{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5442258000397535,
  "eval_steps": 500,
  "global_step": 3200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.0582010582010582e-06,
      "loss": 1.6618,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1164021164021164e-06,
      "loss": 1.696,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 1.7135,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.232804232804233e-06,
      "loss": 1.631,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.291005291005291e-06,
      "loss": 1.6657,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.349206349206349e-06,
      "loss": 1.6476,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.7109,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.465608465608466e-06,
      "loss": 1.6739,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.523809523809523e-06,
      "loss": 1.7259,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0582010582010582e-05,
      "loss": 1.7549,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.164021164021164e-05,
      "loss": 1.6553,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 1.7092,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.3756613756613756e-05,
      "loss": 1.7751,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 1.6998,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 1.6261,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.693121693121693e-05,
      "loss": 1.6808,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.798941798941799e-05,
      "loss": 1.6979,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 1.6986,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.0105820105820105e-05,
      "loss": 1.6548,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.1164021164021164e-05,
      "loss": 1.6378,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.616,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.328042328042328e-05,
      "loss": 1.6715,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.4338624338624338e-05,
      "loss": 1.6333,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 1.5815,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.6455026455026456e-05,
      "loss": 1.6121,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7513227513227512e-05,
      "loss": 1.6195,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.5157,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.962962962962963e-05,
      "loss": 1.5768,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.068783068783069e-05,
      "loss": 1.5739,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 1.5092,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.280423280423281e-05,
      "loss": 1.4757,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.386243386243386e-05,
      "loss": 1.4829,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.492063492063492e-05,
      "loss": 1.4927,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.597883597883598e-05,
      "loss": 1.4505,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.5062,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.809523809523809e-05,
      "loss": 1.4394,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.9153439153439155e-05,
      "loss": 1.483,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.021164021164021e-05,
      "loss": 1.4868,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.126984126984127e-05,
      "loss": 1.4207,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.232804232804233e-05,
      "loss": 1.416,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.3386243386243384e-05,
      "loss": 1.4789,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.4005,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.55026455026455e-05,
      "loss": 1.4074,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.656084656084656e-05,
      "loss": 1.4271,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.4274,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8677248677248676e-05,
      "loss": 1.377,
      "step": 46
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.973544973544973e-05,
      "loss": 1.4208,
      "step": 47
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.0793650793650794e-05,
      "loss": 1.4227,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.185185185185185e-05,
      "loss": 1.3726,
      "step": 49
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.291005291005291e-05,
      "loss": 1.3806,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.396825396825397e-05,
      "loss": 1.331,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.5026455026455024e-05,
      "loss": 1.3416,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.6084656084656086e-05,
      "loss": 1.3727,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.3005,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.82010582010582e-05,
      "loss": 1.3257,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.925925925925926e-05,
      "loss": 1.324,
      "step": 56
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.0317460317460316e-05,
      "loss": 1.3242,
      "step": 57
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.137566137566138e-05,
      "loss": 1.3283,
      "step": 58
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.243386243386243e-05,
      "loss": 1.3716,
      "step": 59
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.349206349206349e-05,
      "loss": 1.3201,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.455026455026454e-05,
      "loss": 1.3319,
      "step": 61
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.560846560846561e-05,
      "loss": 1.3056,
      "step": 62
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2754,
      "step": 63
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.772486772486773e-05,
      "loss": 1.2884,
      "step": 64
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.878306878306878e-05,
      "loss": 1.3128,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.984126984126984e-05,
      "loss": 1.2913,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.089947089947089e-05,
      "loss": 1.3081,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.195767195767196e-05,
      "loss": 1.2619,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.301587301587302e-05,
      "loss": 1.2545,
      "step": 69
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.407407407407407e-05,
      "loss": 1.2793,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.513227513227513e-05,
      "loss": 1.2546,
      "step": 71
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.619047619047618e-05,
      "loss": 1.2823,
      "step": 72
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.724867724867725e-05,
      "loss": 1.284,
      "step": 73
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.830687830687831e-05,
      "loss": 1.2325,
      "step": 74
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.936507936507937e-05,
      "loss": 1.2402,
      "step": 75
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.042328042328042e-05,
      "loss": 1.2588,
      "step": 76
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.148148148148148e-05,
      "loss": 1.2314,
      "step": 77
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.253968253968255e-05,
      "loss": 1.2227,
      "step": 78
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.35978835978836e-05,
      "loss": 1.2109,
      "step": 79
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.465608465608466e-05,
      "loss": 1.2324,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.2087,
      "step": 81
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.677248677248677e-05,
      "loss": 1.2445,
      "step": 82
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.783068783068782e-05,
      "loss": 1.2633,
      "step": 83
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.212,
      "step": 84
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.994708994708995e-05,
      "loss": 1.1948,
      "step": 85
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.1005291005291e-05,
      "loss": 1.2063,
      "step": 86
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.206349206349206e-05,
      "loss": 1.222,
      "step": 87
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.312169312169312e-05,
      "loss": 1.2242,
      "step": 88
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.417989417989419e-05,
      "loss": 1.1912,
      "step": 89
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.1717,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.62962962962963e-05,
      "loss": 1.1881,
      "step": 91
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.735449735449735e-05,
      "loss": 1.189,
      "step": 92
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.841269841269841e-05,
      "loss": 1.1934,
      "step": 93
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.947089947089946e-05,
      "loss": 1.1683,
      "step": 94
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010052910052910055,
      "loss": 1.188,
      "step": 95
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010158730158730159,
      "loss": 1.1912,
      "step": 96
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010264550264550266,
      "loss": 1.2043,
      "step": 97
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001037037037037037,
      "loss": 1.1402,
      "step": 98
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010476190476190477,
      "loss": 1.1985,
      "step": 99
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010582010582010582,
      "loss": 1.1799,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001068783068783069,
      "loss": 1.1967,
      "step": 101
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010793650793650794,
      "loss": 1.1782,
      "step": 102
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000108994708994709,
      "loss": 1.1593,
      "step": 103
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011005291005291005,
      "loss": 1.136,
      "step": 104
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.1841,
      "step": 105
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011216931216931217,
      "loss": 1.1354,
      "step": 106
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011322751322751324,
      "loss": 1.1622,
      "step": 107
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.1408,
      "step": 108
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011534391534391535,
      "loss": 1.1199,
      "step": 109
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001164021164021164,
      "loss": 1.139,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011746031746031746,
      "loss": 1.1302,
      "step": 111
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011851851851851852,
      "loss": 1.146,
      "step": 112
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011957671957671959,
      "loss": 1.1391,
      "step": 113
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012063492063492063,
      "loss": 1.1345,
      "step": 114
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001216931216931217,
      "loss": 1.1439,
      "step": 115
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012275132275132276,
      "loss": 1.1496,
      "step": 116
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001238095238095238,
      "loss": 1.1621,
      "step": 117
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012486772486772487,
      "loss": 1.1683,
      "step": 118
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012592592592592592,
      "loss": 1.1298,
      "step": 119
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012698412698412698,
      "loss": 1.0994,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012804232804232806,
      "loss": 1.1485,
      "step": 121
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001291005291005291,
      "loss": 1.1169,
      "step": 122
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013015873015873017,
      "loss": 1.1045,
      "step": 123
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013121693121693123,
      "loss": 1.1032,
      "step": 124
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013227513227513228,
      "loss": 1.1678,
      "step": 125
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.106,
      "step": 126
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001343915343915344,
      "loss": 1.1382,
      "step": 127
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013544973544973545,
      "loss": 1.1348,
      "step": 128
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001365079365079365,
      "loss": 1.1392,
      "step": 129
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013756613756613756,
      "loss": 1.1178,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013862433862433865,
      "loss": 1.1351,
      "step": 131
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013968253968253967,
      "loss": 1.1128,
      "step": 132
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014074074074074076,
      "loss": 1.1295,
      "step": 133
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014179894179894179,
      "loss": 1.0983,
      "step": 134
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.1304,
      "step": 135
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014391534391534392,
      "loss": 1.0859,
      "step": 136
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014497354497354498,
      "loss": 1.1143,
      "step": 137
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014603174603174603,
      "loss": 1.0783,
      "step": 138
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001470899470899471,
      "loss": 1.0981,
      "step": 139
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014814814814814815,
      "loss": 1.0909,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014920634920634923,
      "loss": 1.0803,
      "step": 141
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015026455026455026,
      "loss": 1.1189,
      "step": 142
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015132275132275134,
      "loss": 1.0906,
      "step": 143
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015238095238095237,
      "loss": 1.1412,
      "step": 144
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015343915343915345,
      "loss": 1.1092,
      "step": 145
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001544973544973545,
      "loss": 1.0699,
      "step": 146
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.1105,
      "step": 147
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015661375661375662,
      "loss": 1.0776,
      "step": 148
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015767195767195767,
      "loss": 1.1087,
      "step": 149
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015873015873015873,
      "loss": 1.107,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015978835978835979,
      "loss": 1.0964,
      "step": 151
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016084656084656084,
      "loss": 1.0856,
      "step": 152
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016190476190476192,
      "loss": 1.1039,
      "step": 153
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016296296296296295,
      "loss": 1.0861,
      "step": 154
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016402116402116404,
      "loss": 1.0926,
      "step": 155
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001650793650793651,
      "loss": 1.082,
      "step": 156
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016613756613756615,
      "loss": 1.0769,
      "step": 157
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001671957671957672,
      "loss": 1.0934,
      "step": 158
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00016825396825396826,
      "loss": 1.0868,
      "step": 159
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00016931216931216931,
      "loss": 1.0544,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017037037037037037,
      "loss": 1.0722,
      "step": 161
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.0886,
      "step": 162
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001724867724867725,
      "loss": 1.0662,
      "step": 163
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017354497354497354,
      "loss": 1.0618,
      "step": 164
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017460317460317462,
      "loss": 1.0686,
      "step": 165
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017566137566137565,
      "loss": 1.0707,
      "step": 166
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017671957671957673,
      "loss": 1.0483,
      "step": 167
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.0873,
      "step": 168
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017883597883597884,
      "loss": 1.0499,
      "step": 169
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001798941798941799,
      "loss": 1.0726,
      "step": 170
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018095238095238095,
      "loss": 1.0841,
      "step": 171
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000182010582010582,
      "loss": 1.0903,
      "step": 172
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001830687830687831,
      "loss": 1.1022,
      "step": 173
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018412698412698412,
      "loss": 1.0613,
      "step": 174
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001851851851851852,
      "loss": 1.0283,
      "step": 175
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018624338624338623,
      "loss": 1.0709,
      "step": 176
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018730158730158731,
      "loss": 1.0379,
      "step": 177
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018835978835978837,
      "loss": 1.0379,
      "step": 178
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018941798941798943,
      "loss": 1.0113,
      "step": 179
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019047619047619048,
      "loss": 1.0556,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019153439153439154,
      "loss": 1.0193,
      "step": 181
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001925925925925926,
      "loss": 1.0217,
      "step": 182
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019365079365079365,
      "loss": 1.0041,
      "step": 183
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001947089947089947,
      "loss": 1.0135,
      "step": 184
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001957671957671958,
      "loss": 1.0233,
      "step": 185
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019682539682539682,
      "loss": 1.0416,
      "step": 186
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001978835978835979,
      "loss": 1.0262,
      "step": 187
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019894179894179893,
      "loss": 1.0642,
      "step": 188
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.0699,
      "step": 189
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999998672055812,
      "loss": 1.0179,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999994688223592,
      "loss": 1.0533,
      "step": 191
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000199999880485044,
      "loss": 1.0252,
      "step": 192
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999978752900001,
      "loss": 1.0041,
      "step": 193
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999966801412863,
      "loss": 1.0187,
      "step": 194
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999995219404616,
      "loss": 1.0842,
      "step": 195
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999934930803773,
      "loss": 1.0295,
      "step": 196
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999915011690287,
      "loss": 1.0225,
      "step": 197
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999989243671099,
      "loss": 0.995,
      "step": 198
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999986720587188,
      "loss": 1.0322,
      "step": 199
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999839319179654,
      "loss": 1.0146,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999808776641724,
      "loss": 0.9905,
      "step": 201
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000199997755782662,
      "loss": 1.0424,
      "step": 202
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999739724061897,
      "loss": 1.0733,
      "step": 203
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999701214038336,
      "loss": 1.0478,
      "step": 204
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999660048205747,
      "loss": 1.0214,
      "step": 205
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999961622657507,
      "loss": 1.0263,
      "step": 206
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999569749157932,
      "loss": 1.0118,
      "step": 207
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999520615966682,
      "loss": 1.0137,
      "step": 208
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999468827014373,
      "loss": 1.024,
      "step": 209
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999941438231475,
      "loss": 1.0151,
      "step": 210
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999357281882282,
      "loss": 1.0314,
      "step": 211
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999297525732134,
      "loss": 1.0336,
      "step": 212
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999923511388017,
      "loss": 0.9969,
      "step": 213
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999917004634297,
      "loss": 1.0084,
      "step": 214
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999102323137814,
      "loss": 1.0002,
      "step": 215
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999031944282691,
      "loss": 1.011,
      "step": 216
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999895890979629,
      "loss": 1.0212,
      "step": 217
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999888321969801,
      "loss": 0.9995,
      "step": 218
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001999880487400795,
      "loss": 1.0069,
      "step": 219
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019998723872746924,
      "loss": 0.9968,
      "step": 220
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998640215936438,
      "loss": 1.0488,
      "step": 221
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998553903598717,
      "loss": 1.0045,
      "step": 222
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998464935756677,
      "loss": 0.9733,
      "step": 223
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998373312433957,
      "loss": 1.0184,
      "step": 224
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999827903365488,
      "loss": 1.0039,
      "step": 225
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998182099444494,
      "loss": 0.9755,
      "step": 226
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999808250982854,
      "loss": 0.9957,
      "step": 227
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019997980264833466,
      "loss": 0.9916,
      "step": 228
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999787536448643,
      "loss": 1.0343,
      "step": 229
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019997767808815293,
      "loss": 0.9894,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999765759784862,
      "loss": 0.9828,
      "step": 231
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999754473161568,
      "loss": 1.0123,
      "step": 232
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999742921014645,
      "loss": 1.0305,
      "step": 233
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999731103347161,
      "loss": 1.0304,
      "step": 234
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019997190201622548,
      "loss": 1.0525,
      "step": 235
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019997066714631356,
      "loss": 1.0051,
      "step": 236
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999694057253083,
      "loss": 1.0114,
      "step": 237
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996811775354476,
      "loss": 0.9965,
      "step": 238
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996680323136493,
      "loss": 1.0161,
      "step": 239
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996546215911794,
      "loss": 0.9731,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996409453716007,
      "loss": 0.9707,
      "step": 241
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996270036585446,
      "loss": 1.0043,
      "step": 242
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996127964557134,
      "loss": 0.9632,
      "step": 243
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019995983237668815,
      "loss": 0.9571,
      "step": 244
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999583585595892,
      "loss": 0.9758,
      "step": 245
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995685819466593,
      "loss": 1.0077,
      "step": 246
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995533128231685,
      "loss": 0.9798,
      "step": 247
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995377782294744,
      "loss": 1.0078,
      "step": 248
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001999521978169703,
      "loss": 1.0,
      "step": 249
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995059126480506,
      "loss": 0.9693,
      "step": 250
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994895816687844,
      "loss": 0.9708,
      "step": 251
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994729852362416,
      "loss": 0.9455,
      "step": 252
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994561233548295,
      "loss": 1.0033,
      "step": 253
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994389960290268,
      "loss": 1.0285,
      "step": 254
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994216032633824,
      "loss": 1.0006,
      "step": 255
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994039450625155,
      "loss": 0.9645,
      "step": 256
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019993860214311159,
      "loss": 1.0057,
      "step": 257
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001999367832373944,
      "loss": 0.9519,
      "step": 258
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019993493778958308,
      "loss": 0.9934,
      "step": 259
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019993306580016774,
      "loss": 0.9576,
      "step": 260
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019993116726964554,
      "loss": 0.9769,
      "step": 261
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019992924219852074,
      "loss": 0.9781,
      "step": 262
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001999272905873046,
      "loss": 0.9606,
      "step": 263
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019992531243651543,
      "loss": 0.9308,
      "step": 264
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019992330774667863,
      "loss": 1.0165,
      "step": 265
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019992127651832667,
      "loss": 0.9323,
      "step": 266
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019991921875199892,
      "loss": 0.9503,
      "step": 267
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019991713444824196,
      "loss": 0.9717,
      "step": 268
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019991502360760933,
      "loss": 0.9931,
      "step": 269
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001999128862306617,
      "loss": 0.9899,
      "step": 270
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019991072231796667,
      "loss": 0.9638,
      "step": 271
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000199908531870099,
      "loss": 0.9361,
      "step": 272
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019990631488764042,
      "loss": 0.9414,
      "step": 273
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019990407137117973,
      "loss": 0.9647,
      "step": 274
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001999018013213128,
      "loss": 0.9603,
      "step": 275
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019989950473864253,
      "loss": 0.9671,
      "step": 276
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019989718162377886,
      "loss": 0.947,
      "step": 277
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001998948319773388,
      "loss": 1.0011,
      "step": 278
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001998924557999464,
      "loss": 0.9674,
      "step": 279
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019989005309223266,
      "loss": 1.0103,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019988762385483578,
      "loss": 0.9491,
      "step": 281
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019988516808840096,
      "loss": 0.964,
      "step": 282
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998826857935804,
      "loss": 1.0016,
      "step": 283
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019988017697103333,
      "loss": 0.9518,
      "step": 284
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019987764162142613,
      "loss": 0.9368,
      "step": 285
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019987507974543215,
      "loss": 0.9567,
      "step": 286
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019987249134373173,
      "loss": 0.9598,
      "step": 287
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998698764170124,
      "loss": 0.9682,
      "step": 288
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019986723496596861,
      "loss": 0.9318,
      "step": 289
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019986456699130193,
      "loss": 0.9627,
      "step": 290
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998618724937209,
      "loss": 0.9604,
      "step": 291
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998591514739412,
      "loss": 0.9708,
      "step": 292
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985640393268547,
      "loss": 1.0019,
      "step": 293
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985362987068347,
      "loss": 0.9639,
      "step": 294
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985082928867186,
      "loss": 0.9354,
      "step": 295
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019984800218739455,
      "loss": 0.9398,
      "step": 296
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019984514856760232,
      "loss": 0.9434,
      "step": 297
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998422684300531,
      "loss": 0.9283,
      "step": 298
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983936177551183,
      "loss": 0.9451,
      "step": 299
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983642860475043,
      "loss": 0.9506,
      "step": 300
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983346891854796,
      "loss": 0.9385,
      "step": 301
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983048271769046,
      "loss": 0.9252,
      "step": 302
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019982747000297105,
      "loss": 0.9531,
      "step": 303
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019982443077518988,
      "loss": 0.9471,
      "step": 304
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998213650351541,
      "loss": 0.9938,
      "step": 305
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019981827278367796,
      "loss": 0.9784,
      "step": 306
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998151540215827,
      "loss": 0.9434,
      "step": 307
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998120087496967,
      "loss": 0.9533,
      "step": 308
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001998088369688552,
      "loss": 0.982,
      "step": 309
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019980563867990066,
      "loss": 0.9564,
      "step": 310
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019980241388368252,
      "loss": 0.9445,
      "step": 311
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019979916258105728,
      "loss": 0.9486,
      "step": 312
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019979588477288834,
      "loss": 0.9554,
      "step": 313
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019979258046004628,
      "loss": 0.9231,
      "step": 314
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019978924964340875,
      "loss": 0.9736,
      "step": 315
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.9463,
      "step": 316
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019978250850229276,
      "loss": 0.985,
      "step": 317
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019977909817960464,
      "loss": 0.9462,
      "step": 318
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019977566135670176,
      "loss": 0.9757,
      "step": 319
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019977219803449692,
      "loss": 0.9708,
      "step": 320
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997687082139099,
      "loss": 0.9614,
      "step": 321
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019976519189586757,
      "loss": 0.9613,
      "step": 322
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019976164908130386,
      "loss": 0.937,
      "step": 323
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019975807977115967,
      "loss": 0.932,
      "step": 324
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019975448396638296,
      "loss": 0.9625,
      "step": 325
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019975086166792877,
      "loss": 0.9289,
      "step": 326
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019974721287675912,
      "loss": 0.9482,
      "step": 327
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997435375938431,
      "loss": 0.9376,
      "step": 328
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997398358201568,
      "loss": 0.9218,
      "step": 329
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997361075566834,
      "loss": 0.9099,
      "step": 330
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019973235280441304,
      "loss": 0.9574,
      "step": 331
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019972857156434298,
      "loss": 0.915,
      "step": 332
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019972476383747748,
      "loss": 0.9438,
      "step": 333
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001997209296248278,
      "loss": 0.9346,
      "step": 334
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019971706892741228,
      "loss": 1.0001,
      "step": 335
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001997131817462563,
      "loss": 0.9215,
      "step": 336
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001997092680823922,
      "loss": 0.9831,
      "step": 337
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019970532793685944,
      "loss": 0.9238,
      "step": 338
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001997013613107045,
      "loss": 0.9369,
      "step": 339
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996973682049808,
      "loss": 0.9582,
      "step": 340
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019969334862074894,
      "loss": 0.9648,
      "step": 341
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019968930255907644,
      "loss": 0.972,
      "step": 342
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996852300210379,
      "loss": 0.9264,
      "step": 343
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019968113100771496,
      "loss": 0.9358,
      "step": 344
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996770055201962,
      "loss": 0.9427,
      "step": 345
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019967285355957737,
      "loss": 0.9058,
      "step": 346
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019966867512696116,
      "loss": 0.9314,
      "step": 347
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019966447022345732,
      "loss": 0.9754,
      "step": 348
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019966023885018263,
      "loss": 0.9543,
      "step": 349
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996559810082609,
      "loss": 0.9355,
      "step": 350
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019965169669882294,
      "loss": 0.955,
      "step": 351
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019964738592300664,
      "loss": 0.9654,
      "step": 352
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996430486819569,
      "loss": 0.9519,
      "step": 353
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019963868497682561,
      "loss": 0.9302,
      "step": 354
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019963429480877173,
      "loss": 0.9487,
      "step": 355
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019962987817896127,
      "loss": 0.9885,
      "step": 356
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996254350885672,
      "loss": 0.9299,
      "step": 357
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996209655387696,
      "loss": 0.9216,
      "step": 358
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019961646953075548,
      "loss": 0.9208,
      "step": 359
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019961194706571896,
      "loss": 0.8981,
      "step": 360
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019960739814486113,
      "loss": 0.9452,
      "step": 361
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001996028227693902,
      "loss": 0.9227,
      "step": 362
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019959822094052124,
      "loss": 0.9335,
      "step": 363
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019959359265947653,
      "loss": 0.939,
      "step": 364
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019958893792748524,
      "loss": 0.9334,
      "step": 365
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019958425674578364,
      "loss": 0.9333,
      "step": 366
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000199579549115615,
      "loss": 0.9338,
      "step": 367
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019957481503822959,
      "loss": 0.9165,
      "step": 368
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019957005451488476,
      "loss": 0.9535,
      "step": 369
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001995652675468448,
      "loss": 0.9334,
      "step": 370
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019956045413538115,
      "loss": 0.8972,
      "step": 371
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019955561428177212,
      "loss": 0.9079,
      "step": 372
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019955074798730317,
      "loss": 0.9516,
      "step": 373
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019954585525326675,
      "loss": 0.9113,
      "step": 374
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019954093608096226,
      "loss": 0.9076,
      "step": 375
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995359904716962,
      "loss": 0.9293,
      "step": 376
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995310184267821,
      "loss": 0.9246,
      "step": 377
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019952601994754045,
      "loss": 0.9215,
      "step": 378
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019952099503529875,
      "loss": 0.9137,
      "step": 379
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019951594369139165,
      "loss": 0.9463,
      "step": 380
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995108659171607,
      "loss": 0.89,
      "step": 381
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995057617139544,
      "loss": 0.9161,
      "step": 382
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019950063108312854,
      "loss": 0.9221,
      "step": 383
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019949547402604566,
      "loss": 0.9409,
      "step": 384
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001994902905440754,
      "loss": 0.9037,
      "step": 385
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019948508063859447,
      "loss": 0.9427,
      "step": 386
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019947984431098657,
      "loss": 0.9376,
      "step": 387
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019947458156264238,
      "loss": 0.9552,
      "step": 388
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019946929239495967,
      "loss": 0.923,
      "step": 389
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019946397680934314,
      "loss": 0.8948,
      "step": 390
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001994586348072046,
      "loss": 0.9177,
      "step": 391
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019945326638996276,
      "loss": 0.9408,
      "step": 392
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019944787155904345,
      "loss": 0.9364,
      "step": 393
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019944245031587948,
      "loss": 0.9624,
      "step": 394
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019943700266191066,
      "loss": 0.9217,
      "step": 395
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019943152859858384,
      "loss": 0.9101,
      "step": 396
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019942602812735288,
      "loss": 0.9306,
      "step": 397
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001994205012496786,
      "loss": 0.9016,
      "step": 398
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001994149479670289,
      "loss": 0.9158,
      "step": 399
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001994093682808787,
      "loss": 0.9016,
      "step": 400
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019940376219270984,
      "loss": 0.95,
      "step": 401
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019939812970401128,
      "loss": 0.9333,
      "step": 402
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019939247081627893,
      "loss": 0.903,
      "step": 403
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019938678553101574,
      "loss": 0.9094,
      "step": 404
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019938107384973166,
      "loss": 0.9432,
      "step": 405
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019937533577394362,
      "loss": 0.942,
      "step": 406
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001993695713051756,
      "loss": 0.924,
      "step": 407
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019936378044495861,
      "loss": 0.9125,
      "step": 408
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993579631948306,
      "loss": 0.8984,
      "step": 409
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019935211955633662,
      "loss": 0.9229,
      "step": 410
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019934624953102858,
      "loss": 0.8958,
      "step": 411
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993403531204656,
      "loss": 0.936,
      "step": 412
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019933443032621364,
      "loss": 0.9208,
      "step": 413
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019932848114984571,
      "loss": 0.9328,
      "step": 414
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019932250559294188,
      "loss": 0.9123,
      "step": 415
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993165036570892,
      "loss": 0.9183,
      "step": 416
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993104753438817,
      "loss": 0.9447,
      "step": 417
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019930442065492043,
      "loss": 0.9592,
      "step": 418
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019929833959181345,
      "loss": 0.9238,
      "step": 419
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019929223215617582,
      "loss": 0.9121,
      "step": 420
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019928609834962964,
