loss": 2.1562,
      "step": 2172
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.530155809394753e-07,
      "loss": 2.1689,
      "step": 2173
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.7027829957559926e-07,
      "loss": 2.207,
      "step": 2174
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.985722865682771e-07,
      "loss": 2.2471,
      "step": 2175
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3789770012762047e-07,
      "loss": 2.1855,
      "step": 2176
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.825467412376664e-08,
      "loss": 2.1104,
      "step": 2177
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.96433180879885e-08,
      "loss": 2.0947,
      "step": 2178
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.206371721158451e-08,
      "loss": 2.1416,
      "step": 2179
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.515932345323549e-09,
      "loss": 2.2588,
      "step": 2180
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 2.1152,
      "step": 2181
    },
    {
      "epoch": 1.0,
      "step": 2181,
      "total_flos": 6.038122451299205e+17,
      "train_loss": 2.332893633940853,
      "train_runtime": 15721.5859,
      "train_samples_per_second": 35.501,
      "train_steps_per_second": 0.139
    }
  ],
  "max_steps": 2181,
  "num_train_epochs": 1,
  "total_flos": 6.038122451299205e+17,
  "trial_name": null,
  "trial_params": null
}