      "loss": 0.9338,
      "step": 421
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019927993817380393,
      "loss": 0.8845,
      "step": 422
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019927375163033482,
      "loss": 0.8971,
      "step": 423
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001992675387208653,
      "loss": 0.9652,
      "step": 424
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019926129944704553,
      "loss": 0.9561,
      "step": 425
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019925503381053257,
      "loss": 0.9028,
      "step": 426
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019924874181299047,
      "loss": 0.919,
      "step": 427
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019924242345609037,
      "loss": 0.934,
      "step": 428
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019923607874151032,
      "loss": 0.9298,
      "step": 429
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019922970767093537,
      "loss": 0.9387,
      "step": 430
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001992233102460577,
      "loss": 0.9166,
      "step": 431
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019921688646857636,
      "loss": 0.9165,
      "step": 432
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019921043634019736,
      "loss": 0.9282,
      "step": 433
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019920395986263386,
      "loss": 0.9216,
      "step": 434
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019919745703760592,
      "loss": 0.9391,
      "step": 435
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001991909278668406,
      "loss": 0.8898,
      "step": 436
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000199184372352072,
      "loss": 0.9293,
      "step": 437
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001991777904950412,
      "loss": 0.8987,
      "step": 438
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019917118229749624,
      "loss": 0.9156,
      "step": 439
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019916454776119216,
      "loss": 0.9255,
      "step": 440
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019915788688789108,
      "loss": 0.9005,
      "step": 441
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019915119967936203,
      "loss": 0.9569,
      "step": 442
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.9639,
      "step": 443
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019913774626373118,
      "loss": 0.926,
      "step": 444
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019913098006020245,
      "loss": 0.9288,
      "step": 445
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019912418752859195,
      "loss": 0.9641,
      "step": 446
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001991173686707036,
      "loss": 0.9236,
      "step": 447
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019911052348834844,
      "loss": 0.9233,
      "step": 448
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019910365198334455,
      "loss": 0.9275,
      "step": 449
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019909675415751682,
      "loss": 0.901,
      "step": 450
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019908983001269733,
      "loss": 0.9307,
      "step": 451
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000199082879550725,
      "loss": 0.9167,
      "step": 452
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019907590277344582,
      "loss": 0.9168,
      "step": 453
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019906889968271271,
      "loss": 0.9395,
      "step": 454
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019906187028038562,
      "loss": 0.945,
      "step": 455
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019905481456833154,
      "loss": 0.9303,
      "step": 456
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001990477325484243,
      "loss": 0.9473,
      "step": 457
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019904062422254487,
      "loss": 0.9128,
      "step": 458
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019903348959258112,
      "loss": 0.9278,
      "step": 459
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001990263286604279,
      "loss": 0.8967,
      "step": 460
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019901914142798715,
      "loss": 0.8986,
      "step": 461
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019901192789716765,
      "loss": 0.8984,
      "step": 462
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019900468806988524,
      "loss": 0.931,
      "step": 463
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019899742194806277,
      "loss": 0.9176,
      "step": 464
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019899012953363001,
      "loss": 0.9233,
      "step": 465
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019898281082852373,
      "loss": 0.9237,
      "step": 466
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019897546583468777,
      "loss": 0.9218,
      "step": 467
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019896809455407285,
      "loss": 0.9358,
      "step": 468
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019896069698863663,
      "loss": 0.9117,
      "step": 469
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001989532731403439,
      "loss": 0.8921,
      "step": 470
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001989458230111663,
      "loss": 0.9008,
      "step": 471
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019893834660308254,
      "loss": 0.9255,
      "step": 472
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019893084391807824,
      "loss": 0.9345,
      "step": 473
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019892331495814606,
      "loss": 0.9173,
      "step": 474
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001989157597252856,
      "loss": 0.9338,
      "step": 475
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001989081782215034,
      "loss": 0.9087,
      "step": 476
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019890057044881306,
      "loss": 0.9103,
      "step": 477
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019889293640923517,
      "loss": 0.8825,
      "step": 478
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019888527610479714,
      "loss": 0.8725,
      "step": 479
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019887758953753356,
      "loss": 0.8922,
      "step": 480
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019886987670948583,
      "loss": 0.9028,
      "step": 481
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019886213762270244,
      "loss": 0.8783,
      "step": 482
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019885437227923876,
      "loss": 0.8964,
      "step": 483
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001988465806811572,
      "loss": 0.8865,
      "step": 484
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019883876283052708,
      "loss": 0.8922,
      "step": 485
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019883091872942483,
      "loss": 0.9529,
      "step": 486
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019882304837993368,
      "loss": 0.904,
      "step": 487
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019881515178414393,
      "loss": 0.8997,
      "step": 488
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019880722894415282,
      "loss": 0.8923,
      "step": 489
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019879927986206456,
      "loss": 0.9008,
      "step": 490
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019879130453999037,
      "loss": 0.9006,
      "step": 491
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019878330298004837,
      "loss": 0.9183,
      "step": 492
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001987752751843637,
      "loss": 0.9184,
      "step": 493
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019876722115506846,
      "loss": 0.9057,
      "step": 494
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001987591408943017,
      "loss": 0.9169,
      "step": 495
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019875103440420946,
      "loss": 0.9157,
      "step": 496
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001987429016869447,
      "loss": 0.9123,
      "step": 497
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019873474274466744,
      "loss": 0.916,
      "step": 498
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019872655757954456,
      "loss": 0.9067,
      "step": 499
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019871834619374993,
      "loss": 0.9115,
      "step": 500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001987101085894644,
      "loss": 0.9393,
      "step": 501
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019870184476887586,
      "loss": 0.9222,
      "step": 502
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019869355473417906,
      "loss": 0.9147,
      "step": 503
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986852384875757,
      "loss": 0.9062,
      "step": 504
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986768960312745,
      "loss": 0.8732,
      "step": 505
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986685273674911,
      "loss": 0.9141,
      "step": 506
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986601324984482,
      "loss": 0.9059,
      "step": 507
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986517114263753,
      "loss": 0.9223,
      "step": 508
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000198643264153509,
      "loss": 0.9223,
      "step": 509
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019863479068209277,
      "loss": 0.9086,
      "step": 510
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001986262910143771,
      "loss": 0.9325,
      "step": 511
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019861776515261935,
      "loss": 0.919,
      "step": 512
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019860921309908396,
      "loss": 0.8973,
      "step": 513
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019860063485604222,
      "loss": 0.8978,
      "step": 514
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001985920304257724,
      "loss": 0.9319,
      "step": 515
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019858339981055983,
      "loss": 0.9037,
      "step": 516
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001985747430126966,
      "loss": 0.9121,
      "step": 517
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019856606003448187,
      "loss": 0.8983,
      "step": 518
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019855735087822183,
      "loss": 0.92,
      "step": 519
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019854861554622944,
      "loss": 0.9338,
      "step": 520
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019853985404082476,
      "loss": 0.9113,
      "step": 521
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001985310663643347,
      "loss": 0.8659,
      "step": 522
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019852225251909325,
      "loss": 0.9064,
      "step": 523
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019851341250744117,
      "loss": 0.9421,
      "step": 524
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019850454633172631,
      "loss": 0.9188,
      "step": 525
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001984956539943035,
      "loss": 0.8988,
      "step": 526
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019848673549753435,
      "loss": 0.8982,
      "step": 527
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019847779084378753,
      "loss": 0.8932,
      "step": 528
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019846882003543868,
      "loss": 0.9142,
      "step": 529
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019845982307487028,
      "loss": 0.8837,
      "step": 530
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001984507999644719,
      "loss": 0.9447,
      "step": 531
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001984417507066399,
      "loss": 0.9332,
      "step": 532
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019843267530377773,
      "loss": 0.8947,
      "step": 533
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001984235737582957,
      "loss": 0.8993,
      "step": 534
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019841444607261103,
      "loss": 0.9027,
      "step": 535
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000198405292249148,
      "loss": 0.9388,
      "step": 536
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019839611229033772,
      "loss": 0.9053,
      "step": 537
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019838690619861828,
      "loss": 0.9347,
      "step": 538
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019837767397643474,
      "loss": 0.8999,
      "step": 539
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019836841562623908,
      "loss": 0.8926,
      "step": 540
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001983591311504902,
      "loss": 0.9303,
      "step": 541
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019834982055165395,
      "loss": 0.9315,
      "step": 542
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019834048383220312,
      "loss": 0.8911,
      "step": 543
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019833112099461742,
      "loss": 0.8919,
      "step": 544
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019832173204138357,
      "loss": 0.9098,
      "step": 545
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019831231697499516,
      "loss": 0.9241,
      "step": 546
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019830287579795266,
      "loss": 0.9093,
      "step": 547
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001982934085127636,
      "loss": 0.9058,
      "step": 548
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001982839151219424,
      "loss": 0.8951,
      "step": 549
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019827439562801033,
      "loss": 0.8868,
      "step": 550
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019826485003349574,
      "loss": 0.886,
      "step": 551
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019825527834093376,
      "loss": 0.86,
      "step": 552
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019824568055286658,
      "loss": 0.9246,
      "step": 553
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019823605667184326,
      "loss": 0.9196,
      "step": 554
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019822640670041976,
      "loss": 0.8891,
      "step": 555
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019821673064115904,
      "loss": 0.917,
      "step": 556
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001982070284966309,
      "loss": 0.9174,
      "step": 557
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001981973002694122,
      "loss": 0.9307,
      "step": 558
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001981875459620866,
      "loss": 0.9116,
      "step": 559
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019817776557724476,
      "loss": 0.9053,
      "step": 560
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019816795911748423,
      "loss": 0.8871,
      "step": 561
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019815812658540945,
      "loss": 0.9064,
      "step": 562
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001981482679836319,
      "loss": 0.969,
      "step": 563
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001981383833147699,
      "loss": 0.9239,
      "step": 564
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001981284725814487,
      "loss": 0.9349,
      "step": 565
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019811853578630042,
      "loss": 0.8823,
      "step": 566
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019810857293196428,
      "loss": 0.8884,
      "step": 567
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001980985840210862,
      "loss": 0.9338,
      "step": 568
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019808856905631917,
      "loss": 0.8774,
      "step": 569
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.9272,
      "step": 570
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019806846097576464,
      "loss": 0.9159,
      "step": 571
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019805836786531756,
      "loss": 0.9497,
      "step": 572
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019804824871166255,
      "loss": 0.8826,
      "step": 573
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019803810351748703,
      "loss": 0.9282,
      "step": 574
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019802793228548553,
      "loss": 0.9106,
      "step": 575
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001980177350183594,
      "loss": 0.9256,
      "step": 576
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019800751171881686,
      "loss": 0.8974,
      "step": 577
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019799726238957317,
      "loss": 0.9016,
      "step": 578
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019798698703335044,
      "loss": 0.9178,
      "step": 579
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019797668565287764,
      "loss": 0.9209,
      "step": 580
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019796635825089073,
      "loss": 0.9086,
      "step": 581
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019795600483013255,
      "loss": 0.8791,
      "step": 582
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001979456253933529,
      "loss": 0.9003,
      "step": 583
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019793521994330833,
      "loss": 0.8943,
      "step": 584
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001979247884827625,
      "loss": 0.9076,
      "step": 585
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019791433101448588,
      "loss": 0.9089,
      "step": 586
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019790384754125582,
      "loss": 0.8834,
      "step": 587
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001978933380658567,
      "loss": 0.8984,
      "step": 588
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019788280259107962,
      "loss": 0.8791,
      "step": 589
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019787224111972272,
      "loss": 0.9391,
      "step": 590
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000197861653654591,
      "loss": 0.9425,
      "step": 591
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019785104019849641,
      "loss": 0.9172,
      "step": 592
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001978404007542577,
      "loss": 0.8827,
      "step": 593
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019782973532470069,
      "loss": 0.8948,
      "step": 594
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001978190439126579,
      "loss": 0.8929,
      "step": 595
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019780832652096887,
      "loss": 0.8794,
      "step": 596
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019779758315248004,
      "loss": 0.8926,
      "step": 597
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019778681381004472,
      "loss": 0.9158,
      "step": 598
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019777601849652317,
      "loss": 0.8823,
      "step": 599
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019776519721478243,
      "loss": 0.9336,
      "step": 600
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019775434996769655,
      "loss": 0.8831,
      "step": 601
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019774347675814645,
      "loss": 0.8789,
      "step": 602
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019773257758901993,
      "loss": 0.8831,
      "step": 603
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019772165246321165,
      "loss": 0.9327,
      "step": 604
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019771070138362325,
      "loss": 0.9498,
      "step": 605
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019769972435316316,
      "loss": 0.9057,
      "step": 606
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001976887213747468,
      "loss": 0.9021,
      "step": 607
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019767769245129647,
      "loss": 0.8686,
      "step": 608
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019766663758574122,
      "loss": 0.9272,
      "step": 609
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001976555567810172,
      "loss": 0.8888,
      "step": 610
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001976444500400673,
      "loss": 0.9179,
      "step": 611
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019763331736584138,
      "loss": 0.8919,
      "step": 612
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019762215876129613,
      "loss": 0.884,
      "step": 613
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019761097422939513,
      "loss": 0.8947,
      "step": 614
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001975997637731089,
      "loss": 0.903,
      "step": 615
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019758852739541484,
      "loss": 0.8927,
      "step": 616
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019757726509929714,
      "loss": 0.9409,
      "step": 617
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019756597688774696,
      "loss": 0.8894,
      "step": 618
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019755466276376234,
      "loss": 0.8773,
      "step": 619
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001975433227303482,
      "loss": 0.9137,
      "step": 620
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019753195679051628,
      "loss": 0.9068,
      "step": 621
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001975205649472853,
      "loss": 0.9115,
      "step": 622
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019750914720368073,
      "loss": 0.8997,
      "step": 623
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019749770356273505,
      "loss": 0.8809,
      "step": 624
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019748623402748757,
      "loss": 0.9058,
      "step": 625
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019747473860098446,
      "loss": 0.8975,
      "step": 626
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001974632172862788,
      "loss": 0.8958,
      "step": 627
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019745167008643045,
      "loss": 0.8729,
      "step": 628
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019744009700450627,
      "loss": 0.9045,
      "step": 629
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019742849804357996,
      "loss": 0.8835,
      "step": 630
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019741687320673203,
      "loss": 0.9133,
      "step": 631
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019740522249704994,
      "loss": 0.8638,
      "step": 632
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019739354591762797,
      "loss": 0.8947,
      "step": 633
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001973818434715673,
      "loss": 0.8901,
      "step": 634
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019737011516197595,
      "loss": 0.8818,
      "step": 635
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019735836099196884,
      "loss": 0.8956,
      "step": 636
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019734658096466775,
      "loss": 0.9269,
      "step": 637
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001973347750832013,
      "loss": 0.9151,
      "step": 638
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019732294335070508,
      "loss": 0.9017,
      "step": 639
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019731108577032136,
      "loss": 0.8948,
      "step": 640
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019729920234519942,
      "loss": 0.9225,
      "step": 641
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019728729307849543,
      "loss": 0.8882,
      "step": 642
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019727535797337226,
      "loss": 0.8737,
      "step": 643
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019726339703299978,
      "loss": 0.8959,
      "step": 644
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001972514102605547,
      "loss": 0.8903,
      "step": 645
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019723939765922056,
      "loss": 0.8987,
      "step": 646
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019722735923218777,
      "loss": 0.9029,
      "step": 647
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019721529498265355,
      "loss": 0.8931,
      "step": 648
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019720320491382215,
      "loss": 0.8931,
      "step": 649
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019719108902890446,
      "loss": 0.926,
      "step": 650
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001971789473311184,
      "loss": 0.9045,
      "step": 651
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019716677982368856,
      "loss": 0.882,
      "step": 652
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019715458650984658,
      "loss": 0.8996,
      "step": 653
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019714236739283084,
      "loss": 0.9227,
      "step": 654
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019713012247588662,
      "loss": 0.8851,
      "step": 655
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019711785176226601,
      "loss": 0.8618,
      "step": 656
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000197105555255228,
      "loss": 0.9306,
      "step": 657
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019709323295803838,
      "loss": 0.8961,
      "step": 658
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001970808848739698,
      "loss": 0.8965,
      "step": 659
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019706851100630184,
      "loss": 0.9167,
      "step": 660
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001970561113583208,
      "loss": 0.8996,
      "step": 661
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001970436859333199,
      "loss": 0.8959,
      "step": 662
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019703123473459918,
      "loss": 0.8915,
      "step": 663
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001970187577654656,
      "loss": 0.8789,
      "step": 664
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019700625502923287,
      "loss": 0.8829,
      "step": 665
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001969937265292215,
      "loss": 0.8769,
      "step": 666
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019698117226875906,
      "loss": 0.8905,
      "step": 667
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019696859225117974,
      "loss": 0.8918,
      "step": 668
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019695598647982468,
      "loss": 0.9376,
      "step": 669
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019694335495804176,
      "loss": 0.8754,
      "step": 670
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019693069768918588,
      "loss": 0.8773,
      "step": 671
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019691801467661862,
      "loss": 0.8909,
      "step": 672
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001969053059237084,
      "loss": 0.8764,
      "step": 673
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968925714338306,
      "loss": 0.938,
      "step": 674
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968798112103673,
      "loss": 0.9016,
      "step": 675
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019686702525670752,
      "loss": 0.923,
      "step": 676
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019685421357624702,
      "loss": 0.8943,
      "step": 677
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968413761723885,
      "loss": 0.8937,
      "step": 678
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019682851304854136,
      "loss": 0.939,
      "step": 679
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019681562420812196,
      "loss": 0.906,
      "step": 680
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968027096545534,
      "loss": 0.8479,
      "step": 681
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019678976939126565,
      "loss": 0.914,
      "step": 682
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001967768034216955,
      "loss": 0.918,
      "step": 683
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019676381174928658,
      "loss": 0.8969,
      "step": 684
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019675079437748928,
      "loss": 0.9162,
      "step": 685
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019673775130976096,
      "loss": 0.9093,
      "step": 686
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019672468254956562,
      "loss": 0.9204,
      "step": 687
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019671158810037427,
      "loss": 0.9033,
      "step": 688
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019669846796566454,
      "loss": 0.8881,
      "step": 689
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019668532214892108,
      "loss": 0.8868,
      "step": 690
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019667215065363524,
      "loss": 0.9028,
      "step": 691
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001966589534833052,
      "loss": 0.9078,
      "step": 692
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019664573064143604,
      "loss": 0.8899,
      "step": 693
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019663248213153955,
      "loss": 0.8791,
      "step": 694
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019661920795713443,
      "loss": 0.8451,
      "step": 695
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019660590812174607,
      "loss": 0.8698,
      "step": 696
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.9196,
      "step": 697
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019657923148215582,
      "loss": 0.8937,
      "step": 698
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001965658546850389,
      "loss": 0.8766,
      "step": 699
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019655245224110883,
      "loss": 0.916,
      "step": 700
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019653902415392517,
      "loss": 0.9238,
      "step": 701
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001965255704270542,
      "loss": 0.8784,
      "step": 702
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019651209106406916,
      "loss": 0.883,
      "step": 703
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019649858606854997,
      "loss": 0.8874,
      "step": 704
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019648505544408345,
      "loss": 0.89,
      "step": 705
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001964714991942631,
      "loss": 0.9004,
      "step": 706
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019645791732268939,
      "loss": 0.8501,
      "step": 707
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001964443098329695,
      "loss": 0.8772,
      "step": 708
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001964306767287174,
      "loss": 0.8971,
      "step": 709
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019641701801355392,
      "loss": 0.9105,
      "step": 710
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019640333369110662,
      "loss": 0.9062,
      "step": 711
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019638962376500993,
      "loss": 0.898,
      "step": 712
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019637588823890508,
      "loss": 0.9197,
      "step": 713
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019636212711644002,
      "loss": 0.93,
      "step": 714
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019634834040126956,
      "loss": 0.882,
      "step": 715
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019633452809705534,
      "loss": 0.8571,
      "step": 716
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019632069020746572,
      "loss": 0.8882,
      "step": 717
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001963068267361759,
      "loss": 0.8891,
      "step": 718
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019629293768686786,
      "loss": 0.8971,
      "step": 719
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019627902306323036,
      "loss": 0.8954,
      "step": 720
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.000196265082868959,
      "loss": 0.9116,
      "step": 721
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001962511171077561,
      "loss": 0.9302,
      "step": 722
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019623712578333084,
      "loss": 0.8898,
      "step": 723
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019622310889939916,
      "loss": 0.9193,
      "step": 724
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001962090664596838,
      "loss": 0.9214,
      "step": 725
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019619499846791424,
      "loss": 0.862,
      "step": 726
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001961809049278268,
      "loss": 0.9022,
      "step": 727
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019616678584316458,
      "loss": 0.9251,
      "step": 728
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001961526412176774,
      "loss": 0.911,
      "step": 729
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019613847105512196,
      "loss": 0.9393,
      "step": 730
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019612427535926173,
      "loss": 0.9038,
      "step": 731
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019611005413386684,
      "loss": 0.9173,
      "step": 732
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019609580738271437,
      "loss": 0.9017,
      "step": 733
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019608153510958804,
      "loss": 0.9017,
      "step": 734
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019606723731827846,
      "loss": 0.9499,
      "step": 735
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001960529140125829,
      "loss": 1.0093,
      "step": 736
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019603856519630552,
      "loss": 0.9239,
      "step": 737
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001960241908732572,
      "loss": 0.9385,
      "step": 738
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019600979104725553,
      "loss": 0.9117,
      "step": 739
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019599536572212508,
      "loss": 0.9056,
      "step": 740
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019598091490169694,
      "loss": 0.8878,
      "step": 741
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001959664385898091,
      "loss": 0.9355,
      "step": 742
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001959519367903064,
      "loss": 0.929,
      "step": 743
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019593740950704023,
      "loss": 0.8823,
      "step": 744
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019592285674386895,
      "loss": 0.8937,
      "step": 745
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019590827850465758,
      "loss": 0.9129,
      "step": 746
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000195893674793278,
      "loss": 0.901,
      "step": 747
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001958790456136087,
      "loss": 0.9393,
      "step": 748
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019586439096953506,
      "loss": 0.8971,
      "step": 749
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001958497108649492,
      "loss": 0.8896,
      "step": 750
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019583500530375,
      "loss": 0.8907,
      "step": 751
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001958202742898431,
      "loss": 0.9205,
      "step": 752
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019580551782714088,
      "loss": 0.9392,
      "step": 753
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019579073591956248,
      "loss": 0.8894,
      "step": 754
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019577592857103381,
      "loss": 0.902,
      "step": 755
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019576109578548756,
      "loss": 0.8844,
      "step": 756
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019574623756686313,
      "loss": 0.9236,
      "step": 757
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001957313539191067,
      "loss": 0.8927,
      "step": 758
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019571644484617123,
      "loss": 0.8923,
      "step": 759
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019570151035201635,
      "loss": 0.8878,
      "step": 760
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019568655044060855,
      "loss": 0.8761,
      "step": 761
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019567156511592098,
      "loss": 0.8802,
      "step": 762
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019565655438193356,
      "loss": 0.8865,
      "step": 763
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000195641518242633,
      "loss": 0.8873,
      "step": 764
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019562645670201276,
      "loss": 0.897,
      "step": 765
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019561136976407298,
      "loss": 0.8832,
      "step": 766
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019559625743282056,
      "loss": 0.9067,
      "step": 767
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019558111971226921,
      "loss": 0.8937,
      "step": 768
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019556595660643935,
      "loss": 0.8959,
      "step": 769
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019555076811935806,
      "loss": 0.8629,
      "step": 770
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019553555425505932,
      "loss": 0.9202,
      "step": 771
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001955203150175837,
      "loss": 0.8742,
      "step": 772
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001955050504109786,
      "loss": 0.8989,
      "step": 773
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001954897604392981,
      "loss": 0.8788,
      "step": 774
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019547444510660308,
      "loss": 0.8795,
      "step": 775
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019545910441696112,
      "loss": 0.9033,
      "step": 776
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019544373837444652,
      "loss": 0.9497,
      "step": 777
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001954283469831403,
      "loss": 0.8831,
      "step": 778
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001954129302471303,
      "loss": 0.9139,
      "step": 779
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019539748817051105,
      "loss": 0.9554,
      "step": 780
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019538202075738373,
      "loss": 0.8618,
      "step": 781
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001953665280118563,
      "loss": 0.891,
      "step": 782
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019535100993804352,
      "loss": 0.9201,
      "step": 783
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001953354665400668,
      "loss": 0.8818,
      "step": 784
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019531989782205426,
      "loss": 0.8931,
      "step": 785
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001953043037881408,
      "loss": 0.882,
      "step": 786
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019528868444246804,
      "loss": 0.8935,
      "step": 787
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001952730397891843,
      "loss": 0.8996,
      "step": 788
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001952573698324446,
      "loss": 0.9049,
      "step": 789
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001952416745764107,
      "loss": 0.8948,
      "step": 790
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019522595402525112,
      "loss": 0.8929,
      "step": 791
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019521020818314105,
      "loss": 0.8924,
      "step": 792
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001951944370542624,
      "loss": 0.8874,
      "step": 793
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019517864064280381,
      "loss": 0.8955,
      "step": 794
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019516281895296062,
      "loss": 0.8729,
      "step": 795
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019514697198893494,
      "loss": 0.9015,
      "step": 796
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001951310997549355,
      "loss": 0.9173,
      "step": 797
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001951152022551778,
      "loss": 0.8898,
      "step": 798
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019509927949388405,
      "loss": 0.8681,
      "step": 799
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019508333147528312,
      "loss": 0.9512,
      "step": 800
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019506735820361067,
      "loss": 0.8867,
      "step": 801
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000195051359683109,
      "loss": 0.8909,
      "step": 802
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019503533591802715,
      "loss": 0.8984,
      "step": 803
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019501928691262086,
      "loss": 0.9011,
      "step": 804
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019500321267115254,
      "loss": 0.8805,
      "step": 805
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019498711319789136,
      "loss": 0.9099,
      "step": 806
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019497098849711311,
      "loss": 0.9121,
      "step": 807
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019495483857310037,
      "loss": 0.891,
      "step": 808
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001949386634301424,
      "loss": 0.896,
      "step": 809
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001949224630725351,
      "loss": 0.8754,
      "step": 810
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001949062375045811,
      "loss": 0.9244,
      "step": 811
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019488998673058977,
      "loss": 0.8839,
      "step": 812
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019487371075487713,
      "loss": 0.9072,
      "step": 813
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019485740958176585,
      "loss": 0.8941,
      "step": 814
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019484108321558537,
      "loss": 0.9109,
      "step": 815
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019482473166067176,
      "loss": 0.8537,
      "step": 816
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019480835492136786,
      "loss": 0.8729,
      "step": 817
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019479195300202315,
      "loss": 0.8675,
      "step": 818
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019477552590699374,
      "loss": 0.9344,
      "step": 819
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019475907364064252,
      "loss": 0.8982,
      "step": 820
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019474259620733903,
      "loss": 0.875,
      "step": 821
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001947260936114595,
      "loss": 0.913,
      "step": 822
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019470956585738682,
      "loss": 0.875,
      "step": 823
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.9159,
      "step": 824
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000194676434892227,
      "loss": 0.8925,
      "step": 825
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019465983168993916,
      "loss": 0.9315,
      "step": 826
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019464320334705655,
      "loss": 0.9071,
      "step": 827
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001946265498679955,
      "loss": 0.8779,
      "step": 828
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019460987125717905,
      "loss": 0.8489,
      "step": 829
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001945931675190368,
      "loss": 0.8831,
      "step": 830
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001945764386580051,
      "loss": 0.9187,
      "step": 831
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019455968467852692,
      "loss": 0.9047,
      "step": 832
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019454290558505198,
      "loss": 0.8473,
      "step": 833
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019452610138203654,
      "loss": 0.9181,
      "step": 834
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001945092720739437,
      "loss": 0.9053,
      "step": 835
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019449241766524304,
      "loss": 0.9004,
      "step": 836
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000194475538160411,
      "loss": 0.8506,
      "step": 837
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019445863356393054,
      "loss": 0.8819,
      "step": 838
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019444170388029132,
      "loss": 0.8645,
      "step": 839
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001944247491139897,
      "loss": 0.9118,
      "step": 840
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019440776926952865,
      "loss": 0.8472,
      "step": 841
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019439076435141787,
      "loss": 0.885,
      "step": 842
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019437373436417366,
      "loss": 0.8739,
      "step": 843
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019435667931231896,
      "loss": 0.8671,
      "step": 844
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019433959920038345,
      "loss": 0.8972,
      "step": 845
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019432249403290337,
      "loss": 0.867,
      "step": 846
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001943053638144217,
      "loss": 0.8445,
      "step": 847
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019428820854948802,
      "loss": 0.8965,
      "step": 848
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019427102824265858,
      "loss": 0.899,
      "step": 849
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019425382289849625,
      "loss": 0.8967,
      "step": 850
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019423659252157066,
      "loss": 0.8926,
      "step": 851
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019421933711645788,
      "loss": 0.8844,
      "step": 852
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019420205668774085,
      "loss": 0.9035,
      "step": 853
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019418475124000905,
      "loss": 0.8881,
      "step": 854
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001941674207778586,
      "loss": 0.9141,
      "step": 855
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001941500653058922,
      "loss": 0.869,
      "step": 856
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001941326848287194,
      "loss": 0.8797,
      "step": 857
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019411527935095618,
      "loss": 0.8881,
      "step": 858
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001940978488772253,
      "loss": 0.9079,
      "step": 859
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019408039341215605,
      "loss": 0.9034,
      "step": 860
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001940629129603844,
      "loss": 0.9038,
      "step": 861
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019404540752655298,
      "loss": 0.9137,
      "step": 862
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019402787711531106,
      "loss": 0.8985,
      "step": 863
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001940103217313145,
      "loss": 0.8804,
      "step": 864
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001939927413792258,
      "loss": 0.8999,
      "step": 865
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001939751360637141,
      "loss": 0.9423,
      "step": 866
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001939575057894552,
      "loss": 0.8603,
      "step": 867
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019393985056113152,
      "loss": 0.8746,
      "step": 868
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001939221703834321,
      "loss": 0.8547,
      "step": 869
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019390446526105254,
      "loss": 0.8834,
      "step": 870
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019388673519869513,
      "loss": 0.907,
      "step": 871
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019386898020106884,
      "loss": 0.8691,
      "step": 872
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019385120027288913,
      "loss": 0.9034,
      "step": 873
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019383339541887814,
      "loss": 0.8919,
      "step": 874
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019381556564376475,
      "loss": 0.9049,
      "step": 875
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019379771095228424,
      "loss": 0.9334,
      "step": 876
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019377983134917867,
      "loss": 0.9028,
      "step": 877
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019376192683919662,
      "loss": 0.92,
      "step": 878
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019374399742709338,
      "loss": 0.8898,
      "step": 879
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019372604311763077,
      "loss": 0.9011,
      "step": 880
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019370806391557727,
      "loss": 0.8797,
      "step": 881
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019369005982570797,
      "loss": 0.8733,
      "step": 882
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001936720308528045,
      "loss": 0.9034,
      "step": 883
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019365397700165518,
      "loss": 0.897,
      "step": 884
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019363589827705492,
      "loss": 0.9058,
      "step": 885
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019361779468380526,
      "loss": 0.9107,
      "step": 886
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019359966622671423,
      "loss": 0.9218,
      "step": 887
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019358151291059663,
      "loss": 0.8558,
      "step": 888
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001935633347402737,
      "loss": 0.8641,
      "step": 889
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019354513172057346,
      "loss": 0.9042,
      "step": 890
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019352690385633032,
      "loss": 0.855,
      "step": 891
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019350865115238546,
      "loss": 0.8841,
      "step": 892
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001934903736135866,
      "loss": 0.8991,
      "step": 893
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000193472071244788,
      "loss": 0.8779,
      "step": 894
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019345374405085061,
      "loss": 0.865,
      "step": 895
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001934353920366419,
      "loss": 0.9172,
      "step": 896
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000193417015207036,
      "loss": 0.9081,
      "step": 897
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019339861356691357,
      "loss": 0.8933,
      "step": 898
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019338018712116185,
      "loss": 0.8952,
      "step": 899
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019336173587467475,
      "loss": 0.882,
      "step": 900
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019334325983235266,
      "loss": 0.9042,
      "step": 901
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019332475899910264,
      "loss": 0.8886,
      "step": 902
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019330623337983832,
      "loss": 0.8786,
      "step": 903
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001932876829794799,
      "loss": 0.9125,
      "step": 904
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001932691078029541,
      "loss": 0.9149,
      "step": 905
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019325050785519438,
      "loss": 0.8493,
      "step": 906
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019323188314114055,
      "loss": 0.8999,
      "step": 907
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019321323366573923,
      "loss": 0.8916,
      "step": 908
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019319455943394347,
      "loss": 0.8929,
      "step": 909
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019317586045071295,
      "loss": 0.8716,
      "step": 910
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019315713672101389,
      "loss": 0.8829,
      "step": 911
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019313838824981913,
      "loss": 0.8847,
      "step": 912
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019311961504210807,
      "loss": 0.9148,
      "step": 913
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019310081710286663,
      "loss": 0.8888,
      "step": 914
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001930819944370873,
      "loss": 0.8904,
      "step": 915
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001930631470497693,
      "loss": 0.8712,
      "step": 916
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019304427494591813,
      "loss": 0.8833,
      "step": 917
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001930253781305461,
      "loss": 0.8896,
      "step": 918
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019300645660867195,
      "loss": 0.9067,
      "step": 919
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019298751038532107,
      "loss": 0.8625,
      "step": 920
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019296853946552532,
      "loss": 0.8655,
      "step": 921
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001929495438543232,
      "loss": 0.8823,
      "step": 922
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019293052355675972,
      "loss": 0.9188,
      "step": 923
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019291147857788645,
      "loss": 0.8871,
      "step": 924
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019289240892276155,
      "loss": 0.8966,
      "step": 925
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019287331459644965,
      "loss": 0.924,
      "step": 926
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019285419560402208,
      "loss": 0.928,
      "step": 927
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019283505195055652,
      "loss": 0.9074,
      "step": 928
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019281588364113744,
      "loss": 0.8876,
      "step": 929
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001927966906808556,
      "loss": 0.9345,
      "step": 930
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001927774730748085,
      "loss": 0.8543,
      "step": 931
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019275823082810016,
      "loss": 0.8923,
      "step": 932
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019273896394584103,
      "loss": 0.9203,
      "step": 933
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019271967243314822,
      "loss": 0.9123,
      "step": 934
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019270035629514535,
      "loss": 0.8815,
      "step": 935
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019268101553696255,
      "loss": 0.881,
      "step": 936
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019266165016373646,
      "loss": 0.8966,
      "step": 937
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019264226018061043,
      "loss": 0.9259,
      "step": 938
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001926228455927341,
      "loss": 0.8909,
      "step": 939
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019260340640526384,
      "loss": 0.8797,
      "step": 940
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019258394262336247,
      "loss": 0.8966,
      "step": 941
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019256445425219933,
      "loss": 0.8767,
      "step": 942
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019254494129695036,
      "loss": 0.8675,
      "step": 943
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019252540376279794,
      "loss": 0.8846,
      "step": 944
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000192505841654931,
      "loss": 0.8827,
      "step": 945
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019248625497854507,
      "loss": 0.8862,
      "step": 946
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019246664373884212,
      "loss": 0.8766,
      "step": 947
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019244700794103072,
      "loss": 0.8631,
      "step": 948
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019242734759032589,
      "loss": 0.8683,
      "step": 949
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019240766269194916,
      "loss": 0.8907,
      "step": 950
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.9023,
      "step": 951
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019236821927309903,
      "loss": 0.8783,
      "step": 952
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019234846076310135,
      "loss": 0.8917,
      "step": 953
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019232867772638325,
      "loss": 0.917,
      "step": 954
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019230887016819892,
      "loss": 0.921,
      "step": 955
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000192289038093809,
      "loss": 0.8745,
      "step": 956
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019226918150848068,
      "loss": 0.9018,
      "step": 957
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019224930041748762,
      "loss": 0.8933,
      "step": 958
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019222939482611007,
      "loss": 0.8739,
      "step": 959
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001922094647396347,
      "loss": 0.8784,
      "step": 960
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001921895101633547,
      "loss": 0.8689,
      "step": 961
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019216953110256984,
      "loss": 0.8655,
      "step": 962
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019214952756258627,
      "loss": 0.8908,
      "step": 963
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019212949954871674,
      "loss": 0.8811,
      "step": 964
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019210944706628047,
      "loss": 0.9038,
      "step": 965
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019208937012060316,
      "loss": 0.8695,
      "step": 966
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019206926871701704,
      "loss": 0.9029,
      "step": 967
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001920491428608608,
      "loss": 0.9006,
      "step": 968
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019202899255747966,
      "loss": 0.8762,
      "step": 969
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001920088178122253,
      "loss": 0.8842,
      "step": 970
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019198861863045595,
      "loss": 0.8731,
      "step": 971
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001919683950175362,
      "loss": 0.8871,
      "step": 972
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001919481469788373,
      "loss": 0.9122,
      "step": 973
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019192787451973687,
      "loss": 0.8962,
      "step": 974
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019190757764561903,
      "loss": 0.8949,
      "step": 975
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019188725636187442,
      "loss": 0.8761,
      "step": 976
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019186691067390018,
      "loss": 0.876,
      "step": 977
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019184654058709984,
      "loss": 0.8813,
      "step": 978
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019182614610688354,
      "loss": 0.8803,
      "step": 979
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019180572723866775,
      "loss": 0.8915,
      "step": 980
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019178528398787551,
      "loss": 0.8406,
      "step": 981
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019176481635993636,
      "loss": 0.9064,
      "step": 982
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019174432436028626,
      "loss": 0.9016,
      "step": 983
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001917238079943676,
      "loss": 0.8927,
      "step": 984
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019170326726762935,
      "loss": 0.8861,
      "step": 985
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001916827021855269,
      "loss": 0.8719,
      "step": 986
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019166211275352212,
      "loss": 0.8903,
      "step": 987
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019164149897708325,
      "loss": 0.9004,
      "step": 988
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019162086086168517,
      "loss": 0.8616,
      "step": 989
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019160019841280913,
      "loss": 0.8793,
      "step": 990
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019157951163594278,
      "loss": 0.8737,
      "step": 991
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019155880053658034,
      "loss": 0.9119,
      "step": 992
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019153806512022244,
      "loss": 0.8803,
      "step": 993
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019151730539237623,
      "loss": 0.8643,
      "step": 994
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019149652135855513,
      "loss": 0.8614,
      "step": 995
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019147571302427927,
      "loss": 0.8685,
      "step": 996
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019145488039507504,
      "loss": 0.9011,
      "step": 997
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001914340234764754,
      "loss": 0.8818,
      "step": 998
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001914131422740197,
      "loss": 0.8765,
      "step": 999
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019139223679325373,
      "loss": 0.8273,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001913713070397298,
      "loss": 0.8786,
      "step": 1001
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019135035301900654,
      "loss": 0.896,
      "step": 1002
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001913293747366492,
      "loss": 0.9027,
      "step": 1003
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001913083721982293,
      "loss": 0.9089,
      "step": 1004
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019128734540932495,
      "loss": 0.8776,
      "step": 1005
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019126629437552056,
      "loss": 0.8929,
      "step": 1006
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001912452191024071,
      "loss": 0.8607,
      "step": 1007
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001912241195955819,
      "loss": 0.9042,
      "step": 1008
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019120299586064876,
      "loss": 0.8522,
      "step": 1009
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019118184790321792,
      "loss": 0.8821,
      "step": 1010
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019116067572890602,
      "loss": 0.883,
      "step": 1011
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019113947934333618,
      "loss": 0.8695,
      "step": 1012
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001911182587521379,
      "loss": 0.8934,
      "step": 1013
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019109701396094713,
      "loss": 0.9036,
      "step": 1014
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001910757449754063,
      "loss": 0.8916,
      "step": 1015
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019105445180116415,
      "loss": 0.8582,
      "step": 1016
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019103313444387594,
      "loss": 0.9079,
      "step": 1017
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019101179290920332,
      "loss": 0.8824,
      "step": 1018
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019099042720281437,
      "loss": 0.9292,
      "step": 1019
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019096903733038353,
      "loss": 0.9327,
      "step": 1020
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001909476232975918,
      "loss": 0.8662,
      "step": 1021
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019092618511012645,
      "loss": 0.896,
      "step": 1022
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019090472277368122,
      "loss": 0.8463,
      "step": 1023
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019088323629395633,
      "loss": 0.9058,
      "step": 1024
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019086172567665826,
      "loss": 0.9044,
      "step": 1025
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019084019092750006,
      "loss": 0.8469,
      "step": 1026
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019081863205220107,
      "loss": 0.9138,
      "step": 1027
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019079704905648713,
      "loss": 0.8832,
      "step": 1028
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019077544194609042,
      "loss": 0.8754,
      "step": 1029
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001907538107267495,
      "loss": 0.8701,
      "step": 1030
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019073215540420948,
      "loss": 0.8746,
      "step": 1031
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001907104759842217,
      "loss": 0.8527,
      "step": 1032
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000190688772472544,
      "loss": 0.8962,
      "step": 1033
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001906670448749406,
      "loss": 0.876,
      "step": 1034
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019064529319718206,
      "loss": 0.8801,
      "step": 1035
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019062351744504542,
      "loss": 0.8884,
      "step": 1036
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001906017176243141,
      "loss": 0.865,
      "step": 1037
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019057989374077783,
      "loss": 0.9122,
      "step": 1038
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019055804580023282,
      "loss": 0.8536,
      "step": 1039
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019053617380848165,
      "loss": 0.889,
      "step": 1040
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019051427777133325,
      "loss": 0.8769,
      "step": 1041
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019049235769460297,
      "loss": 0.9193,
      "step": 1042
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019047041358411258,
      "loss": 0.8999,
      "step": 1043
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019044844544569017,
      "loss": 0.8818,
      "step": 1044
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019042645328517016,
      "loss": 0.884,
      "step": 1045
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001904044371083935,
      "loss": 0.8608,
      "step": 1046
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019038239692120747,
      "loss": 0.8443,
      "step": 1047
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001903603327294656,
      "loss": 0.8523,
      "step": 1048
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019033824453902796,
      "loss": 0.9051,
      "step": 1049
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019031613235576093,
      "loss": 0.8656,
      "step": 1050
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001902939961855372,
      "loss": 0.9002,
      "step": 1051
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019027183603423592,
      "loss": 0.8997,
      "step": 1052
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019024965190774263,
      "loss": 0.892,
      "step": 1053
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001902274438119491,
      "loss": 0.8589,
      "step": 1054
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019020521175275366,
      "loss": 0.884,
      "step": 1055
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001901829557360608,
      "loss": 0.8735,
      "step": 1056
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001901606757677815,
      "loss": 0.8766,
      "step": 1057
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001901383718538331,
      "loss": 0.9036,
      "step": 1058
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001901160440001392,
      "loss": 0.8978,
      "step": 1059
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019009369221262986,
      "loss": 0.8826,
      "step": 1060
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019007131649724152,
      "loss": 0.8798,
      "step": 1061
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019004891685991688,
      "loss": 0.8862,
      "step": 1062
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019002649330660502,
      "loss": 0.8833,
      "step": 1063
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001900040458432614,
      "loss": 0.889,
      "step": 1064
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001899815744758478,
      "loss": 0.8669,
      "step": 1065
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018995907921033237,
      "loss": 0.8844,
      "step": 1066
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018993656005268964,
      "loss": 0.8695,
      "step": 1067
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001899140170089004,
      "loss": 0.8785,
      "step": 1068
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018989145008495187,
      "loss": 0.911,
      "step": 1069
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018986885928683753,
      "loss": 0.8841,
      "step": 1070
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018984624462055723,
      "loss": 0.9093,
      "step": 1071
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018982360609211727,
      "loss": 0.8631,
      "step": 1072
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001898009437075301,
      "loss": 0.8479,
      "step": 1073
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018977825747281465,
      "loss": 0.8516,
      "step": 1074
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018975554739399605,
      "loss": 0.8779,
      "step": 1075
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018973281347710593,
      "loss": 0.8643,
      "step": 1076
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018971005572818213,
      "loss": 0.8788,
      "step": 1077
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.874,
      "step": 1078
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018966446875841664,
      "loss": 0.873,
      "step": 1079
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018964163954968233,
      "loss": 0.884,
      "step": 1080
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001896187865331291,
      "loss": 0.8999,
      "step": 1081
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018959590971482653,
      "loss": 0.874,
      "step": 1082
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018957300910085037,
      "loss": 0.8733,
      "step": 1083
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018955008469728277,
      "loss": 0.8873,
      "step": 1084
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018952713651021225,
      "loss": 0.9041,
      "step": 1085
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018950416454573352,
      "loss": 0.8825,
      "step": 1086
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018948116880994776,
      "loss": 0.8662,
      "step": 1087
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018945814930896232,
      "loss": 0.8781,
      "step": 1088
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018943510604889095,
      "loss": 0.8682,
      "step": 1089
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018941203903585362,
      "loss": 0.8929,
      "step": 1090
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001893889482759768,
      "loss": 0.9023,
      "step": 1091
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000189365833775393,
      "loss": 0.8838,
      "step": 1092
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018934269554024126,
      "loss": 0.9025,
      "step": 1093
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018931953357666684,
      "loss": 0.911,
      "step": 1094
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018929634789082122,
      "loss": 0.9049,
      "step": 1095
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018927313848886233,
      "loss": 0.8785,
      "step": 1096
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018924990537695432,
      "loss": 0.8518,
      "step": 1097
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018922664856126762,
      "loss": 0.8768,
      "step": 1098
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000189203368047979,
      "loss": 0.8932,
      "step": 1099
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001891800638432715,
      "loss": 0.8832,
      "step": 1100
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018915673595333444,
      "loss": 0.8732,
      "step": 1101
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018913338438436347,
      "loss": 0.8698,
      "step": 1102
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018911000914256053,
      "loss": 0.9094,
      "step": 1103
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018908661023413377,
      "loss": 0.8719,
      "step": 1104
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001890631876652977,
      "loss": 0.8763,
      "step": 1105
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018903974144227306,
      "loss": 0.8741,
      "step": 1106
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018901627157128696,
      "loss": 0.8819,
      "step": 1107
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018899277805857275,
      "loss": 0.8656,
      "step": 1108
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018896926091036998,
      "loss": 0.8688,
      "step": 1109
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018894572013292458,
      "loss": 0.8732,
      "step": 1110
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018892215573248868,
      "loss": 0.875,
      "step": 1111
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001888985677153208,
      "loss": 0.868,
      "step": 1112
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018887495608768557,
      "loss": 0.9111,
      "step": 1113
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000188851320855854,
      "loss": 0.9269,
      "step": 1114
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001888276620261034,
      "loss": 0.8567,
      "step": 1115
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018880397960471722,
      "loss": 0.8944,
      "step": 1116
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018878027359798524,
      "loss": 0.8779,
      "step": 1117
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001887565440122036,
      "loss": 0.884,
      "step": 1118
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018873279085367454,
      "loss": 0.8967,
      "step": 1119
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018870901412870663,
      "loss": 0.8867,
      "step": 1120
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018868521384361473,
      "loss": 0.9009,
      "step": 1121
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001886613900047199,
      "loss": 0.8709,
      "step": 1122
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018863754261834955,
      "loss": 0.8764,
      "step": 1123
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001886136716908372,
      "loss": 0.9106,
      "step": 1124
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018858977722852275,
      "loss": 0.9042,
      "step": 1125
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001885658592377523,
      "loss": 0.8911,
      "step": 1126
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018854191772487816,
      "loss": 0.8822,
      "step": 1127
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000188517952696259,
      "loss": 0.8858,
      "step": 1128
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001884939641582596,
      "loss": 0.851,
      "step": 1129
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018846995211725112,
      "loss": 0.9148,
      "step": 1130
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018844591657961082,
      "loss": 0.8559,
      "step": 1131
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018842185755172226,
      "loss": 0.9086,
      "step": 1132
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018839777503997535,
      "loss": 0.8886,
      "step": 1133
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000188373669050766,
      "loss": 0.8927,
      "step": 1134
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001883495395904966,
      "loss": 0.8835,
      "step": 1135
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001883253866655756,
      "loss": 0.8854,
      "step": 1136
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001883012102824178,
      "loss": 0.8983,
      "step": 1137
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018827701044744414,
      "loss": 0.8625,
      "step": 1138
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018825278716708184,
      "loss": 0.8908,
      "step": 1139
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018822854044776434,
      "loss": 0.8371,
      "step": 1140
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018820427029593128,
      "loss": 0.8743,
      "step": 1141
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018817997671802857,
      "loss": 0.867,
      "step": 1142
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018815565972050825,
      "loss": 0.8848,
      "step": 1143
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018813131930982873,
      "loss": 0.886,
      "step": 1144
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018810695549245448,
      "loss": 0.9098,
      "step": 1145
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001880825682748563,
      "loss": 0.8892,
      "step": 1146
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001880581576635111,
      "loss": 0.8769,
      "step": 1147
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018803372366490217,
      "loss": 0.8638,
      "step": 1148
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018800926628551886,
      "loss": 0.8834,
      "step": 1149
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018798478553185675,
      "loss": 0.8606,
      "step": 1150
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018796028141041763,
      "loss": 0.896,
      "step": 1151
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018793575392770962,
      "loss": 0.871,
      "step": 1152
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018791120309024687,
      "loss": 0.8948,
      "step": 1153
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001878866289045498,
      "loss": 0.8747,
      "step": 1154
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018786203137714514,
      "loss": 0.8714,
      "step": 1155
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018783741051456562,
      "loss": 0.8597,
      "step": 1156
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018781276632335025,
      "loss": 0.8851,
      "step": 1157
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018778809881004433,
      "loss": 0.8748,
      "step": 1158
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018776340798119922,
      "loss": 0.8798,
      "step": 1159
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001877386938433726,
      "loss": 0.8812,
      "step": 1160
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018771395640312819,
      "loss": 0.8742,
      "step": 1161
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000187689195667036,
      "loss": 0.8781,
      "step": 1162
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018766441164167218,
      "loss": 0.8893,
      "step": 1163
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018763960433361917,
      "loss": 0.8834,
      "step": 1164
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018761477374946544,
      "loss": 0.8769,
      "step": 1165
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018758991989580576,
      "loss": 0.8489,
      "step": 1166
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018756504277924103,
      "loss": 0.876,
      "step": 1167
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001875401424063783,
      "loss": 0.8867,
      "step": 1168
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018751521878383086,
      "loss": 0.8664,
      "step": 1169
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018749027191821815,
      "loss": 0.8569,
      "step": 1170
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018746530181616578,
      "loss": 0.9198,
      "step": 1171
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001874403084843055,
      "loss": 0.8624,
      "step": 1172
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018741529192927526,
      "loss": 0.8609,
      "step": 1173
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018739025215771924,
      "loss": 0.8575,
      "step": 1174
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018736518917628766,
      "loss": 0.8733,
      "step": 1175
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000187340102991637,
      "loss": 0.8725,
      "step": 1176
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018731499361042983,
      "loss": 0.8686,
      "step": 1177
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018728986103933498,
      "loss": 0.8978,
      "step": 1178
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018726470528502738,
      "loss": 0.8683,
      "step": 1179
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018723952635418803,
      "loss": 0.8698,
      "step": 1180
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018721432425350428,
      "loss": 0.8898,
      "step": 1181
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018718909898966945,
      "loss": 0.8648,
      "step": 1182
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018716385056938314,
      "loss": 0.8601,
      "step": 1183
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018713857899935098,
      "loss": 0.8726,
      "step": 1184
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001871132842862849,
      "loss": 0.8612,
      "step": 1185
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018708796643690284,
      "loss": 0.8894,
      "step": 1186
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018706262545792898,
      "loss": 0.8564,
      "step": 1187
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018703726135609356,
      "loss": 0.8687,
      "step": 1188
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018701187413813303,
      "loss": 0.8973,
      "step": 1189
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018698646381078992,
      "loss": 0.9037,
      "step": 1190
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018696103038081297,
      "loss": 0.8903,
      "step": 1191
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018693557385495696,
      "loss": 0.8844,
      "step": 1192
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018691009423998293,
      "loss": 0.8778,
      "step": 1193
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018688459154265794,
      "loss": 0.8452,
      "step": 1194
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018685906576975522,
      "loss": 0.8981,
      "step": 1195
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018683351692805412,
      "loss": 0.8645,
      "step": 1196
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018680794502434018,
      "loss": 0.8887,
      "step": 1197
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018678235006540497,
      "loss": 0.9185,
      "step": 1198
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001867567320580462,
      "loss": 0.8881,
      "step": 1199
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018673109100906778,
      "loss": 0.8777,
      "step": 1200
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018670542692527967,
      "loss": 0.8869,
      "step": 1201
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018667973981349796,
      "loss": 0.9079,
      "step": 1202
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018665402968054485,
      "loss": 0.8827,
      "step": 1203
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018662829653324868,
      "loss": 0.894,
      "step": 1204
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8422,
      "step": 1205
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018657676122297098,
      "loss": 0.8842,
      "step": 1206
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018655095907367669,
      "loss": 0.8801,
      "step": 1207
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001865251339374137,
      "loss": 0.8736,
      "step": 1208
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018649928582104095,
      "loss": 0.8994,
      "step": 1209
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018647341473142335,
      "loss": 0.8845,
      "step": 1210
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000186447520675432,
      "loss": 0.9085,
      "step": 1211
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001864216036599441,
      "loss": 0.8788,
      "step": 1212
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018639566369184284,
      "loss": 0.8784,
      "step": 1213
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018636970077801768,
      "loss": 0.8956,
      "step": 1214
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000186343714925364,
      "loss": 0.8499,
      "step": 1215
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018631770614078338,
      "loss": 0.8426,
      "step": 1216
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001862916744311835,
      "loss": 0.866,
      "step": 1217
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001862656198034781,
      "loss": 0.8503,
      "step": 1218
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018623954226458693,
      "loss": 0.8684,
      "step": 1219
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001862134418214359,
      "loss": 0.8891,
      "step": 1220
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018618731848095706,
      "loss": 0.8446,
      "step": 1221
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001861611722500884,
      "loss": 0.8626,
      "step": 1222
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018613500313577412,
      "loss": 0.8687,
      "step": 1223
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018610881114496444,
      "loss": 0.8741,
      "step": 1224
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018608259628461566,
      "loss": 0.8517,
      "step": 1225
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018605635856169011,
      "loss": 0.8627,
      "step": 1226
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018603009798315632,
      "loss": 0.858,
      "step": 1227
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018600381455598875,
      "loss": 0.8619,
      "step": 1228
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018597750828716798,
      "loss": 0.8696,
      "step": 1229
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018595117918368068,
      "loss": 0.8483,
      "step": 1230
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018592482725251954,
      "loss": 0.9078,
      "step": 1231
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018589845250068337,
      "loss": 0.876,
      "step": 1232
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000185872054935177,
      "loss": 0.8713,
      "step": 1233
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018584563456301134,
      "loss": 0.8882,
      "step": 1234
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001858191913912033,
      "loss": 0.8877,
      "step": 1235
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018579272542677597,
      "loss": 0.9031,
      "step": 1236
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018576623667675835,
      "loss": 0.8569,
      "step": 1237
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001857397251481856,
      "loss": 0.8733,
      "step": 1238
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018571319084809883,
      "loss": 0.8797,
      "step": 1239
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018568663378354527,
      "loss": 0.9341,
      "step": 1240
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018566005396157824,
      "loss": 0.8346,
      "step": 1241
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000185633451389257,
      "loss": 0.8477,
      "step": 1242
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018560682607364685,
      "loss": 0.8745,
      "step": 1243
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018558017802181923,
      "loss": 0.8434,
      "step": 1244
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018555350724085162,
      "loss": 0.8931,
      "step": 1245
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018552681373782738,
      "loss": 0.8892,
      "step": 1246
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018550009751983605,
      "loss": 0.8726,
      "step": 1247
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018547335859397314,
      "loss": 0.8661,
      "step": 1248
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018544659696734022,
      "loss": 0.8902,
      "step": 1249
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001854198126470449,
      "loss": 0.9011,
      "step": 1250
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018539300564020082,
      "loss": 0.9021,
      "step": 1251
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018536617595392752,
      "loss": 0.8941,
      "step": 1252
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018533932359535076,
      "loss": 0.9058,
      "step": 1253
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001853124485716022,
      "loss": 0.9112,
      "step": 1254
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018528555088981953,
      "loss": 0.8929,
      "step": 1255
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001852586305571465,
      "loss": 0.8583,
      "step": 1256
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001852316875807328,
      "loss": 0.8997,
      "step": 1257
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018520472196773425,
      "loss": 0.8736,
      "step": 1258
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001851777337253126,
      "loss": 0.8654,
      "step": 1259
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001851507228606356,
      "loss": 0.8533,
      "step": 1260
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018512368938087702,
      "loss": 0.8561,
      "step": 1261
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001850966332932167,
      "loss": 0.874,
      "step": 1262
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001850695546048404,
      "loss": 0.898,
      "step": 1263
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018504245332293996,
      "loss": 0.8673,
      "step": 1264
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001850153294547131,
      "loss": 0.8704,
      "step": 1265
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018498818300736368,
      "loss": 0.8618,
      "step": 1266
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001849610139881015,
      "loss": 0.8454,
      "step": 1267
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001849338224041423,
      "loss": 0.8337,
      "step": 1268
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001849066082627079,
      "loss": 0.8667,
      "step": 1269
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018487937157102603,
      "loss": 0.8599,
      "step": 1270
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001848521123363305,
      "loss": 0.8669,
      "step": 1271
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018482483056586103,
      "loss": 0.8731,
      "step": 1272
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018479752626686337,
      "loss": 0.8814,
      "step": 1273
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018477019944658922,
      "loss": 0.8648,
      "step": 1274
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018474285011229631,
      "loss": 0.8903,
      "step": 1275
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00018471547827124827,
      "loss": 0.8809,
      "step": 1276
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001846880839307148,
      "loss": 0.877,
      "step": 1277
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001846606670979715,
      "loss": 0.8594,
      "step": 1278
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018463322778029996,
      "loss": 0.8746,
      "step": 1279
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018460576598498783,
      "loss": 0.8931,
      "step": 1280
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018457828171932858,
      "loss": 0.8957,
      "step": 1281
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018455077499062177,
      "loss": 0.864,
      "step": 1282
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018452324580617283,
      "loss": 0.8431,
      "step": 1283
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001844956941732933,
      "loss": 0.881,
      "step": 1284
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018446812009930046,
      "loss": 0.8604,
      "step": 1285
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001844405235915178,
      "loss": 0.8556,
      "step": 1286
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001844129046572745,
      "loss": 0.8663,
      "step": 1287
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018438526330390599,
      "loss": 0.8647,
      "step": 1288
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00018435759953875342,
      "loss": 0.8821,
      "step": 1289
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000184329913369164,
      "loss": 0.9258,
      "step": 1290
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018430220480249087,
      "loss": 0.8566,
      "step": 1291
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018427447384609312,
      "loss": 0.9153,
      "step": 1292
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018424672050733576,
      "loss": 0.915,
      "step": 1293
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018421894479358976,
      "loss": 0.8803,
      "step": 1294
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001841911467122321,
      "loss": 0.8864,
      "step": 1295
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018416332627064556,
      "loss": 0.8626,
      "step": 1296
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000184135483476219,
      "loss": 0.8661,
      "step": 1297
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018410761833634716,
      "loss": 0.864,
      "step": 1298
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018407973085843063,
      "loss": 0.9085,
      "step": 1299
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001840518210498761,
      "loss": 0.8875,
      "step": 1300
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00018402388891809607,
      "loss": 0.8907,
      "step": 1301
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.000183995934470509,
      "loss": 0.8461,
      "step": 1302
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001839679577145393,
      "loss": 0.849,
      "step": 1303
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018393995865761723,
      "loss": 0.8913,
      "step": 1304
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001839119373071791,
      "loss": 0.8824,
      "step": 1305
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.000183883893670667,
      "loss": 0.8562,
      "step": 1306
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018385582775552904,
      "loss": 0.836,
      "step": 1307
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018382773956921925,
      "loss": 0.8718,
      "step": 1308
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018379962911919747,
      "loss": 0.8595,
      "step": 1309
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018377149641292956,
      "loss": 0.8601,
      "step": 1310
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018374334145788724,
      "loss": 0.8658,
      "step": 1311
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018371516426154817,
      "loss": 0.8528,
      "step": 1312
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00018368696483139587,
      "loss": 0.8643,
      "step": 1313
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001836587431749198,
      "loss": 0.8662,
      "step": 1314
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018363049929961535,
      "loss": 0.8809,
      "step": 1315
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018360223321298372,
      "loss": 0.8955,
      "step": 1316
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018357394492253215,
      "loss": 0.8505,
      "step": 1317
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018354563443577363,
      "loss": 0.8787,
      "step": 1318
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001835173017602271,
      "loss": 0.8755,
      "step": 1319
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018348894690341748,
      "loss": 0.9062,
      "step": 1320
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001834605698728754,
      "loss": 0.8848,
      "step": 1321
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018343217067613756,
      "loss": 0.8879,
      "step": 1322
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018340374932074643,
      "loss": 0.8584,
      "step": 1323
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018337530581425044,
      "loss": 0.861,
      "step": 1324
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00018334684016420384,
      "loss": 0.8997,
      "step": 1325
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001833183523781668,
      "loss": 0.8609,
      "step": 1326
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018328984246370532,
      "loss": 0.8655,
      "step": 1327
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018326131042839137,
      "loss": 0.8769,
      "step": 1328
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018323275627980272,
      "loss": 0.8944,
      "step": 1329
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018320418002552302,
      "loss": 0.8607,
      "step": 1330
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018317558167314183,
      "loss": 0.8667,
      "step": 1331
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.903,
      "step": 1332
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018311831870446242,
      "loss": 0.892,
      "step": 1333
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001830896541033726,
      "loss": 0.8715,
      "step": 1334
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018306096743459806,
      "loss": 0.8614,
      "step": 1335
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001830322587057577,
      "loss": 0.8591,
      "step": 1336
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001830035279244762,
      "loss": 0.8585,
      "step": 1337
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001829747750983842,
      "loss": 0.8748,
      "step": 1338
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00018294600023511804,
      "loss": 0.8742,
      "step": 1339
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018291720334232008,
      "loss": 0.8523,
      "step": 1340
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018288838442763838,
      "loss": 0.8723,
      "step": 1341
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000182859543498727,
      "loss": 0.8737,
      "step": 1342
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018283068056324572,
      "loss": 0.884,
      "step": 1343
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018280179562886023,
      "loss": 0.8546,
      "step": 1344
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000182772888703242,
      "loss": 0.8767,
      "step": 1345
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018274395979406846,
      "loss": 0.905,
      "step": 1346
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018271500890902279,
      "loss": 0.9089,
      "step": 1347
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018268603605579395,
      "loss": 0.8537,
      "step": 1348
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001826570412420769,
      "loss": 0.8752,
      "step": 1349
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001826280244755723,
      "loss": 0.8791,
      "step": 1350
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018259898576398668,
      "loss": 0.8715,
      "step": 1351
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00018256992511503237,
      "loss": 0.8707,
      "step": 1352
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001825408425364276,
      "loss": 0.8621,
      "step": 1353
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018251173803589637,
      "loss": 0.8685,
      "step": 1354
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018248261162116846,
      "loss": 0.8838,
      "step": 1355
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001824534632999796,
      "loss": 0.8766,
      "step": 1356
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001824242930800712,
      "loss": 0.9012,
      "step": 1357
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018239510096919057,
      "loss": 0.8701,
      "step": 1358
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001823658869750908,
      "loss": 0.8631,
      "step": 1359
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001823366511055308,
      "loss": 0.8608,
      "step": 1360
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001823073933682753,
      "loss": 0.9051,
      "step": 1361
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001822781137710948,
      "loss": 0.8823,
      "step": 1362
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001822488123217657,
      "loss": 0.9029,
      "step": 1363
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00018221948902807006,
      "loss": 0.8664,
      "step": 1364
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018219014389779585,
      "loss": 0.8794,
      "step": 1365
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018216077693873682,
      "loss": 0.8617,
      "step": 1366
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018213138815869253,
      "loss": 0.9075,
      "step": 1367
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018210197756546824,
      "loss": 0.8718,
      "step": 1368
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018207254516687513,
      "loss": 0.8668,
      "step": 1369
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001820430909707301,
      "loss": 0.852,
      "step": 1370
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018201361498485587,
      "loss": 0.8601,
      "step": 1371
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001819841172170809,
      "loss": 0.8543,
      "step": 1372
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018195459767523953,
      "loss": 0.8466,
      "step": 1373
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018192505636717174,
      "loss": 0.8658,
      "step": 1374
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001818954933007234,
      "loss": 0.8628,
      "step": 1375
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018186590848374618,
      "loss": 0.8643,
      "step": 1376
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00018183630192409743,
      "loss": 0.8874,
      "step": 1377
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018180667362964034,
      "loss": 0.8799,
      "step": 1378
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018177702360824385,
      "loss": 0.8959,
      "step": 1379
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001817473518677826,
      "loss": 0.8455,
      "step": 1380
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018171765841613723,
      "loss": 0.8628,
      "step": 1381
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018168794326119388,
      "loss": 0.8601,
      "step": 1382
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018165820641084457,
      "loss": 0.8751,
      "step": 1383
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001816284478729871,
      "loss": 0.8805,
      "step": 1384
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000181598667655525,
      "loss": 0.8725,
      "step": 1385
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018156886576636757,
      "loss": 0.861,
      "step": 1386
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001815390422134298,
      "loss": 0.8518,
      "step": 1387
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001815091970046326,
      "loss": 0.8566,
      "step": 1388
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018147933014790244,
      "loss": 0.8612,
      "step": 1389
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018144944165117167,
      "loss": 0.9022,
      "step": 1390
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001814195315223783,
      "loss": 0.8589,
      "step": 1391
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018138959976946617,
      "loss": 0.8551,
      "step": 1392
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001813596464003848,
      "loss": 0.8928,
      "step": 1393
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018132967142308942,
      "loss": 0.8775,
      "step": 1394
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018129967484554116,
      "loss": 0.8504,
      "step": 1395
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018126965667570667,
      "loss": 0.8702,
      "step": 1396
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001812396169215585,
      "loss": 0.8776,
      "step": 1397
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018120955559107485,
      "loss": 0.8351,
      "step": 1398
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001811794726922397,
      "loss": 0.9018,
      "step": 1399
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001811493682330427,
      "loss": 0.8613,
      "step": 1400
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018111924222147927,
      "loss": 0.8449,
      "step": 1401
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00018108909466555052,
      "loss": 0.864,
      "step": 1402
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018105892557326338,
      "loss": 0.8379,
      "step": 1403
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018102873495263035,
      "loss": 0.87,
      "step": 1404
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018099852281166975,
      "loss": 0.8835,
      "step": 1405
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018096828915840557,
      "loss": 0.9088,
      "step": 1406
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018093803400086756,
      "loss": 0.8811,
      "step": 1407
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018090775734709114,
      "loss": 0.8506,
      "step": 1408
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018087745920511742,
      "loss": 0.864,
      "step": 1409
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001808471395829933,
      "loss": 0.8851,
      "step": 1410
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001808167984887713,
      "loss": 0.8695,
      "step": 1411
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00018078643593050968,
      "loss": 0.8599,
      "step": 1412
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001807560519162724,
      "loss": 0.8636,
      "step": 1413
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001807256464541291,
      "loss": 0.8602,
      "step": 1414
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001806952195521552,
      "loss": 0.8772,
      "step": 1415
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018066477121843165,
      "loss": 0.8699,
      "step": 1416
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018063430146104522,
      "loss": 0.8473,
      "step": 1417
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018060381028808838,
      "loss": 0.8484,
      "step": 1418
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001805732977076592,
      "loss": 0.8929,
      "step": 1419
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018054276372786148,
      "loss": 0.8675,
      "step": 1420
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018051220835680473,
      "loss": 0.8523,
      "step": 1421
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018048163160260412,
      "loss": 0.8887,
      "step": 1422
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018045103347338046,
      "loss": 0.8671,
      "step": 1423
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018042041397726028,
      "loss": 0.8573,
      "step": 1424
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001803897731223758,
      "loss": 0.8794,
      "step": 1425
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018035911091686488,
      "loss": 0.846,
      "step": 1426
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00018032842736887106,
      "loss": 0.8685,
      "step": 1427
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018029772248654352,
      "loss": 0.8844,
      "step": 1428
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018026699627803717,
      "loss": 0.8496,
      "step": 1429
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018023624875151254,
      "loss": 0.8449,
      "step": 1430
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001802054799151358,
      "loss": 0.8481,
      "step": 1431
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018017468977707887,
      "loss": 0.8893,
      "step": 1432
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018014387834551921,
      "loss": 0.888,
      "step": 1433
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018011304562864,
      "loss": 0.8727,
      "step": 1434
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018008219163463012,
      "loss": 0.8831,
      "step": 1435
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018005131637168398,
      "loss": 0.8726,
      "step": 1436
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00018002041984800174,
      "loss": 0.8816,
      "step": 1437
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00017998950207178912,
      "loss": 0.878,
      "step": 1438
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001799585630512576,
      "loss": 0.8669,
      "step": 1439
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00017992760279462425,
      "loss": 0.8847,
      "step": 1440
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001798966213101117,
      "loss": 0.8873,
      "step": 1441
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017986561860594834,
      "loss": 0.8661,
      "step": 1442
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017983459469036813,
      "loss": 0.8722,
      "step": 1443
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017980354957161066,
      "loss": 0.8429,
      "step": 1444
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017977248325792115,
      "loss": 0.8812,
      "step": 1445
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017974139575755054,
      "loss": 0.8859,
      "step": 1446
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017971028707875527,
      "loss": 0.8677,
      "step": 1447
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017967915722979743,
      "loss": 0.869,
      "step": 1448
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017964800621894482,
      "loss": 0.8826,
      "step": 1449
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017961683405447076,
      "loss": 0.8485,
      "step": 1450
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00017958564074465426,
      "loss": 0.8427,
      "step": 1451
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001795544262977799,
      "loss": 0.8669,
      "step": 1452
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017952319072213788,
      "loss": 0.8546,
      "step": 1453
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017949193402602402,
      "loss": 0.8566,
      "step": 1454
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017946065621773978,
      "loss": 0.8921,
      "step": 1455
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017942935730559217,
      "loss": 0.8516,
      "step": 1456
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001793980372978938,
      "loss": 0.8787,
      "step": 1457
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017936669620296299,
      "loss": 0.8654,
      "step": 1458
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.8526,
      "step": 1459
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001793039507847049,
      "loss": 0.8644,
      "step": 1460
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017927254647804209,
      "loss": 0.8532,
      "step": 1461
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017924112111747576,
      "loss": 0.869,
      "step": 1462
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017920967471135216,
      "loss": 0.8665,
      "step": 1463
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00017917820726802306,
      "loss": 0.8246,
      "step": 1464
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001791467187958459,
      "loss": 0.865,
      "step": 1465
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017911520930318365,
      "loss": 0.852,
      "step": 1466
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017908367879840485,
      "loss": 0.8777,
      "step": 1467
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001790521272898837,
      "loss": 0.8696,
      "step": 1468
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001790205547859999,
      "loss": 0.8573,
      "step": 1469
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017898896129513877,
      "loss": 0.8544,
      "step": 1470
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017895734682569117,
      "loss": 0.8871,
      "step": 1471
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017892571138605358,
      "loss": 0.845,
      "step": 1472
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017889405498462801,
      "loss": 0.8802,
      "step": 1473
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017886237762982203,
      "loss": 0.8524,
      "step": 1474
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017883067933004878,
      "loss": 0.8551,
      "step": 1475
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000178798960093727,
      "loss": 0.8414,
      "step": 1476
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017876721992928095,
      "loss": 0.8568,
      "step": 1477
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001787354588451405,
      "loss": 0.8502,
      "step": 1478
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.000178703676849741,
      "loss": 0.867,
      "step": 1479
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001786718739515234,
      "loss": 0.8822,
      "step": 1480
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001786400501589342,
      "loss": 0.8782,
      "step": 1481
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017860820548042545,
      "loss": 0.8614,
      "step": 1482
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017857633992445475,
      "loss": 0.8988,
      "step": 1483
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017854445349948521,
      "loss": 0.8837,
      "step": 1484
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001785125462139855,
      "loss": 0.8503,
      "step": 1485
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001784806180764299,
      "loss": 0.8676,
      "step": 1486
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017844866909529807,
      "loss": 0.8525,
      "step": 1487
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017841669927907538,
      "loss": 0.8459,
      "step": 1488
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00017838470863625264,
      "loss": 0.8546,
      "step": 1489
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001783526971753262,
      "loss": 0.8699,
      "step": 1490
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017832066490479798,
      "loss": 0.8696,
      "step": 1491
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017828861183317532,
      "loss": 0.8642,
      "step": 1492
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017825653796897122,
      "loss": 0.8458,
      "step": 1493
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017822444332070414,
      "loss": 0.8725,
      "step": 1494
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.000178192327896898,
      "loss": 0.8658,
      "step": 1495
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017816019170608237,
      "loss": 0.9198,
      "step": 1496
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017812803475679222,
      "loss": 0.8726,
      "step": 1497
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001780958570575681,
      "loss": 0.871,
      "step": 1498
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.000178063658616956,
      "loss": 0.8585,
      "step": 1499
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017803143944350756,
      "loss": 0.8566,
      "step": 1500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017799919954577975,
      "loss": 0.8855,
      "step": 1501
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017796693893233517,
      "loss": 0.8735,
      "step": 1502
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00017793465761174182,
      "loss": 0.8438,
      "step": 1503
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017790235559257336,
      "loss": 0.8673,
      "step": 1504
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017787003288340873,
      "loss": 0.8661,
      "step": 1505
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017783768949283256,
      "loss": 0.8419,
      "step": 1506
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001778053254294349,
      "loss": 0.8848,
      "step": 1507
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001777729407018112,
      "loss": 0.8541,
      "step": 1508
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017774053531856258,
      "loss": 0.8818,
      "step": 1509
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001777081092882955,
      "loss": 0.8444,
      "step": 1510
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017767566261962195,
      "loss": 0.8391,
      "step": 1511
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017764319532115943,
      "loss": 0.8866,
      "step": 1512
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017761070740153083,
      "loss": 0.8807,
      "step": 1513
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017757819886936465,
      "loss": 0.866,
      "step": 1514
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017754566973329476,
      "loss": 0.8663,
      "step": 1515
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017751312000196054,
      "loss": 0.8692,
      "step": 1516
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017748054968400685,
      "loss": 0.8653,
      "step": 1517
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017744795878808396,
      "loss": 0.8506,
      "step": 1518
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001774153473228477,
      "loss": 0.8634,
      "step": 1519
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017738271529695927,
      "loss": 0.8826,
      "step": 1520
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017735006271908538,
      "loss": 0.8693,
      "step": 1521
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017731738959789824,
      "loss": 0.8903,
      "step": 1522
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001772846959420754,
      "loss": 0.8855,
      "step": 1523
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017725198176029997,
      "loss": 0.8895,
      "step": 1524
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017721924706126042,
      "loss": 0.8574,
      "step": 1525
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001771864918536508,
      "loss": 0.8829,
      "step": 1526
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017715371614617046,
      "loss": 0.8677,
      "step": 1527
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017712091994752428,
      "loss": 0.8615,
      "step": 1528
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001770881032664226,
      "loss": 0.8782,
      "step": 1529
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017705526611158114,
      "loss": 0.8451,
      "step": 1530
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017702240849172104,
      "loss": 0.8682,
      "step": 1531
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017698953041556898,
      "loss": 0.8528,
      "step": 1532
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.000176956631891857,
      "loss": 0.8709,
      "step": 1533
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017692371292932254,
      "loss": 0.8742,
      "step": 1534
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017689077353670856,
      "loss": 0.8645,
      "step": 1535
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017685781372276334,
      "loss": 0.8575,
      "step": 1536
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001768248334962407,
      "loss": 0.8743,
      "step": 1537
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017679183286589976,
      "loss": 0.8543,
      "step": 1538
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00017675881184050514,
      "loss": 0.8879,
      "step": 1539
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001767257704288269,
      "loss": 0.851,
      "step": 1540
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017669270863964043,
      "loss": 0.8671,
      "step": 1541
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017665962648172654,
      "loss": 0.8498,
      "step": 1542
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017662652396387154,
      "loss": 0.8563,
      "step": 1543
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017659340109486707,
      "loss": 0.8519,
      "step": 1544
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001765602578835102,
      "loss": 0.8694,
      "step": 1545
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017652709433860336,
      "loss": 0.844,
      "step": 1546
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017649391046895447,
      "loss": 0.8409,
      "step": 1547
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017646070628337678,
      "loss": 0.8627,
      "step": 1548
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001764274817906889,
      "loss": 0.8376,
      "step": 1549
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017639423699971496,
      "loss": 0.8507,
      "step": 1550
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001763609719192844,
      "loss": 0.8495,
      "step": 1551
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017632768655823195,
      "loss": 0.8686,
      "step": 1552
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017629438092539796,
      "loss": 0.8818,
      "step": 1553
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017626105502962797,
      "loss": 0.8758,
      "step": 1554
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017622770887977296,
      "loss": 0.852,
      "step": 1555
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017619434248468933,
      "loss": 0.8472,
      "step": 1556
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017616095585323878,
      "loss": 0.887,
      "step": 1557
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001761275489942885,
      "loss": 0.867,
      "step": 1558
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001760941219167109,
      "loss": 0.8518,
      "step": 1559
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017606067462938384,
      "loss": 0.8538,
      "step": 1560
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001760272071411906,
      "loss": 0.8788,
      "step": 1561
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017599371946101978,
      "loss": 0.9007,
      "step": 1562
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017596021159776526,
      "loss": 0.893,
      "step": 1563
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017592668356032637,
      "loss": 0.8709,
      "step": 1564
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00017589313535760784,
      "loss": 0.8618,
      "step": 1565
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001758595669985197,
      "loss": 0.8614,
      "step": 1566
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017582597849197723,
      "loss": 0.8936,
      "step": 1567
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017579236984690126,
      "loss": 0.8491,
      "step": 1568
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017575874107221787,
      "loss": 0.8582,
      "step": 1569
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001757250921768584,
      "loss": 0.8323,
      "step": 1570
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017569142316975969,
      "loss": 0.8633,
      "step": 1571
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017565773405986385,
      "loss": 0.8432,
      "step": 1572
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017562402485611834,
      "loss": 0.8639,
      "step": 1573
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017559029556747592,
      "loss": 0.8489,
      "step": 1574
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001755565462028947,
      "loss": 0.8408,
      "step": 1575
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017552277677133817,
      "loss": 0.841,
      "step": 1576
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00017548898728177512,
      "loss": 0.8562,
      "step": 1577
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001754551777431796,
      "loss": 0.8708,
      "step": 1578
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017542134816453113,
      "loss": 0.8544,
      "step": 1579
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017538749855481442,
      "loss": 0.8531,
      "step": 1580
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017535362892301954,
      "loss": 0.8394,
      "step": 1581
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017531973927814194,
      "loss": 0.8486,
      "step": 1582
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017528582962918226,
      "loss": 0.8536,
      "step": 1583
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017525189998514654,
      "loss": 0.846,
      "step": 1584
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017521795035504618,
      "loss": 0.8437,
      "step": 1585
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.873,
      "step": 1586
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017514999117272323,
      "loss": 0.9026,
      "step": 1587
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017511598163854987,
      "loss": 0.8398,
      "step": 1588
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017508195215441022,
      "loss": 0.8613,
      "step": 1589
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017504790272934208,
      "loss": 0.8555,
      "step": 1590
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001750138333723887,
      "loss": 0.8442,
      "step": 1591
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017497974409259846,
      "loss": 0.8594,
      "step": 1592
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001749456348990251,
      "loss": 0.86,
      "step": 1593
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017491150580072762,
      "loss": 0.8924,
      "step": 1594
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017487735680677034,
      "loss": 0.8701,
      "step": 1595
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001748431879262229,
      "loss": 0.8648,
      "step": 1596
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001748089991681601,
      "loss": 0.8823,
      "step": 1597
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017477479054166218,
      "loss": 0.8954,
      "step": 1598
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017474056205581446,
      "loss": 0.9052,
      "step": 1599
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017470631371970771,
      "loss": 0.8358,
      "step": 1600
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017467204554243791,
      "loss": 0.8795,
      "step": 1601
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017463775753310626,
      "loss": 0.87,
      "step": 1602
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00017460344970081932,
      "loss": 0.8469,
      "step": 1603
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017456912205468885,
      "loss": 0.8367,
      "step": 1604
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001745347746038319,
      "loss": 0.8946,
      "step": 1605
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017450040735737075,
      "loss": 0.8831,
      "step": 1606
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017446602032443297,
      "loss": 0.8705,
      "step": 1607
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017443161351415136,
      "loss": 0.892,
      "step": 1608
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017439718693566401,
      "loss": 0.8422,
      "step": 1609
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001743627405981142,
      "loss": 0.8412,
      "step": 1610
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017432827451065053,
      "loss": 0.8642,
      "step": 1611
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017429378868242677,
      "loss": 0.8711,
      "step": 1612
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017425928312260198,
      "loss": 0.8836,
      "step": 1613
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017422475784034048,
      "loss": 0.8733,
      "step": 1614
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017419021284481177,
      "loss": 0.8408,
      "step": 1615
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00017415564814519065,
      "loss": 0.8744,
      "step": 1616
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017412106375065708,
      "loss": 0.8691,
      "step": 1617
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001740864596703963,
      "loss": 0.8509,
      "step": 1618
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001740518359135988,
      "loss": 0.9077,
      "step": 1619
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017401719248946021,
      "loss": 0.8713,
      "step": 1620
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017398252940718147,
      "loss": 0.8566,
      "step": 1621
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017394784667596868,
      "loss": 0.8683,
      "step": 1622
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017391314430503321,
      "loss": 0.8699,
      "step": 1623
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017387842230359165,
      "loss": 0.8699,
      "step": 1624
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001738436806808657,
      "loss": 0.8527,
      "step": 1625
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001738089194460824,
      "loss": 0.8589,
      "step": 1626
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017377413860847398,
      "loss": 0.8429,
      "step": 1627
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00017373933817727775,
      "loss": 0.9085,
      "step": 1628
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001737045181617364,
      "loss": 0.8678,
      "step": 1629
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001736696785710977,
      "loss": 0.8799,
      "step": 1630
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017363481941461462,
      "loss": 0.9228,
      "step": 1631
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017359994070154544,
      "loss": 0.8974,
      "step": 1632
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001735650424411535,
      "loss": 0.9044,
      "step": 1633
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017353012464270742,
      "loss": 0.8855,
      "step": 1634
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017349518731548096,
      "loss": 0.8731,
      "step": 1635
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017346023046875311,
      "loss": 0.8697,
      "step": 1636
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017342525411180796,
      "loss": 0.8939,
      "step": 1637
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001733902582539349,
      "loss": 0.8509,
      "step": 1638
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001733552429044284,
      "loss": 0.9018,
      "step": 1639
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00017332020807258819,
      "loss": 0.8986,
      "step": 1640
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001732851537677191,
      "loss": 0.8815,
      "step": 1641
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017325007999913114,
      "loss": 0.8514,
      "step": 1642
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017321498677613957,
      "loss": 0.851,
      "step": 1643
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017317987410806471,
      "loss": 0.8527,
      "step": 1644
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017314474200423209,
      "loss": 0.8716,
      "step": 1645
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017310959047397244,
      "loss": 0.9136,
      "step": 1646
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001730744195266216,
      "loss": 0.8541,
      "step": 1647
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017303922917152057,
      "loss": 0.8482,
      "step": 1648
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017300401941801552,
      "loss": 0.8883,
      "step": 1649
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017296879027545775,
      "loss": 0.8717,
      "step": 1650
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001729335417532038,
      "loss": 0.8516,
      "step": 1651
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001728982738606152,
      "loss": 0.8443,
      "step": 1652
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00017286298660705875,
      "loss": 0.8644,
      "step": 1653
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001728276800019063,
      "loss": 0.8504,
      "step": 1654
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.000172792354054535,
      "loss": 0.8449,
      "step": 1655
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001727570087743269,
      "loss": 0.8699,
      "step": 1656
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017272164417066942,
      "loss": 0.8656,
      "step": 1657
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017268626025295492,
      "loss": 0.8446,
      "step": 1658
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017265085703058102,
      "loss": 0.8697,
      "step": 1659
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001726154345129504,
      "loss": 0.8722,
      "step": 1660
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017257999270947093,
      "loss": 0.9026,
      "step": 1661
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001725445316295555,
      "loss": 0.8464,
      "step": 1662
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017250905128262216,
      "loss": 0.866,
      "step": 1663
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017247355167809416,
      "loss": 0.8735,
      "step": 1664
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00017243803282539978,
      "loss": 0.8704,
      "step": 1665
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001724024947339724,
      "loss": 0.8665,
      "step": 1666
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017236693741325062,
      "loss": 0.876,
      "step": 1667
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017233136087267795,
      "loss": 0.874,
      "step": 1668
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001722957651217032,
      "loss": 0.8934,
      "step": 1669
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017226015016978018,
      "loss": 0.851,
      "step": 1670
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017222451602636783,
      "loss": 0.809,
      "step": 1671
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001721888627009302,
      "loss": 0.8749,
      "step": 1672
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017215319020293638,
      "loss": 0.8714,
      "step": 1673
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001721174985418606,
      "loss": 0.8845,
      "step": 1674
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001720817877271822,
      "loss": 0.8702,
      "step": 1675
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001720460577683855,
      "loss": 0.873,
      "step": 1676
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017201030867496005,
      "loss": 0.8483,
      "step": 1677
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017197454045640037,
      "loss": 0.8608,
      "step": 1678
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00017193875312220612,
      "loss": 0.8498,
      "step": 1679
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017190294668188204,
      "loss": 0.913,
      "step": 1680
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017186712114493783,
      "loss": 0.9096,
      "step": 1681
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017183127652088844,
      "loss": 0.8744,
      "step": 1682
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017179541281925377,
      "loss": 0.8612,
      "step": 1683
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017175953004955883,
      "loss": 0.8573,
      "step": 1684
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001717236282213337,
      "loss": 0.8748,
      "step": 1685
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017168770734411344,
      "loss": 0.8839,
      "step": 1686
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017165176742743826,
      "loss": 0.8889,
      "step": 1687
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017161580848085346,
      "loss": 0.8582,
      "step": 1688
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017157983051390926,
      "loss": 0.8789,
      "step": 1689
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017154383353616107,
      "loss": 0.8925,
      "step": 1690
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00017150781755716923,
      "loss": 0.8525,
      "step": 1691
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017147178258649918,
      "loss": 0.8501,
      "step": 1692
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017143572863372147,
      "loss": 0.8734,
      "step": 1693
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017139965570841156,
      "loss": 0.88,
      "step": 1694
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017136356382015005,
      "loss": 0.8691,
      "step": 1695
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017132745297852257,
      "loss": 0.8673,
      "step": 1696
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001712913231931197,
      "loss": 0.844,
      "step": 1697
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001712551744735371,
      "loss": 0.8417,
      "step": 1698
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017121900682937557,
      "loss": 0.8717,
      "step": 1699
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001711828202702407,
      "loss": 0.8807,
      "step": 1700
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017114661480574332,
      "loss": 0.8688,
      "step": 1701
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017111039044549918,
      "loss": 0.8482,
      "step": 1702
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017107414719912903,
      "loss": 0.8569,
      "step": 1703
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00017103788507625873,
      "loss": 0.8863,
      "step": 1704
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017100160408651906,
      "loss": 0.8481,
      "step": 1705
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017096530423954586,
      "loss": 0.857,
      "step": 1706
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017092898554497992,
      "loss": 0.8574,
      "step": 1707
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017089264801246716,
      "loss": 0.8597,
      "step": 1708
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017085629165165836,
      "loss": 0.8372,
      "step": 1709
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017081991647220938,
      "loss": 0.8619,
      "step": 1710
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017078352248378105,
      "loss": 0.8643,
      "step": 1711
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017074710969603924,
      "loss": 0.8792,
      "step": 1712
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.8556,
      "step": 1713
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017067422776130341,
      "loss": 0.8566,
      "step": 1714
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017063775863366607,
      "loss": 0.8517,
      "step": 1715
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017060127074542845,
      "loss": 0.8731,
      "step": 1716
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017056476410628134,
      "loss": 0.8658,
      "step": 1717
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017052823872592057,
      "loss": 0.8918,
      "step": 1718
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017049169461404677,
      "loss": 0.8753,
      "step": 1719
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017045513178036572,
      "loss": 0.8876,
      "step": 1720
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017041855023458807,
      "loss": 0.8808,
      "step": 1721
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017038194998642947,
      "loss": 0.865,
      "step": 1722
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017034533104561054,
      "loss": 0.8657,
      "step": 1723
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001703086934218569,
      "loss": 0.8412,
      "step": 1724
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.000170272037124899,
      "loss": 0.837,
      "step": 1725
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017023536216447246,
      "loss": 0.8463,
      "step": 1726
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017019866855031769,
      "loss": 0.8539,
      "step": 1727
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017016195629218005,
      "loss": 0.8704,
      "step": 1728
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00017012522539980998,
      "loss": 0.876,
      "step": 1729
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00017008847588296277,
      "loss": 0.8876,
      "step": 1730
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001700517077513987,
      "loss": 0.8675,
      "step": 1731
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00017001492101488292,
      "loss": 0.8323,
      "step": 1732
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016997811568318562,
      "loss": 0.8557,
      "step": 1733
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016994129176608187,
      "loss": 0.85,
      "step": 1734
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016990444927335172,
      "loss": 0.8489,
      "step": 1735
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016986758821478014,
      "loss": 0.8807,
      "step": 1736
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001698307086001569,
      "loss": 0.8733,
      "step": 1737
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016979381043927695,
      "loss": 0.847,
      "step": 1738
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016975689374193996,
      "loss": 0.8598,
      "step": 1739
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016971995851795056,
      "loss": 0.8552,
      "step": 1740
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00016968300477711843,
      "loss": 0.855,
      "step": 1741
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.000169646032529258,
      "loss": 0.8788,
      "step": 1742
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016960904178418872,
      "loss": 0.8691,
      "step": 1743
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016957203255173493,
      "loss": 0.8706,
      "step": 1744
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016953500484172582,
      "loss": 0.8626,
      "step": 1745
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016949795866399553,
      "loss": 0.8532,
      "step": 1746
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001694608940283832,
      "loss": 0.8403,
      "step": 1747
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016942381094473268,
      "loss": 0.8562,
      "step": 1748
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016938670942289293,
      "loss": 0.8616,
      "step": 1749
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016934958947271758,
      "loss": 0.8583,
      "step": 1750
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016931245110406534,
      "loss": 0.8626,
      "step": 1751
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016927529432679976,
      "loss": 0.8685,
      "step": 1752
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00016923811915078925,
      "loss": 0.8735,
      "step": 1753
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001692009255859071,
      "loss": 0.8766,
      "step": 1754
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016916371364203152,
      "loss": 0.8626,
      "step": 1755
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001691264833290456,
      "loss": 0.8758,
      "step": 1756
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001690892346568373,
      "loss": 0.8575,
      "step": 1757
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016905196763529942,
      "loss": 0.855,
      "step": 1758
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016901468227432966,
      "loss": 0.8488,
      "step": 1759
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016897737858383063,
      "loss": 0.8558,
      "step": 1760
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001689400565737098,
      "loss": 0.8602,
      "step": 1761
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016890271625387938,
      "loss": 0.8727,
      "step": 1762
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016886535763425666,
      "loss": 0.8562,
      "step": 1763
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001688279807247636,
      "loss": 0.8467,
      "step": 1764
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016879058553532708,
      "loss": 0.8392,
      "step": 1765
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00016875317207587888,
      "loss": 0.8653,
      "step": 1766
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001687157403563556,
      "loss": 0.8628,
      "step": 1767
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016867829038669867,
      "loss": 0.8671,
      "step": 1768
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016864082217685436,
      "loss": 0.851,
      "step": 1769
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001686033357367739,
      "loss": 0.8402,
      "step": 1770
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016856583107641317,
      "loss": 0.8671,
      "step": 1771
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016852830820573303,
      "loss": 0.851,
      "step": 1772
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016849076713469914,
      "loss": 0.8519,
      "step": 1773
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016845320787328195,
      "loss": 0.8521,
      "step": 1774
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016841563043145681,
      "loss": 0.8597,
      "step": 1775
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016837803481920392,
      "loss": 0.8634,
      "step": 1776
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016834042104650816,
      "loss": 0.8637,
      "step": 1777
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016830278912335938,
      "loss": 0.8513,
      "step": 1778
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00016826513905975223,
      "loss": 0.8667,
      "step": 1779
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016822747086568606,
      "loss": 0.854,
      "step": 1780
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001681897845511652,
      "loss": 0.8574,
      "step": 1781
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001681520801261987,
      "loss": 0.8793,
      "step": 1782
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016811435760080037,
      "loss": 0.8609,
      "step": 1783
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016807661698498897,
      "loss": 0.8578,
      "step": 1784
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016803885828878796,
      "loss": 0.8509,
      "step": 1785
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016800108152222564,
      "loss": 0.8617,
      "step": 1786
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016796328669533507,
      "loss": 0.8679,
      "step": 1787
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016792547381815412,
      "loss": 0.8535,
      "step": 1788
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016788764290072555,
      "loss": 0.8633,
      "step": 1789
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016784979395309673,
      "loss": 0.839,
      "step": 1790
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016781192698532,
      "loss": 0.8465,
      "step": 1791
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00016777404200745232,
      "loss": 0.844,
      "step": 1792
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001677361390295556,
      "loss": 0.8402,
      "step": 1793
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016769821806169642,
      "loss": 0.8201,
      "step": 1794
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016766027911394613,
      "loss": 0.8609,
      "step": 1795
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016762232219638093,
      "loss": 0.8657,
      "step": 1796
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016758434731908178,
      "loss": 0.8723,
      "step": 1797
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001675463544921343,
      "loss": 0.8573,
      "step": 1798
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000167508343725629,
      "loss": 0.8545,
      "step": 1799
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016747031502966115,
      "loss": 0.8855,
      "step": 1800
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001674322684143307,
      "loss": 0.8455,
      "step": 1801
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016739420388974245,
      "loss": 0.8445,
      "step": 1802
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001673561214660059,
      "loss": 0.8468,
      "step": 1803
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00016731802115323524,
      "loss": 0.8195,
      "step": 1804
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016727990296154963,
      "loss": 0.8382,
      "step": 1805
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016724176690107272,
      "loss": 0.8345,
      "step": 1806
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016720361298193308,
      "loss": 0.8648,
      "step": 1807
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016716544121426393,
      "loss": 0.8901,
      "step": 1808
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016712725160820328,
      "loss": 0.8692,
      "step": 1809
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016708904417389388,
      "loss": 0.8752,
      "step": 1810
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016705081892148316,
      "loss": 0.8756,
      "step": 1811
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016701257586112337,
      "loss": 0.8585,
      "step": 1812
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001669743150029714,
      "loss": 0.837,
      "step": 1813
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016693603635718892,
      "loss": 0.8487,
      "step": 1814
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016689773993394232,
      "loss": 0.8385,
      "step": 1815
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001668594257434027,
      "loss": 0.8551,
      "step": 1816
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00016682109379574588,
      "loss": 0.8373,
      "step": 1817
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001667827441011524,
      "loss": 0.873,
      "step": 1818
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001667443766698075,
      "loss": 0.8744,
      "step": 1819
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001667059915119011,
      "loss": 0.8792,
      "step": 1820
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016666758863762793,
      "loss": 0.862,
      "step": 1821
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016662916805718737,
      "loss": 0.8385,
      "step": 1822
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016659072978078348,
      "loss": 0.8658,
      "step": 1823
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016655227381862501,
      "loss": 0.8621,
      "step": 1824
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016651380018092548,
      "loss": 0.8494,
      "step": 1825
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016647530887790307,
      "loss": 0.8725,
      "step": 1826
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016643679991978054,
      "loss": 0.8665,
      "step": 1827
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016639827331678555,
      "loss": 0.875,
      "step": 1828
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016635972907915028,
      "loss": 0.8369,
      "step": 1829
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00016632116721711167,
      "loss": 0.8743,
      "step": 1830
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001662825877409113,
      "loss": 0.867,
      "step": 1831
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016624399066079545,
      "loss": 0.8468,
      "step": 1832
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016620537598701512,
      "loss": 0.8631,
      "step": 1833
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016616674372982586,
      "loss": 0.8321,
      "step": 1834
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016612809389948802,
      "loss": 0.8501,
      "step": 1835
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016608942650626654,
      "loss": 0.8511,
      "step": 1836
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001660507415604311,
      "loss": 0.8464,
      "step": 1837
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016601203907225592,
      "loss": 0.8583,
      "step": 1838
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016597331905201997,
      "loss": 0.8446,
      "step": 1839
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.8607,
      "step": 1840
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001658958264565049,
      "loss": 0.8714,
      "step": 1841
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001658570539018069,
      "loss": 0.8581,
      "step": 1842
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001658182638562105,
      "loss": 0.865,
      "step": 1843
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016577945633001787,
      "loss": 0.8495,
      "step": 1844
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016574063133353582,
      "loss": 0.8422,
      "step": 1845
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001657017888770759,
      "loss": 0.8674,
      "step": 1846
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001656629289709542,
      "loss": 0.9038,
      "step": 1847
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001656240516254915,
      "loss": 0.8488,
      "step": 1848
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016558515685101316,
      "loss": 0.8305,
      "step": 1849
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016554624465784921,
      "loss": 0.8939,
      "step": 1850
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001655073150563343,
      "loss": 0.8693,
      "step": 1851
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016546836805680768,
      "loss": 0.8609,
      "step": 1852
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00016542940366961326,
      "loss": 0.8881,
      "step": 1853
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001653904219050995,
      "loss": 0.8723,
      "step": 1854
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001653514227736196,
      "loss": 0.8549,
      "step": 1855
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016531240628553127,
      "loss": 0.859,
      "step": 1856
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016527337245119677,
      "loss": 0.8775,
      "step": 1857
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016523432128098318,
      "loss": 0.897,
      "step": 1858
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016519525278526197,
      "loss": 0.8355,
      "step": 1859
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016515616697440933,
      "loss": 0.8467,
      "step": 1860
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.000165117063858806,
      "loss": 0.8701,
      "step": 1861
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001650779434488373,
      "loss": 0.8655,
      "step": 1862
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016503880575489323,
      "loss": 0.8446,
      "step": 1863
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001649996507873683,
      "loss": 0.8626,
      "step": 1864
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016496047855666163,
      "loss": 0.8347,
      "step": 1865
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016492128907317696,
      "loss": 0.8725,
      "step": 1866
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00016488208234732255,
      "loss": 0.874,
      "step": 1867
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016484285838951125,
      "loss": 0.8469,
      "step": 1868
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016480361721016054,
      "loss": 0.8608,
      "step": 1869
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001647643588196924,
      "loss": 0.8565,
      "step": 1870
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016472508322853347,
      "loss": 0.8472,
      "step": 1871
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001646857904471149,
      "loss": 0.8594,
      "step": 1872
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016464648048587237,
      "loss": 0.8528,
      "step": 1873
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001646071533552462,
      "loss": 0.8744,
      "step": 1874
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016456780906568122,
      "loss": 0.8583,
      "step": 1875
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016452844762762688,
      "loss": 0.8425,
      "step": 1876
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001644890690515371,
      "loss": 0.8556,
      "step": 1877
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016444967334787035,
      "loss": 0.8327,
      "step": 1878
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016441026052708976,
      "loss": 0.8471,
      "step": 1879
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016437083059966294,
      "loss": 0.8818,
      "step": 1880
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016433138357606198,
      "loss": 0.8578,
      "step": 1881
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001642919194667636,
      "loss": 0.8874,
      "step": 1882
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016425243828224905,
      "loss": 0.8578,
      "step": 1883
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016421294003300405,
      "loss": 0.8635,
      "step": 1884
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016417342472951888,
      "loss": 0.84,
      "step": 1885
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016413389238228843,
      "loss": 0.862,
      "step": 1886
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000164094343001812,
      "loss": 0.8604,
      "step": 1887
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001640547765985935,
      "loss": 0.8704,
      "step": 1888
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001640151931831413,
      "loss": 0.8424,
      "step": 1889
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001639755927659683,
      "loss": 0.8686,
      "step": 1890
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016393597535759193,
      "loss": 0.8461,
      "step": 1891
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00016389634096853416,
      "loss": 0.8727,
      "step": 1892
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016385668960932143,
      "loss": 0.8604,
      "step": 1893
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016381702129048472,
      "loss": 0.8889,
      "step": 1894
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016377733602255946,
      "loss": 0.8326,
      "step": 1895
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001637376338160856,
      "loss": 0.8432,
      "step": 1896
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016369791468160764,
      "loss": 0.879,
      "step": 1897
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016365817862967457,
      "loss": 0.8667,
      "step": 1898
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016361842567083973,
      "loss": 0.8714,
      "step": 1899
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016357865581566113,
      "loss": 0.8339,
      "step": 1900
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016353886907470125,
      "loss": 0.8405,
      "step": 1901
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016349906545852695,
      "loss": 0.8821,
      "step": 1902
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016345924497770958,
      "loss": 0.8488,
      "step": 1903
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016341940764282508,
      "loss": 0.8208,
      "step": 1904
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00016337955346445383,
      "loss": 0.8431,
      "step": 1905
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016333968245318053,
      "loss": 0.8287,
      "step": 1906
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016329979461959465,
      "loss": 0.8587,
      "step": 1907
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016325988997428978,
      "loss": 0.8815,
      "step": 1908
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016321996852786428,
      "loss": 0.8712,
      "step": 1909
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016318003029092078,
      "loss": 0.8651,
      "step": 1910
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016314007527406643,
      "loss": 0.8732,
      "step": 1911
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016310010348791285,
      "loss": 0.887,
      "step": 1912
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001630601149430761,
      "loss": 0.8908,
      "step": 1913
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016302010965017666,
      "loss": 0.8937,
      "step": 1914
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016298008761983957,
      "loss": 0.8837,
      "step": 1915
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016294004886269415,
      "loss": 0.8612,
      "step": 1916
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016289999338937427,
      "loss": 0.8509,
      "step": 1917
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00016285992121051822,
      "loss": 0.8569,
      "step": 1918
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016281983233676876,
      "loss": 0.8552,
      "step": 1919
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016277972677877298,
      "loss": 0.8372,
      "step": 1920
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001627396045471825,
      "loss": 0.8311,
      "step": 1921
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016269946565265338,
      "loss": 0.8367,
      "step": 1922
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.000162659310105846,
      "loss": 0.8791,
      "step": 1923
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016261913791742525,
      "loss": 0.8898,
      "step": 1924
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001625789490980604,
      "loss": 0.8947,
      "step": 1925
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001625387436584252,
      "loss": 0.8463,
      "step": 1926
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001624985216091977,
      "loss": 0.8651,
      "step": 1927
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016245828296106046,
      "loss": 0.8621,
      "step": 1928
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016241802772470044,
      "loss": 0.8561,
      "step": 1929
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00016237775591080892,
      "loss": 0.8747,
      "step": 1930
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001623374675300817,
      "loss": 0.8672,
      "step": 1931
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016229716259321889,
      "loss": 0.8744,
      "step": 1932
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016225684111092505,
      "loss": 0.8806,
      "step": 1933
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001622165030939091,
      "loss": 0.8757,
      "step": 1934
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016217614855288442,
      "loss": 0.8624,
      "step": 1935
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016213577749856867,
      "loss": 0.8871,
      "step": 1936
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016209538994168394,
      "loss": 0.8649,
      "step": 1937
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016205498589295675,
      "loss": 0.8304,
      "step": 1938
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016201456536311793,
      "loss": 0.8289,
      "step": 1939
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016197412836290278,
      "loss": 0.8663,
      "step": 1940
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016193367490305088,
      "loss": 0.9171,
      "step": 1941
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001618932049943062,
      "loss": 0.8595,
      "step": 1942
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001618527186474171,
      "loss": 0.8619,
      "step": 1943
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016181221587313637,
      "loss": 0.8718,
      "step": 1944
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.000161771696682221,
      "loss": 0.8649,
      "step": 1945
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016173116108543248,
      "loss": 0.8802,
      "step": 1946
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016169060909353663,
      "loss": 0.8582,
      "step": 1947
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016165004071730355,
      "loss": 0.8621,
      "step": 1948
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016160945596750784,
      "loss": 0.8502,
      "step": 1949
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016156885485492825,
      "loss": 0.8442,
      "step": 1950
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016152823739034802,
      "loss": 0.8411,
      "step": 1951
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016148760358455474,
      "loss": 0.8498,
      "step": 1952
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016144695344834026,
      "loss": 0.8228,
      "step": 1953
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001614062869925008,
      "loss": 0.8978,
      "step": 1954
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001613656042278369,
      "loss": 0.8597,
      "step": 1955
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016132490516515349,
      "loss": 0.8744,
      "step": 1956
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016128418981525977,
      "loss": 0.8644,
      "step": 1957
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016124345818896926,
      "loss": 0.8445,
      "step": 1958
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016120271029709988,
      "loss": 0.8529,
      "step": 1959
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016116194615047372,
      "loss": 0.8425,
      "step": 1960
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001611211657599174,
      "loss": 0.882,
      "step": 1961
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016108036913626162,
      "loss": 0.8714,
      "step": 1962
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016103955629034162,
      "loss": 0.875,
      "step": 1963
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016099872723299673,
      "loss": 0.8722,
      "step": 1964
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016095788197507081,
      "loss": 0.8619,
      "step": 1965
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001609170205274118,
      "loss": 0.8581,
      "step": 1966
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.8705,
      "step": 1967
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016083524910630832,
      "loss": 0.8781,
      "step": 1968
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016079433915458136,
      "loss": 0.8872,
      "step": 1969
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016075341305655657,
      "loss": 0.8888,
      "step": 1970
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016071247082310338,
      "loss": 0.86,
      "step": 1971
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016067151246509557,
      "loss": 0.8465,
      "step": 1972
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016063053799341125,
      "loss": 0.874,
      "step": 1973
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016058954741893282,
      "loss": 0.8405,
      "step": 1974
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016054854075254687,
      "loss": 0.8565,
      "step": 1975
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016050751800514434,
      "loss": 0.8411,
      "step": 1976
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016046647918762042,
      "loss": 0.8683,
      "step": 1977
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016042542431087448,
      "loss": 0.8605,
      "step": 1978
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016038435338581035,
      "loss": 0.8474,
      "step": 1979
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016034326642333597,
      "loss": 0.8712,
      "step": 1980
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016030216343436353,
      "loss": 0.8397,
      "step": 1981
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016026104442980958,
      "loss": 0.8417,
      "step": 1982
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016021990942059487,
      "loss": 0.8618,
      "step": 1983
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016017875841764436,
      "loss": 0.886,
      "step": 1984
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016013759143188733,
      "loss": 0.8651,
      "step": 1985
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016009640847425725,
      "loss": 0.8718,
      "step": 1986
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016005520955569185,
      "loss": 0.8473,
      "step": 1987
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00016001399468713314,
      "loss": 0.8519,
      "step": 1988
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00015997276387952732,
      "loss": 0.8285,
      "step": 1989
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001599315171438248,
      "loss": 0.8745,
      "step": 1990
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00015989025449098028,
      "loss": 0.8564,
      "step": 1991
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00015984897593195266,
      "loss": 0.8552,
      "step": 1992
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.000159807681477705,
      "loss": 0.8674,
      "step": 1993
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015976637113920475,
      "loss": 0.8498,
      "step": 1994
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015972504492742346,
      "loss": 0.8872,
      "step": 1995
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015968370285333682,
      "loss": 0.9088,
      "step": 1996
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015964234492792491,
      "loss": 0.884,
      "step": 1997
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001596009711621719,
      "loss": 0.8284,
      "step": 1998
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015955958156706621,
      "loss": 0.8535,
      "step": 1999
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015951817615360043,
      "loss": 0.8416,
      "step": 2000
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015947675493277138,
      "loss": 0.8694,
      "step": 2001
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015943531791558013,
      "loss": 0.8736,
      "step": 2002
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015939386511303183,
      "loss": 0.8478,
      "step": 2003
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001593523965361359,
      "loss": 0.8501,
      "step": 2004
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00015931091219590596,
      "loss": 0.8592,
      "step": 2005
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001592694121033597,
      "loss": 0.8642,
      "step": 2006
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001592278962695192,
      "loss": 0.8707,
      "step": 2007
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001591863647054105,
      "loss": 0.8546,
      "step": 2008
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015914481742206396,
      "loss": 0.861,
      "step": 2009
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001591032544305141,
      "loss": 0.8488,
      "step": 2010
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015906167574179957,
      "loss": 0.8679,
      "step": 2011
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015902008136696317,
      "loss": 0.8746,
      "step": 2012
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015897847131705195,
      "loss": 0.8823,
      "step": 2013
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015893684560311705,
      "loss": 0.8685,
      "step": 2014
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001588952042362138,
      "loss": 0.8631,
      "step": 2015
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001588535472274017,
      "loss": 0.8497,
      "step": 2016
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015881187458774437,
      "loss": 0.8722,
      "step": 2017
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015877018632830955,
      "loss": 0.8692,
      "step": 2018
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015872848246016927,
      "loss": 0.8401,
      "step": 2019
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015868676299439955,
      "loss": 0.8726,
      "step": 2020
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015864502794208063,
      "loss": 0.8519,
      "step": 2021
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015860327731429688,
      "loss": 0.8569,
      "step": 2022
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001585615111221368,
      "loss": 0.8432,
      "step": 2023
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000158519729376693,
      "loss": 0.8605,
      "step": 2024
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015847793208906229,
      "loss": 0.8439,
      "step": 2025
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001584361192703455,
      "loss": 0.8684,
      "step": 2026
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001583942909316477,
      "loss": 0.8731,
      "step": 2027
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015835244708407802,
      "loss": 0.851,
      "step": 2028
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015831058773874973,
      "loss": 0.8712,
      "step": 2029
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015826871290678017,
      "loss": 0.8527,
      "step": 2030
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00015822682259929085,
      "loss": 0.8666,
      "step": 2031
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015818491682740736,
      "loss": 0.8464,
      "step": 2032
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001581429956022594,
      "loss": 0.8684,
      "step": 2033
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015810105893498082,
      "loss": 0.8386,
      "step": 2034
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001580591068367095,
      "loss": 0.8764,
      "step": 2035
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015801713931858744,
      "loss": 0.8845,
      "step": 2036
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015797515639176074,
      "loss": 0.8562,
      "step": 2037
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015793315806737965,
      "loss": 0.8366,
      "step": 2038
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015789114435659838,
      "loss": 0.8451,
      "step": 2039
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015784911527057534,
      "loss": 0.8493,
      "step": 2040
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015780707082047298,
      "loss": 0.8494,
      "step": 2041
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00015776501101745787,
      "loss": 0.854,
      "step": 2042
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001577229358727006,
      "loss": 0.8444,
      "step": 2043
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015768084539737585,
      "loss": 0.858,
      "step": 2044
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015763873960266236,
      "loss": 0.8593,
      "step": 2045
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015759661849974299,
      "loss": 0.8905,
      "step": 2046
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015755448209980465,
      "loss": 0.8522,
      "step": 2047
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015751233041403829,
      "loss": 0.8203,
      "step": 2048
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015747016345363886,
      "loss": 0.8793,
      "step": 2049
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015742798122980552,
      "loss": 0.8444,
      "step": 2050
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001573857837537414,
      "loss": 0.8825,
      "step": 2051
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001573435710366536,
      "loss": 0.8498,
      "step": 2052
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001573013430897534,
      "loss": 0.8421,
      "step": 2053
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015725909992425608,
      "loss": 0.8624,
      "step": 2054
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001572168415513809,
      "loss": 0.8511,
      "step": 2055
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00015717456798235125,
      "loss": 0.8623,
      "step": 2056
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015713227922839454,
      "loss": 0.8465,
      "step": 2057
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015708997530074217,
      "loss": 0.8727,
      "step": 2058
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001570476562106296,
      "loss": 0.9095,
      "step": 2059
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015700532196929627,
      "loss": 0.8545,
      "step": 2060
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001569629725879857,
      "loss": 0.8391,
      "step": 2061
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015692060807794545,
      "loss": 0.852,
      "step": 2062
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015687822845042703,
      "loss": 0.8459,
      "step": 2063
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.000156835833716686,
      "loss": 0.8488,
      "step": 2064
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001567934238879819,
      "loss": 0.8429,
      "step": 2065
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00015675099897557835,
      "loss": 0.8694,
      "step": 2066
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001567085589907429,
      "loss": 0.8394,
      "step": 2067
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001566661039447472,
      "loss": 0.8646,
      "step": 2068
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015662363384886675,
      "loss": 0.8599,
      "step": 2069
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015658114871438118,
      "loss": 0.8644,
      "step": 2070
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015653864855257407,
      "loss": 0.8799,
      "step": 2071
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015649613337473297,
      "loss": 0.8633,
      "step": 2072
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015645360319214944,
      "loss": 0.8349,
      "step": 2073
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015641105801611903,
      "loss": 0.8512,
      "step": 2074
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015636849785794128,
      "loss": 0.8678,
      "step": 2075
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015632592272891963,
      "loss": 0.8343,
      "step": 2076
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015628333264036166,
      "loss": 0.8381,
      "step": 2077
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015624072760357874,
      "loss": 0.8752,
      "step": 2078
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001561981076298863,
      "loss": 0.8772,
      "step": 2079
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015615547273060377,
      "loss": 0.8919,
      "step": 2080
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00015611282291705449,
      "loss": 0.8721,
      "step": 2081
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015607015820056575,
      "loss": 0.8595,
      "step": 2082
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001560274785924688,
      "loss": 0.8327,
      "step": 2083
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015598478410409897,
      "loss": 0.8607,
      "step": 2084
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015594207474679532,
      "loss": 0.8374,
      "step": 2085
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015589935053190106,
      "loss": 0.8712,
      "step": 2086
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015585661147076322,
      "loss": 0.8296,
      "step": 2087
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015581385757473286,
      "loss": 0.8528,
      "step": 2088
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001557710888551649,
      "loss": 0.8379,
      "step": 2089
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015572830532341824,
      "loss": 0.8479,
      "step": 2090
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015568550699085574,
      "loss": 0.8489,
      "step": 2091
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001556426938688441,
      "loss": 0.856,
      "step": 2092
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001555998659687541,
      "loss": 0.8436,
      "step": 2093
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.8478,
      "step": 2094
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001555141658798411,
      "loss": 0.8708,
      "step": 2095
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015547129371377917,
      "loss": 0.8464,
      "step": 2096
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015542840681516079,
      "loss": 0.8579,
      "step": 2097
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015538550519537625,
      "loss": 0.8603,
      "step": 2098
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001553425888658197,
      "loss": 0.834,
      "step": 2099
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015529965783788932,
      "loss": 0.8358,
      "step": 2100
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015525671212298704,
      "loss": 0.8467,
      "step": 2101
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015521375173251878,
      "loss": 0.8266,
      "step": 2102
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015517077667789436,
      "loss": 0.8478,
      "step": 2103
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015512778697052742,
      "loss": 0.8587,
      "step": 2104
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00015508478262183563,
      "loss": 0.8719,
      "step": 2105
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001550417636432404,
      "loss": 0.8674,
      "step": 2106
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015499873004616715,
      "loss": 0.8725,
      "step": 2107
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015495568184204506,
      "loss": 0.8514,
      "step": 2108
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015491261904230727,
      "loss": 0.8319,
      "step": 2109
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015486954165839077,
      "loss": 0.8663,
      "step": 2110
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015482644970173649,
      "loss": 0.8708,
      "step": 2111
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001547833431837891,
      "loss": 0.852,
      "step": 2112
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015474022211599725,
      "loss": 0.8447,
      "step": 2113
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015469708650981342,
      "loss": 0.8256,
      "step": 2114
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015465393637669394,
      "loss": 0.9014,
      "step": 2115
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.000154610771728099,
      "loss": 0.8272,
      "step": 2116
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015456759257549262,
      "loss": 0.8668,
      "step": 2117
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001545243989303427,
      "loss": 0.8821,
      "step": 2118
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00015448119080412108,
      "loss": 0.859,
      "step": 2119
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015443796820830324,
      "loss": 0.8503,
      "step": 2120
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001543947311543687,
      "loss": 0.8691,
      "step": 2121
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001543514796538007,
      "loss": 0.8771,
      "step": 2122
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015430821371808636,
      "loss": 0.8435,
      "step": 2123
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015426493335871666,
      "loss": 0.8448,
      "step": 2124
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015422163858718632,
      "loss": 0.8399,
      "step": 2125
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015417832941499402,
      "loss": 0.8608,
      "step": 2126
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015413500585364213,
      "loss": 0.8601,
      "step": 2127
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015409166791463693,
      "loss": 0.8771,
      "step": 2128
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015404831560948852,
      "loss": 0.8256,
      "step": 2129
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00015400494894971076,
      "loss": 0.8424,
      "step": 2130
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001539615679468213,
      "loss": 0.8467,
      "step": 2131
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015391817261234175,
      "loss": 0.8592,
      "step": 2132
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015387476295779736,
      "loss": 0.866,
      "step": 2133
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015383133899471728,
      "loss": 0.8381,
      "step": 2134
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015378790073463443,
      "loss": 0.8829,
      "step": 2135
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015374444818908552,
      "loss": 0.8816,
      "step": 2136
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015370098136961103,
      "loss": 0.853,
      "step": 2137
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015365750028775528,
      "loss": 0.8554,
      "step": 2138
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001536140049550664,
      "loss": 0.8517,
      "step": 2139
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015357049538309623,
      "loss": 0.8603,
      "step": 2140
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015352697158340042,
      "loss": 0.9094,
      "step": 2141
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001534834335675384,
      "loss": 0.8755,
      "step": 2142
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015343988134707343,
      "loss": 0.8756,
      "step": 2143
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00015339631493357242,
      "loss": 0.8513,
      "step": 2144
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015335273433860622,
      "loss": 0.8327,
      "step": 2145
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015330913957374925,
      "loss": 0.8495,
      "step": 2146
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015326553065057988,
      "loss": 0.8778,
      "step": 2147
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015322190758068009,
      "loss": 0.8353,
      "step": 2148
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015317827037563566,
      "loss": 0.8577,
      "step": 2149
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015313461904703624,
      "loss": 0.9,
      "step": 2150
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015309095360647502,
      "loss": 0.8373,
      "step": 2151
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015304727406554919,
      "loss": 0.8321,
      "step": 2152
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001530035804358594,
      "loss": 0.8577,
      "step": 2153
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001529598727290103,
      "loss": 0.8276,
      "step": 2154
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015291615095661012,
      "loss": 0.8632,
      "step": 2155
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015287241513027092,
      "loss": 0.8295,
      "step": 2156
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00015282866526160837,
      "loss": 0.8383,
      "step": 2157
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015278490136224203,
      "loss": 0.83,
      "step": 2158
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015274112344379503,
      "loss": 0.847,
      "step": 2159
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015269733151789433,
      "loss": 0.8946,
      "step": 2160
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001526535255961706,
      "loss": 0.8495,
      "step": 2161
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015260970569025816,
      "loss": 0.8718,
      "step": 2162
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015256587181179513,
      "loss": 0.8583,
      "step": 2163
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015252202397242326,
      "loss": 0.8539,
      "step": 2164
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015247816218378807,
      "loss": 0.8578,
      "step": 2165
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015243428645753877,
      "loss": 0.8474,
      "step": 2166
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015239039680532823,
      "loss": 0.8675,
      "step": 2167
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015234649323881308,
      "loss": 0.8467,
      "step": 2168
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00015230257576965363,
      "loss": 0.8666,
      "step": 2169
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015225864440951382,
      "loss": 0.8444,
      "step": 2170
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015221469917006135,
      "loss": 0.8382,
      "step": 2171
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015217074006296762,
      "loss": 0.8546,
      "step": 2172
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015212676709990762,
      "loss": 0.8513,
      "step": 2173
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001520827802925601,
      "loss": 0.8585,
      "step": 2174
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001520387796526075,
      "loss": 0.8576,
      "step": 2175
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015199476519173587,
      "loss": 0.8804,
      "step": 2176
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015195073692163494,
      "loss": 0.846,
      "step": 2177
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015190669485399817,
      "loss": 0.8436,
      "step": 2178
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015186263900052264,
      "loss": 0.8564,
      "step": 2179
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015181856937290903,
      "loss": 0.8672,
      "step": 2180
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001517744859828618,
      "loss": 0.8761,
      "step": 2181
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00015173038884208902,
      "loss": 0.8932,
      "step": 2182
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015168627796230232,
      "loss": 0.8513,
      "step": 2183
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015164215335521715,
      "loss": 0.8484,
      "step": 2184
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015159801503255245,
      "loss": 0.8327,
      "step": 2185
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015155386300603086,
      "loss": 0.8638,
      "step": 2186
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015150969728737875,
      "loss": 0.8841,
      "step": 2187
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015146551788832593,
      "loss": 0.8447,
      "step": 2188
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.000151421324820606,
      "loss": 0.8676,
      "step": 2189
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015137711809595618,
      "loss": 0.8885,
      "step": 2190
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015133289772611727,
      "loss": 0.8457,
      "step": 2191
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015128866372283368,
      "loss": 0.8537,
      "step": 2192
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015124441609785347,
      "loss": 0.8419,
      "step": 2193
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00015120015486292835,
      "loss": 0.8639,
      "step": 2194
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015115588002981355,
      "loss": 0.8417,
      "step": 2195
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015111159161026801,
      "loss": 0.8764,
      "step": 2196
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001510672896160543,
      "loss": 0.8673,
      "step": 2197
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015102297405893838,
      "loss": 0.8391,
      "step": 2198
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015097864495069012,
      "loss": 0.8792,
      "step": 2199
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001509343023030828,
      "loss": 0.8643,
      "step": 2200
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015088994612789323,
      "loss": 0.8243,
      "step": 2201
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015084557643690202,
      "loss": 0.8603,
      "step": 2202
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015080119324189327,
      "loss": 0.8347,
      "step": 2203
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001507567965546546,
      "loss": 0.8482,
      "step": 2204
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015071238638697732,
      "loss": 0.8749,
      "step": 2205
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015066796275065624,
      "loss": 0.8491,
      "step": 2206
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00015062352565748982,
      "loss": 0.8619,
      "step": 2207
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015057907511928001,
      "loss": 0.8339,
      "step": 2208
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015053461114783242,
      "loss": 0.8324,
      "step": 2209
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001504901337549562,
      "loss": 0.8618,
      "step": 2210
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015044564295246395,
      "loss": 0.8463,
      "step": 2211
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015040113875217204,
      "loss": 0.8625,
      "step": 2212
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015035662116590025,
      "loss": 0.8529,
      "step": 2213
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001503120902054719,
      "loss": 0.8382,
      "step": 2214
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015026754588271402,
      "loss": 0.8396,
      "step": 2215
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.000150222988209457,
      "loss": 0.8354,
      "step": 2216
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015017841719753493,
      "loss": 0.8674,
      "step": 2217
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001501338328587853,
      "loss": 0.8757,
      "step": 2218
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00015008923520504926,
      "loss": 0.8435,
      "step": 2219
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00015004462424817144,
      "loss": 0.8576,
      "step": 2220
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8732,
      "step": 2221
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014995536247238667,
      "loss": 0.8648,
      "step": 2222
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014991071167718664,
      "loss": 0.8844,
      "step": 2223
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001498660476262587,
      "loss": 0.8552,
      "step": 2224
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014982137033146508,
      "loss": 0.8651,
      "step": 2225
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014977667980467163,
      "loss": 0.8749,
      "step": 2226
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014973197605774757,
      "loss": 0.8603,
      "step": 2227
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014968725910256584,
      "loss": 0.8665,
      "step": 2228
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014964252895100264,
      "loss": 0.8648,
      "step": 2229
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014959778561493786,
      "loss": 0.8602,
      "step": 2230
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014955302910625484,
      "loss": 0.9071,
      "step": 2231
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00014950825943684036,
      "loss": 0.8427,
      "step": 2232
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014946347661858484,
      "loss": 0.8587,
      "step": 2233
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014941868066338198,
      "loss": 0.8334,
      "step": 2234
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001493738715831291,
      "loss": 0.8348,
      "step": 2235
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014932904938972714,
      "loss": 0.8701,
      "step": 2236
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014928421409508017,
      "loss": 0.8698,
      "step": 2237
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001492393657110961,
      "loss": 0.8416,
      "step": 2238
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014919450424968607,
      "loss": 0.8644,
      "step": 2239
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001491496297227648,
      "loss": 0.8342,
      "step": 2240
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001491047421422505,
      "loss": 0.8729,
      "step": 2241
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014905984152006476,
      "loss": 0.8589,
      "step": 2242
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014901492786813272,
      "loss": 0.8439,
      "step": 2243
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014897000119838292,
      "loss": 0.8317,
      "step": 2244
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00014892506152274743,
      "loss": 0.8479,
      "step": 2245
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014888010885316167,
      "loss": 0.8496,
      "step": 2246
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001488351432015646,
      "loss": 0.8509,
      "step": 2247
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014879016457989858,
      "loss": 0.8505,
      "step": 2248
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014874517300010945,
      "loss": 0.8254,
      "step": 2249
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014870016847414643,
      "loss": 0.8392,
      "step": 2250
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014865515101396225,
      "loss": 0.8515,
      "step": 2251
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014861012063151305,
      "loss": 0.8306,
      "step": 2252
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014856507733875836,
      "loss": 0.8368,
      "step": 2253
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014852002114766125,
      "loss": 0.8437,
      "step": 2254
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014847495207018807,
      "loss": 0.875,
      "step": 2255
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001484298701183087,
      "loss": 0.8564,
      "step": 2256
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00014838477530399637,
      "loss": 0.8939,
      "step": 2257
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014833966763922783,
      "loss": 0.8608,
      "step": 2258
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014829454713598307,
      "loss": 0.8509,
      "step": 2259
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014824941380624565,
      "loss": 0.8645,
      "step": 2260
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001482042676620025,
      "loss": 0.8435,
      "step": 2261
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001481591087152439,
      "loss": 0.8595,
      "step": 2262
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014811393697796357,
      "loss": 0.8586,
      "step": 2263
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014806875246215864,
      "loss": 0.8821,
      "step": 2264
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014802355517982955,
      "loss": 0.8707,
      "step": 2265
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014797834514298025,
      "loss": 0.8301,
      "step": 2266
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.000147933122363618,
      "loss": 0.8626,
      "step": 2267
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014788788685375347,
      "loss": 0.8296,
      "step": 2268
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014784263862540074,
      "loss": 0.8269,
      "step": 2269
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00014779737769057719,
      "loss": 0.8666,
      "step": 2270
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014775210406130356,
      "loss": 0.8496,
      "step": 2271
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014770681774960417,
      "loss": 0.8577,
      "step": 2272
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014766151876750646,
      "loss": 0.8475,
      "step": 2273
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014761620712704137,
      "loss": 0.862,
      "step": 2274
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014757088284024313,
      "loss": 0.8906,
      "step": 2275
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001475255459191494,
      "loss": 0.8361,
      "step": 2276
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014748019637580114,
      "loss": 0.8454,
      "step": 2277
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014743483422224266,
      "loss": 0.8563,
      "step": 2278
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001473894594705217,
      "loss": 0.8542,
      "step": 2279
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014734407213268927,
      "loss": 0.893,
      "step": 2280
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001472986722207997,
      "loss": 0.8729,
      "step": 2281
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00014725325974691074,
      "loss": 0.8443,
      "step": 2282
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014720783472308343,
      "loss": 0.8463,
      "step": 2283
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014716239716138212,
      "loss": 0.8344,
      "step": 2284
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014711694707387457,
      "loss": 0.8418,
      "step": 2285
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014707148447263177,
      "loss": 0.8568,
      "step": 2286
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014702600936972814,
      "loss": 0.861,
      "step": 2287
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014698052177724127,
      "loss": 0.8707,
      "step": 2288
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001469350217072522,
      "loss": 0.8735,
      "step": 2289
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014688950917184527,
      "loss": 0.8577,
      "step": 2290
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014684398418310805,
      "loss": 0.8632,
      "step": 2291
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001467984467531315,
      "loss": 0.8286,
      "step": 2292
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014675289689400987,
      "loss": 0.8644,
      "step": 2293
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014670733461784067,
      "loss": 0.8526,
      "step": 2294
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00014666175993672474,
      "loss": 0.8553,
      "step": 2295
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001466161728627662,
      "loss": 0.871,
      "step": 2296
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014657057340807246,
      "loss": 0.8684,
      "step": 2297
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014652496158475421,
      "loss": 0.8184,
      "step": 2298
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001464793374049255,
      "loss": 0.8424,
      "step": 2299
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014643370088070356,
      "loss": 0.8864,
      "step": 2300
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014638805202420895,
      "loss": 0.8725,
      "step": 2301
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014634239084756548,
      "loss": 0.8367,
      "step": 2302
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001462967173629003,
      "loss": 0.837,
      "step": 2303
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014625103158234372,
      "loss": 0.8413,
      "step": 2304
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014620533351802938,
      "loss": 0.8659,
      "step": 2305
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00014615962318209426,
      "loss": 0.8737,
      "step": 2306
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001461139005866784,
      "loss": 0.8411,
      "step": 2307
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014606816574392527,
      "loss": 0.8741,
      "step": 2308
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014602241866598151,
      "loss": 0.8866,
      "step": 2309
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014597665936499706,
      "loss": 0.8502,
      "step": 2310
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014593088785312507,
      "loss": 0.8559,
      "step": 2311
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014588510414252195,
      "loss": 0.835,
      "step": 2312
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014583930824534728,
      "loss": 0.8538,
      "step": 2313
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014579350017376402,
      "loss": 0.8246,
      "step": 2314
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014574767993993828,
      "loss": 0.8356,
      "step": 2315
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014570184755603936,
      "loss": 0.8573,
      "step": 2316
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001456560030342398,
      "loss": 0.8683,
      "step": 2317
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00014561014638671548,
      "loss": 0.8528,
      "step": 2318
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001455642776256454,
      "loss": 0.8541,
      "step": 2319
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001455183967632117,
      "loss": 0.8487,
      "step": 2320
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014547250381159992,
      "loss": 0.8798,
      "step": 2321
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001454265987829987,
      "loss": 0.8909,
      "step": 2322
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014538068168959986,
      "loss": 0.8635,
      "step": 2323
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014533475254359848,
      "loss": 0.8657,
      "step": 2324
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001452888113571929,
      "loss": 0.9012,
      "step": 2325
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001452428581425845,
      "loss": 0.867,
      "step": 2326
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014519689291197794,
      "loss": 0.8634,
      "step": 2327
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014515091567758115,
      "loss": 0.8558,
      "step": 2328
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001451049264516051,
      "loss": 0.8778,
      "step": 2329
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.000145058925246264,
      "loss": 0.8634,
      "step": 2330
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014501291207377537,
      "loss": 0.8767,
      "step": 2331
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014496688694635968,
      "loss": 0.8657,
      "step": 2332
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00014492084987624071,
      "loss": 0.8201,
      "step": 2333
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014487480087564547,
      "loss": 0.8513,
      "step": 2334
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014482873995680392,
      "loss": 0.8547,
      "step": 2335
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014478266713194947,
      "loss": 0.8512,
      "step": 2336
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001447365824133185,
      "loss": 0.845,
      "step": 2337
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014469048581315053,
      "loss": 0.8218,
      "step": 2338
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001446443773436884,
      "loss": 0.8384,
      "step": 2339
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001445982570171779,
      "loss": 0.8447,
      "step": 2340
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014455212484586818,
      "loss": 0.8581,
      "step": 2341
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014450598084201136,
      "loss": 0.8581,
      "step": 2342
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014445982501786283,
      "loss": 0.8338,
      "step": 2343
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000144413657385681,
      "loss": 0.8864,
      "step": 2344
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00014436747795772752,
      "loss": 0.8714,
      "step": 2345
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014432128674626713,
      "loss": 0.8377,
      "step": 2346
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014427508376356767,
      "loss": 0.8445,
      "step": 2347
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.8803,
      "step": 2348
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001441826425335387,
      "loss": 0.8594,
      "step": 2349
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014413640431076055,
      "loss": 0.8422,
      "step": 2350
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014409015436584602,
      "loss": 0.8443,
      "step": 2351
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014404389271107865,
      "loss": 0.8636,
      "step": 2352
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.000143997619358745,
      "loss": 0.8312,
      "step": 2353
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014395133432113473,
      "loss": 0.8582,
      "step": 2354
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014390503761054066,
      "loss": 0.8632,
      "step": 2355
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014385872923925862,
      "loss": 0.8252,
      "step": 2356
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014381240921958768,
      "loss": 0.8474,
      "step": 2357
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00014376607756382985,
      "loss": 0.8466,
      "step": 2358
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014371973428429032,
      "loss": 0.8976,
      "step": 2359
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014367337939327738,
      "loss": 0.8687,
      "step": 2360
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014362701290310235,
      "loss": 0.8658,
      "step": 2361
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014358063482607962,
      "loss": 0.8542,
      "step": 2362
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014353424517452674,
      "loss": 0.8735,
      "step": 2363
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014348784396076426,
      "loss": 0.8563,
      "step": 2364
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014344143119711584,
      "loss": 0.8599,
      "step": 2365
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014339500689590815,
      "loss": 0.8625,
      "step": 2366
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014334857106947105,
      "loss": 0.8764,
      "step": 2367
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014330212373013727,
      "loss": 0.8582,
      "step": 2368
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00014325566489024275,
      "loss": 0.8685,
      "step": 2369
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001432091945621265,
      "loss": 0.8277,
      "step": 2370
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014316271275813044,
      "loss": 0.8397,
      "step": 2371
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014311621949059962,
      "loss": 0.8386,
      "step": 2372
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014306971477188223,
      "loss": 0.8431,
      "step": 2373
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014302319861432926,
      "loss": 0.8633,
      "step": 2374
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014297667103029498,
      "loss": 0.8344,
      "step": 2375
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014293013203213662,
      "loss": 0.8452,
      "step": 2376
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001428835816322143,
      "loss": 0.838,
      "step": 2377
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001428370198428914,
      "loss": 0.8401,
      "step": 2378
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014279044667653415,
      "loss": 0.8633,
      "step": 2379
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014274386214551185,
      "loss": 0.8231,
      "step": 2380
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014269726626219692,
      "loss": 0.8494,
      "step": 2381
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014265065903896462,
      "loss": 0.8213,
      "step": 2382
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00014260404048819337,
      "loss": 0.844,
      "step": 2383
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014255741062226446,
      "loss": 0.8393,
      "step": 2384
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014251076945356232,
      "loss": 0.8592,
      "step": 2385
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014246411699447435,
      "loss": 0.8376,
      "step": 2386
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014241745325739084,
      "loss": 0.8164,
      "step": 2387
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001423707782547052,
      "loss": 0.8324,
      "step": 2388
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014232409199881386,
      "loss": 0.847,
      "step": 2389
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.000142277394502116,
      "loss": 0.8487,
      "step": 2390
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001422306857770141,
      "loss": 0.8478,
      "step": 2391
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014218396583591343,
      "loss": 0.875,
      "step": 2392
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001421372346912223,
      "loss": 0.8618,
      "step": 2393
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014209049235535193,
      "loss": 0.8403,
      "step": 2394
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014204373884071662,
      "loss": 0.8526,
      "step": 2395
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00014199697415973357,
      "loss": 0.8627,
      "step": 2396
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001419501983248229,
      "loss": 0.8731,
      "step": 2397
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014190341134840784,
      "loss": 0.8621,
      "step": 2398
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014185661324291445,
      "loss": 0.8809,
      "step": 2399
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014180980402077174,
      "loss": 0.8739,
      "step": 2400
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014176298369441176,
      "loss": 0.8744,
      "step": 2401
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014171615227626946,
      "loss": 0.8415,
      "step": 2402
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014166930977878276,
      "loss": 0.8641,
      "step": 2403
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001416224562143925,
      "loss": 0.845,
      "step": 2404
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014157559159554242,
      "loss": 0.8213,
      "step": 2405
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001415287159346793,
      "loss": 0.817,
      "step": 2406
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014148182924425277,
      "loss": 0.8633,
      "step": 2407
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00014143493153671537,
      "loss": 0.8472,
      "step": 2408
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014138802282452268,
      "loss": 0.8369,
      "step": 2409
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014134110312013308,
      "loss": 0.8524,
      "step": 2410
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014129417243600792,
      "loss": 0.8542,
      "step": 2411
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014124723078461147,
      "loss": 0.8734,
      "step": 2412
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014120027817841096,
      "loss": 0.8586,
      "step": 2413
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001411533146298764,
      "loss": 0.8563,
      "step": 2414
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014110634015148082,
      "loss": 0.8789,
      "step": 2415
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014105935475570015,
      "loss": 0.859,
      "step": 2416
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014101235845501316,
      "loss": 0.8446,
      "step": 2417
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014096535126190149,
      "loss": 0.8809,
      "step": 2418
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001409183331888498,
      "loss": 0.8439,
      "step": 2419
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014087130424834553,
      "loss": 0.8597,
      "step": 2420
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00014082426445287903,
      "loss": 0.8579,
      "step": 2421
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014077721381494359,
      "loss": 0.8611,
      "step": 2422
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014073015234703534,
      "loss": 0.8429,
      "step": 2423
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014068308006165317,
      "loss": 0.8543,
      "step": 2424
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014063599697129912,
      "loss": 0.8581,
      "step": 2425
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001405889030884778,
      "loss": 0.8585,
      "step": 2426
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001405417984256969,
      "loss": 0.8491,
      "step": 2427
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001404946829954668,
      "loss": 0.8524,
      "step": 2428
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014044755681030092,
      "loss": 0.8802,
      "step": 2429
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014040041988271543,
      "loss": 0.8516,
      "step": 2430
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014035327222522933,
      "loss": 0.8697,
      "step": 2431
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014030611385036456,
      "loss": 0.8625,
      "step": 2432
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00014025894477064584,
      "loss": 0.8554,
      "step": 2433
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001402117649986008,
      "loss": 0.8696,
      "step": 2434
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00014016457454675977,
      "loss": 0.8622,
      "step": 2435
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00014011737342765603,
      "loss": 0.8431,
      "step": 2436
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00014007016165382572,
      "loss": 0.8687,
      "step": 2437
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001400229392378077,
      "loss": 0.871,
      "step": 2438
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001399757061921438,
      "loss": 0.8478,
      "step": 2439
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001399284625293785,
      "loss": 0.8535,
      "step": 2440
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013988120826205925,
      "loss": 0.8362,
      "step": 2441
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013983394340273618,
      "loss": 0.8442,
      "step": 2442
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013978666796396241,
      "loss": 0.8456,
      "step": 2443
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013973938195829371,
      "loss": 0.868,
      "step": 2444
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013969208539828872,
      "loss": 0.8575,
      "step": 2445
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001396447782965089,
      "loss": 0.8423,
      "step": 2446
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013959746066551847,
      "loss": 0.8385,
      "step": 2447
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013955013251788447,
      "loss": 0.8548,
      "step": 2448
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001395027938661767,
      "loss": 0.8735,
      "step": 2449
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013945544472296781,
      "loss": 0.8422,
      "step": 2450
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013940808510083322,
      "loss": 0.822,
      "step": 2451
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013936071501235105,
      "loss": 0.859,
      "step": 2452
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013931333447010234,
      "loss": 0.8548,
      "step": 2453
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001392659434866708,
      "loss": 0.8476,
      "step": 2454
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013921854207464294,
      "loss": 0.8156,
      "step": 2455
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001391711302466081,
      "loss": 0.8426,
      "step": 2456
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013912370801515822,
      "loss": 0.8547,
      "step": 2457
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00013907627539288823,
      "loss": 0.8275,
      "step": 2458
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013902883239239565,
      "loss": 0.8661,
      "step": 2459
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013898137902628078,
      "loss": 0.8505,
      "step": 2460
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001389339153071468,
      "loss": 0.853,
      "step": 2461
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013888644124759945,
      "loss": 0.8242,
      "step": 2462
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013883895686024738,
      "loss": 0.8432,
      "step": 2463
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013879146215770184,
      "loss": 0.8741,
      "step": 2464
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.000138743957152577,
      "loss": 0.847,
      "step": 2465
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013869644185748954,
      "loss": 0.8557,
      "step": 2466
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013864891628505906,
      "loss": 0.8272,
      "step": 2467
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001386013804479078,
      "loss": 0.8435,
      "step": 2468
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013855383435866077,
      "loss": 0.8466,
      "step": 2469
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013850627802994563,
      "loss": 0.8444,
      "step": 2470
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013845871147439288,
      "loss": 0.8352,
      "step": 2471
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013841113470463562,
      "loss": 0.8341,
      "step": 2472
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001383635477333097,
      "loss": 0.8457,
      "step": 2473
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013831595057305375,
      "loss": 0.8396,
      "step": 2474
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.000138268343236509,
      "loss": 0.8406,
      "step": 2475
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001382207257363194,
      "loss": 0.8464,
      "step": 2476
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013817309808513168,
      "loss": 0.8759,
      "step": 2477
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001381254602955952,
      "loss": 0.831,
      "step": 2478
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.000138077812380362,
      "loss": 0.844,
      "step": 2479
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013803015435208684,
      "loss": 0.8893,
      "step": 2480
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013798248622342717,
      "loss": 0.8742,
      "step": 2481
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013793480800704312,
      "loss": 0.8694,
      "step": 2482
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001378871197155975,
      "loss": 0.8782,
      "step": 2483
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00013783942136175574,
      "loss": 0.8544,
      "step": 2484
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013779171295818604,
      "loss": 0.8507,
      "step": 2485
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013774399451755922,
      "loss": 0.833,
      "step": 2486
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013769626605254876,
      "loss": 0.8657,
      "step": 2487
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013764852757583074,
      "loss": 0.839,
      "step": 2488
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013760077910008405,
      "loss": 0.8354,
      "step": 2489
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013755302063799013,
      "loss": 0.8777,
      "step": 2490
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013750525220223306,
      "loss": 0.8512,
      "step": 2491
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013745747380549967,
      "loss": 0.8452,
      "step": 2492
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013740968546047935,
      "loss": 0.8739,
      "step": 2493
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013736188717986407,
      "loss": 0.8588,
      "step": 2494
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013731407897634863,
      "loss": 0.8542,
      "step": 2495
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00013726626086263028,
      "loss": 0.8671,
      "step": 2496
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000137218432851409,
      "loss": 0.8617,
      "step": 2497
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001371705949553874,
      "loss": 0.8312,
      "step": 2498
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013712274718727065,
      "loss": 0.8446,
      "step": 2499
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013707488955976664,
      "loss": 0.8554,
      "step": 2500
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001370270220855858,
      "loss": 0.8971,
      "step": 2501
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001369791447774411,
      "loss": 0.8548,
      "step": 2502
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013693125764804837,
      "loss": 0.844,
      "step": 2503
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013688336071012583,
      "loss": 0.856,
      "step": 2504
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013683545397639432,
      "loss": 0.8943,
      "step": 2505
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013678753745957742,
      "loss": 0.8937,
      "step": 2506
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013673961117240116,
      "loss": 0.8417,
      "step": 2507
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001366916751275943,
      "loss": 0.8437,
      "step": 2508
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013664372933788803,
      "loss": 0.832,
      "step": 2509
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001365957738160163,
      "loss": 0.8687,
      "step": 2510
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013654780857471548,
      "loss": 0.8366,
      "step": 2511
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013649983362672464,
      "loss": 0.8492,
      "step": 2512
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001364518489847854,
      "loss": 0.8428,
      "step": 2513
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.000136403854661642,
      "loss": 0.8692,
      "step": 2514
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013635585067004106,
      "loss": 0.8715,
      "step": 2515
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013630783702273203,
      "loss": 0.8439,
      "step": 2516
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001362598137324667,
      "loss": 0.8345,
      "step": 2517
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013621178081199963,
      "loss": 0.8593,
      "step": 2518
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001361637382740877,
      "loss": 0.8484,
      "step": 2519
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013611568613149057,
      "loss": 0.8501,
      "step": 2520
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013606762439697032,
      "loss": 0.8521,
      "step": 2521
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001360195530832916,
      "loss": 0.841,
      "step": 2522
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013597147220322165,
      "loss": 0.8604,
      "step": 2523
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013592338176953017,
      "loss": 0.8375,
      "step": 2524
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013587528179498945,
      "loss": 0.8266,
      "step": 2525
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013582717229237434,
      "loss": 0.8277,
      "step": 2526
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013577905327446214,
      "loss": 0.8331,
      "step": 2527
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001357309247540328,
      "loss": 0.828,
      "step": 2528
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013568278674386863,
      "loss": 0.8359,
      "step": 2529
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013563463925675458,
      "loss": 0.8572,
      "step": 2530
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013558648230547812,
      "loss": 0.8935,
      "step": 2531
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013553831590282914,
      "loss": 0.8559,
      "step": 2532
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013549014006160014,
      "loss": 0.8517,
      "step": 2533
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00013544195479458607,
      "loss": 0.8301,
      "step": 2534
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013539376011458443,
      "loss": 0.8257,
      "step": 2535
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013534555603439514,
      "loss": 0.8289,
      "step": 2536
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013529734256682068,
      "loss": 0.85,
      "step": 2537
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013524911972466602,
      "loss": 0.8745,
      "step": 2538
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013520088752073863,
      "loss": 0.8628,
      "step": 2539
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001351526459678484,
      "loss": 0.8524,
      "step": 2540
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013510439507880776,
      "loss": 0.8428,
      "step": 2541
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013505613486643165,
      "loss": 0.8548,
      "step": 2542
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001350078653435374,
      "loss": 0.8441,
      "step": 2543
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013495958652294486,
      "loss": 0.85,
      "step": 2544
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013491129841747631,
      "loss": 0.8363,
      "step": 2545
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00013486300103995663,
      "loss": 0.8726,
      "step": 2546
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.000134814694403213,
      "loss": 0.9038,
      "step": 2547
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001347663785200751,
      "loss": 0.8725,
      "step": 2548
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013471805340337515,
      "loss": 0.8371,
      "step": 2549
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013466971906594773,
      "loss": 0.8625,
      "step": 2550
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001346213755206299,
      "loss": 0.8651,
      "step": 2551
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013457302278026116,
      "loss": 0.834,
      "step": 2552
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013452466085768348,
      "loss": 0.8467,
      "step": 2553
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013447628976574123,
      "loss": 0.8409,
      "step": 2554
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013442790951728124,
      "loss": 0.8419,
      "step": 2555
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013437952012515275,
      "loss": 0.825,
      "step": 2556
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013433112160220746,
      "loss": 0.8353,
      "step": 2557
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013428271396129948,
      "loss": 0.8589,
      "step": 2558
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013423429721528532,
      "loss": 0.8317,
      "step": 2559
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001341858713770239,
      "loss": 0.8555,
      "step": 2560
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001341374364593767,
      "loss": 0.8533,
      "step": 2561
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013408899247520733,
      "loss": 0.8641,
      "step": 2562
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013404053943738212,
      "loss": 0.8692,
      "step": 2563
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013399207735876955,
      "loss": 0.8474,
      "step": 2564
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013394360625224068,
      "loss": 0.8359,
      "step": 2565
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013389512613066882,
      "loss": 0.8408,
      "step": 2566
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013384663700692984,
      "loss": 0.8596,
      "step": 2567
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013379813889390183,
      "loss": 0.8437,
      "step": 2568
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013374963180446536,
      "loss": 0.851,
      "step": 2569
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013370111575150342,
      "loss": 0.8928,
      "step": 2570
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00013365259074790128,
      "loss": 0.8306,
      "step": 2571
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001336040568065467,
      "loss": 0.8294,
      "step": 2572
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013355551394032968,
      "loss": 0.8308,
      "step": 2573
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001335069621621427,
      "loss": 0.8403,
      "step": 2574
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013345840148488061,
      "loss": 0.8264,
      "step": 2575
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013340983192144048,
      "loss": 0.8364,
      "step": 2576
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013336125348472193,
      "loss": 0.8219,
      "step": 2577
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013331266618762686,
      "loss": 0.8283,
      "step": 2578
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013326407004305942,
      "loss": 0.8541,
      "step": 2579
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013321546506392634,
      "loss": 0.8498,
      "step": 2580
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00013316685126313642,
      "loss": 0.8343,
      "step": 2581
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.000133118228653601,
      "loss": 0.842,
      "step": 2582
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001330695972482338,
      "loss": 0.8391,
      "step": 2583
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001330209570599506,
      "loss": 0.8532,
      "step": 2584
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013297230810166977,
      "loss": 0.8472,
      "step": 2585
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013292365038631201,
      "loss": 0.8568,
      "step": 2586
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013287498392680014,
      "loss": 0.8628,
      "step": 2587
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013282630873605954,
      "loss": 0.8325,
      "step": 2588
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013277762482701767,
      "loss": 0.845,
      "step": 2589
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013272893221260456,
      "loss": 0.8441,
      "step": 2590
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013268023090575235,
      "loss": 0.8286,
      "step": 2591
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013263152091939556,
      "loss": 0.8479,
      "step": 2592
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013258280226647107,
      "loss": 0.8476,
      "step": 2593
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013253407495991798,
      "loss": 0.8335,
      "step": 2594
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0001324853390126777,
      "loss": 0.8565,
      "step": 2595
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013243659443769402,
      "loss": 0.8804,
      "step": 2596
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00013238784124791286,
      "loss": 0.8693,
      "step": 2597
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001323390794562826,
      "loss": 0.8391,
      "step": 2598
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013229030907575378,
      "loss": 0.8439,
      "step": 2599
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001322415301192793,
      "loss": 0.8382,
      "step": 2600
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001321927425998143,
      "loss": 0.8513,
      "step": 2601
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.8647,
      "step": 2602
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013209514192374464,
      "loss": 0.8608,
      "step": 2603
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013204632879306165,
      "loss": 0.8629,
      "step": 2604
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013199750715123145,
      "loss": 0.8646,
      "step": 2605
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001319486770112205,
      "loss": 0.8336,
      "step": 2606
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001318998383859975,
      "loss": 0.8515,
      "step": 2607
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013185099128853352,
      "loss": 0.8522,
      "step": 2608
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00013180213573180178,
      "loss": 0.8356,
      "step": 2609
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013175327172877771,
      "loss": 0.8491,
      "step": 2610
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013170439929243913,
      "loss": 0.8374,
      "step": 2611
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.000131655518435766,
      "loss": 0.8239,
      "step": 2612
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013160662917174044,
      "loss": 0.8695,
      "step": 2613
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013155773151334705,
      "loss": 0.8622,
      "step": 2614
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013150882547357235,
      "loss": 0.8387,
      "step": 2615
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001314599110654053,
      "loss": 0.8469,
      "step": 2616
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013141098830183703,
      "loss": 0.8542,
      "step": 2617
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001313620571958609,
      "loss": 0.8449,
      "step": 2618
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013131311776047236,
      "loss": 0.8417,
      "step": 2619
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013126417000866933,
      "loss": 0.8546,
      "step": 2620
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013121521395345167,
      "loss": 0.8483,
      "step": 2621
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00013116624960782163,
      "loss": 0.8762,
      "step": 2622
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013111727698478356,
      "loss": 0.8508,
      "step": 2623
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013106829609734404,
      "loss": 0.8332,
      "step": 2624
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013101930695851185,
      "loss": 0.8487,
      "step": 2625
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013097030958129796,
      "loss": 0.8562,
      "step": 2626
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013092130397871556,
      "loss": 0.8273,
      "step": 2627
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013087229016377994,
      "loss": 0.8463,
      "step": 2628
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013082326814950864,
      "loss": 0.8405,
      "step": 2629
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013077423794892137,
      "loss": 0.8204,
      "step": 2630
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013072519957504,
      "loss": 0.8455,
      "step": 2631
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013067615304088856,
      "loss": 0.8416,
      "step": 2632
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001306270983594933,
      "loss": 0.8498,
      "step": 2633
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013057803554388252,
      "loss": 0.8495,
      "step": 2634
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013052896460708687,
      "loss": 0.8313,
      "step": 2635
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013047988556213894,
      "loss": 0.8371,
      "step": 2636
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001304307984220736,
      "loss": 0.8402,
      "step": 2637
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013038170319992792,
      "loss": 0.8257,
      "step": 2638
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013033259990874094,
      "loss": 0.8558,
      "step": 2639
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.000130283488561554,
      "loss": 0.8422,
      "step": 2640
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013023436917141052,
      "loss": 0.8597,
      "step": 2641
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013018524175135608,
      "loss": 0.8326,
      "step": 2642
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001301361063144383,
      "loss": 0.8375,
      "step": 2643
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001300869628737071,
      "loss": 0.8293,
      "step": 2644
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001300378114422144,
      "loss": 0.8442,
      "step": 2645
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001299886520330142,
      "loss": 0.8423,
      "step": 2646
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001299394846591628,
      "loss": 0.8806,
      "step": 2647
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012989030933371844,
      "loss": 0.865,
      "step": 2648
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012984112606974154,
      "loss": 0.8382,
      "step": 2649
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012979193488029463,
      "loss": 0.8333,
      "step": 2650
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012974273577844237,
      "loss": 0.8463,
      "step": 2651
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012969352877725148,
      "loss": 0.8448,
      "step": 2652
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012964431388979075,
      "loss": 0.8482,
      "step": 2653
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012959509112913116,
      "loss": 0.8309,
      "step": 2654
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012954586050834568,
      "loss": 0.8701,
      "step": 2655
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012949662204050943,
      "loss": 0.8423,
      "step": 2656
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00012944737573869963,
      "loss": 0.8479,
      "step": 2657
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001293981216159955,
      "loss": 0.8521,
      "step": 2658
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001293488596854784,
      "loss": 0.8484,
      "step": 2659
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001292995899602318,
      "loss": 0.8412,
      "step": 2660
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001292503124533411,
      "loss": 0.8311,
      "step": 2661
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012920102717789387,
      "loss": 0.8376,
      "step": 2662
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012915173414697982,
      "loss": 0.8335,
      "step": 2663
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012910243337369056,
      "loss": 0.8667,
      "step": 2664
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001290531248711198,
      "loss": 0.8236,
      "step": 2665
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001290038086523634,
      "loss": 0.8433,
      "step": 2666
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012895448473051912,
      "loss": 0.8485,
      "step": 2667
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001289051531186869,
      "loss": 0.8697,
      "step": 2668
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012885581382996865,
      "loss": 0.8544,
      "step": 2669
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001288064668774683,
      "loss": 0.8494,
      "step": 2670
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00012875711227429193,
      "loss": 0.8502,
      "step": 2671
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001287077500335475,
      "loss": 0.8523,
      "step": 2672
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012865838016834507,
      "loss": 0.8581,
      "step": 2673
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012860900269179675,
      "loss": 0.8746,
      "step": 2674
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012855961761701668,
      "loss": 0.8773,
      "step": 2675
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001285102249571209,
      "loss": 0.8432,
      "step": 2676
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012846082472522762,
      "loss": 0.8724,
      "step": 2677
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012841141693445697,
      "loss": 0.8678,
      "step": 2678
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012836200159793113,
      "loss": 0.8558,
      "step": 2679
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001283125787287742,
      "loss": 0.8284,
      "step": 2680
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012826314834011237,
      "loss": 0.847,
      "step": 2681
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012821371044507385,
      "loss": 0.8297,
      "step": 2682
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00012816426505678872,
      "loss": 0.8569,
      "step": 2683
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001281148121883892,
      "loss": 0.8573,
      "step": 2684
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001280653518530093,
      "loss": 0.8492,
      "step": 2685
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012801588406378525,
      "loss": 0.832,
      "step": 2686
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012796640883385514,
      "loss": 0.8316,
      "step": 2687
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012791692617635894,
      "loss": 0.8659,
      "step": 2688
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001278674361044388,
      "loss": 0.848,
      "step": 2689
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012781793863123864,
      "loss": 0.8491,
      "step": 2690
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001277684337699045,
      "loss": 0.806,
      "step": 2691
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012771892153358428,
      "loss": 0.8284,
      "step": 2692
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001276694019354279,
      "loss": 0.849,
      "step": 2693
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001276198749885872,
      "loss": 0.8437,
      "step": 2694
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012757034070621603,
      "loss": 0.836,
      "step": 2695
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012752079910147008,
      "loss": 0.84,
      "step": 2696
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00012747125018750706,
      "loss": 0.8208,
      "step": 2697
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012742169397748663,
      "loss": 0.814,
      "step": 2698
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012737213048457036,
      "loss": 0.8241,
      "step": 2699
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012732255972192175,
      "loss": 0.8603,
      "step": 2700
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012727298170270624,
      "loss": 0.8614,
      "step": 2701
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012722339644009122,
      "loss": 0.8567,
      "step": 2702
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012717380394724597,
      "loss": 0.8333,
      "step": 2703
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001271242042373417,
      "loss": 0.8319,
      "step": 2704
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001270745973235515,
      "loss": 0.8472,
      "step": 2705
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001270249832190505,
      "loss": 0.8571,
      "step": 2706
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001269753619370156,
      "loss": 0.8428,
      "step": 2707
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012692573349062564,
      "loss": 0.8445,
      "step": 2708
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00012687609789306144,
      "loss": 0.8481,
      "step": 2709
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001268264551575056,
      "loss": 0.8678,
      "step": 2710
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012677680529714268,
      "loss": 0.85,
      "step": 2711
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012672714832515918,
      "loss": 0.8698,
      "step": 2712
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012667748425474344,
      "loss": 0.8472,
      "step": 2713
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012662781309908557,
      "loss": 0.8694,
      "step": 2714
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012657813487137784,
      "loss": 0.8572,
      "step": 2715
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001265284495848141,
      "loss": 0.839,
      "step": 2716
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012647875725259027,
      "loss": 0.8258,
      "step": 2717
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012642905788790408,
      "loss": 0.8532,
      "step": 2718
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012637935150395507,
      "loss": 0.8249,
      "step": 2719
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001263296381139448,
      "loss": 0.8642,
      "step": 2720
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001262799177310765,
      "loss": 0.8352,
      "step": 2721
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012623019036855538,
      "loss": 0.8338,
      "step": 2722
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00012618045603958849,
      "loss": 0.8445,
      "step": 2723
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012613071475738467,
      "loss": 0.8068,
      "step": 2724
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012608096653515469,
      "loss": 0.8181,
      "step": 2725
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012603121138611112,
      "loss": 0.8312,
      "step": 2726
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012598144932346835,
      "loss": 0.8326,
      "step": 2727
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012593168036044268,
      "loss": 0.8628,
      "step": 2728
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.9016,
      "step": 2729
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012583212178611658,
      "loss": 0.8795,
      "step": 2730
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012578233220125786,
      "loss": 0.8627,
      "step": 2731
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012573253576889944,
      "loss": 0.8582,
      "step": 2732
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001256827325022668,
      "loss": 0.8453,
      "step": 2733
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012563292241458707,
      "loss": 0.8627,
      "step": 2734
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012558310551908923,
      "loss": 0.8648,
      "step": 2735
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012553328182900414,
      "loss": 0.8595,
      "step": 2736
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012548345135756438,
      "loss": 0.8542,
      "step": 2737
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001254336141180044,
      "loss": 0.8335,
      "step": 2738
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012538377012356037,
      "loss": 0.8286,
      "step": 2739
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012533391938747033,
      "loss": 0.8491,
      "step": 2740
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012528406192297407,
      "loss": 0.8592,
      "step": 2741
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001252341977433132,
      "loss": 0.8432,
      "step": 2742
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012518432686173104,
      "loss": 0.8401,
      "step": 2743
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001251344492914728,
      "loss": 0.8505,
      "step": 2744
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012508456504578539,
      "loss": 0.863,
      "step": 2745
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012503467413791744,
      "loss": 0.847,
      "step": 2746
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001249847765811195,
      "loss": 0.8427,
      "step": 2747
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00012493487238864377,
      "loss": 0.856,
      "step": 2748
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012488496157374426,
      "loss": 0.8403,
      "step": 2749
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001248350441496767,
      "loss": 0.851,
      "step": 2750
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012478512012969862,
      "loss": 0.8687,
      "step": 2751
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001247351895270693,
      "loss": 0.8387,
      "step": 2752
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001246852523550497,
      "loss": 0.8303,
      "step": 2753
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012463530862690268,
      "loss": 0.846,
      "step": 2754
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012458535835589257,
      "loss": 0.8305,
      "step": 2755
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012453540155528574,
      "loss": 0.8336,
      "step": 2756
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012448543823835015,
      "loss": 0.8358,
      "step": 2757
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001244354684183554,
      "loss": 0.8392,
      "step": 2758
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012438549210857304,
      "loss": 0.8511,
      "step": 2759
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00012433550932227613,
      "loss": 0.8411,
      "step": 2760
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012428552007273956,
      "loss": 0.8387,
      "step": 2761
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012423552437323997,
      "loss": 0.8432,
      "step": 2762
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001241855222370556,
      "loss": 0.84,
      "step": 2763
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012413551367746646,
      "loss": 0.8189,
      "step": 2764
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012408549870775433,
      "loss": 0.8522,
      "step": 2765
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012403547734120252,
      "loss": 0.8605,
      "step": 2766
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012398544959109627,
      "loss": 0.8243,
      "step": 2767
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001239354154707223,
      "loss": 0.8471,
      "step": 2768
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012388537499336913,
      "loss": 0.8661,
      "step": 2769
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.000123835328172327,
      "loss": 0.8477,
      "step": 2770
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001237852750208877,
      "loss": 0.8761,
      "step": 2771
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001237352155523449,
      "loss": 0.8274,
      "step": 2772
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00012368514977999375,
      "loss": 0.8233,
      "step": 2773
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012363507771713118,
      "loss": 0.8439,
      "step": 2774
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001235849993770558,
      "loss": 0.8561,
      "step": 2775
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012353491477306783,
      "loss": 0.8584,
      "step": 2776
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001234848239184692,
      "loss": 0.8586,
      "step": 2777
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012343472682656344,
      "loss": 0.8288,
      "step": 2778
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012338462351065582,
      "loss": 0.837,
      "step": 2779
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012333451398405322,
      "loss": 0.8463,
      "step": 2780
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012328439826006415,
      "loss": 0.8544,
      "step": 2781
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001232342763519988,
      "loss": 0.8536,
      "step": 2782
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.000123184148273169,
      "loss": 0.8678,
      "step": 2783
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001231340140368882,
      "loss": 0.8532,
      "step": 2784
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00012308387365647148,
      "loss": 0.8617,
      "step": 2785
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012303372714523558,
      "loss": 0.8508,
      "step": 2786
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001229835745164988,
      "loss": 0.8505,
      "step": 2787
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012293341578358127,
      "loss": 0.8668,
      "step": 2788
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001228832509598044,
      "loss": 0.8304,
      "step": 2789
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012283308005849153,
      "loss": 0.8378,
      "step": 2790
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012278290309296745,
      "loss": 0.8346,
      "step": 2791
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001227327200765586,
      "loss": 0.8505,
      "step": 2792
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012268253102259302,
      "loss": 0.8389,
      "step": 2793
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012263233594440043,
      "loss": 0.8424,
      "step": 2794
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012258213485531196,
      "loss": 0.8184,
      "step": 2795
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012253192776866059,
      "loss": 0.8388,
      "step": 2796
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012248171469778066,
      "loss": 0.8368,
      "step": 2797
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00012243149565600828,
      "loss": 0.8422,
      "step": 2798
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.000122381270656681,
      "loss": 0.8353,
      "step": 2799
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001223310397131381,
      "loss": 0.8366,
      "step": 2800
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012228080283872026,
      "loss": 0.8966,
      "step": 2801
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012223056004676986,
      "loss": 0.8557,
      "step": 2802
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001221803113506309,
      "loss": 0.828,
      "step": 2803
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001221300567636488,
      "loss": 0.8514,
      "step": 2804
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001220797962991706,
      "loss": 0.8406,
      "step": 2805
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012202952997054504,
      "loss": 0.8173,
      "step": 2806
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012197925779112214,
      "loss": 0.8299,
      "step": 2807
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001219289797742537,
      "loss": 0.8548,
      "step": 2808
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012187869593329302,
      "loss": 0.87,
      "step": 2809
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012182840628159489,
      "loss": 0.8573,
      "step": 2810
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00012177811083251572,
      "loss": 0.8642,
      "step": 2811
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012172780959941338,
      "loss": 0.8487,
      "step": 2812
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012167750259564732,
      "loss": 0.841,
      "step": 2813
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012162718983457855,
      "loss": 0.8793,
      "step": 2814
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012157687132956956,
      "loss": 0.8806,
      "step": 2815
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012152654709398439,
      "loss": 0.8382,
      "step": 2816
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012147621714118855,
      "loss": 0.8325,
      "step": 2817
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012142588148454918,
      "loss": 0.8568,
      "step": 2818
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012137554013743484,
      "loss": 0.8618,
      "step": 2819
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012132519311321561,
      "loss": 0.8392,
      "step": 2820
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012127484042526313,
      "loss": 0.8329,
      "step": 2821
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012122448208695052,
      "loss": 0.8351,
      "step": 2822
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012117411811165234,
      "loss": 0.8335,
      "step": 2823
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012112374851274477,
      "loss": 0.8384,
      "step": 2824
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012107337330360532,
      "loss": 0.833,
      "step": 2825
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012102299249761316,
      "loss": 0.8507,
      "step": 2826
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012097260610814884,
      "loss": 0.8537,
      "step": 2827
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012092221414859447,
      "loss": 0.8303,
      "step": 2828
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012087181663233354,
      "loss": 0.8354,
      "step": 2829
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012082141357275102,
      "loss": 0.838,
      "step": 2830
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012077100498323352,
      "loss": 0.8147,
      "step": 2831
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012072059087716894,
      "loss": 0.8497,
      "step": 2832
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012067017126794666,
      "loss": 0.8357,
      "step": 2833
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012061974616895765,
      "loss": 0.8237,
      "step": 2834
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00012056931559359422,
      "loss": 0.8498,
      "step": 2835
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001205188795552501,
      "loss": 0.8446,
      "step": 2836
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012046843806732067,
      "loss": 0.8491,
      "step": 2837
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012041799114320249,
      "loss": 0.8237,
      "step": 2838
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012036753879629382,
      "loss": 0.837,
      "step": 2839
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012031708103999415,
      "loss": 0.8125,
      "step": 2840
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012026661788770452,
      "loss": 0.8336,
      "step": 2841
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012021614935282742,
      "loss": 0.8311,
      "step": 2842
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012016567544876669,
      "loss": 0.8231,
      "step": 2843
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012011519618892764,
      "loss": 0.824,
      "step": 2844
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012006471158671702,
      "loss": 0.8382,
      "step": 2845
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00012001422165554297,
      "loss": 0.8186,
      "step": 2846
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00011996372640881502,
      "loss": 0.8639,
      "step": 2847
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00011991322585994415,
      "loss": 0.8658,
      "step": 2848
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001198627200223428,
      "loss": 0.866,
      "step": 2849
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011981220890942471,
      "loss": 0.845,
      "step": 2850
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011976169253460506,
      "loss": 0.8204,
      "step": 2851
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011971117091130045,
      "loss": 0.8381,
      "step": 2852
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011966064405292887,
      "loss": 0.8375,
      "step": 2853
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011961011197290965,
      "loss": 0.8277,
      "step": 2854
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011955957468466364,
      "loss": 0.8475,
      "step": 2855
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.8194,
      "step": 2856
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011945848453718085,
      "loss": 0.8415,
      "step": 2857
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011940793170479261,
      "loss": 0.8325,
      "step": 2858
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001193573737178743,
      "loss": 0.8229,
      "step": 2859
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011930681058985361,
      "loss": 0.8533,
      "step": 2860
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00011925624233415953,
      "loss": 0.8184,
      "step": 2861
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011920566896422238,
      "loss": 0.8402,
      "step": 2862
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011915509049347398,
      "loss": 0.8356,
      "step": 2863
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011910450693534731,
      "loss": 0.8557,
      "step": 2864
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011905391830327686,
      "loss": 0.8535,
      "step": 2865
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011900332461069839,
      "loss": 0.844,
      "step": 2866
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.000118952725871049,
      "loss": 0.8557,
      "step": 2867
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011890212209776717,
      "loss": 0.8859,
      "step": 2868
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011885151330429267,
      "loss": 0.8592,
      "step": 2869
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001188008995040667,
      "loss": 0.8749,
      "step": 2870
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011875028071053164,
      "loss": 0.8491,
      "step": 2871
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011869965693713132,
      "loss": 0.8396,
      "step": 2872
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00011864902819731086,
      "loss": 0.8288,
      "step": 2873
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011859839450451664,
      "loss": 0.8426,
      "step": 2874
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011854775587219642,
      "loss": 0.846,
      "step": 2875
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011849711231379932,
      "loss": 0.8111,
      "step": 2876
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001184464638427756,
      "loss": 0.8317,
      "step": 2877
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.000118395810472577,
      "loss": 0.838,
      "step": 2878
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011834515221665647,
      "loss": 0.8219,
      "step": 2879
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011829448908846827,
      "loss": 0.8368,
      "step": 2880
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011824382110146799,
      "loss": 0.8645,
      "step": 2881
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011819314826911243,
      "loss": 0.8592,
      "step": 2882
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011814247060485976,
      "loss": 0.8452,
      "step": 2883
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001180917881221694,
      "loss": 0.8229,
      "step": 2884
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011804110083450209,
      "loss": 0.8514,
      "step": 2885
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00011799040875531975,
      "loss": 0.859,
      "step": 2886
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011793971189808562,
      "loss": 0.849,
      "step": 2887
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011788901027626426,
      "loss": 0.8715,
      "step": 2888
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011783830390332149,
      "loss": 0.8647,
      "step": 2889
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011778759279272427,
      "loss": 0.8462,
      "step": 2890
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011773687695794096,
      "loss": 0.8359,
      "step": 2891
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011768615641244109,
      "loss": 0.8175,
      "step": 2892
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011763543116969548,
      "loss": 0.8556,
      "step": 2893
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011758470124317622,
      "loss": 0.8318,
      "step": 2894
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011753396664635659,
      "loss": 0.8492,
      "step": 2895
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011748322739271112,
      "loss": 0.8299,
      "step": 2896
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011743248349571559,
      "loss": 0.8492,
      "step": 2897
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011738173496884703,
      "loss": 0.8396,
      "step": 2898
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011733098182558369,
      "loss": 0.8316,
      "step": 2899
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.000117280224079405,
      "loss": 0.8335,
      "step": 2900
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011722946174379168,
      "loss": 0.8543,
      "step": 2901
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011717869483222563,
      "loss": 0.848,
      "step": 2902
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011712792335818999,
      "loss": 0.8319,
      "step": 2903
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011707714733516905,
      "loss": 0.8268,
      "step": 2904
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011702636677664844,
      "loss": 0.8316,
      "step": 2905
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011697558169611482,
      "loss": 0.8427,
      "step": 2906
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011692479210705622,
      "loss": 0.8508,
      "step": 2907
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011687399802296171,
      "loss": 0.8394,
      "step": 2908
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001168231994573217,
      "loss": 0.8562,
      "step": 2909
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011677239642362767,
      "loss": 0.8232,
      "step": 2910
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00011672158893537235,
      "loss": 0.848,
      "step": 2911
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011667077700604966,
      "loss": 0.835,
      "step": 2912
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001166199606491547,
      "loss": 0.8139,
      "step": 2913
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011656913987818368,
      "loss": 0.8253,
      "step": 2914
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011651831470663404,
      "loss": 0.8421,
      "step": 2915
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001164674851480044,
      "loss": 0.8637,
      "step": 2916
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011641665121579452,
      "loss": 0.8573,
      "step": 2917
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001163658129235053,
      "loss": 0.8217,
      "step": 2918
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011631497028463887,
      "loss": 0.8318,
      "step": 2919
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001162641233126984,
      "loss": 0.8335,
      "step": 2920
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011621327202118832,
      "loss": 0.8392,
      "step": 2921
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011616241642361418,
      "loss": 0.8352,
      "step": 2922
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011611155653348264,
      "loss": 0.8263,
      "step": 2923
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00011606069236430151,
      "loss": 0.8652,
      "step": 2924
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011600982392957978,
      "loss": 0.8531,
      "step": 2925
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011595895124282747,
      "loss": 0.8509,
      "step": 2926
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011590807431755584,
      "loss": 0.8515,
      "step": 2927
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011585719316727728,
      "loss": 0.8315,
      "step": 2928
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011580630780550516,
      "loss": 0.8297,
      "step": 2929
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011575541824575416,
      "loss": 0.8555,
      "step": 2930
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011570452450153993,
      "loss": 0.8302,
      "step": 2931
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011565362658637924,
      "loss": 0.8544,
      "step": 2932
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011560272451379009,
      "loss": 0.8424,
      "step": 2933
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011555181829729145,
      "loss": 0.8325,
      "step": 2934
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011550090795040345,
      "loss": 0.8564,
      "step": 2935
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011544999348664732,
      "loss": 0.8628,
      "step": 2936
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011539907491954538,
      "loss": 0.8492,
      "step": 2937
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011534815226262103,
      "loss": 0.8388,
      "step": 2938
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011529722552939872,
      "loss": 0.8582,
      "step": 2939
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011524629473340409,
      "loss": 0.8537,
      "step": 2940
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011519535988816374,
      "loss": 0.8745,
      "step": 2941
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001151444210072054,
      "loss": 0.8552,
      "step": 2942
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011509347810405788,
      "loss": 0.8306,
      "step": 2943
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011504253119225107,
      "loss": 0.8368,
      "step": 2944
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011499158028531585,
      "loss": 0.8389,
      "step": 2945
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001149406253967843,
      "loss": 0.8565,
      "step": 2946
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011488966654018934,
      "loss": 0.845,
      "step": 2947
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011483870372906517,
      "loss": 0.8506,
      "step": 2948
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00011478773697694691,
      "loss": 0.8563,
      "step": 2949
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011473676629737075,
      "loss": 0.8482,
      "step": 2950
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011468579170387399,
      "loss": 0.8335,
      "step": 2951
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011463481320999485,
      "loss": 0.8405,
      "step": 2952
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011458383082927266,
      "loss": 0.8264,
      "step": 2953
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011453284457524783,
      "loss": 0.8466,
      "step": 2954
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011448185446146165,
      "loss": 0.8518,
      "step": 2955
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011443086050145659,
      "loss": 0.8374,
      "step": 2956
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011437986270877605,
      "loss": 0.8687,
      "step": 2957
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011432886109696445,
      "loss": 0.8313,
      "step": 2958
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011427785567956735,
      "loss": 0.867,
      "step": 2959
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011422684647013109,
      "loss": 0.8552,
      "step": 2960
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011417583348220321,
      "loss": 0.8594,
      "step": 2961
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00011412481672933222,
      "loss": 0.8372,
      "step": 2962
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011407379622506753,
      "loss": 0.8344,
      "step": 2963
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011402277198295968,
      "loss": 0.8471,
      "step": 2964
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011397174401656008,
      "loss": 0.8493,
      "step": 2965
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011392071233942123,
      "loss": 0.8389,
      "step": 2966
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011386967696509656,
      "loss": 0.8522,
      "step": 2967
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011381863790714051,
      "loss": 0.8362,
      "step": 2968
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011376759517910848,
      "loss": 0.8526,
      "step": 2969
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011371654879455682,
      "loss": 0.8449,
      "step": 2970
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011366549876704293,
      "loss": 0.8598,
      "step": 2971
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001136144451101251,
      "loss": 0.8476,
      "step": 2972
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011356338783736255,
      "loss": 0.861,
      "step": 2973
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00011351232696231564,
      "loss": 0.8394,
      "step": 2974
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011346126249854551,
      "loss": 0.8249,
      "step": 2975
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011341019445961429,
      "loss": 0.8535,
      "step": 2976
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011335912285908514,
      "loss": 0.8415,
      "step": 2977
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011330804771052204,
      "loss": 0.8789,
      "step": 2978
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011325696902749,
      "loss": 0.8314,
      "step": 2979
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011320588682355499,
      "loss": 0.8425,
      "step": 2980
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001131548011122838,
      "loss": 0.8447,
      "step": 2981
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011310371190724431,
      "loss": 0.848,
      "step": 2982
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.8479,
      "step": 2983
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011300152307013604,
      "loss": 0.854,
      "step": 2984
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011295042346520754,
      "loss": 0.8458,
      "step": 2985
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011289932042079113,
      "loss": 0.8671,
      "step": 2986
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00011284821395045917,
      "loss": 0.8425,
      "step": 2987
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011279710406778499,
      "loss": 0.8371,
      "step": 2988
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011274599078634283,
      "loss": 0.8307,
      "step": 2989
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011269487411970776,
      "loss": 0.8459,
      "step": 2990
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011264375408145582,
      "loss": 0.8191,
      "step": 2991
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011259263068516395,
      "loss": 0.853,
      "step": 2992
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011254150394440992,
      "loss": 0.8582,
      "step": 2993
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001124903738727724,
      "loss": 0.8525,
      "step": 2994
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011243924048383104,
      "loss": 0.8712,
      "step": 2995
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011238810379116622,
      "loss": 0.8538,
      "step": 2996
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001123369638083593,
      "loss": 0.8348,
      "step": 2997
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011228582054899252,
      "loss": 0.8329,
      "step": 2998
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011223467402664893,
      "loss": 0.8389,
      "step": 2999
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011218352425491248,
      "loss": 0.8495,
      "step": 3000
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011213237124736797,
      "loss": 0.8365,
      "step": 3001
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011208121501760107,
      "loss": 0.863,
      "step": 3002
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011203005557919832,
      "loss": 0.8201,
      "step": 3003
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011197889294574708,
      "loss": 0.8132,
      "step": 3004
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011192772713083556,
      "loss": 0.8208,
      "step": 3005
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011187655814805289,
      "loss": 0.8651,
      "step": 3006
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011182538601098893,
      "loss": 0.8411,
      "step": 3007
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011177421073323444,
      "loss": 0.8547,
      "step": 3008
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.000111723032328381,
      "loss": 0.8558,
      "step": 3009
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011167185081002101,
      "loss": 0.8487,
      "step": 3010
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011162066619174774,
      "loss": 0.8338,
      "step": 3011
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001115694784871552,
      "loss": 0.8303,
      "step": 3012
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011151828770983835,
      "loss": 0.8295,
      "step": 3013
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011146709387339285,
      "loss": 0.853,
      "step": 3014
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011141589699141518,
      "loss": 0.8624,
      "step": 3015
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011136469707750272,
      "loss": 0.8515,
      "step": 3016
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011131349414525356,
      "loss": 0.819,
      "step": 3017
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011126228820826663,
      "loss": 0.8369,
      "step": 3018
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011121107928014165,
      "loss": 0.8218,
      "step": 3019
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011115986737447916,
      "loss": 0.7942,
      "step": 3020
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011110865250488047,
      "loss": 0.8353,
      "step": 3021
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011105743468494764,
      "loss": 0.8511,
      "step": 3022
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001110062139282836,
      "loss": 0.8577,
      "step": 3023
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.000110954990248492,
      "loss": 0.8513,
      "step": 3024
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011090376365917723,
      "loss": 0.8153,
      "step": 3025
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001108525341739446,
      "loss": 0.842,
      "step": 3026
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011080130180639998,
      "loss": 0.8648,
      "step": 3027
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011075006657015014,
      "loss": 0.8435,
      "step": 3028
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011069882847880268,
      "loss": 0.8473,
      "step": 3029
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011064758754596574,
      "loss": 0.8381,
      "step": 3030
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011059634378524841,
      "loss": 0.8461,
      "step": 3031
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011054509721026045,
      "loss": 0.8246,
      "step": 3032
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011049384783461236,
      "loss": 0.8297,
      "step": 3033
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011044259567191542,
      "loss": 0.8222,
      "step": 3034
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011039134073578164,
      "loss": 0.8465,
      "step": 3035
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011034008303982373,
      "loss": 0.8594,
      "step": 3036
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011028882259765518,
      "loss": 0.8389,
      "step": 3037
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00011023755942289022,
      "loss": 0.8707,
      "step": 3038
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00011018629352914373,
      "loss": 0.8488,
      "step": 3039
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00011013502493003136,
      "loss": 0.8359,
      "step": 3040
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001100837536391695,
      "loss": 0.8311,
      "step": 3041
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00011003247967017525,
      "loss": 0.8421,
      "step": 3042
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010998120303666635,
      "loss": 0.8785,
      "step": 3043
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010992992375226134,
      "loss": 0.8265,
      "step": 3044
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010987864183057943,
      "loss": 0.868,
      "step": 3045
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001098273572852405,
      "loss": 0.8508,
      "step": 3046
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001097760701298652,
      "loss": 0.8523,
      "step": 3047
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010972478037807474,
      "loss": 0.8248,
      "step": 3048
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010967348804349118,
      "loss": 0.8529,
      "step": 3049
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00010962219313973718,
      "loss": 0.8471,
      "step": 3050
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010957089568043605,
      "loss": 0.8326,
      "step": 3051
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010951959567921188,
      "loss": 0.806,
      "step": 3052
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010946829314968935,
      "loss": 0.8372,
      "step": 3053
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010941698810549385,
      "loss": 0.8572,
      "step": 3054
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010936568056025143,
      "loss": 0.8473,
      "step": 3055
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010931437052758877,
      "loss": 0.8351,
      "step": 3056
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010926305802113328,
      "loss": 0.8302,
      "step": 3057
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010921174305451296,
      "loss": 0.8228,
      "step": 3058
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010916042564135652,
      "loss": 0.8752,
      "step": 3059
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010910910579529325,
      "loss": 0.8738,
      "step": 3060
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010905778352995317,
      "loss": 0.8418,
      "step": 3061
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00010900645885896687,
      "loss": 0.8286,
      "step": 3062
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010895513179596566,
      "loss": 0.824,
      "step": 3063
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010890380235458137,
      "loss": 0.8315,
      "step": 3064
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010885247054844661,
      "loss": 0.8297,
      "step": 3065
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001088011363911944,
      "loss": 0.8444,
      "step": 3066
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010874979989645864,
      "loss": 0.8566,
      "step": 3067
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010869846107787371,
      "loss": 0.8439,
      "step": 3068
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010864711994907458,
      "loss": 0.8324,
      "step": 3069
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010859577652369692,
      "loss": 0.8513,
      "step": 3070
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010854443081537698,
      "loss": 0.8638,
      "step": 3071
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010849308283775154,
      "loss": 0.8359,
      "step": 3072
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010844173260445814,
      "loss": 0.8342,
      "step": 3073
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010839038012913478,
      "loss": 0.8552,
      "step": 3074
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00010833902542542008,
      "loss": 0.8372,
      "step": 3075
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010828766850695333,
      "loss": 0.8469,
      "step": 3076
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010823630938737432,
      "loss": 0.8437,
      "step": 3077
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010818494808032348,
      "loss": 0.8567,
      "step": 3078
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010813358459944179,
      "loss": 0.866,
      "step": 3079
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001080822189583708,
      "loss": 0.8556,
      "step": 3080
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010803085117075269,
      "loss": 0.8375,
      "step": 3081
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010797948125023011,
      "loss": 0.8305,
      "step": 3082
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001079281092104464,
      "loss": 0.8207,
      "step": 3083
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010787673506504538,
      "loss": 0.8621,
      "step": 3084
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010782535882767144,
      "loss": 0.8357,
      "step": 3085
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00010777398051196954,
      "loss": 0.8466,
      "step": 3086
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001077226001315852,
      "loss": 0.8661,
      "step": 3087
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010767121770016446,
      "loss": 0.8451,
      "step": 3088
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001076198332313539,
      "loss": 0.8499,
      "step": 3089
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010756844673880071,
      "loss": 0.84,
      "step": 3090
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010751705823615252,
      "loss": 0.808,
      "step": 3091
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010746566773705757,
      "loss": 0.8397,
      "step": 3092
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010741427525516463,
      "loss": 0.8383,
      "step": 3093
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010736288080412294,
      "loss": 0.8214,
      "step": 3094
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010731148439758223,
      "loss": 0.8254,
      "step": 3095
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010726008604919296,
      "loss": 0.845,
      "step": 3096
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010720868577260581,
      "loss": 0.8572,
      "step": 3097
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010715728358147217,
      "loss": 0.8437,
      "step": 3098
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010710587948944394,
      "loss": 0.8401,
      "step": 3099
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00010705447351017341,
      "loss": 0.8383,
      "step": 3100
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010700306565731348,
      "loss": 0.8536,
      "step": 3101
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010695165594451748,
      "loss": 0.8346,
      "step": 3102
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010690024438543922,
      "loss": 0.8459,
      "step": 3103
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010684883099373309,
      "loss": 0.8439,
      "step": 3104
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010679741578305389,
      "loss": 0.8407,
      "step": 3105
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010674599876705693,
      "loss": 0.8389,
      "step": 3106
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.000106694579959398,
      "loss": 0.8326,
      "step": 3107
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010664315937373334,
      "loss": 0.845,
      "step": 3108
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010659173702371973,
      "loss": 0.8188,
      "step": 3109
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.8168,
      "step": 3110
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001064888870852748,
      "loss": 0.8407,
      "step": 3111
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00010643745952415931,
      "loss": 0.8539,
      "step": 3112
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010638603025332641,
      "loss": 0.8352,
      "step": 3113
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010633459928643516,
      "loss": 0.8398,
      "step": 3114
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010628316663714505,
      "loss": 0.843,
      "step": 3115
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010623173231911599,
      "loss": 0.8287,
      "step": 3116
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010618029634600843,
      "loss": 0.8273,
      "step": 3117
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010612885873148311,
      "loss": 0.8787,
      "step": 3118
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010607741948920133,
      "loss": 0.8481,
      "step": 3119
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010602597863282478,
      "loss": 0.8259,
      "step": 3120
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010597453617601553,
      "loss": 0.8408,
      "step": 3121
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010592309213243618,
      "loss": 0.8755,
      "step": 3122
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010587164651574968,
      "loss": 0.8389,
      "step": 3123
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010582019933961937,
      "loss": 0.8219,
      "step": 3124
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00010576875061770912,
      "loss": 0.8247,
      "step": 3125
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010571730036368308,
      "loss": 0.8536,
      "step": 3126
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001056658485912059,
      "loss": 0.8904,
      "step": 3127
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010561439531394253,
      "loss": 0.833,
      "step": 3128
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010556294054555846,
      "loss": 0.8516,
      "step": 3129
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010551148429971948,
      "loss": 0.8571,
      "step": 3130
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010546002659009178,
      "loss": 0.8381,
      "step": 3131
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010540856743034195,
      "loss": 0.8476,
      "step": 3132
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.000105357106834137,
      "loss": 0.8424,
      "step": 3133
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010530564481514424,
      "loss": 0.8431,
      "step": 3134
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010525418138703149,
      "loss": 0.8349,
      "step": 3135
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010520271656346677,
      "loss": 0.8518,
      "step": 3136
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010515125035811859,
      "loss": 0.8154,
      "step": 3137
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00010509978278465587,
      "loss": 0.838,
      "step": 3138
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001050483138567477,
      "loss": 0.8667,
      "step": 3139
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010499684358806377,
      "loss": 0.8529,
      "step": 3140
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010494537199227392,
      "loss": 0.8397,
      "step": 3141
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010489389908304848,
      "loss": 0.8535,
      "step": 3142
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010484242487405807,
      "loss": 0.8378,
      "step": 3143
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010479094937897365,
      "loss": 0.8185,
      "step": 3144
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010473947261146655,
      "loss": 0.8487,
      "step": 3145
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010468799458520846,
      "loss": 0.8301,
      "step": 3146
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010463651531387129,
      "loss": 0.8289,
      "step": 3147
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010458503481112747,
      "loss": 0.8482,
      "step": 3148
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010453355309064952,
      "loss": 0.8381,
      "step": 3149
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00010448207016611049,
      "loss": 0.8132,
      "step": 3150
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010443058605118366,
      "loss": 0.8247,
      "step": 3151
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010437910075954261,
      "loss": 0.8519,
      "step": 3152
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010432761430486128,
      "loss": 0.8376,
      "step": 3153
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010427612670081392,
      "loss": 0.8544,
      "step": 3154
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.000104224637961075,
      "loss": 0.8352,
      "step": 3155
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010417314809931944,
      "loss": 0.8541,
      "step": 3156
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010412165712922231,
      "loss": 0.8426,
      "step": 3157
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010407016506445903,
      "loss": 0.8334,
      "step": 3158
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010401867191870533,
      "loss": 0.8335,
      "step": 3159
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010396717770563726,
      "loss": 0.8604,
      "step": 3160
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010391568243893106,
      "loss": 0.8557,
      "step": 3161
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001038641861322633,
      "loss": 0.8428,
      "step": 3162
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00010381268879931083,
      "loss": 0.8215,
      "step": 3163
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010376119045375079,
      "loss": 0.8273,
      "step": 3164
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010370969110926052,
      "loss": 0.8687,
      "step": 3165
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010365819077951776,
      "loss": 0.8528,
      "step": 3166
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010360668947820029,
      "loss": 0.8609,
      "step": 3167
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010355518721898639,
      "loss": 0.872,
      "step": 3168
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010350368401555446,
      "loss": 0.8277,
      "step": 3169
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010345217988158311,
      "loss": 0.8354,
      "step": 3170
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010340067483075136,
      "loss": 0.852,
      "step": 3171
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010334916887673833,
      "loss": 0.8552,
      "step": 3172
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010329766203322339,
      "loss": 0.865,
      "step": 3173
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010324615431388626,
      "loss": 0.841,
      "step": 3174
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00010319464573240678,
      "loss": 0.8355,
      "step": 3175
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010314313630246501,
      "loss": 0.8287,
      "step": 3176
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010309162603774136,
      "loss": 0.8551,
      "step": 3177
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010304011495191634,
      "loss": 0.8537,
      "step": 3178
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010298860305867073,
      "loss": 0.8326,
      "step": 3179
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010293709037168548,
      "loss": 0.8473,
      "step": 3180
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010288557690464182,
      "loss": 0.853,
      "step": 3181
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010283406267122116,
      "loss": 0.8595,
      "step": 3182
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010278254768510505,
      "loss": 0.8332,
      "step": 3183
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010273103195997536,
      "loss": 0.8298,
      "step": 3184
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010267951550951407,
      "loss": 0.8658,
      "step": 3185
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010262799834740333,
      "loss": 0.8513,
      "step": 3186
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010257648048732562,
      "loss": 0.8609,
      "step": 3187
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00010252496194296342,
      "loss": 0.8592,
      "step": 3188
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001024734427279995,
      "loss": 0.8582,
      "step": 3189
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010242192285611683,
      "loss": 0.8572,
      "step": 3190
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010237040234099846,
      "loss": 0.8457,
      "step": 3191
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010231888119632769,
      "loss": 0.8358,
      "step": 3192
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010226735943578795,
      "loss": 0.818,
      "step": 3193
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010221583707306285,
      "loss": 0.819,
      "step": 3194
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010216431412183617,
      "loss": 0.8453,
      "step": 3195
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010211279059579182,
      "loss": 0.8503,
      "step": 3196
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010206126650861387,
      "loss": 0.8419,
      "step": 3197
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010200974187398654,
      "loss": 0.8641,
      "step": 3198
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001019582167055942,
      "loss": 0.8367,
      "step": 3199
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00010190669101712135,
      "loss": 0.8532,
      "step": 3200
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 6285,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "total_flos": 8.250905836973457e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}